userns: Avoid recursion in put_user_ns

When freeing a deeply nested user namespace free_user_ns calls
put_user_ns on it's parent which may in turn call free_user_ns again.
When -fno-optimize-sibling-calls is passed to gcc one stack frame per
user namespace is left on the stack, potentially overflowing the
kernel stack.  CONFIG_FRAME_POINTER forces -fno-optimize-sibling-calls
so we can't count on gcc to optimize this code.

Remove struct kref and use a plain atomic_t.  Making the code more
flexible and easier to comprehend.  Make the loop in free_user_ns
explict to guarantee that the stack does not overflow with
CONFIG_FRAME_POINTER enabled.

I have tested this fix with a simple program that uses unshare to
create a deeply nested user namespace structure and then calls exit.
With 1000 nesteuser namespaces before this change running my test
program causes the kernel to die a horrible death.  With 10,000,000
nested user namespaces after this change my test program runs to
completion and causes no harm.

Acked-by: Serge Hallyn <serge.hallyn@canonical.com>
Pointed-out-by: Vasily Kulikov <segoon@openwall.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

kernel/user.c

@@ -47,9 +47,7 @@ struct user_namespace init_user_ns = {
 			.count = 4294967295U,
 		},
 	},
-	.kref = {
-		.refcount	= ATOMIC_INIT(3),
-	},
+	.count = ATOMIC_INIT(3),
 	.owner = GLOBAL_ROOT_UID,
 	.group = GLOBAL_ROOT_GID,
 	.proc_inum = PROC_USER_INIT_INO,