KVM: nSVM: Implement support for nested VNMI

Allow L1 to use vNMI to accelerate its injection of NMI to L2 by
propagating vNMI int_ctl bits from/to vmcb12 to/from vmcb02.

To handle both the case where vNMI is enabled for L1 and L2, and where
vNMI is enabled for L1 but _not_ L2, move pending L1 vNMIs to nmi_pending
on nested VM-Entry and raise KVM_REQ_EVENT, i.e. rely on existing code to
route the NMI to the correct domain.

On nested VM-Exit, reverse the process and set/clear V_NMI_PENDING for L1
based one whether nmi_pending is zero or non-zero.  There is no need to
consider vmcb02 in this case, as V_NMI_PENDING can be set in vmcb02 if
vNMI is disabled for L2, and if vNMI is enabled for L2, then L1 and L2
have different NMI contexts.

Co-developed-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Signed-off-by: Santosh Shukla <santosh.shukla@amd.com>
Link: https://lore.kernel.org/r/20230227084016.3368-12-santosh.shukla@amd.com
[sean: massage changelog to match the code]
Signed-off-by: Sean Christopherson <seanjc@google.com>

Author: sashukla1

arch/x86/kvm/svm/nested.c

@@ -281,6 +281,11 @@ static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu,
 	if (CC(!nested_svm_check_tlb_ctl(vcpu, control->tlb_ctl)))
 		return false;
 
+	if (CC((control->int_ctl & V_NMI_ENABLE_MASK) &&
+	       !vmcb12_is_intercept(control, INTERCEPT_NMI))) {
+		return false;
+	}
+
 	return true;
 }
 
@@ -436,6 +441,9 @@ void nested_sync_control_from_vmcb02(struct vcpu_svm *svm)
 	if (nested_vgif_enabled(svm))
 		mask |= V_GIF_MASK;
 
+	if (nested_vnmi_enabled(svm))
+		mask |= V_NMI_BLOCKING_MASK | V_NMI_PENDING_MASK;
+
 	svm->nested.ctl.int_ctl        &= ~mask;
 	svm->nested.ctl.int_ctl        |= svm->vmcb->control.int_ctl & mask;
 }
@@ -655,6 +663,17 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
 	else
 		int_ctl_vmcb01_bits |= (V_GIF_MASK | V_GIF_ENABLE_MASK);
 
+	if (vnmi) {
+		if (vmcb01->control.int_ctl & V_NMI_PENDING_MASK) {
+			svm->vcpu.arch.nmi_pending++;
+			kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
+		}
+		if (nested_vnmi_enabled(svm))
+			int_ctl_vmcb12_bits |= (V_NMI_PENDING_MASK |
+						V_NMI_ENABLE_MASK |
+						V_NMI_BLOCKING_MASK);
+	}
+
 	/* Copied from vmcb01.  msrpm_base can be overwritten later.  */
 	vmcb02->control.nested_ctl = vmcb01->control.nested_ctl;
 	vmcb02->control.iopm_base_pa = vmcb01->control.iopm_base_pa;
@@ -1055,6 +1074,20 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 		svm_update_lbrv(vcpu);
 	}
 
+	if (vnmi) {
+		if (vmcb02->control.int_ctl & V_NMI_BLOCKING_MASK)
+			vmcb01->control.int_ctl |= V_NMI_BLOCKING_MASK;
+		else
+			vmcb01->control.int_ctl &= ~V_NMI_BLOCKING_MASK;
+
+		if (vcpu->arch.nmi_pending) {
+			vcpu->arch.nmi_pending--;
+			vmcb01->control.int_ctl |= V_NMI_PENDING_MASK;
+		} else {
+			vmcb01->control.int_ctl &= ~V_NMI_PENDING_MASK;
+		}
+	}
+
 	/*
 	 * On vmexit the  GIF is set to false and
 	 * no event can be injected in L1.

arch/x86/kvm/svm/svm.c

@@ -4246,6 +4246,8 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 
 	svm->vgif_enabled = vgif && guest_cpuid_has(vcpu, X86_FEATURE_VGIF);
 
+	svm->vnmi_enabled = vnmi && guest_cpuid_has(vcpu, X86_FEATURE_VNMI);
+
 	svm_recalc_instruction_intercepts(vcpu, svm);
 
 	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
@@ -5001,6 +5003,9 @@ static __init void svm_set_cpu_caps(void)
 		if (vgif)
 			kvm_cpu_cap_set(X86_FEATURE_VGIF);
 
+		if (vnmi)
+			kvm_cpu_cap_set(X86_FEATURE_VNMI);
+
 		/* Nested VM can receive #VMEXIT instead of triggering #GP */
 		kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK);
 	}

arch/x86/kvm/svm/svm.h

@@ -266,6 +266,7 @@ struct vcpu_svm {
 	bool pause_filter_enabled         : 1;
 	bool pause_threshold_enabled      : 1;
 	bool vgif_enabled                 : 1;
+	bool vnmi_enabled                 : 1;
 
 	u32 ldr_reg;
 	u32 dfr_reg;
@@ -540,6 +541,12 @@ static inline bool nested_npt_enabled(struct vcpu_svm *svm)
 	return svm->nested.ctl.nested_ctl & SVM_NESTED_CTL_NP_ENABLE;
 }
 
+static inline bool nested_vnmi_enabled(struct vcpu_svm *svm)
+{
+	return svm->vnmi_enabled &&
+	       (svm->nested.ctl.int_ctl & V_NMI_ENABLE_MASK);
+}
+
 static inline bool is_x2apic_msrpm_offset(u32 offset)
 {
 	/* 4 msrs per u8, and 4 u8 in u32 */