[PATCH 3/3] perf_event: cleanup for cpu_clock_perf_event_update()

[Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>]

Using atomic64_xchg() instead of atomic64_read() and atomic64_set().

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
---
 kernel/perf_event.c |    3 +--
 1 files changed, 1 insertions(+), 2 deletions(-)

diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 592b293..8f46012 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -4079,8 +4079,7 @@ static void cpu_clock_perf_event_update(struct perf_event *event)
 	u64 now;
 
 	now = cpu_clock(cpu);
-	prev = atomic64_read(&event->hw.prev_count);
-	atomic64_set(&event->hw.prev_count, now);
+	prev = atomic64_xchg(&event->hw.prev_count, now);
 	atomic64_add(now - prev, &event->count);
 }
 
-- 
1.6.1.2