From ee6dcfa40a50fe12a3ae0fb4d2653c66c3ed6556 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Fri, 26 Nov 2010 13:49:04 +0100
Subject: perf: Fix the software context switch counter

Stephane noticed that because the perf_sw_event() call is inside the
perf_event_task_sched_out() call it won't get called unless we
have a per-task counter.

Reported-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/perf_event.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'kernel')

diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index f365dd8ef8b..eac7e336433 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -1287,8 +1287,6 @@ void __perf_event_task_sched_out(struct task_struct *task,
 {
 	int ctxn;
 
-	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
-
 	for_each_task_context_nr(ctxn)
 		perf_event_context_sched_out(task, ctxn, next);
 }
-- 
cgit v1.2.3