overlayfs fixes for 5.14-rc6

-----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQSQHSd0lITzzeNWNm3h3BK/laaZPAUCYRKSDgAKCRDh3BK/laaZ
 PKSNAQCd1yGLShL44sI5lCFnGjwHGCXdfU5b8sIxNBy5DOWvTwD/edF4eUJzyME+
 mZ4AwnX70N2eHJCFH/uodL0Y9Sf3egM=
 =zUIV
 -----END PGP SIGNATURE-----

Merge tag 'ovl-fixes-5.14-rc6-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs

Pull overlayfs fixes from Miklos Szeredi:
 "Fix several bugs in overlayfs"

* tag 'ovl-fixes-5.14-rc6-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs:
  ovl: prevent private clone if bind mount is not allowed
  ovl: fix uninitialized pointer read in ovl_lookup_real_one()
  ovl: fix deadlock in splice write
  ovl: skip stale entries in merge dir cache iteration

fs/namespace.c

@@ -1938,6 +1938,20 @@ void drop_collected_mounts(struct vfsmount *mnt)
 	namespace_unlock();
 }
 
+static bool has_locked_children(struct mount *mnt, struct dentry *dentry)
+{
+	struct mount *child;
+
+	list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
+		if (!is_subdir(child->mnt_mountpoint, dentry))
+			continue;
+
+		if (child->mnt.mnt_flags & MNT_LOCKED)
+			return true;
+	}
+	return false;
+}
+
 /**
  * clone_private_mount - create a private clone of a path
  * @path: path to clone
@@ -1953,10 +1967,19 @@ 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);
 	if (IS_MNT_UNBINDABLE(old_mnt))
-		return ERR_PTR(-EINVAL);
+		goto invalid;
+
+	if (!check_mnt(old_mnt))
+		goto invalid;
+
+	if (has_locked_children(old_mnt, path->dentry))
+		goto invalid;
 
 	new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE);
+	up_read(&namespace_sem);
+
 	if (IS_ERR(new_mnt))
 		return ERR_CAST(new_mnt);
 
@@ -1964,6 +1987,10 @@ struct vfsmount *clone_private_mount(const struct path *path)
 	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);
 
@@ -2315,19 +2342,6 @@ static int do_change_type(struct path *path, int ms_flags)
 	return err;
 }
 
-static bool has_locked_children(struct mount *mnt, struct dentry *dentry)
-{
-	struct mount *child;
-	list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
-		if (!is_subdir(child->mnt_mountpoint, dentry))
-			continue;
-
-		if (child->mnt.mnt_flags & MNT_LOCKED)
-			return true;
-	}
-	return false;
-}
-
 static struct mount *__do_loopback(struct path *old_path, int recurse)
 {
 	struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt);

fs/overlayfs/export.c

@@ -392,6 +392,7 @@ static struct dentry *ovl_lookup_real_one(struct dentry *connected,
 	 */
 	take_dentry_name_snapshot(&name, real);
 	this = lookup_one_len(name.name.name, connected, name.name.len);
+	release_dentry_name_snapshot(&name);
 	err = PTR_ERR(this);
 	if (IS_ERR(this)) {
 		goto fail;
@@ -406,7 +407,6 @@ static struct dentry *ovl_lookup_real_one(struct dentry *connected,
 	}
 
 out:
-	release_dentry_name_snapshot(&name);
 	dput(parent);
 	inode_unlock(dir);
 	return this;

fs/overlayfs/file.c

@@ -392,6 +392,51 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	return ret;
 }
 
+/*
+ * Calling iter_file_splice_write() directly from overlay's f_op may deadlock
+ * due to lock order inversion between pipe->mutex in iter_file_splice_write()
+ * and file_start_write(real.file) in ovl_write_iter().
+ *
+ * So do everything ovl_write_iter() does and call iter_file_splice_write() on
+ * the real file.
+ */
+static ssize_t ovl_splice_write(struct pipe_inode_info *pipe, struct file *out,
+				loff_t *ppos, size_t len, unsigned int flags)
+{
+	struct fd real;
+	const struct cred *old_cred;
+	struct inode *inode = file_inode(out);
+	struct inode *realinode = ovl_inode_real(inode);
+	ssize_t ret;
+
+	inode_lock(inode);
+	/* Update mode */
+	ovl_copyattr(realinode, inode);
+	ret = file_remove_privs(out);
+	if (ret)
+		goto out_unlock;
+
+	ret = ovl_real_fdget(out, &real);
+	if (ret)
+		goto out_unlock;
+
+	old_cred = ovl_override_creds(inode->i_sb);
+	file_start_write(real.file);
+
+	ret = iter_file_splice_write(pipe, real.file, ppos, len, flags);
+
+	file_end_write(real.file);
+	/* Update size */
+	ovl_copyattr(realinode, inode);
+	revert_creds(old_cred);
+	fdput(real);
+
+out_unlock:
+	inode_unlock(inode);
+
+	return ret;
+}
+
 static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	struct fd real;
@@ -603,7 +648,7 @@ const struct file_operations ovl_file_operations = {
 	.fadvise	= ovl_fadvise,
 	.flush		= ovl_flush,
 	.splice_read    = generic_file_splice_read,
-	.splice_write   = iter_file_splice_write,
+	.splice_write   = ovl_splice_write,
 
 	.copy_file_range	= ovl_copy_file_range,
 	.remap_file_range	= ovl_remap_file_range,

fs/overlayfs/readdir.c

@@ -481,6 +481,8 @@ static int ovl_cache_update_ino(struct path *path, struct ovl_cache_entry *p)
 	}
 	this = lookup_one_len(p->name, dir, p->len);
 	if (IS_ERR_OR_NULL(this) || !this->d_inode) {
+		/* Mark a stale entry */
+		p->is_whiteout = true;
 		if (IS_ERR(this)) {
 			err = PTR_ERR(this);
 			this = NULL;
@@ -776,6 +778,9 @@ static int ovl_iterate(struct file *file, struct dir_context *ctx)
 				if (err)
 					goto out;
 			}
+		}
+		/* ovl_cache_update_ino() sets is_whiteout on stale entry */
+		if (!p->is_whiteout) {
 			if (!dir_emit(ctx, p->name, p->len, p->ino, p->type))
 				break;
 		}