All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ian Rogers <irogers@google.com>
To: Rob Herring <robh@kernel.org>
Cc: Will Deacon <will@kernel.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Jiri Olsa <jolsa@redhat.com>, Mark Rutland <mark.rutland@arm.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>,
	Zachary.Leaf@arm.com, Raphael Gault <raphael.gault@arm.com>,
	Jonathan Cameron <Jonathan.Cameron@huawei.com>,
	Namhyung Kim <namhyung@kernel.org>,
	Itaru Kitayama <itaru.kitayama@gmail.com>,
	Linux ARM <linux-arm-kernel@lists.infradead.org>,
	LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v6 06/10] libperf: Add support for user space counter access
Date: Tue, 4 May 2021 14:40:52 -0700	[thread overview]
Message-ID: <CAP-5=fUEu1EO7GreYYjZ178BH_riYYa0HdY4GZhi=0DdjkCMJg@mail.gmail.com> (raw)
In-Reply-To: <20210311000837.3630499-7-robh@kernel.org>

On Wed, Mar 10, 2021 at 4:08 PM Rob Herring <robh@kernel.org> wrote:
>
> x86 and arm64 can both support direct access of event counters in
> userspace. The access sequence is less than trivial and currently exists
> in perf test code (tools/perf/arch/x86/tests/rdpmc.c) with copies in
> projects such as PAPI and libpfm4.
>
> In order to support usersapce access, an event must be mmapped first
> with perf_evsel__mmap(). Then subsequent calls to perf_evsel__read()
> will use the fast path (assuming the arch supports it).
>
> Signed-off-by: Rob Herring <robh@kernel.org>
> ---
> v6:
>  - Adapt to mmap changes adding MMAP NULL check
> v5:
>  - Make raw count s64 instead of u64 so that counter width shifting
>    works
>  - Adapt to mmap changes
> v4:
>  - Update perf_evsel__mmap size to pages
> v3:
>  - Split out perf_evsel__mmap() to separate patch
> ---
>  tools/lib/perf/evsel.c                 |  4 ++
>  tools/lib/perf/include/internal/mmap.h |  3 +
>  tools/lib/perf/mmap.c                  | 88 ++++++++++++++++++++++++++
>  tools/lib/perf/tests/test-evsel.c      | 65 +++++++++++++++++++
>  4 files changed, 160 insertions(+)
>
> diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
> index 1057e9b15528..4d67343d36c9 100644
> --- a/tools/lib/perf/evsel.c
> +++ b/tools/lib/perf/evsel.c
> @@ -242,6 +242,10 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
>         if (FD(evsel, cpu, thread) < 0)
>                 return -EINVAL;
>
> +       if (MMAP(evsel, cpu, thread) &&
> +           !perf_mmap__read_self(MMAP(evsel, cpu, thread), count))
> +               return 0;
> +
>         if (readn(FD(evsel, cpu, thread), count->values, size) <= 0)
>                 return -errno;
>
> diff --git a/tools/lib/perf/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h
> index be7556e0a2b2..5e3422f40ed5 100644
> --- a/tools/lib/perf/include/internal/mmap.h
> +++ b/tools/lib/perf/include/internal/mmap.h
> @@ -11,6 +11,7 @@
>  #define PERF_SAMPLE_MAX_SIZE (1 << 16)
>
>  struct perf_mmap;
> +struct perf_counts_values;
>
>  typedef void (*libperf_unmap_cb_t)(struct perf_mmap *map);
>
> @@ -52,4 +53,6 @@ void perf_mmap__put(struct perf_mmap *map);
>
>  u64 perf_mmap__read_head(struct perf_mmap *map);
>
> +int perf_mmap__read_self(struct perf_mmap *map, struct perf_counts_values *count);
> +
>  #endif /* __LIBPERF_INTERNAL_MMAP_H */
> diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
> index 79d5ed6c38cc..915469f00cf4 100644
> --- a/tools/lib/perf/mmap.c
> +++ b/tools/lib/perf/mmap.c
> @@ -8,9 +8,11 @@
>  #include <linux/perf_event.h>
>  #include <perf/mmap.h>
>  #include <perf/event.h>
> +#include <perf/evsel.h>
>  #include <internal/mmap.h>
>  #include <internal/lib.h>
>  #include <linux/kernel.h>
> +#include <linux/math64.h>
>  #include "internal.h"
>
>  void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
> @@ -273,3 +275,89 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map)
>
>         return event;
>  }
> +
> +#if defined(__i386__) || defined(__x86_64__)
> +static u64 read_perf_counter(unsigned int counter)
> +{
> +       unsigned int low, high;
> +
> +       asm volatile("rdpmc" : "=a" (low), "=d" (high) : "c" (counter));
> +
> +       return low | ((u64)high) << 32;
> +}
> +
> +static u64 read_timestamp(void)
> +{
> +       unsigned int low, high;
> +
> +       asm volatile("rdtsc" : "=a" (low), "=d" (high));
> +
> +       return low | ((u64)high) << 32;
> +}
> +#else
> +static u64 read_perf_counter(unsigned int counter) { return 0; }
> +static u64 read_timestamp(void) { return 0; }
> +#endif
> +
> +int perf_mmap__read_self(struct perf_mmap *map, struct perf_counts_values *count)
> +{
> +       struct perf_event_mmap_page *pc = map->base;
> +       u32 seq, idx, time_mult = 0, time_shift = 0;
> +       u64 cnt, cyc = 0, time_offset = 0, time_cycles = 0, time_mask = ~0ULL;
> +
> +       if (!pc || !pc->cap_user_rdpmc)
> +               return -1;
> +
> +       do {
> +               seq = READ_ONCE(pc->lock);
> +               barrier();
> +
> +               count->ena = READ_ONCE(pc->time_enabled);
> +               count->run = READ_ONCE(pc->time_running);
> +
> +               if (pc->cap_user_time && count->ena != count->run) {
> +                       cyc = read_timestamp();
> +                       time_mult = READ_ONCE(pc->time_mult);
> +                       time_shift = READ_ONCE(pc->time_shift);
> +                       time_offset = READ_ONCE(pc->time_offset);
> +
> +                       if (pc->cap_user_time_short) {
> +                               time_cycles = READ_ONCE(pc->time_cycles);
> +                               time_mask = READ_ONCE(pc->time_mask);
> +                       }

