Merge branch kvm-arm64/pmu-unchained into kvmarm-master/next

* kvm-arm64/pmu-unchained:
  : .
  : PMUv3 fixes and improvements:
  :
  : - Make the CHAIN event handling strictly follow the architecture
  :
  : - Add support for PMUv3p5 (64bit counters all the way)
  :
  : - Various fixes and cleanups
  : .
  KVM: arm64: PMU: Fix period computation for 64bit counters with 32bit overflow
  KVM: arm64: PMU: Sanitise PMCR_EL0.LP on first vcpu run
  KVM: arm64: PMU: Simplify PMCR_EL0 reset handling
  KVM: arm64: PMU: Replace version number '0' with ID_AA64DFR0_EL1_PMUVer_NI
  KVM: arm64: PMU: Make kvm_pmc the main data structure
  KVM: arm64: PMU: Simplify vcpu computation on perf overflow notification
  KVM: arm64: PMU: Allow PMUv3p5 to be exposed to the guest
  KVM: arm64: PMU: Implement PMUv3p5 long counter support
  KVM: arm64: PMU: Allow ID_DFR0_EL1.PerfMon to be set from userspace
  KVM: arm64: PMU: Allow ID_AA64DFR0_EL1.PMUver to be set from userspace
  KVM: arm64: PMU: Move the ID_AA64DFR0_EL1.PMUver limit to VM creation
  KVM: arm64: PMU: Do not let AArch32 change the counters' top 32 bits
  KVM: arm64: PMU: Simplify setting a counter to a specific value
  KVM: arm64: PMU: Add counter_index_to_*reg() helpers
  KVM: arm64: PMU: Only narrow counters that are not 64bit wide
  KVM: arm64: PMU: Narrow the overflow checking when required
  KVM: arm64: PMU: Distinguish between 64bit counter and 64bit overflow
  KVM: arm64: PMU: Always advertise the CHAIN event
  KVM: arm64: PMU: Align chained counter implementation with architecture pseudocode
  arm64: Add ID_DFR0_EL1.PerfMon values for PMUv3p7 and IMP_DEF

Signed-off-by: Marc Zyngier <maz@kernel.org>

5 files changed, 343 insertions, 308 deletions

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 63307e7dc9c5..001c8abe87fc 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -227,6 +227,10 @@ struct kvm_arch {
 
 	u8 pfr0_csv2;
 	u8 pfr0_csv3;
+	struct {
+		u8 imp:4;
+		u8 unimp:4;
+	} dfr0_pmuver;
 
 	/* Hypercall features firmware registers' descriptor */
 	struct kvm_smccc_features smccc_feat;
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 7d301700d1a9..84f59ce1dc6d 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -698,6 +698,8 @@
 #define ID_DFR0_PERFMON_8_1		0x4
 #define ID_DFR0_PERFMON_8_4		0x5
 #define ID_DFR0_PERFMON_8_5		0x6
+#define ID_DFR0_PERFMON_8_7		0x7
+#define ID_DFR0_PERFMON_IMP_DEF		0xf
 
 #define ID_ISAR4_SWP_FRAC_SHIFT		28
 #define ID_ISAR4_PSR_M_SHIFT		24
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 1d1a3b93a3de..00da570ed72b 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -164,6 +164,12 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	set_default_spectre(kvm);
 	kvm_arm_init_hypercalls(kvm);
 
+	/*
+	 * Initialise the default PMUver before there is a chance to
+	 * create an actual PMU.
+	 */
+	kvm->arch.dfr0_pmuver.imp = kvm_arm_pmu_get_pmuver_limit();
+
 	return 0;
 
 err_free_cpumask:
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 0003c7d37533..24908400e190 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -15,16 +15,25 @@
 #include <kvm/arm_pmu.h>
 #include <kvm/arm_vgic.h>
 
+#define PERF_ATTR_CFG1_COUNTER_64BIT	BIT(0)
+
 DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available);
 
 static LIST_HEAD(arm_pmus);
 static DEFINE_MUTEX(arm_pmus_lock);
 
-static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx);
-static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx);
-static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc);
+static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc);
+static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc);
+
+static struct kvm_vcpu *kvm_pmc_to_vcpu(const struct kvm_pmc *pmc)
+{
+	return container_of(pmc, struct kvm_vcpu, arch.pmu.pmc[pmc->idx]);
+}
 
-#define PERF_ATTR_CFG1_KVM_PMU_CHAINED 0x1
+static struct kvm_pmc *kvm_vcpu_idx_to_pmc(struct kvm_vcpu *vcpu, int cnt_idx)
+{
+	return &vcpu->arch.pmu.pmc[cnt_idx];
+}
 
 static u32 kvm_pmu_event_mask(struct kvm *kvm)
 {
@@ -47,113 +56,46 @@ static u32 kvm_pmu_event_mask(struct kvm *kvm)
 }
 
