Thread (43 messages) 43 messages, 5 authors, 2026-01-15
STALE195d
Revisions (7)
  1. v2 [diff vs current]
  2. v3 [diff vs current]
  3. v4 [diff vs current]
  4. v5 current
  5. v6 [diff vs current]
  6. v7 [diff vs current]
  7. v8 [diff vs current]

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

From: Colton Lewis <hidden>
Date: 2025-12-09 20:52:47
Also in: kvm, kvmarm, linux-doc, linux-kselftest, linux-perf-users, lkml
Subsystem: arm64 port (aarch64 architecture), kernel virtual machine for arm64 (kvm/arm64), the rest · Maintainers: Catalin Marinas, Will Deacon, Marc Zyngier, Oliver Upton, Linus Torvalds

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 <redacted>
---
 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);
+}
+
 /**
  * kvm_pmu_load() - Load untrapped PMU registers
  * @vcpu: Pointer to struct kvm_vcpu
@@ -244,6 +287,7 @@ void kvm_pmu_load(struct kvm_vcpu *vcpu)
 		return;
 
 	pmu = vcpu->kvm->arch.arm_pmu;
+	kvm_pmu_apply_event_filter(vcpu);
 
 	for (i = 0; i < pmu->hpmn_max; i++) {
 		val = __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i);
-- 
2.52.0.239.gd5f0c6e74e-goog

Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help