Merge tag 'fix-iunlink-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 the last iunlink item

It turns out that there are some serious bugs in how xfs handles the
unlinked inode lists.  Way back before 4.14, there was a bug where a ro
mount of a dirty filesystem would recover the log bug neglect to purge
the unlinked list.  This leads to clean unmounted filesystems with
unlinked inodes.  Starting around 5.15, we also converted the codebase
to maintain a doubly-linked incore unlinked list.  However, we never
provided the ability to load the incore list from disk.  If someone
tries to allocate an O_TMPFILE file on a clean fs with a pre-existing
unlinked list or even deletes a file, the code will fail and the fs
shuts down.

This first part of the correction effort adds the ability to load the
first inode in the bucket when unlinking a file; and to load the next
inode in the list when inactivating (freeing) an inode.

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

* tag 'fix-iunlink-6.6_2023-09-12' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux:
  xfs: load uncached unlinked inodes into memory on demand

2 files changed, 100 insertions, 5 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index f7f8292347abd6..7b11059067f751 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1828,12 +1828,17 @@ xfs_iunlink_lookup(
 
 	rcu_read_lock();
 	ip = radix_tree_lookup(&pag->pag_ici_root, agino);
+	if (!ip) {
+		/* Caller can handle inode not being in memory. */
+		rcu_read_unlock();
+		return NULL;
+	}
 
 	/*
-	 * Inode not in memory or in RCU freeing limbo should not happen.
-	 * Warn about this and let the caller handle the failure.
+	 * Inode in RCU freeing limbo should not happen.  Warn about this and
+	 * let the caller handle the failure.
 	 */
-	if (WARN_ON_ONCE(!ip || !ip->i_ino)) {
+	if (WARN_ON_ONCE(!ip->i_ino)) {
 		rcu_read_unlock();
 		return NULL;
 	}
@@ -1842,7 +1847,10 @@ xfs_iunlink_lookup(
 	return ip;
 }
 
-/* Update the prev pointer of the next agino. */
+/*
+ * Update the prev pointer of the next agino.  Returns -ENOLINK if the inode
+ * is not in cache.
+ */
 static int
 xfs_iunlink_update_backref(
 	struct xfs_perag	*pag,
@@ -1857,7 +1865,8 @@ xfs_iunlink_update_backref(
 
 	ip = xfs_iunlink_lookup(pag, next_agino);
 	if (!ip)
-		return -EFSCORRUPTED;
+		return -ENOLINK;
+
 	ip->i_prev_unlinked = prev_agino;
 	return 0;
 }
@@ -1901,6 +1910,62 @@ xfs_iunlink_update_bucket(
 	return 0;
 }
 
+/*
+ * Load the inode @next_agino into the cache and set its prev_unlinked pointer
+ * to @prev_agino.  Caller must hold the AGI to synchronize with other changes
+ * to the unlinked list.
+ */
+STATIC int
+xfs_iunlink_reload_next(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*agibp,
+	xfs_agino_t		prev_agino,
+	xfs_agino_t		next_agino)
+{
+	struct xfs_perag	*pag = agibp->b_pag;
+	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_inode	*next_ip = NULL;
+	xfs_ino_t		ino;
+	int			error;
+
+	ASSERT(next_agino != NULLAGINO);
+
+#ifdef DEBUG
+	rcu_read_lock();
+	next_ip = radix_tree_lookup(&pag->pag_ici_root, next_agino);
+	ASSERT(next_ip == NULL);
+	rcu_read_unlock();
+#endif
+
+	xfs_info_ratelimited(mp,
+ "Found unrecovered unlinked inode 0x%x in AG 0x%x.  Initiating recovery.",
+			next_agino, pag->pag_agno);
+
+	/*
+	 * Use an untrusted lookup just to be cautious in case the AGI has been
+	 * corrupted and now points at a free inode.  That shouldn't happen,
+	 * but we'd rather shut down now since we're already running in a weird
+	 * situation.
+	 */
+	ino = XFS_AGINO_TO_INO(mp, pag->pag_agno, next_agino);
+	error = xfs_iget(mp, tp, ino, XFS_IGET_UNTRUSTED, 0, &next_ip);
+	if (error)
+		return error;
+
+	/* If this is not an unlinked inode, something is very wrong. */
+	if (VFS_I(next_ip)->i_nlink != 0) {
+		error = -EFSCORRUPTED;
+		goto rele;
+	}
+
+	next_ip->i_prev_unlinked = prev_agino;
+	trace_xfs_iunlink_reload_next(next_ip);
+rele:
+	ASSERT(!(VFS_I(next_ip)->i_state & I_DONTCACHE));
+	xfs_irele(next_ip);
+	return error;
+}
+
 static int
 xfs_iunlink_insert_inode(
 	struct xfs_trans	*tp,
@@ -1932,6 +1997,8 @@ xfs_iunlink_insert_inode(
 	 * inode.
 	 */
 	error = xfs_iunlink_update_backref(pag, agino, next_agino);
+	if (error == -ENOLINK)
+		error = xfs_iunlink_reload_next(tp, agibp, agino, next_agino);
 	if (error)
 		return error;
 
@@ -2026,6 +2093,9 @@ xfs_iunlink_remove_inode(
 	 */
 	error = xfs_iunlink_update_backref(pag, ip->i_prev_unlinked,
 			ip->i_next_unlinked);
+	if (error == -ENOLINK)
+		error = xfs_iunlink_reload_next(tp, agibp, ip->i_prev_unlinked,
+				ip->i_next_unlinked);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 902c7f67a117f4..7b1cb5d59d8fb1 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3824,6 +3824,31 @@ TRACE_EVENT(xfs_iunlink_update_dinode,
 		  __entry->new_ptr)
 );
 
+TRACE_EVENT(xfs_iunlink_reload_next,
+	TP_PROTO(struct xfs_inode *ip),
+	TP_ARGS(ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agino_t, agino)
+		__field(xfs_agino_t, prev_agino)
+		__field(xfs_agino_t, next_agino)
+	),
+	TP_fast_assign(
+		__entry->dev = ip->i_mount->m_super->s_dev;
+		__entry->agno = XFS_INO_TO_AGNO(ip->i_mount, ip->i_ino);
+		__entry->agino = XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino);
+		__entry->prev_agino = ip->i_prev_unlinked;
+		__entry->next_agino = ip->i_next_unlinked;
+	),
+	TP_printk("dev %d:%d agno 0x%x agino 0x%x prev_unlinked 0x%x next_unlinked 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->agno,
+		  __entry->agino,
+		  __entry->prev_agino,
+		  __entry->next_agino)
+);
+
 DECLARE_EVENT_CLASS(xfs_ag_inode_class,
 	TP_PROTO(struct xfs_inode *ip),
 	TP_ARGS(ip),