LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Joonsoo Kim <js1304@gmail.com>
To: Mark Rutland <mark.rutland@arm.com>
Cc: LKML <linux-kernel@vger.kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Christoph Lameter <cl@linux.com>,
	David Rientjes <rientjes@google.com>,
	Jesper Dangaard Brouer <brouer@redhat.com>,
	Joonsoo Kim <iamjoonsoo.kim@lge.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Pekka Enberg <penberg@kernel.org>,
	Steve Capper <steve.capper@linaro.org>
Subject: Re: [PATCHv2] mm/slub: fix lockups on PREEMPT && !SMP kernels
Date: Wed, 18 Mar 2015 14:59:25 +0900	[thread overview]
Message-ID: <CAAmzW4MD_bj1pec-HeYEZa8SZsnp2u24mweCHn4qfLB9AwpXxg@mail.gmail.com> (raw)
In-Reply-To: <1426594533-18221-1-git-send-email-mark.rutland@arm.com>

2015-03-17 21:15 GMT+09:00 Mark Rutland <mark.rutland@arm.com>:
> Commit 9aabf810a67cd97e ("mm/slub: optimize alloc/free fastpath by
> removing preemption on/off") introduced an occasional hang for kernels
> built with CONFIG_PREEMPT && !CONFIG_SMP.
>
> The problem is the following loop the patch introduced to
> slab_alloc_node and slab_free:
>
> do {
>         tid = this_cpu_read(s->cpu_slab->tid);
>         c = raw_cpu_ptr(s->cpu_slab);
> } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid));
>
> GCC 4.9 has been observed to hoist the load of c and c->tid above the
> loop for !SMP kernels (as in this case raw_cpu_ptr(x) is compile-time
> constant and does not force a reload). On arm64 the generated assembly
> looks like:
>
> ffffffc00016d3c4:       f9400404        ldr     x4, [x0,#8]
> ffffffc00016d3c8:       f9400401        ldr     x1, [x0,#8]
> ffffffc00016d3cc:       eb04003f        cmp     x1, x4
> ffffffc00016d3d0:       54ffffc1        b.ne    ffffffc00016d3c8 <slab_alloc_node.constprop.82+0x30>
>
> If the thread is preempted between the load of c->tid (into x1) and tid
> (into x4), and an allocation or free occurs in another thread (bumping
> the cpu_slab's tid), the thread will be stuck in the loop until
> s->cpu_slab->tid wraps, which may be forever in the absence of
> allocations/frees on the same CPU.
>
> This patch changes the loop condition to access c->tid with READ_ONCE.
> This ensures that the value is reloaded even when the compiler would
> otherwise assume it could cache the value, and also ensures that the
> load will not be torn.
>
> Signed-off-by: Mark Rutland <mark.rutland@arm.com>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Christoph Lameter <cl@linux.com>
> Cc: David Rientjes <rientjes@google.com>
> Cc: Jesper Dangaard Brouer <brouer@redhat.com>
> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
> Cc: Linus Torvalds <torvalds@linux-foundation.org>
> Cc: Pekka Enberg <penberg@kernel.org>
> Cc: Steve Capper <steve.capper@linaro.org>
> ---
>  mm/slub.c | 6 ++++--
>  1 file changed, 4 insertions(+), 2 deletions(-)
>
> Since v1 [1]:
> * Do not erroneously remove the loop
>
> [1] lkml.kernel.org/r/1426261632-8911-1-git-send-email-mark.rutland@arm.com
>
> diff --git a/mm/slub.c b/mm/slub.c
> index 6832c4e..82c4737 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -2449,7 +2449,8 @@ redo:
>         do {
>                 tid = this_cpu_read(s->cpu_slab->tid);
>                 c = raw_cpu_ptr(s->cpu_slab);
> -       } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid));
> +       } while (IS_ENABLED(CONFIG_PREEMPT) &&
> +                unlikely(tid != READ_ONCE(c->tid)));
>
>         /*
>          * Irqless object alloc/free algorithm used here depends on sequence
> @@ -2718,7 +2719,8 @@ redo:
>         do {
>                 tid = this_cpu_read(s->cpu_slab->tid);
>                 c = raw_cpu_ptr(s->cpu_slab);
> -       } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid));
> +       } while (IS_ENABLED(CONFIG_PREEMPT) &&
> +                unlikely(tid != READ_ONCE(c->tid)));
>
>         /* Same with comment on barrier() in slab_alloc_node() */
>         barrier();
> --

Hello,

Could you show me generated code again?

What we need to check is redoing whole things in the loop.
Previous attached code seems to me that it already did
refetching c->tid in the loop and this patch looks only handle
refetching c->tid.
READ_ONCE(c->tid) will trigger redoing 'tid = this_cpu_read(s->cpu_slab->tid)'?

Thanks.

  parent reply	other threads:[~2015-03-18  5:59 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-03-13 15:47 [PATCH] " Mark Rutland
2015-03-13 16:29 ` Christoph Lameter
2015-03-13 18:16   ` Mark Rutland
2015-03-13 18:27     ` Christoph Lameter
2015-03-16 12:45   ` [PATCHv2] " Mark Rutland
2015-03-17  1:09 ` [PATCH] " Joonsoo Kim
2015-03-17 12:00   ` Mark Rutland
2015-03-17 12:15     ` [PATCHv2] " Mark Rutland
2015-03-17 18:57       ` Christoph Lameter
2015-03-18  5:59       ` Joonsoo Kim [this message]
2015-03-18 15:21         ` Mark Rutland
2015-03-19 12:13           ` Joonsoo Kim
2015-03-19 16:16             ` Christoph Lameter
2015-03-24 14:17       ` Ville Syrjälä

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=CAAmzW4MD_bj1pec-HeYEZa8SZsnp2u24mweCHn4qfLB9AwpXxg@mail.gmail.com \
    --to=js1304@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=brouer@redhat.com \
    --cc=catalin.marinas@arm.com \
    --cc=cl@linux.com \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=penberg@kernel.org \
    --cc=rientjes@google.com \
    --cc=steve.capper@linaro.org \
    --cc=torvalds@linux-foundation.org \
    --subject='Re: [PATCHv2] mm/slub: fix lockups on PREEMPT && '\!'SMP kernels' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).