Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756415AbXFKP6a (ORCPT ); Mon, 11 Jun 2007 11:58:30 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753979AbXFKP6P (ORCPT ); Mon, 11 Jun 2007 11:58:15 -0400 Received: from nz-out-0506.google.com ([64.233.162.239]:41360 "EHLO nz-out-0506.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753857AbXFKP6N (ORCPT ); Mon, 11 Jun 2007 11:58:13 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:to:subject:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=Xttslqe2JSdCaqDnG3hYHr77duhKPiU5ylt4IsEbwXuIMExP6WO+uqXhYXmSKUN6YlCwBCekOJJpmDG4L7Y9gbreHmk79ICbGISxdq/cpQ+4ih9Q4GgOJl4Kekm5Nhg+32BKIvGuZyAAde+sgGbFYTg6ZOn+AW59qC0udHtHgfU= Message-ID: <1defaf580706110858r16b1b88bg2346734379574b52@mail.gmail.com> Date: Mon, 11 Jun 2007 17:58:12 +0200 From: "=?ISO-8859-1?Q?H=E5vard_Skinnemoen?=" To: "Paul Mundt" , "Haavard Skinnemoen" , "Christoph Lameter" , "Linux Kernel" Subject: Re: kernel BUG at mm/slub.c:3689! In-Reply-To: <20070611153804.GA26209@linux-sh.org> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <20070611161926.2a9f8efd@dhcp-255-175.norway.atmel.com> <20070611153804.GA26209@linux-sh.org> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 939 Lines: 21 On 6/11/07, Paul Mundt wrote: > On Mon, Jun 11, 2007 at 04:19:26PM +0200, Haavard Skinnemoen wrote: > > I think the combination that triggered this bug was: > > * CONFIG_SLUB_DEBUG=y > > * ARCH_KMALLOC_MINALIGN=32 > > * slub_debug not set at the command line > > > ARCH_KMALLOC_MINALIGN and ARCH_SLAB_MINALIGN are both in bytes > (ARCH_KMALLOC_MINALIGN used to be defined as BYTES_PER_WORD) if I recall > correctly, are you sure this is what you want? Yeah, I actually defined it to L1_CACHE_BYTES. The idea is to avoid cacheline sharing between different kmalloc() allocations, which may mess up DMA transfers. So 32 bytes alignment is indeed what I want. Haavard - 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/