From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751563AbaCUUr3 (ORCPT ); Fri, 21 Mar 2014 16:47:29 -0400 Received: from terminus.zytor.com ([198.137.202.10]:40243 "EHLO mail.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750971AbaCUUrS (ORCPT ); Fri, 21 Mar 2014 16:47:18 -0400 User-Agent: K-9 Mail for Android In-Reply-To: <20140321192938.GJ3132@tassilo.jf.intel.com> References: <4055058.qLAukpngnj@al> <20140321192938.GJ3132@tassilo.jf.intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=UTF-8 Subject: Re: GPF in intel_pmu_lbr_reset() with qemu -cpu host From: "H. Peter Anvin" Date: Fri, 21 Mar 2014 13:46:04 -0700 To: Andi Kleen , Peter Wu CC: Peter Zijlstra , Ingo Molnar , linux-kernel@vger.kernel.org Message-ID: <970fd799-8d4c-4759-8a96-1291b411f307@email.android.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Not really. That is equally braindamaged. The problem is that KVM is telling the host that our is something it simply cannot be. On March 21, 2014 12:29:38 PM PDT, Andi Kleen wrote: >On Fri, Mar 21, 2014 at 06:42:40PM +0100, Peter Wu wrote: >> Hi, >> >> While trying to run QEMU with `-enable-kvm -host cpu`, I get a GPF in >> intel_pmu_lbr_reset(): > >Same problem as the RAPL problem earlier. KVM is lying to the guest >that it is a host CPU, but not implementing all MSRs the host >CPU supports. > >KVM should really return 0 on unknown MSRs not #GP > >-Andi -- Sent from my mobile phone. Please pardon brevity and lack of formatting.