lkml.org 
[lkml]   [2013]   [Jun]   [30]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH] percpu_counter: __this_cpu_write doesn't need to be protected by spinlock
Date
__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


\
 
 \ /
  Last update: 2013-07-01 05:21    [W:0.036 / U:18.156 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site