Re: [PATCH v2 2/6] KVM: x86/pmu: Refactoring find_arch_event() to pmc_perf_hw_id()

[Like Xu]

On 14/2/2022 6:14 pm, Ravi Bangoria wrote:
> On 11-Feb-22 11:46 PM, Jim Mattson wrote:
> > On Fri, Feb 11, 2022 at 1:56 AM Ravi Bangoria <ravi.bangoria@xxxxxxx> wrote:
> > > On 10-Feb-22 4:58 PM, Like Xu wrote:
> > > > cc Kim and Ravi to help confirm more details about this change.
> > > >
> > > > On 10/2/2022 3:30 am, Jim Mattson wrote:
> > > > > By the way, the following events from amd_event_mapping[] are not
> > > > > listed in the Milan PPR:
> > > > > { 0x7d, 0x07, PERF_COUNT_HW_CACHE_REFERENCES }
> > > > > { 0x7e, 0x07, PERF_COUNT_HW_CACHE_MISSES }
> > > > > { 0xd0, 0x00, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND }
> > > > > { 0xd1, 0x00, PERF_COUNT_HW_STALLED_CYCLES_BACKEND }
> > > > >
> > > > > Perhaps we should build a table based on amd_f17h_perfmon_event_map[]
> > > > > for newer AMD processors?

So do we need another amd_f19h_perfmon_event_map[] in the host perf code ?

> > > I think Like's other patch series to unify event mapping across kvm
> > > and host will fix it. No?
> > > https://lore.kernel.org/lkml/20220117085307.93030-4-likexu@xxxxxxxxxxx
> >
> > Yes, that should fix it. But why do we even bother? What is the
> > downside of using PERF_TYPE_RAW all of the time?
>
> There are few places where PERF_TYPE_HARDWARE and PERF_TYPE_RAW are treated
> differently. Ex, x86_pmu_event_init(), perf_init_event(). So I think it makes
> sense to keep using PERF_TYPE_HARDWARE for generalized events?
>
> Ravi