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>

1 files changed, 8 insertions, 2 deletions

diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 029c4cd8a691..603f5fe9f816 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -54,6 +54,7 @@
 #include "ocfs1_fs_compat.h"
 
 #include "alloc.h"
+#include "aops.h"
 #include "blockcheck.h"
 #include "dlmglue.h"
 #include "export.h"
@@ -1616,12 +1617,17 @@ static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
         return 0;
 }
 
+wait_queue_head_t ocfs2__ioend_wq[OCFS2_IOEND_WQ_HASH_SZ];
+
 static int __init ocfs2_init(void)
 {
-        int status;
+        int status, i;
 
         ocfs2_print_version();
 
+        for (i = 0; i < OCFS2_IOEND_WQ_HASH_SZ; i++)
+                init_waitqueue_head(&ocfs2__ioend_wq[i]);
+
         status = init_ocfs2_uptodate_cache();
         if (status < 0) {
                 mlog_errno(status);
@@ -1760,7 +1766,7 @@ static void ocfs2_inode_init_once(void *data)
         ocfs2_extent_map_init(&oi->vfs_inode);
         INIT_LIST_HEAD(&oi->ip_io_markers);
         oi->ip_dir_start_lookup = 0;
-
+        atomic_set(&oi->ip_unaligned_aio, 0);
         init_rwsem(&oi->ip_alloc_sem);
         init_rwsem(&oi->ip_xattr_sem);
         mutex_init(&oi->ip_io_mutex);