Merge tag 'pull-mount' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs mount updates from Al Viro: - mount hash conflicts rudiments are gone now - we do not allow multiple mounts with the same parent/mountpoint to be hashed at the same time. - 'struct mount' changes: - mnt_umounting is gone - mnt_slave_list/mnt_slave is an hlist now - overmounts are kept track of by explicit pointer in mount - a bunch of flags moved out of mnt_flags to a new field, with only namespace_sem for protection - mnt_expiry is protected by mount_lock now (instead of namespace_sem) - MNT_LOCKED is used only for mounts that need to remain attached to their parents to prevent mountpoint exposure - no more overloading it for absolute roots - all mnt_list uses are transient now - it's used only to represent temporary sets during umount_tree() - mount refcounting change: children no longer pin parents for any mounts, whether they'd passed through umount_tree() or not - 'struct mountpoint' changes: - refcount is no more; what matters is ->m_list emptiness - instead of temporary bumping the refcount, we insert a new object (pinned_mountpoint) into ->m_list - new calling conventions for lock_mount() and friends - do_move_mount()/attach_recursive_mnt() seriously cleaned up - globals in fs/pnode.c are gone - propagate_mnt(), change_mnt_propagation() and propagate_umount() cleaned up (in the last case - pretty much completely rewritten). - freeing of emptied mnt_namespace is done in namespace_unlock(). For one thing, there are subtle ordering requirements there; for another it simplifies cleanups. - assorted cleanups - restore the machinery for long-term mounts from accumulated bitrot. This is going to get a followup come next cycle, when the change of vfs_fs_parse_string() calling conventions goes into -next * tag 'pull-mount' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (48 commits) statmount_mnt_basic(): simplify the logics for group id invent_group_ids(): zero ->mnt_group_id always implies !IS_MNT_SHARED() get rid of CL_SHARE_TO_SLAVE take freeing of emptied mnt_namespace to namespace_unlock() copy_tree(): don't link the mounts via mnt_list change_mnt_propagation(): move ->mnt_master assignment into MS_SLAVE case mnt_slave_list/mnt_slave: turn into hlist_head/hlist_node turn do_make_slave() into transfer_propagation() do_make_slave(): choose new master sanely change_mnt_propagation(): do_make_slave() is a no-op unless IS_MNT_SHARED() change_mnt_propagation() cleanups, step 1 propagate_mnt(): fix comment and convert to kernel-doc, while we are at it propagate_mnt(): get rid of last_dest fs/pnode.c: get rid of globals propagate_one(): fold into the sole caller propagate_one(): separate the "what should be the master for this copy" part propagate_one(): separate the "do we need secondary here?" logics propagate_mnt(): handle all peer groups in the same loop propagate_one(): get rid of dest_master mount: separate the flags accessed only under namespace_sem ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2025-07-28 10:49:38 -0700
committer: Linus Torvalds <torvalds@linux-foundation.org> 2025-07-28 10:49:38 -0700
commit: 794cbac9c053155754d04231b9365f91ea4ce7d2 (patch)
tree: 2ce6a817a77146b52c8937426cbcbd023a401174 /fs
parent: 953e117bf4aad7e1d01419d4bcc03ab93420387c (diff)
parent: a7cce099450f8fc597a6ac215440666610895fb7 (diff)
download: linux-794cbac9c053155754d04231b9365f91ea4ce7d2.tar.gz
5 files changed, 692 insertions, 785 deletions
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 6e0ade365a3347..b7994186fc665c 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1588,7 +1588,7 @@ static struct vfsmount *__init mount_one_hugetlbfs(struct hstate *h)
 	} else {
 		struct hugetlbfs_fs_context *ctx = fc->fs_private;
 		ctx->hstate = h;
-		mnt = fc_mount(fc);
+		mnt = fc_mount_longterm(fc);
 		put_fs_context(fc);
 	}
 	if (IS_ERR(mnt))
diff --git a/fs/mount.h b/fs/mount.h
index ad7173037924a8..97737051a8b9df 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -44,7 +44,6 @@ struct mountpoint {
 	struct hlist_node m_hash;
 	struct dentry *m_dentry;
 	struct hlist_head m_list;
-	int m_count;
 };
 
 struct mount {
@@ -70,8 +69,8 @@ struct mount {
 	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 */
-	struct list_head mnt_slave;	/* slave list entry */
+	struct hlist_head mnt_slave_list;/* list of slave mounts */
+	struct hlist_node mnt_slave;	/* slave list entry */
 	struct mount *mnt_master;	/* slave is on master->mnt_slave_list */
 	struct mnt_namespace *mnt_ns;	/* containing namespace */
 	struct mountpoint *mnt_mp;	/* where is it mounted */
@@ -79,21 +78,38 @@ struct mount {
 		struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */
 		struct hlist_node mnt_umount;
 	};
-	struct list_head mnt_umounting; /* list entry for umount propagation */
 #ifdef CONFIG_FSNOTIFY
 	struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;
 	struct list_head to_notify;	/* need to queue notification */
 	struct mnt_namespace *prev_ns;	/* previous namespace (NULL if none) */
 #endif
+	int mnt_t_flags;		/* namespace_sem-protected flags */
 	int mnt_id;			/* mount identifier, reused */
 	u64 mnt_id_unique;		/* mount ID unique until reboot */
 	int mnt_group_id;		/* peer group identifier */
 	int mnt_expiry_mark;		/* true if marked for expiry */
 	struct hlist_head mnt_pins;
 	struct hlist_head mnt_stuck_children;
+	struct mount *overmount;	/* mounted on ->mnt_root */
 } __randomize_layout;
 
+enum {
+	T_SHARED		= 1, /* mount is shared */
+	T_UNBINDABLE		= 2, /* mount is unbindable */
+	T_MARKED		= 4, /* internal mark for propagate_... */
+	T_UMOUNT_CANDIDATE	= 8, /* for propagate_umount */
+
+	/*
+	 * T_SHARED_MASK is the set of flags that should be cleared when a
+	 * mount becomes shared.  Currently, this is only the flag that says a
+	 * mount cannot be bind mounted, since this is how we create a mount
+	 * that shares events with another mount.  If you add a new T_*
+	 * flag, consider how it interacts with shared mounts.
+	 */
+	T_SHARED_MASK	= T_UNBINDABLE,
+};
+
 #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */
 
 static inline struct mount *real_mount(struct vfsmount *mnt)
@@ -101,7 +117,7 @@ static inline struct mount *real_mount(struct vfsmount *mnt)
 	return container_of(mnt, struct mount, mnt);
 }
 
-static inline int mnt_has_parent(struct mount *mnt)
+static inline int mnt_has_parent(const struct mount *mnt)
 {
 	return mnt != mnt->mnt_parent;
 }
@@ -146,8 +162,8 @@ struct proc_mounts {
 
 extern const struct seq_operations mounts_op;
 
-extern bool __is_local_mountpoint(struct dentry *dentry);
-static inline bool is_local_mountpoint(struct dentry *dentry)
+extern bool __is_local_mountpoint(const struct dentry *dentry);
+static inline bool is_local_mountpoint(const struct dentry *dentry)
 {
 	if (!d_mountpoint(dentry))
 		return false;
@@ -160,6 +176,13 @@ static inline bool is_anon_ns(struct mnt_namespace *ns)
 	return ns->seq == 0;
 }
 
+static inline bool anon_ns_root(const struct mount *m)
+{
+	struct mnt_namespace *ns = READ_ONCE(m->mnt_ns);
+
+	return !IS_ERR_OR_NULL(ns) && is_anon_ns(ns) && m == ns->root;
+}
+
 static inline bool mnt_ns_attached(const struct mount *mnt)
 {
 	return !RB_EMPTY_NODE(&mnt->mnt_node);
@@ -170,7 +193,7 @@ static inline bool mnt_ns_empty(const struct mnt_namespace *ns)
 	return RB_EMPTY_ROOT(&ns->mounts);
 }
 
-static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list)
+static inline void move_from_ns(struct mount *mnt)
 {
 	struct mnt_namespace *ns = mnt->mnt_ns;
 	WARN_ON(!mnt_ns_attached(mnt));
@@ -180,7 +203,6 @@ static inline void move_from_ns(struct mount *mnt, struct list_head *dt_list)
 		ns->mnt_first_node = rb_next(&mnt->mnt_node);
 	rb_erase(&mnt->mnt_node, &ns->mounts);
 	RB_CLEAR_NODE(&mnt->mnt_node);
-	list_add_tail(&mnt->mnt_list, dt_list);
 }
 
 bool has_locked_children(struct mount *mnt, struct dentry *dentry);
diff --git a/fs/namespace.c b/fs/namespace.c
index 54c59e091919bc..c549bd39c210a3 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -79,6 +79,7 @@ static struct kmem_cache *mnt_cache __ro_after_init;
 static DECLARE_RWSEM(namespace_sem);
 static HLIST_HEAD(unmounted);	/* protected by namespace_sem */
 static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */
+static struct mnt_namespace *emptied_ns; /* protected by namespace_sem */
 static DEFINE_SEQLOCK(mnt_ns_tree_lock);
 
 #ifdef CONFIG_FSNOTIFY
@@ -380,10 +381,9 @@ static struct mount *alloc_vfsmnt(const char *name)
 		INIT_LIST_HEAD(&mnt->mnt_list);
 		INIT_LIST_HEAD(&mnt->mnt_expire);
 		INIT_LIST_HEAD(&mnt->mnt_share);
-		INIT_LIST_HEAD(&mnt->mnt_slave_list);
-		INIT_LIST_HEAD(&mnt->mnt_slave);
+		INIT_HLIST_HEAD(&mnt->mnt_slave_list);
+		INIT_HLIST_NODE(&mnt->mnt_slave);
 		INIT_HLIST_NODE(&mnt->mnt_mp_list);
-		INIT_LIST_HEAD(&mnt->mnt_umounting);
 		INIT_HLIST_HEAD(&mnt->mnt_stuck_children);
 		RB_CLEAR_NODE(&mnt->mnt_node);
 		mnt->mnt.mnt_idmap = &nop_mnt_idmap;
@@ -894,7 +894,7 @@ struct vfsmount *lookup_mnt(const struct path *path)
  * namespace not just a mount that happens to have some specified
  * parent mount.
  */
-bool __is_local_mountpoint(struct dentry *dentry)
+bool __is_local_mountpoint(const struct dentry *dentry)
 {
 	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
 	struct mount *mnt, *n;
@@ -911,42 +911,48 @@ bool __is_local_mountpoint(struct dentry *dentry)
 	return is_covered;
 }
 
-static struct mountpoint *lookup_mountpoint(struct dentry *dentry)
+struct pinned_mountpoint {
+	struct hlist_node node;
+	struct mountpoint *mp;
+};
+
+static bool lookup_mountpoint(struct dentry *dentry, struct pinned_mountpoint *m)
 {
 	struct hlist_head *chain = mp_hash(dentry);
 	struct mountpoint *mp;
 
 	hlist_for_each_entry(mp, chain, m_hash) {
 		if (mp->m_dentry == dentry) {
-			mp->m_count++;
-			return mp;
+			hlist_add_head(&m->node, &mp->m_list);
+			m->mp = mp;
+			return true;
 		}
 	}
-	return NULL;
+	return false;
 }
 
-static struct mountpoint *get_mountpoint(struct dentry *dentry)
+static int get_mountpoint(struct dentry *dentry, struct pinned_mountpoint *m)
 {
-	struct mountpoint *mp, *new = NULL;
+	struct mountpoint *mp __free(kfree) = NULL;
+	bool found;
 	int ret;
 
 	if (d_mountpoint(dentry)) {
 		/* might be worth a WARN_ON() */
 		if (d_unlinked(dentry))
-			return ERR_PTR(-ENOENT);
+			return -ENOENT;
 mountpoint:
 		read_seqlock_excl(&mount_lock);
-		mp = lookup_mountpoint(dentry);
+		found = lookup_mountpoint(dentry, m);
 		read_sequnlock_excl(&mount_lock);
-		if (mp)
-			goto done;
+		if (found)
+			return 0;
 	}
 
