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

Detect that restricted injection feature is active for the guest, 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            |  1 +
 arch/x86/kvm/vmx/vmx.c             |  5 +++++
 arch/x86/kvm/vmx/x86_ops.h         |  1 +
 arch/x86/kvm/x86.c                 |  8 ++++++++
 9 files changed, 50 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 68ad4f923664..9e5764a8e031 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -76,6 +76,7 @@ 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 94e7b5a4fafe..cb1608a69144 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1715,6 +1715,7 @@ 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 9102f7e39c52..0b898b16026b 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -5072,6 +5072,8 @@ static bool __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;
 
@@ -5089,6 +5091,11 @@ 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) {
+		if (__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,
@@ -5153,7 +5160,7 @@ 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 |
@@ -5162,6 +5169,9 @@ 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:
@@ -5179,9 +5189,11 @@ 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 d9c572344f0c..1c13c5da6eea 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3867,6 +3867,22 @@ 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);
@@ -5066,6 +5082,7 @@ static 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 f60ff6229ff4..0cf32954589f 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -44,6 +44,7 @@ extern int lbrv;
 enum inject_type {
 	INJECT_IRQ,
 	INJECT_NMI,
+	INJECT_MCE,
 };
 
 /*
@@ -602,6 +603,7 @@ 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 0bf35ebe8a1b..c3a49a3b7f21 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -84,6 +84,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.cancel_injection = vmx_cancel_injection,
 	.interrupt_allowed = vmx_interrupt_allowed,
 	.nmi_allowed = vmx_nmi_allowed,
+	.mce_allowed = vmx_mce_allowed,
 	.get_nmi_mask = vmx_get_nmi_mask,
 	.set_nmi_mask = vmx_set_nmi_mask,
 	.enable_nmi_window = vmx_enable_nmi_window,
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index f18c2d8c7476..b3dce5d95329 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5093,6 +5093,11 @@ 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 ce3221cd1d01..b2b1a3bb4eb3 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 70219e406987..2007598af873 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -10485,6 +10485,12 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *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;
@@ -10493,6 +10499,8 @@ 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)
 		return 0;
-- 
2.34.1

Hello

On Tue, Sep 10, 2024 at 2:06 PM Melody Wang <huibo.wang@amd.com> wrote:

> @@ -5153,7 +5160,7 @@ 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
>          */

This comment seems ambiguous, and in the following code,
events.nmi/mce/vector appears to be able to be true simultaneously,
rather than being mutually exclusive.


>         if (hvdb->events.vector)
>                 svm->vmcb->control.event_inj |= hvdb->events.vector |
> @@ -5162,6 +5169,9 @@ 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;