Merge branch kvm-arm64/pmu_pmcr_n into kvmarm/next

* kvm-arm64/pmu_pmcr_n:
  : User-defined PMC limit, courtesy Raghavendra Rao Ananta
  :
  : Certain VMMs may want to reserve some PMCs for host use while running a
  : KVM guest. This was a bit difficult before, as KVM advertised all
  : supported counters to the guest. Userspace can now limit the number of
  : advertised PMCs by writing to PMCR_EL0.N, as KVM's sysreg and PMU
  : emulation enforce the specified limit for handling guest accesses.
  KVM: selftests: aarch64: vPMU test for validating user accesses
  KVM: selftests: aarch64: vPMU register test for unimplemented counters
  KVM: selftests: aarch64: vPMU register test for implemented counters
  KVM: selftests: aarch64: Introduce vpmu_counter_access test
  tools: Import arm_pmuv3.h
  KVM: arm64: PMU: Allow userspace to limit PMCR_EL0.N for the guest
  KVM: arm64: Sanitize PM{C,I}NTEN{SET,CLR}, PMOVS{SET,CLR} before first run
  KVM: arm64: Add {get,set}_user for PM{C,I}NTEN{SET,CLR}, PMOVS{SET,CLR}
  KVM: arm64: PMU: Set PMCR_EL0.N for vCPU based on the associated PMU
  KVM: arm64: PMU: Add a helper to read a vCPU's PMCR_EL0
  KVM: arm64: Select default PMU in KVM_ARM_VCPU_INIT handler
  KVM: arm64: PMU: Introduce helpers to set the guest's PMU

Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

9 files changed, 1204 insertions, 56 deletions

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 846a7706e925..5653d3553e3e 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -290,6 +290,9 @@ struct kvm_arch {
 
 	cpumask_var_t supported_cpus;
 
+	/* PMCR_EL0.N value for the guest */
+	u8 pmcr_n;
+
 	/* Hypercall features firmware registers' descriptor */
 	struct kvm_smccc_features smccc_feat;
 	struct maple_tree smccc_filter;
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index c6cad400490f..317964bad1e1 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -857,8 +857,7 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)
 		}
 
 		if (kvm_check_request(KVM_REQ_RELOAD_PMU, vcpu))
-			kvm_pmu_handle_pmcr(vcpu,
-					    __vcpu_sys_reg(vcpu, PMCR_EL0));
+			kvm_vcpu_reload_pmu(vcpu);
 
 		if (kvm_check_request(KVM_REQ_RESYNC_PMU_EL0, vcpu))
 			kvm_vcpu_pmu_restore_guest(vcpu);
@@ -1319,6 +1318,21 @@ static bool kvm_vcpu_init_changed(struct kvm_vcpu *vcpu,
 			     KVM_VCPU_MAX_FEATURES);
 }
 
+static int kvm_setup_vcpu(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	int ret = 0;
+
+	/*
+	 * When the vCPU has a PMU, but no PMU is set for the guest
+	 * yet, set the default one.
+	 */
+	if (kvm_vcpu_has_pmu(vcpu) && !kvm->arch.arm_pmu)
+		ret = kvm_arm_set_default_pmu(kvm);
+
+	return ret;
+}
+
 static int __kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 				 const struct kvm_vcpu_init *init)
 {
@@ -1334,6 +1348,10 @@ static int __kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 
 	bitmap_copy(kvm->arch.vcpu_features, &features, KVM_VCPU_MAX_FEATURES);
 
+	ret = kvm_setup_vcpu(vcpu);
+	if (ret)
+		goto out_unlock;
+
 	/* Now we know what it is, we can reset it. */
 	kvm_reset_vcpu(vcpu);
 
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 845993bab9d2..fe99b3dab6ce 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -89,7 +89,7 @@ static bool kvm_pmc_is_64bit(struct kvm_pmc *pmc)
 
 static bool kvm_pmc_has_64bit_overflow(struct kvm_pmc *pmc)
 {
-	u64 val = __vcpu_sys_reg(kvm_pmc_to_vcpu(pmc), PMCR_EL0);
+	u64 val = kvm_vcpu_read_pmcr(kvm_pmc_to_vcpu(pmc));
 
 	return (pmc->idx < ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LP)) ||
 	       (pmc->idx == ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LC));
@@ -267,7 +267,7 @@ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
 {
-	u64 val = __vcpu_sys_reg(vcpu, PMCR_EL0) >> ARMV8_PMU_PMCR_N_SHIFT;
+	u64 val = kvm_vcpu_read_pmcr(vcpu) >> ARMV8_PMU_PMCR_N_SHIFT;
 
 	val &= ARMV8_PMU_PMCR_N_MASK;
 	if (val == 0)
@@ -289,7 +289,7 @@ void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 	if (!kvm_vcpu_has_pmu(vcpu))
 		return;
 
-	if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E) || !val)
+	if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) || !val)
 		return;
 
 	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
@@ -341,7 +341,7 @@ static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu)
 {
 	u64 reg = 0;
 
-	if ((__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E)) {
+	if ((kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E)) {
 		reg = __vcpu_sys_reg(vcpu, PMOVSSET_EL0);
 		reg &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
 		reg &= __vcpu_sys_reg(vcpu, PMINTENSET_EL1);
@@ -443,7 +443,7 @@ static void kvm_pmu_counter_increment(struct kvm_vcpu *vcpu,
 {
 	int i;
 
-	if (!(__vcpu_sys_reg(vcpu, PMCR_EL0) & ARMV8_PMU_PMCR_E))
+	if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E))
 		return;
 
 	/* Weed out disabled counters */
@@ -586,7 +586,7 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 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) &&
+	return (kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) &&
 	       (__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(pmc->idx));
 }
 
@@ -735,10 +735,9 @@ static struct arm_pmu *kvm_pmu_probe_armpmu(void)
 	 * It is still necessary to get a valid cpu, though, to probe for the
 	 * default PMU instance as userspace is not required to specify a PMU
 	 * type. In order to uphold the preexisting behavior KVM selects the
-	 * PMU instance for the core where the first call to the
-	 * KVM_ARM_VCPU_PMU_V3_CTRL attribute group occurs. A dependent use case
-	 * would be a user with disdain of all things big.LITTLE that affines
-	 * the VMM to a particular cluster of cores.
+	 * PMU instance for the core during vcpu init. A dependent use
+	 * case would be a user with disdain of all things big.LITTLE that
+	 * affines the VMM to a particular cluster of cores.
 	 *
 	 * In any case, userspace should just do the sane thing and use the UAPI
 	 * to select a PMU type directly. But, be wary of the baggage being
@@ -804,6 +803,17 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 	return val & mask;
 }
 
+void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu)
+{
+	u64 mask = kvm_pmu_valid_counter_mask(vcpu);
+
+	kvm_pmu_handle_pmcr(vcpu, kvm_vcpu_read_pmcr(vcpu));
+
+	__vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= mask;
+	__vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= mask;
+	__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= mask;
+}
+
 int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 {
 	if (!kvm_vcpu_has_pmu(vcpu))
@@ -892,6 +902,52 @@ static bool pmu_irq_is_valid(struct kvm *kvm, int irq)
 	return true;
 }
 
+/**
+ * kvm_arm_pmu_get_max_counters - Return the max number of PMU counters.
+ * @kvm: The kvm pointer
+ */
+u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm)
+{
+	struct arm_pmu *arm_pmu = kvm->arch.arm_pmu;
+
+	/*
+	 * The arm_pmu->num_events considers the cycle counter as well.
+	 * Ignore that and return only the general-purpose counters.
+	 */
+	return arm_pmu->num_events - 1;
+}
+
+static void kvm_arm_set_pmu(struct kvm *kvm, struct arm_pmu *arm_pmu)
+{
+	lockdep_assert_held(&kvm->arch.config_lock);
+
+	kvm->arch.arm_pmu = arm_pmu;
+	kvm->arch.pmcr_n = kvm_arm_pmu_get_max_counters(kvm);
+}
+
+/**
+ * kvm_arm_set_default_pmu - No PMU set, get the default one.
+ * @kvm: The kvm pointer
+ *
+ * The observant among you will notice that the supported_cpus
+ * mask does not get updated for the default PMU even though it
+ * is quite possible the selected instance supports only a
+ * subset of cores in the system. This is intentional, and
+ * upholds the preexisting behavior on heterogeneous systems
+ * where vCPUs can be scheduled on any core but the guest
+ * counters could stop working.
+ */
+int kvm_arm_set_default_pmu(struct kvm *kvm)
+{
+	struct arm_pmu *arm_pmu = kvm_pmu_probe_armpmu();
+
+	if (!arm_pmu)
+		return -ENODEV;
+
+	kvm_arm_set_pmu(kvm, arm_pmu);
+	return 0;
+}
+
 static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id)
 {
 	struct kvm *kvm = vcpu->kvm;
@@ -911,7 +967,7 @@ static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id)
 				break;
 			}
 
