[PATCH v1] KVM: VMX: enable guest access to LMCE related MSRs

[Haozhong Zhang]

On Intel platforms, this patch adds LMCE to KVM MCE supported
capabilities and handles guest access to LMCE related MSRs.

Signed-off-by: Ashok Raj <ashok.raj@xxxxxxxxx>
Signed-off-by: Haozhong Zhang <haozhong.zhang@xxxxxxxxx>
---
 arch/x86/include/asm/kvm_host.h |  3 +++
 arch/x86/kvm/vmx.c              | 27 +++++++++++++++++++++++++--
 arch/x86/kvm/x86.c              | 12 ++++++------
 3 files changed, 34 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e0fbe7e..89509f9d 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -598,6 +598,7 @@ struct kvm_vcpu_arch {
 	u64 mcg_cap;
 	u64 mcg_status;
 	u64 mcg_ctl;
+	u64 mcg_ext_ctl;
 	u64 *mce_banks;
 
 	/* Cache MMIO info */
@@ -1077,6 +1078,8 @@ extern u8   kvm_tsc_scaling_ratio_frac_bits;
 /* maximum allowed value of TSC scaling ratio */
 extern u64  kvm_max_tsc_scaling_ratio;
 
+extern u64 kvm_mce_cap_supported;
+
 enum emulation_result {
 	EMULATE_DONE,         /* no further processing */
 	EMULATE_USER_EXIT,    /* kvm_run ready for userspace exit */
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index fb93010..42c3ee1 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2863,6 +2863,11 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 	return 0;
 }
 
+static inline bool vmx_feature_control_msr_required(struct kvm_vcpu *vcpu)
+{
+	return nested_vmx_allowed(vcpu) || (vcpu->arch.mcg_cap & MCG_LMCE_P);
+}
+
 /*
  * Reads an msr value (of 'msr_index') into 'pdata'.
  * Returns 0 on success, non-0 otherwise.
@@ -2904,8 +2909,15 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		msr_info->data = vmcs_read64(GUEST_BNDCFGS);
 		break;
+	case MSR_IA32_MCG_EXT_CTL:
+		if (!(vcpu->arch.mcg_cap & MCG_LMCE_P) ||
+		    !(to_vmx(vcpu)->nested.msr_ia32_feature_control &
+		      FEATURE_CONTROL_LMCE))
+			return 1;
+		msr_info->data = vcpu->arch.mcg_ext_ctl;
+		break;
 	case MSR_IA32_FEATURE_CONTROL:
-		if (!nested_vmx_allowed(vcpu))
+		if (!vmx_feature_control_msr_required(vcpu))
 			return 1;
 		msr_info->data = to_vmx(vcpu)->nested.msr_ia32_feature_control;
 		break;
@@ -2997,8 +3009,17 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_TSC_ADJUST:
 		ret = kvm_set_msr_common(vcpu, msr_info);
 		break;
+	case MSR_IA32_MCG_EXT_CTL:
+		if (!(vcpu->arch.mcg_cap & MCG_LMCE_P) ||
+		    !(to_vmx(vcpu)->nested.msr_ia32_feature_control &
+		      FEATURE_CONTROL_LMCE))
+			return 1;
+		if (data && data != 0x1)
+			return -1;
+		vcpu->arch.mcg_ext_ctl = data;
+		break;
 	case MSR_IA32_FEATURE_CONTROL:
-		if (!nested_vmx_allowed(vcpu) ||
+		if (!vmx_feature_control_msr_required(vcpu) ||
 		    (to_vmx(vcpu)->nested.msr_ia32_feature_control &
 		     FEATURE_CONTROL_LOCKED && !msr_info->host_initiated))
 			return 1;
@@ -6391,6 +6412,8 @@ static __init int hardware_setup(void)
 
 	kvm_set_posted_intr_wakeup_handler(wakeup_handler);
 
+	kvm_mce_cap_supported |= MCG_LMCE_P;
+
 	return alloc_kvm_area();
 
 out8:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 902d9da..0cc8f00 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -70,7 +70,8 @@
 
 #define MAX_IO_MSRS 256
 #define KVM_MAX_MCE_BANKS 32
-#define KVM_MCE_CAP_SUPPORTED (MCG_CTL_P | MCG_SER_P)
+u64 __read_mostly kvm_mce_cap_supported = MCG_CTL_P | MCG_SER_P;
+EXPORT_SYMBOL_GPL(kvm_mce_cap_supported);
 
 #define emul_to_vcpu(ctxt) \
 	container_of(ctxt, struct kvm_vcpu, arch.emulate_ctxt)
@@ -982,6 +983,7 @@ static u32 emulated_msrs[] = {
 	MSR_IA32_MISC_ENABLE,
 	MSR_IA32_MCG_STATUS,
 	MSR_IA32_MCG_CTL,
+	MSR_IA32_MCG_EXT_CTL,
 	MSR_IA32_SMBASE,
 };
 
@@ -2683,11 +2685,9 @@ long kvm_arch_dev_ioctl(struct file *filp,
 		break;
 	}
 	case KVM_X86_GET_MCE_CAP_SUPPORTED: {
-		u64 mce_cap;
-
-		mce_cap = KVM_MCE_CAP_SUPPORTED;
 		r = -EFAULT;
-		if (copy_to_user(argp, &mce_cap, sizeof mce_cap))
+		if (copy_to_user(argp, &kvm_mce_cap_supported,
+				 sizeof(kvm_mce_cap_supported)))
 			goto out;
 		r = 0;
 		break;
@@ -2865,7 +2865,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu,
 	r = -EINVAL;
 	if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS)
 		goto out;
-	if (mcg_cap & ~(KVM_MCE_CAP_SUPPORTED | 0xff | 0xff0000))
+	if (mcg_cap & ~(kvm_mce_cap_supported | 0xff | 0xff0000))
 		goto out;
 	r = 0;
 	vcpu->arch.mcg_cap = mcg_cap;
-- 
2.8.3