From: Rob Herring <robh@kernel.org> To: 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> Cc: linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, Alexander Shishkin <alexander.shishkin@linux.intel.com>, Namhyung Kim <namhyung@kernel.org>, Raphael Gault <raphael.gault@arm.com>, Mark Rutland <mark.rutland@arm.com>, Jonathan Cameron <Jonathan.Cameron@huawei.com>, Ian Rogers <irogers@google.com>, honnappa.nagarahalli@arm.com, Itaru Kitayama <itaru.kitayama@gmail.com> Subject: [PATCH v4 6/9] libperf: Add support for user space counter access Date: Thu, 1 Oct 2020 09:01:13 -0500 [thread overview] Message-ID: <20201001140116.651970-7-robh@kernel.org> (raw) In-Reply-To: <20201001140116.651970-1-robh@kernel.org> 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> --- v4: - Update perf_evsel__mmap size to pages v3: - Split out perf_evsel__mmap() to separate patch --- tools/lib/perf/evsel.c | 3 + tools/lib/perf/include/internal/mmap.h | 3 + tools/lib/perf/mmap.c | 90 ++++++++++++++++++++++++++ tools/lib/perf/tests/test-evsel.c | 63 ++++++++++++++++++ 4 files changed, 159 insertions(+) diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c index 42eaf3c18981..e1f18d65f604 100644 --- a/tools/lib/perf/evsel.c +++ b/tools/lib/perf/evsel.c @@ -222,6 +222,9 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, if (FD(evsel, cpu, thread) < 0) return -EINVAL; + if (evsel->mmap && !perf_mmap__read_self(evsel->mmap, 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..cb07969cfdbf 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 +275,91 @@ 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; + + BUG_ON(!pc); + + if (!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); + } + } + + idx = READ_ONCE(pc->index); + cnt = READ_ONCE(pc->offset); + if (pc->cap_user_rdpmc && idx) { + u64 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); + } + + count->val = cnt; + + return 0; +} diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c index 135722ac965b..eeca8203d73d 100644 --- a/tools/lib/perf/tests/test-evsel.c +++ b/tools/lib/perf/tests/test-evsel.c @@ -120,6 +120,67 @@ 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, + }; + 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); + + pc = perf_evsel__mmap(evsel, 0); + __T("failed to mmap evsel", pc); + +#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 +190,8 @@ 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 0; -- 2.25.1
WARNING: multiple messages have this Message-ID (diff)
From: Rob Herring <robh@kernel.org> To: 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> Cc: Mark Rutland <mark.rutland@arm.com>, Ian Rogers <irogers@google.com>, Alexander Shishkin <alexander.shishkin@linux.intel.com>, linux-kernel@vger.kernel.org, honnappa.nagarahalli@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-kernel@lists.infradead.org Subject: [PATCH v4 6/9] libperf: Add support for user space counter access Date: Thu, 1 Oct 2020 09:01:13 -0500 [thread overview] Message-ID: <20201001140116.651970-7-robh@kernel.org> (raw) In-Reply-To: <20201001140116.651970-1-robh@kernel.org> 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> --- v4: - Update perf_evsel__mmap size to pages v3: - Split out perf_evsel__mmap() to separate patch --- tools/lib/perf/evsel.c | 3 + tools/lib/perf/include/internal/mmap.h | 3 + tools/lib/perf/mmap.c | 90 ++++++++++++++++++++++++++ tools/lib/perf/tests/test-evsel.c | 63 ++++++++++++++++++ 4 files changed, 159 insertions(+) diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c index 42eaf3c18981..e1f18d65f604 100644 --- a/tools/lib/perf/evsel.c +++ b/tools/lib/perf/evsel.c @@ -222,6 +222,9 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread, if (FD(evsel, cpu, thread) < 0) return -EINVAL; + if (evsel->mmap && !perf_mmap__read_self(evsel->mmap, 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..cb07969cfdbf 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 +275,91 @@ 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; + + BUG_ON(!pc); + + if (!