diff options
| author | Ian Rogers <irogers@google.com> | 2025-01-13 11:43:45 -0800 |
|---|---|---|
| committer | Namhyung Kim <namhyung@kernel.org> | 2025-02-12 20:06:11 -0800 |
| commit | dc6d2bc2d893a878e7b58578ff01b4738708deb4 (patch) | |
| tree | b5524ff4429f1e88533f518753091462bc4bd8b4 /tools/perf/util/arm-spe.c | |
| parent | 08d9e883481b2c38326ed37314b1f6a1284c03d8 (diff) | |
perf sample: Make user_regs and intr_regs optional
The struct dump_regs contains 512 bytes of cache_regs, meaning the two
values in perf_sample contribute 1088 bytes of its total 1384 bytes
size. Initializing this much memory has a cost reported by Tavian
Barnes <tavianator@tavianator.com> as about 2.5% when running `perf
script --itrace=i0`:
https://lore.kernel.org/lkml/d841b97b3ad2ca8bcab07e4293375fb7c32dfce7.1736618095.git.tavianator@tavianator.com/
Adrian Hunter <adrian.hunter@intel.com> replied that the zero
initialization was necessary and couldn't simply be removed.
This patch aims to strike a middle ground of still zeroing the
perf_sample, but removing 79% of its size by make user_regs and
intr_regs optional pointers to zalloc-ed memory. To support the
allocation accessors are created for user_regs and intr_regs. To
support correct cleanup perf_sample__init and perf_sample__exit
functions are created and added throughout the code base.
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250113194345.1537821-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Diffstat (limited to 'tools/perf/util/arm-spe.c')
| -rw-r--r-- | tools/perf/util/arm-spe.c | 24 |
1 files changed, 18 insertions, 6 deletions
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index 12761c39788f..251d214adf7f 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -379,8 +379,10 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq, struct arm_spe *spe = speq->spe; struct arm_spe_record *record = &speq->decoder->record; union perf_event *event = speq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; + int ret; + perf_sample__init(&sample, /*all=*/true); arm_spe_prep_sample(spe, speq, event, &sample); sample.id = spe_events_id; @@ -390,7 +392,9 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq, sample.data_src = data_src; sample.weight = record->latency; - return arm_spe_deliver_synth_event(spe, speq, event, &sample); + ret = arm_spe_deliver_synth_event(spe, speq, event, &sample); + perf_sample__exit(&sample); + return ret; } static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq, @@ -399,8 +403,10 @@ static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq, struct arm_spe *spe = speq->spe; struct arm_spe_record *record = &speq->decoder->record; union perf_event *event = speq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; + int ret; + perf_sample__init(&sample, /*all=*/true); arm_spe_prep_sample(spe, speq, event, &sample); sample.id = spe_events_id; @@ -409,7 +415,9 @@ static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq, sample.weight = record->latency; sample.flags = speq->flags; - return arm_spe_deliver_synth_event(spe, speq, event, &sample); + ret = arm_spe_deliver_synth_event(spe, speq, event, &sample); + perf_sample__exit(&sample); + return ret; } static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq, @@ -418,7 +426,8 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq, struct arm_spe *spe = speq->spe; struct arm_spe_record *record = &speq->decoder->record; union perf_event *event = speq->event_buf; - struct perf_sample sample = { .ip = 0, }; + struct perf_sample sample; + int ret; /* * Handles perf instruction sampling period. @@ -428,6 +437,7 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq, return 0; speq->period_instructions = 0; + perf_sample__init(&sample, /*all=*/true); arm_spe_prep_sample(spe, speq, event, &sample); sample.id = spe_events_id; @@ -439,7 +449,9 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq, sample.weight = record->latency; sample.flags = speq->flags; - return arm_spe_deliver_synth_event(spe, speq, event, &sample); + ret = arm_spe_deliver_synth_event(spe, speq, event, &sample); + perf_sample__exit(&sample); + return ret; } static const struct midr_range common_ds_encoding_cpus[] = { |