-	if (!new)
-		new = kmalloc(sizeof(struct mountpoint), GFP_KERNEL);
-	if (!new)
-		return ERR_PTR(-ENOMEM);
-
+	if (!mp)
+		mp = kmalloc(sizeof(struct mountpoint), GFP_KERNEL);
+	if (!mp)
+		return -ENOMEM;
 
 	/* Exactly one processes may set d_mounted */
 	ret = d_set_mounted(dentry);
@@ -956,34 +962,28 @@ mountpoint:
 		goto mountpoint;
 
 	/* The dentry is not available as a mountpoint? */
-	mp = ERR_PTR(ret);
 	if (ret)
-		goto done;
+		return ret;
 
 	/* Add the new mountpoint to the hash table */
 	read_seqlock_excl(&mount_lock);
-	new->m_dentry = dget(dentry);
-	new->m_count = 1;
-	hlist_add_head(&new->m_hash, mp_hash(dentry));
-	INIT_HLIST_HEAD(&new->m_list);
+	mp->m_dentry = dget(dentry);
+	hlist_add_head(&mp->m_hash, mp_hash(dentry));
+	INIT_HLIST_HEAD(&mp->m_list);
+	hlist_add_head(&m->node, &mp->m_list);
+	m->mp = no_free_ptr(mp);
 	read_sequnlock_excl(&mount_lock);
-
-	mp = new;
-	new = NULL;
-done:
-	kfree(new);
-	return mp;
+	return 0;
 }
 
 /*
  * vfsmount lock must be held.  Additionally, the caller is responsible
  * for serializing calls for given disposal list.
  */
-static void __put_mountpoint(struct mountpoint *mp, struct list_head *list)
+static void maybe_free_mountpoint(struct mountpoint *mp, struct list_head *list)
 {
-	if (!--mp->m_count) {
+	if (hlist_empty(&mp->m_list)) {
 		struct dentry *dentry = mp->m_dentry;
-		BUG_ON(!hlist_empty(&mp->m_list));
 		spin_lock(&dentry->d_lock);
 		dentry->d_flags &= ~DCACHE_MOUNTED;
 		spin_unlock(&dentry->d_lock);
@@ -993,10 +993,15 @@ static void __put_mountpoint(struct mountpoint *mp, struct list_head *list)
 	}
 }
 
-/* called with namespace_lock and vfsmount lock */
-static void put_mountpoint(struct mountpoint *mp)
+/*
+ * locks: mount_lock [read_seqlock_excl], namespace_sem [excl]
+ */
+static void unpin_mountpoint(struct pinned_mountpoint *m)
 {
-	__put_mountpoint(mp, &ex_mountpoints);
+	if (m->mp) {
+		hlist_del(&m->node);
+		maybe_free_mountpoint(m->mp, &ex_mountpoints);
+	}
 }
 
 static inline int check_mnt(struct mount *mnt)
@@ -1038,11 +1043,14 @@ static void __touch_mnt_namespace(struct mnt_namespace *ns)
 }
 
 /*
- * vfsmount lock must be held for write
+ * locks: mount_lock[write_seqlock]
  */
-static struct mountpoint *unhash_mnt(struct mount *mnt)
+static void __umount_mnt(struct mount *mnt, struct list_head *shrink_list)
 {
 	struct mountpoint *mp;
+	struct mount *parent = mnt->mnt_parent;
+	if (unlikely(parent->overmount == mnt))
+		parent->overmount = NULL;
 	mnt->mnt_parent = mnt;
 	mnt->mnt_mountpoint = mnt->mnt.mnt_root;
 	list_del_init(&mnt->mnt_child);
@@ -1050,15 +1058,15 @@ static struct mountpoint *unhash_mnt(struct mount *mnt)
 	hlist_del_init(&mnt->mnt_mp_list);
 	mp = mnt->mnt_mp;
 	mnt->mnt_mp = NULL;
-	return mp;
+	maybe_free_mountpoint(mp, shrink_list);
 }
 
 /*
- * vfsmount lock must be held for write
+ * locks: mount_lock[write_seqlock], namespace_sem[excl] (for ex_mountpoints)
  */
 static void umount_mnt(struct mount *mnt)
 {
-	put_mountpoint(unhash_mnt(mnt));
+	__umount_mnt(mnt, &ex_mountpoints);
 }
 
 /*
@@ -1068,43 +1076,17 @@ void mnt_set_mountpoint(struct mount *mnt,
 			struct mountpoint *mp,
 			struct mount *child_mnt)
 {
-	mp->m_count++;
-	mnt_add_count(mnt, 1);	/* essentially, that's mntget */
 	child_mnt->mnt_mountpoint = mp->m_dentry;
 	child_mnt->mnt_parent = mnt;
 	child_mnt->mnt_mp = mp;
 	hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list);
 }
 
-/**
- * mnt_set_mountpoint_beneath - mount a mount beneath another one
- *
- * @new_parent: the source mount
- * @top_mnt:    the mount beneath which @new_parent is mounted
- * @new_mp:     the new mountpoint of @top_mnt on @new_parent
- *
- * Remove @top_mnt from its current mountpoint @top_mnt->mnt_mp and
- * parent @top_mnt->mnt_parent and mount it on top of @new_parent at
- * @new_mp. And mount @new_parent on the old parent and old
- * mountpoint of @top_mnt.
- *
- * Context: This function expects namespace_lock() and lock_mount_hash()
- *          to have been acquired in that order.
- */
-static void mnt_set_mountpoint_beneath(struct mount *new_parent,
-				       struct mount *top_mnt,
-				       struct mountpoint *new_mp)
-{
-	struct mount *old_top_parent = top_mnt->mnt_parent;
-	struct mountpoint *old_top_mp = top_mnt->mnt_mp;
-
-	mnt_set_mountpoint(old_top_parent, old_top_mp, new_parent);
-	mnt_change_mountpoint(new_parent, new_mp, top_mnt);
-}
-
-
-static void __attach_mnt(struct mount *mnt, struct mount *parent)
+static void make_visible(struct mount *mnt)
 {
+	struct mount *parent = mnt->mnt_parent;
+	if (unlikely(mnt->mnt_mountpoint == parent->mnt.mnt_root))
+		parent->overmount = mnt;
 	hlist_add_head_rcu(&mnt->mnt_hash,
 			   m_hash(&parent->mnt, mnt->mnt_mountpoint));
 	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
@@ -1116,51 +1098,34 @@ static void __attach_mnt(struct mount *mnt, struct mount *parent)
  * @parent:  the parent
  * @mnt:     the new mount
  * @mp:      the new mountpoint
- * @beneath: whether to mount @mnt beneath or on top of @parent
  *
- * If @beneath is false, mount @mnt at @mp on @parent. Then attach @mnt
+ * Mount @mnt at @mp on @parent. Then attach @mnt
  * to @parent's child mount list and to @mount_hashtable.
  *
- * If @beneath is true, remove @mnt from its current parent and
- * mountpoint and mount it on @mp on @parent, and mount @parent on the
- * old parent and old mountpoint of @mnt. Finally, attach @parent to
- * @mnt_hashtable and @parent->mnt_parent->mnt_mounts.
- *
- * Note, when __attach_mnt() is called @mnt->mnt_parent already points
+ * Note, when make_visible() is called @mnt->mnt_parent already points
  * to the correct parent.
  *
  * Context: This function expects namespace_lock() and lock_mount_hash()
  *          to have been acquired in that order.
  */
 static void attach_mnt(struct mount *mnt, struct mount *parent,
-		       struct mountpoint *mp, bool beneath)
+		       struct mountpoint *mp)
 {
-	if (beneath)
-		mnt_set_mountpoint_beneath(mnt, parent, mp);
-	else
-		mnt_set_mountpoint(parent, mp, mnt);
-	/*
-	 * Note, @mnt->mnt_parent has to be used. If @mnt was mounted
-	 * beneath @parent then @mnt will need to be attached to
-	 * @parent's old parent, not @parent. IOW, @mnt->mnt_parent
-	 * isn't the same mount as @parent.
-	 */
-	__attach_mnt(mnt, mnt->mnt_parent);
+	mnt_set_mountpoint(parent, mp, mnt);
+	make_visible(mnt);
 }
 
 void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt)
 {
 	struct mountpoint *old_mp = mnt->mnt_mp;
-	struct mount *old_parent = mnt->mnt_parent;
 
 	list_del_init(&mnt->mnt_child);
 	hlist_del_init(&mnt->mnt_mp_list);
 	hlist_del_init_rcu(&mnt->mnt_hash);
 
-	attach_mnt(mnt, parent, mp, false);
+	attach_mnt(mnt, parent, mp);
 
-	put_mountpoint(old_mp);
-	mnt_add_count(old_parent, -1);
+	maybe_free_mountpoint(old_mp, &ex_mountpoints);
 }
 
 static inline struct mount *node_to_mount(struct rb_node *node)
@@ -1197,32 +1162,6 @@ static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt)
 	mnt_notify_add(mnt);
 }
 
-/*
- * vfsmount lock must be held for write
- */
-static void commit_tree(struct mount *mnt)
-{
-	struct mount *parent = mnt->mnt_parent;
-	struct mount *m;
-	LIST_HEAD(head);
-	struct mnt_namespace *n = parent->mnt_ns;
-
-	BUG_ON(parent == mnt);
-
-	list_add_tail(&head, &mnt->mnt_list);
-	while (!list_empty(&head)) {
-		m = list_first_entry(&head, typeof(*m), mnt_list);
-		list_del(&m->mnt_list);
-
-		mnt_add_to_ns(n, m);
-	}
-	n->nr_mounts += n->pending_mounts;
-	n->pending_mounts = 0;
-
-	__attach_mnt(mnt, parent);
-	touch_mnt_namespace(n);
-}
-
 static struct mount *next_mnt(struct mount *p, struct mount *root)
 {
 	struct list_head *next = p->mnt_mounts.next;
@@ -1249,6 +1188,27 @@ static struct mount *skip_mnt_tree(struct mount *p)
 	return p;
 }
 
+/*
+ * vfsmount lock must be held for write
+ */
+static void commit_tree(struct mount *mnt)
+{
+	struct mnt_namespace *n = mnt->mnt_parent->mnt_ns;
+
+	if (!mnt_ns_attached(mnt)) {
+		for (struct mount *m = mnt; m; m = next_mnt(m, mnt))
+			if (unlikely(mnt_ns_attached(m)))
+				m = skip_mnt_tree(m);
+			else
+				mnt_add_to_ns(n, m);
+		n->nr_mounts += n->pending_mounts;
+		n->pending_mounts = 0;
+	}
+
+	make_visible(mnt);
+	touch_mnt_namespace(n);
+}
+
 /**
  * vfs_create_mount - Create a mount for a configured superblock
  * @fc: The configuration context with the superblock attached
@@ -1296,6 +1256,15 @@ struct vfsmount *fc_mount(struct fs_context *fc)
 }
 EXPORT_SYMBOL(fc_mount);
 
+struct vfsmount *fc_mount_longterm(struct fs_context *fc)
+{
+	struct vfsmount *mnt = fc_mount(fc);
+	if (!IS_ERR(mnt))
+		real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL;
+	return mnt;
+}
+EXPORT_SYMBOL(fc_mount_longterm);
+
 struct vfsmount *vfs_kern_mount(struct file_system_type *type,
 				int flags, const char *name,
 				void *data)
@@ -1337,7 +1306,10 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 	if (!mnt)
 		return ERR_PTR(-ENOMEM);
 
-	if (flag & (CL_SLAVE | CL_PRIVATE | CL_SHARED_TO_SLAVE))
+	mnt->mnt.mnt_flags = READ_ONCE(old->mnt.mnt_flags) &
+			     ~MNT_INTERNAL_FLAGS;
+
+	if (flag & (CL_SLAVE | CL_PRIVATE))
 		mnt->mnt_group_id = 0; /* not a peer of original */
 	else
 		mnt->mnt_group_id = old->mnt_group_id;
@@ -1348,8 +1320,8 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 			goto out_free;
 	}
 
