1 files changed, 137 insertions, 120 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index 552ad7f4d18b..54c59e091919 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1326,21 +1326,6 @@ struct vfsmount *vfs_kern_mount(struct file_system_type *type,
 }
 EXPORT_SYMBOL_GPL(vfs_kern_mount);
 
-struct vfsmount *
-vfs_submount(const struct dentry *mountpoint, struct file_system_type *type,
-	     const char *name, void *data)
-{
-	/* Until it is worked out how to pass the user namespace
-	 * through from the parent mount to the submount don't support
-	 * unprivileged mounts with submounts.
-	 */
-	if (mountpoint->d_sb->s_user_ns != &init_user_ns)
-		return ERR_PTR(-EPERM);
-
-	return vfs_kern_mount(type, SB_SUBMOUNT, name, data);
-}
-EXPORT_SYMBOL_GPL(vfs_submount);
-
 static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 					int flag)
 {
@@ -2325,21 +2310,62 @@ out:
 	return dst_mnt;
 }
 
-/* Caller should check returned pointer for errors */
+static inline bool extend_array(struct path **res, struct path **to_free,
+				unsigned n, unsigned *count, unsigned new_count)
+{
+	struct path *p;
+
+	if (likely(n < *count))
+		return true;
+	p = kmalloc_array(new_count, sizeof(struct path), GFP_KERNEL);
+	if (p && *count)
+		memcpy(p, *res, *count * sizeof(struct path));
+	*count = new_count;
+	kfree(*to_free);
+	*to_free = *res = p;
+	return p;
+}
 
-struct vfsmount *collect_mounts(const struct path *path)
+struct path *collect_paths(const struct path *path,
+			      struct path *prealloc, unsigned count)
 {
-	struct mount *tree;
-	namespace_lock();
-	if (!check_mnt(real_mount(path->mnt)))
-		tree = ERR_PTR(-EINVAL);
-	else
-		tree = copy_tree(real_mount(path->mnt), path->dentry,
-				 CL_COPY_ALL | CL_PRIVATE);
-	namespace_unlock();
-	if (IS_ERR(tree))
-		return ERR_CAST(tree);
-	return &tree->mnt;
+	struct mount *root = real_mount(path->mnt);
+	struct mount *child;
+	struct path *res = prealloc, *to_free = NULL;
+	unsigned n = 0;
+
+	guard(rwsem_read)(&namespace_sem);
+
+	if (!check_mnt(root))
+		return ERR_PTR(-EINVAL);
+	if (!extend_array(&res, &to_free, 0, &count, 32))
+		return ERR_PTR(-ENOMEM);
+	res[n++] = *path;
+	list_for_each_entry(child, &root->mnt_mounts, mnt_child) {
+		if (!is_subdir(child->mnt_mountpoint, path->dentry))
+			continue;
+		for (struct mount *m = child; m; m = next_mnt(m, child)) {
+			if (!extend_array(&res, &to_free, n, &count, 2 * count))
+				return ERR_PTR(-ENOMEM);
+			res[n].mnt = &m->mnt;
+			res[n].dentry = m->mnt.mnt_root;
+			n++;
+		}
+	}
+	if (!extend_array(&res, &to_free, n, &count, count + 1))
+		return ERR_PTR(-ENOMEM);
+	memset(res + n, 0, (count - n) * sizeof(struct path));
+	for (struct path *p = res; p->mnt; p++)
+		path_get(p);
+	return res;
+}
+
+void drop_collected_paths(struct path *paths, struct path *prealloc)
+{
+	for (struct path *p = paths; p->mnt; p++)
+		path_put(p);
+	if (paths != prealloc)
+		kfree(paths);
 }
 
 static void free_mnt_ns(struct mnt_namespace *);
@@ -2416,16 +2442,7 @@ void dissolve_on_fput(struct vfsmount *mnt)
 	free_mnt_ns(ns);
 }
 
-void drop_collected_mounts(struct vfsmount *mnt)
-{
-	namespace_lock();
-	lock_mount_hash();
-	umount_tree(real_mount(mnt), 0);
-	unlock_mount_hash();
-	namespace_unlock();
-}
-
-bool has_locked_children(struct mount *mnt, struct dentry *dentry)
+static bool __has_locked_children(struct mount *mnt, struct dentry *dentry)
 {
 	struct mount *child;
 
@@ -2439,6 +2456,16 @@ bool has_locked_children(struct mount *mnt, struct dentry *dentry)
 	return false;
 }
 
