Skip to contentSkip to conversation

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

tip:perf/core tip-bot for Peter Zijlstra 1 participant 1 message May 18, 2010 perf events

lore
Share & tools
lore
#0 lore raw
Commit-ID:  6d1acfd5c6bfd5231c13a8f2858d7f2afbaa1b62
Gitweb:     http://git.kernel.org/tip/6d1acfd5c6bfd5231c13a8f2858d7f2afbaa1b62
Author:     Peter Zijlstra <[email protected]>
AuthorDate: Tue, 18 May 2010 11:12:48 +0200
Committer:  Ingo Molnar <[email protected]>
CommitDate: Tue, 18 May 2010 18:35:49 +0200

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

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

LKML-Reference: <new-submission>

---
 include/linux/perf_event.h |    1 +
 kernel/perf_event.c        |    3 ++-
 2 files changed, 3 insertions(+), 1 deletions(-)
include/linux/perf_event.h +1 -0
index ce76676..fe50347 100644
@@ -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;
 };
kernel/perf_event.c +2 -1
index 1f98c78..7e3bcf1 100644
@@ -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();