From dc6d2bc2d893a878e7b58578ff01b4738708deb4 Mon Sep 17 00:00:00 2001 From: Ian Rogers 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 as about 2.5% when running `perf script --itrace=i0`: https://lore.kernel.org/lkml/d841b97b3ad2ca8bcab07e4293375fb7c32dfce7.1736618095.git.tavianator@tavianator.com/ Adrian Hunter 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 Link: https://lore.kernel.org/r/20250113194345.1537821-1-irogers@google.com Signed-off-by: Namhyung Kim --- tools/perf/util/sample.c | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) create mode 100644 tools/perf/util/sample.c (limited to 'tools/perf/util/sample.c') diff --git a/tools/perf/util/sample.c b/tools/perf/util/sample.c new file mode 100644 index 000000000000..605fee971f55 --- /dev/null +++ b/tools/perf/util/sample.c @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include "sample.h" +#include "debug.h" +#include +#include +#include + +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; +} -- cgit v1.2.3-59-g8ed1b