mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* [PATCH] percpu_counter: __this_cpu_write doesn't need to be protected by spinlock
@ 2013-07-01  2:48 Fan Du
  0 siblings, 0 replies; only message in thread
From: Fan Du @ 2013-07-01  2:48 UTC (permalink / raw)
  To: viro; +Cc: linux-kernel

__this_cpu_write doesn't need to be protected by spinlock, AS we are doing
per cpu write with preempt disabled. And another reason to remove __this_cpu_write
outside of spinlock: __percpu_counter_sum is not a accurate counter.  

Signed-off-by: Fan Du <fan.du@windriver.com>
---
 lib/percpu_counter.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index ba6085d..1fc23a3 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -80,8 +80,8 @@ void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch)
 	if (count >= batch || count <= -batch) {
 		raw_spin_lock(&fbc->lock);
 		fbc->count += count;
-		__this_cpu_write(*fbc->counters, 0);
 		raw_spin_unlock(&fbc->lock);
+		__this_cpu_write(*fbc->counters, 0);
 	} else {
 		__this_cpu_write(*fbc->counters, count);
 	}
-- 
1.7.1


^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2013-07-01  2:49 UTC | newest]

Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2013-07-01  2:48 [PATCH] percpu_counter: __this_cpu_write doesn't need to be protected by spinlock Fan Du

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®