fs: kill MNT_ONRB

Move mnt->mnt_node into the union with mnt->mnt_rcu and mnt->mnt_llist
instead of keeping it with mnt->mnt_list. This allows us to use
RB_CLEAR_NODE(&mnt->mnt_node) in umount_tree() as well as
list_empty(&mnt->mnt_node). That in turn allows us to remove MNT_ONRB.

This also fixes the bug reported in [1] where seemingly MNT_ONRB wasn't
set in @mnt->mnt_flags even though the mount was present in the mount
rbtree of the mount namespace.

The root cause is the following race. When a btrfs subvolume is mounted
a temporary mount is created:

btrfs_get_tree_subvol()
{
        mnt = fc_mount()
        // Register the newly allocated mount with sb->mounts:
        lock_mount_hash();
        list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts);
        unlock_mount_hash();
}

and registered on sb->s_mounts. Later it is added to an anonymous mount
namespace via mount_subvol():

-> mount_subvol()
   -> mount_subtree()
      -> alloc_mnt_ns()
         mnt_add_to_ns()
         vfs_path_lookup()
         put_mnt_ns()

The mnt_add_to_ns() call raises MNT_ONRB in @mnt->mnt_flags. If someone
concurrently does a ro remount:

reconfigure_super()
-> sb_prepare_remount_readonly()
   {
           list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) {
   }

all mounts registered in sb->s_mounts are visited and first
MNT_WRITE_HOLD is raised, then MNT_READONLY is raised, and finally
MNT_WRITE_HOLD is removed again.

The flag modification for MNT_WRITE_HOLD/MNT_READONLY and MNT_ONRB race
so MNT_ONRB might be lost.

Fixes: 2eea9ce4310d ("mounts: keep list of mounts in an rbtree")
Cc: <stable@kernel.org> # v6.8+
Link: https://lore.kernel.org/r/20241215-vfs-6-14-mount-work-v1-1-fd55922c4af8@kernel.org
Link: https://lore.kernel.org/r/ec6784ed-8722-4695-980a-4400d4e7bd1a@gmx.com [1]
Signed-off-by: Christian Brauner <brauner@kernel.org>

1 files changed, 9 insertions, 6 deletions

diff --git a/fs/mount.h b/fs/mount.h
index 185fc56afc13..179f690a0c72 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -38,6 +38,7 @@ struct mount {
 	struct dentry *mnt_mountpoint;
 	struct vfsmount mnt;
 	union {
+		struct rb_node mnt_node; /* node in the ns->mounts rbtree */
 		struct rcu_head mnt_rcu;
 		struct llist_node mnt_llist;
 	};
@@ -51,10 +52,7 @@ struct mount {
 	struct list_head mnt_child;	/* and going through their mnt_child */
 	struct list_head mnt_instance;	/* mount instance on sb->s_mounts */
 	const char *mnt_devname;	/* Name of device e.g. /dev/dsk/hda1 */
-	union {
-		struct rb_node mnt_node;	/* Under ns->mounts */
-		struct list_head mnt_list;
-	};
+	struct list_head mnt_list;
 	struct list_head mnt_expire;	/* link in fs-specific expiry list */
 	struct list_head mnt_share;	/* circular list of shared mounts */
 	struct list_head mnt_slave_list;/* list of slave mounts */
@@ -145,11 +143,16 @@ static inline bool is_anon_ns(struct mnt_namespace *ns)
 	return ns->seq == 0;
 }
 
+static inline bool mnt_ns_attached(const struct mount *mnt)
+{
+	return !RB_EMPTY_NODE(&mnt->mnt_node);
+}
+
 static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list)
 {
-	WARN_ON(!(mnt->mnt.mnt_flags & MNT_ONRB));
-	mnt->mnt.mnt_flags &= ~MNT_ONRB;
+	WARN_ON(!mnt_ns_attached(mnt));
 	rb_erase(&mnt->mnt_node, &mnt->mnt_ns->mounts);
+	RB_CLEAR_NODE(&mnt->mnt_node);
 	list_add_tail(&mnt->mnt_list, dt_list);
 }