+bool has_locked_children(struct mount *mnt, struct dentry *dentry)
+{
+	bool res;
+
+	read_seqlock_excl(&mount_lock);
+	res = __has_locked_children(mnt, dentry);
+	read_sequnlock_excl(&mount_lock);
+	return res;
+}
+
 /*
  * Check that there aren't references to earlier/same mount namespaces in the
  * specified subtree.  Such references can act as pins for mount namespaces
@@ -2483,23 +2510,27 @@ struct vfsmount *clone_private_mount(const struct path *path)
 	if (IS_MNT_UNBINDABLE(old_mnt))
 		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);
-
-		/* Make sure this isn't something purely kernel internal. */
-		if (!is_anon_ns(old_mnt->mnt_ns))
+	/*
+	 * Make sure the source mount is acceptable.
+	 * Anything mounted in our mount namespace is allowed.
+	 * Otherwise, it must be the root of an anonymous mount
+	 * namespace, and we need to make sure no namespace
+	 * 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))
 			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))
+        if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	if (__has_locked_children(old_mnt, path->dentry))
 		return ERR_PTR(-EINVAL);
 
 	new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE);
@@ -2512,21 +2543,6 @@ struct vfsmount *clone_private_mount(const struct path *path)
 }
 EXPORT_SYMBOL_GPL(clone_private_mount);
 
-int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
-		   struct vfsmount *root)
-{
-	struct mount *mnt;
-	int res = f(root, arg);
-	if (res)
-		return res;
-	list_for_each_entry(mnt, &real_mount(root)->mnt_list, mnt_list) {
-		res = f(&mnt->mnt, arg);
-		if (res)
-			return res;
-	}
-	return 0;
-}
-
 static void lock_mnt_tree(struct mount *mnt)
 {
 	struct mount *p;
@@ -2752,14 +2768,14 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 	hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
 		struct mount *q;
 		hlist_del_init(&child->mnt_hash);
-		q = __lookup_mnt(&child->mnt_parent->mnt,
-				 child->mnt_mountpoint);
-		if (q)
-			mnt_change_mountpoint(child, smp, q);
 		/* 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);
 		commit_tree(child);
 	}
 	put_mountpoint(smp);
@@ -2945,6 +2961,10 @@ static int do_change_type(struct path *path, int ms_flags)
 		return -EINVAL;
 
 	namespace_lock();
+	if (!check_mnt(mnt)) {
+		err = -EINVAL;
+		goto out_unlock;
+	}
 	if (type == MS_SHARED) {
 		err = invent_group_ids(mnt, recurse);
 		if (err)
@@ -3036,7 +3056,7 @@ static struct mount *__do_loopback(struct path *old_path, int recurse)
 	if (!may_copy_tree(old_path))
 		return mnt;
 
-	if (!recurse && has_locked_children(old, old_path->dentry))
+	if (!recurse && __has_locked_children(old, old_path->dentry))
 		return mnt;
 
 	if (recurse)
@@ -3429,7 +3449,7 @@ static int do_set_group(struct path *from_path, struct path *to_path)
 		goto out;
 
 	/* From mount should not have locked children in place of To's root */
-	if (has_locked_children(from, to->mnt.mnt_root))
+	if (__has_locked_children(from, to->mnt.mnt_root))
 		goto out;
 
 	/* Setting sharing groups is only allowed on private mounts */
@@ -3443,7 +3463,7 @@ static int do_set_group(struct path *from_path, struct path *to_path)
 	if (IS_MNT_SLAVE(from)) {
 		struct mount *m = from->mnt_master;
 
-		list_add(&to->mnt_slave, &m->mnt_slave_list);
+		list_add(&to->mnt_slave, &from->mnt_slave);
 		to->mnt_master = m;
 	}
 
@@ -3468,18 +3488,25 @@ out:
  * Check if path is overmounted, i.e., if there's a mount on top of
  * @path->mnt with @path->dentry as mountpoint.
  *
- * Context: This function expects namespace_lock() to be held.
+ * Context: namespace_sem must be held at least shared.
+ * MUST NOT be called under lock_mount_hash() (there one should just
+ * call __lookup_mnt() and check if it returns NULL).
  * Return: If path is overmounted true is returned, false if not.
  */
 static inline bool path_overmounted(const struct path *path)
 {
+	unsigned seq = read_seqbegin(&mount_lock);
+	bool no_child;
+
 	rcu_read_lock();
-	if (unlikely(__lookup_mnt(path->mnt, path->dentry))) {
-		rcu_read_unlock();
-		return true;
-	}
+	no_child = !__lookup_mnt(path->mnt, path->dentry);
 	rcu_read_unlock();
-	return false;
+	if (need_seqretry(&mount_lock, seq)) {
+		read_seqlock_excl(&mount_lock);
+		no_child = !__lookup_mnt(path->mnt, path->dentry);
+		read_sequnlock_excl(&mount_lock);
+	}
+	return unlikely(!no_child);
 }
 
 /**
@@ -3638,46 +3665,41 @@ static int do_move_mount(struct path *old_path,
 	ns = old->mnt_ns;
 
 	err = -EINVAL;
-	if (!may_use_mount(p))
-		goto out;
-
 	/* The thing moved must be mounted... */
 	if (!is_mounted(&old->mnt))
 		goto out;
 
