1 files changed, 50 insertions, 21 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index e6585f285234..6f9a6bee9d87 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1015,6 +1015,21 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void
 }
 EXPORT_SYMBOL_GPL(vfs_kern_mount);
 
+struct vfsmount *
+vfs_submount(const struct dentry *mountpoint, struct file_system_type *type,
+	     const char *name, void *data)
+{
+	/* Until it is worked out how to pass the user namespace
+	 * through from the parent mount to the submount don't support
+	 * unprivileged mounts with submounts.
+	 */
+	if (mountpoint->d_sb->s_user_ns != &init_user_ns)
+		return ERR_PTR(-EPERM);
+
+	return vfs_kern_mount(type, MS_SUBMOUNT, name, data);
+}
+EXPORT_SYMBOL_GPL(vfs_submount);
+
 static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 					int flag)
 {
@@ -1850,6 +1865,20 @@ void drop_collected_mounts(struct vfsmount *mnt)
 	namespace_unlock();
 }
 
+static bool has_locked_children(struct mount *mnt, struct dentry *dentry)
+{
+	struct mount *child;
+
+	list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
+		if (!is_subdir(child->mnt_mountpoint, dentry))
+			continue;
+
+		if (child->mnt.mnt_flags & MNT_LOCKED)
+			return true;
+	}
+	return false;
+}
+
 /**
  * clone_private_mount - create a private clone of a path
  *
@@ -1864,16 +1893,27 @@ struct vfsmount *clone_private_mount(struct path *path)
 	struct mount *old_mnt = real_mount(path->mnt);
 	struct mount *new_mnt;
 
+	down_read(&namespace_sem);
 	if (IS_MNT_UNBINDABLE(old_mnt))
-		return ERR_PTR(-EINVAL);
+		goto invalid;
+
+	if (!check_mnt(old_mnt))
+		goto invalid;
+
+	if (has_locked_children(old_mnt, path->dentry))
+		goto invalid;
 
-	down_read(&namespace_sem);
 	new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE);
 	up_read(&namespace_sem);
+
 	if (IS_ERR(new_mnt))
 		return ERR_CAST(new_mnt);
 
 	return &new_mnt->mnt;
+
+invalid:
+	up_read(&namespace_sem);
+	return ERR_PTR(-EINVAL);
 }
 EXPORT_SYMBOL_GPL(clone_private_mount);
 
@@ -2189,19 +2229,6 @@ static int do_change_type(struct path *path, int flag)
 	return err;
 }
 
-static bool has_locked_children(struct mount *mnt, struct dentry *dentry)
-{
-	struct mount *child;
-	list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
-		if (!is_subdir(child->mnt_mountpoint, dentry))
-			continue;
-
-		if (child->mnt.mnt_flags & MNT_LOCKED)
-			return true;
-	}
-	return false;
-}
-
 /*
  * do loopback mount.
  */
@@ -2533,10 +2560,6 @@ static int do_new_mount(struct path *path, const char *fstype, int flags,
 		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.
 		 */
@@ -2856,7 +2879,7 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 
 	flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
 		   MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
-		   MS_STRICTATIME);
+		   MS_STRICTATIME | MS_SUBMOUNT);
 
 	if (flags & MS_REMOUNT)
 		retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags,
@@ -3187,8 +3210,8 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	/* make certain new is below the root */
 	if (!is_path_reachable(new_mnt, new.dentry, &root))
 		goto out4;
-	root_mp->m_count++; /* pin it so it won't go away */
 	lock_mount_hash();
+	root_mp->m_count++; /* pin it so it won't go away */
 	detach_mnt(new_mnt, &parent_path);
 	detach_mnt(root_mnt, &root_parent);
 	if (root_mnt->mnt.mnt_flags & MNT_LOCKED) {
@@ -3491,10 +3514,16 @@ static int mntns_install(struct nsproxy *nsproxy, struct ns_common *ns)
 	return 0;
 }
 
+static struct user_namespace *mntns_owner(struct ns_common *ns)
+{
+	return to_mnt_ns(ns)->user_ns;
+}
+
 const struct proc_ns_operations mntns_operations = {
 	.name		= "mnt",
 	.type		= CLONE_NEWNS,
 	.get		= mntns_get,
 	.put		= mntns_put,
 	.install	= mntns_install,
+	.owner		= mntns_owner,
 };