1 files changed, 356 insertions, 163 deletions

diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index a35ce10e0a9f..25c29107f13f 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -14,17 +14,21 @@
 #include <asm/kvm_emulate.h>
 #include <kvm/arm_pmu.h>
 #include <kvm/arm_vgic.h>
-#include <asm/arm_pmuv3.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_pmc *pmc);
 static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc);
+static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc);
+
+bool kvm_supports_guest_pmuv3(void)
+{
+	guard(mutex)(&arm_pmus_lock);
+	return !list_empty(&arm_pmus);
+}
 
 static struct kvm_vcpu *kvm_pmc_to_vcpu(const struct kvm_pmc *pmc)
 {
@@ -54,7 +58,7 @@ static u32 __kvm_pmu_event_mask(unsigned int pmuver)
 
 static u32 kvm_pmu_event_mask(struct kvm *kvm)
 {
-	u64 dfr0 = IDREG(kvm, SYS_ID_AA64DFR0_EL1);
+	u64 dfr0 = kvm_read_vm_id_reg(kvm, SYS_ID_AA64DFR0_EL1);
 	u8 pmuver = SYS_FIELD_GET(ID_AA64DFR0_EL1, PMUVer, dfr0);
 
 	return __kvm_pmu_event_mask(pmuver);
@@ -90,7 +94,11 @@ static bool kvm_pmc_is_64bit(struct kvm_pmc *pmc)
 
 static bool kvm_pmc_has_64bit_overflow(struct kvm_pmc *pmc)
 {
-	u64 val = kvm_vcpu_read_pmcr(kvm_pmc_to_vcpu(pmc));
+	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
+	u64 val = kvm_vcpu_read_pmcr(vcpu);
+
+	if (kvm_pmu_counter_is_hyp(vcpu, pmc->idx))
+		return __vcpu_sys_reg(vcpu, MDCR_EL2) & MDCR_EL2_HLP;
 
 	return (pmc->idx < ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LP)) ||
 	       (pmc->idx == ARMV8_PMU_CYCLE_IDX && (val & ARMV8_PMU_PMCR_LC));
@@ -112,6 +120,11 @@ static u32 counter_index_to_evtreg(u64 idx)
 	return (idx == ARMV8_PMU_CYCLE_IDX) ? PMCCFILTR_EL0 : PMEVTYPER0_EL0 + idx;
 }
 
+static u64 kvm_pmc_read_evtreg(const struct kvm_pmc *pmc)
+{
+	return __vcpu_sys_reg(kvm_pmc_to_vcpu(pmc), counter_index_to_evtreg(pmc->idx));
+}
+
 static u64 kvm_pmu_get_pmc_value(struct kvm_pmc *pmc)
 {
 	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
@@ -141,9 +154,6 @@ static u64 kvm_pmu_get_pmc_value(struct kvm_pmc *pmc)
  */
 u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
 {
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return 0;
-
 	return kvm_pmu_get_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx));
 }
 
@@ -182,13 +192,23 @@ static void kvm_pmu_set_pmc_value(struct kvm_pmc *pmc, u64 val, bool force)
  */
 void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
 {
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return;
-
 	kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, select_idx), val, false);
 }
 
 /**
+ * kvm_pmu_set_counter_value_user - set PMU counter value from user
+ * @vcpu: The vcpu pointer
+ * @select_idx: The counter index
+ * @val: The counter value
+ */
+void kvm_pmu_set_counter_value_user(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
+{
+	kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, select_idx));
+	__vcpu_sys_reg(vcpu, counter_index_to_reg(select_idx)) = val;
+	kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
+}
+
+/**
  * kvm_pmu_release_perf_event - remove the perf event
  * @pmc: The PMU counter pointer
  */
@@ -234,25 +254,11 @@ void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu)
 	int i;
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 
-	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++)
+	for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++)
 		pmu->pmc[i].idx = i;
 }
 