-			kvm->arch.arm_pmu = arm_pmu;
+			kvm_arm_set_pmu(kvm, arm_pmu);
 			cpumask_copy(kvm->arch.supported_cpus, &arm_pmu->supported_cpus);
 			ret = 0;
 			break;
@@ -934,23 +990,6 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 	if (vcpu->arch.pmu.created)
 		return -EBUSY;
 
-	if (!kvm->arch.arm_pmu) {
-		/*
-		 * No PMU set, get the default one.
-		 *
-		 * The observant among you will notice that the supported_cpus
-		 * mask does not get updated for the default PMU even though it
-		 * is quite possible the selected instance supports only a
-		 * subset of cores in the system. This is intentional, and
-		 * upholds the preexisting behavior on heterogeneous systems
-		 * where vCPUs can be scheduled on any core but the guest
-		 * counters could stop working.
-		 */
-		kvm->arch.arm_pmu = kvm_pmu_probe_armpmu();
-		if (!kvm->arch.arm_pmu)
-			return -ENODEV;
-	}
-
 	switch (attr->attr) {
 	case KVM_ARM_VCPU_PMU_V3_IRQ: {
 		int __user *uaddr = (int __user *)(long)attr->addr;
@@ -1090,3 +1129,15 @@ u8 kvm_arm_pmu_get_pmuver_limit(void)
 					      ID_AA64DFR0_EL1_PMUVer_V3P5);
 	return FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), tmp);
 }
+
+/**
+ * kvm_vcpu_read_pmcr - Read PMCR_EL0 register for the vCPU
+ * @vcpu: The vcpu pointer
+ */
+u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
+{
+	u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0) &
+			~(ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
+
+	return pmcr | ((u64)vcpu->kvm->arch.pmcr_n << ARMV8_PMU_PMCR_N_SHIFT);
+}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index d541ce9f48b9..1a21c526e5e2 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -719,14 +719,9 @@ static unsigned int pmu_visibility(const struct kvm_vcpu *vcpu,
 
 static u64 reset_pmu_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
-	u64 n, mask = BIT(ARMV8_PMU_CYCLE_IDX);
+	u64 mask = BIT(ARMV8_PMU_CYCLE_IDX);
+	u8 n = vcpu->kvm->arch.pmcr_n;
 
-	/* No PMU available, any PMU reg may UNDEF... */
-	if (!kvm_arm_support_pmu_v3())
-		return 0;
-
-	n = read_sysreg(pmcr_el0) >> ARMV8_PMU_PMCR_N_SHIFT;
-	n &= ARMV8_PMU_PMCR_N_MASK;
 	if (n)
 		mask |= GENMASK(n - 1, 0);
 
@@ -766,17 +761,15 @@ static u64 reset_pmselr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 
 static u64 reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
-	u64 pmcr;
-
-	/* No PMU available, PMCR_EL0 may UNDEF... */
-	if (!kvm_arm_support_pmu_v3())
-		return 0;
+	u64 pmcr = 0;
 
-	/* Only preserve PMCR_EL0.N, and reset the rest to 0 */
-	pmcr = read_sysreg(pmcr_el0) & (ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
 	if (!kvm_supports_32bit_el0())
 		pmcr |= ARMV8_PMU_PMCR_LC;
 
+	/*
+	 * The value of PMCR.N field is included when the
+	 * vCPU register is read via kvm_vcpu_read_pmcr().
+	 */
 	__vcpu_sys_reg(vcpu, r->reg) = pmcr;
 
 	return __vcpu_sys_reg(vcpu, r->reg);
@@ -826,7 +819,7 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		 * Only update writeable bits of PMCR (continuing into
 		 * kvm_pmu_handle_pmcr() as well)
 		 */
-		val = __vcpu_sys_reg(vcpu, PMCR_EL0);
+		val = kvm_vcpu_read_pmcr(vcpu);
 		val &= ~ARMV8_PMU_PMCR_MASK;
 		val |= p->regval & ARMV8_PMU_PMCR_MASK;
 		if (!kvm_supports_32bit_el0())
@@ -834,7 +827,7 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		kvm_pmu_handle_pmcr(vcpu, val);
 	} else {
 		/* PMCR.P & PMCR.C are RAZ */
-		val = __vcpu_sys_reg(vcpu, PMCR_EL0)
+		val = kvm_vcpu_read_pmcr(vcpu)
 		      & ~(ARMV8_PMU_PMCR_P | ARMV8_PMU_PMCR_C);
 		p->regval = val;
 	}
@@ -883,7 +876,7 @@ static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx)
 {
 	u64 pmcr, val;
 
-	pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0);
+	pmcr = kvm_vcpu_read_pmcr(vcpu);
 	val = (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
 	if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX) {
 		kvm_inject_undefined(vcpu);
@@ -998,6 +991,39 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	return true;
 }
 
+static int set_pmreg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val)
+{
+	bool set;
+
+	val &= kvm_pmu_valid_counter_mask(vcpu);
+
+	switch (r->reg) {
+	case PMOVSSET_EL0:
+		/* CRm[1] being set indicates a SET register, and CLR otherwise */
+		set = r->CRm & 2;
+		break;
+	default:
+		/* Op2[0] being set indicates a SET register, and CLR otherwise */
+		set = r->Op2 & 1;
+		break;
+	}
+
+	if (set)
+		__vcpu_sys_reg(vcpu, r->reg) |= val;
+	else
+		__vcpu_sys_reg(vcpu, r->reg) &= ~val;
+
+	return 0;
+}
+
+static int get_pmreg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 *val)
+{
+	u64 mask = kvm_pmu_valid_counter_mask(vcpu);
+
+	*val = __vcpu_sys_reg(vcpu, r->reg) & mask;
+	return 0;
+}
+
 static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 			   const struct sys_reg_desc *r)
 {
@@ -1107,6 +1133,51 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	return true;
 }
 
+static int get_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
+		    u64 *val)
+{
+	*val = kvm_vcpu_read_pmcr(vcpu);
+	return 0;
+}
+
+static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
+		    u64 val)
+{
+	u8 new_n = (val >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
+	struct kvm *kvm = vcpu->kvm;
+
+	mutex_lock(&kvm->arch.config_lock);
+
+	/*
+	 * The vCPU can't have more counters than the PMU hardware
+	 * implements. Ignore this error to maintain compatibility
+	 * with the existing KVM behavior.
+	 */
+	if (!kvm_vm_has_ran_once(kvm) &&
+	    new_n <= kvm_arm_pmu_get_max_counters(kvm))
+		kvm->arch.pmcr_n = new_n;
+
+	mutex_unlock(&kvm->arch.config_lock);
+
+	/*
+	 * Ignore writes to RES0 bits, read only bits that are cleared on
+	 * vCPU reset, and writable bits that KVM doesn't support yet.
+	 * (i.e. only PMCR.N and bits [7:0] are mutable from userspace)
+	 * The LP bit is RES0 when FEAT_PMUv3p5 is not supported on the vCPU.
+	 * But, we leave the bit as it is here, as the vCPU's PMUver might
+	 * be changed later (NOTE: the bit will be cleared on first vCPU run
+	 * if necessary).
+	 */
+	val &= ARMV8_PMU_PMCR_MASK;
+
+	/* The LC bit is RES1 when AArch32 is not supported */
+	if (!kvm_supports_32bit_el0())
+		val |= ARMV8_PMU_PMCR_LC;
+
+	__vcpu_sys_reg(vcpu, r->reg) = val;
+	return 0;
+}
+
 /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
 #define DBG_BCR_BVR_WCR_WVR_EL1(n)					\
 	{ SYS_DESC(SYS_DBGBVRn_EL1(n)),					\
@@ -2188,9 +2259,11 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	/* PMBIDR_EL1 is not trapped */
 