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); + } + } + + idx = READ_ONCE(pc->index); + cnt = READ_ONCE(pc->offset); + if (pc->cap_user_rdpmc && idx) { + u64 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); + } + + count->val = cnt; + + return 0; +} diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c index 135722ac965b..eeca8203d73d 100644 --- a/tools/lib/perf/tests/test-evsel.c +++ b/tools/lib/perf/tests/test-evsel.c @@ -120,6 +120,67 @@ 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, + }; + 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); + + pc = perf_evsel__mmap(evsel, 0); + __T("failed to mmap evsel", pc); + +#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 +190,8 @@ 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 0; -- 2.25.1 _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2020-10-01 14:01 UTC|newest] Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top 2020-10-01 14:01 [PATCH v4 0/9] libperf and arm64 userspace counter access support Rob Herring 2020-10-01 14:01 ` Rob Herring 2020-10-01 14:01 ` [PATCH v4 1/9] arm64: pmu: Add function implementation to update event index in userpage Rob Herring 2020-10-01 14:01 ` Rob Herring 2020-10-01 14:01 ` [PATCH v4 2/9] arm64: perf: Enable pmu counter direct access for perf event on armv8 Rob Herring 2020-10-01 14:01 ` Rob Herring 2020-11-13 18:06 ` Mark Rutland 2020-11-13 18:06 ` Mark Rutland 2020-11-19 18:35 ` Rob Herring 2020-11-19 18:35 ` Rob Herring 2020-11-19 19:15 ` Will Deacon 2020-11-19 19:15 ` Will Deacon 2020-11-20 20:03 ` Rob Herring 2020-11-20 20:03 ` Rob Herring 2020-11-20 22:08 ` Rob Herring 2020-11-20 22:08 ` Rob Herring 2020-12-02 14:57 ` Rob Herring 2020-12-02 14:57 ` Rob Herring 2021-01-07 0:17 ` Rob Herring 2021-01-07 0:17 ` Rob Herring 2020-10-01 14:01 ` [PATCH v4 3/9] tools/include: Add an initial math64.h Rob Herring 2020-10-01 14:01 ` Rob Herring 2020-10-01 14:01 ` [PATCH v4 4/9] libperf: Add libperf_evsel__mmap() Rob Herring 2020-10-01 14:01 ` Rob Herring 2020-10-14 11:05 ` Jiri Olsa 2020-10-14 11:05 ` Jiri Olsa 2020-10-16 21:39 ` Rob Herring 2020-10-16 21:39 ` Rob Herring 2020-10-19 20:15 ` Jiri Olsa 2020-10-19 20:15 ` Jiri Olsa 2020-10-20 14:38 ` Rob Herring 2020-10-20 14:38 ` Rob Herring 2020-10-20 15:35 ` Jiri Olsa 2020-10-20 15:35 ` Jiri Olsa 2020-10-20 17:11 ` Rob Herring 2020-10-20 17:11 ` Rob Herring 2020-10-21 11:24 ` Jiri Olsa 2020-10-21 11:24 ` Jiri Olsa 2020-11-05 16:19 ` Rob Herring 2020-11-05 16:19 ` Rob Herring 2020-11-05 22:41 ` Jiri Olsa 2020-11-05 22:41 ` Jiri Olsa 2020-11-06 21:56 ` Rob Herring 2020-11-06 21:56 ` Rob Herring 2020-11-11 12:00 ` Jiri Olsa 2020-11-11 12:00 ` Jiri Olsa 2020-11-11 14:50 ` Rob Herring 2020-11-11 14:50 ` Rob Herring 2020-10-01 14:01 ` [PATCH v4 5/9] libperf: tests: Add support for verbose printing Rob Herring 2020-10-01 14:01 ` Rob Herring 2020-10-01 14:01 ` Rob Herring [this message] 2020-10-01 14:01 ` [PATCH v4 6/9] libperf: Add support for user space counter access Rob Herring 2020-10-01 14:01 ` [PATCH v4 7/9] libperf: Add arm64 support to perf_mmap__read_self() Rob Herring 2020-10-01 14:01 ` Rob Herring 2020-10-01 14:01 ` [PATCH v4 8/9] perf: arm64: Add test for userspace counter access on heterogeneous systems Rob Herring 2020-10-01 14:01 ` Rob Herring 2020-10-01 14:01 ` [PATCH v4 9/9] Documentation: arm64: Document PMU counters access from userspace Rob Herring 2020-10-01 14:01 ` Rob Herring
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=20201001140116.651970-7-robh@kernel.org \ --to=robh@kernel.org \ --cc=Jonathan.Cameron@huawei.com \ --cc=acme@kernel.org \ --cc=alexander.shishkin@linux.intel.com \ --cc=catalin.marinas@arm.com \ --cc=honnappa.nagarahalli@arm.com \ --cc=irogers@google.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=will@kernel.org \ /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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
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.