Re: [PATCH v9 05/12] KVM: x86/pmu: Support PERF_METRICS MSR in mediated vPMU

[Yosry Ahmed]

On Thu, Oct 29, 2026 at 4:26 PM Jim Mattson <jmattson@xxxxxxxxxx> wrote:
>
> On Thu, Oct 29, 2026 at 4:19 PM Yosry Ahmed <yosry@xxxxxxxxxx> wrote:
> >
> > On Thu, Oct 29, 2026 at 4:17 PM Chen, Zide <zide.chen@xxxxxxxxx> wrote:
> > >
> > >
> > >
> > > On 10/29/2026 5:06 PM, Yosry Ahmed wrote:
> > > >> diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
> > > >> index 448044a2b121..f4d3801b97bc 100644
> > > >> --- a/arch/x86/kvm/pmu.c
> > > >> +++ b/arch/x86/kvm/pmu.c
> > > >> @@ -806,9 +806,16 @@ static bool kvm_need_any_pmc_intercept(struct kvm_vcpu *vcpu)
> > > >>                pmu->nr_arch_fixed_counters != kvm_host_pmu.num_counters_fixed;
> > > >>  }
> > > >>
> > > >> +static bool kvm_need_perf_metrics_intercept(struct kvm_vcpu *vcpu)
> > > >
> > > > The name is confusing, this doesn't control the intercept of
> > > > PERF_METRICS (and it wouldn't be correct to use it for that AFAICT).
> > >
> > > Right, these two APIs do not directly determine whether the mentioned
> > > resources need interception:
> > >
> > > kvm_need_any_pmc_intercept()
> > > kvm_need_perf_metrics_intercept()
> >
> > Jim suggested folding kvm_need_perf_metrics_intercept() into
> > kvm_need_any_pmc_intercept(). The name of kvm_need_any_pmc_intercept()
> > might be confusing as well, but at least it's one less interface to
> > worry about?
> >
> > >
> > > This is different from kvm_need_perf_global_ctrl_intercept() and
> > > kvm_need_rdpmc_intercept().
> > >
> > > How about change them to something like these?
> > >
> > > kvm_pmu_has_unexposed_pmcs()
> > > kvm_pmu_has_unexposed_perf_metrics()
> > >
> > > Or merge them into one single API? kvm_pmu_has_unexposed_resources()
> >
> > I don't like this name any better, but I don't have better
> > suggestions. Since we already have kvm_need_any_pmc_intercept(), let's
> > just use it for now?
>
> How about kvm_pmu_incomplete_passthrough()?

Better than kvm_need_any_pmc_intercept() imo.