From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753951AbcEaNQi (ORCPT ); Tue, 31 May 2016 09:16:38 -0400 Received: from mx1.redhat.com ([209.132.183.28]:38728 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751505AbcEaNQf (ORCPT ); Tue, 31 May 2016 09:16:35 -0400 Date: Tue, 31 May 2016 15:16:31 +0200 From: Radim =?utf-8?B?S3LEjW3DocWZ?= To: kmeaw@yandex-team.ru Cc: Paolo Bonzini , "Gabriel L. Somlo" , "linux-kernel@vger.kernel.org" , "kvm@vger.kernel.org" , "gleb@kernel.org" Subject: Re: [PATCH v3] KVM: Handle MSR_IA32_PERF_CTL Message-ID: <20160531131630.GB30721@potion> References: <770161464247923@webcorp02g.yandex-team.ru> <20160526203931.GB25334@potion> <20160526204439.GF2186@HEDWIG.INI.CMU.EDU> <920591464331762@webcorp02f.yandex-team.ru> <20160527152224.GA11721@potion> <20160527153850.GC11721@potion> <1189746463.18391609.1464681232913.JavaMail.zimbra@redhat.com> <1317601464689200@webcorp01d.yandex-team.ru> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <1317601464689200@webcorp01d.yandex-team.ru> X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.26]); Tue, 31 May 2016 13:16:34 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 2016-05-31 13:06+0300, kmeaw@yandex-team.ru: > 31.05.2016, 11:21, "Paolo Bonzini" : > >>  2016-05-27 17:22+0200, Radim Krčmář: > >>  > (I wonder why MacOS X doesn't read IA32_PERF_STATUS, though.) > >> > >>  Oh, it maybe does ... we already emulate status and return 0x1000 in its > >>  bottom 16 bits. I have no idea what is that supposed to mean, but I > >>  think we should return 0x1000 in IA32_PERF_CTL then. > > > > It's 1000, not 0x1000 (instead, on real hardware the value is typically a > > multiple of 256). It was added for Darwin too. > > > > Returning different values is okay, because they are different on real > > hardware too: > > > > (sudo dd if=/dev/cpu/0/msr skip=$((0x198)) iflag=skip_bytes bs=8 count=1; > >  sudo dd if=/dev/cpu/0/msr skip=$((0x199)) iflag=skip_bytes bs=8 count=1) | od -tx8 > > 0000000 00001f3900001100 0000000000001300 > >         ^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^ > >         PERF_STATUS PERF_CTL > > > > And perhaps if we returned non-zero values for PERF_CTL Darwin would try to > > write to it. So returning zero is fine, I think. There is no correct answer... > > Thank you. I have removed MSR_IA32_PERF_CTL from emulated_msrs[]. Returning > 1000 (0x3e8) for PERF_STATUS and 0 for PERF_CTL works fine with MacOS X. > > Just in case here are MSRs from i5-4460: > PERF_STATUS: 0000202800002100 > PERF_CTL: 0000000000002200 > > Chaning KVM's PERL_CTL from 0 to 0x2200 does not seem to interfere with MacOS X > boot process. It does not attempt to wrmsr into this register. > > Here is a refined version of the patch: > -- > > From: Dmitry Bilunov > > Intel CPUs having Turbo Boost feature implement an MSR to provide a > control interface via rdmsr/wrmsr instructions. One could detect the > presence of this feature by issuing one of these instructions and > handling the #GP exception which is generated in case the referenced MSR > is not implemented by the CPU. > > KVM's vCPU model behaves exactly as a real CPU in this case by injecting > a fault when MSR_IA32_PERF_CTL is called (which KVM does not support). > However, some operating systems use this register during an early boot > stage in which their kernel is not capable of handling #GP correctly, > causing #DP and finally a triple fault effectively resetting the vCPU. > > This patch implements a dummy handler for MSR_IA32_PERF_CTL to avoid the > crashes. > --- The code looks good. Please resend with your signed-off-by and preserved writespace (tabs were converted to spaces), thanks. > arch/x86/kvm/x86.c | 1 + > 1 file changed, 1 insertion(+) > > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > index c805cf4..d0a5b4b 100644 > --- a/arch/x86/kvm/x86.c > +++ b/arch/x86/kvm/x86.c > @@ -2314,6 +2314,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) > case MSR_AMD64_NB_CFG: > case MSR_FAM10H_MMIO_CONF_BASE: > case MSR_AMD64_BU_CFG2: > + case MSR_IA32_PERF_CTL: > msr_info->data = 0; > break; > case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: > -- > 2.8.2