 /**
- * kvm_pmu_idx_is_64bit - determine if select_idx is a 64bit counter
- * @vcpu: The vcpu pointer
- * @select_idx: The counter index
+ * kvm_pmc_is_64bit - determine if counter is 64bit
+ * @pmc: counter context
  */
-static bool kvm_pmu_idx_is_64bit(struct kvm_vcpu *vcpu, u64 select_idx)
+static bool kvm_pmc_is_64bit(struct kvm_pmc *pmc)
 {
-	return (select_idx == ARMV8_PMU_CYCLE_IDX &&
-		__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_LC);
+	return (pmc->idx == ARMV8_PMU_CYCLE_IDX ||
+		kvm_pmu_is_3p5(kvm_pmc_to_vcpu(pmc)));
 }
 
-static struct kvm_vcpu *kvm_pmc_to_vcpu(struct kvm_pmc *pmc)
+static bool kvm_pmc_has_64bit_overflow(struct kvm_pmc *pmc)
 {
-	struct kvm_pmu *pmu;
-	struct kvm_vcpu_arch *vcpu_arch;
+	u64 val = __vcpu_sys_reg(kvm_pmc_to_vcpu(pmc), PMCR_EL0);
 
-	pmc -= pmc->idx;
-	pmu = container_of(pmc, struct kvm_pmu, pmc[0]);
-	vcpu_arch = container_of(pmu, struct kvm_vcpu_arch, pmu);
-	return container_of(vcpu_arch, struct kvm_vcpu, arch);
+	return (pmc->idx < ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LP)) ||
+	       (pmc->idx == ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LC));
 }
 
-/**
- * kvm_pmu_pmc_is_chained - determine if the pmc is chained
- * @pmc: The PMU counter pointer
- */
-static bool kvm_pmu_pmc_is_chained(struct kvm_pmc *pmc)
+static bool kvm_pmu_counter_can_chain(struct kvm_pmc *pmc)
 {
-	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
-
-	return test_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
+	return (!(pmc->idx & 1) && (pmc->idx + 1) < ARMV8_PMU_CYCLE_IDX &&
+		!kvm_pmc_has_64bit_overflow(pmc));
 }
 
-/**
- * kvm_pmu_idx_is_high_counter - determine if select_idx is a high/low counter
- * @select_idx: The counter index
- */
-static bool kvm_pmu_idx_is_high_counter(u64 select_idx)
-{
-	return select_idx & 0x1;
-}
-
-/**
- * kvm_pmu_get_canonical_pmc - obtain the canonical pmc
- * @pmc: The PMU counter pointer
- *
- * When a pair of PMCs are chained together we use the low counter (canonical)
- * to hold the underlying perf event.
- */
-static struct kvm_pmc *kvm_pmu_get_canonical_pmc(struct kvm_pmc *pmc)
-{
-	if (kvm_pmu_pmc_is_chained(pmc) &&
-	    kvm_pmu_idx_is_high_counter(pmc->idx))
-		return pmc - 1;
-
-	return pmc;
-}
-static struct kvm_pmc *kvm_pmu_get_alternate_pmc(struct kvm_pmc *pmc)
+static u32 counter_index_to_reg(u64 idx)
 {
-	if (kvm_pmu_idx_is_high_counter(pmc->idx))
-		return pmc - 1;
-	else
-		return pmc + 1;
+	return (idx == ARMV8_PMU_CYCLE_IDX) ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + idx;
 }
 
-/**
- * kvm_pmu_idx_has_chain_evtype - determine if the event type is chain
- * @vcpu: The vcpu pointer
- * @select_idx: The counter index
- */
-static bool kvm_pmu_idx_has_chain_evtype(struct kvm_vcpu *vcpu, u64 select_idx)
+static u32 counter_index_to_evtreg(u64 idx)
 {
-	u64 eventsel, reg;
-
-	select_idx |= 0x1;
-
-	if (select_idx == ARMV8_PMU_CYCLE_IDX)
-		return false;
-
-	reg = PMEVTYPER0_EL0 + select_idx;
-	eventsel = __vcpu_sys_reg(vcpu, reg) & kvm_pmu_event_mask(vcpu->kvm);
-
-	return eventsel == ARMV8_PMUV3_PERFCTR_CHAIN;
+	return (idx == ARMV8_PMU_CYCLE_IDX) ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + idx;
 }
 
-/**
- * kvm_pmu_get_pair_counter_value - get PMU counter value
- * @vcpu: The vcpu pointer
- * @pmc: The PMU counter pointer
- */
-static u64 kvm_pmu_get_pair_counter_value(struct kvm_vcpu *vcpu,
-					  struct kvm_pmc *pmc)
+static u64 kvm_pmu_get_pmc_value(struct kvm_pmc *pmc)
 {
-	u64 counter, counter_high, reg, enabled, running;
-
-	if (kvm_pmu_pmc_is_chained(pmc)) {
-		pmc = kvm_pmu_get_canonical_pmc(pmc);
-		reg = PMEVCNTR0_EL0 + pmc->idx;
+	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
+	u64 counter, reg, enabled, running;
 
