From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755415Ab2F1Phe (ORCPT ); Thu, 28 Jun 2012 11:37:34 -0400 Received: from nat28.tlf.novell.com ([130.57.49.28]:45644 "EHLO nat28.tlf.novell.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752289Ab2F1Phd convert rfc822-to-8bit (ORCPT ); Thu, 28 Jun 2012 11:37:33 -0400 Message-Id: <4FEC9686020000780008C9BB@nat28.tlf.novell.com> X-Mailer: Novell GroupWise Internet Agent 12.0.0 Date: Thu, 28 Jun 2012 16:38:14 +0100 From: "Jan Beulich" To: "Konrad Rzeszutek Wilk" , "H. Peter Anvin" Cc: , , "Suresh B Siddha" , , , , , , , "Jason Garrett-Glaser" Subject: Re: [Xen-devel] [PATCH] x86 fixes for 3.3 impacting distros (v1). References: <1328888091-9692-1-git-send-email-konrad.wilk@oracle.com> <20120510153457.GB6389@phenom.dumpdata.com> <20120627231755.GA1021@gmail.com> <20120628142836.GE8956@phenom.dumpdata.com> <4FEC6D44.8080807@zytor.com> In-Reply-To: <4FEC6D44.8080807@zytor.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 8BIT Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org >>> On 28.06.12 at 16:42, "H. Peter Anvin" wrote: > On 06/28/2012 07:28 AM, Konrad Rzeszutek Wilk wrote: >> I also chatted with the core Xen hypervisor folks about adding in the > context switch code >> to alter the PAT layout - but they were not keen a about it - and I am not > sure how much >> CPU cycles one loses by doing a wrmsr to the PAT register on every guest > context switch >> (worst case when on has a pvops kernel and a old-style one - where the WC bit > would differ)? >> > > And you're comparing that to a bunch of new pvops calls? The discussion > shouldn't even have started until you had ruled out this solution and > had data to show it. That's definitely not an option: Xen itself may be (and is, under certain circumstances at least) using WC page table entries, so we can't allow on-the-fly changes to the meaning of the various indexes. Jan From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Jan Beulich" Subject: Re: [Xen-devel] [PATCH] x86 fixes for 3.3 impacting distros (v1). Date: Thu, 28 Jun 2012 16:38:14 +0100 Message-ID: <4FEC9686020000780008C9BB@nat28.tlf.novell.com> References: <1328888091-9692-1-git-send-email-konrad.wilk@oracle.com> <20120510153457.GB6389@phenom.dumpdata.com> <20120627231755.GA1021@gmail.com> <20120628142836.GE8956@phenom.dumpdata.com> <4FEC6D44.8080807@zytor.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 8BIT Return-path: In-Reply-To: <4FEC6D44.8080807@zytor.com> Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org To: Konrad Rzeszutek Wilk , "H. Peter Anvin" Cc: cyclonusj@gmail.com, rostedt@goodmis.org, Suresh B Siddha , marmarek@invisiblethingslab.com, x86@kernel.org, tglx@linutronix.de, xen-devel@lists.xensource.com, mingo@redhat.com, linux-kernel@vger.kernel.org, Jason Garrett-Glaser List-Id: xen-devel@lists.xenproject.org >>> On 28.06.12 at 16:42, "H. Peter Anvin" wrote: > On 06/28/2012 07:28 AM, Konrad Rzeszutek Wilk wrote: >> I also chatted with the core Xen hypervisor folks about adding in the > context switch code >> to alter the PAT layout - but they were not keen a about it - and I am not > sure how much >> CPU cycles one loses by doing a wrmsr to the PAT register on every guest > context switch >> (worst case when on has a pvops kernel and a old-style one - where the WC bit > would differ)? >> > > And you're comparing that to a bunch of new pvops calls? The discussion > shouldn't even have started until you had ruled out this solution and > had data to show it. That's definitely not an option: Xen itself may be (and is, under certain circumstances at least) using WC page table entries, so we can't allow on-the-fly changes to the meaning of the various indexes. Jan