linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
To: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Christoph Lameter <cl@linux.com>,
	Pekka Enberg <penberg@kernel.org>,
	David Rientjes <rientjes@google.com>,
	Jesper Dangaard Brouer <brouer@redhat.com>,
	linux-mm@kvack.org
Subject: Re: [PATCH v2 06/11] mm/slab: don't keep free slabs if free_objects exceeds free_limit
Date: Tue, 26 Jul 2016 16:18:49 +0900	[thread overview]
Message-ID: <20160726071848.GA15721@js1304-P5Q-DELUXE> (raw)
In-Reply-To: <2b417127-20a6-ef00-f541-57337a97c9ec@I-love.SAKURA.ne.jp>

On Fri, Jul 22, 2016 at 08:51:02PM +0900, Tetsuo Handa wrote:
> Joonsoo Kim wrote:
> > @@ -3313,6 +3310,14 @@ static void free_block(struct kmem_cache *cachep, void **objpp,
> >  			list_add_tail(&page->lru, &n->slabs_partial);
> >  		}
> >  	}
> > +
> > +	while (n->free_objects > n->free_limit && !list_empty(&n->slabs_free)) {
> > +		n->free_objects -= cachep->num;
> > +
> > +		page = list_last_entry(&n->slabs_free, struct page, lru);
> > +		list_del(&page->lru);
> > +		list_add(&page->lru, list);
> > +	}
> >  }
> >  
> >  static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac)
> > 
> 
> I noticed that kmemcheck complains that n->free_limit is not initialized.
> 
> [    0.000000] Console: colour VGA+ 80x25
> [    0.000000] console [tty0] enabled
> [    0.000000] console [ttyS0] enabled
> [    0.000000] WARNING: kmemcheck: Caught 32-bit read from uninitialized memory (ffff88013ec085b8)
> [    0.000000] a085c03e0188ffffa085c03e0188ffff06000000000000000000000000000000
> [    0.000000]  i i i i i i i i i i i i i i i i i i i i i i i i u u u u i i i i
> [    0.000000]                                                  ^
> [    0.000000] RIP: 0010:[<ffffffff8113073e>]  [<ffffffff8113073e>] free_block+0x14e/0x1d0
> [    0.000000] RSP: 0000:ffffffff81803e58  EFLAGS: 00010046
> [    0.000000] RAX: 0000000000000006 RBX: ffff88013ec0c000 RCX: 0000000000000000
> [    0.000000] RDX: 0000000000000000 RSI: ffff88013f7c5418 RDI: ffff88013ec0c000
> [    0.000000] RBP: ffffffff81803e88 R08: ffffffff81803ea0 R09: ffff88013ec08580
> [    0.000000] R10: ffff88013f7c55d0 R11: 00000000000005cd R12: ffff88013f7c5408
> [    0.000000] R13: ffffffff81803ea0 R14: 0000000002000000 R15: 000000000000001b
> [    0.000000] FS:  0000000000000000(0000) GS:ffffffff8182c000(0000) knlGS:0000000000000000
> [    0.000000] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [    0.000000] CR2: ffff88013e800000 CR3: 000000000180c000 CR4: 00000000000406b0
> [    0.000000]  [<ffffffff81131a84>] __do_tune_cpucache+0x84/0x310
> [    0.000000]  [<ffffffff81131d35>] do_tune_cpucache+0x25/0x90
> [    0.000000]  [<ffffffff81131df0>] enable_cpucache+0x50/0xc0
> [    0.000000]  [<ffffffff818b5c70>] kmem_cache_init_late+0x3f/0x68
> [    0.000000]  [<ffffffff81895eda>] start_kernel+0x2f2/0x48d
> [    0.000000]  [<ffffffff8189553a>] x86_64_start_reservations+0x2f/0x31
> [    0.000000]  [<ffffffff81895632>] x86_64_start_kernel+0xf6/0x111
> [    0.000000]  [<ffffffffffffffff>] 0xffffffffffffffff
> [    0.000000] tsc: Unable to calibrate against PIT
> [    0.000000] tsc: using PMTIMER reference calibration
> [    0.000000] tsc: Detected 2793.551 MHz processor
> 
> Setting 0 at kmem_cache_node_init() fixes the problem, but what the initial
> value should be? (Since list_empty(&n->slabs_free) == true, uninitialized
> read of n->free_limit does not cause problems except kmemcheck.)

Setting 0 would be okay because it would mean that we don't want to cache any
object on kmem_cache_node. We will re-initialize it soon so it doesn't
cause any problem.

Thanks.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2016-07-26  7:14 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-04-12  4:50 [PATCH v2 00/11] mm/slab: reduce lock contention in alloc path js1304
2016-04-12  4:50 ` [PATCH v2 01/11] mm/slab: fix the theoretical race by holding proper lock js1304
2016-04-12 16:38   ` Christoph Lameter
2016-04-14  1:56     ` Joonsoo Kim
2016-04-12  4:50 ` [PATCH v2 02/11] mm/slab: remove BAD_ALIEN_MAGIC again js1304
2016-04-12 16:41   ` Christoph Lameter
2016-04-12  4:50 ` [PATCH v2 03/11] mm/slab: drain the free slab as much as possible js1304
2016-04-12  4:50 ` [PATCH v2 04/11] mm/slab: factor out kmem_cache_node initialization code js1304
2016-04-12 16:53   ` Christoph Lameter
2016-04-26  0:47   ` Joonsoo Kim
2016-04-12  4:51 ` [PATCH v2 05/11] mm/slab: clean-up kmem_cache_node setup js1304
2016-04-12 16:55   ` Christoph Lameter
2016-04-12  4:51 ` [PATCH v2 06/11] mm/slab: don't keep free slabs if free_objects exceeds free_limit js1304
2016-07-22 11:51   ` Tetsuo Handa
2016-07-26  7:18     ` Joonsoo Kim [this message]
2016-04-12  4:51 ` [PATCH v2 07/11] mm/slab: racy access/modify the slab color js1304
2016-04-12  4:51 ` [PATCH v2 08/11] mm/slab: make cache_grow() handle the page allocated on arbitrary node js1304
2016-04-12  4:51 ` [PATCH v2 09/11] mm/slab: separate cache_grow() to two parts js1304
2016-04-12  4:51 ` [PATCH v2 10/11] mm/slab: refill cpu cache through a new slab without holding a node lock js1304
2016-04-12  4:51 ` [PATCH v2 11/11] mm/slab: lockless decision to grow cache js1304
2016-04-12  7:24   ` Jesper Dangaard Brouer
2016-04-12  8:16     ` Joonsoo Kim

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20160726071848.GA15721@js1304-P5Q-DELUXE \
    --to=iamjoonsoo.kim@lge.com \
    --cc=akpm@linux-foundation.org \
    --cc=brouer@redhat.com \
    --cc=cl@linux.com \
    --cc=linux-mm@kvack.org \
    --cc=penberg@kernel.org \
    --cc=penguin-kernel@I-love.SAKURA.ne.jp \
    --cc=rientjes@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox