Messages in this thread Patch in this message | | | Date | Wed, 17 Aug 2022 10:49:09 -0700 | Subject | [PATCH v4] perf: Align user space counter reading with code | From | Ian Rogers <> |
| |
Align the user space counter reading documentation with the code in perf_mmap__read_self. Previously the documentation was based on the perf rdpmc test, but now general purpose code is provided by libperf.
Signed-off-by: Ian Rogers <irogers@google.com> Reviewed-by: Rob Herring <robh@kernel.org>
v4. Is a rebase. --- include/uapi/linux/perf_event.h | 35 +++++++++++++++++---------- tools/include/uapi/linux/perf_event.h | 35 +++++++++++++++++---------- 2 files changed, 44 insertions(+), 26 deletions(-)
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 03b370062741..f35c10aa71b9 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -541,9 +541,13 @@ struct perf_event_mmap_page { * * if (pc->cap_usr_time && enabled != running) { * cyc = rdtsc(); - * time_offset = pc->time_offset; * time_mult = pc->time_mult; * time_shift = pc->time_shift; + * time_offset = pc->time_offset; + * if (pc->cap_user_time_short) { + * time_cycles = pc->time_cycles; + * time_mask = pc->time_mask; + * } * } * * index = pc->index; @@ -551,6 +555,9 @@ struct perf_event_mmap_page { * if (pc->cap_user_rdpmc && index) { * width = pc->pmc_width; * pmc = rdpmc(index - 1); + * pmc <<= 64 - width; + * pmc >>= 64 - width; + * count += pmc; * } * * barrier(); @@ -593,25 +600,27 @@ struct perf_event_mmap_page { * If cap_usr_time the below fields can be used to compute the time * delta since time_enabled (in ns) using rdtsc or similar. * - * u64 quot, rem; - * u64 delta; - * - * quot = (cyc >> time_shift); - * rem = cyc & (((u64)1 << time_shift) - 1); - * delta = time_offset + quot * time_mult + - * ((rem * time_mult) >> time_shift); + * cyc = time_cycles + ((cyc - time_cycles) & time_mask); + * delta = time_offset + mul_u64_u32_shr(cyc, time_mult, time_shift); * * Where time_offset,time_mult,time_shift and cyc are read in the - * seqcount loop described above. This delta can then be added to - * enabled and possible running (if index), improving the scaling: + * seqcount loop described above. mul_u64_u32_shr will compute: + * + * (u64)(((unsigned __int128)cyc * time_mult) >> time_shift) + * + * This delta can then be added to enabled and possible running (if + * index) to improve the scaling. Due to event multiplexing, running + * may be zero and so care is needed to avoid division by zero. * * enabled += delta; * if (index) * running += delta; * - * quot = count / running; - * rem = count % running; - * count = quot * enabled + (rem * enabled) / running; + * if (running != 0) { + * quot = count / running; + * rem = count % running; + * count = quot * enabled + (rem * enabled) / running; + * } */ __u16 time_shift; __u32 time_mult; diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 581ed4bdc062..9c93e521a6b0 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -541,9 +541,13 @@ struct perf_event_mmap_page { * * if (pc->cap_usr_time && enabled != running) { * cyc = rdtsc(); - * time_offset = pc->time_offset; * time_mult = pc->time_mult; * time_shift = pc->time_shift; + * time_offset = pc->time_offset; + * if (pc->cap_user_time_short) { + * time_cycles = pc->time_cycles; + * time_mask = pc->time_mask; + * } * } * * index = pc->index; @@ -551,6 +555,9 @@ struct perf_event_mmap_page { * if (pc->cap_user_rdpmc && index) { * width = pc->pmc_width; * pmc = rdpmc(index - 1); + * pmc <<= 64 - width; + * pmc >>= 64 - width; + * count += pmc; * } * * barrier(); @@ -593,25 +600,27 @@ struct perf_event_mmap_page { * If cap_usr_time the below fields can be used to compute the time * delta since time_enabled (in ns) using rdtsc or similar. * - * u64 quot, rem; - * u64 delta; - * - * quot = (cyc >> time_shift); - * rem = cyc & (((u64)1 << time_shift) - 1); - * delta = time_offset + quot * time_mult + - * ((rem * time_mult) >> time_shift); + * cyc = time_cycles + ((cyc - time_cycles) & time_mask); + * delta = time_offset + mul_u64_u32_shr(cyc, time_mult, time_shift); * * Where time_offset,time_mult,time_shift and cyc are read in the - * seqcount loop described above. This delta can then be added to - * enabled and possible running (if index), improving the scaling: + * seqcount loop described above. mul_u64_u32_shr will compute: + * + * (u64)(((unsigned __int128)cyc * time_mult) >> time_shift) + * + * This delta can then be added to enabled and possible running (if + * index) to improve the scaling. Due to event multiplexing, running + * may be zero and so care is needed to avoid division by zero. * * enabled += delta; * if (index) * running += delta; * - * quot = count / running; - * rem = count % running; - * count = quot * enabled + (rem * enabled) / running; + * if (running != 0) { + * quot = count / running; + * rem = count % running; + * count = quot * enabled + (rem * enabled) / running; + * } */ __u16 time_shift; __u32 time_mult; -- 2.37.1.595.g718a3a8f04-goog
| |