-	mnt->mnt.mnt_flags = old->mnt.mnt_flags;
-	mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL);
+	if (mnt->mnt_group_id)
+		set_mnt_shared(mnt);
 
 	atomic_inc(&sb->s_active);
 	mnt->mnt.mnt_idmap = mnt_idmap_get(mnt_idmap(&old->mnt));
@@ -1362,30 +1334,19 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 	list_add_tail(&mnt->mnt_instance, &sb->s_mounts);
 	unlock_mount_hash();
 
-	if ((flag & CL_SLAVE) ||
-	    ((flag & CL_SHARED_TO_SLAVE) && IS_MNT_SHARED(old))) {
-		list_add(&mnt->mnt_slave, &old->mnt_slave_list);
+	if (flag & CL_PRIVATE)	// we are done with it
+		return mnt;
+
+	if (peers(mnt, old))
+		list_add(&mnt->mnt_share, &old->mnt_share);
+
+	if ((flag & CL_SLAVE) && old->mnt_group_id) {
+		hlist_add_head(&mnt->mnt_slave, &old->mnt_slave_list);
 		mnt->mnt_master = old;
-		CLEAR_MNT_SHARED(mnt);
-	} else if (!(flag & CL_PRIVATE)) {
-		if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old))
-			list_add(&mnt->mnt_share, &old->mnt_share);
-		if (IS_MNT_SLAVE(old))
-			list_add(&mnt->mnt_slave, &old->mnt_slave);
+	} else if (IS_MNT_SLAVE(old)) {
+		hlist_add_behind(&mnt->mnt_slave, &old->mnt_slave);
 		mnt->mnt_master = old->mnt_master;
-	} else {
-		CLEAR_MNT_SHARED(mnt);
 	}
-	if (flag & CL_MAKE_SHARED)
-		set_mnt_shared(mnt);
-
-	/* stick the duplicate mount on the same expiry list
-	 * as the original if that was on one */
-	if (flag & CL_EXPIRE) {
-		if (!list_empty(&old->mnt_expire))
-			list_add(&mnt->mnt_expire, &old->mnt_expire);
-	}
-
 	return mnt;
 
  out_free:
@@ -1478,11 +1439,13 @@ static void mntput_no_expire(struct mount *mnt)
 	rcu_read_unlock();
 
 	list_del(&mnt->mnt_instance);
+	if (unlikely(!list_empty(&mnt->mnt_expire)))
+		list_del(&mnt->mnt_expire);
 
 	if (unlikely(!list_empty(&mnt->mnt_mounts))) {
 		struct mount *p, *tmp;
 		list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts,  mnt_child) {
-			__put_mountpoint(unhash_mnt(p), &list);
+			__umount_mnt(p, &list);
 			hlist_add_head(&p->mnt_umount, &mnt->mnt_stuck_children);
 		}
 	}
@@ -1679,23 +1642,19 @@ const struct seq_operations mounts_op = {
 int may_umount_tree(struct vfsmount *m)
 {
 	struct mount *mnt = real_mount(m);
-	int actual_refs = 0;
-	int minimum_refs = 0;
-	struct mount *p;
-	BUG_ON(!m);
+	bool busy = false;
 
 	/* write lock needed for mnt_get_count */
 	lock_mount_hash();
-	for (p = mnt; p; p = next_mnt(p, mnt)) {
-		actual_refs += mnt_get_count(p);
-		minimum_refs += 2;
+	for (struct mount *p = mnt; p; p = next_mnt(p, mnt)) {
+		if (mnt_get_count(p) > (p == mnt ? 2 : 1)) {
+			busy = true;
+			break;
+		}
 	}
 	unlock_mount_hash();
 
-	if (actual_refs > minimum_refs)
-		return 0;
-
-	return 1;
+	return !busy;
 }
 
 EXPORT_SYMBOL(may_umount_tree);
@@ -1771,15 +1730,18 @@ static bool need_notify_mnt_list(void)
 }
 #endif
 
+static void free_mnt_ns(struct mnt_namespace *);
 static void namespace_unlock(void)
 {
 	struct hlist_head head;
 	struct hlist_node *p;
 	struct mount *m;
+	struct mnt_namespace *ns = emptied_ns;
 	LIST_HEAD(list);
 
 	hlist_move_list(&unmounted, &head);
 	list_splice_init(&ex_mountpoints, &list);
+	emptied_ns = NULL;
 
 	if (need_notify_mnt_list()) {
 		/*
@@ -1793,6 +1755,11 @@ static void namespace_unlock(void)
 	} else {
 		up_write(&namespace_sem);
 	}
+	if (unlikely(ns)) {
+		/* Make sure we notice when we leak mounts. */
+		VFS_WARN_ON_ONCE(!mnt_ns_empty(ns));
+		free_mnt_ns(ns);
+	}
 
 	shrink_dentry_list(&list);
 
@@ -1865,9 +1832,8 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 	for (p = mnt; p; p = next_mnt(p, mnt)) {
 		p->mnt.mnt_flags |= MNT_UMOUNT;
 		if (mnt_ns_attached(p))
-			move_from_ns(p, &tmp_list);
-		else
-			list_move(&p->mnt_list, &tmp_list);
+			move_from_ns(p);
+		list_add_tail(&p->mnt_list, &tmp_list);
 	}
 
 	/* Hide the mounts from mnt_mounts */
@@ -1896,7 +1862,6 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 
 		disconnect = disconnect_mount(p, how);
 		if (mnt_has_parent(p)) {
-			mnt_add_count(p->mnt_parent, -1);
 			if (!disconnect) {
 				/* Don't forget about p */
 				list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts);
@@ -1973,7 +1938,7 @@ static int do_umount(struct mount *mnt, int flags)
 		 * all race cases, but it's a slowpath.
 		 */
 		lock_mount_hash();
-		if (mnt_get_count(mnt) != 2) {
+		if (!list_empty(&mnt->mnt_mounts) || mnt_get_count(mnt) != 2) {
 			unlock_mount_hash();
 			return -EBUSY;
 		}
@@ -2019,23 +1984,27 @@ static int do_umount(struct mount *mnt, int flags)
 	namespace_lock();
 	lock_mount_hash();
 
-	/* Recheck MNT_LOCKED with the locks held */
+	/* Repeat the earlier racy checks, now that we are holding the locks */
 	retval = -EINVAL;
+	if (!check_mnt(mnt))
+		goto out;
+
 	if (mnt->mnt.mnt_flags & MNT_LOCKED)
 		goto out;
 
+	if (!mnt_has_parent(mnt)) /* not the absolute root */
+		goto out;
+
 	event++;
 	if (flags & MNT_DETACH) {
-		if (mnt_ns_attached(mnt) || !list_empty(&mnt->mnt_list))
-			umount_tree(mnt, UMOUNT_PROPAGATE);
+		umount_tree(mnt, UMOUNT_PROPAGATE);
 		retval = 0;
 	} else {
 		smp_mb(); // paired with __legitimize_mnt()
 		shrink_submounts(mnt);
 		retval = -EBUSY;
 		if (!propagate_mount_busy(mnt, 2)) {
-			if (mnt_ns_attached(mnt) || !list_empty(&mnt->mnt_list))
-				umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC);
+			umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC);
 			retval = 0;
 		}
 	}
@@ -2057,25 +2026,24 @@ out:
  */
 void __detach_mounts(struct dentry *dentry)
 {
-	struct mountpoint *mp;
+	struct pinned_mountpoint mp = {};
 	struct mount *mnt;
 
 	namespace_lock();
 	lock_mount_hash();
-	mp = lookup_mountpoint(dentry);
-	if (!mp)
+	if (!lookup_mountpoint(dentry, &mp))
 		goto out_unlock;
 
 	event++;
-	while (!hlist_empty(&mp->m_list)) {
-		mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
+	while (mp.node.next) {
+		mnt = hlist_entry(mp.node.next, struct mount, mnt_mp_list);
 		if (mnt->mnt.mnt_flags & MNT_UMOUNT) {
 			umount_mnt(mnt);
 			hlist_add_head(&mnt->mnt_umount, &unmounted);
 		}
 		else umount_tree(mnt, UMOUNT_CONNECTED);
 	}
-	put_mountpoint(mp);
+	unpin_mountpoint(&mp);
 out_unlock:
 	unlock_mount_hash();
 	namespace_unlock();
@@ -2259,7 +2227,6 @@ struct mount *copy_tree(struct mount *src_root, struct dentry *dentry,
 		return dst_mnt;
 
 	src_parent = src_root;
-	dst_mnt->mnt_mountpoint = src_root->mnt_mountpoint;
 
 	list_for_each_entry(src_root_child, &src_root->mnt_mounts, mnt_child) {
 		if (!is_subdir(src_root_child->mnt_mountpoint, dentry))
@@ -2294,8 +2261,16 @@ struct mount *copy_tree(struct mount *src_root, struct dentry *dentry,
 			if (IS_ERR(dst_mnt))
 				goto out;
 			lock_mount_hash();
-			list_add_tail(&dst_mnt->mnt_list, &res->mnt_list);
-			attach_mnt(dst_mnt, dst_parent, src_parent->mnt_mp, false);
+			if (src_mnt->mnt.mnt_flags & MNT_LOCKED)
+				dst_mnt->mnt.mnt_flags |= MNT_LOCKED;
+			if (unlikely(flag & CL_EXPIRE)) {
+				/* stick the duplicate mount on the same expiry
+				 * list as the original if that was on one */
+				if (!list_empty(&src_mnt->mnt_expire))
+					list_add(&dst_mnt->mnt_expire,
+						 &src_mnt->mnt_expire);
+			}
+			attach_mnt(dst_mnt, dst_parent, src_parent->mnt_mp);
 			unlock_mount_hash();
 		}
 	}
@@ -2368,78 +2343,36 @@ void drop_collected_paths(struct path *paths, struct path *prealloc)
 		kfree(paths);
 }
 
-static void free_mnt_ns(struct mnt_namespace *);
 static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *, bool);
 
-static inline bool must_dissolve(struct mnt_namespace *mnt_ns)
-{
-	/*
-        * This mount belonged to an anonymous mount namespace
-        * but was moved to a non-anonymous mount namespace and
-        * then unmounted.
-        */
-	if (unlikely(!mnt_ns))
-		return false;
-
-	/*
-        * This mount belongs to a non-anonymous mount namespace
-        * and we know that such a mount can never transition to
-        * an anonymous mount namespace again.
-        */
-	if (!is_anon_ns(mnt_ns)) {
-		/*
-		 * A detached mount either belongs to an anonymous mount
-		 * namespace or a non-anonymous mount namespace. It
-		 * should never belong to something purely internal.
-		 */
-		VFS_WARN_ON_ONCE(mnt_ns == MNT_NS_INTERNAL);
-		return false;
-	}
-
-	return true;
-}
-
 void dissolve_on_fput(struct vfsmount *mnt)
 {
-	struct mnt_namespace *ns;
 	struct mount *m = real_mount(mnt);
 
+	/*
+	 * m used to be the root of anon namespace; if it still is one,
+	 * we need to dissolve the mount tree and free that namespace.
+	 * Let's try to avoid taking namespace_sem if we can determine
+	 * that there's nothing to do without it - rcu_read_lock() is
+	 * enough to make anon_ns_root() memory-safe and once m has
+	 * left its namespace, it's no longer our concern, since it will
+	 * never become a root of anon ns again.
+	 */
+
 	scoped_guard(rcu) {
-		if (!must_dissolve(READ_ONCE(m->mnt_ns)))
+		if (!anon_ns_root(m))
 			return;
 	}
 
 	scoped_guard(namespace_lock, &namespace_sem) {
-		ns = m->mnt_ns;
-		if (!must_dissolve(ns))
-			return;
-
-		/*
-		 * After must_dissolve() we know that this is a detached
-		 * mount in an anonymous mount namespace.
-		 *
-		 * Now when mnt_has_parent() reports that this mount
-		 * tree has a parent, we know that this anonymous mount
-		 * tree has been moved to another anonymous mount
-		 * namespace.
-		 *
-		 * So when closing this file we cannot unmount the mount
-		 * tree. This will be done when the file referring to
-		 * the root of the anonymous mount namespace will be
-		 * closed (It could already be closed but it would sync
-		 * on @namespace_sem and wait for us to finish.).
-		 */
-		if (mnt_has_parent(m))
+		if (!anon_ns_root(m))
 			return;
 
