From mboxrd@z Thu Jan 1 00:00:00 1970 From: Joerg Roedel Subject: Re: Fwd: [PATCH 0/18] Nested Virtualization: Overview Date: Sat, 17 Apr 2010 13:43:20 +0200 Message-ID: <20100417114320.GC23260@8bytes.org> References: <201004151520.31527.Christoph.Egger@amd.com> <20100416090708.GA4224@ub-qhe2> <201004161132.25376.Christoph.Egger@amd.com> <20100416102711.GA31304@whitby.uk.xensource.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20100416102711.GA31304@whitby.uk.xensource.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Tim Deegan Cc: Christoph Egger , "xen-devel@lists.xensource.com" , Qing He List-Id: xen-devel@lists.xenproject.org On Fri, Apr 16, 2010 at 11:27:11AM +0100, Tim Deegan wrote: > At 10:32 +0100 on 16 Apr (1271413945), Christoph Egger wrote: > Your PDFs suggest that even on Intel CPUs, the nested hypervisor should > always see SVM, not VMX. You shouldn't be surprised or offended if that > isn't popular with Intel. :) Well, it would make sense for Intel too virtualize SVM because it doesn't has the performance issues with lots and lots of emulated vmread/vmwrite instructions that cause vmexits in the nested case. The bigger problem with SVM on VMX is that it could never be complete because afaik VMX has fewer intercepts than SVM. Joerg