Messages in this thread | | | From | "Li,Rongqing" <> | Subject | 答复: [PATCH][v2] kvm: x86: emulate APERF/M PERF registers | Date | Thu, 30 Apr 2020 09:50:08 +0000 |
| |
> -----邮件原件----- > 发件人: Xiaoyao Li [mailto:xiaoyao.li@intel.com] > 发送时间: 2020年4月30日 14:49 > 收件人: Li,Rongqing <lirongqing@baidu.com>; linux-kernel@vger.kernel.org; > kvm@vger.kernel.org; x86@kernel.org; hpa@zytor.com; bp@alien8.de; > mingo@redhat.com; tglx@linutronix.de; joro@8bytes.org; > jmattson@google.com; wanpengli@tencent.com; vkuznets@redhat.com; > sean.j.christopherson@intel.com; pbonzini@redhat.com > 主题: Re: [PATCH][v2] kvm: x86: emulate APERF/MPERF registers > > On 4/29/2020 1:46 PM, Li RongQing wrote: > > Guest kernel reports a fixed cpu frequency in /proc/cpuinfo, this is > > confused to user when turbo is enable, and aperf/mperf can be used to > > show current cpu frequency after 7d5905dc14a > > "(x86 / CPU: Always show current CPU frequency in /proc/cpuinfo)" > > so we should emulate aperf mperf to achieve it > > > > the period of aperf/mperf in guest mode are accumulated as emulated > > value, and add per-VM knod to enable emulate mperfaperf > > > > diff v1: > > 1. support AMD > > 2. support per-vm capability to enable > > > [...] > > diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index > > 851e9cc79930..1d157a8dba46 100644 > > --- a/arch/x86/kvm/svm.c > > +++ b/arch/x86/kvm/svm.c > > @@ -4310,6 +4310,12 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, > struct msr_data *msr_info) > > case MSR_F10H_DECFG: > > msr_info->data = svm->msr_decfg; > > break; > > + case MSR_IA32_MPERF: > > + msr_info->data = vcpu->arch.v_mperf; > > + break; > > + case MSR_IA32_APERF: > > + msr_info->data = vcpu->arch.v_aperf; > > + break; > > default: > > return kvm_get_msr_common(vcpu, msr_info); > > } > > diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index > > 91749f1254e8..b05e276e262b 100644 > > --- a/arch/x86/kvm/vmx/vmx.c > > +++ b/arch/x86/kvm/vmx/vmx.c > > @@ -1914,6 +1914,12 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, > struct msr_data *msr_info) > > !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) > > return 1; > > goto find_shared_msr; > > + case MSR_IA32_MPERF: > > + msr_info->data = vcpu->arch.v_mperf; > > + break; > > + case MSR_IA32_APERF: > > + msr_info->data = vcpu->arch.v_aperf; > > + break; > > They are same for both vmx and svm, you can put them in > kvm_get_msr_common() >
Ok
> BTW, are those two MSR always readable regardless of guest's CPUID?
It should be, not sure if there is abnormal
thanks -LiRongQing
> > default: > > find_shared_msr: > > msr = find_msr_entry(vmx, msr_info->index); >
| |