-		counter = __vcpu_sys_reg(vcpu, reg);
-		counter_high = __vcpu_sys_reg(vcpu, reg + 1);
-
-		counter = lower_32_bits(counter) | (counter_high << 32);
-	} else {
-		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
-		      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
-		counter = __vcpu_sys_reg(vcpu, reg);
-	}
+	reg = counter_index_to_reg(pmc->idx);
+	counter = __vcpu_sys_reg(vcpu, reg);
 
 	/*
 	 * The real counter value is equal to the value of counter register plus
@@ -163,6 +105,9 @@ static u64 kvm_pmu_get_pair_counter_value(struct kvm_vcpu *vcpu,
 		counter += perf_event_read_value(pmc->perf_event, &enabled,
 						 &running);
 
+	if (!kvm_pmc_is_64bit(pmc))
+		counter = lower_32_bits(counter);
+
 	return counter;
 }
 
@@ -173,22 +118,37 @@ static u64 kvm_pmu_get_pair_counter_value(struct kvm_vcpu *vcpu,
  */
 u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
 {
-	u64 counter;
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc = &pmu->pmc[select_idx];
-
 	if (!kvm_vcpu_has_pmu(vcpu))
 		return 0;
 
-	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
+	return kvm_pmu_get_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx));
+}
 
-	if (kvm_pmu_pmc_is_chained(pmc) &&
-	    kvm_pmu_idx_is_high_counter(select_idx))
-		counter = upper_32_bits(counter);
-	else if (select_idx != ARMV8_PMU_CYCLE_IDX)
-		counter = lower_32_bits(counter);
+static void kvm_pmu_set_pmc_value(struct kvm_pmc *pmc, u64 val, bool force)
+{
+	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
+	u64 reg;
 
-	return counter;
+	kvm_pmu_release_perf_event(pmc);
+
+	reg = counter_index_to_reg(pmc->idx);
+
+	if (vcpu_mode_is_32bit(vcpu) && pmc->idx != ARMV8_PMU_CYCLE_IDX &&
+	    !force) {
+		/*
+		 * Even with PMUv3p5, AArch32 cannot write to the top
+		 * 32bit of the counters. The only possible course of
+		 * action is to use PMCR.P, which will reset them to
+		 * 0 (the only use of the 'force' parameter).
+		 */
+		val  = __vcpu_sys_reg(vcpu, reg) & GENMASK(63, 32);
+		val |= lower_32_bits(val);
+	}
+
+	__vcpu_sys_reg(vcpu, reg) = val;
+
+	/* Recreate the perf event to reflect the updated sample_period */
+	kvm_pmu_create_perf_event(pmc);
 }
 
 /**
@@ -199,17 +159,10 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
  */
 void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
 {
-	u64 reg;
-
 	if (!kvm_vcpu_has_pmu(vcpu))
 		return;
 
-	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
-	      ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + select_idx;
-	__vcpu_sys_reg(vcpu, reg) += (s64)val - kvm_pmu_get_counter_value(vcpu, select_idx);
-
-	/* Recreate the perf event to reflect the updated sample_period */
-	kvm_pmu_create_perf_event(vcpu, select_idx);
+	kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx), val, false);
 }
 
 /**
@@ -218,7 +171,6 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
  */
 static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc)
 {
-	pmc = kvm_pmu_get_canonical_pmc(pmc);
 	if (pmc->perf_event) {
 		perf_event_disable(pmc->perf_event);
 		perf_event_release_kernel(pmc->perf_event);
@@ -232,29 +184,20 @@ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc)
  *
  * If this counter has been configured to monitor some event, release it here.
  */
-static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
+static void kvm_pmu_stop_counter(struct kvm_pmc *pmc)
 {
-	u64 counter, reg, val;
+	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
+	u64 reg, val;
 
-	pmc = kvm_pmu_get_canonical_pmc(pmc);
 	if (!pmc->perf_event)
 		return;
 
-	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
+	val = kvm_pmu_get_pmc_value(pmc);
 
-	if (pmc->idx == ARMV8_PMU_CYCLE_IDX) {
-		reg = PMCCNTR_EL0;
-		val = counter;
-	} else {
-		reg = PMEVCNTR0_EL0 + pmc->idx;
-		val = lower_32_bits(counter);
-	}
+	reg = counter_index_to_reg(pmc->idx);
 
 	__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);
 }
 
@@ -280,13 +223,10 @@ void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu)
 void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
 {
 	unsigned long mask = kvm_pmu_valid_counter_mask(vcpu);
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 	int i;
 
 	for_each_set_bit(i, &mask, 32)
-		kvm_pmu_stop_counter(vcpu, &pmu->pmc[i]);
-
-	bitmap_zero(vcpu->arch.pmu.chained, ARMV8_PMU_MAX_COUNTER_PAIRS);
+		kvm_pmu_stop_counter(kvm_vcpu_idx_to_pmc(vcpu, i));
 }
 
