Merge tag 'vfs-6.15-rc1.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs mount updates from Christian Brauner:

 - Mount notifications

   The day has come where we finally provide a new api to listen for
   mount topology changes outside of /proc/<pid>/mountinfo. A mount
   namespace file descriptor can be supplied and registered with
   fanotify to listen for mount topology changes.

   Currently notifications for mount, umount and moving mounts are
   generated. The generated notification record contains the unique
   mount id of the mount.

   The listmount() and statmount() api can be used to query detailed
   information about the mount using the received unique mount id.

   This allows userspace to figure out exactly how the mount topology
   changed without having to generating diffs of /proc/<pid>/mountinfo
   in userspace.

 - Support O_PATH file descriptors with FSCONFIG_SET_FD in the new mount
   api

 - Support detached mounts in overlayfs

   Since last cycle we support specifying overlayfs layers via file
   descriptors. However, we don't allow detached mounts which means
   userspace cannot user file descriptors received via
   open_tree(OPEN_TREE_CLONE) and fsmount() directly. They have to
   attach them to a mount namespace via move_mount() first.

   This is cumbersome and means they have to undo mounts via umount().
   Allow them to directly use detached mounts.

 - Allow to retrieve idmappings with statmount

   Currently it isn't possible to figure out what idmapping has been
   attached to an idmapped mount. Add an extension to statmount() which
   allows to read the idmapping from the mount.

 - Allow creating idmapped mounts from mounts that are already idmapped

   So far it isn't possible to allow the creation of idmapped mounts
   from already idmapped mounts as this has significant lifetime
   implications. Make the creation of idmapped mounts atomic by allow to
   pass struct mount_attr together with the open_tree_attr() system call
   allowing to solve these issues without complicating VFS lookup in any
   way.

   The system call has in general the benefit that creating a detached
   mount and applying mount attributes to it becomes an atomic operation
   for userspace.

 - Add a way to query statmount() for supported options

   Allow userspace to query which mount information can be retrieved
   through statmount().

 - Allow superblock owners to force unmount

* tag 'vfs-6.15-rc1.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (21 commits)
  umount: Allow superblock owners to force umount
  selftests: add tests for mount notification
  selinux: add FILE__WATCH_MOUNTNS
  samples/vfs: fix printf format string for size_t
  fs: allow changing idmappings
  fs: add kflags member to struct mount_kattr
  fs: add open_tree_attr()
  fs: add copy_mount_setattr() helper
  fs: add vfs_open_tree() helper
  statmount: add a new supported_mask field
  samples/vfs: add STATMOUNT_MNT_{G,U}IDMAP
  selftests: add tests for using detached mount with overlayfs
  samples/vfs: check whether flag was raised
  statmount: allow to retrieve idmappings
  uidgid: add map_id_range_up()
  fs: allow detached mounts in clone_private_mount()
  selftests/overlayfs: test specifying layers as O_PATH file descriptors
  fs: support O_PATH fds with FSCONFIG_SET_FD
  vfs: add notifications for mount attach and detach
  fanotify: notify on mount attach and detach
  ...

14 files changed, 642 insertions, 151 deletions

diff --git a/fs/autofs/autofs_i.h b/fs/autofs/autofs_i.h
index 77c7991d89aa..23cea74f9933 100644
--- a/fs/autofs/autofs_i.h
+++ b/fs/autofs/autofs_i.h
@@ -218,6 +218,8 @@ void autofs_clean_ino(struct autofs_info *);
 
 static inline int autofs_check_pipe(struct file *pipe)
 {
+	if (pipe->f_mode & FMODE_PATH)
+		return -EINVAL;
 	if (!(pipe->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
 	if (!S_ISFIFO(file_inode(pipe)->i_mode))
diff --git a/fs/fsopen.c b/fs/fsopen.c
index 094a7f510edf..1aaf4cb2afb2 100644
--- a/fs/fsopen.c
+++ b/fs/fsopen.c
@@ -453,7 +453,7 @@ SYSCALL_DEFINE5(fsconfig,
 	case FSCONFIG_SET_FD:
 		param.type = fs_value_is_file;
 		ret = -EBADF;
-		param.file = fget(aux);
+		param.file = fget_raw(aux);
 		if (!param.file)
 			goto out_key;
 		param.dirfd = aux;
diff --git a/fs/internal.h b/fs/internal.h
index 82127c69e641..4c19d15ef08a 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -338,3 +338,4 @@ static inline bool path_mounted(const struct path *path)
 }
 void file_f_owner_release(struct file *file);
 bool file_seek_cur_needs_f_lock(struct file *file);
+int statmount_mnt_idmap(struct mnt_idmap *idmap, struct seq_file *seq, bool uid_map);
diff --git a/fs/mnt_idmapping.c b/fs/mnt_idmapping.c
index 7b1df8cc2821..a37991fdb194 100644
--- a/fs/mnt_idmapping.c
+++ b/fs/mnt_idmapping.c
@@ -6,6 +6,7 @@
 #include <linux/mnt_idmapping.h>
 #include <linux/slab.h>
 #include <linux/user_namespace.h>
+#include <linux/seq_file.h>
 
 #include "internal.h"
 
@@ -334,3 +335,53 @@ void mnt_idmap_put(struct mnt_idmap *idmap)
 		free_mnt_idmap(idmap);
 }
 EXPORT_SYMBOL_GPL(mnt_idmap_put);
+
+int statmount_mnt_idmap(struct mnt_idmap *idmap, struct seq_file *seq, bool uid_map)
+{
+	struct uid_gid_map *map, *map_up;
+	u32 idx, nr_mappings;
+
+	if (!is_valid_mnt_idmap(idmap))
+		return 0;
+
+	/*
+	 * Idmappings are shown relative to the caller's idmapping.
+	 * This is both the most intuitive and most useful solution.
+	 */
+	if (uid_map) {
+		map = &idmap->uid_map;
+		map_up = &current_user_ns()->uid_map;
+	} else {
+		map = &idmap->gid_map;
+		map_up = &current_user_ns()->gid_map;
+	}
+
+	for (idx = 0, nr_mappings = 0; idx < map->nr_extents; idx++) {
+		uid_t lower;
+		struct uid_gid_extent *extent;
+
+		if (map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
+			extent = &map->extent[idx];
+		else
+			extent = &map->forward[idx];
+
+		/*
+		 * Verify that the whole range of the mapping can be
+		 * resolved in the caller's idmapping. If it cannot be
+		 * resolved skip the mapping.
+		 */
+		lower = map_id_range_up(map_up, extent->lower_first, extent->count);
+		if (lower == (uid_t) -1)
+			continue;
+
+		seq_printf(seq, "%u %u %u", extent->first, lower, extent->count);
+
+		seq->count++; /* mappings are separated by \0 */
+		if (seq_has_overflowed(seq))
+			return -EAGAIN;
+
+		nr_mappings++;
+	}
+
+	return nr_mappings;
+}
diff --git a/fs/mount.h b/fs/mount.h
index ffb613cdfeee..946dc8b792d7 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -5,6 +5,8 @@
 #include <linux/ns_common.h>
 #include <linux/fs_pin.h>
 