+		emptied_ns = m->mnt_ns;
 		lock_mount_hash();
 		umount_tree(m, UMOUNT_CONNECTED);
 		unlock_mount_hash();
 	}
-
-	/* Make sure we notice when we leak mounts. */
-	VFS_WARN_ON_ONCE(!mnt_ns_empty(ns));
-	free_mnt_ns(ns);
 }
 
 static bool __has_locked_children(struct mount *mnt, struct dentry *dentry)
@@ -2518,9 +2451,7 @@ struct vfsmount *clone_private_mount(const struct path *path)
 	 * loops get created.
 	 */
 	if (!check_mnt(old_mnt)) {
-		if (!is_mounted(&old_mnt->mnt) ||
-			!is_anon_ns(old_mnt->mnt_ns) ||
-			mnt_has_parent(old_mnt))
+		if (!anon_ns_root(old_mnt))
 			return ERR_PTR(-EINVAL);
 
 		if (!check_for_nsfs_mounts(old_mnt))
@@ -2564,7 +2495,7 @@ static void lock_mnt_tree(struct mount *mnt)
 		if (flags & MNT_NOEXEC)
 			flags |= MNT_LOCK_NOEXEC;
 		/* Don't allow unprivileged users to reveal what is under a mount */
-		if (list_empty(&p->mnt_expire))
+		if (list_empty(&p->mnt_expire) && p != mnt)
 			flags |= MNT_LOCKED;
 		p->mnt.mnt_flags = flags;
 	}
@@ -2585,7 +2516,7 @@ static int invent_group_ids(struct mount *mnt, bool recurse)
 	struct mount *p;
 
 	for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) {
-		if (!p->mnt_group_id && !IS_MNT_SHARED(p)) {
+		if (!p->mnt_group_id) {
 			int err = mnt_alloc_group_id(p);
 			if (err) {
 				cleanup_group_ids(mnt, p);
@@ -2621,17 +2552,15 @@ int count_mounts(struct mnt_namespace *ns, struct mount *mnt)
 }
 
 enum mnt_tree_flags_t {
-	MNT_TREE_MOVE = BIT(0),
-	MNT_TREE_BENEATH = BIT(1),
-	MNT_TREE_PROPAGATION = BIT(2),
+	MNT_TREE_BENEATH = BIT(0),
+	MNT_TREE_PROPAGATION = BIT(1),
 };
 
 /**
  * attach_recursive_mnt - attach a source mount tree
  * @source_mnt: mount tree to be attached
- * @top_mnt:    mount that @source_mnt will be mounted on or mounted beneath
+ * @dest_mnt:   mount that @source_mnt will be mounted on
  * @dest_mp:    the mountpoint @source_mnt will be mounted at
- * @flags:      modify how @source_mnt is supposed to be attached
  *
  *  NOTE: in the table below explains the semantics when a source mount
  *  of a given type is attached to a destination mount of a given type.
@@ -2694,26 +2623,31 @@ enum mnt_tree_flags_t {
  *         Otherwise a negative error code is returned.
  */
 static int attach_recursive_mnt(struct mount *source_mnt,
-				struct mount *top_mnt,
-				struct mountpoint *dest_mp,
-				enum mnt_tree_flags_t flags)
+				struct mount *dest_mnt,
+				struct mountpoint *dest_mp)
 {
 	struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
 	HLIST_HEAD(tree_list);
-	struct mnt_namespace *ns = top_mnt->mnt_ns;
-	struct mountpoint *smp;
-	struct mount *child, *dest_mnt, *p;
+	struct mnt_namespace *ns = dest_mnt->mnt_ns;
+	struct pinned_mountpoint root = {};
+	struct mountpoint *shorter = NULL;
+	struct mount *child, *p;
+	struct mount *top;
 	struct hlist_node *n;
 	int err = 0;
-	bool moving = flags & MNT_TREE_MOVE, beneath = flags & MNT_TREE_BENEATH;
+	bool moving = mnt_has_parent(source_mnt);
 
 	/*
 	 * Preallocate a mountpoint in case the new mounts need to be
 	 * mounted beneath mounts on the same mountpoint.
 	 */
-	smp = get_mountpoint(source_mnt->mnt.mnt_root);
-	if (IS_ERR(smp))
-		return PTR_ERR(smp);
+	for (top = source_mnt; unlikely(top->overmount); top = top->overmount) {
+		if (!shorter && is_mnt_ns_file(top->mnt.mnt_root))
+			shorter = top->mnt_mp;
+	}
+	err = get_mountpoint(top->mnt.mnt_root, &root);
+	if (err)
+		return err;
 
 	/* Is there space to add these mounts to the mount namespace? */
 	if (!moving) {
@@ -2722,11 +2656,6 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 			goto out;
 	}
 
-	if (beneath)
-		dest_mnt = top_mnt->mnt_parent;
-	else
-		dest_mnt = top_mnt;
-
 	if (IS_MNT_SHARED(dest_mnt)) {
 		err = invent_group_ids(source_mnt, true);
 		if (err)
@@ -2743,42 +2672,50 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 	}
 
 	if (moving) {
-		if (beneath)
-			dest_mp = smp;
-		unhash_mnt(source_mnt);
-		attach_mnt(source_mnt, top_mnt, dest_mp, beneath);
+		umount_mnt(source_mnt);
 		mnt_notify_add(source_mnt);
-		touch_mnt_namespace(source_mnt->mnt_ns);
+		/* if the mount is moved, it should no longer be expired
+		 * automatically */
+		list_del_init(&source_mnt->mnt_expire);
 	} else {
 		if (source_mnt->mnt_ns) {
-			LIST_HEAD(head);
-
 			/* move from anon - the caller will destroy */
+			emptied_ns = source_mnt->mnt_ns;
 			for (p = source_mnt; p; p = next_mnt(p, source_mnt))
-				move_from_ns(p, &head);
-			list_del_init(&head);
+				move_from_ns(p);
 		}
-		if (beneath)
-			mnt_set_mountpoint_beneath(source_mnt, top_mnt, smp);
-		else
-			mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
-		commit_tree(source_mnt);
 	}
 
+	mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
+	/*
+	 * Now the original copy is in the same state as the secondaries -
+	 * its root attached to mountpoint, but not hashed and all mounts
+	 * in it are either in our namespace or in no namespace at all.
+	 * Add the original to the list of copies and deal with the
+	 * rest of work for all of them uniformly.
+	 */
+	hlist_add_head(&source_mnt->mnt_hash, &tree_list);
+
 	hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
 		struct mount *q;
 		hlist_del_init(&child->mnt_hash);
 		/* Notice when we are propagating across user namespaces */
 		if (child->mnt_parent->mnt_ns->user_ns != user_ns)
 			lock_mnt_tree(child);
-		child->mnt.mnt_flags &= ~MNT_LOCKED;
 		q = __lookup_mnt(&child->mnt_parent->mnt,
 				 child->mnt_mountpoint);
-		if (q)
-			mnt_change_mountpoint(child, smp, q);
+		if (q) {
+			struct mountpoint *mp = root.mp;
+			struct mount *r = child;
+			while (unlikely(r->overmount))
+				r = r->overmount;
+			if (unlikely(shorter) && child != source_mnt)
+				mp = shorter;
+			mnt_change_mountpoint(r, mp, q);
+		}
 		commit_tree(child);
 	}
-	put_mountpoint(smp);
+	unpin_mountpoint(&root);
 	unlock_mount_hash();
 
 	return 0;
@@ -2795,7 +2732,7 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 	ns->pending_mounts = 0;
 
 	read_seqlock_excl(&mount_lock);
-	put_mountpoint(smp);
+	unpin_mountpoint(&root);
 	read_sequnlock_excl(&mount_lock);
 
 	return err;
@@ -2835,12 +2772,12 @@ static int attach_recursive_mnt(struct mount *source_mnt,
  * Return: Either the target mountpoint on the top mount or the top
  *         mount's mountpoint.
  */
-static struct mountpoint *do_lock_mount(struct path *path, bool beneath)
+static int do_lock_mount(struct path *path, struct pinned_mountpoint *pinned, bool beneath)
 {
 	struct vfsmount *mnt = path->mnt;
 	struct dentry *dentry;
-	struct mountpoint *mp = ERR_PTR(-ENOENT);
 	struct path under = {};
+	int err = -ENOENT;
 
 	for (;;) {
 		struct mount *m = real_mount(mnt);
@@ -2878,8 +2815,8 @@ static struct mountpoint *do_lock_mount(struct path *path, bool beneath)
 			path->dentry = dget(mnt->mnt_root);
 			continue;	// got overmounted
 		}
-		mp = get_mountpoint(dentry);
-		if (IS_ERR(mp))
+		err = get_mountpoint(dentry, pinned);
+		if (err)
 			break;
 		if (beneath) {
 			/*
@@ -2890,25 +2827,25 @@ static struct mountpoint *do_lock_mount(struct path *path, bool beneath)
 			 */
 			path_put(&under);
 		}
-		return mp;
+		return 0;
 	}
 	namespace_unlock();
 	inode_unlock(dentry->d_inode);
 	if (beneath)
 		path_put(&under);
-	return mp;
+	return err;
 }
 
-static inline struct mountpoint *lock_mount(struct path *path)
+static inline int lock_mount(struct path *path, struct pinned_mountpoint *m)
 {
-	return do_lock_mount(path, false);
+	return do_lock_mount(path, m, false);
 }
 
-static void unlock_mount(struct mountpoint *where)
+static void unlock_mount(struct pinned_mountpoint *m)
 {
-	inode_unlock(where->m_dentry->d_inode);
+	inode_unlock(m->mp->m_dentry->d_inode);
 	read_seqlock_excl(&mount_lock);
-	put_mountpoint(where);
+	unpin_mountpoint(m);
 	read_sequnlock_excl(&mount_lock);
 	namespace_unlock();
 }
@@ -2922,7 +2859,7 @@ static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp)
 	      d_is_dir(mnt->mnt.mnt_root))
 		return -ENOTDIR;
 
-	return attach_recursive_mnt(mnt, p, mp, 0);
+	return attach_recursive_mnt(mnt, p, mp);
 }
 
 /*
@@ -2971,10 +2908,8 @@ static int do_change_type(struct path *path, int ms_flags)
 			goto out_unlock;
 	}
 
-	lock_mount_hash();
 	for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL))
 		change_mnt_propagation(m, type);
-	unlock_mount_hash();
 
  out_unlock:
 	namespace_unlock();
@@ -3048,26 +2983,21 @@ static inline bool may_copy_tree(struct path *path)
 
 static struct mount *__do_loopback(struct path *old_path, int recurse)
 {
-	struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt);
+	struct mount *old = real_mount(old_path->mnt);
 
 	if (IS_MNT_UNBINDABLE(old))
-		return mnt;
+		return ERR_PTR(-EINVAL);
 
 	if (!may_copy_tree(old_path))
-		return mnt;
+		return ERR_PTR(-EINVAL);
 
 	if (!recurse && __has_locked_children(old, old_path->dentry))
-		return mnt;
+		return ERR_PTR(-EINVAL);
 
 	if (recurse)
-		mnt = copy_tree(old, old_path->dentry, CL_COPY_MNT_NS_FILE);
+		return copy_tree(old, old_path->dentry, CL_COPY_MNT_NS_FILE);
 	else
-		mnt = clone_mnt(old, old_path->dentry, 0);
-
-	if (!IS_ERR(mnt))
-		mnt->mnt.mnt_flags &= ~MNT_LOCKED;
-
-	return mnt;
+		return clone_mnt(old, old_path->dentry, 0);
 }
 
 /*
@@ -3078,7 +3008,7 @@ static int do_loopback(struct path *path, const char *old_name,
 {
 	struct path old_path;
 	struct mount *mnt = NULL, *parent;
-	struct mountpoint *mp;
+	struct pinned_mountpoint mp = {};
 	int err;
 	if (!old_name || !*old_name)
 		return -EINVAL;
@@ -3090,11 +3020,9 @@ static int do_loopback(struct path *path, const char *old_name,
 	if (mnt_ns_loop(old_path.dentry))
 		goto out;
 
