Re: [PATCH 3/7] KVM: x86/pmu: Avoid setting BIT_ULL(-1) to pmu->host_cross_mapped_mask

[Like Xu]

On 21/7/2022 8:45 am, Sean Christopherson wrote:
> On Wed, Jul 13, 2022, Like Xu wrote:
> > From: Like Xu <likexu@xxxxxxxxxxx>
> >
> > In the extreme case of host counters multiplexing and contention, the
> > perf_event requested by the guest's pebs counter is not allocated to any
> > actual physical counter, in which case hw.idx is bookkept as -1,
> > resulting in an out-of-bounds access to host_cross_mapped_mask.
> >
> > Fixes: 854250329c02 ("KVM: x86/pmu: Disable guest PEBS temporarily in two rare situations")
> > Signed-off-by: Like Xu <likexu@xxxxxxxxxxx>
> > ---
> >   arch/x86/kvm/vmx/pmu_intel.c | 11 +++++------
> >   1 file changed, 5 insertions(+), 6 deletions(-)
> >
> > diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
> > index 53ccba896e77..1588627974fa 100644
> > --- a/arch/x86/kvm/vmx/pmu_intel.c
> > +++ b/arch/x86/kvm/vmx/pmu_intel.c
> > @@ -783,20 +783,19 @@ static void intel_pmu_cleanup(struct kvm_vcpu *vcpu)
> >   void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu)
> >   {
> >   	struct kvm_pmc *pmc = NULL;
> > -	int bit;
> > +	int bit, hw_idx;
> >   
> >   	for_each_set_bit(bit, (unsigned long *)&pmu->global_ctrl,
> >   			 X86_PMC_IDX_MAX) {
> >   		pmc = intel_pmc_idx_to_pmc(pmu, bit);
> >   
> >   		if (!pmc || !pmc_speculative_in_use(pmc) ||
> > -		    !intel_pmc_is_enabled(pmc))
> > +		    !intel_pmc_is_enabled(pmc) || !pmc->perf_event)
> >   			continue;
> >   
> > -		if (pmc->perf_event && pmc->idx != pmc->perf_event->hw.idx) {
> > -			pmu->host_cross_mapped_mask |=
> > -				BIT_ULL(pmc->perf_event->hw.idx);
> > -		}
> > +		hw_idx = pmc->perf_event->hw.idx;
> > +		if (hw_idx != pmc->idx && hw_idx != -1)
>
> How about "hw_idx > 0" so that KVM is a little less dependent on perf's exact
> behavior?  A comment here would be nice too.

The "hw->idx = 0" means that it occupies counter 0, so this part will look like 
this:

		hw_idx = pmc->perf_event->hw.idx;
		/* make it a little less dependent on perf's exact behavior */
		if (hw_idx != pmc->idx && hw_idx > -1)
			pmu->host_cross_mapped_mask |= BIT_ULL(hw_idx);

, what do you think ?

> > +			pmu->host_cross_mapped_mask |= BIT_ULL(hw_idx);
> >   	}
> >   }
> >   
> > --
> > 2.37.0