From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755862AbZETIEM (ORCPT ); Wed, 20 May 2009 04:04:12 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754070AbZETIDt (ORCPT ); Wed, 20 May 2009 04:03:49 -0400 Received: from mx2.redhat.com ([66.187.237.31]:35551 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753803AbZETIDq (ORCPT ); Wed, 20 May 2009 04:03:46 -0400 Message-ID: <4A13B8E9.9060703@redhat.com> Date: Wed, 20 May 2009 10:01:45 +0200 From: Gerd Hoffmann User-Agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1b3pre) Gecko/20090513 Fedora/3.0-2.3.beta2.fc11 Lightning/1.0pre Thunderbird/3.0b2 MIME-Version: 1.0 To: Ingo Molnar CC: Jan Beulich , Jeremy Fitzhardinge , Xen-devel , the arch/x86 maintainers , Linux Kernel Mailing List , Jesse Barnes , "Eric W. Biederman" , "H. Peter Anvin" , Thomas Gleixner , Linus Torvalds Subject: Re: [Xen-devel] Re: [GIT PULL] xen /proc/mtrr implementation References: <20090519095918.GA11790@elte.hu> <4A12A46A02000078000017E1@vpn.id2.novell.com> <20090519110837.GA10548@elte.hu> <4A12A05C.6050004@redhat.com> <20090519122623.GD14305@elte.hu> <4A12B244.8070301@redhat.com> <20090519133138.GA8410@elte.hu> <4A12B97C.9040706@redhat.com> <20090519141708.GA6008@elte.hu> <4A12C84A.5070100@redhat.com> <20090519152456.GB21271@elte.hu> In-Reply-To: <20090519152456.GB21271@elte.hu> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 05/19/09 17:24, Ingo Molnar wrote: > the Xen hypervisor can simply repeat all requests (i.e. not care at > all about the fact that a guest does these modifications on all CPUs > it sees), or realize that the modification has already been done and > skip it. Could be done, yes. It still feels wrong that wrmsr(mtrr) works slightly different on xen and on native. And it wouldn't work on existing Xen deployments as the Xen hypervisor doesn't support that today. >>>>> Yeah, the third one is to not touch MTRRs after bootup and use PAT. > That's a really old CPU, but even Coppermine has PAT support in the > CPU. You need to go back to things like P5 200 MHz CPUs to find > PAT-less CPUs. Linux shouln't say "PAT not supported by CPU." then. Also it doesn't make sense to me to handle things differently on native and xen. While it might make sense to deprecate mtrrs in favor of PAT (don't know enougth about all the different cpus in the wild to justify that) I don't think it makes sense to do that for xen only. Native should declare mtrrs obsolete as well. cheers, Gerd