Merge tag 'fix-iunlink-list-6.6_2023-09-12' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into xfs-6.6-fixesA

xfs: reload entire iunlink lists

This is the second part of correcting XFS to reload the incore unlinked
inode list from the ondisk contents.  Whereas part one tackled failures
from regular filesystem calls, this part takes on the problem of needing
to reload the entire incore unlinked inode list on account of somebody
loading an inode that's in the /middle/ of an unlinked list.  This
happens during quotacheck, bulkstat, or even opening a file by handle.

In this case we don't know the length of the list that we're reloading,
so we don't want to create a new unbounded memory load while holding
resources locked.  Instead, we'll target UNTRUSTED iget calls to reload
the entire bucket.

Note that this changes the definition of the incore unlinked inode list
slightly -- i_prev_unlinked == 0 now means "not on the incore list".

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>

* tag 'fix-iunlink-list-6.6_2023-09-12' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux:
  xfs: make inode unlinked bucket recovery work with quotacheck
  xfs: reload entire unlinked bucket lists
  xfs: use i_prev_unlinked to distinguish inodes that are not on the unlinked list

1 files changed, 111 insertions, 4 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 7b11059067f7..f94f7b374041 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1742,9 +1742,13 @@ xfs_inactive(
 	     ip->i_df.if_nextents > 0 || ip->i_delayed_blks > 0))
 		truncate = 1;
 
-	error = xfs_qm_dqattach(ip);
-	if (error)
-		goto out;
+	if (xfs_iflags_test(ip, XFS_IQUOTAUNCHECKED)) {
+		xfs_qm_dqdetach(ip);
+	} else {
+		error = xfs_qm_dqattach(ip);
+		if (error)
+			goto out;
+	}
 
 	if (S_ISLNK(VFS_I(ip)->i_mode))
 		error = xfs_inactive_symlink(ip);
@@ -1962,6 +1966,8 @@ xfs_iunlink_reload_next(
 	trace_xfs_iunlink_reload_next(next_ip);
 rele:
 	ASSERT(!(VFS_I(next_ip)->i_state & I_DONTCACHE));
+	if (xfs_is_quotacheck_running(mp) && next_ip)
+		xfs_iflags_set(next_ip, XFS_IQUOTAUNCHECKED);
 	xfs_irele(next_ip);
 	return error;
 }
@@ -2014,6 +2020,7 @@ xfs_iunlink_insert_inode(
 	}
 
 	/* Point the head of the list to point to this inode. */
+	ip->i_prev_unlinked = NULLAGINO;
 	return xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, agino);
 }
 
@@ -2116,7 +2123,7 @@ xfs_iunlink_remove_inode(
 	}
 
 	ip->i_next_unlinked = NULLAGINO;
-	ip->i_prev_unlinked = NULLAGINO;
+	ip->i_prev_unlinked = 0;
 	return error;
 }
 
@@ -3605,3 +3612,103 @@ xfs_iunlock2_io_mmap(
 	if (ip1 != ip2)
 		inode_unlock(VFS_I(ip1));
 }
+
+/*
+ * Reload the incore inode list for this inode.  Caller should ensure that
+ * the link count cannot change, either by taking ILOCK_SHARED or otherwise
+ * preventing other threads from executing.
+ */
+int
+xfs_inode_reload_unlinked_bucket(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_buf		*agibp;
+	struct xfs_agi		*agi;
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
+	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
+	xfs_agino_t		prev_agino, next_agino;
+	unsigned int		bucket;
+	bool			foundit = false;
+	int			error;
+
+	/* Grab the first inode in the list */
+	pag = xfs_perag_get(mp, agno);
+	error = xfs_ialloc_read_agi(pag, tp, &agibp);
+	xfs_perag_put(pag);
+	if (error)
+		return error;
+
+	bucket = agino % XFS_AGI_UNLINKED_BUCKETS;
+	agi = agibp->b_addr;
+
+	trace_xfs_inode_reload_unlinked_bucket(ip);
+
+	xfs_info_ratelimited(mp,
+ "Found unrecovered unlinked inode 0x%x in AG 0x%x.  Initiating list recovery.",
+			agino, agno);
+
+	prev_agino = NULLAGINO;
+	next_agino = be32_to_cpu(agi->agi_unlinked[bucket]);
+	while (next_agino != NULLAGINO) {
+		struct xfs_inode	*next_ip = NULL;
+
+		if (next_agino == agino) {
+			/* Found this inode, set its backlink. */
+			next_ip = ip;
+			next_ip->i_prev_unlinked = prev_agino;
+			foundit = true;
+		}
+		if (!next_ip) {
+			/* Inode already in memory. */
+			next_ip = xfs_iunlink_lookup(pag, next_agino);
+		}
+		if (!next_ip) {
+			/* Inode not in memory, reload. */
+			error = xfs_iunlink_reload_next(tp, agibp, prev_agino,
+					next_agino);
+			if (error)
+				break;
+
+			next_ip = xfs_iunlink_lookup(pag, next_agino);
+		}
+		if (!next_ip) {
+			/* No incore inode at all?  We reloaded it... */
+			ASSERT(next_ip != NULL);
+			error = -EFSCORRUPTED;
+			break;
+		}
+
+		prev_agino = next_agino;
+		next_agino = next_ip->i_next_unlinked;
+	}
+
+	xfs_trans_brelse(tp, agibp);
+	/* Should have found this inode somewhere in the iunlinked bucket. */
+	if (!error && !foundit)
+		error = -EFSCORRUPTED;
+	return error;
+}
+
+/* Decide if this inode is missing its unlinked list and reload it. */
+int
+xfs_inode_reload_unlinked(
+	struct xfs_inode	*ip)
+{
+	struct xfs_trans	*tp;
+	int			error;
+
+	error = xfs_trans_alloc_empty(ip->i_mount, &tp);
+	if (error)
+		return error;
+
+	xfs_ilock(ip, XFS_ILOCK_SHARED);
+	if (xfs_inode_unlinked_incomplete(ip))
+		error = xfs_inode_reload_unlinked_bucket(tp, ip);
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	xfs_trans_cancel(tp);
+
+	return error;
+}