Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757710AbYJPT0s (ORCPT ); Thu, 16 Oct 2008 15:26:48 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753810AbYJPT0k (ORCPT ); Thu, 16 Oct 2008 15:26:40 -0400 Received: from g4t0016.houston.hp.com ([15.201.24.19]:28361 "EHLO g4t0016.houston.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753259AbYJPT0k (ORCPT ); Thu, 16 Oct 2008 15:26:40 -0400 Subject: Re: [PATCH] disable CPU side GART accesses From: Bob Montgomery Reply-To: bob.montgomery@hp.com To: Yinghai Lu Cc: Ingo Molnar , "linux-kernel@vger.kernel.org" , "vojtech@suse.cz" , Linus Torvalds , "chandru@in.ibm.com" , Joerg Roedel , FUJITA Tomonori , Jesse Barnes , Pavel Machek In-Reply-To: <86802c440810161043k4c4bf6e6x4f5a70c54c53ca3b@mail.gmail.com> References: <1224107317.2215.238.camel@amd.troyhebe> <20081015234842.GA10999@elte.hu> <48F68940.40409@kernel.org> <1224176445.2215.258.camel@amd.troyhebe> <86802c440810161043k4c4bf6e6x4f5a70c54c53ca3b@mail.gmail.com> Content-Type: text/plain Organization: Contractor at HP Date: Thu, 16 Oct 2008 13:26:48 -0600 Message-Id: <1224185208.2215.301.camel@amd.troyhebe> Mime-Version: 1.0 X-Mailer: Evolution 2.6.3 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1084 Lines: 25 On Thu, 2008-10-16 at 17:43 +0000, Yinghai Lu wrote: > On Thu, Oct 16, 2008 at 10:00 AM, Bob Montgomery wrote: > > > > The problem occurs when the copy operation reads from the GART aperture > > (iommu window) and wakes up the GART translation hardware. This patch > > stops that by telling the GART to ignore addresses that come from the > > CPU and to only translate addresses from the IO side. > > why kdump need to copy those area? those area is supposed to be > reserved in e820 table by BIOS or first kernel. > > YH The crashdump analysis tools do not need a copy of this area. But if a user tool associated with the kdump operation manages to touch it through /proc/vmcore or /dev/oldmem, it can crash the kdump kernel. This seemed like a simple and logical way to prevent that danger. Bob Montgomery -- 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/