[RFC PATCH v5 5/8] KVM: SVM: Inject MCEs when Restricted Injection is active

[Melody Wang <huibo.wang@amd.com>]

When Restricted Injection is active, only #HV exceptions can be injected
into the SEV-SNP guest.

Detect that, and then follow the #HV doorbell communication from the
GHCB specification to inject the MCEs.

Co-developed-by: Thomas Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Thomas Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Melody Wang <huibo.wang@amd.com>
---
 arch/x86/include/asm/kvm-x86-ops.h |  1 +
 arch/x86/include/asm/kvm_host.h    |  1 +
 arch/x86/kvm/svm/sev.c             | 17 +++++++++++++++--
 arch/x86/kvm/svm/svm.c             | 17 +++++++++++++++++
 arch/x86/kvm/svm/svm.h             |  2 ++
 arch/x86/kvm/vmx/main.c            | 10 ++++++++++
 arch/x86/kvm/vmx/vmx.c             |  5 +++++
 arch/x86/kvm/vmx/x86_ops.h         |  1 +
 arch/x86/kvm/x86.c                 |  6 ++++++
 9 files changed, 58 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 2074c2050c55..e3da9fb0b2b6 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -80,6 +80,7 @@ KVM_X86_OP(inject_exception)
 KVM_X86_OP(cancel_injection)
 KVM_X86_OP(interrupt_allowed)
 KVM_X86_OP(nmi_allowed)
+KVM_X86_OP(mce_allowed)
 KVM_X86_OP(get_nmi_mask)
 KVM_X86_OP(set_nmi_mask)
 KVM_X86_OP(enable_nmi_window)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 4de443140c53..fa83477ebcab 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1606,6 +1606,7 @@ struct kvm_x86_ops {
 	void (*cancel_injection)(struct kvm_vcpu *vcpu);
 	int (*interrupt_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
 	int (*nmi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
+	int (*mce_allowed)(struct kvm_vcpu *vcpu);
 	bool (*get_nmi_mask)(struct kvm_vcpu *vcpu);
 	void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked);
 	/* Whether or not a virtual NMI is pending in hardware. */
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index f80dfd876d5e..6a1262c274ff 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -5565,7 +5565,9 @@ static void __sev_snp_inject(enum inject_type type, struct kvm_vcpu *vcpu)
 		return;
 	}
 
-	if (type == INJECT_NMI) {
+	if (type == INJECT_MCE) {
+		hvdb->events.mce = 1;
+	} else if (type == INJECT_NMI) {
 		hvdb->events.nmi = 1;
 	} else if (type == INJECT_IRQ) {
 		hvdb->events.vector = vcpu->arch.interrupt.nr;
@@ -5602,6 +5604,11 @@ bool sev_snp_queue_exception(struct kvm_vcpu *vcpu)
 	if (!sev_snp_is_rinj_active(vcpu))
 		return false;
 
+	if (vcpu->arch.exception.vector == MC_VECTOR) {
+		__sev_snp_inject(INJECT_MCE, vcpu);
+		return true;
+	}
+
 	/*
 	 * Restricted Injection is enabled, only #HV is supported.
 	 * If the vector is not HV_VECTOR, do not inject the exception,
@@ -5682,6 +5689,10 @@ void sev_snp_cancel_injection(struct kvm_vcpu *vcpu)
 	if (hvdb->events.nmi)
 		svm->vmcb->control.event_inj |= SVM_EVTINJ_TYPE_NMI;
 
+	if (hvdb->events.mce)
+		svm->vmcb->control.event_inj |= MC_VECTOR | SVM_EVTINJ_TYPE_EXEPT;
+
+
 	hvdb->events.no_further_signal = 0;
 	svm->sev_es.cancel_flag = true;
 
@@ -5702,7 +5713,9 @@ bool sev_snp_blocked(enum inject_type type, struct kvm_vcpu *vcpu)
 		return true;
 
 	/* Indicate interrupts blocked based on guest acknowledgment */
-	if (type == INJECT_NMI)
+	if (type == INJECT_MCE)
+		blocked = hvdb->events.mce;
+	else if (type == INJECT_NMI)
 		blocked = hvdb->events.nmi;
 	else if (type == INJECT_IRQ) {
 		irq = kvm_cpu_get_interrupt(vcpu);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 75e86592f1c9..ad99b2b1b07b 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4114,6 +4114,22 @@ static bool svm_is_noack_required(struct kvm_vcpu *vcpu)
 	return true;
 }
 
