User namespaces: set of cleanups (v2)

The user_ns is moved from nsproxy to user_struct, so that a struct
cred by itself is sufficient to determine access (which it otherwise
would not be).  Corresponding ecryptfs fixes (by David Howells) are
here as well.

Fix refcounting.  The following rules now apply:
        1. The task pins the user struct.
        2. The user struct pins its user namespace.
        3. The user namespace pins the struct user which created it.

User namespaces are cloned during copy_creds().  Unsharing a new user_ns
is no longer possible.  (We could re-add that, but it'll cause code
duplication and doesn't seem useful if PAM doesn't need to clone user
namespaces).

When a user namespace is created, its first user (uid 0) gets empty
keyrings and a clean group_info.

This incorporates a previous patch by David Howells.  Here
is his original patch description:

>I suggest adding the attached incremental patch.  It makes the following
>changes:
>
> (1) Provides a current_user_ns() macro to wrap accesses to current's user
>     namespace.
>
> (2) Fixes eCryptFS.
>
> (3) Renames create_new_userns() to create_user_ns() to be more consistent
>     with the other associated functions and because the 'new' in the name is
>     superfluous.
>
> (4) Moves the argument and permission checks made for CLONE_NEWUSER to the
>     beginning of do_fork() so that they're done prior to making any attempts
>     at allocation.
>
> (5) Calls create_user_ns() after prepare_creds(), and gives it the new creds
>     to fill in rather than have it return the new root user.  I don't imagine
>     the new root user being used for anything other than filling in a cred
>     struct.
>
>     This also permits me to get rid of a get_uid() and a free_uid(), as the
>     reference the creds were holding on the old user_struct can just be
>     transferred to the new namespace's creator pointer.
>
> (6) Makes create_user_ns() reset the UIDs and GIDs of the creds under
>     preparation rather than doing it in copy_creds().
>
>David

>Signed-off-by: David Howells <dhowells@redhat.com>

Changelog:
	Oct 20: integrate dhowells comments
		1. leave thread_keyring alone
		2. use current_user_ns() in set_user()

Signed-off-by: Serge Hallyn <serue@us.ibm.com>
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 0d9c51d..7908431 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -9,70 +9,55 @@
 #include <linux/nsproxy.h>
 #include <linux/slab.h>
 #include <linux/user_namespace.h>
+#include <linux/cred.h>
 
 /*
- * Clone a new ns copying an original user ns, setting refcount to 1
- * @old_ns: namespace to clone
- * Return NULL on error (failure to kmalloc), new ns otherwise
+ * Create a new user namespace, deriving the creator from the user in the
+ * passed credentials, and replacing that user with the new root user for the
+ * new namespace.
+ *
+ * This is called by copy_creds(), which will finish setting the target task's
+ * credentials.
  */
-static struct user_namespace *clone_user_ns(struct user_namespace *old_ns)
+int create_user_ns(struct cred *new)
 {
 	struct user_namespace *ns;
-	struct user_struct *new_user;
-	struct cred *new;
+	struct user_struct *root_user;
 	int n;
 
 	ns = kmalloc(sizeof(struct user_namespace), GFP_KERNEL);
 	if (!ns)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
 	kref_init(&ns->kref);
 
 	for (n = 0; n < UIDHASH_SZ; ++n)
 		INIT_HLIST_HEAD(ns->uidhash_table + n);
 
-	/* Insert new root user.  */
-	ns->root_user = alloc_uid(ns, 0);
-	if (!ns->root_user) {
+	/* Alloc new root user.  */
+	root_user = alloc_uid(ns, 0);
+	if (!root_user) {
 		kfree(ns);
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 	}
 
-	/* Reset current->user with a new one */
-	new_user = alloc_uid(ns, current_uid());
-	if (!new_user) {
-		free_uid(ns->root_user);
-		kfree(ns);
-		return ERR_PTR(-ENOMEM);
-	}
+	/* set the new root user in the credentials under preparation */
+	ns->creator = new->user;
+	new->user = root_user;
+	new->uid = new->euid = new->suid = new->fsuid = 0;
+	new->gid = new->egid = new->sgid = new->fsgid = 0;
+	put_group_info(new->group_info);
+	new->group_info = get_group_info(&init_groups);
+#ifdef CONFIG_KEYS
+	key_put(new->request_key_auth);
+	new->request_key_auth = NULL;
+#endif
+	/* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */
 
-	/* Install the new user */
-	new = prepare_creds();
-	if (!new) {
-		free_uid(new_user);
-		free_uid(ns->root_user);
-		kfree(ns);
-	}
-	free_uid(new->user);
-	new->user = new_user;
-	commit_creds(new);
-	return ns;
-}
+	/* alloc_uid() incremented the userns refcount.  Just set it to 1 */
+	kref_set(&ns->kref, 1);
 
-struct user_namespace * copy_user_ns(int flags, struct user_namespace *old_ns)
-{
-	struct user_namespace *new_ns;
-
-	BUG_ON(!old_ns);
-	get_user_ns(old_ns);
-
-	if (!(flags & CLONE_NEWUSER))
-		return old_ns;
-
-	new_ns = clone_user_ns(old_ns);
-
-	put_user_ns(old_ns);
-	return new_ns;
+	return 0;
 }
 
 void free_user_ns(struct kref *kref)
@@ -80,7 +65,7 @@
 	struct user_namespace *ns;
 
 	ns = container_of(kref, struct user_namespace, kref);
-	release_uids(ns);
+	free_uid(ns->creator);
 	kfree(ns);
 }
 EXPORT_SYMBOL(free_user_ns);