Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Reply-To: Sean Christopherson <seanjc@google.com>
Date:   Tue,  4 May 2021 10:17:22 -0700
In-Reply-To: <20210504171734.1434054-1-seanjc@google.com>
Message-Id: <20210504171734.1434054-4-seanjc@google.com>
Mime-Version: 1.0
References: <20210504171734.1434054-1-seanjc@google.com>
Subject: [PATCH 03/15] KVM: SVM: Inject #UD on RDTSCP when it should be
 disabled in the guest
From:   Sean Christopherson <seanjc@google.com>
To:     Paolo Bonzini <pbonzini@redhat.com>
Cc:     Sean Christopherson <seanjc@google.com>,
        Vitaly Kuznetsov <vkuznets@redhat.com>,
        Wanpeng Li <wanpengli@tencent.com>,
        Jim Mattson <jmattson@google.com>,
        Joerg Roedel <joro@8bytes.org>, kvm@vger.kernel.org,
        linux-kernel@vger.kernel.org, Xiaoyao Li <xiaoyao.li@intel.com>,
        Reiji Watanabe <reijiw@google.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

Intercept RDTSCP to inject #UD if RDTSC is disabled in the guest.

Note, SVM does not support intercepting RDPID.  Unlike VMX's
ENABLE_RDTSCP control, RDTSCP interception does not apply to RDPID.  This
is a benign virtualization hole as the host kernel (incorrectly) sets
MSR_TSC_AUX if RDTSCP is supported, and KVM loads the guest's MSR_TSC_AUX
into hardware if RDTSCP is supported in the host, i.e. KVM will not leak
the host's MSR_TSC_AUX to the guest.

But, when the kernel bug is fixed, KVM will start leaking the host's
MSR_TSC_AUX if RDPID is supported in hardware, but RDTSCP isn't available
for whatever reason.  This leak will be remedied in a future commit.

Fixes: 46896c73c1a4 ("KVM: svm: add support for RDTSCP")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index a7271f31df47..8f2b184270c0 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1100,7 +1100,9 @@ static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 	return svm->vmcb->control.tsc_offset;
 }
 
-static void svm_check_invpcid(struct vcpu_svm *svm)
+/* Evaluate instruction intercepts that depend on guest CPUID features. */
+static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu,
+					      struct vcpu_svm *svm)
 {
 	/*
 	 * Intercept INVPCID if shadow paging is enabled to sync/free shadow
@@ -1113,6 +1115,13 @@ static void svm_check_invpcid(struct vcpu_svm *svm)
 		else
 			svm_clr_intercept(svm, INTERCEPT_INVPCID);
 	}
+
+	if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) {
+		if (guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
+			svm_clr_intercept(svm, INTERCEPT_RDTSCP);
+		else
+			svm_set_intercept(svm, INTERCEPT_RDTSCP);
+	}
 }
 
 static void init_vmcb(struct kvm_vcpu *vcpu)
@@ -1248,7 +1257,7 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
 		svm_clr_intercept(svm, INTERCEPT_PAUSE);
 	}
 
-	svm_check_invpcid(svm);
+	svm_recalc_instruction_intercepts(vcpu, svm);
 
 	/*
 	 * If the host supports V_SPEC_CTRL then disable the interception
@@ -3084,6 +3093,7 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[SVM_EXIT_STGI]				= stgi_interception,
 	[SVM_EXIT_CLGI]				= clgi_interception,
 	[SVM_EXIT_SKINIT]			= skinit_interception,
+	[SVM_EXIT_RDTSCP]			= kvm_handle_invalid_op,
 	[SVM_EXIT_WBINVD]                       = kvm_emulate_wbinvd,
 	[SVM_EXIT_MONITOR]			= kvm_emulate_monitor,
 	[SVM_EXIT_MWAIT]			= kvm_emulate_mwait,
@@ -4007,8 +4017,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	svm->nrips_enabled = kvm_cpu_cap_has(X86_FEATURE_NRIPS) &&
 			     guest_cpuid_has(vcpu, X86_FEATURE_NRIPS);
 
-	/* Check again if INVPCID interception if required */
-	svm_check_invpcid(svm);
+	svm_recalc_instruction_intercepts(vcpu, svm);
 
 	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
 	if (sev_guest(vcpu->kvm)) {
-- 
2.31.1.527.g47e6f16901-goog