KVM: x86/pmu: Synthesize at most one PMI per VM-exit

When the irq_work callback, kvm_pmi_trigger_fn(), is invoked during a
VM-exit that also invokes __kvm_perf_overflow() as a result of
instruction emulation, kvm_pmu_deliver_pmi() will be called twice
before the next VM-entry.

Calling kvm_pmu_deliver_pmi() twice is unlikely to be problematic now that
KVM sets the LVTPC mask bit when delivering a PMI.  But using IRQ work to
trigger the PMI is still broken, albeit very theoretically.

E.g. if the self-IPI to trigger IRQ work is be delayed long enough for the
vCPU to be migrated to a different pCPU, then it's possible for
kvm_pmi_trigger_fn() to race with the kvm_pmu_deliver_pmi() from
KVM_REQ_PMI and still generate two PMIs.

KVM could set the mask bit using an atomic operation, but that'd just be
piling on unnecessary code to workaround what is effectively a hack.  The
*only* reason KVM uses IRQ work is to ensure the PMI is treated as a wake
event, e.g. if the vCPU just executed HLT.

Remove the irq_work callback for synthesizing a PMI, and all of the
logic for invoking it. Instead, to prevent a vcpu from leaving C0 with
a PMI pending, add a check for KVM_REQ_PMI to kvm_vcpu_has_events().

Fixes: 9cd803d4 ("KVM: x86: Update vPMCs when retiring instructions")
Signed-off-by: Jim Mattson <jmattson@google.com>
Tested-by: Mingwei Zhang <mizhang@google.com>
Tested-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Mingwei Zhang <mizhang@google.com>
Link: https://lore.kernel.org/r/20230925173448.3518223-2-mizhang@google.com
[sean: massage changelog]
Signed-off-by: Sean Christopherson <seanjc@google.com>

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

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);

arch/x86/kvm/x86.c

@@ -12843,6 +12843,9 @@ 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)))