 /**
- * kvm_pmu_vcpu_reset - reset pmu state for cpu
- * @vcpu: The vcpu pointer
- *
- */
-void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu)
-{
-	unsigned long mask = kvm_pmu_valid_counter_mask(vcpu);
-	int i;
-
-	for_each_set_bit(i, &mask, 32)
-		kvm_pmu_stop_counter(kvm_vcpu_idx_to_pmc(vcpu, i));
-}
-
-/**
  * kvm_pmu_vcpu_destroy - free perf event of PMU for cpu
  * @vcpu: The vcpu pointer
  *
@@ -261,12 +267,55 @@ void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	int i;
 
-	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++)
+	for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++)
 		kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, i));
 	irq_work_sync(&vcpu->arch.pmu.overflow_work);
 }
 
-u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
+static u64 kvm_pmu_hyp_counter_mask(struct kvm_vcpu *vcpu)
+{
+	unsigned int hpmn, n;
+
+	if (!vcpu_has_nv(vcpu))
+		return 0;
+
+	hpmn = SYS_FIELD_GET(MDCR_EL2, HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2));
+	n = vcpu->kvm->arch.nr_pmu_counters;
+
+	/*
+	 * Programming HPMN to a value greater than PMCR_EL0.N is
+	 * CONSTRAINED UNPREDICTABLE. Make the implementation choice that an
+	 * UNKNOWN number of counters (in our case, zero) are reserved for EL2.
+	 */
+	if (hpmn >= n)
+		return 0;
+
+	/*
+	 * Programming HPMN=0 is CONSTRAINED UNPREDICTABLE if FEAT_HPMN0 isn't
+	 * implemented. Since KVM's ability to emulate HPMN=0 does not directly
+	 * depend on hardware (all PMU registers are trapped), make the
+	 * implementation choice that all counters are included in the second
+	 * range reserved for EL2/EL3.
+	 */
+	return GENMASK(n - 1, hpmn);
+}
+
+bool kvm_pmu_counter_is_hyp(struct kvm_vcpu *vcpu, unsigned int idx)
+{
+	return kvm_pmu_hyp_counter_mask(vcpu) & BIT(idx);
+}
+
+u64 kvm_pmu_accessible_counter_mask(struct kvm_vcpu *vcpu)
+{
+	u64 mask = kvm_pmu_implemented_counter_mask(vcpu);
+
+	if (!vcpu_has_nv(vcpu) || vcpu_is_el2(vcpu))
+		return mask;
+
+	return mask & ~kvm_pmu_hyp_counter_mask(vcpu);
+}
+
+u64 kvm_pmu_implemented_counter_mask(struct kvm_vcpu *vcpu)
 {
 	u64 val = FIELD_GET(ARMV8_PMU_PMCR_N, kvm_vcpu_read_pmcr(vcpu));
 
@@ -276,76 +325,70 @@ u64 kvm_pmu_valid_counter_mask(struct kvm_vcpu *vcpu)
 		return GENMASK(val - 1, 0) | BIT(ARMV8_PMU_CYCLE_IDX);
 }
 
-/**
- * kvm_pmu_enable_counter_mask - enable selected PMU counters
- * @vcpu: The vcpu pointer
- * @val: the value guest writes to PMCNTENSET register
- *
- * Call perf_event_enable to start counting the perf event
- */
-void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
+static void kvm_pmc_enable_perf_event(struct kvm_pmc *pmc)
 {
-	int i;
-	if (!kvm_vcpu_has_pmu(vcpu))
+	if (!pmc->perf_event) {
+		kvm_pmu_create_perf_event(pmc);
 		return;
+	}
 
-	if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) || !val)
-		return;
-
-	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
-		struct kvm_pmc *pmc;
-
-		if (!(val & BIT(i)))
-			continue;
-
-		pmc = kvm_vcpu_idx_to_pmc(vcpu, i);
+	perf_event_enable(pmc->perf_event);
+	if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE)
+		kvm_debug("fail to enable perf event\n");
+}
 
-		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");
-		}
-	}
+static void kvm_pmc_disable_perf_event(struct kvm_pmc *pmc)
+{
+	if (pmc->perf_event)
+		perf_event_disable(pmc->perf_event);
 }
 