 	{ PMU_SYS_REG(PMINTENSET_EL1),
-	  .access = access_pminten, .reg = PMINTENSET_EL1 },
+	  .access = access_pminten, .reg = PMINTENSET_EL1,
+	  .get_user = get_pmreg, .set_user = set_pmreg },
 	{ PMU_SYS_REG(PMINTENCLR_EL1),
-	  .access = access_pminten, .reg = PMINTENSET_EL1 },
+	  .access = access_pminten, .reg = PMINTENSET_EL1,
+	  .get_user = get_pmreg, .set_user = set_pmreg },
 	{ SYS_DESC(SYS_PMMIR_EL1), trap_raz_wi },
 
 	{ SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 },
@@ -2238,14 +2311,17 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_CTR_EL0), access_ctr },
 	{ SYS_DESC(SYS_SVCR), undef_access },
 
-	{ PMU_SYS_REG(PMCR_EL0), .access = access_pmcr,
-	  .reset = reset_pmcr, .reg = PMCR_EL0 },
+	{ PMU_SYS_REG(PMCR_EL0), .access = access_pmcr, .reset = reset_pmcr,
+	  .reg = PMCR_EL0, .get_user = get_pmcr, .set_user = set_pmcr },
 	{ PMU_SYS_REG(PMCNTENSET_EL0),
-	  .access = access_pmcnten, .reg = PMCNTENSET_EL0 },
+	  .access = access_pmcnten, .reg = PMCNTENSET_EL0,
+	  .get_user = get_pmreg, .set_user = set_pmreg },
 	{ PMU_SYS_REG(PMCNTENCLR_EL0),
-	  .access = access_pmcnten, .reg = PMCNTENSET_EL0 },
+	  .access = access_pmcnten, .reg = PMCNTENSET_EL0,
+	  .get_user = get_pmreg, .set_user = set_pmreg },
 	{ PMU_SYS_REG(PMOVSCLR_EL0),
-	  .access = access_pmovs, .reg = PMOVSSET_EL0 },
+	  .access = access_pmovs, .reg = PMOVSSET_EL0,
+	  .get_user = get_pmreg, .set_user = set_pmreg },
 	/*
 	 * PM_SWINC_EL0 is exposed to userspace as RAZ/WI, as it was
 	 * previously (and pointlessly) advertised in the past...
@@ -2273,7 +2349,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ PMU_SYS_REG(PMUSERENR_EL0), .access = access_pmuserenr,
 	  .reset = reset_val, .reg = PMUSERENR_EL0, .val = 0 },
 	{ PMU_SYS_REG(PMOVSSET_EL0),
-	  .access = access_pmovs, .reg = PMOVSSET_EL0 },
+	  .access = access_pmovs, .reg = PMOVSSET_EL0,
+	  .get_user = get_pmreg, .set_user = set_pmreg },
 
 	{ SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
 	{ SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 },
diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 4df71290b676..4b9d8fb393a8 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -13,7 +13,6 @@
 #define ARMV8_PMU_CYCLE_IDX		(ARMV8_PMU_MAX_COUNTERS - 1)
 
 #if IS_ENABLED(CONFIG_HW_PERF_EVENTS) && IS_ENABLED(CONFIG_KVM)
-
 struct kvm_pmc {
 	u8 idx;	/* index into the pmu->pmc array */
 	struct perf_event *perf_event;
@@ -63,6 +62,7 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 				    u64 select_idx);
+void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu);
 int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
 int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu,
@@ -102,7 +102,10 @@ void kvm_vcpu_pmu_resync_el0(void);
 
 u8 kvm_arm_pmu_get_pmuver_limit(void);
 u64 kvm_pmu_evtyper_mask(struct kvm *kvm);
+int kvm_arm_set_default_pmu(struct kvm *kvm);
+u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm);
 
+u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu);
 #else
 struct kvm_pmu {
 };
@@ -169,6 +172,7 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 static inline void kvm_pmu_update_vcpu_events(struct kvm_vcpu *vcpu) {}
 static inline void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu) {}
 static inline void kvm_vcpu_pmu_restore_host(struct kvm_vcpu *vcpu) {}
+static inline void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu) {}
 static inline u8 kvm_arm_pmu_get_pmuver_limit(void)
 {
 	return 0;
@@ -179,6 +183,21 @@ static inline u64 kvm_pmu_evtyper_mask(struct kvm *kvm)
 }
 static inline void kvm_vcpu_pmu_resync_el0(void) {}
 
+static inline int kvm_arm_set_default_pmu(struct kvm *kvm)
+{
+	return -ENODEV;
+}
+
+static inline u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm)
+{
+	return 0;
+}
+
+static inline u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
 #endif
 
