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>

5 files changed, 7 insertions, 11 deletions

diff --git a/include/linux/cred.h b/include/linux/cred.h
index 26c1ab1..3282ee43 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -60,6 +60,7 @@ do {							\
 } while (0)
 
 extern struct group_info *groups_alloc(int);
+extern struct group_info init_groups;
 extern void groups_free(struct group_info *);
 extern int set_current_groups(struct group_info *);
 extern int set_groups(struct cred *, struct group_info *);
@@ -315,6 +316,7 @@ static inline void put_cred(const struct cred *_cred)
 #define current_fsgid() 	(current_cred_xxx(fsgid))
 #define current_cap()		(current_cred_xxx(cap_effective))
 #define current_user()		(current_cred_xxx(user))
+#define current_user_ns()	(current_cred_xxx(user)->user_ns)
 #define current_security()	(current_cred_xxx(security))
 
 #define current_uid_gid(_uid, _gid)		\
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 2597858..959f552 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -57,7 +57,6 @@ extern struct nsproxy init_nsproxy;
 	.mnt_ns		= NULL,						\
 	INIT_NET_NS(net_ns)                                             \
 	INIT_IPC_NS(ipc_ns)						\
-	.user_ns	= &init_user_ns,				\
 }
 
 #define INIT_SIGHAND(sighand) {						\
diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
index c8a768e..afad7de 100644
--- a/include/linux/nsproxy.h
+++ b/include/linux/nsproxy.h
@@ -27,7 +27,6 @@ struct nsproxy {
 	struct ipc_namespace *ipc_ns;
 	struct mnt_namespace *mnt_ns;
 	struct pid_namespace *pid_ns;
-	struct user_namespace *user_ns;
 	struct net 	     *net_ns;
 };
 extern struct nsproxy init_nsproxy;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2036e9f..7f8015a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -638,6 +638,7 @@ struct user_struct {
 	/* Hash table maintenance information */
 	struct hlist_node uidhash_node;
 	uid_t uid;
+	struct user_namespace *user_ns;
 
 #ifdef CONFIG_USER_SCHED
 	struct task_group *tg;
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index b5f41d4..315bcd3 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -12,7 +12,7 @@
 struct user_namespace {
 	struct kref		kref;
 	struct hlist_head	uidhash_table[UIDHASH_SZ];
-	struct user_struct	*root_user;
+	struct user_struct	*creator;
 };
 
 extern struct user_namespace init_user_ns;
@@ -26,8 +26,7 @@ static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
 	return ns;
 }
 
-extern struct user_namespace *copy_user_ns(int flags,
-					   struct user_namespace *old_ns);
+extern int create_user_ns(struct cred *new);
 extern void free_user_ns(struct kref *kref);
 
 static inline void put_user_ns(struct user_namespace *ns)
@@ -43,13 +42,9 @@ static inline struct user_namespace *get_user_ns(struct user_namespace *ns)
 	return &init_user_ns;
 }
 
-static inline struct user_namespace *copy_user_ns(int flags,
-						  struct user_namespace *old_ns)
+static inline int create_user_ns(struct cred *new)
 {
-	if (flags & CLONE_NEWUSER)
-		return ERR_PTR(-EINVAL);
-
-	return old_ns;
+	return -EINVAL;
 }
 
 static inline void put_user_ns(struct user_namespace *ns)