kernel/linux.git/drivers/perf/arm_pmu.c, branch linux-7.1.y

Convert 'alloc_obj' family to use the new default GFP_KERNEL argument

2026-02-22T01:09:51+00:00

This was done entirely with mindless brute force, using git grep -l '\

treewide: Replace kmalloc with kmalloc_obj for non-scalar types

2026-02-21T09:02:28+00:00

This is the result of running the Coccinelle script from scripts/coccinelle/api/kmalloc_objs.cocci. The script is designed to avoid scalar types (which need careful case-by-case checking), and instead replace kmalloc-family calls that allocate struct or union object instances: Single allocations: kmalloc(sizeof(TYPE), ...) are replaced with: kmalloc_obj(TYPE, ...) Array allocations: kmalloc_array(COUNT, sizeof(TYPE), ...) are replaced with: kmalloc_objs(TYPE, COUNT, ...) Flex array allocations: kmalloc(struct_size(PTR, FAM, COUNT), ...) are replaced with: kmalloc_flex(*PTR, FAM, COUNT, ...) (where TYPE may also be *VAR) The resulting allocations no longer return "void *", instead returning "TYPE *". Signed-off-by: Kees Cook

Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

2025-12-03T01:03:55+00:00

Pull arm64 updates from Catalin Marinas: "These are the arm64 updates for 6.19. The biggest part is the Arm MPAM driver under drivers/resctrl/. There's a patch touching mm/ to handle spurious faults for huge pmd (similar to the pte version). The corresponding arm64 part allows us to avoid the TLB maintenance if a (huge) page is reused after a write fault. There's EFI refactoring to allow runtime services with preemption enabled and the rest is the usual perf/PMU updates and several cleanups/typos. Summary: Core features: - Basic Arm MPAM (Memory system resource Partitioning And Monitoring) driver under drivers/resctrl/ which makes use of the fs/rectrl/ API Perf and PMU: - Avoid cycle counter on multi-threaded CPUs - Extend CSPMU device probing and add additional filtering support for NVIDIA implementations - Add support for the PMUs on the NoC S3 interconnect - Add additional compatible strings for new Cortex and C1 CPUs - Add support for data source filtering to the SPE driver - Add support for i.MX8QM and "DB" PMU in the imx PMU driver Memory managemennt: - Avoid broadcast TLBI if page reused in write fault - Elide TLB invalidation if the old PTE was not valid - Drop redundant cpu_set_*_tcr_t0sz() macros - Propagate pgtable_alloc() errors outside of __create_pgd_mapping() - Propagate return value from __change_memory_common() ACPI and EFI: - Call EFI runtime services without disabling preemption - Remove unused ACPI function Miscellaneous: - ptrace support to disable streaming on SME-only systems - Improve sysreg generation to include a 'Prefix' descriptor - Replace __ASSEMBLY__ with __ASSEMBLER__ - Align register dumps in the kselftest zt-test - Remove some no longer used macros/functions - Various spelling corrections" * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (94 commits) arm64/mm: Document why linear map split failure upon vm_reset_perms is not problematic arm64/pageattr: Propagate return value from __change_memory_common arm64/sysreg: Remove unused define ARM64_FEATURE_FIELD_BITS KVM: arm64: selftests: Consider all 7 possible levels of cache KVM: arm64: selftests: Remove ARM64_FEATURE_FIELD_BITS and its last user arm64: atomics: lse: Remove unused parameters from ATOMIC_FETCH_OP_AND macros Documentation/arm64: Fix the typo of register names ACPI: GTDT: Get rid of acpi_arch_timer_mem_init() perf: arm_spe: Add support for filtering on data source perf: Add perf_event_attr::config4 perf/imx_ddr: Add support for PMU in DB (system interconnects) perf/imx_ddr: Get and enable optional clks perf/imx_ddr: Move ida_alloc() from ddr_perf_init() to ddr_perf_probe() dt-bindings: perf: fsl-imx-ddr: Add compatible string for i.MX8QM, i.MX8QXP and i.MX8DXL arm64: remove duplicate ARCH_HAS_MEM_ENCRYPT arm64: mm: use untagged address to calculate page index MAINTAINERS: new entry for MPAM Driver arm_mpam: Add kunit tests for props_mismatch() arm_mpam: Add kunit test for bitmap reset arm_mpam: Add helper to reset saved mbwu state ...