-/**
- * kvm_pmu_disable_counter_mask - disable selected PMU counters
- * @vcpu: The vcpu pointer
- * @val: the value guest writes to PMCNTENCLR register
- *
- * Call perf_event_disable to stop counting the perf event
- */
-void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val)
+void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val)
 {
 	int i;
 
-	if (!kvm_vcpu_has_pmu(vcpu) || !val)
+	if (!val)
 		return;
 
-	for (i = 0; i < ARMV8_PMU_MAX_COUNTERS; i++) {
-		struct kvm_pmc *pmc;
+	for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) {
+		struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i);
 
 		if (!(val & BIT(i)))
 			continue;
 
-		pmc = kvm_vcpu_idx_to_pmc(vcpu, i);
-
-		if (pmc->perf_event)
-			perf_event_disable(pmc->perf_event);
+		if (kvm_pmu_counter_is_enabled(pmc))
+			kvm_pmc_enable_perf_event(pmc);
+		else
+			kvm_pmc_disable_perf_event(pmc);
 	}
+
+	kvm_vcpu_pmu_restore_guest(vcpu);
 }
 
-static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu)
+/*
+ * Returns the PMU overflow state, which is true if there exists an event
+ * counter where the values of the global enable control, PMOVSSET_EL0[n], and
+ * PMINTENSET_EL1[n] are all 1.
+ */
+static bool kvm_pmu_overflow_status(struct kvm_vcpu *vcpu)
 {
-	u64 reg = 0;
+	u64 reg = __vcpu_sys_reg(vcpu, PMOVSSET_EL0);
 
-	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);
-	}
+	reg &= __vcpu_sys_reg(vcpu, PMINTENSET_EL1);
+
+	/*
+	 * PMCR_EL0.E is the global enable control for event counters available
+	 * to EL0 and EL1.
+	 */
+	if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E))
+		reg &= kvm_pmu_hyp_counter_mask(vcpu);
+
+	/*
+	 * Otherwise, MDCR_EL2.HPME is the global enable control for event
+	 * counters reserved for EL2.
+	 */
+	if (!(vcpu_read_sys_reg(vcpu, MDCR_EL2) & MDCR_EL2_HPME))
+		reg &= ~kvm_pmu_hyp_counter_mask(vcpu);
 
 	return reg;
 }
@@ -355,10 +398,7 @@ static void kvm_pmu_update_state(struct kvm_vcpu *vcpu)
 	struct kvm_pmu *pmu = &vcpu->arch.pmu;
 	bool overflow;
 
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return;
-
-	overflow = !!kvm_pmu_overflow_status(vcpu);
+	overflow = kvm_pmu_overflow_status(vcpu);
 	if (pmu->irq_level == overflow)
 		return;
 
@@ -553,41 +593,87 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
 {
 	int i;
 
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return;
-
 	/* Fixup PMCR_EL0 to reconcile the PMU version and the LP bit */
 	if (!kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5))
 		val &= ~ARMV8_PMU_PMCR_LP;
 
+	/* Request a reload of the PMU to enable/disable affected counters */
+	if ((__vcpu_sys_reg(vcpu, PMCR_EL0) ^ val) & ARMV8_PMU_PMCR_E)
+		kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
+
 	/* The reset bits don't indicate any state, and shouldn't be saved. */
 	__vcpu_sys_reg(vcpu, PMCR_EL0) = val & ~(ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_P);
 
