Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Xiaoyao Li <xiaoyao.li@linux.intel.com>
To:     kvm@vger.kernel.org, Paolo Bonzini <pbonzini@redhat.com>,
        =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= <rkrcmar@redhat.com>
Cc:     Xiaoyao Li <xiaoyao.li@linux.intel.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        "H. Peter Anvin" <hpa@zytor.com>, linux-kernel@vger.kernel.org,
        chao.gao@intel.com
Subject: [PATCH v2 2/2] kvm/vmx: Using hardware cpuid faulting to avoid emulation overhead
Date:   Mon, 18 Mar 2019 19:43:24 +0800
Message-Id: <20190318114324.14198-3-xiaoyao.li@linux.intel.com>
In-Reply-To: <20190318114324.14198-1-xiaoyao.li@linux.intel.com>
References: <20190318114324.14198-1-xiaoyao.li@linux.intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Current cpuid faulting of guest is purely emulated in kvm, which exploits
CPUID vm exit to inject #GP to guest. However, if host hardware cpu has
X86_FEATURE_CPUID_FAULT, we can just use the hardware cpuid faulting for
guest to avoid the vm exit overhead.

Note: cpuid faulting takes higher priority over CPUID instruction vm
exit (Intel SDM vol3.25.1.1).

Since cpuid faulting only exists on some Intel's cpu, just apply this
optimization to vmx.

Signed-off-by: Xiaoyao Li <xiaoyao.li@linux.intel.com>
---
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/vmx/vmx.c          | 19 +++++++++++++++----
 arch/x86/kvm/x86.c              | 15 ++++++++++++---
 3 files changed, 29 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index ce79d7bfe1fd..14cad587b804 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1339,6 +1339,8 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
 void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
 int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr);
 
+int kvm_supported_msr_misc_features_enables(struct kvm_vcpu *vcpu, u64 data);
+
 int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr);
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr);
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 2c59e0209e36..6b413e471dca 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1037,7 +1037,7 @@ static void pt_guest_exit(struct vcpu_vmx *vmx)
 
 static void vmx_save_host_cpuid_fault(struct vcpu_vmx *vmx)
 {
-	u64 host_val;
+	u64 host_val, guest_val;
 
 	if (!boot_cpu_has(X86_FEATURE_CPUID_FAULT))
 		return;
@@ -1045,10 +1045,12 @@ static void vmx_save_host_cpuid_fault(struct vcpu_vmx *vmx)
 	rdmsrl(MSR_MISC_FEATURES_ENABLES, host_val);
 	vmx->host_msr_misc_features_enables = host_val;
 
-	/* clear cpuid fault bit to avoid it leak to guest */
-	if (host_val & MSR_MISC_FEATURES_ENABLES_CPUID_FAULT) {
+	guest_val = vmx->vcpu.arch.msr_misc_features_enables;
+
+	/* we can use the hardware cpuid faulting to avoid emulation overhead */
+	if ((host_val ^ guest_val) & MSR_MISC_FEATURES_ENABLES_CPUID_FAULT) {
 		wrmsrl(MSR_MISC_FEATURES_ENABLES,
-		       host_val & ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT);
+		       host_val ^ MSR_MISC_FEATURES_ENABLES_CPUID_FAULT);
 	}
 }
 
@@ -2057,6 +2059,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		else
 			vmx->pt_desc.guest.addr_a[index / 2] = data;
 		break;
+	case MSR_MISC_FEATURES_ENABLES:
+		if (!kvm_supported_msr_misc_features_enables(vcpu, data))
+			return 1;
+		if (boot_cpu_has(X86_FEATURE_CPUID_FAULT)) {
+			if (vmx->loaded_cpu_state)
+				wrmsrl(MSR_MISC_FEATURES_ENABLES, data);
+		}
+		vcpu->arch.msr_misc_features_enables = data;
+		break;
 	case MSR_TSC_AUX:
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 434ec113cc79..33a8c95b2f2e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2449,6 +2449,17 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
 }
 
+int kvm_supported_msr_misc_features_enables(struct kvm_vcpu *vcpu, u64 data)
+{
+	if (data & ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT ||
+	    (data & MSR_MISC_FEATURES_ENABLES_CPUID_FAULT &&
+	     !supports_cpuid_fault(vcpu)))
+		return 0;
+	else
+		return 1;
+}
+EXPORT_SYMBOL_GPL(kvm_supported_msr_misc_features_enables);
+
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	bool pr = false;
@@ -2669,9 +2680,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vcpu->arch.msr_platform_info = data;
 		break;
 	case MSR_MISC_FEATURES_ENABLES:
-		if (data & ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT ||
-		    (data & MSR_MISC_FEATURES_ENABLES_CPUID_FAULT &&
-		     !supports_cpuid_fault(vcpu)))
+		if (!kvm_supported_msr_misc_features_enables(vcpu, data))
 			return 1;
 		vcpu->arch.msr_misc_features_enables = data;
 		break;
-- 
2.19.1