KVM: TDX: Implement callbacks for MSR operations

Add functions to implement MSR related callbacks, .set_msr(), .get_msr(),
and .has_emulated_msr(), for preparation of handling hypercalls from TDX
guest for PV RDMSR and WRMSR.  Ignore KVM_REQ_MSR_FILTER_CHANGED for TDX.

There are three classes of MSR virtualization for TDX.
- Non-configurable: TDX module directly virtualizes it. VMM can't configure
  it, the value set by KVM_SET_MSRS is ignored.
- Configurable: TDX module directly virtualizes it. VMM can configure it at
  VM creation time.  The value set by KVM_SET_MSRS is used.
- #VE case: TDX guest would issue TDG.VP.VMCALL<INSTRUCTION.{WRMSR,RDMSR}>
  and VMM handles the MSR hypercall. The value set by KVM_SET_MSRS is used.

For the MSRs belonging to the #VE case, the TDX module injects #VE to the
TDX guest upon RDMSR or WRMSR.  The exact list of such MSRs is defined in
TDX Module ABI Spec.

Upon #VE, the TDX guest may call TDG.VP.VMCALL<INSTRUCTION.{WRMSR,RDMSR}>,
which are defined in GHCI (Guest-Host Communication Interface) so that the
host VMM (e.g. KVM) can virtualize the MSRs.

TDX doesn't allow VMM to configure interception of MSR accesses.  Ignore
KVM_REQ_MSR_FILTER_CHANGED for TDX guest.  If the userspace has set any
MSR filters, it will be applied when handling
TDG.VP.VMCALL<INSTRUCTION.{WRMSR,RDMSR}> in a later patch.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
Co-developed-by: Binbin Wu <binbin.wu@linux.intel.com>
Signed-off-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <20250227012021.1778144-9-binbin.wu@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Author: yamahata

arch/x86/kvm/vmx/main.c

@@ -193,6 +193,48 @@ static int vt_handle_exit(struct kvm_vcpu *vcpu,
 	return vmx_handle_exit(vcpu, fastpath);
 }
 
+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_has_emulated_msr(index);
+
+	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_msr_filter_changed(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * TDX doesn't allow VMM to configure interception of MSR accesses.
+	 * TDX guest requests MSR accesses by calling TDVMCALL.  The MSR
+	 * filters will be applied when handling the TDVMCALL for RDMSR/WRMSR
+	 * if the userspace has set any.
+	 */
+	if (is_td_vcpu(vcpu))
+		return;
+
+	vmx_msr_filter_changed(vcpu);
+}
+
 #ifdef CONFIG_KVM_SMM
 static int vt_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
 {
@@ -516,7 +558,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.disable_virtualization_cpu = vt_disable_virtualization_cpu,
 	.emergency_disable_virtualization_cpu = vmx_emergency_disable_virtualization_cpu,
 
-	.has_emulated_msr = vmx_has_emulated_msr,
+	.has_emulated_msr = vt_has_emulated_msr,
 
 	.vm_size = sizeof(struct kvm_vmx),
 
@@ -535,8 +577,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 
 	.update_exception_bitmap = vmx_update_exception_bitmap,
 	.get_feature_msr = vmx_get_feature_msr,
-	.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,
@@ -643,7 +685,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.apic_init_signal_blocked = vt_apic_init_signal_blocked,
 	.migrate_timers = vmx_migrate_timers,
 
-	.msr_filter_changed = vmx_msr_filter_changed,
+	.msr_filter_changed = vt_msr_filter_changed,
 	.complete_emulated_msr = kvm_complete_insn_gp,
 
 	.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,

arch/x86/kvm/vmx/tdx.c

@@ -2028,6 +2028,73 @@ void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
 	*error_code = 0;
 }
 
+bool tdx_has_emulated_msr(u32 index)
+{
+	switch (index) {
+	case MSR_IA32_UCODE_REV:
+	case MSR_IA32_ARCH_CAPABILITIES:
+	case MSR_IA32_POWER_CTL:
+	case MSR_IA32_CR_PAT:
+	case MSR_IA32_TSC_DEADLINE:
+	case MSR_IA32_MISC_ENABLE:
+	case MSR_PLATFORM_INFO:
+	case MSR_MISC_FEATURES_ENABLES:
+	case MSR_IA32_APICBASE:
+	case MSR_EFER:
+	case MSR_IA32_MCG_CAP:
+	case MSR_IA32_MCG_STATUS:
+	case MSR_IA32_MCG_CTL:
+	case MSR_IA32_MCG_EXT_CTL:
+	case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
+	case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1:
+		/* MSR_IA32_MCx_{CTL, STATUS, ADDR, MISC, CTL2} */
+	case MSR_KVM_POLL_CONTROL:
+		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;
+		}
+	default:
+		return false;
+	}
+}
+
+static bool tdx_is_read_only_msr(u32 index)
+{
+	return  index == MSR_IA32_APICBASE || index == MSR_EFER;
+}
+
+int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
+{
+	if (!tdx_has_emulated_msr(msr->index))
+		return 1;
+
+	return kvm_get_msr_common(vcpu, msr);
+}
+
+int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
+{
+	if (tdx_is_read_only_msr(msr->index))
+		return 1;
+
+	if (!tdx_has_emulated_msr(msr->index))
+		return 1;
+
+	return kvm_set_msr_common(vcpu, msr);
+}
+
 static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd)
 {
 	const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf;

arch/x86/kvm/vmx/x86_ops.h

@@ -144,6 +144,9 @@ void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
 void tdx_inject_nmi(struct kvm_vcpu *vcpu);
 void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
 		u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code);
+bool tdx_has_emulated_msr(u32 index);
+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_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp);
 
@@ -187,6 +190,9 @@ static inline void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mo
 static inline void tdx_inject_nmi(struct kvm_vcpu *vcpu) {}
 static inline void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, u64 *info1,
 				     u64 *info2, u32 *intr_info, u32 *error_code) {}
+static inline bool tdx_has_emulated_msr(u32 index) { return false; }
+static inline int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { return 1; }
+static inline int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { return 1; }
 
 static inline int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp) { return -EOPNOTSUPP; }