 #endif
diff --git a/tools/include/perf/arm_pmuv3.h b/tools/include/perf/arm_pmuv3.h
new file mode 100644
index 000000000000..e822d49fb5b8
--- /dev/null
+++ b/tools/include/perf/arm_pmuv3.h
@@ -0,0 +1,308 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ */
+
+#ifndef __PERF_ARM_PMUV3_H
+#define __PERF_ARM_PMUV3_H
+
+#include <assert.h>
+#include <asm/bug.h>
+
+#define ARMV8_PMU_MAX_COUNTERS	32
+#define ARMV8_PMU_COUNTER_MASK	(ARMV8_PMU_MAX_COUNTERS - 1)
+
+/*
+ * Common architectural and microarchitectural event numbers.
+ */
+#define ARMV8_PMUV3_PERFCTR_SW_INCR				0x0000
+#define ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL			0x0001
+#define ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL			0x0002
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL			0x0003
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE				0x0004
+#define ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL			0x0005
+#define ARMV8_PMUV3_PERFCTR_LD_RETIRED				0x0006
+#define ARMV8_PMUV3_PERFCTR_ST_RETIRED				0x0007
+#define ARMV8_PMUV3_PERFCTR_INST_RETIRED			0x0008
+#define ARMV8_PMUV3_PERFCTR_EXC_TAKEN				0x0009
+#define ARMV8_PMUV3_PERFCTR_EXC_RETURN				0x000A
+#define ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED			0x000B
+#define ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED			0x000C
+#define ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED			0x000D
+#define ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED			0x000E
+#define ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED		0x000F
+#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED				0x0010
+#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES				0x0011
+#define ARMV8_PMUV3_PERFCTR_BR_PRED				0x0012
+#define ARMV8_PMUV3_PERFCTR_MEM_ACCESS				0x0013
+#define ARMV8_PMUV3_PERFCTR_L1I_CACHE				0x0014
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB			0x0015
+#define ARMV8_PMUV3_PERFCTR_L2D_CACHE				0x0016
+#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL			0x0017
+#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB			0x0018
+#define ARMV8_PMUV3_PERFCTR_BUS_ACCESS				0x0019
+#define ARMV8_PMUV3_PERFCTR_MEMORY_ERROR			0x001A
+#define ARMV8_PMUV3_PERFCTR_INST_SPEC				0x001B
+#define ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED			0x001C
+#define ARMV8_PMUV3_PERFCTR_BUS_CYCLES				0x001D
+#define ARMV8_PMUV3_PERFCTR_CHAIN				0x001E
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE			0x001F
+#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE			0x0020
+#define ARMV8_PMUV3_PERFCTR_BR_RETIRED				0x0021
+#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED			0x0022
+#define ARMV8_PMUV3_PERFCTR_STALL_FRONTEND			0x0023
+#define ARMV8_PMUV3_PERFCTR_STALL_BACKEND			0x0024
+#define ARMV8_PMUV3_PERFCTR_L1D_TLB				0x0025
+#define ARMV8_PMUV3_PERFCTR_L1I_TLB				0x0026
+#define ARMV8_PMUV3_PERFCTR_L2I_CACHE				0x0027
+#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL			0x0028
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE			0x0029
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL			0x002A
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE				0x002B
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB			0x002C
+#define ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL			0x002D
+#define ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL			0x002E
+#define ARMV8_PMUV3_PERFCTR_L2D_TLB				0x002F
+#define ARMV8_PMUV3_PERFCTR_L2I_TLB				0x0030
+#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS			0x0031
+#define ARMV8_PMUV3_PERFCTR_LL_CACHE				0x0032
+#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS			0x0033
+#define ARMV8_PMUV3_PERFCTR_DTLB_WALK				0x0034
+#define ARMV8_PMUV3_PERFCTR_ITLB_WALK				0x0035
+#define ARMV8_PMUV3_PERFCTR_LL_CACHE_RD				0x0036
+#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD			0x0037
+#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD			0x0038
+#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_LMISS_RD			0x0039
+#define ARMV8_PMUV3_PERFCTR_OP_RETIRED				0x003A
+#define ARMV8_PMUV3_PERFCTR_OP_SPEC				0x003B
+#define ARMV8_PMUV3_PERFCTR_STALL				0x003C
+#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND			0x003D
+#define ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND			0x003E
+#define ARMV8_PMUV3_PERFCTR_STALL_SLOT				0x003F
+
+/* Statistical profiling extension microarchitectural events */
+#define ARMV8_SPE_PERFCTR_SAMPLE_POP				0x4000
+#define ARMV8_SPE_PERFCTR_SAMPLE_FEED				0x4001
+#define ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE			0x4002
+#define ARMV8_SPE_PERFCTR_SAMPLE_COLLISION			0x4003
+
+/* AMUv1 architecture events */
+#define ARMV8_AMU_PERFCTR_CNT_CYCLES				0x4004
+#define ARMV8_AMU_PERFCTR_STALL_BACKEND_MEM			0x4005
+
+/* long-latency read miss events */
+#define ARMV8_PMUV3_PERFCTR_L1I_CACHE_LMISS			0x4006
+#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_LMISS_RD			0x4009
+#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_LMISS			0x400A
+#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_LMISS_RD			0x400B
+
+/* Trace buffer events */
+#define ARMV8_PMUV3_PERFCTR_TRB_WRAP				0x400C
+#define ARMV8_PMUV3_PERFCTR_TRB_TRIG				0x400E
+
+/* Trace unit events */
+#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT0				0x4010
+#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT1				0x4011
+#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT2				0x4012
+#define ARMV8_PMUV3_PERFCTR_TRCEXTOUT3				0x4013
+#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT4			0x4018
+#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT5			0x4019
+#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT6			0x401A
+#define ARMV8_PMUV3_PERFCTR_CTI_TRIGOUT7			0x401B
+
+/* additional latency from alignment events */
+#define ARMV8_PMUV3_PERFCTR_LDST_ALIGN_LAT			0x4020
+#define ARMV8_PMUV3_PERFCTR_LD_ALIGN_LAT			0x4021
+#define ARMV8_PMUV3_PERFCTR_ST_ALIGN_LAT			0x4022
+
+/* Armv8.5 Memory Tagging Extension events */
+#define ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED			0x4024
+#define ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_RD			0x4025
+#define ARMV8_MTE_PERFCTR_MEM_ACCESS_CHECKED_WR			0x4026
+
+/* ARMv8 recommended implementation defined event types */
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD			0x0040
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR			0x0041
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD		0x0042
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR		0x0043
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_INNER		0x0044
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_OUTER		0x0045
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_VICTIM		0x0046
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_CLEAN			0x0047
+#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_INVAL			0x0048
+
+#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD			0x004C
+#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR			0x004D
+#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD				0x004E
+#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR				0x004F
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_RD			0x0050
