summaryrefslogtreecommitdiff
path: root/fs/xfs
diff options
context:
space:
mode:
authorBrian Foster <bfoster@redhat.com>2017-09-17 14:07:05 -0700
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2017-09-20 08:20:01 +0200
commita51e3e2cf3cbb306faa16784fd4f1791ee304816 (patch)
tree6aec4f4c6efa575eed582a9d8f38da33a39dafcc /fs/xfs
parentf9e583edf1a71b7b40d5c5c492319a07ebe82d71 (diff)
xfs: move bmbt owner change to last step of extent swap
commit 6fb10d6d22094bc4062f92b9ccbcee2f54033d04 upstream. The extent swap operation currently resets bmbt block owners before the inode forks are swapped. The bmbt buffers are marked as ordered so they do not have to be physically logged in the transaction. This use of ordered buffers is not safe as bmbt buffers may have been previously physically logged. The bmbt owner change algorithm needs to be updated to physically log buffers that are already dirty when/if they are encountered. This means that an extent swap will eventually require multiple rolling transactions to handle large btrees. In addition, all inode related changes must be logged before the bmbt owner change scan begins and can roll the transaction for the first time to preserve fs consistency via log recovery. In preparation for such fixes to the bmbt owner change algorithm, refactor the bmbt scan out of the extent fork swap code to the last operation before the transaction is committed. Update xfs_swap_extent_forks() to only set the inode log flags when an owner change scan is necessary. Update xfs_swap_extents() to trigger the owner change based on the inode log flags. Note that since the owner change now occurs after the extent fork swap, the inode btrees must be fixed up with the inode number of the current inode (similar to log recovery). Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'fs/xfs')
-rw-r--r--fs/xfs/xfs_bmap_util.c44
1 files changed, 26 insertions, 18 deletions
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 87b495e2f15a..15cd36f29fc4 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1825,29 +1825,18 @@ 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
@@ -2077,6 +2066,25 @@ 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_bmbt_change_owner(tp, ip, XFS_DATA_FORK,
+ ip->i_ino, NULL);
+ 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);
+ 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.
*/