xfs: add in-memory iunlink log item

Now that we have a clean operation to update the di_next_unlinked
field of inode cluster buffers, we can easily defer this operation
to transaction commit time so we can order the inode cluster buffer
locking consistently.

To do this, we introduce a new in-memory log item to track the
unlinked list item modification that we are going to make. This
follows the same observations as the in-memory double linked list
used to track unlinked inodes in that the inodes on the list are
pinned in memory and cannot go away, and hence we can simply
reference them for the duration of the transaction without needing
to take active references or pin them or look them up.

This allows us to pass the xfs_inode to the transaction commit code
along with the modification to be made, and then order the logged
modifications via the ->iop_sort and ->iop_precommit operations
for the new log item type. As this is an in-memory log item, it
doesn't have formatting, CIL or AIL operational hooks - it exists
purely to run the inode unlink modifications and is then removed
from the transaction item list and freed once the precommit
operation has run.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>

1 files changed, 1 insertions, 63 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 515878399dda..ace537a17d0d 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -20,6 +20,7 @@
 #include "xfs_trans.h"
 #include "xfs_buf_item.h"
 #include "xfs_inode_item.h"
+#include "xfs_iunlink_item.h"
 #include "xfs_ialloc.h"
 #include "xfs_bmap.h"
 #include "xfs_bmap_util.h"
@@ -1905,69 +1906,6 @@ xfs_iunlink_update_bucket(
 	return 0;
 }
 
-/* Set an in-core inode's unlinked pointer and return the old value. */
-static int
-xfs_iunlink_log_inode(
-	struct xfs_trans	*tp,
-	struct xfs_inode	*ip,
-	struct xfs_perag	*pag,
-	xfs_agino_t		next_agino)
-{
-	struct xfs_mount	*mp = tp->t_mountp;
-	struct xfs_dinode	*dip;
-	struct xfs_buf		*ibp;
-	xfs_agino_t		old_value;
-	int			offset;
-	int			error;
-
-	ASSERT(xfs_verify_agino_or_null(pag, next_agino));
-
-	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &ibp);
-	if (error)
-		return error;
-	dip = xfs_buf_offset(ibp, ip->i_imap.im_boffset);
-
-	/* Make sure the old pointer isn't garbage. */
-	old_value = be32_to_cpu(dip->di_next_unlinked);
-	if (old_value != ip->i_next_unlinked ||
-	    !xfs_verify_agino_or_null(pag, old_value)) {
-		xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip,
-				sizeof(*dip), __this_address);
-		error = -EFSCORRUPTED;
-		goto out;
-	}
-
-	/*
-	 * Since we're updating a linked list, we should never find that the
-	 * current pointer is the same as the new value, unless we're
-	 * terminating the list.
-	 */
-	if (old_value == next_agino) {
-		if (next_agino != NULLAGINO) {
-			xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__,
-					dip, sizeof(*dip), __this_address);
-			error = -EFSCORRUPTED;
-		}
-		goto out;
-	}
-
-	trace_xfs_iunlink_update_dinode(mp, pag->pag_agno,
-			XFS_INO_TO_AGINO(mp, ip->i_ino),
-			be32_to_cpu(dip->di_next_unlinked), next_agino);
-
-	dip->di_next_unlinked = cpu_to_be32(next_agino);
-	offset = ip->i_imap.im_boffset +
-			offsetof(struct xfs_dinode, di_next_unlinked);
-
-	xfs_dinode_calc_crc(mp, dip);
-	xfs_trans_inode_buf(tp, ibp);
-	xfs_trans_log_buf(tp, ibp, offset, offset + sizeof(xfs_agino_t) - 1);
-	return 0;
-out:
-	xfs_trans_brelse(tp, ibp);
-	return error;
-}
-
 static int
 xfs_iunlink_insert_inode(
 	struct xfs_trans	*tp,