+extern struct list_head notify_list;
+
 struct mnt_namespace {
 	struct ns_common	ns;
 	struct mount *	root;
@@ -21,6 +23,10 @@ struct mnt_namespace {
 		struct rcu_head		mnt_ns_rcu;
 	};
 	u64 event;
+#ifdef CONFIG_FSNOTIFY
+	__u32			n_fsnotify_mask;
+	struct fsnotify_mark_connector __rcu *n_fsnotify_marks;
+#endif
 	unsigned int		nr_mounts; /* # of mounts in the namespace */
 	unsigned int		pending_mounts;
 	struct rb_node		mnt_ns_tree_node; /* node in the mnt_ns_tree */
@@ -76,6 +82,8 @@ struct mount {
 #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_id;			/* mount identifier, reused */
 	u64 mnt_id_unique;		/* mount ID unique until reboot */
@@ -177,3 +185,21 @@ static inline struct mnt_namespace *to_mnt_ns(struct ns_common *ns)
 {
 	return container_of(ns, struct mnt_namespace, ns);
 }
+
+#ifdef CONFIG_FSNOTIFY
+static inline void mnt_notify_add(struct mount *m)
+{
+	/* Optimize the case where there are no watches */
+	if ((m->mnt_ns && m->mnt_ns->n_fsnotify_marks) ||
+	    (m->prev_ns && m->prev_ns->n_fsnotify_marks))
+		list_add_tail(&m->to_notify, &notify_list);
+	else
+		m->prev_ns = m->mnt_ns;
+}
+#else
+static inline void mnt_notify_add(struct mount *m)
+{
+}
+#endif
+
+struct mnt_namespace *mnt_ns_from_dentry(struct dentry *dentry);
diff --git a/fs/namespace.c b/fs/namespace.c
index 8f1000f9f3df..4c8bd48c8a62 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -81,15 +81,23 @@ static HLIST_HEAD(unmounted);	/* protected by namespace_sem */
 static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */
 static DEFINE_SEQLOCK(mnt_ns_tree_lock);
 
+#ifdef CONFIG_FSNOTIFY
+LIST_HEAD(notify_list); /* protected by namespace_sem */
+#endif
 static struct rb_root mnt_ns_tree = RB_ROOT; /* protected by mnt_ns_tree_lock */
 static LIST_HEAD(mnt_ns_list); /* protected by mnt_ns_tree_lock */
 
+enum mount_kattr_flags_t {
+	MOUNT_KATTR_RECURSE		= (1 << 0),
+	MOUNT_KATTR_IDMAP_REPLACE	= (1 << 1),
+};
+
 struct mount_kattr {
 	unsigned int attr_set;
 	unsigned int attr_clr;
 	unsigned int propagation;
 	unsigned int lookup_flags;
-	bool recurse;
+	enum mount_kattr_flags_t kflags;
 	struct user_namespace *mnt_userns;
 	struct mnt_idmap *mnt_idmap;
 };
@@ -163,6 +171,7 @@ static void mnt_ns_release(struct mnt_namespace *ns)
 {
 	/* keep alive for {list,stat}mount() */
 	if (refcount_dec_and_test(&ns->passive)) {
+		fsnotify_mntns_delete(ns);
 		put_user_ns(ns->user_ns);
 		kfree(ns);
 	}
@@ -1176,6 +1185,8 @@ static void mnt_add_to_ns(struct mnt_namespace *ns, struct mount *mnt)
 		ns->mnt_first_node = &mnt->mnt_node;
 	rb_link_node(&mnt->mnt_node, parent, link);
 	rb_insert_color(&mnt->mnt_node, &ns->mounts);
+
+	mnt_notify_add(mnt);
 }
 
 /*
@@ -1723,6 +1734,50 @@ int may_umount(struct vfsmount *mnt)
 
 EXPORT_SYMBOL(may_umount);
 
+#ifdef CONFIG_FSNOTIFY
+static void mnt_notify(struct mount *p)
+{
+	if (!p->prev_ns && p->mnt_ns) {
+		fsnotify_mnt_attach(p->mnt_ns, &p->mnt);
+	} else if (p->prev_ns && !p->mnt_ns) {
+		fsnotify_mnt_detach(p->prev_ns, &p->mnt);
+	} else if (p->prev_ns == p->mnt_ns) {
+		fsnotify_mnt_move(p->mnt_ns, &p->mnt);
+	} else {
+		fsnotify_mnt_detach(p->prev_ns, &p->mnt);
+		fsnotify_mnt_attach(p->mnt_ns, &p->mnt);
+	}
+	p->prev_ns = p->mnt_ns;
+}
+
+static void notify_mnt_list(void)
+{
+	struct mount *m, *tmp;
+	/*
+	 * Notify about mounts that were added/reparented/detached/remain
+	 * connected after unmount.
+	 */
+	list_for_each_entry_safe(m, tmp, &notify_list, to_notify) {
+		mnt_notify(m);
+		list_del_init(&m->to_notify);
+	}
+}
+
+static bool need_notify_mnt_list(void)
+{
+	return !list_empty(&notify_list);
+}
+#else
+static void notify_mnt_list(void)
+{
+}
+
+static bool need_notify_mnt_list(void)
+{
+	return false;
+}
+#endif
+
 static void namespace_unlock(void)
 {
 	struct hlist_head head;
@@ -1733,7 +1788,18 @@ static void namespace_unlock(void)
 	hlist_move_list(&unmounted, &head);
 	list_splice_init(&ex_mountpoints, &list);
 
-	up_write(&namespace_sem);
+	if (need_notify_mnt_list()) {
+		/*
+		 * No point blocking out concurrent readers while notifications
+		 * are sent. This will also allow statmount()/listmount() to run
+		 * concurrently.
+		 */
+		downgrade_write(&namespace_sem);
+		notify_mnt_list();
+		up_read(&namespace_sem);
+	} else {
+		up_write(&namespace_sem);
+	}
 
 	shrink_dentry_list(&list);
 
@@ -1846,6 +1912,19 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 		change_mnt_propagation(p, MS_PRIVATE);
 		if (disconnect)
 			hlist_add_head(&p->mnt_umount, &unmounted);
+
+		/*
+		 * At this point p->mnt_ns is NULL, notification will be queued
+		 * only if
+		 *
+		 *  - p->prev_ns is non-NULL *and*
+		 *  - p->prev_ns->n_fsnotify_marks is non-NULL
+		 *
+		 * This will preclude queuing the mount if this is a cleanup
+		 * after a failed copy_tree() or destruction of an anonymous
+		 * namespace, etc.
+		 */
+		mnt_notify_add(p);
 	}
 }
 
@@ -2026,6 +2105,7 @@ static void warn_mandlock(void)
 static int can_umount(const struct path *path, int flags)
 {
 	struct mount *mnt = real_mount(path->mnt);
+	struct super_block *sb = path->dentry->d_sb;
 
 	if (!may_mount())
 		return -EPERM;
@@ -2035,7 +2115,7 @@ static int can_umount(const struct path *path, int flags)
 		return -EINVAL;
 	if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */
 		return -EINVAL;
-	if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN))
+	if (flags & MNT_FORCE && !ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 	return 0;
 }
@@ -2145,16 +2225,24 @@ struct mnt_namespace *get_sequential_mnt_ns(struct mnt_namespace *mntns, bool pr
 	}
 }
 
+struct mnt_namespace *mnt_ns_from_dentry(struct dentry *dentry)
+{
+	if (!is_mnt_ns_file(dentry))
+		return NULL;
+
+	return to_mnt_ns(get_proc_ns(dentry->d_inode));
+}
+
 static bool mnt_ns_loop(struct dentry *dentry)
 {
 	/* Could bind mounting the mount namespace inode cause a
 	 * mount namespace loop?
 	 */
-	struct mnt_namespace *mnt_ns;
-	if (!is_mnt_ns_file(dentry))
+	struct mnt_namespace *mnt_ns = mnt_ns_from_dentry(dentry);
+
+	if (!mnt_ns)
 		return false;
 
-	mnt_ns = to_mnt_ns(get_proc_ns(dentry->d_inode));
 	return current->nsproxy->mnt_ns->seq >= mnt_ns->seq;
 }
 
@@ -2287,6 +2375,28 @@ bool has_locked_children(struct mount *mnt, struct dentry *dentry)
 	return false;
 }
 