-	if (val & ARMV8_PMU_PMCR_E) {
-		kvm_pmu_enable_counter_mask(vcpu,
-		       __vcpu_sys_reg(vcpu, PMCNTENSET_EL0));
-	} else {
-		kvm_pmu_disable_counter_mask(vcpu,
-		       __vcpu_sys_reg(vcpu, PMCNTENSET_EL0));
-	}
-
 	if (val & ARMV8_PMU_PMCR_C)
 		kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0);
 
 	if (val & ARMV8_PMU_PMCR_P) {
-		unsigned long mask = kvm_pmu_valid_counter_mask(vcpu);
-		mask &= ~BIT(ARMV8_PMU_CYCLE_IDX);
+		unsigned long mask = kvm_pmu_implemented_counter_mask(vcpu) &
+				     ~BIT(ARMV8_PMU_CYCLE_IDX);
+
+		if (!vcpu_is_el2(vcpu))
+			mask &= ~kvm_pmu_hyp_counter_mask(vcpu);
+
 		for_each_set_bit(i, &mask, 32)
 			kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, i), 0, true);
 	}
-	kvm_vcpu_pmu_restore_guest(vcpu);
 }
 
 static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc)
 {
 	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
-	return (kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) &&
-	       (__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(pmc->idx));
+	unsigned int mdcr = __vcpu_sys_reg(vcpu, MDCR_EL2);
+
+	if (!(__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & BIT(pmc->idx)))
+		return false;
+
+	if (kvm_pmu_counter_is_hyp(vcpu, pmc->idx))
+		return mdcr & MDCR_EL2_HPME;
+
+	return kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E;
+}
+
+static bool kvm_pmc_counts_at_el0(struct kvm_pmc *pmc)
+{
+	u64 evtreg = kvm_pmc_read_evtreg(pmc);
+	bool nsu = evtreg & ARMV8_PMU_EXCLUDE_NS_EL0;
+	bool u = evtreg & ARMV8_PMU_EXCLUDE_EL0;
+
+	return u == nsu;
+}
+
+static bool kvm_pmc_counts_at_el1(struct kvm_pmc *pmc)
+{
+	u64 evtreg = kvm_pmc_read_evtreg(pmc);
+	bool nsk = evtreg & ARMV8_PMU_EXCLUDE_NS_EL1;
+	bool p = evtreg & ARMV8_PMU_EXCLUDE_EL1;
+
+	return p == nsk;
+}
+
+static bool kvm_pmc_counts_at_el2(struct kvm_pmc *pmc)
+{
+	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
+	u64 mdcr = __vcpu_sys_reg(vcpu, MDCR_EL2);
+
+	if (!kvm_pmu_counter_is_hyp(vcpu, pmc->idx) && (mdcr & MDCR_EL2_HPMD))
+		return false;
+
+	return kvm_pmc_read_evtreg(pmc) & ARMV8_PMU_INCLUDE_EL2;
+}
+
+static int kvm_map_pmu_event(struct kvm *kvm, unsigned int eventsel)
+{
+	struct arm_pmu *pmu = kvm->arch.arm_pmu;
+
+	/*
+	 * The CPU PMU likely isn't PMUv3; let the driver provide a mapping
+	 * for the guest's PMUv3 event ID.
+	 */
+	if (unlikely(pmu->map_pmuv3_event))
+		return pmu->map_pmuv3_event(eventsel);
+
+	return eventsel;
 }
 
 /**
@@ -600,17 +686,16 @@ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc)
 	struct arm_pmu *arm_pmu = vcpu->kvm->arch.arm_pmu;
 	struct perf_event *event;
 	struct perf_event_attr attr;
-	u64 eventsel, reg, data;
-	bool p, u, nsk, nsu;
+	int eventsel;
+	u64 evtreg;
 
-	reg = counter_index_to_evtreg(pmc->idx);
-	data = __vcpu_sys_reg(vcpu, reg);
+	evtreg = kvm_pmc_read_evtreg(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);
+		eventsel = evtreg & kvm_pmu_event_mask(vcpu->kvm);
 
 	/*
 	 * Neither SW increment nor chained events need to be backed
@@ -628,23 +713,34 @@ static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc)
 	    !test_bit(eventsel, vcpu->kvm->arch.pmu_filter))
 		return;
 
