[PATCH 1/2] KVM: x86: Synthesize at most one PMI per VM-exit

[Mingwei Zhang <mizhang@google.com>]

From: Jim Mattson <jmattson@google.com>

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.

That shouldn't be a problem. The local APIC is supposed to
automatically set the mask flag in LVTPC when it handles a PMI, so the
second PMI should be inhibited. However, KVM's local APIC emulation
fails to set the mask flag in LVTPC when it handles a PMI, so two PMIs
are delivered via the local APIC. In the common case, where LVTPC is
configured to deliver an NMI, the first NMI is vectored through the
guest IDT, and the second one is held pending. When the NMI handler
returns, the second NMI is vectored through the IDT. For Linux guests,
this results in the "dazed and confused" spurious NMI message.

Though the obvious fix is to set the mask flag in LVTPC when handling
a PMI, KVM's logic around synthesizing a PMI is unnecessarily
convoluted.

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: 9cd803d496e7 ("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>
---
 arch/x86/include/asm/kvm_host.h |  1 -
 arch/x86/kvm/pmu.c              | 27 +--------------------------
 arch/x86/kvm/x86.c              |  3 +++
 3 files changed, 4 insertions(+), 27 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 28bd38303d70..de951d6aa9a8 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/pmu.c b/arch/x86/kvm/pmu.c
index edb89b51b383..9ae07db6f0f6 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/x86.c b/arch/x86/kvm/x86.c
index a6b9bea62fb8..6f24a8c1e136 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12820,6 +12820,9 @@ 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)))
-- 
2.42.0.515.g380fc7ccd1-goog