mnt: Refactor the logic for mounting sysfs and proc in a user namespace

commit 1b852bceb0d111e510d1a15826ecc4a19358d512 upstream.

Fresh mounts of proc and sysfs are a very special case that works very
much like a bind mount.  Unfortunately the current structure can not
preserve the MNT_LOCK... mount flags.  Therefore refactor the logic
into a form that can be modified to preserve those lock bits.

Add a new filesystem flag FS_USERNS_VISIBLE that requires some mount
of the filesystem be fully visible in the current mount namespace,
before the filesystem may be mounted.

Move the logic for calling fs_fully_visible from proc and sysfs into
fs/namespace.c where it has greater access to mount namespace state.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 1 insertions, 4 deletions

diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 8a49486bf30c..1c6ac6fcee9f 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -31,9 +31,6 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
         bool new_sb;
 
         if (!(flags & MS_KERNMOUNT)) {
-                if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
-                        return ERR_PTR(-EPERM);
-
                 if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET))
                         return ERR_PTR(-EPERM);
         }
@@ -58,7 +55,7 @@ static struct file_system_type sysfs_fs_type = {
         .name           = "sysfs",
         .mount          = sysfs_mount,
         .kill_sb        = sysfs_kill_sb,
-        .fs_flags       = FS_USERNS_MOUNT,
+        .fs_flags       = FS_USERNS_VISIBLE | FS_USERNS_MOUNT,
 };
 
 int __init sysfs_init(void)