vfs: Allow unprivileged manipulation of the mount namespace.

- Add a filesystem flag to mark filesystems that are safe to mount as
  an unprivileged user.

- Add a filesystem flag to mark filesystems that don't need MNT_NODEV
  when mounted by an unprivileged user.

- Relax the permission checks to allow unprivileged users that have
  CAP_SYS_ADMIN permissions in the user namespace referred to by the
  current mount namespace to be allowed to mount, unmount, and move
  filesystems.

Acked-by: "Serge E. Hallyn" <serge@hallyn.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

1 files changed, 43 insertions, 26 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index 4dfcaf05d17c..9ddc86f93221 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1269,7 +1269,7 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
                 goto dput_and_out;
 
         retval = -EPERM;
-        if (!capable(CAP_SYS_ADMIN))
+        if (!ns_capable(mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
                 goto dput_and_out;
 
         retval = do_umount(mnt, flags);
@@ -1295,7 +1295,7 @@ SYSCALL_DEFINE1(oldumount, char __user *, name)
 
 static int mount_is_safe(struct path *path)
 {
-        if (capable(CAP_SYS_ADMIN))
+        if (ns_capable(real_mount(path->mnt)->mnt_ns->user_ns, CAP_SYS_ADMIN))
                 return 0;
         return -EPERM;
 #ifdef notyet
@@ -1633,7 +1633,7 @@ static int do_change_type(struct path *path, int flag)
         int type;
         int err = 0;
 
-        if (!capable(CAP_SYS_ADMIN))
+        if (!ns_capable(mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
                 return -EPERM;
 
         if (path->dentry != path->mnt->mnt_root)
@@ -1797,7 +1797,7 @@ static int do_move_mount(struct path *path, const char *old_name)
         struct mount *p;
         struct mount *old;
         int err = 0;
-        if (!capable(CAP_SYS_ADMIN))
+        if (!ns_capable(real_mount(path->mnt)->mnt_ns->user_ns, CAP_SYS_ADMIN))
                 return -EPERM;
         if (!old_name || !*old_name)
                 return -EINVAL;
@@ -1884,21 +1884,6 @@ static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
         return ERR_PTR(err);
 }
 
-static struct vfsmount *
-do_kern_mount(const char *fstype, int flags, const char *name, void *data)
-{
-        struct file_system_type *type = get_fs_type(fstype);
-        struct vfsmount *mnt;
-        if (!type)
-                return ERR_PTR(-ENODEV);
-        mnt = vfs_kern_mount(type, flags, name, data);
-        if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
-            !mnt->mnt_sb->s_subtype)
-                mnt = fs_set_subtype(mnt, fstype);
-        put_filesystem(type);
-        return mnt;
-}
-
 /*
  * add a mount into a namespace's mount tree
  */
@@ -1944,20 +1929,46 @@ unlock:
  * create a new mount for userspace and request it to be added into the
  * namespace's tree
  */
-static int do_new_mount(struct path *path, const char *type, int flags,
+static int do_new_mount(struct path *path, const char *fstype, int flags,
                         int mnt_flags, const char *name, void *data)
 {
+        struct file_system_type *type;
+        struct user_namespace *user_ns;
         struct vfsmount *mnt;
         int err;
 
-        if (!type)
+        if (!fstype)
                 return -EINVAL;
 
         /* we need capabilities... */
-        if (!capable(CAP_SYS_ADMIN))
+        user_ns = real_mount(path->mnt)->mnt_ns->user_ns;
+        if (!ns_capable(user_ns, CAP_SYS_ADMIN))
                 return -EPERM;
 
-        mnt = do_kern_mount(type, flags, name, data);
+        type = get_fs_type(fstype);
+        if (!type)
+                return -ENODEV;
+
+        if (user_ns != &init_user_ns) {
+                if (!(type->fs_flags & FS_USERNS_MOUNT)) {
+                        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 = vfs_kern_mount(type, flags, name, data);
+        if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
+            !mnt->mnt_sb->s_subtype)
+                mnt = fs_set_subtype(mnt, fstype);
+
+        put_filesystem(type);
         if (IS_ERR(mnt))
                 return PTR_ERR(mnt);
 
@@ -2549,7 +2560,7 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
         struct mount *new_mnt, *root_mnt;
         int error;
 
-        if (!capable(CAP_SYS_ADMIN))
+        if (!ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN))
                 return -EPERM;
 
         error = user_path_dir(new_root, &new);
@@ -2631,8 +2642,13 @@ static void __init init_mount_tree(void)
         struct vfsmount *mnt;
         struct mnt_namespace *ns;
         struct path root;
+        struct file_system_type *type;
 
-        mnt = do_kern_mount("rootfs", 0, "rootfs", NULL);
+        type = get_fs_type("rootfs");
+        if (!type)
+                panic("Can't find rootfs type");
+        mnt = vfs_kern_mount(type, 0, "rootfs", NULL);
+        put_filesystem(type);
         if (IS_ERR(mnt))
                 panic("Can't create rootfs");
 
@@ -2757,7 +2773,8 @@ static int mntns_install(struct nsproxy *nsproxy, void *ns)
         struct mnt_namespace *mnt_ns = ns;
         struct path root;
 
-        if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_CHROOT))
+        if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) ||
+            !nsown_capable(CAP_SYS_CHROOT))
                 return -EINVAL;
 
         if (fs->users != 1)