summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorDave Chinner <dchinner@redhat.com>2022-04-21 08:45:16 +1000
committerDave Chinner <david@fromorbit.com>2022-04-21 08:45:16 +1000
commit9a5280b312e2e7898b6397b2ca3cfd03f67d7be1 (patch)
tree84fb79f27e7a84457ab82013e1e13c7d29d7bfc2 /fs
parentd65a92de4383e54b920ba11f333032b0ea5e4174 (diff)
downloadlinux-9a5280b312e2e7898b6397b2ca3cfd03f67d7be1.tar.gz
linux-9a5280b312e2e7898b6397b2ca3cfd03f67d7be1.tar.bz2
linux-9a5280b312e2e7898b6397b2ca3cfd03f67d7be1.zip
xfs: reorder iunlink remove operation in xfs_ifree
The O_TMPFILE creation implementation creates a specific order of operations for inode allocation/freeing and unlinked list modification. Currently both are serialised by the AGI, so the order doesn't strictly matter as long as the are both in the same transaction. However, if we want to move the unlinked list insertions largely out from under the AGI lock, then we have to be concerned about the order in which we do unlinked list modification operations. O_TMPFILE creation tells us this order is inode allocation/free, then unlinked list modification. Change xfs_ifree() to use this same ordering on unlinked list removal. This way we always guarantee that when we enter the iunlinked list removal code from this path, we already have the AGI locked and we don't have to worry about lock nesting AGI reads inside unlink list locks because it's already locked and attached to the transaction. We can do this safely as the inode freeing and unlinked list removal are done in the same transaction and hence are atomic operations with respect to log recovery. Reported-by: Frank Hofmann <fhofmann@cloudflare.com> Fixes: 298f7bec503f ("xfs: pin inode backing buffer to the inode log item") Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
Diffstat (limited to 'fs')
-rw-r--r--fs/xfs/xfs_inode.c24
1 files changed, 13 insertions, 11 deletions
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 9de6205fe134..39ae53efb3ab 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2594,14 +2594,13 @@ xfs_ifree_cluster(
}
/*
- * This is called to return an inode to the inode free list.
- * The inode should already be truncated to 0 length and have
- * no pages associated with it. This routine also assumes that
- * the inode is already a part of the transaction.
+ * This is called to return an inode to the inode free list. The inode should
+ * already be truncated to 0 length and have no pages associated with it. This
+ * routine also assumes that the inode is already a part of the transaction.
*
- * The on-disk copy of the inode will have been added to the list
- * of unlinked inodes in the AGI. We need to remove the inode from
- * that list atomically with respect to freeing it here.
+ * The on-disk copy of the inode will have been added to the list of unlinked
+ * inodes in the AGI. We need to remove the inode from that list atomically with
+ * respect to freeing it here.
*/
int
xfs_ifree(
@@ -2623,13 +2622,16 @@ xfs_ifree(
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
/*
- * Pull the on-disk inode from the AGI unlinked list.
+ * Free the inode first so that we guarantee that the AGI lock is going
+ * to be taken before we remove the inode from the unlinked list. This
+ * makes the AGI lock -> unlinked list modification order the same as
+ * used in O_TMPFILE creation.
*/
- error = xfs_iunlink_remove(tp, pag, ip);
+ error = xfs_difree(tp, pag, ip->i_ino, &xic);
if (error)
- goto out;
+ return error;
- error = xfs_difree(tp, pag, ip->i_ino, &xic);
+ error = xfs_iunlink_remove(tp, pag, ip);
if (error)
goto out;