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WR			0x0051
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_RD		0x0052
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_WR		0x0053
+
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_VICTIM		0x0056
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_CLEAN			0x0057
+#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_INVAL			0x0058
+
+#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_RD			0x005C
+#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_WR			0x005D
+#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_RD				0x005E
+#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_WR				0x005F
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD			0x0060
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR			0x0061
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_SHARED			0x0062
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NOT_SHARED		0x0063
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NORMAL			0x0064
+#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_PERIPH			0x0065
+#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_RD			0x0066
+#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_WR			0x0067
+#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LD_SPEC			0x0068
+#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_ST_SPEC			0x0069
+#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LDST_SPEC		0x006A
+
+#define ARMV8_IMPDEF_PERFCTR_LDREX_SPEC				0x006C
+#define ARMV8_IMPDEF_PERFCTR_STREX_PASS_SPEC			0x006D
+#define ARMV8_IMPDEF_PERFCTR_STREX_FAIL_SPEC			0x006E
+#define ARMV8_IMPDEF_PERFCTR_STREX_SPEC				0x006F
+#define ARMV8_IMPDEF_PERFCTR_LD_SPEC				0x0070
+#define ARMV8_IMPDEF_PERFCTR_ST_SPEC				0x0071
+#define ARMV8_IMPDEF_PERFCTR_LDST_SPEC				0x0072
+#define ARMV8_IMPDEF_PERFCTR_DP_SPEC				0x0073
+#define ARMV8_IMPDEF_PERFCTR_ASE_SPEC				0x0074
+#define ARMV8_IMPDEF_PERFCTR_VFP_SPEC				0x0075
+#define ARMV8_IMPDEF_PERFCTR_PC_WRITE_SPEC			0x0076
+#define ARMV8_IMPDEF_PERFCTR_CRYPTO_SPEC			0x0077
+#define ARMV8_IMPDEF_PERFCTR_BR_IMMED_SPEC			0x0078
+#define ARMV8_IMPDEF_PERFCTR_BR_RETURN_SPEC			0x0079
+#define ARMV8_IMPDEF_PERFCTR_BR_INDIRECT_SPEC			0x007A
+
+#define ARMV8_IMPDEF_PERFCTR_ISB_SPEC				0x007C
+#define ARMV8_IMPDEF_PERFCTR_DSB_SPEC				0x007D
+#define ARMV8_IMPDEF_PERFCTR_DMB_SPEC				0x007E
+
+#define ARMV8_IMPDEF_PERFCTR_EXC_UNDEF				0x0081
+#define ARMV8_IMPDEF_PERFCTR_EXC_SVC				0x0082
+#define ARMV8_IMPDEF_PERFCTR_EXC_PABORT				0x0083
+#define ARMV8_IMPDEF_PERFCTR_EXC_DABORT				0x0084
+
+#define ARMV8_IMPDEF_PERFCTR_EXC_IRQ				0x0086
+#define ARMV8_IMPDEF_PERFCTR_EXC_FIQ				0x0087
+#define ARMV8_IMPDEF_PERFCTR_EXC_SMC				0x0088
+
+#define ARMV8_IMPDEF_PERFCTR_EXC_HVC				0x008A
+#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_PABORT			0x008B
+#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_DABORT			0x008C
+#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_OTHER			0x008D
+#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_IRQ			0x008E
+#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_FIQ			0x008F
+#define ARMV8_IMPDEF_PERFCTR_RC_LD_SPEC				0x0090
+#define ARMV8_IMPDEF_PERFCTR_RC_ST_SPEC				0x0091
+
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_RD			0x00A0
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WR			0x00A1
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_RD		0x00A2
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_WR		0x00A3
+
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_VICTIM		0x00A6
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_CLEAN			0x00A7
+#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_INVAL			0x00A8
+
+/*
+ * Per-CPU PMCR: config reg
+ */
+#define ARMV8_PMU_PMCR_E	(1 << 0) /* Enable all counters */
+#define ARMV8_PMU_PMCR_P	(1 << 1) /* Reset all counters */
+#define ARMV8_PMU_PMCR_C	(1 << 2) /* Cycle counter reset */
+#define ARMV8_PMU_PMCR_D	(1 << 3) /* CCNT counts every 64th cpu cycle */
+#define ARMV8_PMU_PMCR_X	(1 << 4) /* Export to ETM */
+#define ARMV8_PMU_PMCR_DP	(1 << 5) /* Disable CCNT if non-invasive debug*/
+#define ARMV8_PMU_PMCR_LC	(1 << 6) /* Overflow on 64 bit cycle counter */
+#define ARMV8_PMU_PMCR_LP	(1 << 7) /* Long event counter enable */
+#define ARMV8_PMU_PMCR_N_SHIFT	11  /* Number of counters supported */
+#define ARMV8_PMU_PMCR_N_MASK	0x1f
+#define ARMV8_PMU_PMCR_MASK	0xff    /* Mask for writable bits */
+
+/*
+ * PMOVSR: counters overflow flag status reg
+ */
+#define ARMV8_PMU_OVSR_MASK		0xffffffff	/* Mask for writable bits */
+#define ARMV8_PMU_OVERFLOWED_MASK	ARMV8_PMU_OVSR_MASK
+
+/*
+ * PMXEVTYPER: Event selection reg
+ */
+#define ARMV8_PMU_EVTYPE_MASK	0xc800ffff	/* Mask for writable bits */
+#define ARMV8_PMU_EVTYPE_EVENT	0xffff		/* Mask for EVENT bits */
+
+/*
+ * Event filters for PMUv3
+ */
+#define ARMV8_PMU_EXCLUDE_EL1	(1U << 31)
+#define ARMV8_PMU_EXCLUDE_EL0	(1U << 30)
+#define ARMV8_PMU_INCLUDE_EL2	(1U << 27)
+
+/*
+ * PMUSERENR: user enable reg
+ */
+#define ARMV8_PMU_USERENR_MASK	0xf		/* Mask for writable bits */
+#define ARMV8_PMU_USERENR_EN	(1 << 0) /* PMU regs can be accessed at EL0 */
+#define ARMV8_PMU_USERENR_SW	(1 << 1) /* PMSWINC can be written at EL0 */
+#define ARMV8_PMU_USERENR_CR	(1 << 2) /* Cycle counter can be read at EL0 */
+#define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
+
+/* PMMIR_EL1.SLOTS mask */
+#define ARMV8_PMU_SLOTS_MASK	0xff
+
+#define ARMV8_PMU_BUS_SLOTS_SHIFT 8
+#define ARMV8_PMU_BUS_SLOTS_MASK 0xff
+#define ARMV8_PMU_BUS_WIDTH_SHIFT 16
+#define ARMV8_PMU_BUS_WIDTH_MASK 0xf
+
+/*
+ * This code is really good
+ */
+
+#define PMEVN_CASE(n, case_macro) \
+	case n: case_macro(n); break
+
+#define PMEVN_SWITCH(x, case_macro)				\
+	do {							\
+		switch (x) {					\
+		PMEVN_CASE(0,  case_macro);			\
+		PMEVN_CASE(1,  case_macro);			\
+		PMEVN_CASE(2,  case_macro);			\
+		PMEVN_CASE(3,  case_macro);			\
+		PMEVN_CASE(4,  case_macro);			\
+		PMEVN_CASE(5,  case_macro);			\
+		PMEVN_CASE(6,  case_macro);			\
+		PMEVN_CASE(7,  case_macro);			\
+		PMEVN_CASE(8,  case_macro);			\
+		PMEVN_CASE(9,  case_macro);			\
+		PMEVN_CASE(10, case_macro);			\
+		PMEVN_CASE(11, case_macro);			\
+		PMEVN_CASE(12, case_macro);			\
+		PMEVN_CASE(13, case_macro);			\
+		PMEVN_CASE(14, case_macro);			\
+		PMEVN_CASE(15, case_macro);			\
+		PMEVN_CASE(16, case_macro);			\
+		PMEVN_CASE(17, case_macro);			\
+		PMEVN_CASE(18, case_macro);			\
+		PMEVN_CASE(19, case_macro);			\
+		PMEVN_CASE(20, case_macro);			\
+		PMEVN_CASE(21, case_macro);			\
+		PMEVN_CASE(22, case_macro);			\
+		PMEVN_CASE(23, case_macro);			\
+		PMEVN_CASE(24, case_macro);			\
+		PMEVN_CASE(25, case_macro);			\
+		PMEVN_CASE(26, case_macro);			\
+		PMEVN_CASE(27, case_macro);			\
+		PMEVN_CASE(28, case_macro);			\
+		PMEVN_CASE(29, case_macro);			\
+		PMEVN_CASE(30, case_macro);			\
+		default:					\
+			WARN(1, "Invalid PMEV* index\n");	\
+			assert(0);				\
+		}						\
+	} while (0)
+
+#endif
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 4de096bbf124..04dfbf06b51e 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -159,6 +159,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/smccc_filter
 TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
 TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq
+TEST_GEN_PROGS_aarch64 += aarch64/vpmu_counter_access
 TEST_GEN_PROGS_aarch64 += access_tracking_perf_test
 TEST_GEN_PROGS_aarch64 += demand_paging_test
 TEST_GEN_PROGS_aarch64 += dirty_log_test
diff --git a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
new file mode 100644
index 000000000000..5ea78986e665
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c
@@ -0,0 +1,670 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vpmu_counter_access - Test vPMU event counter access
+ *
+ * Copyright (c) 2023 Google LLC.
+ *
+ * This test checks if the guest can see the same number of the PMU event
+ * counters (PMCR_EL0.N) that userspace sets, if the guest can access
+ * those counters, and if the guest is prevented from accessing any
+ * other counters.
+ * It also checks if the userspace accesses to the PMU regsisters honor the
+ * PMCR.N value that's set for the guest.
+ * This test runs only when KVM_CAP_ARM_PMU_V3 is supported on the host.
+ */
+#include <kvm_util.h>
+#include <processor.h>
+#include <test_util.h>
+#include <vgic.h>
+#include <perf/arm_pmuv3.h>
+#include <linux/bitfield.h>
+
+/* The max number of the PMU event counters (excluding the cycle counter) */
+#define ARMV8_PMU_MAX_GENERAL_COUNTERS	(ARMV8_PMU_MAX_COUNTERS - 1)
+
+/* The cycle counter bit position that's common among the PMU registers */
+#define ARMV8_PMU_CYCLE_IDX		31
+
+struct vpmu_vm {
+	struct kvm_vm *vm;
+	struct kvm_vcpu *vcpu;
+	int gic_fd;
+};
+
+static struct vpmu_vm vpmu_vm;
+
+struct pmreg_sets {
+	uint64_t set_reg_id;
+	uint64_t clr_reg_id;
+};
+
+#define PMREG_SET(set, clr) {.set_reg_id = set, .clr_reg_id = clr}
+
+static uint64_t get_pmcr_n(uint64_t pmcr)
+{
+	return (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
+}
+
+static void set_pmcr_n(uint64_t *pmcr, uint64_t pmcr_n)
+{
+	*pmcr = *pmcr & ~(ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT);
+	*pmcr |= (pmcr_n << ARMV8_PMU_PMCR_N_SHIFT);
+}
+
+static uint64_t get_counters_mask(uint64_t n)
+{
+	uint64_t mask = BIT(ARMV8_PMU_CYCLE_IDX);
+
+	if (n)
+		mask |= GENMASK(n - 1, 0);
+	return mask;
+}
+
+/* Read PMEVTCNTR<n>_EL0 through PMXEVCNTR_EL0 */
+static inline unsigned long read_sel_evcntr(int sel)
+{
+	write_sysreg(sel, pmselr_el0);
+	isb();
+	return read_sysreg(pmxevcntr_el0);
+}
+
+/* Write PMEVTCNTR<n>_EL0 through PMXEVCNTR_EL0 */
+static inline void write_sel_evcntr(int sel, unsigned long val)
+{
+	write_sysreg(sel, pmselr_el0);
+	isb();
+	write_sysreg(val, pmxevcntr_el0);
+	isb();
+}
+
+/* Read PMEVTYPER<n>_EL0 through PMXEVTYPER_EL0 */
+static inline unsigned long read_sel_evtyper(int sel)
+{
+	write_sysreg(sel, pmselr_el0);
+	isb();
+	return read_sysreg(pmxevtyper_el0);
+}
+
+/* Write PMEVTYPER<n>_EL0 through PMXEVTYPER_EL0 */
+static inline void write_sel_evtyper(int sel, unsigned long val)
+{
+	write_sysreg(sel, pmselr_el0);
+	isb();
+	write_sysreg(val, pmxevtyper_el0);
+	isb();
+}
+
+static inline void enable_counter(int idx)
+{
+	uint64_t v = read_sysreg(pmcntenset_el0);
+
+	write_sysreg(BIT(idx) | v, pmcntenset_el0);
+	isb();
+}
+
+static inline void disable_counter(int idx)
+{
+	uint64_t v = read_sysreg(pmcntenset_el0);
+
+	write_sysreg(BIT(idx) | v, pmcntenclr_el0);
+	isb();
+}
+
+static void pmu_disable_reset(void)
+{
+	uint64_t pmcr = read_sysreg(pmcr_el0);
+
+	/* Reset all counters, disabling them */
+	pmcr &= ~ARMV8_PMU_PMCR_E;
+	write_sysreg(pmcr | ARMV8_PMU_PMCR_P, pmcr_el0);
+	isb();
+}
+
+#define RETURN_READ_PMEVCNTRN(n) \
+	return read_sysreg(pmevcntr##n##_el0)
+static unsigned long read_pmevcntrn(int n)
+{
+	PMEVN_SWITCH(n, RETURN_READ_PMEVCNTRN);
+	return 0;
+}
+
+#define WRITE_PMEVCNTRN(n) \
+	write_sysreg(val, pmevcntr##n##_el0)
+static void write_pmevcntrn(int n, unsigned long val)
+{
+	PMEVN_SWITCH(n, WRITE_PMEVCNTRN);
+	isb();
+}
+
+#define READ_PMEVTYPERN(n) \
+	return read_sysreg(pmevtyper##n##_el0)
+static unsigned long read_pmevtypern(int n)
+{
+	PMEVN_SWITCH(n, READ_PMEVTYPERN);
+	return 0;
+}
+
+#define WRITE_PMEVTYPERN(n) \
+	write_sysreg(val, pmevtyper##n##_el0)
+static void write_pmevtypern(int n, unsigned long val)
+{
+	PMEVN_SWITCH(n, WRITE_PMEVTYPERN);
+	isb();
+}
+
+/*
+ * The pmc_accessor structure has pointers to PMEV{CNTR,TYPER}<n>_EL0
+ * accessors that test cases will use. Each of the accessors will
+ * either directly reads/writes PMEV{CNTR,TYPER}<n>_EL0
+ * (i.e. {read,write}_pmev{cnt,type}rn()), or reads/writes them through
+ * PMXEV{CNTR,TYPER}_EL0 (i.e. {read,write}_sel_ev{cnt,type}r()).
+ *
+ * This is used to test that combinations of those accessors provide
+ * the consistent behavior.
+ */
+struct pmc_accessor {
+	/* A function to be used to read PMEVTCNTR<n>_EL0 */
+	unsigned long	(*read_cntr)(int idx);
+	/* A function to be used to write PMEVTCNTR<n>_EL0 */
+	void		(*write_cntr)(int idx, unsigned long val);
+	/* A function to be used to read PMEVTYPER<n>_EL0 */
+	unsigned long	(*read_typer)(int idx);
+	/* A function to be used to write PMEVTYPER<n>_EL0 */
+	void		(*write_typer)(int idx, unsigned long val);
+};
+
+struct pmc_accessor pmc_accessors[] = {
+	/* test with all direct accesses */
+	{ read_pmevcntrn, write_pmevcntrn, read_pmevtypern, write_pmevtypern },
+	/* test with all indirect accesses */
+	{ read_sel_evcntr, write_sel_evcntr, read_sel_evtyper, write_sel_evtyper },
+	/* read with direct accesses, and write with indirect accesses */
+	{ read_pmevcntrn, write_sel_evcntr, read_pmevtypern, write_sel_evtyper },
+	/* read with indirect accesses, and write with direct accesses */
+	{ read_sel_evcntr, write_pmevcntrn, read_sel_evtyper, write_pmevtypern },
+};
+
+/*
+ * Convert a pointer of pmc_accessor to an index in pmc_accessors[],
+ * assuming that the pointer is one of the entries in pmc_accessors[].
+ */
+#define PMC_ACC_TO_IDX(acc)	(acc - &pmc_accessors[0])
+
+#define GUEST_ASSERT_BITMAP_REG(regname, mask, set_expected)			 \
+{										 \
+	uint64_t _tval = read_sysreg(regname);					 \
+										 \
+	if (set_expected)							 \
+		__GUEST_ASSERT((_tval & mask),					 \
+				"tval: 0x%lx; mask: 0x%lx; set_expected: 0x%lx", \
+				_tval, mask, set_expected);			 \
+	else									 \
+		__GUEST_ASSERT(!(_tval & mask),					 \
+				"tval: 0x%lx; mask: 0x%lx; set_expected: 0x%lx", \
+				_tval, mask, set_expected);			 \
+}
+
+/*
+ * Check if @mask bits in {PMCNTEN,PMINTEN,PMOVS}{SET,CLR} registers
+ * are set or cleared as specified in @set_expected.
+ */
+static void check_bitmap_pmu_regs(uint64_t mask, bool set_expected)
+{
+	GUEST_ASSERT_BITMAP_REG(pmcntenset_el0, mask, set_expected);
+	GUEST_ASSERT_BITMAP_REG(pmcntenclr_el0, mask, set_expected);
+	GUEST_ASSERT_BITMAP_REG(pmintenset_el1, mask, set_expected);
+	GUEST_ASSERT_BITMAP_REG(pmintenclr_el1, mask, set_expected);
+	GUEST_ASSERT_BITMAP_REG(pmovsset_el0, mask, set_expected);
+	GUEST_ASSERT_BITMAP_REG(pmovsclr_el0, mask, set_expected);
+}
+
+/*
+ * Check if the bit in {PMCNTEN,PMINTEN,PMOVS}{SET,CLR} registers corresponding
+ * to the specified counter (@pmc_idx) can be read/written as expected.
+ * When @set_op is true, it tries to set the bit for the counter in
+ * those registers by writing the SET registers (the bit won't be set
