1 files changed, 85 insertions, 39 deletions

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 93e955262d07..cd9a5400ba4f 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -222,22 +222,21 @@ xfs_bmap_eof(
  * Count leaf blocks given a range of extent records.  Delayed allocation
  * extents are not counted towards the totals.
  */
-STATIC void
+xfs_extnum_t
 xfs_bmap_count_leaves(
 	struct xfs_ifork	*ifp,
-	xfs_extnum_t		*numrecs,
 	xfs_filblks_t		*count)
 {
-	xfs_extnum_t		i;
-	xfs_extnum_t		nr_exts = xfs_iext_count(ifp);
-
-	for (i = 0; i < nr_exts; i++) {
-		xfs_bmbt_rec_host_t *frp = xfs_iext_get_ext(ifp, i);
-		if (!isnullstartblock(xfs_bmbt_get_startblock(frp))) {
-			(*numrecs)++;
-			*count += xfs_bmbt_get_blockcount(frp);
+	struct xfs_bmbt_irec	got;
+	xfs_extnum_t		numrecs = 0, i = 0;
+
+	while (xfs_iext_get_extent(ifp, i++, &got)) {
+		if (!isnullstartblock(got.br_startblock)) {
+			*count += got.br_blockcount;
+			numrecs++;
 		}
 	}
+	return numrecs;
 }
 
 /*
@@ -370,7 +369,7 @@ xfs_bmap_count_blocks(
 
 	switch (XFS_IFORK_FORMAT(ip, whichfork)) {
 	case XFS_DINODE_FMT_EXTENTS:
-		xfs_bmap_count_leaves(ifp, nextents, count);
+		*nextents = xfs_bmap_count_leaves(ifp, count);
 		return 0;
 	case XFS_DINODE_FMT_BTREE:
 		if (!(ifp->if_flags & XFS_IFEXTENTS)) {
@@ -1136,7 +1135,7 @@ xfs_alloc_file_space(
 		/*
 		 * Complete the transaction
 		 */
-		error = xfs_defer_finish(&tp, &dfops, NULL);
+		error = xfs_defer_finish(&tp, &dfops);
 		if (error)
 			goto error0;
 
@@ -1202,7 +1201,8 @@ xfs_unmap_extent(
 	if (error)
 		goto out_bmap_cancel;
 
-	error = xfs_defer_finish(&tp, &dfops, ip);
+	xfs_defer_ijoin(&dfops, ip);
+	error = xfs_defer_finish(&tp, &dfops);
 	if (error)
 		goto out_bmap_cancel;
 
@@ -1496,7 +1496,7 @@ xfs_shift_file_space(
 		if (error)
 			goto out_bmap_cancel;
 
-		error = xfs_defer_finish(&tp, &dfops, NULL);
+		error = xfs_defer_finish(&tp, &dfops);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -1777,7 +1777,8 @@ xfs_swap_extent_rmap(
 			if (error)
 				goto out_defer;
 
-			error = xfs_defer_finish(tpp, &dfops, ip);
+			xfs_defer_ijoin(&dfops, ip);
+			error = xfs_defer_finish(tpp, &dfops);
 			if (error)
 				goto out_defer;
 
