Merge tag 'fuse-update-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse

Pull fuse updates from Miklos Szeredi:
 "The most interesting part of this update is user namespace support,
  mostly done by Eric Biederman. This enables safe unprivileged fuse
  mounts within a user namespace.

  There are also a couple of fixes for bugs found by syzbot and
  miscellaneous fixes and cleanups"

* tag 'fuse-update-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse:
  fuse: don't keep dead fuse_conn at fuse_fill_super().
  fuse: fix control dir setup and teardown
  fuse: fix congested state leak on aborted connections
  fuse: Allow fully unprivileged mounts
  fuse: Ensure posix acls are translated outside of init_user_ns
  fuse: add writeback documentation
  fuse: honor AT_STATX_FORCE_SYNC
  fuse: honor AT_STATX_DONT_SYNC
  fuse: Restrict allow_other to the superblock's namespace or a descendant
  fuse: Support fuse filesystems outside of init_user_ns
  fuse: Fail all requests with invalid uids or gids
  fuse: Remove the buggy retranslation of pids in fuse_dev_do_read
  fuse: return -ECONNABORTED on /dev/fuse read after abort
  fuse: atomic_o_trunc should truncate pagecache

1 files changed, 34 insertions, 16 deletions

diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index ef309958e060..ffcaf98044b9 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -171,8 +171,8 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
 	inode->i_ino     = fuse_squash_ino(attr->ino);
 	inode->i_mode    = (inode->i_mode & S_IFMT) | (attr->mode & 07777);
 	set_nlink(inode, attr->nlink);
-	inode->i_uid     = make_kuid(&init_user_ns, attr->uid);
-	inode->i_gid     = make_kgid(&init_user_ns, attr->gid);
+	inode->i_uid     = make_kuid(fc->user_ns, attr->uid);
+	inode->i_gid     = make_kgid(fc->user_ns, attr->gid);
 	inode->i_blocks  = attr->blocks;
 	inode->i_atime.tv_sec   = attr->atime;
 	inode->i_atime.tv_nsec  = attr->atimensec;
@@ -371,7 +371,7 @@ void fuse_unlock_inode(struct inode *inode)
 
 static void fuse_umount_begin(struct super_block *sb)
 {
-	fuse_abort_conn(get_fuse_conn_super(sb));
+	fuse_abort_conn(get_fuse_conn_super(sb), false);
 }
 
 static void fuse_send_destroy(struct fuse_conn *fc)
@@ -393,7 +393,7 @@ static void fuse_put_super(struct super_block *sb)
 
 	fuse_send_destroy(fc);
 
-	fuse_abort_conn(fc);
+	fuse_abort_conn(fc, false);
 	mutex_lock(&fuse_mutex);
 	list_del(&fc->entry);
 	fuse_ctl_remove_conn(fc);
@@ -477,7 +477,8 @@ static int fuse_match_uint(substring_t *s, unsigned int *res)
 	return err;
 }
 
-static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
+static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev,
+			  struct user_namespace *user_ns)
 {
 	char *p;
 	memset(d, 0, sizeof(struct fuse_mount_data));
@@ -513,7 +514,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 		case OPT_USER_ID:
 			if (fuse_match_uint(&args[0], &uv))
 				return 0;
-			d->user_id = make_kuid(current_user_ns(), uv);
+			d->user_id = make_kuid(user_ns, uv);
 			if (!uid_valid(d->user_id))
 				return 0;
 			d->user_id_present = 1;
@@ -522,7 +523,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev)
 		case OPT_GROUP_ID:
 			if (fuse_match_uint(&args[0], &uv))
 				return 0;
-			d->group_id = make_kgid(current_user_ns(), uv);
+			d->group_id = make_kgid(user_ns, uv);
 			if (!gid_valid(d->group_id))
 				return 0;
 			d->group_id_present = 1;
@@ -565,8 +566,8 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root)
 	struct super_block *sb = root->d_sb;
 	struct fuse_conn *fc = get_fuse_conn_super(sb);
 
