On Mon, Nov 07, 2011 at 03:59:08PM +0100, Peter Zijlstra wrote:
> On Mon, 2011-11-07 at 16:46 +0200, Avi Kivity wrote:
> > On 11/07/2011 04:34 PM, Peter Zijlstra wrote:
> > > On Thu, 2011-11-03 at 14:33 +0200, Gleb Natapov wrote:
> > > > +static void kvm_perf_overflow_intr(struct perf_event *perf_event,
> > > > + struct perf_sample_data *data, struct pt_regs *regs)
> > > > +{
> > > > + struct kvm_pmc *pmc = perf_event->overflow_handler_context;
> > > > + struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu;
> > > > + if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) {
> > > > + kvm_perf_overflow(perf_event, data, regs);
> > > > + kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
> > > > + /*
> > > > + * Inject PMI. If vcpu was in a guest mode during NMI PMI
> > > > + * can be ejected on a guest mode re-entry. Otherwise we can't
> > > > + * be sure that vcpu is not halted, so we should kick it, but
> > > > + * this is impossible from NMI context. Do it from irq work
> > > > + * instead.
> > > > + */
> > > > + if (!kvm_is_in_guest())
> > > > + irq_work_queue(&pmc->vcpu->arch.pmu.irq_work);
> > > > + else
> > > > + kvm_make_request(KVM_REQ_PMI, pmc->vcpu);
> > > > + }
> > > > +}
> > >
> > > I'm not sure I get this, since the counters are vcpu task bound and only
> > > count while the guest is running as per (144d31e6f19) how can we get an
> > > NMI outside of guest context with the vcpu not halted?
> >
> > PMI skew. Do we know how bad it can get?
>
I checked and we do get them. Not often. Something like once per second of
"perf record" run in a guest.
> You're talking about the PMI getting asserted before leaving guest mode
> but not getting ran until after we left guest mode?
>
> But in that case we know the guest is stopped, right? So we can simply
> set that REQ_PMI bit and have guest entry sort things, no?
If exit reason was HALT a guest will not attempt a reentry unless MPI or
other event is injected. We can't eject event in NMI context so we
schedule irq work in this case.
--
Gleb.
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
