From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753902AbaIDPNN (ORCPT ); Thu, 4 Sep 2014 11:13:13 -0400 Received: from smtp02.citrix.com ([66.165.176.63]:49966 "EHLO SMTP02.CITRIX.COM" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750882AbaIDPNL (ORCPT ); Thu, 4 Sep 2014 11:13:11 -0400 X-IronPort-AV: E=Sophos;i="5.04,466,1406592000"; d="scan'208";a="169127696" Message-ID: <54088183.7020608@citrix.com> Date: Thu, 4 Sep 2014 16:13:07 +0100 From: David Vrabel User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Icedove/24.5.0 MIME-Version: 1.0 To: Jan Beulich , Andrew Cooper CC: , , , Juergen Gross , Subject: Re: [Xen-devel] [PATCH 3/3] xen: eliminate scalability issues from initial mapping setup References: <1409834326-29287-1-git-send-email-jgross@suse.com> <1409834326-29287-4-git-send-email-jgross@suse.com> <54086244.7020601@citrix.com> <540862FE.7070108@citrix.com> <540893F00200007800030E4F@mail.emea.novell.com> In-Reply-To: <540893F00200007800030E4F@mail.emea.novell.com> Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit X-DLP: MIA2 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 04/09/14 15:31, Jan Beulich wrote: >>>> On 04.09.14 at 15:02, wrote: >> On 04/09/14 13:59, David Vrabel wrote: >>> On 04/09/14 13:38, Juergen Gross wrote: >>>> Direct Xen to place the initial P->M table outside of the initial >>>> mapping, as otherwise the 1G (implementation) / 2G (theoretical) >>>> restriction on the size of the initial mapping limits the amount >>>> of memory a domain can be handed initially. >>> The three level p2m limits memory to 512 GiB on x86-64 but this patch >>> doesn't seem to address this limit and thus seems a bit useless to me. >> >> Any increase of the p2m beyond 3 levels will need to come with >> substantial libxc changes first. 3 level p2ms are hard coded throughout >> all the PV build and migrate code. > > No, there no such dependency - the kernel could use 4 levels at > any time (sacrificing being able to get migrated), making sure it > only exposes the 3 levels hanging off the fourth level (or not > exposing this information at all) to external entities making this > wrong assumption. I don't think we want a kernel that may or may not be saved or migrated based on how much memory it has. Nor do we want a kernel that has even more differences between dom0 and domU. David