-	mp = lock_mount(path);
-	if (IS_ERR(mp)) {
-		err = PTR_ERR(mp);
+	err = lock_mount(path, &mp);
+	if (err)
 		goto out;
-	}
 
 	parent = real_mount(path->mnt);
 	if (!check_mnt(parent))
@@ -3106,14 +3034,14 @@ static int do_loopback(struct path *path, const char *old_name,
 		goto out2;
 	}
 
-	err = graft_tree(mnt, parent, mp);
+	err = graft_tree(mnt, parent, mp.mp);
 	if (err) {
 		lock_mount_hash();
 		umount_tree(mnt, UMOUNT_SYNC);
 		unlock_mount_hash();
 	}
 out2:
-	unlock_mount(mp);
+	unlock_mount(&mp);
 out:
 	path_put(&old_path);
 	return err;
@@ -3461,18 +3389,14 @@ static int do_set_group(struct path *from_path, struct path *to_path)
 		goto out;
 
 	if (IS_MNT_SLAVE(from)) {
-		struct mount *m = from->mnt_master;
-
-		list_add(&to->mnt_slave, &from->mnt_slave);
-		to->mnt_master = m;
+		hlist_add_behind(&to->mnt_slave, &from->mnt_slave);
+		to->mnt_master = from->mnt_master;
 	}
 
 	if (IS_MNT_SHARED(from)) {
 		to->mnt_group_id = from->mnt_group_id;
 		list_add(&to->mnt_share, &from->mnt_share);
-		lock_mount_hash();
 		set_mnt_shared(to);
-		unlock_mount_hash();
 	}
 
 	err = 0;
@@ -3509,6 +3433,17 @@ static inline bool path_overmounted(const struct path *path)
 	return unlikely(!no_child);
 }
 
+/*
+ * Check if there is a possibly empty chain of descent from p1 to p2.
+ * Locks: namespace_sem (shared) or mount_lock (read_seqlock_excl).
+ */
+static bool mount_is_ancestor(const struct mount *p1, const struct mount *p2)
+{
+	while (p2 != p1 && mnt_has_parent(p2))
+		p2 = p2->mnt_parent;
+	return p2 == p1;
+}
+
 /**
  * can_move_mount_beneath - check that we can mount beneath the top mount
  * @from: mount to mount beneath
@@ -3560,9 +3495,8 @@ static int can_move_mount_beneath(const struct path *from,
 	if (parent_mnt_to == current->nsproxy->mnt_ns->root)
 		return -EINVAL;
 
-	for (struct mount *p = mnt_from; mnt_has_parent(p); p = p->mnt_parent)
-		if (p == mnt_to)
-			return -EINVAL;
+	if (mount_is_ancestor(mnt_to, mnt_from))
+		return -EINVAL;
 
 	/*
 	 * If the parent mount propagates to the child mount this would
@@ -3647,27 +3581,20 @@ static int do_move_mount(struct path *old_path,
 	struct mount *p;
 	struct mount *old;
 	struct mount *parent;
-	struct mountpoint *mp, *old_mp;
+	struct pinned_mountpoint mp;
 	int err;
-	bool attached, beneath = flags & MNT_TREE_BENEATH;
+	bool beneath = flags & MNT_TREE_BENEATH;
 
-	mp = do_lock_mount(new_path, beneath);
-	if (IS_ERR(mp))
-		return PTR_ERR(mp);
+	err = do_lock_mount(new_path, &mp, beneath);
+	if (err)
+		return err;
 
 	old = real_mount(old_path->mnt);
 	p = real_mount(new_path->mnt);
 	parent = old->mnt_parent;
-	attached = mnt_has_parent(old);
-	if (attached)
-		flags |= MNT_TREE_MOVE;
-	old_mp = old->mnt_mp;
 	ns = old->mnt_ns;
 
 	err = -EINVAL;
-	/* The thing moved must be mounted... */
-	if (!is_mounted(&old->mnt))
-		goto out;
 
 	if (check_mnt(old)) {
 		/* if the source is in our namespace... */
@@ -3677,13 +3604,14 @@ static int do_move_mount(struct path *old_path,
 		/* ... and the target should be in our namespace */
 		if (!check_mnt(p))
 			goto out;
+		/* parent of the source should not be shared */
+		if (IS_MNT_SHARED(parent))
+			goto out;
 	} else {
 		/*
 		 * otherwise the source must be the root of some anon namespace.
-		 * AV: check for mount being root of an anon namespace is worth
-		 * an inlined predicate...
 		 */
-		if (!is_anon_ns(ns) || mnt_has_parent(old))
+		if (!anon_ns_root(old))
 			goto out;
 		/*
 		 * Bail out early if the target is within the same namespace -
@@ -3706,20 +3634,14 @@ static int do_move_mount(struct path *old_path,
 	if (d_is_dir(new_path->dentry) !=
 	    d_is_dir(old_path->dentry))
 		goto out;
-	/*
-	 * Don't move a mount residing in a shared parent.
-	 */
-	if (attached && IS_MNT_SHARED(parent))
-		goto out;
 
 	if (beneath) {
-		err = can_move_mount_beneath(old_path, new_path, mp);
+		err = can_move_mount_beneath(old_path, new_path, mp.mp);
 		if (err)
 			goto out;
 
 		err = -EINVAL;
 		p = p->mnt_parent;
-		flags |= MNT_TREE_BENEATH;
 	}
 
 	/*
@@ -3731,30 +3653,12 @@ static int do_move_mount(struct path *old_path,
 	err = -ELOOP;
 	if (!check_for_nsfs_mounts(old))
 		goto out;
-	for (; mnt_has_parent(p); p = p->mnt_parent)
-		if (p == old)
-			goto out;
-
-	err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp, flags);
-	if (err)
+	if (mount_is_ancestor(old, p))
 		goto out;
 
-	/* if the mount is moved, it should no longer be expire
-	 * automatically */
-	list_del_init(&old->mnt_expire);
-	if (attached)
-		put_mountpoint(old_mp);
+	err = attach_recursive_mnt(old, p, mp.mp);
 out:
-	unlock_mount(mp);
-	if (!err) {
-		if (attached) {
-			mntput_no_expire(parent);
-		} else {
-			/* Make sure we notice when we leak mounts. */
-			VFS_WARN_ON_ONCE(!mnt_ns_empty(ns));
-			free_mnt_ns(ns);
-		}
-	}
+	unlock_mount(&mp);
 	return err;
 }
 
@@ -3815,7 +3719,7 @@ static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint,
 			   unsigned int mnt_flags)
 {
 	struct vfsmount *mnt;
-	struct mountpoint *mp;
+	struct pinned_mountpoint mp = {};
 	struct super_block *sb = fc->root->d_sb;
 	int error;
 
@@ -3836,13 +3740,12 @@ static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint,
 
 	mnt_warn_timestamp_expiry(mountpoint, mnt);
 
-	mp = lock_mount(mountpoint);
-	if (IS_ERR(mp)) {
-		mntput(mnt);
-		return PTR_ERR(mp);
+	error = lock_mount(mountpoint, &mp);
+	if (!error) {
+		error = do_add_mount(real_mount(mnt), mp.mp,
+				     mountpoint, mnt_flags);
+		unlock_mount(&mp);
 	}
-	error = do_add_mount(real_mount(mnt), mp, mountpoint, mnt_flags);
-	unlock_mount(mp);
 	if (error < 0)
 		mntput(mnt);
 	return error;
@@ -3910,7 +3813,7 @@ static int do_new_mount(struct path *path, const char *fstype, int sb_flags,
 int finish_automount(struct vfsmount *m, const struct path *path)
 {
 	struct dentry *dentry = path->dentry;
-	struct mountpoint *mp;
+	struct pinned_mountpoint mp = {};
 	struct mount *mnt;
 	int err;
 
@@ -3942,14 +3845,13 @@ int finish_automount(struct vfsmount *m, const struct path *path)
 		err = 0;
 		goto discard_locked;
 	}
-	mp = get_mountpoint(dentry);
-	if (IS_ERR(mp)) {
-		err = PTR_ERR(mp);
+	err = get_mountpoint(dentry, &mp);
+	if (err)
 		goto discard_locked;
-	}
 
-	err = do_add_mount(mnt, mp, path, path->mnt->mnt_flags | MNT_SHRINKABLE);
-	unlock_mount(mp);
+	err = do_add_mount(mnt, mp.mp, path,
+			   path->mnt->mnt_flags | MNT_SHRINKABLE);
+	unlock_mount(&mp);
 	if (unlikely(err))
 		goto discard;
 	return 0;
@@ -3958,12 +3860,6 @@ discard_locked:
 	namespace_unlock();
 	inode_unlock(dentry->d_inode);
 discard:
-	/* remove m from any expiration list it may be on */
-	if (!list_empty(&mnt->mnt_expire)) {
-		namespace_lock();
-		list_del_init(&mnt->mnt_expire);
-		namespace_unlock();
-	}
 	mntput(m);
 	return err;
 }
@@ -3975,11 +3871,9 @@ discard:
  */
 void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list)
 {
-	namespace_lock();
-
+	read_seqlock_excl(&mount_lock);
 	list_add_tail(&real_mount(mnt)->mnt_expire, expiry_list);
-
-	namespace_unlock();
+	read_sequnlock_excl(&mount_lock);
 }
 EXPORT_SYMBOL(mnt_set_expiry);
 
@@ -4333,7 +4227,7 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
 	/* First pass: copy the tree topology */
 	copy_flags = CL_COPY_UNBINDABLE | CL_EXPIRE;
 	if (user_ns != ns->user_ns)
-		copy_flags |= CL_SHARED_TO_SLAVE;
+		copy_flags |= CL_SLAVE;
 	new = copy_tree(old, old->mnt.mnt_root, copy_flags);
 	if (IS_ERR(new)) {
 		namespace_unlock();
@@ -4758,7 +4652,7 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 {
 	struct path new, old, root;
 	struct mount *new_mnt, *root_mnt, *old_mnt, *root_parent, *ex_parent;
-	struct mountpoint *old_mp, *root_mp;
+	struct pinned_mountpoint old_mp = {};
 	int error;
 
 	if (!may_mount())
@@ -4779,9 +4673,8 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 		goto out2;
 
 	get_fs_root(current->fs, &root);
-	old_mp = lock_mount(&old);
-	error = PTR_ERR(old_mp);
-	if (IS_ERR(old_mp))
+	error = lock_mount(&old, &old_mp);
+	if (error)
 		goto out3;
 
 	error = -EINVAL;
@@ -4808,11 +4701,11 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	if (!path_mounted(&root))
 		goto out4; /* not a mountpoint */
 	if (!mnt_has_parent(root_mnt))
-		goto out4; /* not attached */
+		goto out4; /* absolute root */
 	if (!path_mounted(&new))
 		goto out4; /* not a mountpoint */
 	if (!mnt_has_parent(new_mnt))
-		goto out4; /* not attached */
+		goto out4; /* absolute root */
 	/* make sure we can reach put_old from new_root */
 	if (!is_path_reachable(old_mnt, old.dentry, &new))
 		goto out4;
@@ -4821,29 +4714,25 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 		goto out4;
 	lock_mount_hash();
 	umount_mnt(new_mnt);
-	root_mp = unhash_mnt(root_mnt);  /* we'll need its mountpoint */
 	if (root_mnt->mnt.mnt_flags & MNT_LOCKED) {
 		new_mnt->mnt.mnt_flags |= MNT_LOCKED;
 		root_mnt->mnt.mnt_flags &= ~MNT_LOCKED;
 	}
-	/* mount old root on put_old */
-	attach_mnt(root_mnt, old_mnt, old_mp, false);
 	/* mount new_root on / */
-	attach_mnt(new_mnt, root_parent, root_mp, false);
-	mnt_add_count(root_parent, -1);
+	attach_mnt(new_mnt, root_parent, root_mnt->mnt_mp);
+	umount_mnt(root_mnt);
+	/* mount old root on put_old */
+	attach_mnt(root_mnt, old_mnt, old_mp.mp);
 	touch_mnt_namespace(current->nsproxy->mnt_ns);
 	/* A moved mount should not expire automatically */
 	list_del_init(&new_mnt->mnt_expire);
-	put_mountpoint(root_mp);
 	unlock_mount_hash();
 	mnt_notify_add(root_mnt);
 	mnt_notify_add(new_mnt);
 	chroot_fs_refs(&root, &new);
 	error = 0;
 out4:
-	unlock_mount(old_mp);
-	if (!error)
-		mntput_no_expire(ex_parent);
+	unlock_mount(&old_mp);
 out3:
 	path_put(&root);
 out2:
@@ -5045,22 +4934,7 @@ static int do_mount_setattr(struct path *path, struct mount_kattr *kattr)
 	err = -EINVAL;
 	lock_mount_hash();
 