+/*
+ * Check that there aren't references to earlier/same mount namespaces in the
+ * specified subtree.  Such references can act as pins for mount namespaces
+ * that aren't checked by the mount-cycle checking code, thereby allowing
+ * cycles to be made.
+ */
+static bool check_for_nsfs_mounts(struct mount *subtree)
+{
+	struct mount *p;
+	bool ret = false;
+
+	lock_mount_hash();
+	for (p = subtree; p; p = next_mnt(p, subtree))
+		if (mnt_ns_loop(p->mnt.mnt_root))
+			goto out;
+
+	ret = true;
+out:
+	unlock_mount_hash();
+	return ret;
+}
+
 /**
  * clone_private_mount - create a private clone of a path
  * @path: path to clone
@@ -2295,6 +2405,8 @@ bool has_locked_children(struct mount *mnt, struct dentry *dentry)
  * will not be attached anywhere in the namespace and will be private (i.e.
  * changes to the originating mount won't be propagated into this).
  *
+ * This assumes caller has called or done the equivalent of may_mount().
+ *
  * Release with mntput().
  */
 struct vfsmount *clone_private_mount(const struct path *path)
@@ -2302,30 +2414,36 @@ struct vfsmount *clone_private_mount(const struct path *path)
 	struct mount *old_mnt = real_mount(path->mnt);
 	struct mount *new_mnt;
 
-	down_read(&namespace_sem);
+	scoped_guard(rwsem_read, &namespace_sem)
 	if (IS_MNT_UNBINDABLE(old_mnt))
-		goto invalid;
+		return ERR_PTR(-EINVAL);
+
+	if (mnt_has_parent(old_mnt)) {
+		if (!check_mnt(old_mnt))
+			return ERR_PTR(-EINVAL);
+	} else {
+		if (!is_mounted(&old_mnt->mnt))
+			return ERR_PTR(-EINVAL);
 
-	if (!check_mnt(old_mnt))
-		goto invalid;
+		/* Make sure this isn't something purely kernel internal. */
+		if (!is_anon_ns(old_mnt->mnt_ns))
+			return ERR_PTR(-EINVAL);
+
+		/* Make sure we don't create mount namespace loops. */
+		if (!check_for_nsfs_mounts(old_mnt))
+			return ERR_PTR(-EINVAL);
+	}
 
 	if (has_locked_children(old_mnt, path->dentry))
-		goto invalid;
+		return ERR_PTR(-EINVAL);
 
 	new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE);
-	up_read(&namespace_sem);
-
 	if (IS_ERR(new_mnt))
-		return ERR_CAST(new_mnt);
+		return ERR_PTR(-EINVAL);
 
 	/* Longterm mount to be removed by kern_unmount*() */
 	new_mnt->mnt_ns = MNT_NS_INTERNAL;
-
 	return &new_mnt->mnt;
-
-invalid:
-	up_read(&namespace_sem);
-	return ERR_PTR(-EINVAL);
 }
 EXPORT_SYMBOL_GPL(clone_private_mount);
 
@@ -2547,6 +2665,7 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 			dest_mp = smp;
 		unhash_mnt(source_mnt);
 		attach_mnt(source_mnt, top_mnt, dest_mp, beneath);
+		mnt_notify_add(source_mnt);
 		touch_mnt_namespace(source_mnt->mnt_ns);
 	} else {
 		if (source_mnt->mnt_ns) {
@@ -2889,24 +3008,22 @@ static struct file *open_detached_copy(struct path *path, bool recursive)
 	return file;
 }
 
-SYSCALL_DEFINE3(open_tree, int, dfd, const char __user *, filename, unsigned, flags)
+static struct file *vfs_open_tree(int dfd, const char __user *filename, unsigned int flags)
 {
-	struct file *file;
-	struct path path;
+	int ret;
+	struct path path __free(path_put) = {};
 	int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW;
 	bool detached = flags & OPEN_TREE_CLONE;
-	int error;
-	int fd;
 
 	BUILD_BUG_ON(OPEN_TREE_CLOEXEC != O_CLOEXEC);
 
 	if (flags & ~(AT_EMPTY_PATH | AT_NO_AUTOMOUNT | AT_RECURSIVE |
 		      AT_SYMLINK_NOFOLLOW | OPEN_TREE_CLONE |
 		      OPEN_TREE_CLOEXEC))
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 
 	if ((flags & (AT_RECURSIVE | OPEN_TREE_CLONE)) == AT_RECURSIVE)
-		return -EINVAL;
+		return ERR_PTR(-EINVAL);
 
 	if (flags & AT_NO_AUTOMOUNT)
 		lookup_flags &= ~LOOKUP_AUTOMOUNT;
@@ -2916,27 +3033,32 @@ SYSCALL_DEFINE3(open_tree, int, dfd, const char __user *, filename, unsigned, fl
 		lookup_flags |= LOOKUP_EMPTY;
 
 	if (detached && !may_mount())
-		return -EPERM;
+		return ERR_PTR(-EPERM);
+
+	ret = user_path_at(dfd, filename, lookup_flags, &path);
+	if (unlikely(ret))
+		return ERR_PTR(ret);
+
+	if (detached)
+		return open_detached_copy(&path, flags & AT_RECURSIVE);
+
+	return dentry_open(&path, O_PATH, current_cred());
+}
+
+SYSCALL_DEFINE3(open_tree, int, dfd, const char __user *, filename, unsigned, flags)
+{
+	int fd;
+	struct file *file __free(fput) = NULL;
+
+	file = vfs_open_tree(dfd, filename, flags);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
 
 	fd = get_unused_fd_flags(flags & O_CLOEXEC);
 	if (fd < 0)
 		return fd;
 
-	error = user_path_at(dfd, filename, lookup_flags, &path);
-	if (unlikely(error)) {
-		file = ERR_PTR(error);
-	} else {
-		if (detached)
-			file = open_detached_copy(&path, flags & AT_RECURSIVE);
-		else
-			file = dentry_open(&path, O_PATH, current_cred());
-		path_put(&path);
-	}
-	if (IS_ERR(file)) {
-		put_unused_fd(fd);
-		return PTR_ERR(file);
-	}
-	fd_install(fd, file);
+	fd_install(fd, no_free_ptr(file));
 	return fd;
 }
 
@@ -3123,28 +3245,6 @@ static inline int tree_contains_unbindable(struct mount *mnt)
 	return 0;
 }
 
-/*
- * Check that there aren't references to earlier/same mount namespaces in the
- * specified subtree.  Such references can act as pins for mount namespaces
- * that aren't checked by the mount-cycle checking code, thereby allowing
- * cycles to be made.
- */
-static bool check_for_nsfs_mounts(struct mount *subtree)
-{
-	struct mount *p;
-	bool ret = false;
-
-	lock_mount_hash();
-	for (p = subtree; p; p = next_mnt(p, subtree))
-		if (mnt_ns_loop(p->mnt.mnt_root))
-			goto out;
-
-	ret = true;
-out:
-	unlock_mount_hash();
-	return ret;
-}
-
 static int do_set_group(struct path *from_path, struct path *to_path)
 {
 	struct mount *from, *to;
@@ -4468,6 +4568,8 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	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:
@@ -4512,11 +4614,10 @@ static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt)
 		return -EINVAL;
 
 	/*
-	 * Once a mount has been idmapped we don't allow it to change its
-	 * mapping. It makes things simpler and callers can just create
-	 * another bind-mount they can idmap if they want to.
+	 * We only allow an mount to change it's idmapping if it has
+	 * never been accessible to userspace.
 	 */
-	if (is_idmapped_mnt(m))
+	if (!(kattr->kflags & MOUNT_KATTR_IDMAP_REPLACE) && is_idmapped_mnt(m))
 		return -EPERM;
 
 	/* The underlying filesystem doesn't support idmapped mounts yet. */
@@ -4576,7 +4677,7 @@ static int mount_setattr_prepare(struct mount_kattr *kattr, struct mount *mnt)
 				break;
 		}
 
-		if (!kattr->recurse)
+		if (!(kattr->kflags & MOUNT_KATTR_RECURSE))
 			return 0;
 	}
 
@@ -4606,18 +4707,16 @@ static int mount_setattr_prepare(struct mount_kattr *kattr, struct mount *mnt)
 
 static void do_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt)
 {
+	struct mnt_idmap *old_idmap;
+
 	if (!kattr->mnt_idmap)
 		return;
 
