xfs: xfs_iflush_cluster fails to abort on error

commit b1438f477934f5a4d5a44df26f3079a7575d5946 upstream.

When a failure due to an inode buffer occurs, the error handling
fails to abort the inode writeback correctly. This can result in the
inode being reclaimed whilst still in the AIL, leading to
use-after-free situations as well as filesystems that cannot be
unmounted as the inode log items left in the AIL never get removed.

Fix this by ensuring fatal errors from xfs_imap_to_bp() result in
the inode flush being aborted correctly.

Reported-by: Shyam Kaushik <shyam@zadarastorage.com>
Diagnosed-by: Shyam Kaushik <shyam@zadarastorage.com>
Tested-by: Shyam Kaushik <shyam@zadarastorage.com>
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[wt: in kernels < 3.17, the error sign is positive, not negative]
Signed-off-by: Willy Tarreau <w@1wt.eu>

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index f010ab4594f1ac9b8b7917ed31d61dcf6b400221..e27645569802cd7a0f4e7c1d552e18c222ee58bc 100644 (file)
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2726,7 +2726,7 @@ xfs_iflush(
        struct xfs_buf          **bpp)
 {
        struct xfs_mount        *mp = ip->i_mount;
-       struct xfs_buf          *bp;
+       struct xfs_buf          *bp = NULL;
        struct xfs_dinode       *dip;
        int                     error;
 
@@ -2768,14 +2768,22 @@ xfs_iflush(
        }
 
        /*
-        * Get the buffer containing the on-disk inode.
+        * Get the buffer containing the on-disk inode. We are doing a try-lock
+        * operation here, so we may get  an EAGAIN error. In that case, we
+        * simply want to return with the inode still dirty.
+        *
+        * If we get any other error, we effectively have a corruption situation
+        * and we cannot flush the inode, so we treat it the same as failing
+        * xfs_iflush_int().
         */
        error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &bp, XBF_TRYLOCK,
                               0);
-       if (error || !bp) {
+       if (error == EAGAIN) {
                xfs_ifunlock(ip);
                return error;
        }
+       if (error)
+               goto corrupt_out;
 
        /*
         * First flush out the inode that xfs_iflush was called with.
@@ -2803,7 +2811,8 @@ xfs_iflush(
        return 0;
 
 corrupt_out:
-       xfs_buf_relse(bp);
+       if (bp)
+               xfs_buf_relse(bp);
        xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 cluster_corrupt_out:
        error = XFS_ERROR(EFSCORRUPTED);