-	p = data & ARMV8_PMU_EXCLUDE_EL1;
-	u = data & ARMV8_PMU_EXCLUDE_EL0;
-	nsk = data & ARMV8_PMU_EXCLUDE_NS_EL1;
-	nsu = data & ARMV8_PMU_EXCLUDE_NS_EL0;
+	/*
+	 * Don't create an event if we're running on hardware that requires
+	 * PMUv3 event translation and we couldn't find a valid mapping.
+	 */
+	eventsel = kvm_map_pmu_event(vcpu->kvm, eventsel);
+	if (eventsel < 0)
+		return;
 
 	memset(&attr, 0, sizeof(struct perf_event_attr));
 	attr.type = arm_pmu->pmu.type;
 	attr.size = sizeof(attr);
 	attr.pinned = 1;
 	attr.disabled = !kvm_pmu_counter_is_enabled(pmc);
-	attr.exclude_user = (u != nsu);
-	attr.exclude_kernel = (p != nsk);
+	attr.exclude_user = !kvm_pmc_counts_at_el0(pmc);
 	attr.exclude_hv = 1; /* Don't count EL2 events */
 	attr.exclude_host = 1; /* Don't count host events */
 	attr.config = eventsel;
 
 	/*
+	 * Filter events at EL1 (i.e. vEL2) when in a hyp context based on the
+	 * guest's EL2 filter.
+	 */
+	if (unlikely(is_hyp_ctxt(vcpu)))
+		attr.exclude_kernel = !kvm_pmc_counts_at_el2(pmc);
+	else
+		attr.exclude_kernel = !kvm_pmc_counts_at_el1(pmc);
+
+	/*
 	 * 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.
@@ -682,9 +778,6 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
 	struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, select_idx);
 	u64 reg;
 
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return;
-
 	reg = counter_index_to_evtreg(pmc->idx);
 	__vcpu_sys_reg(vcpu, reg) = data & kvm_pmu_evtyper_mask(vcpu->kvm);
 
@@ -702,29 +795,23 @@ void kvm_host_pmu_init(struct arm_pmu *pmu)
 	if (!pmuv3_implemented(kvm_arm_pmu_get_pmuver_limit()))
 		return;
 
-	mutex_lock(&arm_pmus_lock);
+	guard(mutex)(&arm_pmus_lock);
 
 	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
-		goto out_unlock;
+		return;
 
 	entry->arm_pmu = pmu;
 	list_add_tail(&entry->entry, &arm_pmus);
-
-	if (list_is_singular(&arm_pmus))
-		static_branch_enable(&kvm_arm_pmu_available);
-
-out_unlock:
-	mutex_unlock(&arm_pmus_lock);
 }
 
 static struct arm_pmu *kvm_pmu_probe_armpmu(void)
 {
-	struct arm_pmu *tmp, *pmu = NULL;
 	struct arm_pmu_entry *entry;
+	struct arm_pmu *pmu;
 	int cpu;
 
-	mutex_lock(&arm_pmus_lock);
+	guard(mutex)(&arm_pmus_lock);
 
 	/*
 	 * It is safe to use a stale cpu to iterate the list of PMUs so long as
@@ -745,42 +832,62 @@ static struct arm_pmu *kvm_pmu_probe_armpmu(void)
 	 */
 	cpu = raw_smp_processor_id();
 	list_for_each_entry(entry, &arm_pmus, entry) {
-		tmp = entry->arm_pmu;
+		pmu = entry->arm_pmu;
 
-		if (cpumask_test_cpu(cpu, &tmp->supported_cpus)) {
-			pmu = tmp;
-			break;
-		}
+		if (cpumask_test_cpu(cpu, &pmu->supported_cpus))
+			return pmu;
 	}
 
-	mutex_unlock(&arm_pmus_lock);
+	return NULL;
+}
+
+static u64 __compute_pmceid(struct arm_pmu *pmu, bool pmceid1)
+{
+	u32 hi[2], lo[2];
+
+	bitmap_to_arr32(lo, pmu->pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
+	bitmap_to_arr32(hi, pmu->pmceid_ext_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
+
+	return ((u64)hi[pmceid1] << 32) | lo[pmceid1];
+}
+
+static u64 compute_pmceid0(struct arm_pmu *pmu)
+{
+	u64 val = __compute_pmceid(pmu, 0);
+
+	/* always support SW_INCR */
+	val |= BIT(ARMV8_PMUV3_PERFCTR_SW_INCR);
+	/* always support CHAIN */
+	val |= BIT(ARMV8_PMUV3_PERFCTR_CHAIN);
+	return val;
+}
+
+static u64 compute_pmceid1(struct arm_pmu *pmu)
+{
+	u64 val = __compute_pmceid(pmu, 1);
 
