[PATCH v1 3/3] RISC-V: KVM: Fix perf-backed counter accounting across stop and read

pmu_ctr_read() adds the event count returned by perf_event_read_value()
to counter_val, which can accumulate the same count repeatedly across
reads. kvm_riscv_vcpu_pmu_ctr_stop() also leaves counter_val stale by
not folding the current event count into it.

Make reads of perf-backed counters side-effect free, and use
perf_event_pause() when stopping a counter to fold the current event
count into counter_val while resetting it. This preserves the counter
value across stop/start and lets the snapshot path use counter_val
directly.

Fixes: 0cb74b65d2e5 ("RISC-V: KVM: Implement perf support without sampling")
Signed-off-by: SeungJu Cheon <[email protected]>
---
 arch/riscv/kvm/vcpu_pmu.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c
index 45dd5233340d..7d50490cc622 100644
--- a/arch/riscv/kvm/vcpu_pmu.c
+++ b/arch/riscv/kvm/vcpu_pmu.c
@@ -268,12 +268,13 @@ static int pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx,
 			return -EINVAL;
 
 		pmc->counter_val = kvpmu->fw_event[fevent_code].value;
+		*out_val = pmc->counter_val;
 	} else if (pmc->perf_event) {
-		pmc->counter_val += perf_event_read_value(pmc->perf_event, &enabled, &running);
+		*out_val = pmc->counter_val +
+			   perf_event_read_value(pmc->perf_event, &enabled, &running);
 	} else {
 		return -EINVAL;
 	}
-	*out_val = pmc->counter_val;
 
 	return 0;
 }
@@ -641,7 +642,6 @@ int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base,
 {
 	struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu);
 	int i, pmc_index, sbiret = 0;
-	u64 enabled, running;
 	struct kvm_pmc *pmc;
 	int fevent_code;
 	bool snap_flag_set = flags & SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT;
@@ -679,8 +679,11 @@ int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base,
 			}
 		} else if (pmc->perf_event) {
 			if (pmc->started) {
-				/* Stop counting the counter */
-				perf_event_disable(pmc->perf_event);
+				/*
+				 * Stop the counter and fold the live count into counter_val.
+				 * Reset the event value to avoid redundant accumulation.
+				 */
+				pmc->counter_val += perf_event_pause(pmc->perf_event, true);
 				pmc->started = false;
 			} else {
 				sbiret = SBI_ERR_ALREADY_STOPPED;
@@ -694,9 +697,6 @@ int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base,
 		}
 
 		if (snap_flag_set && !sbiret) {
-			if (pmc->perf_event)
-				pmc->counter_val += perf_event_read_value(pmc->perf_event,
-									  &enabled, &running);
 			/*
 			 * The counter and overflow indices in the snapshot region are w.r.to
 			 * cbase. Modify the set bit in the counter mask instead of the pmc_index
-- 
2.52.0