From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756056AbYHUDmd (ORCPT ); Wed, 20 Aug 2008 23:42:33 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753651AbYHUDmY (ORCPT ); Wed, 20 Aug 2008 23:42:24 -0400 Received: from one.firstfloor.org ([213.235.205.2]:37627 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753279AbYHUDmX (ORCPT ); Wed, 20 Aug 2008 23:42:23 -0400 To: Venki Pallipadi Cc: Dave Airlie , Rene Herman , Ingo Molnar , "Li, Shaohua" , Yinghai Lu , Andreas Herrmann , Arjan van de Ven , Linux Kernel , "Siddha, Suresh B" , Thomas Gleixner , "H. Peter Anvin" , Dave Jones Subject: Re: AGP and PAT (induced?) problem (on AMD family 6) From: Andi Kleen References: <48AA9C3B.5030309@keyaccess.nl> <20080819102633.GE6722@elte.hu> <48AAD680.7020508@keyaccess.nl> <20080819190757.GA17470@linux-os.sc.intel.com> <20080820100440.GE28492@elte.hu> <48ABF6DC.8070305@keyaccess.nl> <48AC29CA.1060203@keyaccess.nl> <20080820194127.GA10887@linux-os.sc.intel.com> <48AC8F69.4050201@keyaccess.nl> <21d7e9970808201446k3c1a6bc1naf04568a8ad06ed4@mail.gmail.com> <20080820221630.GA3598@linux-os.sc.intel.com> Date: Thu, 21 Aug 2008 05:42:18 +0200 In-Reply-To: <20080820221630.GA3598@linux-os.sc.intel.com> (Venki Pallipadi's message of "Wed, 20 Aug 2008 15:16:30 -0700") Message-ID: <87wsibxcdh.fsf@basil.nowhere.org> User-Agent: Gnus/5.1008 (Gnus v5.10.8) Emacs/21.3 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Venki Pallipadi writes: > > We are also looking at changing the reserve_memtype in PAT, not to use linked > list for RAM backed pages and track them in page struct. Back when I hacked on this I explicitely chose to not do this because it would make it impossible to put any normal anonymous pages into the PAT list. While that's not done today there's no reason it couldn't be done in the future. Also it doesn't fix the scalability of the data structure anyways (a list is a list), just saves some memory. -Andi