Skip to main content

Browse the archive

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 
memcg: fix oops on NULL lru list
 
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
Raw File
cgroup_debug.c 
/*
 * kernel/ccontainer_debug.c - Example cgroup subsystem that
 * exposes debug info
 *
 * Copyright (C) Google Inc, 2007
 *
 * Developed by Paul Menage (menage@google.com)
 *
 */

#include <linux/cgroup.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/rcupdate.h>

#include <asm/atomic.h>

static struct cgroup_subsys_state *debug_create(struct cgroup_subsys *ss,
						   struct cgroup *cont)
{
	struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);

	if (!css)
		return ERR_PTR(-ENOMEM);

	return css;
}

static void debug_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
{
	kfree(cont->subsys[debug_subsys_id]);
}

static u64 cgroup_refcount_read(struct cgroup *cont, struct cftype *cft)
{
	return atomic_read(&cont->count);
}

static u64 taskcount_read(struct cgroup *cont, struct cftype *cft)
{
	u64 count;

	cgroup_lock();
	count = cgroup_task_count(cont);
	cgroup_unlock();
	return count;
}

static u64 current_css_set_read(struct cgroup *cont, struct cftype *cft)
{
	return (u64)(long)current->cgroups;
}

static u64 current_css_set_refcount_read(struct cgroup *cont,
					   struct cftype *cft)
{
	u64 count;

	rcu_read_lock();
	count = atomic_read(&current->cgroups->ref.refcount);
	rcu_read_unlock();
	return count;
}

static struct cftype files[] =  {
	{
		.name = "cgroup_refcount",
		.read_uint = cgroup_refcount_read,
	},
	{
		.name = "taskcount",
		.read_uint = taskcount_read,
	},

	{
		.name = "current_css_set",
		.read_uint = current_css_set_read,
	},

	{
		.name = "current_css_set_refcount",
		.read_uint = current_css_set_refcount_read,
	},
};

static int debug_populate(struct cgroup_subsys *ss, struct cgroup *cont)
{
	return cgroup_add_files(cont, ss, files, ARRAY_SIZE(files));
}

struct cgroup_subsys debug_subsys = {
	.name = "debug",
	.create = debug_create,
	.destroy = debug_destroy,
	.populate = debug_populate,
	.subsys_id = debug_subsys_id,
};
back to top