perf: arm_pmuv3: Don't use PMCCNTR_EL0 on SMT cores

2025-11-03T13:28:48+00:00

CPU_CYCLES is expected to count the logical CPU (PE) clock. Currently it's preferred to use PMCCNTR_EL0 for counting CPU_CYCLES, but it'll count processor clock rather than the PE clock (ARM DDI0487 L.b D13.1.3) if one of the SMT siblings is not idle on a multi-threaded implementation. So don't use it on SMT cores. Introduce topology_core_has_smt() for knowing the SMT implementation and cached it in arm_pmu::has_smt during allocation. When counting cycles on SMT CPU 2-3 and CPU 3 is idle, without this patch we'll get: [root@client1 tmp]# perf stat -e cycles -A -C 2-3 -- stress-ng -c 1 --taskset 2 --timeout 1 [...] Performance counter stats for 'CPU(s) 2-3': CPU2 2880457316 cycles CPU3 2880459810 cycles 1.254688470 seconds time elapsed With this patch the idle state of CPU3 is observed as expected: [root@client1 ~]# perf stat -e cycles -A -C 2-3 -- stress-ng -c 1 --taskset 2 --timeout 1 [...] Performance counter stats for 'CPU(s) 2-3': CPU2 2558580492 cycles CPU3 305749 cycles 1.113626410 seconds time elapsed Signed-off-by: Yicong Yang Signed-off-by: Will Deacon

perf: arm_pmu: Kill last use of per-CPU cpu_armpmu pointer

2025-10-27T16:16:37+00:00

Having removed the use of the cpu_armpmu per-CPU variable from the interrupt handling, the only user left is the BRBE scheduler hook. It is easy to drop the use of this variable by following the pointer to the generic PMU structure, and get the arm_pmu structure from there. Perform the conversion and kill cpu_armpmu altogether. Suggested-by: Will Deacon Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Tested-by: Will Deacon Link: https://patch.msgid.link/20251020122944.3074811-27-maz@kernel.org

perf: arm_pmu: Request specific affinities for per CPU NMIs/interrupts

2025-10-27T16:16:35+00:00

Let the PMU driver request both NMIs and normal interrupts with an affinity mask matching the PMU affinity. Signed-off-by: Will Deacon Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Tested-by: Will Deacon Link: https://patch.msgid.link/20251020122944.3074811-19-maz@kernel.org

genirq: Update request_percpu_nmi() to take an affinity

2025-10-27T16:16:35+00:00

Continue spreading the notion of affinity to the per CPU interrupt request code by updating the call sites that use request_percpu_nmi() (all two of them) to take an affinity pointer. This pointer is firmly NULL for now. Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Tested-by: Will Deacon Link: https://patch.msgid.link/20251020122944.3074811-16-maz@kernel.org

perf: arm_pmuv3: Add support for the Branch Record Buffer Extension (BRBE)

