[PATCH 3/4] KVM: arm64: pmu: Fix chained SW_INCR counters

[Eric Auger]

At the moment a SW_INCR counter always overflows on 32-bit
boundary, independently on whether the n+1th counter is
programmed as CHAIN.

Check whether the SW_INCR counter is a 64b counter and if so,
implement the 64b logic.

Fixes: 80f393a23be6 ("KVM: arm/arm64: Support chained PMU counters")
Signed-off-by: Eric Auger <eric.auger@xxxxxxxxxx>
Signed-off-by: Marc Zyngier <maz@xxxxxxxxxx>

---

v1 -> v2:
- Reorganize the kvm_pmu_software_increment() flow as suggested by
  Marc. At the exception I did not use kvm_pmu_get_counter_value()
  as it returns only the right half of the 64b counter.
---
 virt/kvm/arm/pmu.c | 43 ++++++++++++++++++++++++++++++-------------
 1 file changed, 30 insertions(+), 13 deletions(-)

diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index 9f605e0b8dd7..560db6282137 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -477,28 +477,45 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
  */
 void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
 {
+	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 	int i;
-	u64 type, enable, reg;
-
-	if (val == 0)
-		return;
 
 	if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E))
 		return;
 
-	enable = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
+	/* Weed out disabled counters */
+	val &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
+
 	for (i = 0; i < ARMV8_PMU_CYCLE_IDX; i++) {
+		u64 type, reg;
+
 		if (!(val & BIT(i)))
 			continue;
-		type = __vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i)
-		       & ARMV8_PMU_EVTYPE_EVENT;
-		if ((type == ARMV8_PMUV3_PERFCTR_SW_INCR)
-		    && (enable & BIT(i))) {
-			reg = __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) + 1;
+
+		/* PMSWINC only applies to ... SW_INC! */
+		type = __vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i);
+		type &= ARMV8_PMU_EVTYPE_EVENT;
+		if (type != ARMV8_PMUV3_PERFCTR_SW_INCR)
+			continue;
+
+		/* increment this even SW_INC counter */
+		reg = __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) + 1;
+		reg = lower_32_bits(reg);
+		__vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) = reg;
+
+		if (reg) /* no overflow on the low part */
+			continue;
+
+		if (kvm_pmu_pmc_is_chained(&pmu->pmc[i])) {
+			/* increment the high counter */
+			reg = __vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i + 1) + 1;
 			reg = lower_32_bits(reg);
-			__vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i) = reg;
-			if (!reg)
-				__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i);
+			__vcpu_sys_reg(vcpu, PMEVCNTR0_EL0 + i + 1) = reg;
+			if (!reg) /* mark overflow on the high counter */
+				__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i + 1);
+		} else {
+			/* mark overflow on low counter */
+			__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i);
 		}
 	}
 }
-- 
2.20.1