Nit, this is now out of sync with the comment code in perf_event.h.

> +               }
> +
> +               idx = READ_ONCE(pc->index);
> +               cnt = READ_ONCE(pc->offset);
> +               if (pc->cap_user_rdpmc && idx) {
> +                       s64 evcnt = read_perf_counter(idx - 1);
> +                       u16 width = READ_ONCE(pc->pmc_width);
> +
> +                       evcnt <<= 64 - width;
> +                       evcnt >>= 64 - width;
> +                       cnt += evcnt;
> +               } else
> +                       return -1;
> +
> +               barrier();
> +       } while (READ_ONCE(pc->lock) != seq);
> +
> +       if (count->ena != count->run) {
> +               u64 delta;
> +
> +               /* Adjust for cap_usr_time_short, a nop if not */
> +               cyc = time_cycles + ((cyc - time_cycles) & time_mask);
> +
> +               delta = time_offset + mul_u64_u32_shr(cyc, time_mult, time_shift);
> +
> +               count->ena += delta;
> +               if (idx)
> +                       count->run += delta;
> +
> +               cnt = mul_u64_u64_div64(cnt, count->ena, count->run);

Does this still suffer the divide by zero if multiplexing hasn't run
the counter? If so, we still need to add something like:
https://lore.kernel.org/lkml/CAP-5=fVRdqvswtyQMg5cB+ntTGda+SAYskjTQednEH-AeZo13g@mail.gmail.com/

