diff options
| author | OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> | 2006-04-18 09:44:06 +0200 |
|---|---|---|
| committer | Jens Axboe <axboe@suse.de> | 2006-04-18 09:44:06 +0200 |
| commit | fba822722e3f9d438fca8fd9541d7ddd447d7a48 (patch) | |
| tree | 05fc35428f61fb6b66726e3aae03ce9187212c21 /block/cfq-iosched.c | |
| parent | a9a5cd5d2a57fb76dbae2115450f777b69beccf7 (diff) | |
| download | linux-fba822722e3f9d438fca8fd9541d7ddd447d7a48.tar.gz linux-fba822722e3f9d438fca8fd9541d7ddd447d7a48.tar.bz2 linux-fba822722e3f9d438fca8fd9541d7ddd447d7a48.zip | |
[PATCH 1/2] iosched: fix typo and barrier()
On rmmod path, cfq/as waits to make sure all io-contexts was
freed. However, it's using complete(), not wait_for_completion().
I think barrier() is not enough in here. To avoid the following case,
this patch replaces barrier() with smb_wmb().
cpu0 visibility cpu1
[ioc_gnone=NULL,ioc_count=1]
ioc_gnone = &all_gone NULL,ioc_count=1
atomic_read(&ioc_count) NULL,ioc_count=1
wait_for_completion() NULL,ioc_count=0 atomic_sub_and_test()
NULL,ioc_count=0 if ( && ioc_gone)
[ioc_gone==NULL,
so doesn't call complete()]
&all_gone,ioc_count=0
Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Signed-off-by: Jens Axboe <axboe@suse.de>
Diffstat (limited to 'block/cfq-iosched.c')
| -rw-r--r-- | block/cfq-iosched.c | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 67d446de0227..01820b1094e9 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -2439,9 +2439,10 @@ static void __exit cfq_exit(void) DECLARE_COMPLETION(all_gone); elv_unregister(&iosched_cfq); ioc_gone = &all_gone; - barrier(); + /* ioc_gone's update must be visible before reading ioc_count */ + smp_wmb(); if (atomic_read(&ioc_count)) - complete(ioc_gone); + wait_for_completion(ioc_gone); synchronize_rcu(); cfq_slab_kill(); } |