-	seq_printf(m, ",user_id=%u", from_kuid_munged(&init_user_ns, fc->user_id));
-	seq_printf(m, ",group_id=%u", from_kgid_munged(&init_user_ns, fc->group_id));
+	seq_printf(m, ",user_id=%u", from_kuid_munged(fc->user_ns, fc->user_id));
+	seq_printf(m, ",group_id=%u", from_kgid_munged(fc->user_ns, fc->group_id));
 	if (fc->default_permissions)
 		seq_puts(m, ",default_permissions");
 	if (fc->allow_other)
@@ -597,7 +598,7 @@ static void fuse_pqueue_init(struct fuse_pqueue *fpq)
 	fpq->connected = 1;
 }
 
-void fuse_conn_init(struct fuse_conn *fc)
+void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns)
 {
 	memset(fc, 0, sizeof(*fc));
 	spin_lock_init(&fc->lock);
@@ -621,6 +622,7 @@ void fuse_conn_init(struct fuse_conn *fc)
 	fc->attr_version = 1;
 	get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
 	fc->pid_ns = get_pid_ns(task_active_pid_ns(current));
+	fc->user_ns = get_user_ns(user_ns);
 }
 EXPORT_SYMBOL_GPL(fuse_conn_init);
 
@@ -630,6 +632,7 @@ void fuse_conn_put(struct fuse_conn *fc)
 		if (fc->destroy_req)
 			fuse_request_free(fc->destroy_req);
 		put_pid_ns(fc->pid_ns);
+		put_user_ns(fc->user_ns);
 		fc->release(fc);
 	}
 }
@@ -918,6 +921,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 				fc->posix_acl = 1;
 				fc->sb->s_xattr = fuse_acl_xattr_handlers;
 			}
+			if (arg->flags & FUSE_ABORT_ERROR)
+				fc->abort_err = 1;
 		} else {
 			ra_pages = fc->max_read / PAGE_SIZE;
 			fc->no_lock = 1;
@@ -948,7 +953,8 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 		FUSE_FLOCK_LOCKS | FUSE_HAS_IOCTL_DIR | FUSE_AUTO_INVAL_DATA |
 		FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO |
 		FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT |
-		FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL;
+		FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL |
+		FUSE_ABORT_ERROR;
 	req->in.h.opcode = FUSE_INIT;
 	req->in.numargs = 1;
 	req->in.args[0].size = sizeof(*arg);
@@ -1061,7 +1067,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 
 	sb->s_flags &= ~(SB_NOSEC | SB_I_VERSION);
 
-	if (!parse_fuse_opt(data, &d, is_bdev))
+	if (!parse_fuse_opt(data, &d, is_bdev, sb->s_user_ns))
 		goto err;
 
 	if (is_bdev) {
@@ -1089,16 +1095,27 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 	if (!file)
 		goto err;
 
-	if ((file->f_op != &fuse_dev_operations) ||
-	    (file->f_cred->user_ns != &init_user_ns))
+	/*
+	 * Require mount to happen from the same user namespace which
+	 * opened /dev/fuse to prevent potential attacks.
+	 */
+	if (file->f_op != &fuse_dev_operations ||
+	    file->f_cred->user_ns != sb->s_user_ns)
 		goto err_fput;
 
+	/*
+	 * If we are not in the initial user namespace posix
+	 * acls must be translated.
+	 */
+	if (sb->s_user_ns != &init_user_ns)
+		sb->s_xattr = fuse_no_acl_xattr_handlers;
+
 	fc = kmalloc(sizeof(*fc), GFP_KERNEL);
 	err = -ENOMEM;
 	if (!fc)
 		goto err_fput;
 
-	fuse_conn_init(fc);
+	fuse_conn_init(fc, sb->s_user_ns);
 	fc->release = fuse_free_conn;
 
 	fud = fuse_dev_alloc(fc);
@@ -1179,6 +1196,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 	fuse_dev_free(fud);
  err_put_conn:
 	fuse_conn_put(fc);
+	sb->s_fs_info = NULL;
  err_fput:
 	fput(file);
  err:
@@ -1208,7 +1226,7 @@ static void fuse_kill_sb_anon(struct super_block *sb)
 static struct file_system_type fuse_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "fuse",
-	.fs_flags	= FS_HAS_SUBTYPE,
+	.fs_flags	= FS_HAS_SUBTYPE | FS_USERNS_MOUNT,
 	.mount		= fuse_mount,
 	.kill_sb	= fuse_kill_sb_anon,
 };