summaryrefslogtreecommitdiffstats
path: root/fs/ocfs2/aops.c
diff options
context:
space:
mode:
authorMark Fasheh <mfasheh@suse.com>2011-06-22 14:23:38 -0700
committerJoel Becker <jlbec@evilplan.org>2011-07-28 02:07:16 -0700
commita11f7e63c59810a81494d4c4b028af707d4c7ca4 (patch)
tree6d28cfc9519f96db5c20780bf765de9e0fc03bef /fs/ocfs2/aops.c
parent730e663bd82c1a10a85ff00728d34152a5a67ec8 (diff)
downloadlinux-a11f7e63c59810a81494d4c4b028af707d4c7ca4.tar.bz2
ocfs2: serialize unaligned aio
Fix a corruption that can happen when we have (two or more) outstanding aio's to an overlapping unaligned region. Ext4 (e9e3bcecf44c04b9e6b505fd8e2eb9cea58fb94d) and xfs recently had to fix similar issues. In our case what happens is that we can have an outstanding aio on a region and if a write comes in with some bytes overlapping the original aio we may decide to read that region into a page before continuing (typically because of buffered-io fallback). Since we have no ordering guarantees with the aio, we can read stale or bad data into the page and then write it back out. If the i/o is page and block aligned, then we avoid this issue as there won't be any need to read data from disk. I took the same approach as Eric in the ext4 patch and introduced some serialization of unaligned async direct i/o. I don't expect this to have an effect on the most common cases of AIO. Unaligned aio will be slower though, but that's far more acceptable than data corruption. Signed-off-by: Mark Fasheh <mfasheh@suse.com> Signed-off-by: Joel Becker <jlbec@evilplan.org>
Diffstat (limited to 'fs/ocfs2/aops.c')
-rw-r--r--fs/ocfs2/aops.c10
1 files changed, 10 insertions, 0 deletions
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index ac97bca282d2..4c1ec8f2d8c1 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -564,6 +564,7 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
{
struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
int level;
+ wait_queue_head_t *wq = ocfs2_ioend_wq(inode);
/* this io's submitter should not have unlocked this before we could */
BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
@@ -573,6 +574,15 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
ocfs2_iocb_clear_sem_locked(iocb);
}
+ if (ocfs2_iocb_is_unaligned_aio(iocb)) {
+ ocfs2_iocb_clear_unaligned_aio(iocb);
+
+ if (atomic_dec_and_test(&OCFS2_I(inode)->ip_unaligned_aio) &&
+ waitqueue_active(wq)) {
+ wake_up_all(wq);
+ }
+ }
+
ocfs2_iocb_clear_rw_locked(iocb);
level = ocfs2_iocb_rw_locked_level(iocb);