From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754186AbbIILkn (ORCPT ); Wed, 9 Sep 2015 07:40:43 -0400 Received: from mail-wi0-f173.google.com ([209.85.212.173]:33635 "EHLO mail-wi0-f173.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751886AbbIILkf (ORCPT ); Wed, 9 Sep 2015 07:40:35 -0400 Subject: Re: Kernel 4.1.6 Panic due to slab corruption To: Christoph Lameter References: <55ED4DAD.7080701@kyup.com> <55ED7186.7060503@kyup.com> <55EEEB6F.2090302@kyup.com> <55EEF3B1.9080104@kyup.com> Cc: "Linux-Kernel@Vger. Kernel. Org" , Marian Marinov , SiteGround Operations From: Nikolay Borisov Message-ID: <55F01AB0.6050409@kyup.com> Date: Wed, 9 Sep 2015 14:40:32 +0300 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20100101 Thunderbird/38.1.0 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 09/08/2015 06:15 PM, Christoph Lameter wrote: > On Tue, 8 Sep 2015, Nikolay Borisov wrote: > >>> You have read https://www.kernel.org/doc/Documentation/vm/slub.txt? >> >> I've read that I'm also following the merge/nomerge thread on the DM >> mailing list. I guess my understanding is wrong in that if multiple slab >> caches are merged, then it's enough to just instrument the cache to >> which they are being merge in order to have them all instrumented? I >> guess that's not the case, so even though slab caches might be merge >> they are still somehow considered different entities in the kernel? > > Enabling debugging on bootup disables merging. > > If you switch debug options later then its possible to affect all aliases > caches. But then these option changes are only allowed to be used in such > a way as to not affect the object layout. You can switch on sanity checks > and double free checks I believe but nothing else. I tried the following: [root@kernighan vm]# ./slabinfo -da kmalloc-32 Cannot write to dma-kmalloc-32/sanity [root@kernighan vm]# ./slabinfo -dF kmalloc-32 Cannot write to dma-kmalloc-32/sanity [root@kernighan vm]# ./slabinfo -dz kmalloc-32 kmalloc-32 not empty cannot enable redzoning [root@kernighan vm]# ./slabinfo -dp kmalloc-32 kmalloc-32 not empty cannot enable poisoning [root@kernighan vm]# ./slabinfo -du kmalloc-32 kmalloc-32 not empty cannot enable tracking [root@kernighan vm]# ./slabinfo -dt ^kmalloc-32$ kmalloc-32 can only enable trace for one slab at a time I did however had success with enabling tracing but couldn't see where the output is produced - tried dmesg and the ftrace buffer but nothing turned up. But it seems it is not possible to enable any debugging whatsoever, so I will restor to doing it at boot time. In this case can you advice which options might not result in very high performance degradation - I'm thinking of sanity checking and maybe redzoning? > -- > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > Please read the FAQ at http://www.tux.org/lkml/ >