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;
From:   Yang Weijiang <weijiang.yang@intel.com>
To:     pbonzini@redhat.com, jmattson@google.com, seanjc@google.com,
        vkuznets@redhat.com, wei.w.wang@intel.com, like.xu.linux@gmail.com,
        kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Cc:     Yang Weijiang <weijiang.yang@intel.com>
Subject: [PATCH v6 11/12] KVM: x86/vmx: Check Arch LBR config  when return perf capabilities
Date:   Fri, 16 Jul 2021 16:50:05 +0800
Message-Id: <1626425406-18582-12-git-send-email-weijiang.yang@intel.com>
In-Reply-To: <1626425406-18582-1-git-send-email-weijiang.yang@intel.com>
References: <1626425406-18582-1-git-send-email-weijiang.yang@intel.com>
Precedence: bulk

Two new bit fields(VM_EXIT_CLEAR_IA32_LBR_CTL, VM_ENTRY_LOAD_IA32_LBR_CTL)
are added to support guest Arch LBR. These two bits should be set in order
to make Arch LBR workable in both guest and host.

Co-developed-by: Like Xu <like.xu@linux.intel.com>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
Signed-off-by: Yang Weijiang <weijiang.yang@intel.com>
---
 arch/x86/include/asm/vmx.h      |  2 ++
 arch/x86/kvm/vmx/capabilities.h | 25 +++++++++++++++++--------
 arch/x86/kvm/vmx/vmx.c          |  6 ++++--
 3 files changed, 23 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index ea3be961cc8e..d9b1dffc4638 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -95,6 +95,7 @@
 #define VM_EXIT_CLEAR_BNDCFGS                   0x00800000
 #define VM_EXIT_PT_CONCEAL_PIP			0x01000000
 #define VM_EXIT_CLEAR_IA32_RTIT_CTL		0x02000000
+#define VM_EXIT_CLEAR_IA32_LBR_CTL		0x04000000
 
 #define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR	0x00036dff
 
@@ -108,6 +109,7 @@
 #define VM_ENTRY_LOAD_BNDCFGS                   0x00010000
 #define VM_ENTRY_PT_CONCEAL_PIP			0x00020000
 #define VM_ENTRY_LOAD_IA32_RTIT_CTL		0x00040000
+#define VM_ENTRY_LOAD_IA32_LBR_CTL		0x00200000
 
 #define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR	0x000011ff
 
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index aa0e7872fcc9..b65e4087c9a9 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -377,20 +377,29 @@ static inline bool vmx_pt_mode_is_host_guest(void)
 	return pt_mode == PT_MODE_HOST_GUEST;
 }
 
-static inline u64 vmx_get_perf_capabilities(void)
+static inline bool cpu_has_vmx_arch_lbr(void)
 {
-	u64 perf_cap = 0;
-
-	if (boot_cpu_has(X86_FEATURE_PDCM))
-		rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_cap);
-
-	perf_cap &= PMU_CAP_LBR_FMT;
+	return (vmcs_config.vmexit_ctrl & VM_EXIT_CLEAR_IA32_LBR_CTL) &&
+		(vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_LBR_CTL);
+}
 
+static inline u64 vmx_get_perf_capabilities(void)
+{
 	/*
 	 * Since counters are virtualized, KVM would support full
 	 * width counting unconditionally, even if the host lacks it.
 	 */
-	return PMU_CAP_FW_WRITES | perf_cap;
+	u64 perf_cap = PMU_CAP_FW_WRITES;
+	u64 host_perf_cap = 0;
+
+	if (boot_cpu_has(X86_FEATURE_PDCM))
+		rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
+
+	perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT;
+	if (boot_cpu_has(X86_FEATURE_ARCH_LBR) && !cpu_has_vmx_arch_lbr())
+		perf_cap &= ~PMU_CAP_LBR_FMT;
+
+	return perf_cap;
 }
 
 static inline u64 vmx_supported_debugctl(void)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 81d7a300fb6c..7ccb0bb4831d 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2599,7 +2599,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 	      VM_EXIT_LOAD_IA32_EFER |
 	      VM_EXIT_CLEAR_BNDCFGS |
 	      VM_EXIT_PT_CONCEAL_PIP |
-	      VM_EXIT_CLEAR_IA32_RTIT_CTL;
+	      VM_EXIT_CLEAR_IA32_RTIT_CTL |
+	      VM_EXIT_CLEAR_IA32_LBR_CTL;
 	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS,
 				&_vmexit_control) < 0)
 		return -EIO;
@@ -2623,7 +2624,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 	      VM_ENTRY_LOAD_IA32_EFER |
 	      VM_ENTRY_LOAD_BNDCFGS |
 	      VM_ENTRY_PT_CONCEAL_PIP |
-	      VM_ENTRY_LOAD_IA32_RTIT_CTL;
+	      VM_ENTRY_LOAD_IA32_RTIT_CTL |
+	      VM_ENTRY_LOAD_IA32_LBR_CTL;
 	if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_ENTRY_CTLS,
 				&_vmentry_control) < 0)
 		return -EIO;
-- 
2.21.1