+bool svm_mce_blocked(struct kvm_vcpu *vcpu)
+{
+	if (sev_snp_is_rinj_active(vcpu))
+		return sev_snp_blocked(INJECT_MCE, vcpu);
+
+	return false;
+}
+
+static int svm_mce_allowed(struct kvm_vcpu *vcpu)
+{
+	if (svm_mce_blocked(vcpu))
+		return 0;
+
+	return 1;
+}
+
 static void svm_enable_irq_window(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -5429,6 +5445,7 @@ struct kvm_x86_ops svm_x86_ops __initdata = {
 	.cancel_injection = svm_cancel_injection,
 	.interrupt_allowed = svm_interrupt_allowed,
 	.nmi_allowed = svm_nmi_allowed,
+	.mce_allowed = svm_mce_allowed,
 	.get_nmi_mask = svm_get_nmi_mask,
 	.set_nmi_mask = svm_set_nmi_mask,
 	.enable_nmi_window = svm_enable_nmi_window,
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 2909f57508de..e19b398a3df5 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -61,6 +61,7 @@ extern struct kvm_x86_ops svm_x86_ops __initdata;
 enum inject_type {
 	INJECT_IRQ,
 	INJECT_NMI,
+	INJECT_MCE,
 };
 
 /*
@@ -826,6 +827,7 @@ void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
 void disable_nmi_singlestep(struct vcpu_svm *svm);
 bool svm_smi_blocked(struct kvm_vcpu *vcpu);
 bool svm_nmi_blocked(struct kvm_vcpu *vcpu);
+bool svm_mce_blocked(struct kvm_vcpu *vcpu);
 bool svm_interrupt_blocked(struct kvm_vcpu *vcpu);
 void svm_set_gif(struct vcpu_svm *svm, bool value);
 int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code);
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 4c52ab8d0786..e083e2965cd9 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -828,6 +828,15 @@ static void vt_cancel_hv_timer(struct kvm_vcpu *vcpu)
 }
 #endif
 
+static int vt_mce_allowed(struct kvm_vcpu *vcpu)
+{
+	if (is_td_vcpu(vcpu))
+		return 0;
+
+	return vmx_mce_allowed(vcpu);
+}
+
+
 static void vt_setup_mce(struct kvm_vcpu *vcpu)
 {
 	if (is_td_vcpu(vcpu))
@@ -962,6 +971,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.cancel_injection = vt_op(cancel_injection),
 	.interrupt_allowed = vt_op(interrupt_allowed),
 	.nmi_allowed = vt_op(nmi_allowed),
+	.mce_allowed = vt_op(mce_allowed),
 	.get_nmi_mask = vt_op(get_nmi_mask),
 	.set_nmi_mask = vt_op(set_nmi_mask),
 	.enable_nmi_window = vt_op(enable_nmi_window),
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 612ab07d4100..2b391c282b51 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5273,6 +5273,11 @@ int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
 	return 1;
 }
 
+int vmx_mce_allowed(struct kvm_vcpu *vcpu)
+{
+	return 1;
+}
+
 int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
 {
 	void __user *ret;
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 054fd14bb2e1..f68316638f21 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -93,6 +93,7 @@ void vmx_inject_exception(struct kvm_vcpu *vcpu);
 void vmx_cancel_injection(struct kvm_vcpu *vcpu);
 int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection);
 int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection);
+int vmx_mce_allowed(struct kvm_vcpu *vcpu);
 bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu);
 void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
 void vmx_enable_nmi_window(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 79468ddfe473..1492a06a6935 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7673,6 +7673,12 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
 			kvm_update_dr7(vcpu);
 		}
 
+		if (vcpu->arch.exception.vector == MC_VECTOR) {
+			r = static_call(kvm_x86_mce_allowed)(vcpu);
+			if (!r)
+				goto out;
+		}
+
 		kvm_inject_exception(vcpu);
 
 		vcpu->arch.exception.pending = false;
-- 
2.43.0