xfs: Don't flush stale inodes

commit 44e08c45cc14e6190a424be8d450070c8e508fad upstream

Because inodes remain in cache much longer than inode buffers do
under memory pressure, we can get the situation where we have
stale, dirty inodes being reclaimed but the backing storage has
been freed.  Hence we should never, ever flush XFS_ISTALE inodes
to disk as there is no guarantee that the backing buffer is in
cache and still marked stale when the flush occurs.

Signed-off-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Alex Elder <aelder@sgi.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index b92a4fa2a0a12eda161c2ff897bd820f5cbde1e8..13d7d21f889bc8b057ce614df33af464d9c0bf38 100644 (file)
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2877,10 +2877,14 @@ xfs_iflush(
        mp = ip->i_mount;
 
        /*
-        * If the inode isn't dirty, then just release the inode
-        * flush lock and do nothing.
+        * If the inode isn't dirty, then just release the inode flush lock and
+        * do nothing. Treat stale inodes the same; we cannot rely on the
+        * backing buffer remaining stale in cache for the remaining life of
+        * the stale inode and so xfs_itobp() below may give us a buffer that
+        * no longer contains inodes below. Doing this stale check here also
+        * avoids forcing the log on pinned, stale inodes.
         */
-       if (xfs_inode_clean(ip)) {
+       if (xfs_inode_clean(ip) || xfs_iflags_test(ip, XFS_ISTALE)) {
                xfs_ifunlock(ip);
                return 0;
        }