Revision f6ba488073fe8159851fe398cc3c5ee383bb4c7a authored by Vladimir Davydov on 18 August 2017, 22:16:08 UTC, committed by Linus Torvalds on 18 August 2017, 22:32:01 UTC
To avoid a possible deadlock, sysfs_slab_remove() schedules an
asynchronous work to delete sysfs entries corresponding to the kmem
cache.  To ensure the cache isn't freed before the work function is
called, it takes a reference to the cache kobject.  The reference is
supposed to be released by the work function.

However, the work function (sysfs_slab_remove_workfn()) does nothing in
case the cache sysfs entry has already been deleted, leaking the kobject
and the corresponding cache.

This may happen on a per memcg cache destruction, because sysfs entries
of a per memcg cache are deleted on memcg offline if the cache is empty
(see __kmemcg_cache_deactivate()).

The kmemleak report looks like this:

  unreferenced object 0xffff9f798a79f540 (size 32):
    comm "kworker/1:4", pid 15416, jiffies 4307432429 (age 28687.554s)
    hex dump (first 32 bytes):
      6b 6d 61 6c 6c 6f 63 2d 31 36 28 31 35 39 39 3a  kmalloc-16(1599:
      6e 65 77 72 6f 6f 74 29 00 23 6b c0 ff ff ff ff  newroot).#k.....
    backtrace:
       kmemleak_alloc+0x4a/0xa0
       __kmalloc_track_caller+0x148/0x2c0
       kvasprintf+0x66/0xd0
       kasprintf+0x49/0x70
       memcg_create_kmem_cache+0xe6/0x160
       memcg_kmem_cache_create_func+0x20/0x110
       process_one_work+0x205/0x5d0
       worker_thread+0x4e/0x3a0
       kthread+0x109/0x140
       ret_from_fork+0x2a/0x40
  unreferenced object 0xffff9f79b6136840 (size 416):
    comm "kworker/1:4", pid 15416, jiffies 4307432429 (age 28687.573s)
    hex dump (first 32 bytes):
      40 fb 80 c2 3e 33 00 00 00 00 00 40 00 00 00 00  @...>3.....@....
      00 00 00 00 00 00 00 00 10 00 00 00 10 00 00 00  ................
    backtrace:
       kmemleak_alloc+0x4a/0xa0
       kmem_cache_alloc+0x128/0x280
       create_cache+0x3b/0x1e0
       memcg_create_kmem_cache+0x118/0x160
       memcg_kmem_cache_create_func+0x20/0x110
       process_one_work+0x205/0x5d0
       worker_thread+0x4e/0x3a0
       kthread+0x109/0x140
       ret_from_fork+0x2a/0x40

Fix the leak by adding the missing call to kobject_put() to
sysfs_slab_remove_workfn().

Link: http://lkml.kernel.org/r/20170812181134.25027-1-vdavydov.dev@gmail.com
Fixes: 3b7b314053d02 ("slub: make sysfs file removal asynchronous")
Signed-off-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Reported-by: Andrei Vagin <avagin@gmail.com>
Tested-by: Andrei Vagin <avagin@gmail.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: <stable@vger.kernel.org>	[4.12.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 3010f87
Raw File
llist.c
/*
 * Lock-less NULL terminated single linked list
 *
 * The basic atomic operation of this list is cmpxchg on long.  On
 * architectures that don't have NMI-safe cmpxchg implementation, the
 * list can NOT be used in NMI handlers.  So code that uses the list in
 * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
 *
 * Copyright 2010,2011 Intel Corp.
 *   Author: Huang Ying <ying.huang@intel.com>
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License version
 * 2 as published by the Free Software Foundation;
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/llist.h>


/**
 * llist_add_batch - add several linked entries in batch
 * @new_first:	first entry in batch to be added
 * @new_last:	last entry in batch to be added
 * @head:	the head for your lock-less list
 *
 * Return whether list is empty before adding.
 */
bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last,
		     struct llist_head *head)
{
	struct llist_node *first;

	do {
		new_last->next = first = ACCESS_ONCE(head->first);
	} while (cmpxchg(&head->first, first, new_first) != first);

	return !first;
}
EXPORT_SYMBOL_GPL(llist_add_batch);

/**
 * llist_del_first - delete the first entry of lock-less list
 * @head:	the head for your lock-less list
 *
 * If list is empty, return NULL, otherwise, return the first entry
 * deleted, this is the newest added one.
 *
 * Only one llist_del_first user can be used simultaneously with
 * multiple llist_add users without lock.  Because otherwise
 * llist_del_first, llist_add, llist_add (or llist_del_all, llist_add,
 * llist_add) sequence in another user may change @head->first->next,
 * but keep @head->first.  If multiple consumers are needed, please
 * use llist_del_all or use lock between consumers.
 */
struct llist_node *llist_del_first(struct llist_head *head)
{
	struct llist_node *entry, *old_entry, *next;

	entry = smp_load_acquire(&head->first);
	for (;;) {
		if (entry == NULL)
			return NULL;
		old_entry = entry;
		next = READ_ONCE(entry->next);
		entry = cmpxchg(&head->first, old_entry, next);
		if (entry == old_entry)
			break;
	}

	return entry;
}
EXPORT_SYMBOL_GPL(llist_del_first);

/**
 * llist_reverse_order - reverse order of a llist chain
 * @head:	first item of the list to be reversed
 *
 * Reverse the order of a chain of llist entries and return the
 * new first entry.
 */
struct llist_node *llist_reverse_order(struct llist_node *head)
{
	struct llist_node *new_head = NULL;

	while (head) {
		struct llist_node *tmp = head;
		head = head->next;
		tmp->next = new_head;
		new_head = tmp;
	}

	return new_head;
}
EXPORT_SYMBOL_GPL(llist_reverse_order);
back to top