forge/linux-pinenote
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

perf: Optimize perf_output_*() by avoiding local_xchg()

Browse source 
Since the x86 XCHG ins implies LOCK, avoid the use by
using a sequence count instead.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Peter Zijlstra 2010-05-18 11:12:48 +02:00 • committed by Ingo Molnar
commit 6d1acfd5c6
2 changed files with 3 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

1
include/linux/perf_event.h
View file

@ -804,6 +804,7 @@ struct perf_output_handle {
struct perf_mmap_data *data;
unsigned long head;
unsigned long offset;
unsigned long wakeup;
int nmi;
int sample;
};

3
kernel/perf_event.c
View file

@ -2917,6 +2917,7 @@ static void perf_output_get_handle(struct perf_output_handle *handle)
preempt_disable();
local_inc(&data->nest);
handle->wakeup = local_read(&data->wakeup);
}
static void perf_output_put_handle(struct perf_output_handle *handle)
@ -2950,7 +2951,7 @@ again:
goto again;
}
if (local_xchg(&data->wakeup, 0))
if (handle->wakeup != local_read(&data->wakeup))
perf_output_wakeup(handle);
preempt_enable();