raspi/linux
1
0
Fork 1
mirror of https://github.com/raspberrypi/linux.git synced 2025-12-20 08:42:06 +00:00
Code Issues Projects Releases Wiki Activity

perf sample: Make user_regs and intr_regs optional

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

29
tools/perf/util/arm64-frame-pointer-unwind-support.c
View File

@@ -4,6 +4,7 @@
#include "event.h"
#include "perf_regs.h" // SMPL_REG_MASK
#include "unwind.h"
#include <string.h>
#define perf_event_arm_regs perf_event_arm64_regs
#include "../../arch/arm64/include/uapi/asm/perf_regs.h"
@@ -16,8 +17,13 @@ struct entries {
static bool get_leaf_frame_caller_enabled(struct perf_sample *sample)
{
return callchain_param.record_mode == CALLCHAIN_FP && sample->user_regs.regs
&& sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_LR);
struct regs_dump *regs;
if (callchain_param.record_mode != CALLCHAIN_FP)
return false;
regs = perf_sample__user_regs(sample);
return regs->regs && regs->mask & SMPL_REG_MASK(PERF_REG_ARM64_LR);
}
static int add_entry(struct unwind_entry *entry, void *arg)
@@ -32,7 +38,7 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr
{
int ret;
struct entries entries = {};
struct regs_dump old_regs = sample->user_regs;
struct regs_dump old_regs, *regs;
if (!get_leaf_frame_caller_enabled(sample))
return 0;
@@ -42,19 +48,20 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr
* and set its mask. SP is not used when doing the unwinding but it
* still needs to be set to prevent failures.
*/
if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_PC))) {
sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_PC);
sample->user_regs.cache_regs[PERF_REG_ARM64_PC] = sample->callchain->ips[usr_idx+1];
regs = perf_sample__user_regs(sample);
memcpy(&old_regs, regs, sizeof(*regs));
if (!(regs->mask & SMPL_REG_MASK(PERF_REG_ARM64_PC))) {
regs->cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_PC);
regs->cache_regs[PERF_REG_ARM64_PC] = sample->callchain->ips[usr_idx+1];
}
if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_SP))) {
sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_SP);
sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0;
if (!(regs->mask & SMPL_REG_MASK(PERF_REG_ARM64_SP))) {
regs->cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_SP);
regs->cache_regs[PERF_REG_ARM64_SP] = 0;
}
ret = unwind__get_entries(add_entry, &entries, thread, sample, 2, true);
sample->user_regs = old_regs;
memcpy(regs, &old_regs, sizeof(*regs));
if (ret || entries.length != 2)
return ret;