mirror of
https://github.com/torvalds/linux.git
synced 2025-04-11 04:53:02 +00:00
dc6d2bc2d8
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>
44 lines
970 B
C
44 lines
970 B
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#include "sample.h"
|
|
#include "debug.h"
|
|
#include <linux/zalloc.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
|
|
void perf_sample__init(struct perf_sample *sample, bool all)
|
|
{
|
|
if (all) {
|
|
memset(sample, 0, sizeof(*sample));
|
|
} else {
|
|
sample->user_regs = NULL;
|
|
sample->intr_regs = NULL;
|
|
}
|
|
}
|
|
|
|
void perf_sample__exit(struct perf_sample *sample)
|
|
{
|
|
free(sample->user_regs);
|
|
free(sample->intr_regs);
|
|
}
|
|
|
|
struct regs_dump *perf_sample__user_regs(struct perf_sample *sample)
|
|
{
|
|
if (!sample->user_regs) {
|
|
sample->user_regs = zalloc(sizeof(*sample->user_regs));
|
|
if (!sample->user_regs)
|
|
pr_err("Failure to allocate sample user_regs");
|
|
}
|
|
return sample->user_regs;
|
|
}
|
|
|
|
|
|
struct regs_dump *perf_sample__intr_regs(struct perf_sample *sample)
|
|
{
|
|
if (!sample->intr_regs) {
|
|
sample->intr_regs = zalloc(sizeof(*sample->intr_regs));
|
|
if (!sample->intr_regs)
|
|
pr_err("Failure to allocate sample intr_regs");
|
|
}
|
|
return sample->intr_regs;
|
|
}
|