+ * if the counter is not implemented though).
+ * Otherwise, it tries to clear the bits in the registers by writing
+ * the CLR registers.
+ * Then, it checks if the values indicated in the registers are as expected.
+ */
+static void test_bitmap_pmu_regs(int pmc_idx, bool set_op)
+{
+	uint64_t pmcr_n, test_bit = BIT(pmc_idx);
+	bool set_expected = false;
+
+	if (set_op) {
+		write_sysreg(test_bit, pmcntenset_el0);
+		write_sysreg(test_bit, pmintenset_el1);
+		write_sysreg(test_bit, pmovsset_el0);
+
+		/* The bit will be set only if the counter is implemented */
+		pmcr_n = get_pmcr_n(read_sysreg(pmcr_el0));
+		set_expected = (pmc_idx < pmcr_n) ? true : false;
+	} else {
+		write_sysreg(test_bit, pmcntenclr_el0);
+		write_sysreg(test_bit, pmintenclr_el1);
+		write_sysreg(test_bit, pmovsclr_el0);
+	}
+	check_bitmap_pmu_regs(test_bit, set_expected);
+}
+
+/*
+ * Tests for reading/writing registers for the (implemented) event counter
+ * specified by @pmc_idx.
+ */
+static void test_access_pmc_regs(struct pmc_accessor *acc, int pmc_idx)
+{
+	uint64_t write_data, read_data;
+
+	/* Disable all PMCs and reset all PMCs to zero. */
+	pmu_disable_reset();
+
+	/*
+	 * Tests for reading/writing {PMCNTEN,PMINTEN,PMOVS}{SET,CLR}_EL1.
+	 */
+
+	/* Make sure that the bit in those registers are set to 0 */
+	test_bitmap_pmu_regs(pmc_idx, false);
+	/* Test if setting the bit in those registers works */
+	test_bitmap_pmu_regs(pmc_idx, true);
+	/* Test if clearing the bit in those registers works */
+	test_bitmap_pmu_regs(pmc_idx, false);
+
+	/*
+	 * Tests for reading/writing the event type register.
+	 */
+
+	/*
+	 * Set the event type register to an arbitrary value just for testing
+	 * of reading/writing the register.
+	 * Arm ARM says that for the event from 0x0000 to 0x003F,
+	 * the value indicated in the PMEVTYPER<n>_EL0.evtCount field is
+	 * the value written to the field even when the specified event
+	 * is not supported.
+	 */
+	write_data = (ARMV8_PMU_EXCLUDE_EL1 | ARMV8_PMUV3_PERFCTR_INST_RETIRED);
+	acc->write_typer(pmc_idx, write_data);
+	read_data = acc->read_typer(pmc_idx);
+	__GUEST_ASSERT(read_data == write_data,
+		       "pmc_idx: 0x%lx; acc_idx: 0x%lx; read_data: 0x%lx; write_data: 0x%lx",
+		       pmc_idx, PMC_ACC_TO_IDX(acc), read_data, write_data);
+
+	/*
+	 * Tests for reading/writing the event count register.
+	 */
+
+	read_data = acc->read_cntr(pmc_idx);
+
+	/* The count value must be 0, as it is disabled and reset */
+	__GUEST_ASSERT(read_data == 0,
+		       "pmc_idx: 0x%lx; acc_idx: 0x%lx; read_data: 0x%lx",
+		       pmc_idx, PMC_ACC_TO_IDX(acc), read_data);
+
+	write_data = read_data + pmc_idx + 0x12345;
+	acc->write_cntr(pmc_idx, write_data);
+	read_data = acc->read_cntr(pmc_idx);
+	__GUEST_ASSERT(read_data == write_data,
+		       "pmc_idx: 0x%lx; acc_idx: 0x%lx; read_data: 0x%lx; write_data: 0x%lx",
+		       pmc_idx, PMC_ACC_TO_IDX(acc), read_data, write_data);
+}
+
+#define INVALID_EC	(-1ul)
+uint64_t expected_ec = INVALID_EC;
+
+static void guest_sync_handler(struct ex_regs *regs)
+{
+	uint64_t esr, ec;
+
+	esr = read_sysreg(esr_el1);
+	ec = (esr >> ESR_EC_SHIFT) & ESR_EC_MASK;
+
+	__GUEST_ASSERT(expected_ec == ec,
+			"PC: 0x%lx; ESR: 0x%lx; EC: 0x%lx; EC expected: 0x%lx",
+			regs->pc, esr, ec, expected_ec);
+
+	/* skip the trapping instruction */
+	regs->pc += 4;
+
+	/* Use INVALID_EC to indicate an exception occurred */
+	expected_ec = INVALID_EC;
+}
+
+/*
+ * Run the given operation that should trigger an exception with the
+ * given exception class. The exception handler (guest_sync_handler)
+ * will reset op_end_addr to 0, expected_ec to INVALID_EC, and skip
+ * the instruction that trapped.
+ */
+#define TEST_EXCEPTION(ec, ops)				\
+({							\
+	GUEST_ASSERT(ec != INVALID_EC);			\
+	WRITE_ONCE(expected_ec, ec);			\
+	dsb(ish);					\
+	ops;						\
+	GUEST_ASSERT(expected_ec == INVALID_EC);	\
+})
+
+/*
+ * Tests for reading/writing registers for the unimplemented event counter
+ * specified by @pmc_idx (>= PMCR_EL0.N).
+ */
+static void test_access_invalid_pmc_regs(struct pmc_accessor *acc, int pmc_idx)
+{
+	/*
+	 * Reading/writing the event count/type registers should cause
+	 * an UNDEFINED exception.
+	 */
+	TEST_EXCEPTION(ESR_EC_UNKNOWN, acc->read_cntr(pmc_idx));
+	TEST_EXCEPTION(ESR_EC_UNKNOWN, acc->write_cntr(pmc_idx, 0));
+	TEST_EXCEPTION(ESR_EC_UNKNOWN, acc->read_typer(pmc_idx));
+	TEST_EXCEPTION(ESR_EC_UNKNOWN, acc->write_typer(pmc_idx, 0));
+	/*
+	 * The bit corresponding to the (unimplemented) counter in
+	 * {PMCNTEN,PMINTEN,PMOVS}{SET,CLR} registers should be RAZ.
+	 */
+	test_bitmap_pmu_regs(pmc_idx, 1);
+	test_bitmap_pmu_regs(pmc_idx, 0);
+}
+
+/*
+ * The guest is configured with PMUv3 with @expected_pmcr_n number of
+ * event counters.
+ * Check if @expected_pmcr_n is consistent with PMCR_EL0.N, and
+ * if reading/writing PMU registers for implemented or unimplemented
+ * counters works as expected.
+ */
+static void guest_code(uint64_t expected_pmcr_n)
+{
+	uint64_t pmcr, pmcr_n, unimp_mask;
+	int i, pmc;
+
+	__GUEST_ASSERT(expected_pmcr_n <= ARMV8_PMU_MAX_GENERAL_COUNTERS,
+			"Expected PMCR.N: 0x%lx; ARMv8 general counters: 0x%lx",
+			expected_pmcr_n, ARMV8_PMU_MAX_GENERAL_COUNTERS);
+
+	pmcr = read_sysreg(pmcr_el0);
+	pmcr_n = get_pmcr_n(pmcr);
+
+	/* Make sure that PMCR_EL0.N indicates the value userspace set */
+	__GUEST_ASSERT(pmcr_n == expected_pmcr_n,
+			"Expected PMCR.N: 0x%lx, PMCR.N: 0x%lx",
+			expected_pmcr_n, pmcr_n);
+
+	/*
+	 * Make sure that (RAZ) bits corresponding to unimplemented event
+	 * counters in {PMCNTEN,PMINTEN,PMOVS}{SET,CLR} registers are reset
+	 * to zero.
+	 * (NOTE: bits for implemented event counters are reset to UNKNOWN)
+	 */
+	unimp_mask = GENMASK_ULL(ARMV8_PMU_MAX_GENERAL_COUNTERS - 1, pmcr_n);
+	check_bitmap_pmu_regs(unimp_mask, false);
+
+	/*
+	 * Tests for reading/writing PMU registers for implemented counters.
+	 * Use each combination of PMEV{CNTR,TYPER}<n>_EL0 accessor functions.
+	 */
+	for (i = 0; i < ARRAY_SIZE(pmc_accessors); i++) {
+		for (pmc = 0; pmc < pmcr_n; pmc++)
+			test_access_pmc_regs(&pmc_accessors[i], pmc);
+	}
+
+	/*
+	 * Tests for reading/writing PMU registers for unimplemented counters.
+	 * Use each combination of PMEV{CNTR,TYPER}<n>_EL0 accessor functions.
+	 */
+	for (i = 0; i < ARRAY_SIZE(pmc_accessors); i++) {
+		for (pmc = pmcr_n; pmc < ARMV8_PMU_MAX_GENERAL_COUNTERS; pmc++)
+			test_access_invalid_pmc_regs(&pmc_accessors[i], pmc);
+	}
+
+	GUEST_DONE();
+}
+
+#define GICD_BASE_GPA	0x8000000ULL
+#define GICR_BASE_GPA	0x80A0000ULL
+
+/* Create a VM that has one vCPU with PMUv3 configured. */
+static void create_vpmu_vm(void *guest_code)
+{
+	struct kvm_vcpu_init init;
+	uint8_t pmuver, ec;
+	uint64_t dfr0, irq = 23;
+	struct kvm_device_attr irq_attr = {
+		.group = KVM_ARM_VCPU_PMU_V3_CTRL,
+		.attr = KVM_ARM_VCPU_PMU_V3_IRQ,
+		.addr = (uint64_t)&irq,
+	};
+	struct kvm_device_attr init_attr = {
+		.group = KVM_ARM_VCPU_PMU_V3_CTRL,
+		.attr = KVM_ARM_VCPU_PMU_V3_INIT,
+	};
+
+	/* The test creates the vpmu_vm multiple times. Ensure a clean state */
+	memset(&vpmu_vm, 0, sizeof(vpmu_vm));
+
+	vpmu_vm.vm = vm_create(1);
+	vm_init_descriptor_tables(vpmu_vm.vm);