> +       }
> +
> +       count->val = cnt;
> +
> +       return 0;
> +}
> diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c
> index 0ad82d7a2a51..54fb4809b9ee 100644
> --- a/tools/lib/perf/tests/test-evsel.c
> +++ b/tools/lib/perf/tests/test-evsel.c
> @@ -120,6 +120,69 @@ static int test_stat_thread_enable(void)
>         return 0;
>  }
>
> +static int test_stat_user_read(int event)
> +{
> +       struct perf_counts_values counts = { .val = 0 };
> +       struct perf_thread_map *threads;
> +       struct perf_evsel *evsel;
> +       struct perf_event_mmap_page *pc;
> +       struct perf_event_attr attr = {
> +               .type   = PERF_TYPE_HARDWARE,
> +               .config = event,
> +       };

A nit, previously test-evsel was able to run and pass on a hypervisor.
As now there is a reliance on hardware events the evsel open fails on
a hypervisor. It'd be nice if we could detect running on a hypervisor
and test software events in that case.

Thanks,
Ian

> +       int err, i;
> +
> +       threads = perf_thread_map__new_dummy();
> +       __T("failed to create threads", threads);
> +
> +       perf_thread_map__set_pid(threads, 0, 0);
> +
> +       evsel = perf_evsel__new(&attr);
> +       __T("failed to create evsel", evsel);
> +
> +       err = perf_evsel__open(evsel, NULL, threads);
> +       __T("failed to open evsel", err == 0);
> +
> +       err = perf_evsel__mmap(evsel, 0);
> +       __T("failed to mmap evsel", err == 0);
> +
> +       pc = perf_evsel__mmap_base(evsel, 0, 0);
> +
> +#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
> +       __T("userspace counter access not supported", pc->cap_user_rdpmc);
> +       __T("userspace counter access not enabled", pc->index);
> +       __T("userspace counter width not set", pc->pmc_width >= 32);
> +#endif
> +
> +       perf_evsel__read(evsel, 0, 0, &counts);
> +       __T("failed to read value for evsel", counts.val != 0);
> +
> +       for (i = 0; i < 5; i++) {
> +               volatile int count = 0x10000 << i;
> +               __u64 start, end, last = 0;
> +
> +               __T_VERBOSE("\tloop = %u, ", count);
> +
> +               perf_evsel__read(evsel, 0, 0, &counts);
> +               start = counts.val;
> +
> +               while (count--) ;
> +
> +               perf_evsel__read(evsel, 0, 0, &counts);
> +               end = counts.val;
> +
> +               __T("invalid counter data", (end - start) > last);
> +               last = end - start;
> +               __T_VERBOSE("count = %llu\n", end - start);
> +       }
> +
> +       perf_evsel__close(evsel);
> +       perf_evsel__delete(evsel);
> +
> +       perf_thread_map__put(threads);
> +       return 0;
> +}
> +
>  int main(int argc, char **argv)
>  {
>         __T_START;
> @@ -129,6 +192,8 @@ int main(int argc, char **argv)
>         test_stat_cpu();
>         test_stat_thread();
>         test_stat_thread_enable();
> +       test_stat_user_read(PERF_COUNT_HW_INSTRUCTIONS);
> +       test_stat_user_read(PERF_COUNT_HW_CPU_CYCLES);
>
>         __T_END;
>         return tests_failed == 0 ? 0 : -1;
> --
> 2.27.0
>