-	/* Ensure that this isn't anything purely vfs internal. */
-	if (!is_mounted(&mnt->mnt))
-		goto out;
-
-	/*
-	 * If this is an attached mount make sure it's located in the callers
-	 * mount namespace. If it's not don't let the caller interact with it.
-	 *
-	 * If this mount doesn't have a parent it's most often simply a
-	 * detached mount with an anonymous mount namespace. IOW, something
-	 * that's simply not attached yet. But there are apparently also users
-	 * that do change mount properties on the rootfs itself. That obviously
-	 * neither has a parent nor is it a detached mount so we cannot
-	 * unconditionally check for detached mounts.
-	 */
-	if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt))
+	if (!anon_ns_root(mnt) && !check_mnt(mnt))
 		goto out;
 
 	/*
@@ -5424,7 +5298,7 @@ static void statmount_mnt_basic(struct kstatmount *s)
 	s->sm.mnt_parent_id_old = m->mnt_parent->mnt_id;
 	s->sm.mnt_attr = mnt_to_attr_flags(&m->mnt);
 	s->sm.mnt_propagation = mnt_to_propagation_flags(m);
-	s->sm.mnt_peer_group = IS_MNT_SHARED(m) ? m->mnt_group_id : 0;
+	s->sm.mnt_peer_group = m->mnt_group_id;
 	s->sm.mnt_master = IS_MNT_SLAVE(m) ? m->mnt_master->mnt_group_id : 0;
 }
 
@@ -6228,7 +6102,6 @@ static void __init init_mount_tree(void)
 
 	root.mnt = mnt;
 	root.dentry = mnt->mnt_root;
-	mnt->mnt_flags |= MNT_LOCKED;
 
 	set_fs_pwd(current->fs, &root);
 	set_fs_root(current->fs, &root);
@@ -6276,11 +6149,11 @@ void put_mnt_ns(struct mnt_namespace *ns)
 	if (!refcount_dec_and_test(&ns->ns.count))
 		return;
 	namespace_lock();
+	emptied_ns = ns;
 	lock_mount_hash();
 	umount_tree(ns->root, 0);
 	unlock_mount_hash();
 	namespace_unlock();
-	free_mnt_ns(ns);
 }
 
 struct vfsmount *kern_mount(struct file_system_type *type)
diff --git a/fs/pnode.c b/fs/pnode.c
index ffd429b760d5d4..81f7599bdac4fc 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -21,17 +21,12 @@ static inline struct mount *next_peer(struct mount *p)
 
 static inline struct mount *first_slave(struct mount *p)
 {
-	return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave);
-}
-
-static inline struct mount *last_slave(struct mount *p)
-{
-	return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave);
+	return hlist_entry(p->mnt_slave_list.first, struct mount, mnt_slave);
 }
 
 static inline struct mount *next_slave(struct mount *p)
 {
-	return list_entry(p->mnt_slave.next, struct mount, mnt_slave);
+	return hlist_entry(p->mnt_slave.next, struct mount, mnt_slave);
 }
 
 static struct mount *get_peer_under_root(struct mount *mnt,
@@ -70,69 +65,90 @@ int get_dominating_id(struct mount *mnt, const struct path *root)
 	return 0;
 }
 
-static int do_make_slave(struct mount *mnt)
+static inline bool will_be_unmounted(struct mount *m)
 {
-	struct mount *master, *slave_mnt;
+	return m->mnt.mnt_flags & MNT_UMOUNT;
+}
 
-	if (list_empty(&mnt->mnt_share)) {
-		if (IS_MNT_SHARED(mnt)) {
-			mnt_release_group_id(mnt);
-			CLEAR_MNT_SHARED(mnt);
-		}
-		master = mnt->mnt_master;
-		if (!master) {
-			struct list_head *p = &mnt->mnt_slave_list;
-			while (!list_empty(p)) {
-				slave_mnt = list_first_entry(p,
-						struct mount, mnt_slave);
-				list_del_init(&slave_mnt->mnt_slave);
-				slave_mnt->mnt_master = NULL;
-			}
-			return 0;
-		}
-	} else {
+static struct mount *propagation_source(struct mount *mnt)
+{
+	do {
 		struct mount *m;
-		/*
-		 * slave 'mnt' to a peer mount that has the
-		 * same root dentry. If none is available then
-		 * slave it to anything that is available.
-		 */
-		for (m = master = next_peer(mnt); m != mnt; m = next_peer(m)) {
-			if (m->mnt.mnt_root == mnt->mnt.mnt_root) {
-				master = m;
-				break;
-			}
+		for (m = next_peer(mnt); m != mnt; m = next_peer(m)) {
+			if (!will_be_unmounted(m))
+				return m;
 		}
-		list_del_init(&mnt->mnt_share);
-		mnt->mnt_group_id = 0;
-		CLEAR_MNT_SHARED(mnt);
+		mnt = mnt->mnt_master;
+	} while (mnt && will_be_unmounted(mnt));
+	return mnt;
+}
+
+static void transfer_propagation(struct mount *mnt, struct mount *to)
+{
+	struct hlist_node *p = NULL, *n;
+	struct mount *m;
+
+	hlist_for_each_entry_safe(m, n, &mnt->mnt_slave_list, mnt_slave) {
+		m->mnt_master = to;
+		if (!to)
+			hlist_del_init(&m->mnt_slave);
+		else
+			p = &m->mnt_slave;
 	}
-	list_for_each_entry(slave_mnt, &mnt->mnt_slave_list, mnt_slave)
-		slave_mnt->mnt_master = master;
-	list_move(&mnt->mnt_slave, &master->mnt_slave_list);
-	list_splice(&mnt->mnt_slave_list, master->mnt_slave_list.prev);
-	INIT_LIST_HEAD(&mnt->mnt_slave_list);
-	mnt->mnt_master = master;
-	return 0;
+	if (p)
+		hlist_splice_init(&mnt->mnt_slave_list, p, &to->mnt_slave_list);
 }
 
 /*
- * vfsmount lock must be held for write
+ * EXCL[namespace_sem]
  */
 void change_mnt_propagation(struct mount *mnt, int type)
 {
+	struct mount *m = mnt->mnt_master;
+
 	if (type == MS_SHARED) {
 		set_mnt_shared(mnt);
 		return;
 	}
-	do_make_slave(mnt);
-	if (type != MS_SLAVE) {
-		list_del_init(&mnt->mnt_slave);
+	if (IS_MNT_SHARED(mnt)) {
+		m = propagation_source(mnt);
+		if (list_empty(&mnt->mnt_share)) {
+			mnt_release_group_id(mnt);
+		} else {
+			list_del_init(&mnt->mnt_share);
+			mnt->mnt_group_id = 0;
+		}
+		CLEAR_MNT_SHARED(mnt);
+		transfer_propagation(mnt, m);
+	}
+	hlist_del_init(&mnt->mnt_slave);
+	if (type == MS_SLAVE) {
+		mnt->mnt_master = m;
+		if (m)
+			hlist_add_head(&mnt->mnt_slave, &m->mnt_slave_list);
+	} else {
 		mnt->mnt_master = NULL;
 		if (type == MS_UNBINDABLE)
-			mnt->mnt.mnt_flags |= MNT_UNBINDABLE;
+			mnt->mnt_t_flags |= T_UNBINDABLE;
 		else
-			mnt->mnt.mnt_flags &= ~MNT_UNBINDABLE;
+			mnt->mnt_t_flags &= ~T_UNBINDABLE;
+	}
+}
+
+static struct mount *__propagation_next(struct mount *m,
+					 struct mount *origin)
+{
+	while (1) {
+		struct mount *master = m->mnt_master;
+
+		if (master == origin->mnt_master) {
+			struct mount *next = next_peer(m);
+			return (next == origin) ? NULL : next;
+		} else if (m->mnt_slave.next)
+			return next_slave(m);
+
+		/* back at master */
+		m = master;
 	}
 }
 
@@ -150,34 +166,24 @@ static struct mount *propagation_next(struct mount *m,
 					 struct mount *origin)
 {
 	/* are there any slaves of this mount? */
-	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
+	if (!IS_MNT_NEW(m) && !hlist_empty(&m->mnt_slave_list))
 		return first_slave(m);
 
-	while (1) {
-		struct mount *master = m->mnt_master;
-
-		if (master == origin->mnt_master) {
-			struct mount *next = next_peer(m);
-			return (next == origin) ? NULL : next;
-		} else if (m->mnt_slave.next != &master->mnt_slave_list)
-			return next_slave(m);
-
-		/* back at master */
-		m = master;
-	}
+	return __propagation_next(m, origin);
 }
 
 static struct mount *skip_propagation_subtree(struct mount *m,
 						struct mount *origin)
 {
 	/*
-	 * Advance m such that propagation_next will not return
-	 * the slaves of m.
+	 * Advance m past everything that gets propagation from it.
 	 */
-	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
-		m = last_slave(m);
+	struct mount *p = __propagation_next(m, origin);
+
+	while (p && peers(m, p))
+		p = __propagation_next(p, origin);
 
-	return m;
+	return p;
 }
 
 static struct mount *next_group(struct mount *m, struct mount *origin)
@@ -185,7 +191,7 @@ static struct mount *next_group(struct mount *m, struct mount *origin)
 	while (1) {
 		while (1) {
 			struct mount *next;
-			if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
+			if (!IS_MNT_NEW(m) && !hlist_empty(&m->mnt_slave_list))
 				return first_slave(m);
 			next = next_peer(m);
 			if (m->mnt_group_id == origin->mnt_group_id) {
@@ -198,7 +204,7 @@ static struct mount *next_group(struct mount *m, struct mount *origin)
 		/* m is the last peer */
 		while (1) {
 			struct mount *master = m->mnt_master;
-			if (m->mnt_slave.next != &master->mnt_slave_list)
+			if (m->mnt_slave.next)
 				return next_slave(m);
 			m = next_peer(master);
 			if (master->mnt_group_id == origin->mnt_group_id)
@@ -212,142 +218,113 @@ static struct mount *next_group(struct mount *m, struct mount *origin)
 	}
 }
 
-/* all accesses are serialized by namespace_sem */
-static struct mount *last_dest, *first_source, *last_source, *dest_master;
-static struct hlist_head *list;
-
-static inline bool peers(const struct mount *m1, const struct mount *m2)
-{
-	return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id;
-}
-
-static int propagate_one(struct mount *m, struct mountpoint *dest_mp)
+static bool need_secondary(struct mount *m, struct mountpoint *dest_mp)
 {
-	struct mount *child;
-	int type;
 	/* skip ones added by this propagate_mnt() */
 	if (IS_MNT_NEW(m))
-		return 0;
+		return false;
 	/* skip if mountpoint isn't visible in m */
 	if (!is_subdir(dest_mp->m_dentry, m->mnt.mnt_root))
-		return 0;
+		return false;
 	/* skip if m is in the anon_ns */
 	if (is_anon_ns(m->mnt_ns))
-		return 0;
+		return false;
+	return true;
+}
 
