Re: [PATCH] fs: allow clone_private_mount() for a path on real rootfs

[Al Viro <viro@xxxxxxxxxxxxxxxxxx>]

On Wed, May 14, 2025 at 12:25:58AM +0000, KONDO KAZUMA(近藤 和真) wrote:

> @@ -2482,17 +2482,13 @@ 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 (!is_mounted(&old_mnt->mnt))
> +		return ERR_PTR(-EINVAL);
> +
> +	if (mnt_has_parent(old_mnt) || !is_anon_ns(old_mnt->mnt_ns)) {
>  		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))
> -			return ERR_PTR(-EINVAL);
> -
>  		/* Make sure we don't create mount namespace loops. */
>  		if (!check_for_nsfs_mounts(old_mnt))
>  			return ERR_PTR(-EINVAL);

Not the right way to do that.  What we want is

	/* ours are always fine */
	if (!check_mnt(old_mnt)) {
		/* they'd better be mounted _somewhere */
		if (!is_mounted(old_mnt))
			return -EINVAL;
		/* no other real namespaces; only anon */
		if (!is_anon_ns(old_mnt->mnt_ns))
			return -EINVAL;
		/* ... and root of that anon */
		if (mnt_has_parent(old_mnt))
			return -EINVAL;
		/* Make sure we don't create mount namespace loops. */
		if (!check_for_nsfs_mounts(old_mnt))
			return ERR_PTR(-EINVAL);
	}