WARNING: multiple messages have this Message-ID
From: Ian Rogers <irogers@google.com>
To: Rob Herring <robh@kernel.org>
Cc: Will Deacon <will@kernel.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	 Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	 Arnaldo Carvalho de Melo <acme@kernel.org>,
	Jiri Olsa <jolsa@redhat.com>, Mark Rutland <mark.rutland@arm.com>,
	 Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	 Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>,
	Zachary.Leaf@arm.com,  Raphael Gault <raphael.gault@arm.com>,
	Jonathan Cameron <Jonathan.Cameron@huawei.com>,
	 Namhyung Kim <namhyung@kernel.org>,
	Itaru Kitayama <itaru.kitayama@gmail.com>,
	 Linux ARM <linux-arm-kernel@lists.infradead.org>,
	LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v6 06/10] libperf: Add support for user space counter access
Date: Tue, 4 May 2021 14:40:52 -0700	[thread overview]
Message-ID: <CAP-5=fUEu1EO7GreYYjZ178BH_riYYa0HdY4GZhi=0DdjkCMJg@mail.gmail.com> (raw)
In-Reply-To: <20210311000837.3630499-7-robh@kernel.org>

On Wed, Mar 10, 2021 at 4:08 PM Rob Herring <robh@kernel.org> wrote:
>
> x86 and arm64 can both support direct access of event counters in
> userspace. The access sequence is less than trivial and currently exists
> in perf test code (tools/perf/arch/x86/tests/rdpmc.c) with copies in
> projects such as PAPI and libpfm4.
>
> In order to support usersapce access, an event must be mmapped first
> with perf_evsel__mmap(). Then subsequent calls to perf_evsel__read()
> will use the fast path (assuming the arch supports it).
>
> Signed-off-by: Rob Herring <robh@kernel.org>
> ---
> v6:
>  - Adapt to mmap changes adding MMAP NULL check
> v5:
>  - Make raw count s64 instead of u64 so that counter width shifting
>    works
>  - Adapt to mmap changes
> v4:
>  - Update perf_evsel__mmap size to pages
> v3:
>  - Split out perf_evsel__mmap() to separate patch
> ---
>  tools/lib/perf/evsel.c                 |  4 ++
>  tools/lib/perf/include/internal/mmap.h |  3 +
>  tools/lib/perf/mmap.c                  | 88 ++++++++++++++++++++++++++
>  tools/lib/perf/tests/test-evsel.c      | 65 +++++++++++++++++++
>  4 files changed, 160 insertions(+)
>
> diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
> index 1057e9b15528..4d67343d36c9 100644
> --- a/tools/lib/perf/evsel.c
> +++ b/tools/lib/perf/evsel.c
> @@ -242,6 +242,10 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
>         if (FD(evsel, cpu, thread) < 0)
>                 return -EINVAL;
>
> +       if (MMAP(evsel, cpu, thread) &&
> +           !perf_mmap__read_self(MMAP(evsel, cpu, thread), count))
> +               return 0;
> +
>         if (readn(FD(evsel, cpu, thread), count->values, size) <= 0)
>                 return -errno;
>
> diff --git a/tools/lib/perf/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h
> index be7556e0a2b2..5e3422f40ed5 100644
> --- a/tools/lib/perf/include/internal/mmap.h
> +++ b/tools/lib/perf/include/internal/mmap.h
> @@ -11,6 +11,7 @@
>  #define PERF_SAMPLE_MAX_SIZE (1 << 16)
>
>  struct perf_mmap;
> +struct perf_counts_values;
>
>  typedef void (*libperf_unmap_cb_t)(struct perf_mmap *map);
>
> @@ -52,4 +53,6 @@ void perf_mmap__put(struct perf_mmap *map);
>
>  u64 perf_mmap__read_head(struct perf_mmap *map);
>
> +int perf_mmap__read_self(struct perf_mmap *map, struct perf_counts_values *count);
> +
>  #endif /* __LIBPERF_INTERNAL_MMAP_H */
> diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
> index 79d5ed6c38cc..915469f00cf4 100644
> --- a/tools/lib/perf/mmap.c
> +++ b/tools/lib/perf/mmap.c
> @@ -8,9 +8,11 @@
>  #include <linux/perf_event.h>
>  #include <perf/mmap.h>
>  #include <perf/event.h>
> +#include <perf/evsel.h>
>  #include <internal/mmap.h>
>  #include <internal/lib.h>
>  #include <linux/kernel.h>
> +#include <linux/math64.h>
>  #include "internal.h"
>
>  void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
> @@ -273,3 +275,89 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map)
>
>         return event;
>  }
> +
> +#if defined(__i386__) || defined(__x86_64__)
> +static u64 read_perf_counter(unsigned int counter)
> +{
> +       unsigned int low, high;
> +
> +       asm volatile("rdpmc" : "=a" (low), "=d" (high) : "c" (counter));
> +
> +       return low | ((u64)high) << 32;
> +}
> +
> +static u64 read_timestamp(void)
> +{
> +       unsigned int low, high;
> +
> +       asm volatile("rdtsc" : "=a" (low), "=d" (high));
> +
> +       return low | ((u64)high) << 32;
> +}
> +#else
> +static u64 read_perf_counter(unsigned int counter) { return 0; }
> +static u64 read_timestamp(void) { return 0; }
> +#endif
> +
> +int perf_mmap__read_self(struct perf_mmap *map, struct perf_counts_values *count)
> +{
> +       struct perf_event_mmap_page *pc = map->base;
> +       u32 seq, idx, time_mult = 0, time_shift = 0;
> +       u64 cnt, cyc = 0, time_offset = 0, time_cycles = 0, time_mask = ~0ULL;
> +
> +       if (!pc || !pc->cap_user_rdpmc)
> +               return -1;
> +
> +       do {
> +               seq = READ_ONCE(pc->lock);
> +               barrier();
> +
> +               count->ena = READ_ONCE(pc->time_enabled);
> +               count->run = READ_ONCE(pc->time_running);
> +
> +               if (pc->cap_user_time && count->ena != count->run) {
> +                       cyc = read_timestamp();
> +                       time_mult = READ_ONCE(pc->time_mult);
> +                       time_shift = READ_ONCE(pc->time_shift);
> +                       time_offset = READ_ONCE(pc->time_offset);
> +
> +                       if (pc->cap_user_time_short) {
> +                               time_cycles = READ_ONCE(pc->time_cycles);
> +                               time_mask = READ_ONCE(pc->time_mask);
> +                       }

