xfs: refactor failed buffer resubmission into xfsaild

Flush locked log items whose underlying buffers fail metadata
writeback are tagged with a special flag to indicate that the flush
lock is already held. This is currently implemented in the type
specific ->iop_push() callback, but the processing required for such
items is not type specific because we're only doing basic state
management on the underlying buffer.

Factor the failed log item handling out of the inode and dquot
->iop_push() callbacks and open code the buffer resubmit helper into
a single helper called from xfsaild_push_item(). This provides a
generic mechanism for handling failed metadata buffer writeback with
a bit less code.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Allison Collins <allison.henderson@oracle.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>

1 files changed, 41 insertions, 0 deletions

diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 564253550b75..2574d01e4a83 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -345,6 +345,45 @@ xfs_ail_delete(
 	xfs_trans_ail_cursor_clear(ailp, lip);
 }
 
+/*
+ * Requeue a failed buffer for writeback.
+ *
+ * We clear the log item failed state here as well, but we have to be careful
+ * about reference counts because the only active reference counts on the buffer
+ * may be the failed log items. Hence if we clear the log item failed state
+ * before queuing the buffer for IO we can release all active references to
+ * the buffer and free it, leading to use after free problems in
+ * xfs_buf_delwri_queue. It makes no difference to the buffer or log items which
+ * order we process them in - the buffer is locked, and we own the buffer list
+ * so nothing on them is going to change while we are performing this action.
+ *
+ * Hence we can safely queue the buffer for IO before we clear the failed log
+ * item state, therefore  always having an active reference to the buffer and
+ * avoiding the transient zero-reference state that leads to use-after-free.
+ */
+static inline int
+xfsaild_resubmit_item(
+	struct xfs_log_item	*lip,
+	struct list_head	*buffer_list)
+{
+	struct xfs_buf		*bp = lip->li_buf;
+
+	if (!xfs_buf_trylock(bp))
+		return XFS_ITEM_LOCKED;
+
+	if (!xfs_buf_delwri_queue(bp, buffer_list)) {
+		xfs_buf_unlock(bp);
+		return XFS_ITEM_FLUSHING;
+	}
+
+	/* protected by ail_lock */
+	list_for_each_entry(lip, &bp->b_li_list, li_bio_list)
+		xfs_clear_li_failed(lip);
+
+	xfs_buf_unlock(bp);
+	return XFS_ITEM_SUCCESS;
+}
+
 static inline uint
 xfsaild_push_item(
 	struct xfs_ail		*ailp,
@@ -365,6 +404,8 @@ xfsaild_push_item(
 	 */
 	if (!lip->li_ops->iop_push)
 		return XFS_ITEM_PINNED;
+	if (test_bit(XFS_LI_FAILED, &lip->li_flags))
+		return xfsaild_resubmit_item(lip, &ailp->ail_buf_list);
 	return lip->li_ops->iop_push(lip, &ailp->ail_buf_list);
 }