diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 2071260a275b..46822afc57e0 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -632,6 +632,8 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	 */
 	val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
 	       | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E);
+	if (!system_supports_32bit_el0())
+		val |= ARMV8_PMU_PMCR_LC;
 	__vcpu_sys_reg(vcpu, r->reg) = val;
 }
 
@@ -682,6 +684,8 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		val = __vcpu_sys_reg(vcpu, PMCR_EL0);
 		val &= ~ARMV8_PMU_PMCR_MASK;
 		val |= p->regval & ARMV8_PMU_PMCR_MASK;
+		if (!system_supports_32bit_el0())
+			val |= ARMV8_PMU_PMCR_LC;
 		__vcpu_sys_reg(vcpu, PMCR_EL0) = val;
 		kvm_pmu_handle_pmcr(vcpu, val);
 		kvm_vcpu_pmu_restore_guest(vcpu);
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index 362a01886bab..8731dfeced8b 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -8,6 +8,7 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <linux/perf_event.h>
+#include <linux/perf/arm_pmu.h>
 #include <linux/uaccess.h>
 #include <asm/kvm_emulate.h>
 #include <kvm/arm_pmu.h>
@@ -146,8 +147,7 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
 	if (kvm_pmu_pmc_is_chained(pmc) &&
 	    kvm_pmu_idx_is_high_counter(select_idx))
 		counter = upper_32_bits(counter);
-
-	else if (!kvm_pmu_idx_is_64bit(vcpu, select_idx))
+	else if (select_idx != ARMV8_PMU_CYCLE_IDX)
 		counter = lower_32_bits(counter);
 
 	return counter;
@@ -193,7 +193,7 @@ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc)
  */
 static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
 {
-	u64 counter, reg;
+	u64 counter, reg, val;
 
 	pmc = kvm_pmu_get_canonical_pmc(pmc);
 	if (!pmc->perf_event)
@@ -201,16 +201,19 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
 
 	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
 
-	if (kvm_pmu_pmc_is_chained(pmc)) {
-		reg = PMEVCNTR0_EL0 + pmc->idx;
-		__vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter);
-		__vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter);
+	if (pmc->idx == ARMV8_PMU_CYCLE_IDX) {
+		reg = PMCCNTR_EL0;
+		val = counter;
 	} else {
-		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
-		       ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
-		__vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter);
+		reg = PMEVCNTR0_EL0 + pmc->idx;
+		val = lower_32_bits(counter);
 	}
 
+	__vcpu_sys_reg(vcpu, reg) = val;
+
+	if (kvm_pmu_pmc_is_chained(pmc))
+		__vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter);
+
 	kvm_pmu_release_perf_event(pmc);
 }
 
@@ -440,8 +443,25 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
 				  struct pt_regs *regs)
 {
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
+	struct arm_pmu *cpu_pmu = to_arm_pmu(perf_event->pmu);
 	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
 	int idx = pmc->idx;
+	u64 period;
+
+	cpu_pmu->pmu.stop(perf_event, PERF_EF_UPDATE);
+
+	/*
+	 * Reset the sample period to the architectural limit,
+	 * i.e. the point where the counter overflows.
+	 */
+	period = -(local64_read(&perf_event->count));
+
+	if (!kvm_pmu_idx_is_64bit(vcpu, pmc->idx))
+		period &= GENMASK(31, 0);
+
+	local64_set(&perf_event->hw.period_left, 0);
+	perf_event->attr.sample_period = period;
+	perf_event->hw.sample_period = period;
 
 	__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx);
 
@@ -449,6 +469,8 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
 		kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 		kvm_vcpu_kick(vcpu);
 	}
+
+	cpu_pmu->pmu.start(perf_event, PERF_EF_RELOAD);
 }
 
 /**
@@ -567,12 +589,12 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 		 * high counter.
 		 */
 		attr.sample_period = (-counter) & GENMASK(63, 0);
+		if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1))
+			attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
+
 		event = perf_event_create_kernel_counter(&attr, -1, current,
 							 kvm_pmu_perf_overflow,
 							 pmc + 1);
-
-		if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1))
-			attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
 	} else {
 		/* The initial sample period (overflow count) of an event. */
 		if (kvm_pmu_idx_is_64bit(vcpu, pmc->idx))