-	if (peers(m, last_dest)) {
-		type = CL_MAKE_SHARED;
-	} else {
-		struct mount *n, *p;
-		bool done;
-		for (n = m; ; n = p) {
-			p = n->mnt_master;
-			if (p == dest_master || IS_MNT_MARKED(p))
-				break;
+static struct mount *find_master(struct mount *m,
+				struct mount *last_copy,
+				struct mount *original)
+{
+	struct mount *p;
+
+	// ascend until there's a copy for something with the same master
+	for (;;) {
+		p = m->mnt_master;
+		if (!p || IS_MNT_MARKED(p))
+			break;
+		m = p;
+	}
+	while (!peers(last_copy, original)) {
+		struct mount *parent = last_copy->mnt_parent;
+		if (parent->mnt_master == p) {
+			if (!peers(parent, m))
+				last_copy = last_copy->mnt_master;
+			break;
 		}
-		do {
-			struct mount *parent = last_source->mnt_parent;
-			if (peers(last_source, first_source))
-				break;
-			done = parent->mnt_master == p;
-			if (done && peers(n, parent))
-				break;
-			last_source = last_source->mnt_master;
-		} while (!done);
-
-		type = CL_SLAVE;
-		/* beginning of peer group among the slaves? */
-		if (IS_MNT_SHARED(m))
-			type |= CL_MAKE_SHARED;
+		last_copy = last_copy->mnt_master;
 	}
-		
-	child = copy_tree(last_source, last_source->mnt.mnt_root, type);
-	if (IS_ERR(child))
-		return PTR_ERR(child);
-	read_seqlock_excl(&mount_lock);
-	mnt_set_mountpoint(m, dest_mp, child);
-	if (m->mnt_master != dest_master)
-		SET_MNT_MARK(m->mnt_master);
-	read_sequnlock_excl(&mount_lock);
-	last_dest = m;
-	last_source = child;
-	hlist_add_head(&child->mnt_hash, list);
-	return count_mounts(m->mnt_ns, child);
+	return last_copy;
 }
 
-/*
- * mount 'source_mnt' under the destination 'dest_mnt' at
- * dentry 'dest_dentry'. And propagate that mount to
- * all the peer and slave mounts of 'dest_mnt'.
- * Link all the new mounts into a propagation tree headed at
- * source_mnt. Also link all the new mounts using ->mnt_list
- * headed at source_mnt's ->mnt_list
+/**
+ * propagate_mnt() - create secondary copies for tree attachment
+ * @dest_mnt:    destination mount.
+ * @dest_mp:     destination mountpoint.
+ * @source_mnt:  source mount.
+ * @tree_list:   list of secondaries to be attached.
  *
- * @dest_mnt: destination mount.
- * @dest_dentry: destination dentry.
- * @source_mnt: source mount.
- * @tree_list : list of heads of trees to be attached.
+ * Create secondary copies for attaching a tree with root @source_mnt
+ * at mount @dest_mnt with mountpoint @dest_mp.  Link all new mounts
+ * into a propagation graph.  Set mountpoints for all secondaries,
+ * link their roots into @tree_list via ->mnt_hash.
  */
 int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
-		    struct mount *source_mnt, struct hlist_head *tree_list)
+		  struct mount *source_mnt, struct hlist_head *tree_list)
 {
-	struct mount *m, *n;
-	int ret = 0;
-
-	/*
-	 * we don't want to bother passing tons of arguments to
-	 * propagate_one(); everything is serialized by namespace_sem,
-	 * so globals will do just fine.
-	 */
-	last_dest = dest_mnt;
-	first_source = source_mnt;
-	last_source = source_mnt;
-	list = tree_list;
-	dest_master = dest_mnt->mnt_master;
-
-	/* all peers of dest_mnt, except dest_mnt itself */
-	for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) {
-		ret = propagate_one(n, dest_mp);
-		if (ret)
-			goto out;
-	}
-
-	/* all slave groups */
-	for (m = next_group(dest_mnt, dest_mnt); m;
-			m = next_group(m, dest_mnt)) {
-		/* everything in that slave group */
-		n = m;
+	struct mount *m, *n, *copy, *this;
+	int err = 0, type;
+
+	if (dest_mnt->mnt_master)
+		SET_MNT_MARK(dest_mnt->mnt_master);
+
+	/* iterate over peer groups, depth first */
+	for (m = dest_mnt; m && !err; m = next_group(m, dest_mnt)) {
+		if (m == dest_mnt) { // have one for dest_mnt itself
+			copy = source_mnt;
+			type = CL_MAKE_SHARED;
+			n = next_peer(m);
+			if (n == m)
+				continue;
+		} else {
+			type = CL_SLAVE;
+			/* beginning of peer group among the slaves? */
+			if (IS_MNT_SHARED(m))
+				type |= CL_MAKE_SHARED;
+			n = m;
+		}
 		do {
-			ret = propagate_one(n, dest_mp);
-			if (ret)
-				goto out;
-			n = next_peer(n);
-		} while (n != m);
+			if (!need_secondary(n, dest_mp))
+				continue;
+			if (type & CL_SLAVE) // first in this peer group
+				copy = find_master(n, copy, source_mnt);
+			this = copy_tree(copy, copy->mnt.mnt_root, type);
+			if (IS_ERR(this)) {
+				err = PTR_ERR(this);
+				break;
+			}
+			read_seqlock_excl(&mount_lock);
+			mnt_set_mountpoint(n, dest_mp, this);
+			read_sequnlock_excl(&mount_lock);
+			if (n->mnt_master)
+				SET_MNT_MARK(n->mnt_master);
+			copy = this;
+			hlist_add_head(&this->mnt_hash, tree_list);
+			err = count_mounts(n->mnt_ns, this);
+			if (err)
+				break;
+			type = CL_MAKE_SHARED;
+		} while ((n = next_peer(n)) != m);
 	}
-out:
-	read_seqlock_excl(&mount_lock);
+
 	hlist_for_each_entry(n, tree_list, mnt_hash) {
 		m = n->mnt_parent;
-		if (m->mnt_master != dest_mnt->mnt_master)
+		if (m->mnt_master)
 			CLEAR_MNT_MARK(m->mnt_master);
 	}
-	read_sequnlock_excl(&mount_lock);
-	return ret;
-}
-
-static struct mount *find_topper(struct mount *mnt)
-{
-	/* If there is exactly one mount covering mnt completely return it. */
-	struct mount *child;
-
-	if (!list_is_singular(&mnt->mnt_mounts))
-		return NULL;
-
-	child = list_first_entry(&mnt->mnt_mounts, struct mount, mnt_child);
-	if (child->mnt_mountpoint != mnt->mnt.mnt_root)
-		return NULL;
-
-	return child;
+	if (dest_mnt->mnt_master)
+		CLEAR_MNT_MARK(dest_mnt->mnt_master);
+	return err;
 }
 
 /*
@@ -407,12 +384,8 @@ bool propagation_would_overmount(const struct mount *from,
  */
 int propagate_mount_busy(struct mount *mnt, int refcnt)
 {
-	struct mount *m, *child, *topper;
 	struct mount *parent = mnt->mnt_parent;
 
-	if (mnt == parent)
-		return do_refcount_check(mnt, refcnt);
-
 	/*
 	 * quickly check if the current mount can be unmounted.
 	 * If not, we don't have to go checking for all other
@@ -421,23 +394,27 @@ int propagate_mount_busy(struct mount *mnt, int refcnt)
 	if (!list_empty(&mnt->mnt_mounts) || do_refcount_check(mnt, refcnt))
 		return 1;
 
-	for (m = propagation_next(parent, parent); m;
+	if (mnt == parent)
+		return 0;
+
+	for (struct mount *m = propagation_next(parent, parent); m;
 	     		m = propagation_next(m, parent)) {
-		int count = 1;
-		child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
-		if (!child)
-			continue;
+		struct list_head *head;
+		struct mount *child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
 
-		/* Is there exactly one mount on the child that covers
-		 * it completely whose reference should be ignored?
-		 */
-		topper = find_topper(child);
-		if (topper)
-			count += 1;
-		else if (!list_empty(&child->mnt_mounts))
+		if (!child)
 			continue;
 
-		if (do_refcount_check(child, count))
+		head = &child->mnt_mounts;
+		if (!list_empty(head)) {
+			/*
+			 * a mount that covers child completely wouldn't prevent
+			 * it being pulled out; any other would.
+			 */
+			if (!list_is_singular(head) || !child->overmount)
+				continue;
+		}
+		if (do_refcount_check(child, 1))
 			return 1;
 	}
 	return 0;
@@ -463,181 +440,209 @@ void propagate_mount_unlock(struct mount *mnt)
 	}
 }
 
-static void umount_one(struct mount *mnt, struct list_head *to_umount)
+static inline bool is_candidate(struct mount *m)
 {
-	CLEAR_MNT_MARK(mnt);
-	mnt->mnt.mnt_flags |= MNT_UMOUNT;
-	list_del_init(&mnt->mnt_child);
-	list_del_init(&mnt->mnt_umounting);
-	move_from_ns(mnt, to_umount);
+	return m->mnt_t_flags & T_UMOUNT_CANDIDATE;
 }
 
-/*
- * NOTE: unmounting 'mnt' naturally propagates to all other mounts its
- * parent propagates to.
- */
-static bool __propagate_umount(struct mount *mnt,
-			       struct list_head *to_umount,
-			       struct list_head *to_restore)
+static void umount_one(struct mount *m, struct list_head *to_umount)
 {
-	bool progress = false;
-	struct mount *child;
-
-	/*
-	 * The state of the parent won't change if this mount is
-	 * already unmounted or marked as without children.
-	 */
-	if (mnt->mnt.mnt_flags & (MNT_UMOUNT | MNT_MARKED))
-		goto out;
+	m->mnt.mnt_flags |= MNT_UMOUNT;
+	list_del_init(&m->mnt_child);
+	move_from_ns(m);
+	list_add_tail(&m->mnt_list, to_umount);
+}
 
-	/* Verify topper is the only grandchild that has not been
-	 * speculatively unmounted.
-	 */
-	list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
-		if (child->mnt_mountpoint == mnt->mnt.mnt_root)
-			continue;
-		if (!list_empty(&child->mnt_umounting) && IS_MNT_MARKED(child))
-			continue;
-		/* Found a mounted child */
-		goto children;
-	}
+static void remove_from_candidate_list(struct mount *m)
+{
+	m->mnt_t_flags &= ~(T_MARKED | T_UMOUNT_CANDIDATE);
+	list_del_init(&m->mnt_list);
+}
 
-	/* Mark mounts that can be unmounted if not locked */
-	SET_MNT_MARK(mnt);
-	progress = true;
+static void gather_candidates(struct list_head *set,
+			      struct list_head *candidates)
+{
+	struct mount *m, *p, *q;
 
-	/* If a mount is without children and not locked umount it. */
-	if (!IS_MNT_LOCKED(mnt)) {
-		umount_one(mnt, to_umount);
-	} else {
-children:
-		list_move_tail(&mnt->mnt_umounting, to_restore);
+	list_for_each_entry(m, set, mnt_list) {
+		if (is_candidate(m))
+			continue;
+		m->mnt_t_flags |= T_UMOUNT_CANDIDATE;
+		p = m->mnt_parent;
+		q = propagation_next(p, p);
+		while (q) {
+			struct mount *child = __lookup_mnt(&q->mnt,
+							   m->mnt_mountpoint);
+			if (child) {
+				/*
+				 * We might've already run into this one.  That
+				 * must've happened on earlier iteration of the
+				 * outer loop; in that case we can skip those
+				 * parents that get propagation from q - there
+				 * will be nothing new on those as well.
+				 */
+				if (is_candidate(child)) {
+					q = skip_propagation_subtree(q, p);
+					continue;
+				}
+				child->mnt_t_flags |= T_UMOUNT_CANDIDATE;
+				if (!will_be_unmounted(child))
+					list_add(&child->mnt_list, candidates);
+			}
+			q = propagation_next(q, p);
+		}
 	}
-out:
-	return progress;
+	list_for_each_entry(m, set, mnt_list)
+		m->mnt_t_flags &= ~T_UMOUNT_CANDIDATE;
 }
 