-	/* ... and either ours or the root of anon namespace */
-	if (!(attached ? check_mnt(old) : is_anon_ns(ns)))
-		goto out;
-
-	if (is_anon_ns(ns)) {
+	if (check_mnt(old)) {
+		/* if the source is in our namespace... */
+		/* ... it should be detachable from parent */
+		if (!mnt_has_parent(old) || IS_MNT_LOCKED(old))
+			goto out;
+		/* ... and the target should be in our namespace */
+		if (!check_mnt(p))
+			goto out;
+	} else {
 		/*
-		 * Ending up with two files referring to the root of the
-		 * same anonymous mount namespace would cause an error
-		 * as this would mean trying to move the same mount
-		 * twice into the mount tree which would be rejected
-		 * later. But be explicit about it right here.
+		 * 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(p->mnt_ns) && ns == p->mnt_ns))
+		if (!is_anon_ns(ns) || mnt_has_parent(old))
 			goto out;
-
 		/*
-		 * If this is an anonymous mount tree ensure that mount
-		 * propagation can detect mounts that were just
-		 * propagated to the target mount tree so we don't
-		 * propagate onto them.
+		 * Bail out early if the target is within the same namespace -
+		 * subsequent checks would've rejected that, but they lose
+		 * some corner cases if we check it early.
 		 */
-		ns->mntns_flags |= MNTNS_PROPAGATING;
-	} else if (is_anon_ns(p->mnt_ns)) {
+		if (ns == p->mnt_ns)
+			goto out;
 		/*
-		 * Don't allow moving an attached mount tree to an
-		 * anonymous mount tree.
+		 * Target should be either in our namespace or in an acceptable
+		 * anon namespace, sensu check_anonymous_mnt().
 		 */
-		goto out;
+		if (!may_use_mount(p))
+			goto out;
 	}
 
-	if (old->mnt.mnt_flags & MNT_LOCKED)
-		goto out;
-
 	if (!path_mounted(old_path))
 		goto out;
 
@@ -3723,8 +3745,6 @@ static int do_move_mount(struct path *old_path,
 	if (attached)
 		put_mountpoint(old_mp);
 out:
-	if (is_anon_ns(ns))
-		ns->mntns_flags &= ~MNTNS_PROPAGATING;
 	unlock_mount(mp);
 	if (!err) {
 		if (attached) {
@@ -3900,10 +3920,6 @@ int finish_automount(struct vfsmount *m, const struct path *path)
 		return PTR_ERR(m);
 
 	mnt = real_mount(m);
-	/* The new mount record should have at least 2 refs to prevent it being
-	 * expired before we get a chance to add it
-	 */
-	BUG_ON(mnt_get_count(mnt) < 2);
 
 	if (m->mnt_sb == path->mnt->mnt_sb &&
 	    m->mnt_root == dentry) {
@@ -3936,7 +3952,6 @@ int finish_automount(struct vfsmount *m, const struct path *path)
 	unlock_mount(mp);
 	if (unlikely(err))
 		goto discard;
-	mntput(m);
 	return 0;
 
 discard_locked:
@@ -3950,7 +3965,6 @@ discard:
 		namespace_unlock();
 	}
 	mntput(m);
-	mntput(m);
 	return err;
 }
 
@@ -3987,11 +4001,14 @@ void mark_mounts_for_expiry(struct list_head *mounts)
 
 	/* extract from the expiration list every vfsmount that matches the
 	 * following criteria:
+	 * - already mounted
 	 * - only referenced by its parent vfsmount
 	 * - still marked for expiry (marked on the last call here; marks are
 	 *   cleared by mntput())
 	 */
 	list_for_each_entry_safe(mnt, next, mounts, mnt_expire) {
+		if (!is_mounted(&mnt->mnt))
+			continue;
 		if (!xchg(&mnt->mnt_expiry_mark, 1) ||
 			propagate_mount_busy(mnt, 1))
 			continue;
@@ -5290,16 +5307,12 @@ SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename,
 			kattr.kflags |= MOUNT_KATTR_RECURSE;
 
 		ret = wants_mount_setattr(uattr, usize, &kattr);
-		if (ret < 0)
-			return ret;
-
-		if (ret) {
+		if (ret > 0) {
 			ret = do_mount_setattr(&file->f_path, &kattr);
-			if (ret)
-				return ret;
-
 			finish_mount_kattr(&kattr);
 		}
+		if (ret)
+			return ret;
 	}
 
 	fd = get_unused_fd_flags(flags & O_CLOEXEC);
@@ -6262,7 +6275,11 @@ void put_mnt_ns(struct mnt_namespace *ns)
 {
 	if (!refcount_dec_and_test(&ns->ns.count))
 		return;
-	drop_collected_mounts(&ns->root->mnt);
+	namespace_lock();
+	lock_mount_hash();
+	umount_tree(ns->root, 0);
+	unlock_mount_hash();
+	namespace_unlock();
 	free_mnt_ns(ns);
 }