-	/*
-	 * Pairs with smp_load_acquire() in mnt_idmap().
-	 *
-	 * Since we only allow a mount to change the idmapping once and
-	 * verified this in can_idmap_mount() we know that the mount has
-	 * @nop_mnt_idmap attached to it. So there's no need to drop any
-	 * references.
-	 */
+	old_idmap = mnt_idmap(&mnt->mnt);
+
+	/* Pairs with smp_load_acquire() in mnt_idmap(). */
 	smp_store_release(&mnt->mnt.mnt_idmap, mnt_idmap_get(kattr->mnt_idmap));
+	mnt_idmap_put(old_idmap);
 }
 
 static void mount_setattr_commit(struct mount_kattr *kattr, struct mount *mnt)
@@ -4637,7 +4736,7 @@ static void mount_setattr_commit(struct mount_kattr *kattr, struct mount *mnt)
 
 		if (kattr->propagation)
 			change_mnt_propagation(m, kattr->propagation);
-		if (!kattr->recurse)
+		if (!(kattr->kflags & MOUNT_KATTR_RECURSE))
 			break;
 	}
 	touch_mnt_namespace(mnt->mnt_ns);
@@ -4667,7 +4766,7 @@ static int do_mount_setattr(struct path *path, struct mount_kattr *kattr)
 		 */
 		namespace_lock();
 		if (kattr->propagation == MS_SHARED) {
-			err = invent_group_ids(mnt, kattr->recurse);
+			err = invent_group_ids(mnt, kattr->kflags & MOUNT_KATTR_RECURSE);
 			if (err) {
 				namespace_unlock();
 				return err;
@@ -4718,7 +4817,7 @@ out:
 }
 
 static int build_mount_idmapped(const struct mount_attr *attr, size_t usize,
-				struct mount_kattr *kattr, unsigned int flags)
+				struct mount_kattr *kattr)
 {
 	struct ns_common *ns;
 	struct user_namespace *mnt_userns;
@@ -4726,13 +4825,23 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize,
 	if (!((attr->attr_set | attr->attr_clr) & MOUNT_ATTR_IDMAP))
 		return 0;
 
-	/*
-	 * We currently do not support clearing an idmapped mount. If this ever
-	 * is a use-case we can revisit this but for now let's keep it simple
-	 * and not allow it.
-	 */
-	if (attr->attr_clr & MOUNT_ATTR_IDMAP)
-		return -EINVAL;
+	if (attr->attr_clr & MOUNT_ATTR_IDMAP) {
+		/*
+		 * We can only remove an idmapping if it's never been
+		 * exposed to userspace.
+		 */
+		if (!(kattr->kflags & MOUNT_KATTR_IDMAP_REPLACE))
+			return -EINVAL;
+
+		/*
+		 * Removal of idmappings is equivalent to setting
+		 * nop_mnt_idmap.
+		 */
+		if (!(attr->attr_set & MOUNT_ATTR_IDMAP)) {
+			kattr->mnt_idmap = &nop_mnt_idmap;
+			return 0;
+		}
+	}
 
 	if (attr->userns_fd > INT_MAX)
 		return -EINVAL;
@@ -4769,22 +4878,8 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize,
 }
 
 static int build_mount_kattr(const struct mount_attr *attr, size_t usize,
-			     struct mount_kattr *kattr, unsigned int flags)
+			     struct mount_kattr *kattr)
 {
-	unsigned int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW;
-
-	if (flags & AT_NO_AUTOMOUNT)
-		lookup_flags &= ~LOOKUP_AUTOMOUNT;
-	if (flags & AT_SYMLINK_NOFOLLOW)
-		lookup_flags &= ~LOOKUP_FOLLOW;
-	if (flags & AT_EMPTY_PATH)
-		lookup_flags |= LOOKUP_EMPTY;
-
-	*kattr = (struct mount_kattr) {
-		.lookup_flags	= lookup_flags,
-		.recurse	= !!(flags & AT_RECURSIVE),
-	};
-
 	if (attr->propagation & ~MOUNT_SETATTR_PROPAGATION_FLAGS)
 		return -EINVAL;
 	if (hweight32(attr->propagation & MOUNT_SETATTR_PROPAGATION_FLAGS) > 1)
@@ -4832,35 +4927,28 @@ static int build_mount_kattr(const struct mount_attr *attr, size_t usize,
 			return -EINVAL;
 	}
 
-	return build_mount_idmapped(attr, usize, kattr, flags);
+	return build_mount_idmapped(attr, usize, kattr);
 }
 
 static void finish_mount_kattr(struct mount_kattr *kattr)
 {
-	put_user_ns(kattr->mnt_userns);
-	kattr->mnt_userns = NULL;
+	if (kattr->mnt_userns) {
+		put_user_ns(kattr->mnt_userns);
+		kattr->mnt_userns = NULL;
+	}
 
 	if (kattr->mnt_idmap)
 		mnt_idmap_put(kattr->mnt_idmap);
 }
 
-SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path,
-		unsigned int, flags, struct mount_attr __user *, uattr,
-		size_t, usize)
+static int copy_mount_setattr(struct mount_attr __user *uattr, size_t usize,
+			      struct mount_kattr *kattr)
 {
-	int err;
-	struct path target;
+	int ret;
 	struct mount_attr attr;
-	struct mount_kattr kattr;
 
 	BUILD_BUG_ON(sizeof(struct mount_attr) != MOUNT_ATTR_SIZE_VER0);
 
-	if (flags & ~(AT_EMPTY_PATH |
-		      AT_RECURSIVE |
-		      AT_SYMLINK_NOFOLLOW |
-		      AT_NO_AUTOMOUNT))
-		return -EINVAL;
-
 	if (unlikely(usize > PAGE_SIZE))
 		return -E2BIG;
 	if (unlikely(usize < MOUNT_ATTR_SIZE_VER0))
@@ -4869,9 +4957,9 @@ SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path,
 	if (!may_mount())
 		return -EPERM;
 
-	err = copy_struct_from_user(&attr, sizeof(attr), uattr, usize);
-	if (err)
-		return err;
+	ret = copy_struct_from_user(&attr, sizeof(attr), uattr, usize);
+	if (ret)
+		return ret;
 
 	/* Don't bother walking through the mounts if this is a nop. */
 	if (attr.attr_set == 0 &&
@@ -4879,7 +4967,39 @@ SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path,
 	    attr.propagation == 0)
 		return 0;
 
-	err = build_mount_kattr(&attr, usize, &kattr, flags);
+	return build_mount_kattr(&attr, usize, kattr);
+}
+
+SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path,
+		unsigned int, flags, struct mount_attr __user *, uattr,
+		size_t, usize)
+{
+	int err;
+	struct path target;
+	struct mount_kattr kattr;
+	unsigned int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW;
+
+	if (flags & ~(AT_EMPTY_PATH |
+		      AT_RECURSIVE |
+		      AT_SYMLINK_NOFOLLOW |
+		      AT_NO_AUTOMOUNT))
+		return -EINVAL;
+
+	if (flags & AT_NO_AUTOMOUNT)
+		lookup_flags &= ~LOOKUP_AUTOMOUNT;
+	if (flags & AT_SYMLINK_NOFOLLOW)
+		lookup_flags &= ~LOOKUP_FOLLOW;
+	if (flags & AT_EMPTY_PATH)
+		lookup_flags |= LOOKUP_EMPTY;
+
+	kattr = (struct mount_kattr) {
+		.lookup_flags	= lookup_flags,
+	};
+
+	if (flags & AT_RECURSIVE)
+		kattr.kflags |= MOUNT_KATTR_RECURSE;
+
+	err = copy_mount_setattr(uattr, usize, &kattr);
 	if (err)
 		return err;
 
@@ -4892,6 +5012,47 @@ SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path,
 	return err;
 }
 
+SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename,
+		unsigned, flags, struct mount_attr __user *, uattr,
+		size_t, usize)
+{
+	struct file __free(fput) *file = NULL;
+	int fd;
+
+	if (!uattr && usize)
+		return -EINVAL;
+
+	file = vfs_open_tree(dfd, filename, flags);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	if (uattr) {
+		int ret;
+		struct mount_kattr kattr = {};
+
+		kattr.kflags = MOUNT_KATTR_IDMAP_REPLACE;
+		if (flags & AT_RECURSIVE)
+			kattr.kflags |= MOUNT_KATTR_RECURSE;
+
+		ret = copy_mount_setattr(uattr, usize, &kattr);
+		if (ret)
+			return ret;
+
+		ret = do_mount_setattr(&file->f_path, &kattr);
+		if (ret)
+			return ret;
+
+		finish_mount_kattr(&kattr);
+	}
+
+	fd = get_unused_fd_flags(flags & O_CLOEXEC);
+	if (fd < 0)
+		return fd;
+
+	fd_install(fd, no_free_ptr(file));
+	return fd;
+}
+
 int show_path(struct seq_file *m, struct dentry *root)
 {
 	if (root->d_sb->s_op->show_path)
@@ -4915,6 +5076,7 @@ struct kstatmount {
 	struct statmount __user *buf;
 	size_t bufsize;
 	struct vfsmount *mnt;
+	struct mnt_idmap *idmap;
 	u64 mask;
 	struct path root;
 	struct statmount sm;
@@ -5184,6 +5346,46 @@ static int statmount_opt_sec_array(struct kstatmount *s, struct seq_file *seq)
 	return 0;
 }
 
+static inline int statmount_mnt_uidmap(struct kstatmount *s, struct seq_file *seq)
+{
+	int ret;
+
+	ret = statmount_mnt_idmap(s->idmap, seq, true);
+	if (ret < 0)
+		return ret;
+
+	s->sm.mnt_uidmap_num = ret;
+	/*
+	 * Always raise STATMOUNT_MNT_UIDMAP even if there are no valid
+	 * mappings. This allows userspace to distinguish between a
+	 * non-idmapped mount and an idmapped mount where none of the
+	 * individual mappings are valid in the caller's idmapping.
+	 */
+	if (is_valid_mnt_idmap(s->idmap))
+		s->sm.mask |= STATMOUNT_MNT_UIDMAP;
+	return 0;
+}
+
+static inline int statmount_mnt_gidmap(struct kstatmount *s, struct seq_file *seq)
+{
+	int ret;
+
+	ret = statmount_mnt_idmap(s->idmap, seq, false);
+	if (ret < 0)
+		return ret;
+
+	s->sm.mnt_gidmap_num = ret;
+	/*
+	 * Always raise STATMOUNT_MNT_GIDMAP even if there are no valid
+	 * mappings. This allows userspace to distinguish between a
+	 * non-idmapped mount and an idmapped mount where none of the
+	 * individual mappings are valid in the caller's idmapping.
+	 */
+	if (is_valid_mnt_idmap(s->idmap))
+		s->sm.mask |= STATMOUNT_MNT_GIDMAP;
+	return 0;
+}
+
 static int statmount_string(struct kstatmount *s, u64 flag)
 {
 	int ret = 0;
@@ -5231,6 +5433,14 @@ static int statmount_string(struct kstatmount *s, u64 flag)
 		offp = &sm->sb_source;
 		ret = statmount_sb_source(s, seq);
 		break;
+	case STATMOUNT_MNT_UIDMAP:
+		sm->mnt_uidmap = start;
+		ret = statmount_mnt_uidmap(s, seq);
+		break;
+	case STATMOUNT_MNT_GIDMAP:
+		sm->mnt_gidmap = start;
+		ret = statmount_mnt_gidmap(s, seq);
+		break;
 	default:
 		WARN_ON_ONCE(true);
 		return -EINVAL;
@@ -5323,6 +5533,21 @@ static int grab_requested_root(struct mnt_namespace *ns, struct path *root)
 	return 0;
 }
 
+/* This must be updated whenever a new flag is added */
+#define STATMOUNT_SUPPORTED (STATMOUNT_SB_BASIC | \
+			     STATMOUNT_MNT_BASIC | \
+			     STATMOUNT_PROPAGATE_FROM | \
+			     STATMOUNT_MNT_ROOT | \
+			     STATMOUNT_MNT_POINT | \
+			     STATMOUNT_FS_TYPE | \
+			     STATMOUNT_MNT_NS_ID | \
+			     STATMOUNT_MNT_OPTS | \
+			     STATMOUNT_FS_SUBTYPE | \
+			     STATMOUNT_SB_SOURCE | \
+			     STATMOUNT_OPT_ARRAY | \
+			     STATMOUNT_OPT_SEC_ARRAY | \
+			     STATMOUNT_SUPPORTED_MASK)
+
 static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id,
 			struct mnt_namespace *ns)
 {
@@ -5356,6 +5581,7 @@ static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id,
 		return err;
 
 	s->root = root;
+	s->idmap = mnt_idmap(s->mnt);
 	if (s->mask & STATMOUNT_SB_BASIC)
 		statmount_sb_basic(s);
 
@@ -5389,12 +5615,26 @@ static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id,
 	if (!err && s->mask & STATMOUNT_SB_SOURCE)
 		err = statmount_string(s, STATMOUNT_SB_SOURCE);
 
+	if (!err && s->mask & STATMOUNT_MNT_UIDMAP)
+		err = statmount_string(s, STATMOUNT_MNT_UIDMAP);
+
+	if (!err && s->mask & STATMOUNT_MNT_GIDMAP)
+		err = statmount_string(s, STATMOUNT_MNT_GIDMAP);
+
 	if (!err && s->mask & STATMOUNT_MNT_NS_ID)
 		statmount_mnt_ns_id(s, ns);
 
+	if (!err && s->mask & STATMOUNT_SUPPORTED_MASK) {
+		s->sm.mask |= STATMOUNT_SUPPORTED_MASK;
+		s->sm.supported_mask = STATMOUNT_SUPPORTED;
+	}
+
 	if (err)
 		return err;
 
+	/* Are there bits in the return mask not present in STATMOUNT_SUPPORTED? */
+	WARN_ON_ONCE(~STATMOUNT_SUPPORTED & s->sm.mask);
+
 	return 0;
 }
 
@@ -5412,7 +5652,8 @@ static inline bool retry_statmount(const long ret, size_t *seq_size)
 #define STATMOUNT_STRING_REQ (STATMOUNT_MNT_ROOT | STATMOUNT_MNT_POINT | \
 			      STATMOUNT_FS_TYPE | STATMOUNT_MNT_OPTS | \
 			      STATMOUNT_FS_SUBTYPE | STATMOUNT_SB_SOURCE | \
-			      STATMOUNT_OPT_ARRAY | STATMOUNT_OPT_SEC_ARRAY)
+			      STATMOUNT_OPT_ARRAY | STATMOUNT_OPT_SEC_ARRAY | \
+			      STATMOUNT_MNT_UIDMAP | STATMOUNT_MNT_GIDMAP)
 
 static int prepare_kstatmount(struct kstatmount *ks, struct mnt_id_req *kreq,
 			      struct statmount __user *buf, size_t bufsize,
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 95646f7c46ca..6d386080faf2 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -166,6 +166,8 @@ static bool fanotify_should_merge(struct fanotify_event *old,
 	case FANOTIFY_EVENT_TYPE_FS_ERROR:
 		return fanotify_error_event_equal(FANOTIFY_EE(old),
 						  FANOTIFY_EE(new));
+	case FANOTIFY_EVENT_TYPE_MNT:
+		return false;
 	default:
 		WARN_ON_ONCE(1);
 	}
@@ -312,7 +314,10 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group,
 	pr_debug("%s: report_mask=%x mask=%x data=%p data_type=%d\n",
 		 __func__, iter_info->report_mask, event_mask, data, data_type);
 
