kernel.git/arch/arm64/kernel/perf_event.c, branch linux-6.0.y

arm64: perf: Expose some Armv9 common events under sysfs

2022-03-08T11:40:44Z

Armv9[1] has introduced some common architectural events (0x400C-0x400F) and common microarchitectural events (0x4010-0x401B), which can be detected by PMCEID0_EL0 from bit44 to bit59, so expose these common events under sysfs. [1] https://developer.arm.com/documentation/ddi0608/ba Cc: Mark Rutland Cc: Will Deacon Signed-off-by: Shaokun Zhang Link: https://lore.kernel.org/r/20220303085419.64085-1-zhangshaokun@hisilicon.com Signed-off-by: Will Deacon

arm64: perf: Don't register user access sysctl handler multiple times

2022-01-04T14:57:14Z

Commit e2012600810c ("arm64: perf: Add userspace counter access disable switch") introduced a new 'perf_user_access' sysctl file to enable and disable direct userspace access to the PMU counters. Sadly, Geert reports that on his big.LITTLE SoC ('Renesas Salvator-XS w/ R-Car H3'), the file is created for each PMU type probed, resulting in a splat during boot: | hw perfevents: enabled with armv8_cortex_a53 PMU driver, 7 counters available | sysctl duplicate entry: /kernel//perf_user_access | CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.16.0-rc3-arm64-renesas-00003-ge2012600810c #1420 | Hardware name: Renesas Salvator-X 2nd version board based on r8a77951 (DT) | Call trace: | dump_backtrace+0x0/0x190 | show_stack+0x14/0x20 | dump_stack_lvl+0x88/0xb0 | dump_stack+0x14/0x2c | __register_sysctl_table+0x384/0x818 | register_sysctl+0x20/0x28 | armv8_pmu_init.constprop.0+0x118/0x150 | armv8_a57_pmu_init+0x1c/0x28 | arm_pmu_device_probe+0x1b4/0x558 | armv8_pmu_device_probe+0x18/0x20 | platform_probe+0x64/0xd0 | hw perfevents: enabled with armv8_cortex_a57 PMU driver, 7 counters available Introduce a state variable to track creation of the sysctl file and ensure that it is only created once. Reported-by: Geert Uytterhoeven Fixes: e2012600810c ("arm64: perf: Add userspace counter access disable switch") Link: https://lore.kernel.org/r/CAMuHMdVcDxR9sGzc5pcnORiotonERBgc6dsXZXMd6wTvLGA9iw@mail.gmail.com Signed-off-by: Will Deacon

Merge branch 'for-next/perf-cpu' into for-next/perf

2021-12-14T18:13:25Z

* for-next/perf-cpu: arm64: perf: Support new DT compatibles arm64: perf: Simplify registration boilerplate arm64: perf: Support Denver and Carmel PMUs

arm64: perf: Support new DT compatibles

2021-12-14T18:05:11Z

Wire up the new DT compatibles so we can present appropriate PMU names to userspace for the latest and greatest CPUs. Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/62d14ba12d847ec7f1fba7cb0b3b881b437e1cc5.1639490264.git.robin.murphy@arm.com Signed-off-by: Will Deacon

arm64: perf: Simplify registration boilerplate

2021-12-14T18:05:11Z

With the trend for per-core events moving to userspace JSON, registering names for PMUv3 implementations is increasingly a pure boilerplate exercise. Let's wrap things a step further so we can generate the basic PMUv3 init function with a macro invocation, and reduce further new addition to just 2 lines each. Suggested-by: Mark Rutland Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/b79477ea3b97f685d00511d4ecd2f686184dca34.1639490264.git.robin.murphy@arm.com Signed-off-by: Will Deacon

arm64: perf: Support Denver and Carmel PMUs

2021-12-14T18:05:11Z

Add support for the NVIDIA Denver and Carmel PMUs using the generic PMUv3 event map for now. Acked-by: Mark Rutland Signed-off-by: Thierry Reding [ rm: reorder entries alphabetically ] Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/5f0f69d47acca78a9e479501aa4d8b429e23cf11.1639490264.git.robin.murphy@arm.com Signed-off-by: Will Deacon

arm64: perf: Enable PMU counter userspace access for perf event

2021-12-14T11:40:59Z

Arm PMUs can support direct userspace access of counters which allows for low overhead (i.e. no syscall) self-monitoring of tasks. The same feature exists on x86 called 'rdpmc'. Unlike x86, userspace access will only be enabled for thread bound events. This could be extended if needed, but simplifies the implementation and reduces the chances for any information leaks (which the x86 implementation suffers from). PMU EL0 access will be enabled when an event with userspace access is part of the thread's context. This includes when the event is not scheduled on the PMU. There's some additional overhead clearing dirty counters when access is enabled in order to prevent leaking disabled counter data from other tasks. Unlike x86, enabling of userspace access must be requested with a new attr bit: config1:1. If the user requests userspace access with 64-bit counters, then the event open will fail if the h/w doesn't support 64-bit counters. Chaining is not supported with userspace access. The modes for config1 are as follows: config1 = 0 : user access disabled and always 32-bit config1 = 1 : user access disabled and always 64-bit (using chaining if needed) config1 = 2 : user access enabled and always 32-bit config1 = 3 : user access enabled and always 64-bit Based on work by Raphael Gault , but has been completely re-written. Cc: Will Deacon Cc: Mark Rutland Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Catalin Marinas Cc: linux-arm-kernel@lists.infradead.org Cc: linux-perf-users@vger.kernel.org Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20211208201124.310740-5-robh@kernel.org [will: Made armv8pmu_proc_user_access_handler() static] Signed-off-by: Will Deacon

arm64: perf: Add userspace counter access disable switch

2021-12-14T11:30:54Z

Like x86, some users may want to disable userspace PMU counter altogether. Add a sysctl 'perf_user_access' file to control userspace counter access. The default is '0' which is disabled. Writing '1' enables access. Note that x86 supports globally enabling user access by writing '2' to /sys/bus/event_source/devices/cpu/rdpmc. As there's not existing userspace support to worry about, this shouldn't be necessary for Arm. It could be added later if the need arises. Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Catalin Marinas Cc: linux-perf-users@vger.kernel.org Acked-by: Will Deacon Reviewed-by: Mark Rutland Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20211208201124.310740-4-robh@kernel.org Signed-off-by: Will Deacon

arm64/perf: Replace '0xf' instances with ID_AA64DFR0_PMUVER_IMP_DEF

2021-08-11T10:02:12Z

ID_AA64DFR0_PMUVER_IMP_DEF, indicating an "implementation defined" PMU, never actually gets used although there are '0xf' instances scattered all around. Use the symbolic name instead of the raw hex constant. Cc: Catalin Marinas Cc: Will Deacon Cc: Mark Rutland Cc: Peter Zijlstra Signed-off-by: Anshuman Khandual Link: https://lore.kernel.org/r/1628652427-24695-2-git-send-email-anshuman.khandual@arm.com Signed-off-by: Will Deacon

arm64: perf: Simplify EVENT ATTR macro in perf_event.c

2021-06-11T10:18:41Z

Use common macro PMU_EVENT_ATTR_ID to simplify ARMV8_EVENT_ATTR Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Cc: Will Deacon Signed-off-by: Qi Liu Link: https://lore.kernel.org/r/1623220863-58233-8-git-send-email-liuqi115@huawei.com Signed-off-by: Will Deacon