xfs: Properly retry failed dquot items in case of error during buffer writeback

Once the inode item writeback errors is already fixed, it's time to fix the same
problem in dquot code.

Although there were no reports of users hitting this bug in dquot code (at least
none I've seen), the bug is there and I was already planning to fix it when the
correct approach to fix the inodes part was decided.

This patch aims to fix the same problem in dquot code, regarding failed buffers
being unable to be resubmitted once they are flush locked.

Tested with the recently test-case sent to fstests list by Hou Tao.
Reviewed-by: NBrian Foster <bfoster@redhat.com>
Signed-off-by: NCarlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: NDarrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: NDarrick J. Wong <darrick.wong@oracle.com>

fs/xfs/xfs_dquot.c

@@ -970,14 +970,22 @@ xfs_qm_dqflush_done(
 	 * holding the lock before removing the dquot from the AIL.
 	 */
 	if ((lip->li_flags & XFS_LI_IN_AIL) &&
-	    lip->li_lsn == qip->qli_flush_lsn) {
+	    ((lip->li_lsn == qip->qli_flush_lsn) ||
+	     (lip->li_flags & XFS_LI_FAILED))) {
 
 		/* xfs_trans_ail_delete() drops the AIL lock. */
 		spin_lock(&ailp->xa_lock);
-		if (lip->li_lsn == qip->qli_flush_lsn)
+		if (lip->li_lsn == qip->qli_flush_lsn) {
 			xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE);
-		else
+		} else {
+			/*
+			 * Clear the failed state since we are about to drop the
+			 * flush lock
+			 */
+			if (lip->li_flags & XFS_LI_FAILED)
+				xfs_clear_li_failed(lip);
 			spin_unlock(&ailp->xa_lock);
+		}
 	}
 
 	/*

fs/xfs/xfs_dquot_item.c

@@ -137,6 +137,26 @@ xfs_qm_dqunpin_wait(
 	wait_event(dqp->q_pinwait, (atomic_read(&dqp->q_pincount) == 0));
 }
 
+/*
+ * Callback used to mark a buffer with XFS_LI_FAILED when items in the buffer
+ * have been failed during writeback
+ *
+ * this informs the AIL that the dquot is already flush locked on the next push,
+ * and acquires a hold on the buffer to ensure that it isn't reclaimed before
+ * dirty data makes it to disk.
+ */
+STATIC void
+xfs_dquot_item_error(
+	struct xfs_log_item	*lip,
+	struct xfs_buf		*bp)
+{
+	struct xfs_dquot	*dqp;
+
+	dqp = DQUOT_ITEM(lip)->qli_dquot;
+	ASSERT(!completion_done(&dqp->q_flush));
+	xfs_set_li_failed(lip, bp);
+}
+
 STATIC uint
 xfs_qm_dquot_logitem_push(
 	struct xfs_log_item	*lip,
@@ -144,13 +164,28 @@ xfs_qm_dquot_logitem_push(
 					      __acquires(&lip->li_ailp->xa_lock)
 {
 	struct xfs_dquot	*dqp = DQUOT_ITEM(lip)->qli_dquot;
-	struct xfs_buf		*bp = NULL;
+	struct xfs_buf		*bp = lip->li_buf;
 	uint			rval = XFS_ITEM_SUCCESS;
 	int			error;
 
 	if (atomic_read(&dqp->q_pincount) > 0)
 		return XFS_ITEM_PINNED;
 
+	/*
+	 * The buffer containing this item failed to be written back
+	 * previously. Resubmit the buffer for IO
+	 */
+	if (lip->li_flags & XFS_LI_FAILED) {
+		if (!xfs_buf_trylock(bp))
+			return XFS_ITEM_LOCKED;
+
+		if (!xfs_buf_resubmit_failed_buffers(bp, lip, buffer_list))
+			rval = XFS_ITEM_FLUSHING;
+
+		xfs_buf_unlock(bp);
+		return rval;
+	}
+
 	if (!xfs_dqlock_nowait(dqp))
 		return XFS_ITEM_LOCKED;
 
@@ -242,7 +277,8 @@ static const struct xfs_item_ops xfs_dquot_item_ops = {
 	.iop_unlock	= xfs_qm_dquot_logitem_unlock,
 	.iop_committed	= xfs_qm_dquot_logitem_committed,
 	.iop_push	= xfs_qm_dquot_logitem_push,
-	.iop_committing = xfs_qm_dquot_logitem_committing
+	.iop_committing = xfs_qm_dquot_logitem_committing,
+	.iop_error	= xfs_dquot_item_error
 };
 
 /*