 /**
@@ -297,10 +237,9 @@ void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
 void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	int i;
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 
 	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++)
-		kvm_pmu_release_perf_event(&pmu->pmc[i]);
+		kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, i));
 	irq_work_sync(&vcpu->arch.pmu.overflow_work);
 }
 
@@ -325,9 +264,6 @@ u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
 void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 {
 	int i;
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc;
-
 	if (!kvm_vcpu_has_pmu(vcpu))
 		return;
 
@@ -335,17 +271,16 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 		return;
 
 	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+		struct kvm_pmc *pmc;
+
 		if (!(val & BIT(i)))
 			continue;
 
-		pmc = &pmu->pmc[i];
-
-		/* A change in the enable state may affect the chain state */
-		kvm_pmu_update_pmc_chained(vcpu, i);
-		kvm_pmu_create_perf_event(vcpu, i);
+		pmc = kvm_vcpu_idx_to_pmc(vcpu, i);
 
-		/* At this point, pmc must be the canonical */
-		if (pmc->perf_event) {
+		if (!pmc->perf_event) {
+			kvm_pmu_create_perf_event(pmc);
+		} else {
 			perf_event_enable(pmc->perf_event);
 			if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE)
 				kvm_debug("fail to enable perf event\n");
@@ -363,23 +298,18 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 {
 	int i;
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc;
 
 	if (!kvm_vcpu_has_pmu(vcpu) || !val)
 		return;
 
 	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
+		struct kvm_pmc *pmc;
+
 		if (!(val & BIT(i)))
 			continue;
 
-		pmc = &pmu->pmc[i];
-
-		/* A change in the enable state may affect the chain state */
-		kvm_pmu_update_pmc_chained(vcpu, i);
-		kvm_pmu_create_perf_event(vcpu, i);
+		pmc = kvm_vcpu_idx_to_pmc(vcpu, i);
 
-		/* At this point, pmc must be the canonical */
 		if (pmc->perf_event)
 			perf_event_disable(pmc->perf_event);
 	}
@@ -476,14 +406,69 @@ void kvm_pmu_sync_hwstate(struct kvm_vcpu *vcpu)
 static void kvm_pmu_perf_overflow_notify_vcpu(struct irq_work *work)
 {
 	struct kvm_vcpu *vcpu;
-	struct kvm_pmu *pmu;
-
-	pmu = container_of(work, struct kvm_pmu, overflow_work);
-	vcpu = kvm_pmc_to_vcpu(pmu->pmc);
 
+	vcpu = container_of(work, struct kvm_vcpu, arch.pmu.overflow_work);
 	kvm_vcpu_kick(vcpu);
 }
 
+/*
+ * Perform an increment on any of the counters described in @mask,
+ * generating the overflow if required, and propagate it as a chained
+ * event if possible.
+ */
+static void kvm_pmu_counter_increment(struct kvm_vcpu *vcpu,
+				      unsigned long mask, u32 event)
+{
+	int i;
+
+	if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E))
+		return;
+
+	/* Weed out disabled counters */
+	mask &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
+
+	for_each_set_bit(i, &mask, ARMV8_PMU_CYCLE_IDX) {
+		struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i);
+		u64 type, reg;
+
+		/* Filter on event type */
+		type = __vcpu_sys_reg(vcpu, counter_index_to_evtreg(i));
+		type &= kvm_pmu_event_mask(vcpu->kvm);
+		if (type != event)
+			continue;
+
+		/* Increment this counter */
+		reg = __vcpu_sys_reg(vcpu, counter_index_to_reg(i)) + 1;
+		if (!kvm_pmc_is_64bit(pmc))
+			reg = lower_32_bits(reg);
+		__vcpu_sys_reg(vcpu, counter_index_to_reg(i)) = reg;
+
+		/* No overflow? move on */
+		if (kvm_pmc_has_64bit_overflow(pmc) ? reg : lower_32_bits(reg))
+			continue;
+
+		/* Mark overflow */
+		__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i);
+
+		if (kvm_pmu_counter_can_chain(pmc))
+			kvm_pmu_counter_increment(vcpu, BIT(i + 1),
+						  ARMV8_PMUV3_PERFCTR_CHAIN);
+	}
+}
+
+/* Compute the sample period for a given counter value */
+static u64 compute_period(struct kvm_pmc *pmc, u64 counter)
+{
+	u64 val;
+
+	if (kvm_pmc_is_64bit(pmc) && kvm_pmc_has_64bit_overflow(pmc))
+		val = (-counter) & GENMASK(63, 0);
+	else
+		val = (-counter) & GENMASK(31, 0);
+
+	return val;
+}
+
 /**
  * When the perf event overflows, set the overflow status and inform the vcpu.
  */
@@ -503,10 +488,7 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
 	 * 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);
+	period = compute_period(pmc, local64_read(&perf_event->count));
 
 	local64_set(&perf_event->hw.period_left, 0);
 	perf_event->attr.sample_period = period;
@@ -514,6 +496,10 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
 
