[PATCH v5 18/24] KVM: arm64: Enforce PMU event filter at vcpu_load()

[Colton Lewis]

Oliver Upton <oupton at kernel.org> writes:

> On Tue, Dec 09, 2025 at 08:51:15PM +0000, Colton Lewis wrote:
>> The KVM API for event filtering says that counters do not count when
>> blocked by the event filter. To enforce that, the event filter must be
>> rechecked on every load since it might have changed since the last
>> time the guest wrote a value. If the event is filtered, exclude
>> counting at all exception levels before writing the hardware.

>> Signed-off-by: Colton Lewis <coltonlewis at google.com>
>> ---
>>   arch/arm64/kvm/pmu-direct.c | 44 +++++++++++++++++++++++++++++++++++++
>>   1 file changed, 44 insertions(+)

>> diff --git a/arch/arm64/kvm/pmu-direct.c b/arch/arm64/kvm/pmu-direct.c
>> index 71977d24f489a..8d0d6d1a0d851 100644
>> --- a/arch/arm64/kvm/pmu-direct.c
>> +++ b/arch/arm64/kvm/pmu-direct.c
>> @@ -221,6 +221,49 @@ u8 kvm_pmu_hpmn(struct kvm_vcpu *vcpu)
>>   	return nr_host_cnt_max;
>>   }

>> +/**
>> + * kvm_pmu_apply_event_filter()
>> + * @vcpu: Pointer to vcpu struct
>> + *
>> + * To uphold the guarantee of the KVM PMU event filter, we must ensure
>> + * no counter counts if the event is filtered. Accomplish this by
>> + * filtering all exception levels if the event is filtered.
>> + */
>> +static void kvm_pmu_apply_event_filter(struct kvm_vcpu *vcpu)
>> +{
>> +	struct arm_pmu *pmu = vcpu->kvm->arch.arm_pmu;
>> +	u64 evtyper_set = ARMV8_PMU_EXCLUDE_EL0 |
>> +		ARMV8_PMU_EXCLUDE_EL1;
>> +	u64 evtyper_clr = ARMV8_PMU_INCLUDE_EL2;
>> +	u8 i;
>> +	u64 val;
>> +	u64 evsel;
>> +
>> +	if (!pmu)
>> +		return;
>> +
>> +	for (i = 0; i < pmu->hpmn_max; i++) {
>> +		val = __vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i);
>> +		evsel = val & kvm_pmu_event_mask(vcpu->kvm);
>> +
>> +		if (vcpu->kvm->arch.pmu_filter &&
>> +		    !test_bit(evsel, vcpu->kvm->arch.pmu_filter))
>> +			val |= evtyper_set;
>> +
>> +		val &= ~evtyper_clr;
>> +		write_pmevtypern(i, val);
>> +	}
>> +
>> +	val = __vcpu_sys_reg(vcpu, PMCCFILTR_EL0);
>> +
>> +	if (vcpu->kvm->arch.pmu_filter &&
>> +	    !test_bit(ARMV8_PMUV3_PERFCTR_CPU_CYCLES,  
>> vcpu->kvm->arch.pmu_filter))
>> +		val |= evtyper_set;
>> +
>> +	val &= ~evtyper_clr;
>> +	write_pmccfiltr(val);
>> +}

> This doesn't work for nested. I agree that the hardware value of
> PMEVTYPERn_EL0 needs to be under KVM control, but depending on whether
> or not we're in a hyp context the meaning of the EL1 filtering bit
> changes. Have a look at kvm_pmu_create_perf_event().

That's where I got the ideas for this code. I'll look at the handling
for hyp context too.


> Thanks,
> Oliver