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>
This commit is contained in:
Ian Rogers
2025-01-13 11:43:45 -08:00
committed by Namhyung Kim
parent 08d9e88348
commit dc6d2bc2d8
34 changed files with 448 additions and 191 deletions

View File

@@ -131,9 +131,11 @@ static int process_sample_event(struct evlist *evlist,
pid_t next_tid, prev_tid;
int cpu, err;
perf_sample__init(&sample, /*all=*/false);
if (evlist__parse_sample(evlist, event, &sample)) {
pr_debug("evlist__parse_sample failed\n");
return -1;
err = -1;
goto out;
}
evsel = evlist__id2evsel(evlist, sample.id);
@@ -145,7 +147,7 @@ static int process_sample_event(struct evlist *evlist,
cpu, prev_tid, next_tid);
err = check_cpu(switch_tracking, cpu);
if (err)
return err;
goto out;
/*
* Check for no missing sched_switch events i.e. that the
* evsel->core.system_wide flag has worked.
@@ -153,7 +155,8 @@ static int process_sample_event(struct evlist *evlist,
if (switch_tracking->tids[cpu] != -1 &&
switch_tracking->tids[cpu] != prev_tid) {
pr_debug("Missing sched_switch events\n");
return -1;
err = -1;
goto out;
}
switch_tracking->tids[cpu] = next_tid;
}
@@ -169,7 +172,10 @@ static int process_sample_event(struct evlist *evlist,
switch_tracking->cycles_after_comm_4 = 1;
}
return 0;
err = 0;
out:
perf_sample__exit(&sample);
return err;
}
static int process_event(struct evlist *evlist, union perf_event *event,