 	__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx);
 
+	if (kvm_pmu_counter_can_chain(pmc))
+		kvm_pmu_counter_increment(vcpu, BIT(idx + 1),
+					  ARMV8_PMUV3_PERFCTR_CHAIN);
+
 	if (kvm_pmu_overflow_status(vcpu)) {
 		kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 
@@ -533,50 +519,7 @@ 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;
-
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return;
-
-	if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E))
-		return;
-
-	/* 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;
-
-		/* PMSWINC only applies to ... SW_INC! */
-		type = __vcpu_sys_reg(vcpu, PMEVTYPER0_EL0 + i);
-		type &= kvm_pmu_event_mask(vcpu->kvm);
-		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 + 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);
-		}
-	}
+	kvm_pmu_counter_increment(vcpu, val, ARMV8_PMUV3_PERFCTR_SW_INCR);
 }
 
 /**
@@ -591,6 +534,12 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 	if (!kvm_vcpu_has_pmu(vcpu))
 		return;
 
+	/* Fixup PMCR_EL0 to reconcile the PMU version and the LP bit */
+	if (!kvm_pmu_is_3p5(vcpu))
+		val &= ~ARMV8_PMU_PMCR_LP;
+
+	__vcpu_sys_reg(vcpu, PMCR_EL0) = val;
+
 	if (val & ARMV8_PMU_PMCR_E) {
 		kvm_pmu_enable_counter_mask(vcpu,
 		       __vcpu_sys_reg(vcpu, PMCNTENSET_EL0));
@@ -606,49 +555,44 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 		unsigned long mask = kvm_pmu_valid_counter_mask(vcpu);
 		mask &= ~BIT(ARMV8_PMU_CYCLE_IDX);
 		for_each_set_bit(i, &mask, 32)
-			kvm_pmu_set_counter_value(vcpu, i, 0);
+			kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, i), 0, true);
 	}
 }
 
-static bool kvm_pmu_counter_is_enabled(struct kvm_vcpu *vcpu, u64 select_idx)
+static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc)
 {
+	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
 	return (__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) &&
-	       (__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(select_idx));
+	       (__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(pmc->idx));
 }
 
 /**
  * kvm_pmu_create_perf_event - create a perf event for a counter
- * @vcpu: The vcpu pointer
- * @select_idx: The number of selected counter
+ * @pmc: Counter context
  */
-static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
+static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc)
 {
+	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
 	struct arm_pmu *arm_pmu = vcpu->kvm->arch.arm_pmu;
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc;
 	struct perf_event *event;
 	struct perf_event_attr attr;
-	u64 eventsel, counter, reg, data;
+	u64 eventsel, reg, data;
 
-	/*
-	 * For chained counters the event type and filtering attributes are
-	 * obtained from the low/even counter. We also use this counter to
-	 * determine if the event is enabled/disabled.
-	 */
-	pmc = kvm_pmu_get_canonical_pmc(&pmu->pmc[select_idx]);
-
-	reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
-	      ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + pmc->idx;
+	reg = counter_index_to_evtreg(pmc->idx);
 	data = __vcpu_sys_reg(vcpu, reg);
 
-	kvm_pmu_stop_counter(vcpu, pmc);
+	kvm_pmu_stop_counter(pmc);
 	if (pmc->idx == ARMV8_PMU_CYCLE_IDX)
 		eventsel = ARMV8_PMUV3_PERFCTR_CPU_CYCLES;
 	else
 		eventsel = data & kvm_pmu_event_mask(vcpu->kvm);
 
-	/* Software increment event doesn't need to be backed by a perf event */
-	if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR)
+	/*
+	 * Neither SW increment nor chained events need to be backed
+	 * by a perf event.
+	 */
+	if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR ||
+	    eventsel == ARMV8_PMUV3_PERFCTR_CHAIN)
 		return;
 
 	/*
@@ -663,37 +607,25 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 	attr.type = arm_pmu->pmu.type;
 	attr.size = sizeof(attr);
 	attr.pinned = 1;
-	attr.disabled = !kvm_pmu_counter_is_enabled(vcpu, pmc->idx);
+	attr.disabled = !kvm_pmu_counter_is_enabled(pmc);
 	attr.exclude_user = data & ARMV8_PMU_EXCLUDE_EL0 ? 1 : 0;
 	attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0;
 	attr.exclude_hv = 1; /* Don't count EL2 events */
 	attr.exclude_host = 1; /* Don't count host events */
 	attr.config = eventsel;
 
