Merge tag 'kvm-x86-pmu-6.6-fixes' of https://github.com/kvm-x86/linux into HEAD

KVM x86/pmu fixes for 6.6:

 - Truncate writes to PMU counters to the counter's width to avoid spurious
   overflows when emulating counter events in software.

 - Set the LVTPC entry mask bit when handling a PMI (to match Intel-defined
   architectural behavior).

 - Treat KVM_REQ_PMI as a wake event instead of queueing host IRQ work to
   kick the guest out of emulated halt.

7 files changed, 19 insertions, 32 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 17715cb8731d5d..70d139406bc80d 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -528,7 +528,6 @@ struct kvm_pmu {
 	u64 raw_event_mask;
 	struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC];
 	struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED];
-	struct irq_work irq_work;
 
 	/*
 	 * Overlay the bitmap with a 64-bit atomic so that all bits can be
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index dcd60b39e794d9..3e977dbbf9933d 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2759,13 +2759,17 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type)
 {
 	u32 reg = kvm_lapic_get_reg(apic, lvt_type);
 	int vector, mode, trig_mode;
+	int r;
 
 	if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) {
 		vector = reg & APIC_VECTOR_MASK;
 		mode = reg & APIC_MODE_MASK;
 		trig_mode = reg & APIC_LVT_LEVEL_TRIGGER;
-		return __apic_accept_irq(apic, mode, vector, 1, trig_mode,
-					NULL);
+
+		r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL);
+		if (r && lvt_type == APIC_LVTPC)
+			kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED);
+		return r;
 	}
 	return 0;
 }
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index edb89b51b38381..9ae07db6f0f648 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -93,14 +93,6 @@ void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops)
 #undef __KVM_X86_PMU_OP
 }
 
-static void kvm_pmi_trigger_fn(struct irq_work *irq_work)
-{
-	struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work);
-	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
-
-	kvm_pmu_deliver_pmi(vcpu);
-}
-
 static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
 {
 	struct kvm_pmu *pmu = pmc_to_pmu(pmc);
@@ -124,20 +116,7 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
 		__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
 	}
 
-	if (!pmc->intr || skip_pmi)
-		return;
-
-	/*
-	 * Inject PMI. If vcpu was in a guest mode during NMI PMI
-	 * can be ejected on a guest mode re-entry. Otherwise we can't
-	 * be sure that vcpu wasn't executing hlt instruction at the
-	 * time of vmexit and is not going to re-enter guest mode until
-	 * woken up. So we should wake it, but this is impossible from
-	 * NMI context. Do it from irq work instead.
-	 */
-	if (in_pmi && !kvm_handling_nmi_from_guest(pmc->vcpu))
-		irq_work_queue(&pmc_to_pmu(pmc)->irq_work);
-	else
+	if (pmc->intr && !skip_pmi)
 		kvm_make_request(KVM_REQ_PMI, pmc->vcpu);
 }
 
@@ -675,9 +654,6 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
 
 void kvm_pmu_reset(struct kvm_vcpu *vcpu)
 {
-	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-
-	irq_work_sync(&pmu->irq_work);
 	static_call(kvm_x86_pmu_reset)(vcpu);
 }
 
@@ -687,7 +663,6 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu)
 
 	memset(pmu, 0, sizeof(*pmu));
 	static_call(kvm_x86_pmu_init)(vcpu);
-	init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn);
 	pmu->event_count = 0;
 	pmu->need_cleanup = false;
 	kvm_pmu_refresh(vcpu);
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 7d9ba301c09062..1d64113de4883e 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -74,6 +74,12 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc)
 	return counter & pmc_bitmask(pmc);
 }
 
+static inline void pmc_write_counter(struct kvm_pmc *pmc, u64 val)
+{
+	pmc->counter += val - pmc_read_counter(pmc);
+	pmc->counter &= pmc_bitmask(pmc);
+}
+
 static inline void pmc_release_perf_event(struct kvm_pmc *pmc)
 {
 	if (pmc->perf_event) {
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index cef5a3d0abd096..373ff6a6687b3a 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -160,7 +160,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	/* MSR_PERFCTRn */
 	pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
 	if (pmc) {
-		pmc->counter += data - pmc_read_counter(pmc);
+		pmc_write_counter(pmc, data);
 		pmc_update_sample_period(pmc);
 		return 0;
 	}
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index f2efa0bf7ae8d4..820d3e1f6b4f82 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -436,11 +436,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			if (!msr_info->host_initiated &&
 			    !(msr & MSR_PMC_FULL_WIDTH_BIT))
 				data = (s64)(s32)data;
-			pmc->counter += data - pmc_read_counter(pmc);
+			pmc_write_counter(pmc, data);
 			pmc_update_sample_period(pmc);
 			break;
 		} else if ((pmc = get_fixed_pmc(pmu, msr))) {
-			pmc->counter += data - pmc_read_counter(pmc);
+			pmc_write_counter(pmc, data);
 			pmc_update_sample_period(pmc);
 			break;
 		} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1e645f5b1e2cf1..41cce5031126a0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12854,6 +12854,9 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 		return true;
 #endif
 
+	if (kvm_test_request(KVM_REQ_PMI, vcpu))
+		return true;
+
 	if (kvm_arch_interrupt_allowed(vcpu) &&
 	    (kvm_cpu_has_interrupt(vcpu) ||
 	    kvm_guest_apic_has_interrupt(vcpu)))