Nit, this is now out of sync with the comment code in perf_event.h.

> +               }
> +
> +               idx = READ_ONCE(pc->index);
> +               cnt = READ_ONCE(pc->offset);
> +               if (pc->cap_user_rdpmc && idx) {
> +                       s64 evcnt = read_perf_counter(idx - 1);
> +                       u16 width = READ_ONCE(pc->pmc_width);
> +
> +                       evcnt <<= 64 - width;
> +                       evcnt >>= 64 - width;
> +                       cnt += evcnt;
> +               } else
> +                       return -1;
> +
> +               barrier();
> +       } while (READ_ONCE(pc->lock) != seq);
> +
> +       if (count->ena != count->run) {
> +               u64 delta;
> +
> +               /* Adjust for cap_usr_time_short, a nop if not */
> +               cyc = time_cycles + ((cyc - time_cycles) & time_mask);
> +
> +               delta = time_offset + mul_u64_u32_shr(cyc, time_mult, time_shift);
> +
> +               count->ena += delta;
> +               if (idx)
> +                       count->run += delta;
> +
> +               cnt = mul_u64_u64_div64(cnt, count->ena, count->run);

Does this still suffer the divide by zero if multiplexing hasn't run
the counter? If so, we still need to add something like:
https://lore.kernel.org/lkml/CAP-5=fVRdqvswtyQMg5cB+ntTGda+SAYskjTQednEH-AeZo13g@mail.gmail.com/

