[PATCHv2 6/7] KVM: nSVM: implement nested VNMI

[Santosh Shukla]

Currently nested_vmcb02_prepare_control func checks and programs bits
(V_TPR,_INTR, _IRQ) in nested mode, To support nested VNMI,
extending the check for VNMI bits if VNMI is enabled and
on vmexit save V_NMI_MASK/PENDING state to vmcb12.

Tested with the KVM-unit-test and Nested Guest scenario.

Signed-off-by: Santosh Shukla <santosh.shukla@xxxxxxx>
---
v2:
- Save the V_NMI_PENDING/MASK state in vmcb12 on vmexit.
- Tested nested environment - L1 injecting vnmi to L2.
- Tested vnmi in kvm-unit-test.

 arch/x86/kvm/svm/nested.c | 16 +++++++++++++++-
 arch/x86/kvm/svm/svm.c    |  5 +++++
 arch/x86/kvm/svm/svm.h    |  6 ++++++
 3 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index ba7cd26f438f..f97651f317a0 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -629,6 +629,9 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
 	else
 		int_ctl_vmcb01_bits |= (V_GIF_MASK | V_GIF_ENABLE_MASK);
 
+	if (nested_vnmi_enabled(svm))
+		int_ctl_vmcb12_bits |= (V_NMI_PENDING | V_NMI_ENABLE);
+
 	/* 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;
@@ -951,10 +954,21 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	vmcb12->control.event_inj         = svm->nested.ctl.event_inj;
 	vmcb12->control.event_inj_err     = svm->nested.ctl.event_inj_err;
 
+	if (nested_vnmi_enabled(svm)) {
+		if (vmcb02->control.int_ctl & V_NMI_MASK)
+			vmcb12->control.int_ctl |= V_NMI_MASK;
+		else
+			vmcb12->control.int_ctl &= ~V_NMI_MASK;
+
+		if (vmcb02->control.int_ctl & V_NMI_PENDING)
+			vmcb12->control.int_ctl |= V_NMI_PENDING;
+		else
+			vmcb12->control.int_ctl &= ~V_NMI_PENDING;
+	}
+
 	if (!kvm_pause_in_guest(vcpu->kvm)) {
 		vmcb01->control.pause_filter_count = vmcb02->control.pause_filter_count;
 		vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS);
-
 	}
 
 	nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index c73a1809a7c7..d81ad913542d 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4069,6 +4069,8 @@ 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_V_NMI);
+
 	svm_recalc_instruction_intercepts(vcpu, svm);
 
 	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
@@ -4827,6 +4829,9 @@ 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_V_NMI);
+
 		/* Nested VM can receive #VMEXIT instead of triggering #GP */
 		kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK);
 	}
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index f36e30df6202..0094ca2698fa 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -241,6 +241,7 @@ 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;
@@ -510,6 +511,11 @@ 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);
+}
+
 static inline struct vmcb *get_vnmi_vmcb(struct vcpu_svm *svm)
 {
 	if (!vnmi)
-- 
2.25.1