+	for (ec = 0; ec < ESR_EC_NUM; ec++) {
+		vm_install_sync_handler(vpmu_vm.vm, VECTOR_SYNC_CURRENT, ec,
+					guest_sync_handler);
+	}
+
+	/* Create vCPU with PMUv3 */
+	vm_ioctl(vpmu_vm.vm, KVM_ARM_PREFERRED_TARGET, &init);
+	init.features[0] |= (1 << KVM_ARM_VCPU_PMU_V3);
+	vpmu_vm.vcpu = aarch64_vcpu_add(vpmu_vm.vm, 0, &init, guest_code);
+	vcpu_init_descriptor_tables(vpmu_vm.vcpu);
+	vpmu_vm.gic_fd = vgic_v3_setup(vpmu_vm.vm, 1, 64,
+					GICD_BASE_GPA, GICR_BASE_GPA);
+	__TEST_REQUIRE(vpmu_vm.gic_fd >= 0,
+		       "Failed to create vgic-v3, skipping");
+
+	/* Make sure that PMUv3 support is indicated in the ID register */
+	vcpu_get_reg(vpmu_vm.vcpu,
+		     KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1), &dfr0);
+	pmuver = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), dfr0);
+	TEST_ASSERT(pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF &&
+		    pmuver >= ID_AA64DFR0_EL1_PMUVer_IMP,
+		    "Unexpected PMUVER (0x%x) on the vCPU with PMUv3", pmuver);
+
+	/* Initialize vPMU */
+	vcpu_ioctl(vpmu_vm.vcpu, KVM_SET_DEVICE_ATTR, &irq_attr);
+	vcpu_ioctl(vpmu_vm.vcpu, KVM_SET_DEVICE_ATTR, &init_attr);
+}
+
+static void destroy_vpmu_vm(void)
+{
+	close(vpmu_vm.gic_fd);
+	kvm_vm_free(vpmu_vm.vm);
+}
+
+static void run_vcpu(struct kvm_vcpu *vcpu, uint64_t pmcr_n)
+{
+	struct ucall uc;
+
+	vcpu_args_set(vcpu, 1, pmcr_n);
+	vcpu_run(vcpu);
+	switch (get_ucall(vcpu, &uc)) {
+	case UCALL_ABORT:
+		REPORT_GUEST_ASSERT(uc);
+		break;
+	case UCALL_DONE:
+		break;
+	default:
+		TEST_FAIL("Unknown ucall %lu", uc.cmd);
+		break;
+	}
+}
+
+static void test_create_vpmu_vm_with_pmcr_n(uint64_t pmcr_n, bool expect_fail)
+{
+	struct kvm_vcpu *vcpu;
+	uint64_t pmcr, pmcr_orig;
+
+	create_vpmu_vm(guest_code);
+	vcpu = vpmu_vm.vcpu;
+
+	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr_orig);
+	pmcr = pmcr_orig;
+
+	/*
+	 * Setting a larger value of PMCR.N should not modify the field, and
+	 * return a success.
+	 */
+	set_pmcr_n(&pmcr, pmcr_n);
+	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), pmcr);
+	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr);
+
+	if (expect_fail)
+		TEST_ASSERT(pmcr_orig == pmcr,
+			    "PMCR.N modified by KVM to a larger value (PMCR: 0x%lx) for pmcr_n: 0x%lx\n",
+			    pmcr, pmcr_n);
+	else
+		TEST_ASSERT(pmcr_n == get_pmcr_n(pmcr),
+			    "Failed to update PMCR.N to %lu (received: %lu)\n",
+			    pmcr_n, get_pmcr_n(pmcr));
+}
+
+/*
+ * Create a guest with one vCPU, set the PMCR_EL0.N for the vCPU to @pmcr_n,
+ * and run the test.
+ */
+static void run_access_test(uint64_t pmcr_n)
+{
+	uint64_t sp;
+	struct kvm_vcpu *vcpu;
+	struct kvm_vcpu_init init;
+
+	pr_debug("Test with pmcr_n %lu\n", pmcr_n);
+
+	test_create_vpmu_vm_with_pmcr_n(pmcr_n, false);
+	vcpu = vpmu_vm.vcpu;
+
+	/* Save the initial sp to restore them later to run the guest again */
+	vcpu_get_reg(vcpu, ARM64_CORE_REG(sp_el1), &sp);
+
+	run_vcpu(vcpu, pmcr_n);
+
+	/*
+	 * Reset and re-initialize the vCPU, and run the guest code again to
+	 * check if PMCR_EL0.N is preserved.
+	 */
+	vm_ioctl(vpmu_vm.vm, KVM_ARM_PREFERRED_TARGET, &init);
+	init.features[0] |= (1 << KVM_ARM_VCPU_PMU_V3);
+	aarch64_vcpu_setup(vcpu, &init);
+	vcpu_init_descriptor_tables(vcpu);
+	vcpu_set_reg(vcpu, ARM64_CORE_REG(sp_el1), sp);
+	vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code);
+
+	run_vcpu(vcpu, pmcr_n);
+
+	destroy_vpmu_vm();
+}
+
+static struct pmreg_sets validity_check_reg_sets[] = {
+	PMREG_SET(SYS_PMCNTENSET_EL0, SYS_PMCNTENCLR_EL0),
+	PMREG_SET(SYS_PMINTENSET_EL1, SYS_PMINTENCLR_EL1),
+	PMREG_SET(SYS_PMOVSSET_EL0, SYS_PMOVSCLR_EL0),
+};
+
+/*
+ * Create a VM, and check if KVM handles the userspace accesses of
+ * the PMU register sets in @validity_check_reg_sets[] correctly.
+ */
+static void run_pmregs_validity_test(uint64_t pmcr_n)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+	uint64_t set_reg_id, clr_reg_id, reg_val;
+	uint64_t valid_counters_mask, max_counters_mask;
+
+	test_create_vpmu_vm_with_pmcr_n(pmcr_n, false);
+	vcpu = vpmu_vm.vcpu;
+
+	valid_counters_mask = get_counters_mask(pmcr_n);
+	max_counters_mask = get_counters_mask(ARMV8_PMU_MAX_COUNTERS);
+
+	for (i = 0; i < ARRAY_SIZE(validity_check_reg_sets); i++) {
+		set_reg_id = validity_check_reg_sets[i].set_reg_id;
+		clr_reg_id = validity_check_reg_sets[i].clr_reg_id;
+
+		/*
+		 * Test if the 'set' and 'clr' variants of the registers
+		 * are initialized based on the number of valid counters.
+		 */
+		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), &reg_val);
+		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
+			    "Initial read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+			    KVM_ARM64_SYS_REG(set_reg_id), reg_val);
+
+		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), &reg_val);
+		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
+			    "Initial read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+			    KVM_ARM64_SYS_REG(clr_reg_id), reg_val);
+
+		/*
+		 * Using the 'set' variant, force-set the register to the
+		 * max number of possible counters and test if KVM discards
+		 * the bits for unimplemented counters as it should.
+		 */
+		vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), max_counters_mask);
+
+		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), &reg_val);
+		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
+			    "Read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+			    KVM_ARM64_SYS_REG(set_reg_id), reg_val);
+
+		vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), &reg_val);
+		TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0,
+			    "Read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx\n",
+			    KVM_ARM64_SYS_REG(clr_reg_id), reg_val);
+	}
+
+	destroy_vpmu_vm();
+}
+
+/*
+ * Create a guest with one vCPU, and attempt to set the PMCR_EL0.N for
+ * the vCPU to @pmcr_n, which is larger than the host value.
+ * The attempt should fail as @pmcr_n is too big to set for the vCPU.
+ */
+static void run_error_test(uint64_t pmcr_n)
+{
+	pr_debug("Error test with pmcr_n %lu (larger than the host)\n", pmcr_n);
+
+	test_create_vpmu_vm_with_pmcr_n(pmcr_n, true);
+	destroy_vpmu_vm();
+}
+
+/*
+ * Return the default number of implemented PMU event counters excluding
+ * the cycle counter (i.e. PMCR_EL0.N value) for the guest.
+ */
+static uint64_t get_pmcr_n_limit(void)
+{
+	uint64_t pmcr;
+
+	create_vpmu_vm(guest_code);
+	vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr);
+	destroy_vpmu_vm();
+	return get_pmcr_n(pmcr);
+}
+
+int main(void)
+{
+	uint64_t i, pmcr_n;
+
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_ARM_PMU_V3));
+
+	pmcr_n = get_pmcr_n_limit();
+	for (i = 0; i <= pmcr_n; i++) {
+		run_access_test(i);
+		run_pmregs_validity_test(i);
+	}
+
+	for (i = pmcr_n + 1; i < ARMV8_PMU_MAX_COUNTERS; i++)
+		run_error_test(i);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index cb537253a6b9..c42d683102c7 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -104,6 +104,7 @@ enum {
 #define ESR_EC_SHIFT		26
 #define ESR_EC_MASK		(ESR_EC_NUM - 1)
 
+#define ESR_EC_UNKNOWN		0x0
 #define ESR_EC_SVC64		0x15
 #define ESR_EC_IABT		0x21
 #define ESR_EC_DABT		0x25