Merge branch 'kvm-arm64/pmu-fixes' into kvmarm/next

* kvm-arm64/pmu-fixes:
  : vPMU fixes for 6.15 courtesy of Akihiko Odaki
  :
  : Various fixes to KVM's vPMU implementation, notably ensuring
  : userspace-directed changes to the PMCs are reflected in the backing perf
  : events.
  KVM: arm64: PMU: Reload when resetting
  KVM: arm64: PMU: Reload when user modifies registers
  KVM: arm64: PMU: Fix SET_ONE_REG for vPMC regs
  KVM: arm64: PMU: Assume PMU presence in pmu-emul.c
  KVM: arm64: PMU: Set raw values from user to PM{C,I}NTEN{SET,CLR}, PMOVS{SET,CLR}

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

Author: oupton

arch/arm64/kvm/arm.c

@@ -858,9 +858,11 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 	if (ret)
 		return ret;
 
-	ret = kvm_arm_pmu_v3_enable(vcpu);
-	if (ret)
-		return ret;
+	if (kvm_vcpu_has_pmu(vcpu)) {
+		ret = kvm_arm_pmu_v3_enable(vcpu);
+		if (ret)
+			return ret;
+	}
 
 	if (is_protected_kvm_enabled()) {
 		ret = pkvm_create_hyp_vm(kvm);
@@ -1175,7 +1177,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		preempt_disable();
 
-		kvm_pmu_flush_hwstate(vcpu);
+		if (kvm_vcpu_has_pmu(vcpu))
+			kvm_pmu_flush_hwstate(vcpu);
 
 		local_irq_disable();
 
@@ -1194,7 +1197,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		if (ret <= 0 || kvm_vcpu_exit_request(vcpu, &ret)) {
 			vcpu->mode = OUTSIDE_GUEST_MODE;
 			isb(); /* Ensure work in x_flush_hwstate is committed */
-			kvm_pmu_sync_hwstate(vcpu);
+			if (kvm_vcpu_has_pmu(vcpu))
+				kvm_pmu_sync_hwstate(vcpu);
 			if (unlikely(!irqchip_in_kernel(vcpu->kvm)))
 				kvm_timer_sync_user(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
@@ -1224,7 +1228,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 * that the vgic can properly sample the updated state of the
 		 * interrupt line.
 		 */
-		kvm_pmu_sync_hwstate(vcpu);
+		if (kvm_vcpu_has_pmu(vcpu))
+			kvm_pmu_sync_hwstate(vcpu);
 
 		/*
 		 * Sync the vgic state before syncing the timer state because

arch/arm64/kvm/emulate-nested.c

@@ -2518,7 +2518,8 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
 	vcpu_clear_flag(vcpu, IN_NESTED_ERET);
 	preempt_enable();
 
-	kvm_pmu_nested_transition(vcpu);
+	if (kvm_vcpu_has_pmu(vcpu))
+		kvm_pmu_nested_transition(vcpu);
 }
 
 static void kvm_inject_el2_exception(struct kvm_vcpu *vcpu, u64 esr_el2,
@@ -2601,7 +2602,8 @@ static int kvm_inject_nested(struct kvm_vcpu *vcpu, u64 esr_el2,
 	kvm_arch_vcpu_load(vcpu, smp_processor_id());
 	preempt_enable();
 
-	kvm_pmu_nested_transition(vcpu);
+	if (kvm_vcpu_has_pmu(vcpu))
+		kvm_pmu_nested_transition(vcpu);
 
 	return 1;
 }

arch/arm64/kvm/pmu-emul.c

@@ -154,9 +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));
 }
 
@@ -195,12 +192,22 @@ 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
@@ -251,20 +258,6 @@ void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu)
 		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_implemented_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
@@ -354,7 +347,7 @@ 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 < KVM_ARMV8_PMU_MAX_COUNTERS; i++) {
@@ -405,9 +398,6 @@ 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);
 	if (pmu->irq_level == overflow)
 		return;
@@ -603,9 +593,6 @@ 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;
@@ -793,9 +780,6 @@ 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);
 
@@ -901,9 +885,6 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 	u64 val, mask = 0;
 	int base, i, nr_events;
 
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return 0;
-
 	if (!pmceid1) {
 		val = compute_pmceid0(cpu_pmu);
 		base = 0;
@@ -944,9 +925,6 @@ void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu)
 
 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;
 
@@ -969,9 +947,6 @@ 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;
 }
 
@@ -1295,9 +1270,6 @@ void kvm_pmu_nested_transition(struct kvm_vcpu *vcpu)
 	unsigned long mask;
 	int i;
 
-	if (!kvm_vcpu_has_pmu(vcpu))
-		return;
-
 	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);

arch/arm64/kvm/reset.c

@@ -196,9 +196,6 @@ void kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	vcpu->arch.reset_state.reset = false;
 	spin_unlock(&vcpu->arch.mp_state_lock);
 
-	/* Reset PMU outside of the non-preemptible section */
-	kvm_pmu_vcpu_reset(vcpu);
-
 	preempt_disable();
 	loaded = (vcpu->cpu != -1);
 	if (loaded)

arch/arm64/kvm/sys_regs.c

@@ -967,6 +967,22 @@ static int get_pmu_evcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 	return 0;
 }
 
