[PATCH v4 5/7] 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             | 16 ++++++++++++++--
 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                 |  7 +++++++
 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 3776cf5382a2..c8bff1e9325e 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -79,6 +79,7 @@ KVM_X86_OP(inject_exception)
 KVM_X86_OP(cancel_injection)
 KVM_X86_OP(interrupt_allowed)
 KVM_X86_OP(nmi_allowed)
+KVM_X86_OP_OPTIONAL(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 c470e40a00aa..2e445fbc6796 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1860,6 +1860,7 @@ 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 61e1e54deb07..2483357bdd97 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -5371,6 +5371,8 @@ static void __sev_snp_inject(enum inject_type type, struct kvm_vcpu *vcpu)
 
 	if (type == INJECT_NMI)
 		hvdb->events.nmi = 1;
+	else if (type == INJECT_MCE)
+		hvdb->events.mce = 1;
 	else
 		hvdb->events.vector = vcpu->arch.interrupt.nr;
 
@@ -5386,6 +5388,11 @@ 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,
@@ -5454,7 +5461,7 @@ void sev_snp_cancel_injection(struct kvm_vcpu *vcpu)
 
 	/*
 	 * KVM only injects a single event each time (prepare_hv_injection),
-	 * so when events.nmi is true, the vector will be zero
+	 * so when events.nmi is true, the MCE and vector will be zero.
 	 */
 	if (hvdb->events.vector)
 		svm->vmcb->control.event_inj |= hvdb->events.vector |
@@ -5463,6 +5470,9 @@ 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.pending_events = 0;
 
 out:
@@ -5488,9 +5498,11 @@ bool sev_snp_blocked(enum inject_type type, struct kvm_vcpu *vcpu)
 	if (!hvdb)
 		return true;
 
-	/* Indicate NMIs and interrupts blocked based on guest acknowledgment */
+	/* Indicate NMIs, MCEs and interrupts blocked based on guest acknowledgment */
 	if (type == INJECT_NMI)
 		blocked = hvdb->events.nmi;
+	else if (type == INJECT_MCE)
+		blocked = hvdb->events.mce;
 	else
 		blocked = !!hvdb->events.vector;
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 925e284374b6..68bf30ab3a12 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4038,6 +4038,22 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
 	return 1;
 }
 
+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);
@@ -5351,6 +5367,7 @@ 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 16cb76b9fdd5..9254a463041a 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -58,6 +58,7 @@ extern struct kvm_x86_ops svm_x86_ops __initdata;
 enum inject_type {
 	INJECT_IRQ,
 	INJECT_NMI,
+	INJECT_MCE,
 };
 
 /*
@@ -798,6 +799,7 @@ 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 dbebddf648be..f9c4703dda54 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -812,6 +812,15 @@ 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))
@@ -945,6 +954,7 @@ 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 a29896a9ef14..7aa728c1e946 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5210,6 +5210,11 @@ int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
 	return !vmx_interrupt_blocked(vcpu);
 }
 
+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 d09abeac2b56..b75dfe7f039d 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -92,6 +92,7 @@ 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 0a1b63c63d1a..420f1ec0dcfb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10789,6 +10789,12 @@ 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_except;
+		}
+
 		kvm_inject_exception(vcpu);
 
 		vcpu->arch.exception.pending = false;
@@ -10796,6 +10802,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
 
 		can_inject = false;
 	}
+out_except:
 
 	/* Don't inject interrupts if the user asked to avoid doing so */
 	if (vcpu->guest_debug & KVM_GUESTDBG_BLOCKIRQ)
-- 
2.43.0