@@ -1840,29 +1841,18 @@ xfs_swap_extent_forks(
 	}
 
 	/*
-	 * Before we've swapped the forks, lets set the owners of the forks
-	 * appropriately. We have to do this as we are demand paging the btree
-	 * buffers, and so the validation done on read will expect the owner
-	 * field to be correctly set. Once we change the owners, we can swap the
-	 * inode forks.
+	 * Btree format (v3) inodes have the inode number stamped in the bmbt
+	 * block headers. We can't start changing the bmbt blocks until the
+	 * inode owner change is logged so recovery does the right thing in the
+	 * event of a crash. Set the owner change log flags now and leave the
+	 * bmbt scan as the last step.
 	 */
 	if (ip->i_d.di_version == 3 &&
-	    ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+	    ip->i_d.di_format == XFS_DINODE_FMT_BTREE)
 		(*target_log_flags) |= XFS_ILOG_DOWNER;
-		error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK,
-					      tip->i_ino, NULL);
-		if (error)
-			return error;
-	}
-
 	if (tip->i_d.di_version == 3 &&
-	    tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+	    tip->i_d.di_format == XFS_DINODE_FMT_BTREE)
 		(*src_log_flags) |= XFS_ILOG_DOWNER;
-		error = xfs_bmbt_change_owner(tp, tip, XFS_DATA_FORK,
-					      ip->i_ino, NULL);
-		if (error)
-			return error;
-	}
 
 	/*
 	 * Swap the data forks of the inodes
@@ -1940,6 +1930,48 @@ xfs_swap_extent_forks(
 	return 0;
 }
 
+/*
+ * Fix up the owners of the bmbt blocks to refer to the current inode. The
+ * change owner scan attempts to order all modified buffers in the current
+ * transaction. In the event of ordered buffer failure, the offending buffer is
+ * physically logged as a fallback and the scan returns -EAGAIN. We must roll
+ * the transaction in this case to replenish the fallback log reservation and
+ * restart the scan. This process repeats until the scan completes.
+ */
+static int
+xfs_swap_change_owner(
+	struct xfs_trans	**tpp,
+	struct xfs_inode	*ip,
+	struct xfs_inode	*tmpip)
+{
+	int			error;
+	struct xfs_trans	*tp = *tpp;
+
+	do {
+		error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK, ip->i_ino,
+					      NULL);
+		/* success or fatal error */
+		if (error != -EAGAIN)
+			break;
+
+		error = xfs_trans_roll(tpp);
+		if (error)
+			break;
+		tp = *tpp;
+
+		/*
+		 * Redirty both inodes so they can relog and keep the log tail
+		 * moving forward.
+		 */
+		xfs_trans_ijoin(tp, ip, 0);
+		xfs_trans_ijoin(tp, tmpip, 0);
+		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+		xfs_trans_log_inode(tp, tmpip, XFS_ILOG_CORE);
+	} while (true);
+
+	return error;
+}
+
 int
 xfs_swap_extents(
 	struct xfs_inode	*ip,	/* target inode */
@@ -1954,7 +1986,7 @@ xfs_swap_extents(
 	int			lock_flags;
 	struct xfs_ifork	*cowfp;
 	uint64_t		f;
-	int			resblks;
+	int			resblks = 0;
 
 	/*
 	 * Lock the inodes against other IO, page faults and truncate to
@@ -2002,11 +2034,8 @@ xfs_swap_extents(
 			  XFS_SWAP_RMAP_SPACE_RES(mp,
 				XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK),
 				XFS_DATA_FORK);
-		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks,
-				0, 0, &tp);
-	} else
-		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0,
-				0, 0, &tp);
+	}
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
 	if (error)
 		goto out_unlock;
 
@@ -2092,6 +2121,23 @@ xfs_swap_extents(
 	xfs_trans_log_inode(tp, tip, target_log_flags);
 
 	/*
+	 * The extent forks have been swapped, but crc=1,rmapbt=0 filesystems
+	 * have inode number owner values in the bmbt blocks that still refer to
+	 * the old inode. Scan each bmbt to fix up the owner values with the
+	 * inode number of the current inode.
+	 */
+	if (src_log_flags & XFS_ILOG_DOWNER) {
+		error = xfs_swap_change_owner(&tp, ip, tip);
+		if (error)
+			goto out_trans_cancel;
+	}
+	if (target_log_flags & XFS_ILOG_DOWNER) {
+		error = xfs_swap_change_owner(&tp, tip, ip);
+		if (error)
+			goto out_trans_cancel;
+	}
+
+	/*
 	 * If this is a synchronous mount, make sure that the
 	 * transaction goes to disk before returning to the user.
 	 */