summaryrefslogtreecommitdiff
path: root/tools/perf/tests/code-reading.c
diff options
context:
space:
mode:
authorIan Rogers <irogers@google.com>2025-01-13 22:43:45 +0300
committerNamhyung Kim <namhyung@kernel.org>2025-02-13 07:06:11 +0300
commitdc6d2bc2d893a878e7b58578ff01b4738708deb4 (patch)
treeb5524ff4429f1e88533f518753091462bc4bd8b4 /tools/perf/tests/code-reading.c
parent08d9e883481b2c38326ed37314b1f6a1284c03d8 (diff)
downloadlinux-dc6d2bc2d893a878e7b58578ff01b4738708deb4.tar.xz
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/tests/code-reading.c')
-rw-r--r--tools/perf/tests/code-reading.c12
1 files changed, 9 insertions, 3 deletions
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index b1abb34d7818..cf6edbe697b2 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -479,19 +479,25 @@ static int process_sample_event(struct machine *machine,
struct thread *thread;
int ret;
- if (evlist__parse_sample(evlist, event, &sample)) {
+ perf_sample__init(&sample, /*all=*/false);
+ ret = evlist__parse_sample(evlist, event, &sample);
+ if (ret) {
pr_debug("evlist__parse_sample failed\n");
- return -1;
+ ret = -1;
+ goto out;
}
thread = machine__findnew_thread(machine, sample.pid, sample.tid);
if (!thread) {
pr_debug("machine__findnew_thread failed\n");
- return -1;
+ ret = -1;
+ goto out;
}
ret = read_object_code(sample.ip, READLEN, sample.cpumode, thread, state);
thread__put(thread);
+out:
+ perf_sample__exit(&sample);
return ret;
}