+static int set_pmu_evcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
+			  u64 val)
+{
+	u64 idx;
+
+	if (r->CRn == 9 && r->CRm == 13 && r->Op2 == 0)
+		/* PMCCNTR_EL0 */
+		idx = ARMV8_PMU_CYCLE_IDX;
+	else
+		/* PMEVCNTRn_EL0 */
+		idx = ((r->CRm & 3) << 3) | (r->Op2 & 7);
+
+	kvm_pmu_set_counter_value_user(vcpu, idx, val);
+	return 0;
+}
+
 static bool access_pmu_evcntr(struct kvm_vcpu *vcpu,
 			      struct sys_reg_params *p,
 			      const struct sys_reg_desc *r)
@@ -1058,25 +1074,10 @@ static bool access_pmu_evtyper(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 
 static int set_pmreg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 val)
 {
-	bool set;
-
-	val &= kvm_pmu_accessible_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;
-	}
+	u64 mask = kvm_pmu_accessible_counter_mask(vcpu);
 
-	if (set)
-		__vcpu_sys_reg(vcpu, r->reg) |= val;
-	else
-		__vcpu_sys_reg(vcpu, r->reg) &= ~val;
+	__vcpu_sys_reg(vcpu, r->reg) = val & mask;
+	kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
 
 	return 0;
 }
@@ -1236,6 +1237,8 @@ static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 		val |= ARMV8_PMU_PMCR_LC;
 
 	__vcpu_sys_reg(vcpu, r->reg) = val;
+	kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
+
 	return 0;
 }
 
@@ -1262,6 +1265,7 @@ static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
 #define PMU_PMEVCNTR_EL0(n)						\
 	{ PMU_SYS_REG(PMEVCNTRn_EL0(n)),				\
 	  .reset = reset_pmevcntr, .get_user = get_pmu_evcntr,		\
+	  .set_user = set_pmu_evcntr,					\
 	  .access = access_pmu_evcntr, .reg = (PMEVCNTR0_EL0 + n), }
 
 /* Macro to expand the PMEVTYPERn_EL0 register */
@@ -1880,12 +1884,14 @@ static int set_id_aa64dfr0_el1(struct kvm_vcpu *vcpu,
 static u64 read_sanitised_id_dfr0_el1(struct kvm_vcpu *vcpu,
 				      const struct sys_reg_desc *rd)
 {
-	u8 perfmon = pmuver_to_perfmon(kvm_arm_pmu_get_pmuver_limit());
+	u8 perfmon;
 	u64 val = read_sanitised_ftr_reg(SYS_ID_DFR0_EL1);
 
 	val &= ~ID_DFR0_EL1_PerfMon_MASK;
-	if (kvm_vcpu_has_pmu(vcpu))
+	if (kvm_vcpu_has_pmu(vcpu)) {
+		perfmon = pmuver_to_perfmon(kvm_arm_pmu_get_pmuver_limit());
 		val |= SYS_FIELD_PREP(ID_DFR0_EL1, PerfMon, perfmon);
+	}
 
 	val = ID_REG_LIMIT_FIELD_ENUM(val, ID_DFR0_EL1, CopDbg, Debugv8p8);
 
@@ -3052,7 +3058,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	  .access = access_pmceid, .reset = NULL },
 	{ PMU_SYS_REG(PMCCNTR_EL0),
 	  .access = access_pmu_evcntr, .reset = reset_unknown,
-	  .reg = PMCCNTR_EL0, .get_user = get_pmu_evcntr},
+	  .reg = PMCCNTR_EL0, .get_user = get_pmu_evcntr,
+	  .set_user = set_pmu_evcntr },
 	{ PMU_SYS_REG(PMXEVTYPER_EL0),
 	  .access = access_pmu_evtyper, .reset = NULL },
 	{ PMU_SYS_REG(PMXEVCNTR_EL0),
@@ -4712,6 +4719,9 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
 	}
 
 	set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags);
+
+	if (kvm_vcpu_has_pmu(vcpu))
+		kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
 }
 
 /**

include/kvm/arm_pmu.h

@@ -41,11 +41,11 @@ bool kvm_supports_guest_pmuv3(void);
 #define kvm_arm_pmu_irq_initialized(v)	((v)->arch.pmu.irq_num >= VGIC_NR_SGIS)
 u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx);
 void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val);
+void kvm_pmu_set_counter_value_user(struct kvm_vcpu *vcpu, u64 select_idx, u64 val);
 u64 kvm_pmu_implemented_counter_mask(struct kvm_vcpu *vcpu);
 u64 kvm_pmu_accessible_counter_mask(struct kvm_vcpu *vcpu);
 u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1);
 void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu);
-void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu);
 void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu);
 void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val);
 void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu);
@@ -109,6 +109,8 @@ static inline u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu,
 }
 static inline void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu,
 					     u64 select_idx, u64 val) {}
+static inline void kvm_pmu_set_counter_value_user(struct kvm_vcpu *vcpu,
+						  u64 select_idx, u64 val) {}
 static inline u64 kvm_pmu_implemented_counter_mask(struct kvm_vcpu *vcpu)
 {
 	return 0;
@@ -118,7 +120,6 @@ static inline u64 kvm_pmu_accessible_counter_mask(struct kvm_vcpu *vcpu)
 	return 0;
 }
 static inline void kvm_pmu_vcpu_init(struct kvm_vcpu *vcpu) {}
-static inline void kvm_pmu_vcpu_reset(struct kvm_vcpu *vcpu) {}
 static inline void kvm_pmu_vcpu_destroy(struct kvm_vcpu *vcpu) {}
 static inline void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val) {}
 static inline void kvm_pmu_flush_hwstate(struct kvm_vcpu *vcpu) {}