> +       }
> +
> +       count->val = cnt;
> +
> +       return 0;
> +}
> diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c
> index 0ad82d7a2a51..54fb4809b9ee 100644
> --- a/tools/lib/perf/tests/test-evsel.c
> +++ b/tools/lib/perf/tests/test-evsel.c
> @@ -120,6 +120,69 @@ static int test_stat_thread_enable(void)
>         return 0;
>  }
>
> +static int test_stat_user_read(int event)
> +{
> +       struct perf_counts_values counts = { .val = 0 };
> +       struct perf_thread_map *threads;
> +       struct perf_evsel *evsel;
> +       struct perf_event_mmap_page *pc;
> +       struct perf_event_attr attr = {
> +               .type   = PERF_TYPE_HARDWARE,
> +               .config = event,
> +       };

A nit, previously test-evsel was able to run and pass on a hypervisor.
As now there is a reliance on hardware events the evsel open fails on
a hypervisor. It'd be nice if we could detect running on a hypervisor
and test software events in that case.

Thanks,
Ian

> +       int err, i;
> +
> +       threads = perf_thread_map__new_dummy();
> +       __T("failed to create threads", threads);
> +
> +       perf_thread_map__set_pid(threads, 0, 0);
> +
> +       evsel = perf_evsel__new(&attr);
> +       __T("failed to create evsel", evsel);
> +
> +       err = perf_evsel__open(evsel, NULL, threads);
> +       __T("failed to open evsel", err == 0);
> +
> +       err = perf_evsel__mmap(evsel, 0);
> +       __T("failed to mmap evsel", err == 0);
> +
> +       pc = perf_evsel__mmap_base(evsel, 0, 0);
> +
> +#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
> +       __T("userspace counter access not supported", pc->cap_user_rdpmc);
> +       __T("userspace counter access not enabled", pc->index);
> +       __T("userspace counter width not set", pc->pmc_width >= 32);
> +#endif
> +
> +       perf_evsel__read(evsel, 0, 0, &counts);
> +       __T("failed to read value for evsel", counts.val != 0);
> +
> +       for (i = 0; i < 5; i++) {
> +               volatile int count = 0x10000 << i;
> +               __u64 start, end, last = 0;
> +
> +               __T_VERBOSE("\tloop = %u, ", count);
> +
> +               perf_evsel__read(evsel, 0, 0, &counts);
> +               start = counts.val;
> +
> +               while (count--) ;
> +
> +               perf_evsel__read(evsel, 0, 0, &counts);
> +               end = counts.val;
> +
> +               __T("invalid counter data", (end - start) > last);
> +               last = end - start;
> +               __T_VERBOSE("count = %llu\n", end - start);
> +       }
> +
> +       perf_evsel__close(evsel);
> +       perf_evsel__delete(evsel);
> +
> +       perf_thread_map__put(threads);
> +       return 0;
> +}
> +
>  int main(int argc, char **argv)
>  {
>         __T_START;
> @@ -129,6 +192,8 @@ int main(int argc, char **argv)
>         test_stat_cpu();
>         test_stat_thread();
>         test_stat_thread_enable();
> +       test_stat_user_read(PERF_COUNT_HW_INSTRUCTIONS);
> +       test_stat_user_read(PERF_COUNT_HW_CPU_CYCLES);
>
>         __T_END;
>         return tests_failed == 0 ? 0 : -1;
> --
> 2.27.0
>

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

  reply	other threads:[~2021-05-04 21:41 UTC|newest]

