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 (ex