Re: [PATCH] [RFC] kvm: x86: emulate APERF/MPERF registers

[Peter Zijlstra]

On Fri, Apr 24, 2020 at 01:08:55PM +0800, 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
> 
> Signed-off-by: Li RongQing <lirongqing@xxxxxxxxx>
> ---
>  arch/x86/include/asm/kvm_host.h |  5 +++++
>  arch/x86/kvm/cpuid.c            |  5 ++++-
>  arch/x86/kvm/vmx/vmx.c          | 20 ++++++++++++++++++++
>  3 files changed, 29 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 42a2d0d3984a..526bd13a3d3d 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -820,6 +820,11 @@ struct kvm_vcpu_arch {
>  
>  	/* AMD MSRC001_0015 Hardware Configuration */
>  	u64 msr_hwcr;
> +
> +	u64 host_mperf;
> +	u64 host_aperf;
> +	u64 v_mperf;
> +	u64 v_aperf;
>  };
>  
>  struct kvm_lpage_info {
> diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
> index 901cd1fdecd9..00e4993cb338 100644
> --- a/arch/x86/kvm/cpuid.c
> +++ b/arch/x86/kvm/cpuid.c
> @@ -558,7 +558,10 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
>  	case 6: /* Thermal management */
>  		entry->eax = 0x4; /* allow ARAT */
>  		entry->ebx = 0;
> -		entry->ecx = 0;
> +		if (boot_cpu_has(X86_FEATURE_APERFMPERF))
> +			entry->ecx = 0x1;
> +		else
> +			entry->ecx = 0x0;
>  		entry->edx = 0;
>  		break;
>  	/* function 7 has additional index. */

AFAICT this is generic x86 code, that is, this will tell an AMD SVM
guest it has APERFMPERF on.

> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index 91749f1254e8..f20216fc0b57 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -1064,6 +1064,11 @@ static inline void pt_save_msr(struct pt_ctx *ctx, u32 addr_range)
>  
>  static void pt_guest_enter(struct vcpu_vmx *vmx)
>  {
> +	struct kvm_vcpu *vcpu = &vmx->vcpu;
> +
> +	rdmsrl(MSR_IA32_MPERF, vcpu->arch.host_mperf);
> +	rdmsrl(MSR_IA32_APERF, vcpu->arch.host_aperf);
> +
>  	if (vmx_pt_mode_is_system())
>  		return;
>  
> @@ -1081,6 +1086,15 @@ static void pt_guest_enter(struct vcpu_vmx *vmx)
>  
>  static void pt_guest_exit(struct vcpu_vmx *vmx)
>  {
> +	struct kvm_vcpu *vcpu = &vmx->vcpu;
> +	u64 perf;
> +
> +	rdmsrl(MSR_IA32_MPERF, perf);
> +	vcpu->arch.v_mperf += perf - vcpu->arch.host_mperf;
> +
> +	rdmsrl(MSR_IA32_APERF, perf);
> +	vcpu->arch.v_aperf += perf - vcpu->arch.host_aperf;
> +
>  	if (vmx_pt_mode_is_system())
>  		return;
>  
> @@ -1914,6 +1928,12 @@ 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;
>  	default:
>  	find_shared_msr:
>  		msr = find_msr_entry(vmx, msr_info->index);

But then here you only emulate it for VMX, which then results in SVM
guests going wobbly.

Also, on Intel, the moment you advertise APERFMPERF, we'll try and read
MSR_PLATFORM_INFO / MSR_TURBO_RATIO_LIMIT*, I don't suppose you're
passing those through as well?