Re: [PATCH v6 07/16] KVM: x86/pmu: Reprogram PEBS event to emulate guest PEBS counter

[Xu, Like]

On 2021/5/17 17:14, Peter Zijlstra wrote:
> On Tue, May 11, 2021 at 10:42:05AM +0800, Like Xu wrote:
> > @@ -99,6 +109,7 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
> >   				  bool exclude_kernel, bool intr,
> >   				  bool in_tx, bool in_tx_cp)
> >   {
> > +	struct kvm_pmu *pmu = vcpu_to_pmu(pmc->vcpu);
> >   	struct perf_event *event;
> >   	struct perf_event_attr attr = {
> >   		.type = type,
> > @@ -110,6 +121,7 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
> >   		.exclude_kernel = exclude_kernel,
> >   		.config = config,
> >   	};
> > +	bool pebs = test_bit(pmc->idx, (unsigned long *)&pmu->pebs_enable);
> >   
> >   	attr.sample_period = get_sample_period(pmc, pmc->counter);
> >   
> > @@ -124,9 +136,23 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
> >   		attr.sample_period = 0;
> >   		attr.config |= HSW_IN_TX_CHECKPOINTED;
> >   	}
> > +	if (pebs) {
> > +		/*
> > +		 * The non-zero precision level of guest event makes the ordinary
> > +		 * guest event becomes a guest PEBS event and triggers the host
> > +		 * PEBS PMI handler to determine whether the PEBS overflow PMI
> > +		 * comes from the host counters or the guest.
> > +		 *
> > +		 * For most PEBS hardware events, the difference in the software
> > +		 * precision levels of guest and host PEBS events will not affect
> > +		 * the accuracy of the PEBS profiling result, because the "event IP"
> > +		 * in the PEBS record is calibrated on the guest side.
> > +		 */
> > +		attr.precise_ip = 1;
> > +	}
> >   
> >   	event = perf_event_create_kernel_counter(&attr, -1, current,
> > -						 intr ? kvm_perf_overflow_intr :
> > +						 (intr || pebs) ? kvm_perf_overflow_intr :
> >   						 kvm_perf_overflow, pmc);
> How would pebs && !intr be possible?

I don't think it's possible.

> Also; wouldn't this be more legible
> when written like:
>
> 	perf_overflow_handler_t ovf = kvm_perf_overflow;
>
> 	...
>
> 	if (intr)
> 		ovf = kvm_perf_overflow_intr;
>
> 	...
>
> 	event = perf_event_create_kernel_counter(&attr, -1, current, ovf, pmc);

Please yell if you don't like this:

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 711294babb97..a607f5a1b9cd 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -122,6 +122,8 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, 
u32 type,
                .config = config,
        };
        bool pebs = test_bit(pmc->idx, (unsigned long *)&pmu->pebs_enable);
+       perf_overflow_handler_t ovf = (intr || pebs) ?
+               kvm_perf_overflow_intr : kvm_perf_overflow;

        attr.sample_period = get_sample_period(pmc, pmc->counter);

@@ -151,9 +153,7 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, 
u32 type,
                attr.precise_ip = 1;
        }

-       event = perf_event_create_kernel_counter(&attr, -1, current,
-                                                (intr || pebs) ? 
kvm_perf_overflow_intr :
-                                                kvm_perf_overflow, pmc);
+       event = perf_event_create_kernel_counter(&attr, -1, current, ovf, pmc);
        if (IS_ERR(event)) {
                pr_debug_ratelimited("kvm_pmu: event creation failed %ld 
for pmc->idx = %d\n",
                            PTR_ERR(event), pmc->idx);