userns: Simpilify MNT_NODEV handling.

- Consolidate the testing if a device node may be opened in a new
  function may_open_dev.

- Move the check for allowing access to device nodes on filesystems
  not mounted in the initial user namespace from mount time to open
  time and include it in may_open_dev.

This set of changes removes the implicit adding of MNT_NODEV which
simplifies the logic in fs/namespace.c and removes a potentially
problematic difference in how normal and unprivileged mount
namespaces work.  This is a user visible change in behavior for
remount in unpriviliged mount namespaces but is unlikely to cause
problems for existing software.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

fs/block_dev.c

@@ -1730,7 +1730,7 @@ struct block_device *lookup_bdev(const char *pathname)
 	if (!S_ISBLK(inode->i_mode))
 		goto fail;
 	error = -EACCES;
-	if (path.mnt->mnt_flags & MNT_NODEV)
+	if (!may_open_dev(&path))
 		goto fail;
 	error = -ENOMEM;
 	bdev = bd_acquire(inode);

fs/namei.c

@@ -2663,6 +2663,13 @@ int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 }
 EXPORT_SYMBOL(vfs_create);
 
+bool may_open_dev(const struct path *path)
+{
+	return !(path->mnt->mnt_flags & MNT_NODEV) &&
+		((path->mnt->mnt_sb->s_user_ns == &init_user_ns) ||
+		 (path->mnt->mnt_sb->s_type->fs_flags & FS_USERNS_DEV_MOUNT));
+}
+
 static int may_open(struct path *path, int acc_mode, int flag)
 {
 	struct dentry *dentry = path->dentry;
@@ -2685,7 +2692,7 @@ static int may_open(struct path *path, int acc_mode, int flag)
 		break;
 	case S_IFBLK:
 	case S_IFCHR:
-		if (path->mnt->mnt_flags & MNT_NODEV)
+		if (!may_open_dev(path))
 			return -EACCES;
 		/*FALLTHRU*/
 	case S_IFIFO:

fs/namespace.c

@@ -2177,14 +2177,8 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
 	}
 	if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) &&
 	    !(mnt_flags & MNT_NODEV)) {
-		/* Was the nodev implicitly added in mount? */
-		if ((mnt->mnt_ns->user_ns != &init_user_ns) &&
-		    !(sb->s_type->fs_flags & FS_USERNS_DEV_MOUNT)) {
-			mnt_flags |= MNT_NODEV;
-		} else {
 		return -EPERM;
 	}
-	}
 	if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) &&
 	    !(mnt_flags & MNT_NOSUID)) {
 		return -EPERM;
@@ -2396,13 +2390,6 @@ static int do_new_mount(struct path *path, const char *fstype, int flags,
 			put_filesystem(type);
 			return -EPERM;
 		}
-		/* Only in special cases allow devices from mounts
-		 * created outside the initial user namespace.
-		 */
-		if (!(type->fs_flags & FS_USERNS_DEV_MOUNT)) {
-			flags |= MS_NODEV;
-			mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
-		}
 		if (type->fs_flags & FS_USERNS_VISIBLE) {
 			if (!fs_fully_visible(type, &mnt_flags))
 				return -EPERM;
@@ -3238,6 +3225,9 @@ static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags)
 		mnt_flags = mnt->mnt.mnt_flags;
 		if (mnt->mnt.mnt_sb->s_iflags & SB_I_NOEXEC)
 			mnt_flags &= ~(MNT_LOCK_NOSUID | MNT_LOCK_NOEXEC);
+		if (mnt->mnt.mnt_sb->s_user_ns != &init_user_ns &&
+		    !(mnt->mnt.mnt_sb->s_type->fs_flags & FS_USERNS_DEV_MOUNT))
+			mnt_flags &= ~(MNT_LOCK_NODEV);
 
 		/* Verify the mount flags are equal to or more permissive
 		 * than the proposed new mount.

include/linux/fs.h

@@ -1542,6 +1542,7 @@ extern void dentry_unhash(struct dentry *dentry);
  */
 extern void inode_init_owner(struct inode *inode, const struct inode *dir,
 			umode_t mode);
+extern bool may_open_dev(const struct path *path);
 /*
  * VFS FS_IOC_FIEMAP helper definitions.
  */