linux-kernel - Re: [GIT PULL] SLAB changes for v2.6.39-rc1

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20110324142146.GA11682@elte.hu>
Date:	Thu, 24 Mar 2011 15:21:46 +0100
From:	Ingo Molnar <mingo@...e.hu>
To:	Pekka Enberg <penberg@...nel.org>
Cc:	torvalds@...ux-foundation.org, cl@...ux-foundation.org,
	akpm@...ux-foundation.org, tj@...nel.org, npiggin@...nel.dk,
	rientjes@...gle.com, linux-kernel@...r.kernel.org,
	linux-mm@...ck.org
Subject: Re: [GIT PULL] SLAB changes for v2.6.39-rc1


hi Pekka,

* Pekka Enberg <penberg@...nel.org> wrote:

> Hi Linus,
> 
> Here's SLAB updates for 2.6.39-rc1. The interesting bits are SLUB
> lockless fastpath patches from Christoph which improve performance
> and updates to support bigger 'struct rcu_head' from Lai. I pulled
> the per-CPU tree to slub/lockless which is why some already merged
> patches show up in the pull request.
> 
>                         Pekka
> 
> The following changes since commit a952baa034ae7c2e4a66932005cbc7ebbccfe28d:
>   Linus Torvalds (1):
>         Merge branch 'for-linus' of git://git.kernel.org/.../dtor/input
> 
> are available in the git repository at:
> 
>   ssh://master.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6.git for-linus
> 
> Christoph Lameter (5):
>       mm: Remove support for kmem_cache_name()
>       slub: min_partial needs to be in first cacheline
>       slub: Get rid of slab_free_hook_irq()
>       Lockless (and preemptless) fastpaths for slub
>       slub: Dont define useless label in the !CONFIG_CMPXCHG_LOCAL case
> 
> Eric Dumazet (1):
>       slub: fix kmemcheck calls to match ksize() hints
> 
> Lai Jiangshan (3):
>       slub: automatically reserve bytes at the end of slab
>       slub,rcu: don't assume the size of struct rcu_head
>       slab,rcu: don't assume the size of struct rcu_head
> 
> Mariusz Kozlowski (1):
>       slub: fix ksize() build error
> 
> Pekka Enberg (6):
>       Revert "slab: Fix missing DEBUG_SLAB last user"
>       Merge branch 'for-2.6.39' of git://git.kernel.org/.../tj/percpu into slub/lockless
>       Merge branch 'slab/rcu' into slab/next
>       Merge branch 'slab/urgent' into slab/next
>       Merge branch 'slab/next' into for-linus
>       Merge branch 'slub/lockless' into for-linus

FYI, some sort of boot crash has snuck upstream in the last 24 hours:

 BUG: unable to handle kernel paging request at ffff87ffc147e020                               
 IP: [<ffffffff811aa762>] this_cpu_cmpxchg16b_emu+0x2/0x1c           

     [<ffffffff810d9cbc>] ? kmem_cache_alloc+0x4c/0x110                                           
     [<ffffffff8151cf06>] kmem_cache_init+0xeb/0x2b0                                              
     [<ffffffff81504a06>] start_kernel+0x1de/0x49b                                                
     [<ffffffff8150432b>] x86_64_start_reservations+0x132/0x136                                   
     [<ffffffff81504140>] ? early_idt_handlers+0x140/0x140         

And the SLAB changes are one of the suspects. It triggers in about 5% of all 
randconfigs. I'm bisecting it currently.

Config attached.

	Ingo

View attachment "config" of type "text/plain" (58825 bytes)