2025-07-08T16:58:49+00:00

The ARMv9.2 architecture introduces the optional Branch Record Buffer Extension (BRBE), which records information about branches as they are executed into set of branch record registers. BRBE is similar to x86's Last Branch Record (LBR) and PowerPC's Branch History Rolling Buffer (BHRB). BRBE supports filtering by exception level and can filter just the source or target address if excluded to avoid leaking privileged addresses. The h/w filter would be sufficient except when there are multiple events with disjoint filtering requirements. In this case, BRBE is configured with a union of all the events' desired branches, and then the recorded branches are filtered based on each event's filter. For example, with one event capturing kernel events and another event capturing user events, BRBE will be configured to capture both kernel and user branches. When handling event overflow, the branch records have to be filtered by software to only include kernel or user branch addresses for that event. In contrast, x86 simply configures LBR using the last installed event which seems broken. It is possible on x86 to configure branch filter such that no branches are ever recorded (e.g. -j save_type). For BRBE, events with a configuration that will result in no samples are rejected. Recording branches in KVM guests is not supported like x86. However, perf on x86 allows requesting branch recording in guests. The guest events are recorded, but the resulting branches are all from the host. For BRBE, events with branch recording and "exclude_host" set are rejected. Requiring "exclude_guest" to be set did not work. The default for the perf tool does set "exclude_guest" if no exception level options are specified. However, specifying kernel or user events defaults to including both host and guest. In this case, only host branches are recorded. BRBE can support some additional exception branch types compared to x86. On x86, all exceptions other than syscalls are recorded as IRQ. With BRBE, it is possible to better categorize these exceptions. One limitation relative to x86 is we cannot distinguish a syscall return from other exception returns. So all exception returns are recorded as ERET type. The FIQ branch type is omitted as the only FIQ user is Apple platforms which don't support BRBE. The debug branch types are omitted as there is no clear need for them. BRBE records are invalidated whenever events are reconfigured, a new task is scheduled in, or after recording is paused (and the records have been recorded for the event). The architecture allows branch records to be invalidated by the PE under implementation defined conditions. It is expected that these conditions are rare. Cc: Catalin Marinas Co-developed-by: Anshuman Khandual Signed-off-by: Anshuman Khandual Co-developed-by: Mark Rutland Signed-off-by: Mark Rutland Tested-by: James Clark Signed-off-by: Rob Herring (Arm) tested-by: Adam Young Acked-by: Mark Rutland Link: https://lore.kernel.org/r/20250611-arm-brbe-v19-v23-4-e7775563036e@kernel.org [will: Fix sparse warnings about mixed declarations and code. Fix C99 comment syntax.] Signed-off-by: Will Deacon

perf: arm_pmu: Don't disable counter in armpmu_add()

2025-03-01T05:08:10+00:00

Currently armpmu_add() tries to handle a newly-allocated counter having a stale associated event, but this should not be possible, and if this were to happen the current mitigation is insufficient and potentially expensive. It would be better to warn if we encounter the impossible case. Calls to pmu::add() and pmu::del() are serialized by the core perf code, and armpmu_del() clears the relevant slot in pmu_hw_events::events[] before clearing the bit in pmu_hw_events::used_mask such that the counter can be reallocated. Thus when armpmu_add() allocates a counter index from pmu_hw_events::used_mask, it should not be possible to observe a stale even in pmu_hw_events::events[] unless either pmu_hw_events::used_mask or pmu_hw_events::events[] have been corrupted. If this were to happen, we'd end up with two events with the same event->hw.idx, which would clash with each other during reprogramming, deletion, etc, and produce bogus results. Add a WARN_ON_ONCE() for this case so that we can detect if this ever occurs in practice. That possiblity aside, there's no need to call arm_pmu::disable(event) for the new event. The PMU reset code initialises the counter in a disabled state, and armpmu_del() will disable the counter before it can be reused. Remove the redundant disable. Signed-off-by: Mark Rutland Signed-off-by: Rob Herring (Arm) Reviewed-by: Anshuman Khandual Tested-by: James Clark Link: https://lore.kernel.org/r/20250218-arm-brbe-v19-v20-2-4e9922fc2e8e@kernel.org Signed-off-by: Will Deacon

perf: arm_pmu: Remove event index to counter remapping

2024-08-16T12:09:11+00:00

Xscale and Armv6 PMUs defined the cycle counter at 0 and event counters starting at 1 and had 1:1 event index to counter numbering. On Armv7 and later, this changed the cycle counter to 31 and event counters start at 0. The drivers for Armv7 and PMUv3 kept the old event index numbering and introduced an event index to counter conversion. The conversion uses masking to convert from event index to a counter number. This operation relies on having at most 32 counters so that the cycle counter index 0 can be transformed to counter number 31. Armv9.4 adds support for an additional fixed function counter (instructions) which increases possible counters to more than 32, and the conversion won't work anymore as a simple subtract and mask. The primary reason for the translation (other than history) seems to be to have a contiguous mask of counters 0-N. Keeping that would result in more complicated index to counter conversions. Instead, store a mask of available counters rather than just number of events. That provides more information in addition to the number of events. No (intended) functional changes. Acked-by: Mark Rutland Signed-off-by: Rob Herring (Arm) Tested-by: James Clark Link: https://lore.kernel.org/r/20240731-arm-pmu-3-9-icntr-v3-1-280a8d7ff465@kernel.org Signed-off-by: Will Deacon