[PATCH v2 21/21] KVM:x86: Support CET supervisor shadow stack MSR access

[Yang Weijiang <weijiang.yang@intel.com>]

Add MSR access interfaces for supervisor shadow stack, i.e.,
MSR_IA32_PL{0,1,2} and MSR_IA32_INT_SSP_TAB, meanwhile pass through
them to {L1,L2} guests when {L0,L1} KVM supports supervisor shadow
stack.

Note, currently supervisor shadow stack is not supported on Intel
platforms, i.e., VMX always clears CPUID(EAX=07H,ECX=1).EDX.[bit 18].

The main purpose of this patch is to facilitate AMD folks to enable
supervisor shadow stack for their platforms.

Signed-off-by: Yang Weijiang <weijiang.yang@intel.com>
---
 arch/x86/kvm/cpuid.h      |  6 +++++
 arch/x86/kvm/vmx/nested.c | 12 +++++++++
 arch/x86/kvm/vmx/vmx.c    | 51 ++++++++++++++++++++++++++++++++++-----
 3 files changed, 63 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index b1658c0de847..019a16b25b88 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -232,4 +232,10 @@ static __always_inline bool guest_pv_has(struct kvm_vcpu *vcpu,
 	return vcpu->arch.pv_cpuid.features & (1u << kvm_feature);
 }
 
+static __always_inline bool kvm_cet_kernel_shstk_supported(void)
+{
+	return !IS_ENABLED(CONFIG_KVM_INTEL) &&
+	       kvm_cpu_cap_has(X86_FEATURE_SHSTK);
+}
+
 #endif
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index bf690827bfee..aaaae92dc9f6 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -670,6 +670,18 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
 					 MSR_IA32_PL3_SSP, MSR_TYPE_RW);
 
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_IA32_PL0_SSP, MSR_TYPE_RW);
+
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_IA32_PL1_SSP, MSR_TYPE_RW);
+
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_IA32_PL2_SSP, MSR_TYPE_RW);
+
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_IA32_INT_SSP_TAB, MSR_TYPE_RW);
+
 	kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false);
 
 	vmx->nested.force_msr_bitmap_recalc = false;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 6eab3e452bbb..074b618f1a07 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -713,6 +713,9 @@ static bool is_valid_passthrough_msr(u32 msr)
 	case MSR_IA32_PL3_SSP:
 	case MSR_IA32_S_CET:
 		return true;
+	case MSR_IA32_PL0_SSP ... MSR_IA32_PL2_SSP:
+	case MSR_IA32_INT_SSP_TAB:
+		return true;
 	}
 
 	r = possible_passthrough_msr_slot(msr) != -ENOENT;
@@ -1962,8 +1965,11 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr)
 static bool cet_is_msr_accessible(struct kvm_vcpu *vcpu,
 				  struct msr_data *msr)
 {
+	u64 mask;
+
 	if (!kvm_cet_user_supported() &&
-	    !kvm_cpu_cap_has(X86_FEATURE_IBT))
+	    !(kvm_cpu_cap_has(X86_FEATURE_IBT) ||
+	      kvm_cpu_cap_has(X86_FEATURE_SHSTK)))
 		return false;
 
 	if (msr->host_initiated)
@@ -1973,15 +1979,27 @@ static bool cet_is_msr_accessible(struct kvm_vcpu *vcpu,
 	    !guest_cpuid_has(vcpu, X86_FEATURE_IBT))
 		return false;
 
+	if (msr->index == MSR_IA32_U_CET)
+		return true;
+
 	if (msr->index == MSR_IA32_S_CET)
-		return guest_cpuid_has(vcpu, X86_FEATURE_IBT);
+		return guest_cpuid_has(vcpu, X86_FEATURE_IBT) ||
+		       kvm_cet_kernel_shstk_supported();
 
-	if ((msr->index == MSR_IA32_PL3_SSP ||
-	     msr->index == MSR_KVM_GUEST_SSP) &&
+	if (msr->index == MSR_KVM_GUEST_SSP)
+		return guest_cpuid_has(vcpu, X86_FEATURE_SHSTK);
+
+	if (msr->index == MSR_IA32_INT_SSP_TAB)
+		return guest_cpuid_has(vcpu, X86_FEATURE_SHSTK) &&
+		       kvm_cet_kernel_shstk_supported();
+
+	if (msr->index == MSR_IA32_PL3_SSP &&
 	    !guest_cpuid_has(vcpu, X86_FEATURE_SHSTK))
 		return false;
 
-	return true;
+	mask = (msr->index == MSR_IA32_PL3_SSP) ? XFEATURE_MASK_CET_USER :
+						  XFEATURE_MASK_CET_KERNEL;
+	return !!(kvm_caps.supported_xss & mask);
 }
 
 /*
@@ -2135,6 +2153,12 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		else
 			kvm_get_xsave_msr(msr_info);
 		break;
+	case MSR_IA32_PL0_SSP ... MSR_IA32_PL2_SSP:
+	case MSR_IA32_INT_SSP_TAB:
+		if (!cet_is_msr_accessible(vcpu, msr_info))
+			return 1;
+		kvm_get_xsave_msr(msr_info);
+		break;
 	case MSR_IA32_DEBUGCTLMSR:
 		msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL);
 		break;
@@ -2471,6 +2495,12 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		else
 			kvm_set_xsave_msr(msr_info);
 		break;
+	case MSR_IA32_PL0_SSP ... MSR_IA32_PL2_SSP:
+	case MSR_IA32_INT_SSP_TAB:
+		if (!cet_is_msr_accessible(vcpu, msr_info))
+			return 1;
+		kvm_set_xsave_msr(msr_info);
+		break;
 	case MSR_IA32_PERF_CAPABILITIES:
 		if (data && !vcpu_to_pmu(vcpu)->version)
 			return 1;
@@ -7774,6 +7804,14 @@ static void vmx_update_intercept_for_cet_msr(struct kvm_vcpu *vcpu)
 
 	incpt |= !guest_cpuid_has(vcpu, X86_FEATURE_IBT);
 	vmx_set_intercept_for_msr(vcpu, MSR_IA32_S_CET, MSR_TYPE_RW, incpt);
+
+	incpt = !is_cet_state_supported(vcpu, XFEATURE_MASK_CET_KERNEL);
+	incpt |= !guest_cpuid_has(vcpu, X86_FEATURE_SHSTK);
+
+	vmx_set_intercept_for_msr(vcpu, MSR_IA32_INT_SSP_TAB, MSR_TYPE_RW, incpt);
+	vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL0_SSP, MSR_TYPE_RW, incpt);
+	vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL1_SSP, MSR_TYPE_RW, incpt);
+	vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL2_SSP, MSR_TYPE_RW, incpt);
 }
 
 static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
@@ -7844,7 +7882,8 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	/* Refresh #PF interception to account for MAXPHYADDR changes. */
 	vmx_update_exception_bitmap(vcpu);
 
-	if (kvm_cet_user_supported() || kvm_cpu_cap_has(X86_FEATURE_IBT))
+	if (kvm_cet_user_supported() || kvm_cpu_cap_has(X86_FEATURE_IBT) ||
+	    kvm_cpu_cap_has(X86_FEATURE_SHSTK))
 		vmx_update_intercept_for_cet_msr(vcpu);
 }
 
-- 
2.27.0