From mboxrd@z Thu Jan 1 00:00:00 1970 From: Joerg Roedel Subject: Re: [PATCH]: Fix MSR_K7_EVNTSEL{0,3} for SVM Date: Mon, 28 Apr 2008 14:46:09 +0200 Message-ID: <20080428124609.GU6567@amd.com> References: <480F7E92.6030709@redhat.com> <48103855.70006@qumranet.com> <4810926E.3070900@redhat.com> <4810A538.1070104@qumranet.com> <481105FB.1080705@redhat.com> <4811887E.6040202@qumranet.com> <48122647.4080404@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: kvm-devel , Avi Kivity To: Chris Lalancette Return-path: Content-Disposition: inline In-Reply-To: <48122647.4080404@redhat.com> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: kvm-devel-bounces@lists.sourceforge.net Errors-To: kvm-devel-bounces@lists.sourceforge.net List-Id: kvm.vger.kernel.org On Fri, Apr 25, 2008 at 02:43:19PM -0400, Chris Lalancette wrote: > Unfortunately, we can't just "fake emulate" MSR_K7_PERFCTR[0-3] like we are > doing for MSR_K7_EVNTSEL[0-3]; if they are there, linux expects to be able to > put values into them. I think the correct solution here is to emulate > MSR_K7_PERFCTR[0-3] and MSR_K7_EVNTSEL[0-3] for real. I'm working on a patch to > do this now. We already discussed the emulation of the performance counter registers in the past. The conclusion is, that we loose live migration with that emulation because performance monitoring is implemented differently between AMD and Intel systems. Maybe discarding _any_ writes to the performance counter MSRs will fix the guest crash. What we should not do is injecting GPF on zero writes to the MSRs because that will break Windows XP 64bit installation. Joerg -- | AMD Saxony Limited Liability Company & Co. KG Operating | Wilschdorfer Landstr. 101, 01109 Dresden, Germany System | Register Court Dresden: HRA 4896 Research | General Partner authorized to represent: Center | AMD Saxony LLC (Wilmington, Delaware, US) | General Manager of AMD Saxony LLC: Dr. Hans-R. Deppe, Thomas McCoy ------------------------------------------------------------------------- This SF.net email is sponsored by the 2008 JavaOne(SM) Conference Don't miss this year's exciting event. There's still time to save $100. Use priority code J8TL2D2. http://ad.doubleclick.net/clk;198757673;13503038;p?http://java.sun.com/javaone