userns: Simplify the user_namespace by making userns->creator a kuid.

- Transform userns->creator from a user_struct reference to a simple
  kuid_t, kgid_t pair.

  In cap_capable this allows the check to see if we are the creator of
  a namespace to become the classic suser style euid permission check.

  This allows us to remove the need for a struct cred in the mapping
  functions and still be able to dispaly the user namespace creators
  uid and gid as 0.

- Remove the now unnecessary delayed_work in free_user_ns.

  All that is left for free_user_ns to do is to call kmem_cache_free
  and put_user_ns.  Those functions can be called in any context
  so call them directly from free_user_ns removing the need for delayed work.

Acked-by: Serge Hallyn <[email protected]>
Signed-off-by: Eric W. Biederman <[email protected]>

include/linux/user_namespace.h

@@ -9,8 +9,8 @@
 struct user_namespace {
 	struct kref		kref;
 	struct user_namespace	*parent;
-	struct user_struct	*creator;
-	struct work_struct	destroyer;
+	kuid_t			owner;
+	kgid_t			group;
 };
 
 extern struct user_namespace init_user_ns;

kernel/user.c

@@ -25,7 +25,8 @@ struct user_namespace init_user_ns = {
 	.kref = {
 		.refcount	= ATOMIC_INIT(3),
 	},
-	.creator = &root_user,
+	.owner = GLOBAL_ROOT_UID,
+	.group = GLOBAL_ROOT_GID,
 };
 EXPORT_SYMBOL_GPL(init_user_ns);
 
@@ -54,9 +55,9 @@ struct hlist_head uidhash_table[UIDHASH_SZ];
  */
 static DEFINE_SPINLOCK(uidhash_lock);
 
-/* root_user.__count is 2, 1 for init task cred, 1 for init_user_ns->user_ns */
+/* root_user.__count is 1, for init task cred */
 struct user_struct root_user = {
-	.__count	= ATOMIC_INIT(2),
+	.__count	= ATOMIC_INIT(1),
 	.processes	= ATOMIC_INIT(1),
 	.files		= ATOMIC_INIT(0),
 	.sigpending	= ATOMIC_INIT(0),

kernel/user_namespace.c

@@ -27,6 +27,16 @@ int create_user_ns(struct cred *new)
 {
 	struct user_namespace *ns, *parent_ns = new->user_ns;
 	struct user_struct *root_user;
+	kuid_t owner = make_kuid(new->user_ns, new->euid);
+	kgid_t group = make_kgid(new->user_ns, new->egid);
+
+	/* The creator needs a mapping in the parent user namespace
+	 * or else we won't be able to reasonably tell userspace who
+	 * created a user_namespace.
+	 */
+	if (!kuid_has_mapping(parent_ns, owner) ||
+	    !kgid_has_mapping(parent_ns, group))
+		return -EPERM;
 
 	ns = kmem_cache_alloc(user_ns_cachep, GFP_KERNEL);
 	if (!ns)
@@ -43,7 +53,9 @@ int create_user_ns(struct cred *new)
 
 	/* set the new root user in the credentials under preparation */
 	ns->parent = parent_ns;
-	ns->creator = new->user;
+	ns->owner = owner;
+	ns->group = group;
+	free_uid(new->user);
 	new->user = root_user;
 	new->uid = new->euid = new->suid = new->fsuid = 0;
 	new->gid = new->egid = new->sgid = new->fsgid = 0;
@@ -63,35 +75,22 @@ int create_user_ns(struct cred *new)
 #endif
 	/* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */
 
-	/* Leave the reference to our user_ns with the new cred */
+	/* Leave the new->user_ns reference with the new user namespace. */
+	/* Leave the reference to our user_ns with the new cred. */
 	new->user_ns = ns;
 
 	return 0;
 }
 
-/*
- * Deferred destructor for a user namespace.  This is required because
- * free_user_ns() may be called with uidhash_lock held, but we need to call
- * back to free_uid() which will want to take the lock again.
- */
-static void free_user_ns_work(struct work_struct *work)
+void free_user_ns(struct kref *kref)
 {
 	struct user_namespace *parent, *ns =
-		container_of(work, struct user_namespace, destroyer);
+		container_of(kref, struct user_namespace, kref);
+
 	parent = ns->parent;
-	free_uid(ns->creator);
 	kmem_cache_free(user_ns_cachep, ns);
 	put_user_ns(parent);
 }
-
-void free_user_ns(struct kref *kref)
-{
-	struct user_namespace *ns =
-		container_of(kref, struct user_namespace, kref);
-
-	INIT_WORK(&ns->destroyer, free_user_ns_work);
-	schedule_work(&ns->destroyer);
-}
 EXPORT_SYMBOL(free_user_ns);
 
 uid_t user_ns_map_uid(struct user_namespace *to, const struct cred *cred, uid_t uid)
@@ -101,12 +100,11 @@ uid_t user_ns_map_uid(struct user_namespace *to, const struct cred *cred, uid_t
 	if (likely(to == cred->user_ns))
 		return uid;
 
-
 	/* Is cred->user the creator of the target user_ns
 	 * or the creator of one of it's parents?
 	 */
 	for ( tmp = to; tmp != &init_user_ns; tmp = tmp->parent ) {
-		if (cred->user == tmp->creator) {
+		if (uid_eq(cred->user->uid, tmp->owner)) {
 			return (uid_t)0;
 		}
 	}
@@ -126,7 +124,7 @@ gid_t user_ns_map_gid(struct user_namespace *to, const struct cred *cred, gid_t
 	 * or the creator of one of it's parents?
 	 */
 	for ( tmp = to; tmp != &init_user_ns; tmp = tmp->parent ) {
-		if (cred->user == tmp->creator) {
+		if (uid_eq(cred->user->uid, tmp->owner)) {
 			return (gid_t)0;
 		}
 	}

security/commoncap.c

@@ -76,8 +76,9 @@ int cap_capable(const struct cred *cred, struct user_namespace *targ_ns,
 		int cap, int audit)
 {
 	for (;;) {
-		/* The creator of the user namespace has all caps. */
-		if (targ_ns != &init_user_ns && targ_ns->creator == cred->user)
+		/* The owner of the user namespace has all caps. */
+		if (targ_ns != &init_user_ns && uid_eq(targ_ns->owner,
+						       make_kuid(cred->user_ns, cred->euid)))
 			return 0;
 
 		/* Do we have the necessary capabilities? */