KVM/VMX: Emulate MSR_IA32_ARCH_CAPABILITIES

Intel processors use MSR_IA32_ARCH_CAPABILITIES MSR to indicate RDCL_NO
(bit 0) and IBRS_ALL (bit 1). This is a read-only MSR. By default the
contents will come directly from the hardware, but user-space can still
override it.

[dwmw2: The bit in kvm_cpuid_7_0_edx_x86_features can be unconditional]

Signed-off-by: KarimAllah Ahmed <[email protected]>
Signed-off-by: David Woodhouse <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Reviewed-by: Paolo Bonzini <[email protected]>
Reviewed-by: Darren Kenny <[email protected]>
Reviewed-by: Jim Mattson <[email protected]>
Reviewed-by: Konrad Rzeszutek Wilk <[email protected]>
Cc: Andrea Arcangeli <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Jun Nakajima <[email protected]>
Cc: [email protected]
Cc: Dave Hansen <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Asit Mallick <[email protected]>
Cc: Arjan Van De Ven <[email protected]>
Cc: Greg KH <[email protected]>
Cc: Dan Williams <[email protected]>
Cc: Tim Chen <[email protected]>
Cc: Ashok Raj <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

Author: KarimAllah Ahmed

arch/x86/kvm/cpuid.c

@@ -394,7 +394,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 
 	/* cpuid 7.0.edx*/
 	const u32 kvm_cpuid_7_0_edx_x86_features =
-		F(AVX512_4VNNIW) | F(AVX512_4FMAPS);
+		F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(ARCH_CAPABILITIES);
 
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();

arch/x86/kvm/vmx.c

@@ -594,6 +594,8 @@ struct vcpu_vmx {
 	u64 		      msr_guest_kernel_gs_base;
 #endif
 
+	u64 		      arch_capabilities;
+
 	u32 vm_entry_controls_shadow;
 	u32 vm_exit_controls_shadow;
 	u32 secondary_exec_control;
@@ -3260,6 +3262,12 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_TSC:
 		msr_info->data = guest_read_tsc(vcpu);
 		break;
+	case MSR_IA32_ARCH_CAPABILITIES:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES))
+			return 1;
+		msr_info->data = to_vmx(vcpu)->arch_capabilities;
+		break;
 	case MSR_IA32_SYSENTER_CS:
 		msr_info->data = vmcs_read32(GUEST_SYSENTER_CS);
 		break;
@@ -3395,6 +3403,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD,
 					      MSR_TYPE_W);
 		break;
+	case MSR_IA32_ARCH_CAPABILITIES:
+		if (!msr_info->host_initiated)
+			return 1;
+		vmx->arch_capabilities = data;
+		break;
 	case MSR_IA32_CR_PAT:
 		if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
 			if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
@@ -5657,6 +5670,8 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		++vmx->nmsrs;
 	}
 
+	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
+		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities);
 
 	vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl);
 

arch/x86/kvm/x86.c

@@ -1009,6 +1009,7 @@ static u32 msrs_to_save[] = {
 #endif
 	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
 	MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
+	MSR_IA32_ARCH_CAPABILITIES
 };
 
 static unsigned num_msrs_to_save;