Revision fb59e9f1e9786635ea12e12bf6adbb132e10f979 authored by Hugh Dickins on 04 March 2008, 22:29:16 UTC, committed by Linus Torvalds on 05 March 2008, 00:35:15 UTC
While testing force_empty, during an exit_mmap, __mem_cgroup_remove_list called from mem_cgroup_uncharge_page oopsed on a NULL pointer in the lru list. I couldn't see what racing tasks on other cpus were doing, but surmise that another must have been in mem_cgroup_charge_common on the same page, between its unlock_page_cgroup and spin_lock_irqsave near done (thanks to that kzalloc which I'd almost changed to a kmalloc). Normally such a race cannot happen, the ref_cnt prevents it, the final uncharge cannot race with the initial charge. But force_empty buggers the ref_cnt, that's what it's all about; and thereafter forced pages are vulnerable to races such as this (just think of a shared page also mapped into an mm of another mem_cgroup than that just emptied). And remain vulnerable until they're freed indefinitely later. This patch just fixes the oops by moving the unlock_page_cgroups down below adding to and removing from the list (only possible given the previous patch); and while we're at it, we might as well make it an invariant that page->page_cgroup is always set while pc is on lru. But this behaviour of force_empty seems highly unsatisfactory to me: why have a ref_cnt if we always have to cope with it being violated (as in the earlier page migration patch). We may prefer force_empty to move pages to an orphan mem_cgroup (could be the root, but better not), from which other cgroups could recover them; we might need to reverse the locking again; but no time now for such concerns. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 9b3c0a0
user_namespace.c
/*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation, version 2 of the
* License.
*/
#include <linux/module.h>
#include <linux/version.h>
#include <linux/nsproxy.h>
#include <linux/user_namespace.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
*/
static struct user_namespace *clone_user_ns(struct user_namespace *old_ns)
{
struct user_namespace *ns;
struct user_struct *new_user;
int n;
ns = kmalloc(sizeof(struct user_namespace), GFP_KERNEL);
if (!ns)
return ERR_PTR(-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) {
kfree(ns);
return ERR_PTR(-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);
}
switch_uid(new_user);
return ns;
}
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;
}
void free_user_ns(struct kref *kref)
{
struct user_namespace *ns;
ns = container_of(kref, struct user_namespace, kref);
release_uids(ns);
kfree(ns);
}
Computing file changes ...
