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

Pull mount fixes from Al Viro:
 "Several mount-related fixes"

* tag 'pull-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  userns and mnt_idmap leak in open_tree_attr(2)
  attach_recursive_mnt(): do not lock the covering tree when sliding something under it
  replace collect_mounts()/drop_collected_mounts() with a safer variant

Author: torvalds

Documentation/filesystems/porting.rst

@@ -1249,3 +1249,12 @@ Using try_lookup_noperm() will require linux/namei.h to be included.
 
 Calling conventions for ->d_automount() have changed; we should *not* grab
 an extra reference to new mount - it should be returned with refcount 1.
+
+---
+
+collect_mounts()/drop_collected_mounts()/iterate_mounts() are gone now.
+Replacement is collect_paths()/drop_collected_path(), with no special
+iterator needed.  Instead of a cloned mount tree, the new interface returns
+an array of struct path, one for each mount collect_mounts() would've
+created.  These struct path point to locations in the caller's namespace
+that would be roots of the cloned mounts.

fs/namespace.c

@@ -2310,21 +2310,62 @@ struct mount *copy_tree(struct mount *src_root, struct dentry *dentry,
 	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;
 
-struct vfsmount *collect_mounts(const struct path *path)
+	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 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 *);
@@ -2401,15 +2442,6 @@ 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();
-}
-
 static bool __has_locked_children(struct mount *mnt, struct dentry *dentry)
 {
 	struct mount *child;
@@ -2511,21 +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;
@@ -2751,14 +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);
@@ -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);
 }
 

fs/pnode.h

@@ -28,8 +28,6 @@
 #define CL_SHARED_TO_SLAVE	0x20
 #define CL_COPY_MNT_NS_FILE	0x40
 
-#define CL_COPY_ALL		(CL_COPY_UNBINDABLE | CL_COPY_MNT_NS_FILE)
-
 static inline void set_mnt_shared(struct mount *mnt)
 {
 	mnt->mnt.mnt_flags &= ~MNT_SHARED_MASK;

include/linux/mount.h

@@ -116,10 +116,8 @@ extern int may_umount_tree(struct vfsmount *);
 extern int may_umount(struct vfsmount *);
 int do_mount(const char *, const char __user *,
 		     const char *, unsigned long, void *);
-extern struct vfsmount *collect_mounts(const struct path *);
-extern void drop_collected_mounts(struct vfsmount *);
-extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
-			  struct vfsmount *);
+extern struct path *collect_paths(const struct path *, struct path *, unsigned);
+extern void drop_collected_paths(struct path *, struct path *);
 extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num);
 
 extern int cifs_root_data(char **dev, char **opts);

kernel/audit_tree.c

@@ -668,12 +668,6 @@ int audit_remove_tree_rule(struct audit_krule *rule)
 	return 0;
 }
 
-static int compare_root(struct vfsmount *mnt, void *arg)
-{
-	return inode_to_key(d_backing_inode(mnt->mnt_root)) ==
-	       (unsigned long)arg;
-}
-
 void audit_trim_trees(void)
 {
 	struct list_head cursor;
@@ -683,8 +677,9 @@ void audit_trim_trees(void)
 	while (cursor.next != &tree_list) {
 		struct audit_tree *tree;
 		struct path path;
-		struct vfsmount *root_mnt;
 		struct audit_node *node;
+		struct path *paths;
+		struct path array[16];
 		int err;
 
 		tree = container_of(cursor.next, struct audit_tree, list);
@@ -696,24 +691,27 @@ void audit_trim_trees(void)
 		if (err)
 			goto skip_it;
 