Thread overview: 70+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-11  0:08 [PATCH v6 00/10] libperf and arm64 userspace counter access support Rob Herring
2021-03-11  0:08 ` Rob Herring
2021-03-11  0:08 ` [PATCH v6 01/10] arm64: pmu: Add function implementation to update event index in userpage Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-30 15:30   ` Will Deacon
2021-03-30 15:30     ` Will Deacon
2021-03-11  0:08 ` [PATCH v6 02/10] arm64: perf: Enable PMU counter direct access for perf event Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-30 11:30   ` Zachary Leaf
2021-03-30 11:30     ` Zachary Leaf
2021-03-30 15:31   ` Will Deacon
2021-03-30 15:31     ` Will Deacon
2021-03-30 17:09     ` Rob Herring
2021-03-30 17:09       ` Rob Herring
2021-03-30 21:08       ` Rob Herring
2021-03-30 21:08         ` Rob Herring
2021-03-31 15:38         ` Will Deacon
2021-03-31 15:38           ` Will Deacon
2021-03-31 17:52           ` Rob Herring
2021-03-31 17:52             ` Rob Herring
2021-04-01  9:04             ` Will Deacon
2021-04-01  9:04               ` Will Deacon
2021-03-31 16:00       ` Will Deacon
2021-03-31 16:00         ` Will Deacon
2021-04-01 19:45         ` Rob Herring
2021-04-01 19:45           ` Rob Herring
2021-04-07 12:44           ` Will Deacon
2021-04-07 12:44             ` Will Deacon
2021-04-08 11:08             ` Mark Rutland
2021-04-08 11:08               ` Mark Rutland
2021-04-08 18:38               ` Rob Herring
2021-04-08 18:38                 ` Rob Herring
2021-04-19 16:14                 ` Will Deacon
2021-04-19 16:14                   ` Will Deacon
2021-04-19 19:00                   ` Rob Herring
2021-04-19 19:00                     ` Rob Herring
2021-03-11  0:08 ` [PATCH v6 03/10] tools/include: Add an initial math64.h Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-11  0:08 ` [PATCH v6 04/10] libperf: Add evsel mmap support Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-12 13:58   ` Jiri Olsa
2021-03-12 13:58     ` Jiri Olsa
2021-03-12 14:34     ` Rob Herring
2021-03-12 14:34       ` Rob Herring
2021-03-12 18:29       ` Jiri Olsa
2021-03-12 18:29         ` Jiri Olsa
2021-03-31 22:06         ` Rob Herring
2021-03-31 22:06           ` Rob Herring
2021-03-11  0:08 ` [PATCH v6 05/10] libperf: tests: Add support for verbose printing Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-11  0:08 ` [PATCH v6 06/10] libperf: Add support for user space counter access Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-05-04 21:40   ` Ian Rogers [this message]
2021-05-04 21:40     ` Ian Rogers
2021-05-05  2:12     ` Rob Herring
2021-05-05  2:12       ` Rob Herring
2021-03-11  0:08 ` [PATCH v6 07/10] libperf: Add arm64 support to perf_mmap__read_self() Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-11  0:08 ` [PATCH v6 08/10] perf: arm64: Add test for userspace counter access on heterogeneous systems Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-15 16:09   ` Masayoshi Mizuma
2021-03-15 16:09     ` Masayoshi Mizuma
2021-03-11  0:08 ` [PATCH v6 09/10] perf: arm64: Add tests for 32-bit and 64-bit counter size userspace access Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-11  0:08 ` [PATCH v6 10/10] Documentation: arm64: Document PMU counters access from userspace Rob Herring
2021-03-11  0:08   ` Rob Herring
2021-03-31 16:00   ` Will Deacon
2021-03-31 16:00     ` Will Deacon
2021-03-30 11:31 ` [PATCH v6 00/10] libperf and arm64 userspace counter access support Zachary Leaf
2021-03-30 11:31   ` Zachary Leaf

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='CAP-5=fUEu1EO7GreYYjZ178BH_riYYa0HdY4GZhi=0DdjkCMJg@mail.gmail.com' \
    --to=irogers@google.com \
    --cc=Jonathan.Cameron@huawei.com \
    --cc=Zachary.Leaf@arm.com \
    --cc=acme@kernel.org \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=catalin.marinas@arm.com \
    --cc=honnappa.nagarahalli@arm.com \
    --cc=itaru.kitayama@gmail.com \
    --cc=jolsa@redhat.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=raphael.gault@arm.com \
    --cc=robh@kernel.org \
    --cc=will@kernel.org \
    --subject='Re: [PATCH v6 06/10] libperf: Add support for user space counter access' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.