-	if (!fid_mode) {
+	if (FAN_GROUP_FLAG(group, FAN_REPORT_MNT)) {
+		if (data_type != FSNOTIFY_EVENT_MNT)
+			return 0;
+	} else if (!fid_mode) {
 		/* Do we have path to open a file descriptor? */
 		if (!path)
 			return 0;
@@ -557,6 +562,20 @@ static struct fanotify_event *fanotify_alloc_path_event(const struct path *path,
 	return &pevent->fae;
 }
 
+static struct fanotify_event *fanotify_alloc_mnt_event(u64 mnt_id, gfp_t gfp)
+{
+	struct fanotify_mnt_event *pevent;
+
+	pevent = kmem_cache_alloc(fanotify_mnt_event_cachep, gfp);
+	if (!pevent)
+		return NULL;
+
+	pevent->fae.type = FANOTIFY_EVENT_TYPE_MNT;
+	pevent->mnt_id = mnt_id;
+
+	return &pevent->fae;
+}
+
 static struct fanotify_event *fanotify_alloc_perm_event(const void *data,
 							int data_type,
 							gfp_t gfp)
@@ -731,6 +750,7 @@ static struct fanotify_event *fanotify_alloc_event(
 					      fid_mode);
 	struct inode *dirid = fanotify_dfid_inode(mask, data, data_type, dir);
 	const struct path *path = fsnotify_data_path(data, data_type);
+	u64 mnt_id = fsnotify_data_mnt_id(data, data_type);
 	struct mem_cgroup *old_memcg;
 	struct dentry *moved = NULL;
 	struct inode *child = NULL;
@@ -826,8 +846,12 @@ static struct fanotify_event *fanotify_alloc_event(
 						  moved, &hash, gfp);
 	} else if (fid_mode) {
 		event = fanotify_alloc_fid_event(id, fsid, &hash, gfp);
-	} else {
+	} else if (path) {
 		event = fanotify_alloc_path_event(path, &hash, gfp);
+	} else if (mnt_id) {
+		event = fanotify_alloc_mnt_event(mnt_id, gfp);
+	} else {
+		WARN_ON_ONCE(1);
 	}
 
 	if (!event)
@@ -927,7 +951,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask,
 	BUILD_BUG_ON(FAN_RENAME != FS_RENAME);
 	BUILD_BUG_ON(FAN_PRE_ACCESS != FS_PRE_ACCESS);
 
-	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 22);
+	BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 24);
 
 	mask = fanotify_group_event_mask(group, iter_info, &match_mask,
 					 mask, data, data_type, dir);
@@ -1028,6 +1052,11 @@ static void fanotify_free_error_event(struct fsnotify_group *group,
 	mempool_free(fee, &group->fanotify_data.error_events_pool);
 }
 
+static void fanotify_free_mnt_event(struct fanotify_event *event)
+{
+	kmem_cache_free(fanotify_mnt_event_cachep, FANOTIFY_ME(event));
+}
+
 static void fanotify_free_event(struct fsnotify_group *group,
 				struct fsnotify_event *fsn_event)
 {
@@ -1054,6 +1083,9 @@ static void fanotify_free_event(struct fsnotify_group *group,
 	case FANOTIFY_EVENT_TYPE_FS_ERROR:
 		fanotify_free_error_event(group, event);
 		break;
+	case FANOTIFY_EVENT_TYPE_MNT:
+		fanotify_free_mnt_event(event);
+		break;
 	default:
 		WARN_ON_ONCE(1);
 	}
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
index c12cbc270539..b44e70e44be6 100644
--- a/fs/notify/fanotify/fanotify.h
+++ b/fs/notify/fanotify/fanotify.h
@@ -9,6 +9,7 @@ extern struct kmem_cache *fanotify_mark_cache;
 extern struct kmem_cache *fanotify_fid_event_cachep;
 extern struct kmem_cache *fanotify_path_event_cachep;
 extern struct kmem_cache *fanotify_perm_event_cachep;
+extern struct kmem_cache *fanotify_mnt_event_cachep;
 
 /* Possible states of the permission event */
 enum {
@@ -244,6 +245,7 @@ enum fanotify_event_type {
 	FANOTIFY_EVENT_TYPE_PATH_PERM,
 	FANOTIFY_EVENT_TYPE_OVERFLOW, /* struct fanotify_event */
 	FANOTIFY_EVENT_TYPE_FS_ERROR, /* struct fanotify_error_event */
+	FANOTIFY_EVENT_TYPE_MNT,
 	__FANOTIFY_EVENT_TYPE_NUM
 };
 
@@ -409,12 +411,23 @@ struct fanotify_path_event {
 	struct path path;
 };
 
+struct fanotify_mnt_event {
+	struct fanotify_event fae;
+	u64 mnt_id;
+};
+
 static inline struct fanotify_path_event *
 FANOTIFY_PE(struct fanotify_event *event)
 {
 	return container_of(event, struct fanotify_path_event, fae);
 }
 
+static inline struct fanotify_mnt_event *
+FANOTIFY_ME(struct fanotify_event *event)
+{
+	return container_of(event, struct fanotify_mnt_event, fae);
+}
+
 /*
  * Structure for permission fanotify events. It gets allocated and freed in
  * fanotify_handle_event() since we wait there for user response. When the
@@ -466,6 +479,11 @@ static inline bool fanotify_is_error_event(u32 mask)
 	return mask & FAN_FS_ERROR;
 }
 
+static inline bool fanotify_is_mnt_event(u32 mask)
+{
+	return mask & (FAN_MNT_ATTACH | FAN_MNT_DETACH);
+}
+
 static inline const struct path *fanotify_event_path(struct fanotify_event *event)
 {
 	if (event->type == FANOTIFY_EVENT_TYPE_PATH)
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index ba3e2d09eb44..f2d840ae4ded 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -113,6 +113,7 @@ struct kmem_cache *fanotify_mark_cache __ro_after_init;
 struct kmem_cache *fanotify_fid_event_cachep __ro_after_init;
 struct kmem_cache *fanotify_path_event_cachep __ro_after_init;
 struct kmem_cache *fanotify_perm_event_cachep __ro_after_init;
+struct kmem_cache *fanotify_mnt_event_cachep __ro_after_init;
 
 #define FANOTIFY_EVENT_ALIGN 4
 #define FANOTIFY_FID_INFO_HDR_LEN \
@@ -123,6 +124,8 @@ struct kmem_cache *fanotify_perm_event_cachep __ro_after_init;
 	(sizeof(struct fanotify_event_info_error))
 #define FANOTIFY_RANGE_INFO_LEN \
 	(sizeof(struct fanotify_event_info_range))
+#define FANOTIFY_MNT_INFO_LEN \
+	(sizeof(struct fanotify_event_info_mnt))
 
 static int fanotify_fid_info_len(int fh_len, int name_len)
 {
@@ -178,6 +181,8 @@ static size_t fanotify_event_len(unsigned int info_mode,
 		fh_len = fanotify_event_object_fh_len(event);
 		event_len += fanotify_fid_info_len(fh_len, dot_len);
 	}
+	if (fanotify_is_mnt_event(event->mask))
+		event_len += FANOTIFY_MNT_INFO_LEN;
 
 	if (info_mode & FAN_REPORT_PIDFD)
 		event_len += FANOTIFY_PIDFD_INFO_LEN;
@@ -405,6 +410,25 @@ static int process_access_response(struct fsnotify_group *group,
 	return -ENOENT;
 }
 
+static size_t copy_mnt_info_to_user(struct fanotify_event *event,
+				    char __user *buf, int count)
+{
+	struct fanotify_event_info_mnt info = { };
+
+	info.hdr.info_type = FAN_EVENT_INFO_TYPE_MNT;
+	info.hdr.len = FANOTIFY_MNT_INFO_LEN;
+
+	if (WARN_ON(count < info.hdr.len))
+		return -EFAULT;
+
+	info.mnt_id = FANOTIFY_ME(event)->mnt_id;
+
+	if (copy_to_user(buf, &info, sizeof(info)))
+		return -EFAULT;
+
+	return info.hdr.len;
+}
+
 static size_t copy_error_info_to_user(struct fanotify_event *event,
 				      char __user *buf, int count)
 {
@@ -700,6 +724,15 @@ static int copy_info_records_to_user(struct fanotify_event *event,
 		total_bytes += ret;
 	}
 