-		root_mnt = collect_mounts(&path);
+		paths = collect_paths(&path, array, 16);
 		path_put(&path);
-		if (IS_ERR(root_mnt))
+		if (IS_ERR(paths))
 			goto skip_it;
 
 		spin_lock(&hash_lock);
 		list_for_each_entry(node, &tree->chunks, list) {
 			struct audit_chunk *chunk = find_chunk(node);
 			/* this could be NULL if the watch is dying else where... */
 			node->index |= 1U<<31;
-			if (iterate_mounts(compare_root,
-					   (void *)(chunk->key),
-					   root_mnt))
-				node->index &= ~(1U<<31);
+			for (struct path *p = paths; p->dentry; p++) {
+				struct inode *inode = p->dentry->d_inode;
+				if (inode_to_key(inode) == chunk->key) {
+					node->index &= ~(1U<<31);
+					break;
+				}
+			}
 		}
 		spin_unlock(&hash_lock);
 		trim_marked(tree);
-		drop_collected_mounts(root_mnt);
+		drop_collected_paths(paths, array);
 skip_it:
 		put_tree(tree);
 		mutex_lock(&audit_filter_mutex);
@@ -742,9 +740,14 @@ void audit_put_tree(struct audit_tree *tree)
 	put_tree(tree);
 }
 
-static int tag_mount(struct vfsmount *mnt, void *arg)
+static int tag_mounts(struct path *paths, struct audit_tree *tree)
 {
-	return tag_chunk(d_backing_inode(mnt->mnt_root), arg);
+	for (struct path *p = paths; p->dentry; p++) {
+		int err = tag_chunk(p->dentry->d_inode, tree);
+		if (err)
+			return err;
+	}
+	return 0;
 }
 
 /*
@@ -801,7 +804,8 @@ int audit_add_tree_rule(struct audit_krule *rule)
 {
 	struct audit_tree *seed = rule->tree, *tree;
 	struct path path;
-	struct vfsmount *mnt;
+	struct path array[16];
+	struct path *paths;
 	int err;
 
 	rule->tree = NULL;
@@ -828,16 +832,16 @@ int audit_add_tree_rule(struct audit_krule *rule)
 	err = kern_path(tree->pathname, 0, &path);
 	if (err)
 		goto Err;
-	mnt = collect_mounts(&path);
+	paths = collect_paths(&path, array, 16);
 	path_put(&path);
-	if (IS_ERR(mnt)) {
-		err = PTR_ERR(mnt);
+	if (IS_ERR(paths)) {
+		err = PTR_ERR(paths);
 		goto Err;
 	}
 
 	get_tree(tree);
-	err = iterate_mounts(tag_mount, tree, mnt);
-	drop_collected_mounts(mnt);
+	err = tag_mounts(paths, tree);
+	drop_collected_paths(paths, array);
 
 	if (!err) {
 		struct audit_node *node;
@@ -872,20 +876,21 @@ int audit_tag_tree(char *old, char *new)
 	struct list_head cursor, barrier;
 	int failed = 0;
 	struct path path1, path2;
-	struct vfsmount *tagged;
+	struct path array[16];
+	struct path *paths;
 	int err;
 
 	err = kern_path(new, 0, &path2);
 	if (err)
 		return err;
-	tagged = collect_mounts(&path2);
+	paths = collect_paths(&path2, array, 16);
 	path_put(&path2);
-	if (IS_ERR(tagged))
-		return PTR_ERR(tagged);
+	if (IS_ERR(paths))
+		return PTR_ERR(paths);
 
 	err = kern_path(old, 0, &path1);
 	if (err) {
-		drop_collected_mounts(tagged);
+		drop_collected_paths(paths, array);
 		return err;
 	}
 
@@ -914,7 +919,7 @@ int audit_tag_tree(char *old, char *new)
 			continue;
 		}
 
-		failed = iterate_mounts(tag_mount, tree, tagged);
+		failed = tag_mounts(paths, tree);
 		if (failed) {
 			put_tree(tree);
 			mutex_lock(&audit_filter_mutex);
@@ -955,7 +960,7 @@ int audit_tag_tree(char *old, char *new)
 	list_del(&cursor);
 	mutex_unlock(&audit_filter_mutex);
 	path_put(&path1);
-	drop_collected_mounts(tagged);
+	drop_collected_paths(paths, array);
 	return failed;
 }