super: make iterate_supers_type() deletion-safe

iterate_supers_type() drops sb_lock while invoking the callback and keeps
only a passive reference to the current superblock. That reference keeps
the object allocated, but does not keep its s_instances node linked.

After the iterator releases s_umount, final teardown can unlink the current
s_instances node. The iterator then advances through a reinitialized node.
With the current hlist it stops without visiting the remaining superblocks.
The unlink moved from generic_shutdown_super() to kill_super_notify(), but
the cursor lifetime has been unsafe since the helper was introduced.

The CIFS DFS lookup can consequently miss a matching superblock and return
-EINVAL.

Move removal from fs_supers to put_super(), alongside removal from
super_blocks, so a passive reference keeps both list nodes linked. Keep
the filesystem module reference until then, since unlinking s_instances
may touch type->fs_supers.

Make sget_fc() skip SB_DEAD superblocks before invoking test(), and set
SB_DEAD under sb_lock to serialize with those callbacks. This allows
kernfs to free its private information after kill_anon_super() returns.
Keep matching SB_DYING superblocks until SB_DEAD is set so concurrent
mounts still wait for teardown before retrying.

Fixes: 43e15cdbefea ("new helper: iterate_supers_type()")
Reported-by: Karl Mehltretter <kmehltretter@gmail.com>
Closes: https://lore.kernel.org/r/20260903013336.92081-1-kmehltretter@gmail.com
Suggested-by: Jan Kara <jack@suse.cz>
Cc: stable@vger.kernel.org
Tested-by: Karl Mehltretter <kmehltretter@gmail.com>
[kmehltretter: supplied the commit message]
Signed-off-by: Karl Mehltretter <kmehltretter@gmail.com>
Link: https://patch.msgid.link/20260909193034.7467-1-kmehltretter@gmail.com
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>

2 files changed, 21 insertions, 22 deletions

diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index f183a96778b9..a57399021c8b 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -434,8 +434,8 @@ void kernfs_kill_sb(struct super_block *sb)
 	up_write(&root->kernfs_supers_rwsem);
 
 	/*
-	 * Remove the superblock from fs_supers/s_instances
-	 * so we can't find it, before freeing kernfs_super_info.
+	 * Mark the superblock dead so sget_fc() can't find it,
+	 * before freeing kernfs_super_info.
 	 */
 	kill_anon_super(sb);
 	kfree(info);
diff --git a/fs/super.c b/fs/super.c
index 01db6124e409..e41cae9e5c62 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -433,15 +433,19 @@ fail:
 void put_super(struct super_block *s)
 {
 	if (refcount_dec_and_test(&s->s_passive)) {
+		struct file_system_type *type = s->s_type;
 
 		spin_lock(&sb_lock);
 		list_del_init(&s->s_list);
+		hlist_del_init(&s->s_instances);
 		spin_unlock(&sb_lock);
 
 		WARN_ON(s->s_dentry_lru.node);
 		WARN_ON(s->s_inode_lru.node);
 		WARN_ON(s->s_mounts);
 		call_rcu(&s->rcu, destroy_super_rcu);
+		/* The unlink above may touch type->fs_supers, so drop it last. */
+		put_filesystem(type);
 	}
 }
 
@@ -558,17 +562,6 @@ static void kill_super_notify(struct super_block *sb)
 	if (sb->s_flags & SB_DEAD)
 		return;
 
-	/*
-	 * Remove it from @fs_supers so it isn't found by new
-	 * sget_fc() walkers anymore. Any concurrent mounter still
-	 * managing to grab a temporary reference is guaranteed to
-	 * already see SB_DYING and will wait until we notify them about
-	 * SB_DEAD.
-	 */
-	spin_lock(&sb_lock);
-	hlist_del_init(&sb->s_instances);
-	spin_unlock(&sb_lock);
-
 	/* Drop sget_fc()'s claim; a never-registered entry stays with the sb. */
 	if (sb->s_super_dev->sd_dev) {
 		super_dev_put(sb->s_super_dev);
@@ -577,11 +570,15 @@ static void kill_super_notify(struct super_block *sb)
 
 	/*
 	 * Let concurrent mounts know that this thing is really dead.
-	 * We don't need @sb->s_umount here as every concurrent caller
-	 * will see SB_DYING and either discard the superblock or wait
-	 * for SB_DEAD.
+	 * sget_fc() skips SB_DEAD superblocks and calls test() under
+	 * sb_lock, so set it under sb_lock: once we return no test()
+	 * runs on this superblock anymore and none will start. Everyone
+	 * else already saw SB_DYING and either discarded the superblock
+	 * or waits for SB_DEAD.
 	 */
+	spin_lock(&sb_lock);
 	super_wake(sb, SB_DEAD);
+	spin_unlock(&sb_lock);
 }
 
 /**
@@ -608,7 +605,6 @@ void deactivate_locked_super(struct super_block *s)
 		list_lru_destroy(&s->s_dentry_lru);
 		list_lru_destroy(&s->s_inode_lru);
 
-		put_filesystem(fs);
 		put_super(s);
 	} else {
 		super_unlock_excl(s);
@@ -795,12 +791,12 @@ void generic_shutdown_super(struct super_block *sb)
 	}
 	/*
 	 * Broadcast to everyone that grabbed a temporary reference to this
-	 * superblock before we removed it from @fs_supers that the superblock
-	 * is dying. Every walker of @fs_supers outside of sget_fc() will now
-	 * discard this superblock and treat it as dead.
+	 * superblock that it is dying. Every walker of @fs_supers outside
+	 * of sget_fc() will now discard this superblock and treat it as
+	 * dead.
 	 *
-	 * We leave the superblock on @fs_supers so it can be found by
-	 * sget_fc() until we passed sb->kill_sb().
+	 * sget_fc() keeps finding the superblock until SB_DEAD is set, so
+	 * a concurrent mounter waits until we passed sb->kill_sb().
 	 */
 	super_wake(sb, SB_DYING);
 	super_unlock_excl(sb);
@@ -879,6 +875,9 @@ retry:
 	spin_lock(&sb_lock);
 	if (test) {
 		hlist_for_each_entry(old, &fc->fs_type->fs_supers, s_instances) {
+			/* Only unlinked at the last passive reference. */
+			if (super_flags(old, SB_DEAD))
+				continue;
 			if (test(old, fc))
 				goto share_extant_sb;
 		}