-	return pmu;
+	/*
+	 * Don't advertise STALL_SLOT*, as PMMIR_EL0 is handled
+	 * as RAZ
+	 */
+	val &= ~(BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32) |
+		 BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND - 32) |
+		 BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND - 32));
+	return val;
 }
 
 u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 {
+	struct arm_pmu *cpu_pmu = vcpu->kvm->arch.arm_pmu;
 	unsigned long *bmap = vcpu->kvm->arch.pmu_filter;
 	u64 val, mask = 0;
 	int base, i, nr_events;
 
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return 0;
-
 	if (!pmceid1) {
-		val = read_sysreg(pmceid0_el0);
-		/* always support CHAIN */
-		val |= BIT(ARMV8_PMUV3_PERFCTR_CHAIN);
+		val = compute_pmceid0(cpu_pmu);
 		base = 0;
 	} else {
-		val = read_sysreg(pmceid1_el0);
-		/*
-		 * Don't advertise STALL_SLOT*, as PMMIR_EL0 is handled
-		 * as RAZ
-		 */
-		val &= ~(BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT - 32) |
-			 BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_FRONTEND - 32) |
-			 BIT_ULL(ARMV8_PMUV3_PERFCTR_STALL_SLOT_BACKEND - 32));
+		val = compute_pmceid1(cpu_pmu);
 		base = 32;
 	}
 
@@ -805,20 +912,17 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 
 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));
+	u64 mask = kvm_pmu_implemented_counter_mask(vcpu);
 
 	__vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= mask;
 	__vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= mask;
 	__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= mask;
+
+	kvm_pmu_reprogram_counter_mask(vcpu, mask);
 }
 
 int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 {
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return 0;
-
 	if (!vcpu->arch.pmu.created)
 		return -EINVAL;
 
@@ -841,9 +945,6 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
 		   return -EINVAL;
 	}
 
-	/* One-off reload of the PMU on first run */
-	kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
-
 	return 0;
 }
 
@@ -911,10 +1012,35 @@ 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.
+	 * PMUv3 requires that all event counters are capable of counting any
+	 * event, though the same may not be true of non-PMUv3 hardware.
+	 */
+	if (cpus_have_final_cap(ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS))
+		return 1;
+
+	/*
+	 * The arm_pmu->cntr_mask considers the fixed counter(s) as well.
+	 * Ignore those and return only the general-purpose counters.
 	 */
-	return arm_pmu->num_events - 1;
+	return bitmap_weight(arm_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS);
+}
+
+static void kvm_arm_set_nr_counters(struct kvm *kvm, unsigned int nr)
+{
+	kvm->arch.nr_pmu_counters = nr;
+
+	/* Reset MDCR_EL2.HPMN behind the vcpus' back... */
+	if (test_bit(KVM_ARM_VCPU_HAS_EL2, kvm->arch.vcpu_features)) {
+		struct kvm_vcpu *vcpu;
+		unsigned long i;
+
+		kvm_for_each_vcpu(i, vcpu, kvm) {
+			u64 val = __vcpu_sys_reg(vcpu, MDCR_EL2);
+			val &= ~MDCR_EL2_HPMN;
+			val |= FIELD_PREP(MDCR_EL2_HPMN, kvm->arch.nr_pmu_counters);
+			__vcpu_sys_reg(vcpu, MDCR_EL2) = val;
+		}
+	}
 }
 
 static void kvm_arm_set_pmu(struct kvm *kvm, struct arm_pmu *arm_pmu)
@@ -922,7 +1048,7 @@ 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_nr_counters(kvm, kvm_arm_pmu_get_max_counters(kvm));
 }
 
