[PATCH 42/47] xfs: relog dirty buffers during swapext bmbt owner change

[Christoph Hellwig <hch@lst.de>]

From: Brian Foster <bfoster@redhat.com>

commit 2dd3d709fc4338681a3aa61658122fa8faa5a437 upstream.

The owner change bmbt scan that occurs during extent swap operations
does not handle ordered buffer failures. Buffers that cannot be
marked ordered must be physically logged so previously dirty ranges
of the buffer can be relogged in the transaction.

Since the bmbt scan may need to process and potentially log a large
number of blocks, we can't expect to complete this operation in a
single transaction. Update extent swap to use a permanent
transaction with enough log reservation to physically log a buffer.
Update the bmbt scan to physically log any buffers that cannot be
ordered and to terminate the scan with -EAGAIN. On -EAGAIN, the
caller rolls the transaction and restarts the scan. Finally, update
the bmbt scan helper function to skip bmbt blocks that already match
the expected owner so they are not reprocessed after scan restarts.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
[darrick: fix the xfs_trans_roll call]
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_btree.c | 26 ++++++++++++++-------
 fs/xfs/xfs_bmap_util.c    | 59 ++++++++++++++++++++++++++++++++++++++---------
 2 files changed, 66 insertions(+), 19 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 1df747fadc3a..4ad1e214b1b2 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -4435,10 +4435,15 @@ xfs_btree_block_change_owner(
 
 	/* modify the owner */
 	block = xfs_btree_get_block(cur, level, &bp);
-	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		if (block->bb_u.l.bb_owner == cpu_to_be64(bbcoi->new_owner))
+			return 0;
 		block->bb_u.l.bb_owner = cpu_to_be64(bbcoi->new_owner);
-	else
+	} else {
+		if (block->bb_u.s.bb_owner == cpu_to_be32(bbcoi->new_owner))
+			return 0;
 		block->bb_u.s.bb_owner = cpu_to_be32(bbcoi->new_owner);
+	}
 
 	/*
 	 * If the block is a root block hosted in an inode, we might not have a
@@ -4447,14 +4452,19 @@ xfs_btree_block_change_owner(
 	 * block is formatted into the on-disk inode fork. We still change it,
 	 * though, so everything is consistent in memory.
 	 */
-	if (bp) {
-		if (cur->bc_tp)
-			xfs_trans_ordered_buf(cur->bc_tp, bp);
-		else
-			xfs_buf_delwri_queue(bp, bbcoi->buffer_list);
-	} else {
+	if (!bp) {
 		ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE);
 		ASSERT(level == cur->bc_nlevels - 1);
+		return 0;
+	}
+
+	if (cur->bc_tp) {
+		if (!xfs_trans_ordered_buf(cur->bc_tp, bp)) {
+			xfs_btree_log_block(cur, bp, XFS_BB_OWNER);
+			return -EAGAIN;
+		}
+	} else {
+		xfs_buf_delwri_queue(bp, bbcoi->buffer_list);
 	}
 
 	return 0;
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 15cd36f29fc4..5ffefac081f7 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1914,6 +1914,48 @@ 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, NULL);
+		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 */
@@ -1927,8 +1969,8 @@ xfs_swap_extents(
 	int			error = 0;
 	int			lock_flags;
 	struct xfs_ifork	*cowfp;
-	__uint64_t		f;
-	int			resblks;
+	uint64_t		f;
+	int			resblks = 0;
 
 	/*
 	 * Lock the inodes against other IO, page faults and truncate to
@@ -1976,11 +2018,8 @@ 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;
 
@@ -2072,14 +2111,12 @@ xfs_swap_extents(
 	 * inode number of the current inode.
 	 */
 	if (src_log_flags & XFS_ILOG_DOWNER) {
-		error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK,
-					      ip->i_ino, NULL);
+		error = xfs_swap_change_owner(&tp, ip, tip);
 		if (error)
 			goto out_trans_cancel;
 	}
 	if (target_log_flags & XFS_ILOG_DOWNER) {
-		error = xfs_bmbt_change_owner(tp, tip, XFS_DATA_FORK,
-					      tip->i_ino, NULL);
+		error = xfs_swap_change_owner(&tp, tip, ip);
 		if (error)
 			goto out_trans_cancel;
 	}
-- 
2.14.1