perf: Reduce stack usage of perf_output_begin()

Browse source

__perf_output_begin() has an on-stack struct perf_sample_data in the
unlikely case it needs to generate a LOST record. However, every call
to perf_output_begin() must already have a perf_sample_data on-stack.

Reported-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201030151954.985416146@infradead.org

...

This commit is contained in:

Peter Zijlstra 2020-10-30 15:50:32 +01:00

parent 7bdb157cde

commit 267fb27352

6 changed files with 37 additions and 30 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

2

arch/powerpc/perf/imc-pmu.c

View file

2

arch/s390/kernel/perf_cpum_sf.c

View file

4

arch/x86/events/intel/ds.c

View file

7

include/linux/perf_event.h

View file

32

kernel/events/core.c

View file

20

kernel/events/ring_buffer.c

View file