summaryrefslogtreecommitdiffstats
path: root/fs/ocfs2/aops.h
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.h
parent730e663bd82c1a10a85ff00728d34152a5a67ec8 (diff)
downloadop-kernel-dev-a11f7e63c59810a81494d4c4b028af707d4c7ca4.zip
op-kernel-dev-a11f7e63c59810a81494d4c4b028af707d4c7ca4.tar.gz
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.h')
-rw-r--r--fs/ocfs2/aops.h14
1 files changed, 14 insertions, 0 deletions
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 75cf3ad..ffb2da3 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -78,6 +78,7 @@ enum ocfs2_iocb_lock_bits {
OCFS2_IOCB_RW_LOCK = 0,
OCFS2_IOCB_RW_LOCK_LEVEL,
OCFS2_IOCB_SEM,
+ OCFS2_IOCB_UNALIGNED_IO,
OCFS2_IOCB_NUM_LOCKS
};
@@ -91,4 +92,17 @@ enum ocfs2_iocb_lock_bits {
clear_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private)
#define ocfs2_iocb_is_sem_locked(iocb) \
test_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private)
+
+#define ocfs2_iocb_set_unaligned_aio(iocb) \
+ set_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
+#define ocfs2_iocb_clear_unaligned_aio(iocb) \
+ clear_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
+#define ocfs2_iocb_is_unaligned_aio(iocb) \
+ test_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
+
+#define OCFS2_IOEND_WQ_HASH_SZ 37
+#define ocfs2_ioend_wq(v) (&ocfs2__ioend_wq[((unsigned long)(v)) %\
+ OCFS2_IOEND_WQ_HASH_SZ])
+extern wait_queue_head_t ocfs2__ioend_wq[OCFS2_IOEND_WQ_HASH_SZ];
+
#endif /* OCFS2_FILE_H */
OpenPOWER on IntegriCloud