-	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
-
-	if (kvm_pmu_pmc_is_chained(pmc)) {
-		/**
-		 * The initial sample period (overflow count) of an event. For
-		 * chained counters we only support overflow interrupts on the
-		 * high counter.
-		 */
-		attr.sample_period = (-counter) & GENMASK(63, 0);
-		attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
+	/*
+	 * If counting with a 64bit counter, advertise it to the perf
+	 * code, carefully dealing with the initial sample period
+	 * which also depends on the overflow.
+	 */
+	if (kvm_pmc_is_64bit(pmc))
+		attr.config1 |= PERF_ATTR_CFG1_COUNTER_64BIT;
 
-		event = perf_event_create_kernel_counter(&attr, -1, current,
-							 kvm_pmu_perf_overflow,
-							 pmc + 1);
-	} else {
-		/* The initial sample period (overflow count) of an event. */
-		if (kvm_pmu_idx_is_64bit(vcpu, pmc->idx))
-			attr.sample_period = (-counter) & GENMASK(63, 0);
-		else
-			attr.sample_period = (-counter) & GENMASK(31, 0);
+	attr.sample_period = compute_period(pmc, kvm_pmu_get_pmc_value(pmc));
 
-		event = perf_event_create_kernel_counter(&attr, -1, current,
+	event = perf_event_create_kernel_counter(&attr, -1, current,
 						 kvm_pmu_perf_overflow, pmc);
-	}
 
 	if (IS_ERR(event)) {
 		pr_err_once("kvm: pmu event creation failed %ld\n",
@@ -705,41 +637,6 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 }
 
 /**
- * kvm_pmu_update_pmc_chained - update chained bitmap
- * @vcpu: The vcpu pointer
- * @select_idx: The number of selected counter
- *
- * Update the chained bitmap based on the event type written in the
- * typer register and the enable state of the odd register.
- */
-static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx)
-{
-	struct kvm_pmu *pmu = &vcpu->arch.pmu;
-	struct kvm_pmc *pmc = &pmu->pmc[select_idx], *canonical_pmc;
-	bool new_state, old_state;
-
-	old_state = kvm_pmu_pmc_is_chained(pmc);
-	new_state = kvm_pmu_idx_has_chain_evtype(vcpu, pmc->idx) &&
-		    kvm_pmu_counter_is_enabled(vcpu, pmc->idx | 0x1);
-
-	if (old_state == new_state)
-		return;
-
-	canonical_pmc = kvm_pmu_get_canonical_pmc(pmc);
-	kvm_pmu_stop_counter(vcpu, canonical_pmc);
-	if (new_state) {
-		/*
-		 * During promotion from !chained to chained we must ensure
-		 * the adjacent counter is stopped and its event destroyed
-		 */
-		kvm_pmu_stop_counter(vcpu, kvm_pmu_get_alternate_pmc(pmc));
-		set_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
-		return;
-	}
-	clear_bit(pmc->idx >> 1, vcpu->arch.pmu.chained);
-}
-
-/**
  * kvm_pmu_set_counter_event_type - set selected counter to monitor some event
  * @vcpu: The vcpu pointer
  * @data: The data guest writes to PMXEVTYPER_EL0
@@ -752,6 +649,7 @@ static void kvm_pmu_update_pmc_chained(struct kvm_vcpu *vcpu, u64 select_idx)
 void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 				    u64 select_idx)
 {
+	struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, select_idx);
 	u64 reg, mask;
 
 	if (!kvm_vcpu_has_pmu(vcpu))
@@ -761,20 +659,19 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	mask &= ~ARMV8_PMU_EVTYPE_EVENT;
 	mask |= kvm_pmu_event_mask(vcpu->kvm);
 
-	reg = (select_idx == ARMV8_PMU_CYCLE_IDX)
-	      ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + select_idx;
+	reg = counter_index_to_evtreg(pmc->idx);
 
 	__vcpu_sys_reg(vcpu, reg) = data & mask;
 
-	kvm_pmu_update_pmc_chained(vcpu, select_idx);
-	kvm_pmu_create_perf_event(vcpu, select_idx);
+	kvm_pmu_create_perf_event(pmc);
 }
 
 void kvm_host_pmu_init(struct arm_pmu *pmu)
 {
 	struct arm_pmu_entry *entry;
 
