summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_bmap_item.c
diff options
context:
space:
mode:
authorDarrick J. Wong <darrick.wong@oracle.com>2020-09-25 17:39:37 -0700
committerDarrick J. Wong <darrick.wong@oracle.com>2020-10-07 08:40:28 -0700
commite6fff81e487089e47358a028526a9f63cdbcd503 (patch)
treeac399fe6c365d17d7f631c4ac79f775c3280f805 /fs/xfs/xfs_bmap_item.c
parent901219bb25076ec0c43824dd2f3daa8c63a89184 (diff)
xfs: proper replay of deferred ops queued during log recovery
When we replay unfinished intent items that have been recovered from the log, it's possible that the replay will cause the creation of more deferred work items. As outlined in commit 509955823cc9c ("xfs: log recovery should replay deferred ops in order"), later work items have an implicit ordering dependency on earlier work items. Therefore, recovery must replay the items (both recovered and created) in the same order that they would have been during normal operation. For log recovery, we enforce this ordering by using an empty transaction to collect deferred ops that get created in the process of recovering a log intent item to prevent them from being committed before the rest of the recovered intent items. After we finish committing all the recovered log items, we allocate a transaction with an enormous block reservation, splice our huge list of created deferred ops into that transaction, and commit it, thereby finishing all those ops. This is /really/ hokey -- it's the one place in XFS where we allow nested transactions; the splicing of the defer ops list is is inelegant and has to be done twice per recovery function; and the broken way we handle inode pointers and block reservations cause subtle use-after-free and allocator problems that will be fixed by this patch and the two patches after it. Therefore, replace the hokey empty transaction with a structure designed to capture each chain of deferred ops that are created as part of recovering a single unfinished log intent. Finally, refactor the loop that replays those chains to do so using one transaction per chain. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de>
Diffstat (limited to 'fs/xfs/xfs_bmap_item.c')
-rw-r--r--fs/xfs/xfs_bmap_item.c16
1 files changed, 4 insertions, 12 deletions
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index b04ebcd78316..126df48dae5f 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -424,13 +424,13 @@ const struct xfs_defer_op_type xfs_bmap_update_defer_type = {
STATIC int
xfs_bui_item_recover(
struct xfs_log_item *lip,
- struct xfs_trans *parent_tp)
+ struct list_head *capture_list)
{
struct xfs_bmbt_irec irec;
struct xfs_bui_log_item *buip = BUI_ITEM(lip);
struct xfs_trans *tp;
struct xfs_inode *ip = NULL;
- struct xfs_mount *mp = parent_tp->t_mountp;
+ struct xfs_mount *mp = lip->li_mountp;
struct xfs_map_extent *bmap;
struct xfs_bud_log_item *budp;
xfs_fsblock_t startblock_fsb;
@@ -478,12 +478,7 @@ xfs_bui_item_recover(
XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp);
if (error)
return error;
- /*
- * Recovery stashes all deferred ops during intent processing and
- * finishes them on completion. Transfer current dfops state to this
- * transaction and transfer the result back before we return.
- */
- xfs_defer_move(tp, parent_tp);
+
budp = xfs_trans_get_bud(tp, buip);
/* Grab the inode. */
@@ -531,15 +526,12 @@ xfs_bui_item_recover(
xfs_bmap_unmap_extent(tp, ip, &irec);
}
- xfs_defer_capture(parent_tp, tp);
- error = xfs_trans_commit(tp);
+ error = xfs_defer_ops_capture_and_commit(tp, capture_list);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_irele(ip);
-
return error;
err_inode:
- xfs_defer_move(parent_tp, tp);
xfs_trans_cancel(tp);
if (ip) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);