+	if (fanotify_is_mnt_event(event->mask)) {
+		ret = copy_mnt_info_to_user(event, buf, count);
+		if (ret < 0)
+			return ret;
+		buf += ret;
+		count -= ret;
+		total_bytes += ret;
+	}
+
 	return total_bytes;
 }
 
@@ -1508,6 +1541,14 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	if ((flags & FAN_REPORT_PIDFD) && (flags & FAN_REPORT_TID))
 		return -EINVAL;
 
+	/* Don't allow mixing mnt events with inode events for now */
+	if (flags & FAN_REPORT_MNT) {
+		if (class != FAN_CLASS_NOTIF)
+			return -EINVAL;
+		if (flags & (FANOTIFY_FID_BITS | FAN_REPORT_FD_ERROR))
+			return -EINVAL;
+	}
+
 	if (event_f_flags & ~FANOTIFY_INIT_ALL_EVENT_F_BITS)
 		return -EINVAL;
 
@@ -1767,7 +1808,6 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 			    int dfd, const char  __user *pathname)
 {
 	struct inode *inode = NULL;
-	struct vfsmount *mnt = NULL;
 	struct fsnotify_group *group;
 	struct path path;
 	struct fan_fsid __fsid, *fsid = NULL;
@@ -1776,7 +1816,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	unsigned int mark_cmd = flags & FANOTIFY_MARK_CMD_BITS;
 	unsigned int ignore = flags & FANOTIFY_MARK_IGNORE_BITS;
 	unsigned int obj_type, fid_mode;
-	void *obj;
+	void *obj = NULL;
 	u32 umask = 0;
 	int ret;
 
@@ -1800,6 +1840,9 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	case FAN_MARK_FILESYSTEM:
 		obj_type = FSNOTIFY_OBJ_TYPE_SB;
 		break;
+	case FAN_MARK_MNTNS:
+		obj_type = FSNOTIFY_OBJ_TYPE_MNTNS;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1847,6 +1890,19 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 		return -EINVAL;
 	group = fd_file(f)->private_data;
 
+	/* Only report mount events on mnt namespace */
+	if (FAN_GROUP_FLAG(group, FAN_REPORT_MNT)) {
+		if (mask & ~FANOTIFY_MOUNT_EVENTS)
+			return -EINVAL;
+		if (mark_type != FAN_MARK_MNTNS)
+			return -EINVAL;
+	} else {
+		if (mask & FANOTIFY_MOUNT_EVENTS)
+			return -EINVAL;
+		if (mark_type == FAN_MARK_MNTNS)
+			return -EINVAL;
+	}
+
 	/*
 	 * An unprivileged user is not allowed to setup mount nor filesystem
 	 * marks.  This also includes setting up such marks by a group that
@@ -1888,7 +1944,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	 * point.
 	 */
 	fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS);
-	if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_EVENT_FLAGS) &&
+	if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_MOUNT_EVENTS|FANOTIFY_EVENT_FLAGS) &&
 	    (!fid_mode || mark_type == FAN_MARK_MOUNT))
 		return -EINVAL;
 
@@ -1938,17 +1994,21 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	}
 
 	/* inode held in place by reference to path; group by fget on fd */
-	if (mark_type == FAN_MARK_INODE) {
+	if (obj_type == FSNOTIFY_OBJ_TYPE_INODE) {
 		inode = path.dentry->d_inode;
 		obj = inode;
-	} else {
-		mnt = path.mnt;
-		if (mark_type == FAN_MARK_MOUNT)
-			obj = mnt;
-		else
-			obj = mnt->mnt_sb;
+	} else if (obj_type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
+		obj = path.mnt;
+	} else if (obj_type == FSNOTIFY_OBJ_TYPE_SB) {
+		obj = path.mnt->mnt_sb;
+	} else if (obj_type == FSNOTIFY_OBJ_TYPE_MNTNS) {
+		obj = mnt_ns_from_dentry(path.dentry);
 	}
 
+	ret = -EINVAL;
+	if (!obj)
+		goto path_put_and_out;
+
 	/*
 	 * If some other task has this inode open for write we should not add
 	 * an ignore mask, unless that ignore mask is supposed to survive
@@ -1956,10 +2016,10 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	 */
 	if (mark_cmd == FAN_MARK_ADD && (flags & FANOTIFY_MARK_IGNORE_BITS) &&
 	    !(flags & FAN_MARK_IGNORED_SURV_MODIFY)) {
-		ret = mnt ? -EINVAL : -EISDIR;
+		ret = !inode ? -EINVAL : -EISDIR;
 		/* FAN_MARK_IGNORE requires SURV_MODIFY for sb/mount/dir marks */
 		if (ignore == FAN_MARK_IGNORE &&
-		    (mnt || S_ISDIR(inode->i_mode)))
+		    (!inode || S_ISDIR(inode->i_mode)))
 			goto path_put_and_out;
 
 		ret = 0;
@@ -1968,7 +2028,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask,
 	}
 
 	/* Mask out FAN_EVENT_ON_CHILD flag for sb/mount/non-dir marks */
-	if (mnt || !S_ISDIR(inode->i_mode)) {
+	if (!inode || !S_ISDIR(inode->i_mode)) {
 		mask &= ~FAN_EVENT_ON_CHILD;
 		umask = FAN_EVENT_ON_CHILD;
 		/*
@@ -2042,7 +2102,7 @@ static int __init fanotify_user_setup(void)
 				     FANOTIFY_DEFAULT_MAX_USER_MARKS);
 
 	BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS);
-	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 13);
+	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 14);
 	BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 11);
 
 	fanotify_mark_cache = KMEM_CACHE(fanotify_mark,
@@ -2055,6 +2115,7 @@ static int __init fanotify_user_setup(void)
 		fanotify_perm_event_cachep =
 			KMEM_CACHE(fanotify_perm_event, SLAB_PANIC);
 	}
+	fanotify_mnt_event_cachep = KMEM_CACHE(fanotify_mnt_event, SLAB_PANIC);
 
 	fanotify_max_queued_events = FANOTIFY_DEFAULT_MAX_EVENTS;
 	init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS] =
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index e933f9c65d90..1161eabf11ee 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -121,6 +121,11 @@ static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
 
 		seq_printf(m, "fanotify sdev:%x mflags:%x mask:%x ignored_mask:%x\n",
 			   sb->s_dev, mflags, mark->mask, mark->ignore_mask);
+	} else if (mark->connector->type == FSNOTIFY_OBJ_TYPE_MNTNS) {
+		struct mnt_namespace *mnt_ns = fsnotify_conn_mntns(mark->connector);
+
+		seq_printf(m, "fanotify mnt_ns:%u mflags:%x mask:%x ignored_mask:%x\n",
+			   mnt_ns->ns.inum, mflags, mark->mask, mark->ignore_mask);
 	}
 }
 
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index fae1b6d397ea..e2b4f17a48bb 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -28,6 +28,11 @@ void __fsnotify_vfsmount_delete(struct vfsmount *mnt)
 	fsnotify_clear_marks_by_mount(mnt);
 }
 
+void __fsnotify_mntns_delete(struct mnt_namespace *mntns)
+{
+	fsnotify_clear_marks_by_mntns(mntns);
+}
+
 /**
  * fsnotify_unmount_inodes - an sb is unmounting.  handle any watched inodes.
  * @sb: superblock being unmounted.
@@ -420,7 +425,7 @@ static int send_to_group(__u32 mask, const void *data, int data_type,
 				     file_name, cookie, iter_info);
 }
 