-	if (pmu->pmuver == 0 || pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
+	if (pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_NI ||
+	    pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
 		return;
 
 	mutex_lock(&arm_pmus_lock);
@@ -827,7 +724,7 @@ static struct arm_pmu *kvm_pmu_probe_armpmu(void)
 
 	if (event->pmu) {
 		pmu = to_arm_pmu(event->pmu);
-		if (pmu->pmuver == 0 ||
+		if (pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_NI ||
 		    pmu->pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
 			pmu = NULL;
 	}
@@ -849,6 +746,8 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 
 	if (!pmceid1) {
 		val = read_sysreg(pmceid0_el0);
+		/* always support CHAIN */
+		val |= BIT(ARMV8_PMUV3_PERFCTR_CHAIN);
 		base = 0;
 	} else {
 		val = read_sysreg(pmceid1_el0);
@@ -1150,3 +1049,14 @@ int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 
 	return -ENXIO;
 }
+
+u8 kvm_arm_pmu_get_pmuver_limit(void)
+{
+	u64 tmp;
+
+	tmp = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1);
+	tmp = cpuid_feature_cap_perfmon_field(tmp,
+					      ID_AA64DFR0_EL1_PMUVer_SHIFT,
+					      ID_AA64DFR0_EL1_PMUVer_V3P5);
+	return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), tmp);
+}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index f4a7c5abcbca..528d253c571a 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -639,22 +639,18 @@ static void reset_pmselr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 
 static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
-	u64 pmcr, val;
+	u64 pmcr;
 
 	/* No PMU available, PMCR_EL0 may UNDEF... */
 	if (!kvm_arm_support_pmu_v3())
 		return;
 
-	pmcr = read_sysreg(pmcr_el0);
-	/*
-	 * Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) are reset to UNKNOWN
-	 * except PMCR.E resetting to zero.
-	 */
-	val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
-	       | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E);
+	/* Only preserve PMCR_EL0.N, and reset the rest to 0 */
+	pmcr = read_sysreg(pmcr_el0) & ARMV8_PMU_PMCR_N_MASK;
 	if (!kvm_supports_32bit_el0())
-		val |= ARMV8_PMU_PMCR_LC;
-	__vcpu_sys_reg(vcpu, r->reg) = val;
+		pmcr |= ARMV8_PMU_PMCR_LC;
+
+	__vcpu_sys_reg(vcpu, r->reg) = pmcr;
 }
 
 static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags)
@@ -697,13 +693,15 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		return false;
 
 	if (p->is_write) {
-		/* Only update writeable bits of PMCR */
+		/*
+		 * Only update writeable bits of PMCR (continuing into
+		 * kvm_pmu_handle_pmcr() as well)
+		 */
 		val = __vcpu_sys_reg(vcpu, PMCR_EL0);
 		val &= ~ARMV8_PMU_PMCR_MASK;
 		val |= p->regval & ARMV8_PMU_PMCR_MASK;
 		if (!kvm_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);
 	} else {
@@ -1062,6 +1060,40 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static u8 vcpu_pmuver(const struct kvm_vcpu *vcpu)
+{
+	if (kvm_vcpu_has_pmu(vcpu))
+		return vcpu->kvm->arch.dfr0_pmuver.imp;
+
+	return vcpu->kvm->arch.dfr0_pmuver.unimp;
+}
+
+static u8 perfmon_to_pmuver(u8 perfmon)
+{
+	switch (perfmon) {
+	case ID_DFR0_PERFMON_8_0:
+		return ID_AA64DFR0_EL1_PMUVer_IMP;
+	case ID_DFR0_PERFMON_IMP_DEF:
+		return ID_AA64DFR0_EL1_PMUVer_IMP_DEF;
+	default:
+		/* Anything ARMv8.1+ and NI have the same value. For now. */
+		return perfmon;
+	}
+}
+
+static u8 pmuver_to_perfmon(u8 pmuver)
+{
+	switch (pmuver) {
+	case ID_AA64DFR0_EL1_PMUVer_IMP:
+		return ID_DFR0_PERFMON_8_0;
+	case ID_AA64DFR0_EL1_PMUVer_IMP_DEF:
+		return ID_DFR0_PERFMON_IMP_DEF;
+	default:
+		/* Anything ARMv8.1+ and NI have the same value. For now. */
+		return pmuver;
+	}
+}
+
 /* Read a sanitised cpufeature ID register by sys_reg_desc */
 static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r)
 {
@@ -1111,18 +1143,17 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r
 		/* Limit debug to ARMv8.0 */
 		val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer);
 		val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_DebugVer), 6);
-		/* Limit guests to PMUv3 for ARMv8.4 */
-		val = cpuid_feature_cap_perfmon_field(val,
-						      ID_AA64DFR0_EL1_PMUVer_SHIFT,
-						      kvm_vcpu_has_pmu(vcpu) ? ID_AA64DFR0_EL1_PMUVer_V3P4 : 0);
+		/* Set PMUver to the required version */
+		val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer);
+		val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer),
+				  vcpu_pmuver(vcpu));
 		/* Hide SPE from guests */
 		val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMSVer);
 		break;
 	case SYS_ID_DFR0_EL1:
-		/* Limit guests to PMUv3 for ARMv8.4 */
-		val = cpuid_feature_cap_perfmon_field(val,
-						      ID_DFR0_PERFMON_SHIFT,
-						      kvm_vcpu_has_pmu(vcpu) ? ID_DFR0_PERFMON_8_4 : 0);
+		val &= ~ARM64_FEATURE_MASK(ID_DFR0_PERFMON);
+		val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_DFR0_PERFMON),
+				  pmuver_to_perfmon(vcpu_pmuver(vcpu)));
 		break;
 	}
 