-static void umount_list(struct list_head *to_umount,
-			struct list_head *to_restore)
+/*
+ * We know that some child of @m can't be unmounted.  In all places where the
+ * chain of descent of @m has child not overmounting the root of parent,
+ * the parent can't be unmounted either.
+ */
+static void trim_ancestors(struct mount *m)
 {
-	struct mount *mnt, *child, *tmp;
-	list_for_each_entry(mnt, to_umount, mnt_list) {
-		list_for_each_entry_safe(child, tmp, &mnt->mnt_mounts, mnt_child) {
-			/* topper? */
-			if (child->mnt_mountpoint == mnt->mnt.mnt_root)
-				list_move_tail(&child->mnt_umounting, to_restore);
-			else
-				umount_one(child, to_umount);
-		}
+	struct mount *p;
+
+	for (p = m->mnt_parent; is_candidate(p); m = p, p = p->mnt_parent) {
+		if (IS_MNT_MARKED(m))	// all candidates beneath are overmounts
+			return;
+		SET_MNT_MARK(m);
+		if (m != p->overmount)
+			p->mnt_t_flags &= ~T_UMOUNT_CANDIDATE;
 	}
 }
 
-static void restore_mounts(struct list_head *to_restore)
+/*
+ * Find and exclude all umount candidates forbidden by @m
+ * (see Documentation/filesystems/propagate_umount.txt)
+ * If we can immediately tell that @m is OK to unmount (unlocked
+ * and all children are already committed to unmounting) commit
+ * to unmounting it.
+ * Only @m itself might be taken from the candidates list;
+ * anything found by trim_ancestors() is marked non-candidate
+ * and left on the list.
+ */
+static void trim_one(struct mount *m, struct list_head *to_umount)
 {
-	/* Restore mounts to a clean working state */
-	while (!list_empty(to_restore)) {
-		struct mount *mnt, *parent;
-		struct mountpoint *mp;
-
-		mnt = list_first_entry(to_restore, struct mount, mnt_umounting);
-		CLEAR_MNT_MARK(mnt);
-		list_del_init(&mnt->mnt_umounting);
-
-		/* Should this mount be reparented? */
-		mp = mnt->mnt_mp;
-		parent = mnt->mnt_parent;
-		while (parent->mnt.mnt_flags & MNT_UMOUNT) {
-			mp = parent->mnt_mp;
-			parent = parent->mnt_parent;
-		}
-		if (parent != mnt->mnt_parent) {
-			mnt_change_mountpoint(parent, mp, mnt);
-			mnt_notify_add(mnt);
+	bool remove_this = false, found = false, umount_this = false;
+	struct mount *n;
+
+	if (!is_candidate(m)) { // trim_ancestors() left it on list
+		remove_from_candidate_list(m);
+		return;
+	}
+
+	list_for_each_entry(n, &m->mnt_mounts, mnt_child) {
+		if (!is_candidate(n)) {
+			found = true;
+			if (n != m->overmount) {
+				remove_this = true;
+				break;
+			}
 		}
 	}
+	if (found) {
+		trim_ancestors(m);
+	} else if (!IS_MNT_LOCKED(m) && list_empty(&m->mnt_mounts)) {
+		remove_this = true;
+		umount_this = true;
+	}
+	if (remove_this) {
+		remove_from_candidate_list(m);
+		if (umount_this)
+			umount_one(m, to_umount);
+	}
 }
 
-static void cleanup_umount_visitations(struct list_head *visited)
+static void handle_locked(struct mount *m, struct list_head *to_umount)
 {
-	while (!list_empty(visited)) {
-		struct mount *mnt =
-			list_first_entry(visited, struct mount, mnt_umounting);
-		list_del_init(&mnt->mnt_umounting);
+	struct mount *cutoff = m, *p;
+
+	if (!is_candidate(m)) { // trim_ancestors() left it on list
+		remove_from_candidate_list(m);
+		return;
+	}
+	for (p = m; is_candidate(p); p = p->mnt_parent) {
+		remove_from_candidate_list(p);
+		if (!IS_MNT_LOCKED(p))
+			cutoff = p->mnt_parent;
+	}
+	if (will_be_unmounted(p))
+		cutoff = p;
+	while (m != cutoff) {
+		umount_one(m, to_umount);
+		m = m->mnt_parent;
 	}
 }
 
 /*
- * collect all mounts that receive propagation from the mount in @list,
- * and return these additional mounts in the same list.
- * @list: the list of mounts to be unmounted.
+ * @m is not to going away, and it overmounts the top of a stack of mounts
+ * that are going away.  We know that all of those are fully overmounted
+ * by the one above (@m being the topmost of the chain), so @m can be slid
+ * in place where the bottom of the stack is attached.
  *
- * vfsmount lock must be held for write
+ * NOTE: here we temporarily violate a constraint - two mounts end up with
+ * the same parent and mountpoint; that will be remedied as soon as we
+ * return from propagate_umount() - its caller (umount_tree()) will detach
+ * the stack from the parent it (and now @m) is attached to.  umount_tree()
+ * might choose to keep unmounted pieces stuck to each other, but it always
+ * detaches them from the mounts that remain in the tree.
  */
-int propagate_umount(struct list_head *list)
+static void reparent(struct mount *m)
 {
-	struct mount *mnt;
-	LIST_HEAD(to_restore);
-	LIST_HEAD(to_umount);
-	LIST_HEAD(visited);
-
-	/* Find candidates for unmounting */
-	list_for_each_entry_reverse(mnt, list, mnt_list) {
-		struct mount *parent = mnt->mnt_parent;
-		struct mount *m;
+	struct mount *p = m;
+	struct mountpoint *mp;
 
-		/*
-		 * If this mount has already been visited it is known that it's
-		 * entire peer group and all of their slaves in the propagation
-		 * tree for the mountpoint has already been visited and there is
-		 * no need to visit them again.
-		 */
-		if (!list_empty(&mnt->mnt_umounting))
-			continue;
+	do {
+		mp = p->mnt_mp;
+		p = p->mnt_parent;
+	} while (will_be_unmounted(p));
 
-		list_add_tail(&mnt->mnt_umounting, &visited);
-		for (m = propagation_next(parent, parent); m;
-		     m = propagation_next(m, parent)) {
-			struct mount *child = __lookup_mnt(&m->mnt,
-							   mnt->mnt_mountpoint);
-			if (!child)
-				continue;
+	mnt_change_mountpoint(p, mp, m);
+	mnt_notify_add(m);
+}
 
-			if (!list_empty(&child->mnt_umounting)) {
-				/*
-				 * If the child has already been visited it is
-				 * know that it's entire peer group and all of
-				 * their slaves in the propgation tree for the
-				 * mountpoint has already been visited and there
-				 * is no need to visit this subtree again.
-				 */
-				m = skip_propagation_subtree(m, parent);
-				continue;
-			} else if (child->mnt.mnt_flags & MNT_UMOUNT) {
-				/*
-				 * We have come across a partially unmounted
-				 * mount in a list that has not been visited
-				 * yet. Remember it has been visited and
-				 * continue about our merry way.
-				 */
-				list_add_tail(&child->mnt_umounting, &visited);
-				continue;
-			}
+/**
+ * propagate_umount - apply propagation rules to the set of mounts for umount()
+ * @set: the list of mounts to be unmounted.
+ *
+ * Collect all mounts that receive propagation from the mount in @set and have
+ * no obstacles to being unmounted.  Add these additional mounts to the set.
+ *
+ * See Documentation/filesystems/propagate_umount.txt if you do anything in
+ * this area.
+ *
+ * Locks held:
+ * mount_lock (write_seqlock), namespace_sem (exclusive).
+ */
+void propagate_umount(struct list_head *set)
+{
+	struct mount *m, *p;
+	LIST_HEAD(to_umount);	// committed to unmounting
+	LIST_HEAD(candidates);	// undecided umount candidates
 
-			/* Check the child and parents while progress is made */
-			while (__propagate_umount(child,
-						  &to_umount, &to_restore)) {
-				/* Is the parent a umount candidate? */
-				child = child->mnt_parent;
-				if (list_empty(&child->mnt_umounting))
-					break;
-			}
-		}
+	// collect all candidates
+	gather_candidates(set, &candidates);
+
+	// reduce the set until it's non-shifting
+	list_for_each_entry_safe(m, p, &candidates, mnt_list)
+		trim_one(m, &to_umount);
+
+	// ... and non-revealing
+	while (!list_empty(&candidates)) {
+		m = list_first_entry(&candidates,struct mount, mnt_list);
+		handle_locked(m, &to_umount);
 	}
 
-	umount_list(&to_umount, &to_restore);
-	restore_mounts(&to_restore);
-	cleanup_umount_visitations(&visited);
-	list_splice_tail(&to_umount, list);
+	// now to_umount consists of all acceptable candidates
+	// deal with reparenting of remaining overmounts on those
+	list_for_each_entry(m, &to_umount, mnt_list) {
+		if (m->overmount)
+			reparent(m->overmount);
+	}
 
-	return 0;
+	// and fold them into the set
+	list_splice_tail_init(&to_umount, set);
 }
diff --git a/fs/pnode.h b/fs/pnode.h
index 2d026fb98b182b..00ab153e3e9d32 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -10,14 +10,14 @@
 #include <linux/list.h>
 #include "mount.h"
 
-#define IS_MNT_SHARED(m) ((m)->mnt.mnt_flags & MNT_SHARED)
+#define IS_MNT_SHARED(m) ((m)->mnt_t_flags & T_SHARED)
 #define IS_MNT_SLAVE(m) ((m)->mnt_master)
 #define IS_MNT_NEW(m) (!(m)->mnt_ns)
-#define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED)
-#define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE)
-#define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED)
-#define SET_MNT_MARK(m) ((m)->mnt.mnt_flags |= MNT_MARKED)
-#define CLEAR_MNT_MARK(m) ((m)->mnt.mnt_flags &= ~MNT_MARKED)
+#define CLEAR_MNT_SHARED(m) ((m)->mnt_t_flags &= ~T_SHARED)
+#define IS_MNT_UNBINDABLE(m) ((m)->mnt_t_flags & T_UNBINDABLE)
+#define IS_MNT_MARKED(m) ((m)->mnt_t_flags & T_MARKED)
+#define SET_MNT_MARK(m) ((m)->mnt_t_flags |= T_MARKED)
+#define CLEAR_MNT_MARK(m) ((m)->mnt_t_flags &= ~T_MARKED)
 #define IS_MNT_LOCKED(m) ((m)->mnt.mnt_flags & MNT_LOCKED)
 
 #define CL_EXPIRE    		0x01
@@ -25,19 +25,26 @@
 #define CL_COPY_UNBINDABLE	0x04
 #define CL_MAKE_SHARED 		0x08
 #define CL_PRIVATE 		0x10
-#define CL_SHARED_TO_SLAVE	0x20
 #define CL_COPY_MNT_NS_FILE	0x40
 
+/*
+ * EXCL[namespace_sem]
+ */
 static inline void set_mnt_shared(struct mount *mnt)
 {
-	mnt->mnt.mnt_flags &= ~MNT_SHARED_MASK;
-	mnt->mnt.mnt_flags |= MNT_SHARED;
+	mnt->mnt_t_flags &= ~T_SHARED_MASK;
+	mnt->mnt_t_flags |= T_SHARED;
+}
+
+static inline bool peers(const struct mount *m1, const struct mount *m2)
+{
+	return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id;
 }
 
 void change_mnt_propagation(struct mount *, int);
 int propagate_mnt(struct mount *, struct mountpoint *, struct mount *,
 		struct hlist_head *);
-int propagate_umount(struct list_head *);
+void propagate_umount(struct list_head *);
 int propagate_mount_busy(struct mount *, int);
 void propagate_mount_unlock(struct mount *);
 void mnt_release_group_id(struct mount *);
author	Linus Torvalds <torvalds@linux-foundation.org>	2025-07-28 10:49:38 -0700
committer	Linus Torvalds <torvalds@linux-foundation.org>	2025-07-28 10:49:38 -0700
commit	794cbac9c053155754d04231b9365f91ea4ce7d2 (patch)
tree	2ce6a817a77146b52c8937426cbcbd023a401174 /fs
parent	953e117bf4aad7e1d01419d4bcc03ab93420387c (diff)
parent	a7cce099450f8fc597a6ac215440666610895fb7 (diff)
download	linux-794cbac9c053155754d04231b9365f91ea4ce7d2.tar.gz