KVM: TDX: Implement callbacks for MSR operations for TDX

Implements set_msr/get_msr/has_emulated_msr methods for TDX.  The TDX
module handles some MSRs and VMM handles some MSRs.  The TDX module
specification defines it.  Without explicit allowance, KVM doesn't handle
MSRs.

Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>

arch/x86/kvm/vmx/main.c

@@ -167,6 +167,34 @@ static void vt_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 	vmx_handle_exit_irqoff(vcpu);
 }
 
+static int vt_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+	if (unlikely(is_td_vcpu(vcpu)))
+		return tdx_set_msr(vcpu, msr_info);
+
+	return vmx_set_msr(vcpu, msr_info);
+}
+
+/*
+ * The kvm parameter can be NULL (module initialization, or invocation before
+ * VM creation). Be sure to check the kvm parameter before using it.
+ */
+static bool vt_has_emulated_msr(struct kvm *kvm, u32 index)
+{
+	if (kvm && is_td(kvm))
+		return tdx_is_emulated_msr(index, true);
+
+	return vmx_has_emulated_msr(kvm, index);
+}
+
+static int vt_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+	if (unlikely(is_td_vcpu(vcpu)))
+		return tdx_get_msr(vcpu, msr_info);
+
+	return vmx_get_msr(vcpu, msr_info);
+}
+
 static void vt_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 {
 	if (is_td_vcpu(vcpu))
@@ -358,7 +386,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.hardware_enable = vt_hardware_enable,
 	.hardware_disable = vt_hardware_disable,
 	.cpu_has_accelerated_tpr = report_flexpriority,
-	.has_emulated_msr = vmx_has_emulated_msr,
+	.has_emulated_msr = vt_has_emulated_msr,
 
 	.is_vm_type_supported = vt_is_vm_type_supported,
 	.vm_size = sizeof(struct kvm_vmx),
@@ -376,8 +404,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 
 	.update_exception_bitmap = vmx_update_exception_bitmap,
 	.get_msr_feature = vmx_get_msr_feature,
-	.get_msr = vmx_get_msr,
-	.set_msr = vmx_set_msr,
+	.get_msr = vt_get_msr,
+	.set_msr = vt_set_msr,
 	.get_segment_base = vmx_get_segment_base,
 	.get_segment = vmx_get_segment,
 	.set_segment = vmx_set_segment,

arch/x86/kvm/vmx/tdx.c

@@ -1210,6 +1210,62 @@ void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
 	*error_code = 0;
 }
 
+bool tdx_is_emulated_msr(u32 index, bool write)
+{
+	switch (index) {
+	case MSR_IA32_UCODE_REV:
+	case MSR_IA32_ARCH_CAPABILITIES:
+	case MSR_IA32_POWER_CTL:
+	case MSR_MTRRcap:
+	case 0x200 ... 0x2ff:
+	case MSR_IA32_TSC_DEADLINE:
+	case MSR_IA32_MISC_ENABLE:
+	case MSR_KVM_STEAL_TIME:
+	case MSR_KVM_POLL_CONTROL:
+	case MSR_PLATFORM_INFO:
+	case MSR_MISC_FEATURES_ENABLES:
+	case MSR_IA32_MCG_CTL:
+	case MSR_IA32_MCG_STATUS:
+	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(32) - 1:
+		return true;
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
+		/*
+		 * x2APIC registers that are virtualized by the CPU can't be
+		 * emulated, KVM doesn't have access to the virtual APIC page.
+		 */
+		switch (index) {
+		case X2APIC_MSR(APIC_TASKPRI):
+		case X2APIC_MSR(APIC_PROCPRI):
+		case X2APIC_MSR(APIC_EOI):
+		case X2APIC_MSR(APIC_ISR) ... X2APIC_MSR(APIC_ISR + APIC_ISR_NR):
+		case X2APIC_MSR(APIC_TMR) ... X2APIC_MSR(APIC_TMR + APIC_ISR_NR):
+		case X2APIC_MSR(APIC_IRR) ... X2APIC_MSR(APIC_IRR + APIC_ISR_NR):
+			return false;
+		default:
+			return true;
+		}
+	case MSR_IA32_APICBASE:
+	case MSR_EFER:
+		return !write;
+	default:
+		return false;
+	}
+}
+
+int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
+{
+	if (tdx_is_emulated_msr(msr->index, false))
+		return kvm_get_msr_common(vcpu, msr);
+	return 1;
+}
+
+int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
+{
+	if (tdx_is_emulated_msr(msr->index, true))
+		return kvm_set_msr_common(vcpu, msr);
+	return 1;
+}
+
 int tdx_dev_ioctl(void __user *argp)
 {
 	struct kvm_tdx_capabilities __user *user_caps;

arch/x86/kvm/vmx/tdx_stubs.c

@@ -17,6 +17,9 @@ void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) {}
 void tdx_handle_exit_irqoff(struct kvm_vcpu *vcpu) {}
 int tdx_handle_exit(struct kvm_vcpu *vcpu,
 		enum exit_fastpath_completion fastpath) { return 0; }
+bool tdx_is_emulated_msr(u32 index, bool write) { return false; }
+int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { return 1; }
+int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { return 1; }
 
 void tdx_apicv_post_state_restore(struct kvm_vcpu *vcpu) {}
 int tdx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) { return 0; }

arch/x86/kvm/vmx/x86_ops.h

@@ -146,6 +146,9 @@ void tdx_apicv_post_state_restore(struct kvm_vcpu *vcpu);
 int tdx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector);
 void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
 		u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code);
+bool tdx_is_emulated_msr(u32 index, bool write);
+int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
+int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
 
 int tdx_dev_ioctl(void __user *argp);
 int tdx_vm_ioctl(struct kvm *kvm, void __user *argp);