 /**
@@ -978,6 +1104,20 @@ static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id)
 	return ret;
 }
 
+static int kvm_arm_pmu_v3_set_nr_counters(struct kvm_vcpu *vcpu, unsigned int n)
+{
+	struct kvm *kvm = vcpu->kvm;
+
+	if (!kvm->arch.arm_pmu)
+		return -EINVAL;
+
+	if (n > kvm_arm_pmu_get_max_counters(kvm))
+		return -EINVAL;
+
+	kvm_arm_set_nr_counters(kvm, n);
+	return 0;
+}
+
 int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 {
 	struct kvm *kvm = vcpu->kvm;
@@ -1074,6 +1214,15 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 
 		return kvm_arm_pmu_v3_set_pmu(vcpu, pmu_id);
 	}
+	case KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS: {
+		unsigned int __user *uaddr = (unsigned int __user *)(long)attr->addr;
+		unsigned int n;
+
+		if (get_user(n, uaddr))
+			return -EFAULT;
+
+		return kvm_arm_pmu_v3_set_nr_counters(vcpu, n);
+	}
 	case KVM_ARM_VCPU_PMU_V3_INIT:
 		return kvm_arm_pmu_v3_init(vcpu);
 	}
@@ -1112,6 +1261,7 @@ int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 	case KVM_ARM_VCPU_PMU_V3_INIT:
 	case KVM_ARM_VCPU_PMU_V3_FILTER:
 	case KVM_ARM_VCPU_PMU_V3_SET_PMU:
+	case KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS:
 		if (kvm_vcpu_has_pmu(vcpu))
 			return 0;
 	}
@@ -1121,13 +1271,26 @@ int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 
 u8 kvm_arm_pmu_get_pmuver_limit(void)
 {
-	u64 tmp;
+	unsigned int pmuver;
+
+	pmuver = SYS_FIELD_GET(ID_AA64DFR0_EL1, PMUVer,
+			       read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1));
+
+	/*
+	 * Spoof a barebones PMUv3 implementation if the system supports IMPDEF
+	 * traps of the PMUv3 sysregs
+	 */
+	if (cpus_have_final_cap(ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS))
+		return ID_AA64DFR0_EL1_PMUVer_IMP;
+
+	/*
+	 * Otherwise, treat IMPLEMENTATION DEFINED functionality as
+	 * unimplemented
+	 */
+	if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF)
+		return 0;
 
-	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);
+	return min(pmuver, ID_AA64DFR0_EL1_PMUVer_V3P5);
 }
 
 /**
@@ -1137,6 +1300,36 @@ u8 kvm_arm_pmu_get_pmuver_limit(void)
 u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
 {
 	u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0);
+	u64 n = vcpu->kvm->arch.nr_pmu_counters;
+
+	if (vcpu_has_nv(vcpu) && !vcpu_is_el2(vcpu))
+		n = FIELD_GET(MDCR_EL2_HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2));
+
+	return u64_replace_bits(pmcr, n, ARMV8_PMU_PMCR_N);
+}
+
+void kvm_pmu_nested_transition(struct kvm_vcpu *vcpu)
+{
+	bool reprogrammed = false;
+	unsigned long mask;
+	int i;
+
+	mask = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
+	for_each_set_bit(i, &mask, 32) {
+		struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i);
+
+		/*
+		 * We only need to reconfigure events where the filter is
+		 * different at EL1 vs. EL2, as we're multiplexing the true EL1
+		 * event filter bit for nested.
+		 */
+		if (kvm_pmc_counts_at_el1(pmc) == kvm_pmc_counts_at_el2(pmc))
+			continue;
+
+		kvm_pmu_create_perf_event(pmc);
+		reprogrammed = true;
+	}
 
-	return u64_replace_bits(pmcr, vcpu->kvm->arch.pmcr_n, ARMV8_PMU_PMCR_N);
+	if (reprogrammed)
+		kvm_vcpu_pmu_restore_guest(vcpu);
 }