@@ -1222,6 +1253,85 @@ static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static int set_id_aa64dfr0_el1(struct kvm_vcpu *vcpu,
+			       const struct sys_reg_desc *rd,
+			       u64 val)
+{
+	u8 pmuver, host_pmuver;
+	bool valid_pmu;
+
+	host_pmuver = kvm_arm_pmu_get_pmuver_limit();
+
+	/*
+	 * Allow AA64DFR0_EL1.PMUver to be set from userspace as long
+	 * as it doesn't promise more than what the HW gives us. We
+	 * allow an IMPDEF PMU though, only if no PMU is supported
+	 * (KVM backward compatibility handling).
+	 */
+	pmuver = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), val);
+	if ((pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF && pmuver > host_pmuver))
+		return -EINVAL;
+
+	valid_pmu = (pmuver != 0 && pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF);
+
+	/* Make sure view register and PMU support do match */
+	if (kvm_vcpu_has_pmu(vcpu) != valid_pmu)
+		return -EINVAL;
+
+	/* We can only differ with PMUver, and anything else is an error */
+	val ^= read_id_reg(vcpu, rd);
+	val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer);
+	if (val)
+		return -EINVAL;
+
+	if (valid_pmu)
+		vcpu->kvm->arch.dfr0_pmuver.imp = pmuver;
+	else
+		vcpu->kvm->arch.dfr0_pmuver.unimp = pmuver;
+
+	return 0;
+}
+
+static int set_id_dfr0_el1(struct kvm_vcpu *vcpu,
+			   const struct sys_reg_desc *rd,
+			   u64 val)
+{
+	u8 perfmon, host_perfmon;
+	bool valid_pmu;
+
+	host_perfmon = pmuver_to_perfmon(kvm_arm_pmu_get_pmuver_limit());
+
+	/*
+	 * Allow DFR0_EL1.PerfMon to be set from userspace as long as
+	 * it doesn't promise more than what the HW gives us on the
+	 * AArch64 side (as everything is emulated with that), and
+	 * that this is a PMUv3.
+	 */
+	perfmon = FIELD_GET(ARM64_FEATURE_MASK(ID_DFR0_PERFMON), val);
+	if ((perfmon != ID_DFR0_PERFMON_IMP_DEF && perfmon > host_perfmon) ||
+	    (perfmon != 0 && perfmon < ID_DFR0_PERFMON_8_0))
+		return -EINVAL;
+
+	valid_pmu = (perfmon != 0 && perfmon != ID_DFR0_PERFMON_IMP_DEF);
+
+	/* Make sure view register and PMU support do match */
+	if (kvm_vcpu_has_pmu(vcpu) != valid_pmu)
+		return -EINVAL;
+
+	/* We can only differ with PerfMon, and anything else is an error */
+	val ^= read_id_reg(vcpu, rd);
+	val &= ~ARM64_FEATURE_MASK(ID_DFR0_PERFMON);
+	if (val)
+		return -EINVAL;
+
+	if (valid_pmu)
+		vcpu->kvm->arch.dfr0_pmuver.imp = perfmon_to_pmuver(perfmon);
+	else
+		vcpu->kvm->arch.dfr0_pmuver.unimp = perfmon_to_pmuver(perfmon);
+
+	return 0;
+}
+
 /*
  * cpufeature ID register user accessors
  *
@@ -1443,7 +1553,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	/* CRm=1 */
 	AA32_ID_SANITISED(ID_PFR0_EL1),
 	AA32_ID_SANITISED(ID_PFR1_EL1),
-	AA32_ID_SANITISED(ID_DFR0_EL1),
+	{ SYS_DESC(SYS_ID_DFR0_EL1), .access = access_id_reg,
+	  .get_user = get_id_reg, .set_user = set_id_dfr0_el1,
+	  .visibility = aa32_id_visibility, },
 	ID_HIDDEN(ID_AFR0_EL1),
 	AA32_ID_SANITISED(ID_MMFR0_EL1),
 	AA32_ID_SANITISED(ID_MMFR1_EL1),
@@ -1483,7 +1595,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	ID_UNALLOCATED(4,7),
 
 	/* CRm=5 */
-	ID_SANITISED(ID_AA64DFR0_EL1),
+	{ SYS_DESC(SYS_ID_AA64DFR0_EL1), .access = access_id_reg,
+	  .get_user = get_id_reg, .set_user = set_id_aa64dfr0_el1, },
 	ID_SANITISED(ID_AA64DFR1_EL1),
 	ID_UNALLOCATED(5,2),
 	ID_UNALLOCATED(5,3),