Received-SPF: pass (google.com: domain of linux-kernel+bounces-8083-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
From: Yang Weijiang <weijiang.yang@intel.com>
To: seanjc@google.com,
	pbonzini@redhat.com,
	dave.hansen@intel.com,
	kvm@vger.kernel.org,
	linux-kernel@vger.kernel.org
Cc: peterz@infradead.org,
	chao.gao@intel.com,
	rick.p.edgecombe@intel.com,
	mlevitsk@redhat.com,
	john.allen@amd.com,
	weijiang.yang@intel.com
Subject: [PATCH v8 22/26] KVM: VMX: Set up interception for CET MSRs
Date: Thu, 21 Dec 2023 09:02:35 -0500
Message-Id: <20231221140239.4349-23-weijiang.yang@intel.com>
In-Reply-To: <20231221140239.4349-1-weijiang.yang@intel.com>
References: <20231221140239.4349-1-weijiang.yang@intel.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

Enable/disable CET MSRs interception per associated feature configuration.
Shadow Stack feature requires all CET MSRs passed through to guest to make
it supported in user and supervisor mode while IBT feature only depends on
MSR_IA32_{U,S}_CETS_CET to enable user and supervisor IBT.

Note, this MSR design introduced an architectural limitation of SHSTK and
IBT control for guest, i.e., when SHSTK is exposed, IBT is also available
to guest from architectual perspective since IBT relies on subset of SHSTK
relevant MSRs.

Signed-off-by: Yang Weijiang <weijiang.yang@intel.com>
---
 arch/x86/kvm/vmx/vmx.c | 42 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 064a5fe87948..08058b182893 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -692,6 +692,10 @@ static bool is_valid_passthrough_msr(u32 msr)
 	case MSR_LBR_CORE_TO ... MSR_LBR_CORE_TO + 8:
 		/* LBR MSRs. These are handled in vmx_update_intercept_for_lbr_msrs() */
 		return true;
+	case MSR_IA32_U_CET:
+	case MSR_IA32_S_CET:
+	case MSR_IA32_PL0_SSP ... MSR_IA32_INT_SSP_TAB:
+		return true;
 	}
 
 	r = possible_passthrough_msr_slot(msr) != -ENOENT;
@@ -7767,6 +7771,42 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
 		vmx->pt_desc.ctl_bitmask &= ~(0xfULL << (32 + i * 4));
 }
 
+static void vmx_update_intercept_for_cet_msr(struct kvm_vcpu *vcpu)
+{
+	bool incpt;
+
+	if (kvm_cpu_cap_has(X86_FEATURE_SHSTK)) {
+		incpt = !guest_cpuid_has(vcpu, X86_FEATURE_SHSTK);
+
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_U_CET,
+					  MSR_TYPE_RW, incpt);
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_S_CET,
+					  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);
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL3_SSP,
+					  MSR_TYPE_RW, incpt);
+		if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
+			vmx_set_intercept_for_msr(vcpu, MSR_IA32_INT_SSP_TAB,
+						  MSR_TYPE_RW, incpt);
+		if (!incpt)
+			return;
+	}
+
+	if (kvm_cpu_cap_has(X86_FEATURE_IBT)) {
+		incpt = !guest_cpuid_has(vcpu, X86_FEATURE_IBT);
+
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_U_CET,
+					  MSR_TYPE_RW, incpt);
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_S_CET,
+					  MSR_TYPE_RW, incpt);
+	}
+}
+
 static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -7845,6 +7885,8 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 
 	/* Refresh #PF interception to account for MAXPHYADDR changes. */
 	vmx_update_exception_bitmap(vcpu);
+
+	vmx_update_intercept_for_cet_msr(vcpu);
 }
 
 static u64 vmx_get_perf_capabilities(void)
-- 
2.39.3