-static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector **connp)
+static struct fsnotify_mark *fsnotify_first_mark(struct fsnotify_mark_connector *const *connp)
 {
 	struct fsnotify_mark_connector *conn;
 	struct hlist_node *node = NULL;
@@ -538,14 +543,15 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
 {
 	const struct path *path = fsnotify_data_path(data, data_type);
 	struct super_block *sb = fsnotify_data_sb(data, data_type);
-	struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb);
+	const struct fsnotify_mnt *mnt_data = fsnotify_data_mnt(data, data_type);
+	struct fsnotify_sb_info *sbinfo = sb ? fsnotify_sb_info(sb) : NULL;
 	struct fsnotify_iter_info iter_info = {};
 	struct mount *mnt = NULL;
 	struct inode *inode2 = NULL;
 	struct dentry *moved;
 	int inode2_type;
 	int ret = 0;
-	__u32 test_mask, marks_mask;
+	__u32 test_mask, marks_mask = 0;
 
 	if (path)
 		mnt = real_mount(path->mnt);
@@ -578,17 +584,20 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
 	if ((!sbinfo || !sbinfo->sb_marks) &&
 	    (!mnt || !mnt->mnt_fsnotify_marks) &&
 	    (!inode || !inode->i_fsnotify_marks) &&
-	    (!inode2 || !inode2->i_fsnotify_marks))
+	    (!inode2 || !inode2->i_fsnotify_marks) &&
+	    (!mnt_data || !mnt_data->ns->n_fsnotify_marks))
 		return 0;
 
-	marks_mask = READ_ONCE(sb->s_fsnotify_mask);
+	if (sb)
+		marks_mask |= READ_ONCE(sb->s_fsnotify_mask);
 	if (mnt)
 		marks_mask |= READ_ONCE(mnt->mnt_fsnotify_mask);
 	if (inode)
 		marks_mask |= READ_ONCE(inode->i_fsnotify_mask);
 	if (inode2)
 		marks_mask |= READ_ONCE(inode2->i_fsnotify_mask);
-
+	if (mnt_data)
+		marks_mask |= READ_ONCE(mnt_data->ns->n_fsnotify_mask);
 
 	/*
 	 * If this is a modify event we may need to clear some ignore masks.
@@ -618,6 +627,10 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir,
 		iter_info.marks[inode2_type] =
 			fsnotify_first_mark(&inode2->i_fsnotify_marks);
 	}
+	if (mnt_data) {
+		iter_info.marks[FSNOTIFY_ITER_TYPE_MNTNS] =
+			fsnotify_first_mark(&mnt_data->ns->n_fsnotify_marks);
+	}
 
 	/*
 	 * We need to merge inode/vfsmount/sb mark lists so that e.g. inode mark
@@ -708,11 +721,31 @@ void file_set_fsnotify_mode_from_watchers(struct file *file)
 }
 #endif
 
+void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt)
+{
+	struct fsnotify_mnt data = {
+		.ns = ns,
+		.mnt_id = real_mount(mnt)->mnt_id_unique,
+	};
+
+	if (WARN_ON_ONCE(!ns))
+		return;
+
+	/*
+	 * This is an optimization as well as making sure fsnotify_init() has
+	 * been called.
+	 */
+	if (!ns->n_fsnotify_marks)
+		return;
+
+	fsnotify(mask, &data, FSNOTIFY_EVENT_MNT, NULL, NULL, NULL, 0);
+}
+
 static __init int fsnotify_init(void)
 {
 	int ret;
 
-	BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 24);
+	BUILD_BUG_ON(HWEIGHT32(ALL_FSNOTIFY_BITS) != 26);
 
 	ret = init_srcu_struct(&fsnotify_mark_srcu);
 	if (ret)
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index 663759ed6fbc..5950c7a67f41 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -33,6 +33,12 @@ static inline struct super_block *fsnotify_conn_sb(
 	return conn->obj;
 }
 
+static inline struct mnt_namespace *fsnotify_conn_mntns(
+				struct fsnotify_mark_connector *conn)
+{
+	return conn->obj;
+}
+
 static inline struct super_block *fsnotify_object_sb(void *obj,
 			enum fsnotify_obj_type obj_type)
 {
@@ -89,6 +95,11 @@ static inline void fsnotify_clear_marks_by_sb(struct super_block *sb)
 	fsnotify_destroy_marks(fsnotify_sb_marks(sb));
 }
 
+static inline void fsnotify_clear_marks_by_mntns(struct mnt_namespace *mntns)
+{
+	fsnotify_destroy_marks(&mntns->n_fsnotify_marks);
+}
+
 /*
  * update the dentry->d_flags of all of inode's children to indicate if inode cares
  * about events that happen to its children.
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 4981439e6209..798340db69d7 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -107,6 +107,8 @@ static fsnotify_connp_t *fsnotify_object_connp(void *obj,
 		return &real_mount(obj)->mnt_fsnotify_marks;
 	case FSNOTIFY_OBJ_TYPE_SB:
 		return fsnotify_sb_marks(obj);
+	case FSNOTIFY_OBJ_TYPE_MNTNS:
+		return &((struct mnt_namespace *)obj)->n_fsnotify_marks;
 	default:
 		return NULL;
 	}
@@ -120,6 +122,8 @@ static __u32 *fsnotify_conn_mask_p(struct fsnotify_mark_connector *conn)
 		return &fsnotify_conn_mount(conn)->mnt_fsnotify_mask;
 	else if (conn->type == FSNOTIFY_OBJ_TYPE_SB)
 		return &fsnotify_conn_sb(conn)->s_fsnotify_mask;
+	else if (conn->type == FSNOTIFY_OBJ_TYPE_MNTNS)
+		return &fsnotify_conn_mntns(conn)->n_fsnotify_mask;
 	return NULL;
 }
 
@@ -346,12 +350,15 @@ static void *fsnotify_detach_connector_from_object(
 		fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0;
 	} else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) {
 		fsnotify_conn_sb(conn)->s_fsnotify_mask = 0;
+	} else if (conn->type == FSNOTIFY_OBJ_TYPE_MNTNS) {
+		fsnotify_conn_mntns(conn)->n_fsnotify_mask = 0;
 	}
 
 	rcu_assign_pointer(*connp, NULL);
 	conn->obj = NULL;
 	conn->type = FSNOTIFY_OBJ_TYPE_DETACHED;
-	fsnotify_update_sb_watchers(sb, conn);
+	if (sb)
+		fsnotify_update_sb_watchers(sb, conn);
 
 	return inode;
 }
@@ -724,7 +731,7 @@ static int fsnotify_add_mark_list(struct fsnotify_mark *mark, void *obj,
 	 * Attach the sb info before attaching a connector to any object on sb.
 	 * The sb info will remain attached as long as sb lives.
 	 */
-	if (!fsnotify_sb_info(sb)) {
+	if (sb && !fsnotify_sb_info(sb)) {
 		err = fsnotify_attach_info_to_sb(sb);
 		if (err)
 			return err;
@@ -770,7 +777,8 @@ restart:
 	/* mark should be the last entry.  last is the current last entry */
 	hlist_add_behind_rcu(&mark->obj_list, &last->obj_list);
 added:
-	fsnotify_update_sb_watchers(sb, conn);
+	if (sb)
+		fsnotify_update_sb_watchers(sb, conn);
 	/*
 	 * Since connector is attached to object using cmpxchg() we are
 	 * guaranteed that connector initialization is fully visible by anyone
diff --git a/fs/pnode.c b/fs/pnode.c
index ef048f008bdd..82d809c785ec 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -549,8 +549,10 @@ static void restore_mounts(struct list_head *to_restore)
 			mp = parent->mnt_mp;
 			parent = parent->mnt_parent;
 		}
-		if (parent != mnt->mnt_parent)
+		if (parent != mnt->mnt_parent) {
 			mnt_change_mountpoint(parent, mp, mnt);
+			mnt_notify_add(mnt);
+		}
 	}
 }