From dc6d2bc2d893a878e7b58578ff01b4738708deb4 Mon Sep 17 00:00:00 2001
From: Ian Rogers <irogers@google.com>
Date: Mon, 13 Jan 2025 11:43:45 -0800
Subject: 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>
---
tools/perf/builtin-script.c | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
(limited to 'tools/perf/builtin-script.c')
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 33667b534634..d797cec4f054 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -783,14 +783,20 @@ tod_scnprintf(struct perf_script *script, char *buf, int buflen,
static int perf_sample__fprintf_iregs(struct perf_sample *sample,
struct perf_event_attr *attr, const char *arch, FILE *fp)
{
- return perf_sample__fprintf_regs(&sample->intr_regs,
+ if (!sample->intr_regs)
+ return 0;
+
+ return perf_sample__fprintf_regs(perf_sample__intr_regs(sample),
attr->sample_regs_intr, arch, fp);
}
static int perf_sample__fprintf_uregs(struct perf_sample *sample,
struct perf_event_attr *attr, const char *arch, FILE *fp)
{
- return perf_sample__fprintf_regs(&sample->user_regs,
+ if (!sample->user_regs)
+ return 0;
+
+ return perf_sample__fprintf_regs(perf_sample__user_regs(sample),
attr->sample_regs_user, arch, fp);
}
--
cgit