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:   Zhu Lingshan <lingshan.zhu@intel.com>
To:     peterz@infradead.org, pbonzini@redhat.com
Cc:     bp@alien8.de, seanjc@google.com, vkuznets@redhat.com,
        wanpengli@tencent.com, jmattson@google.com, joro@8bytes.org,
        kan.liang@linux.intel.com, ak@linux.intel.com,
        wei.w.wang@intel.com, eranian@google.com, liuxiangdong5@huawei.com,
        linux-kernel@vger.kernel.org, x86@kernel.org, kvm@vger.kernel.org,
        like.xu.linux@gmail.com, boris.ostrvsky@oracle.com,
        Like Xu <like.xu@linux.intel.com>,
        Luwei Kang <luwei.kang@intel.com>,
        Zhu Lingshan <lingshan.zhu@intel.com>
Subject: [PATCH V8 12/18] KVM: x86/pmu: Add PEBS_DATA_CFG MSR emulation to support adaptive PEBS
Date:   Fri, 16 Jul 2021 16:53:19 +0800
Message-Id: <20210716085325.10300-13-lingshan.zhu@intel.com>
In-Reply-To: <20210716085325.10300-1-lingshan.zhu@intel.com>
References: <20210716085325.10300-1-lingshan.zhu@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Like Xu <like.xu@linux.intel.com>

If IA32_PERF_CAPABILITIES.PEBS_BASELINE [bit 14] is set, the adaptive
PEBS is supported. The PEBS_DATA_CFG MSR and adaptive record enable
bits (IA32_PERFEVTSELx.Adaptive_Record and IA32_FIXED_CTR_CTRL.
FCx_Adaptive_Record) are also supported.

Adaptive PEBS provides software the capability to configure the PEBS
records to capture only the data of interest, keeping the record size
compact. An overflow of PMCx results in generation of an adaptive PEBS
record with state information based on the selections specified in
MSR_PEBS_DATA_CFG.By default, the record only contain the Basic group.

When guest adaptive PEBS is enabled, the IA32_PEBS_ENABLE MSR will
be added to the perf_guest_switch_msr() and switched during the VMX
transitions just like CORE_PERF_GLOBAL_CTRL MSR.

Co-developed-by: Luwei Kang <luwei.kang@intel.com>
Signed-off-by: Luwei Kang <luwei.kang@intel.com>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
Signed-off-by: Zhu Lingshan <lingshan.zhu@intel.com>
---
 arch/x86/events/intel/core.c    |  8 ++++++++
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/vmx/pmu_intel.c    | 16 ++++++++++++++++
 3 files changed, 26 insertions(+)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index b9825d7caaba..71622bf4c4dd 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3958,6 +3958,14 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
 		.guest = kvm_pmu->ds_area,
 	};
 
+	if (x86_pmu.intel_cap.pebs_baseline) {
+		arr[(*nr)++] = (struct perf_guest_switch_msr){
+			.msr = MSR_PEBS_DATA_CFG,
+			.host = cpuc->pebs_data_cfg,
+			.guest = kvm_pmu->pebs_data_cfg,
+		};
+	}
+
 	arr[*nr] = (struct perf_guest_switch_msr){
 		.msr = MSR_IA32_PEBS_ENABLE,
 		.host = cpuc->pebs_enabled & ~cpuc->intel_ctrl_guest_mask,
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 35f106f9f124..0fc1fef1af70 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -508,6 +508,8 @@ struct kvm_pmu {
 	u64 ds_area;
 	u64 pebs_enable;
 	u64 pebs_enable_mask;
+	u64 pebs_data_cfg;
+	u64 pebs_data_cfg_mask;
 
 	/*
 	 * The gate to release perf_events not marked in
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 5584b8dfadb3..58f32a55cc2e 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -226,6 +226,9 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 	case MSR_IA32_DS_AREA:
 		ret = guest_cpuid_has(vcpu, X86_FEATURE_DS);
 		break;
+	case MSR_PEBS_DATA_CFG:
+		ret = vcpu->arch.perf_capabilities & PERF_CAP_PEBS_BASELINE;
+		break;
 	default:
 		ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) ||
 			get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) ||
@@ -379,6 +382,9 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_DS_AREA:
 		msr_info->data = pmu->ds_area;
 		return 0;
+	case MSR_PEBS_DATA_CFG:
+		msr_info->data = pmu->pebs_data_cfg;
+		return 0;
 	default:
 		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
 		    (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) {
@@ -452,6 +458,14 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		pmu->ds_area = data;
 		return 0;
+	case MSR_PEBS_DATA_CFG:
+		if (pmu->pebs_data_cfg == data)
+			return 0;
+		if (!(data & pmu->pebs_data_cfg_mask)) {
+			pmu->pebs_data_cfg = data;
+			return 0;
+		}
+		break;
 	default:
 		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
 		    (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) {
@@ -505,6 +519,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	pmu->reserved_bits = 0xffffffff00200000ull;
 	pmu->fixed_ctr_ctrl_mask = ~0ull;
 	pmu->pebs_enable_mask = ~0ull;
+	pmu->pebs_data_cfg_mask = ~0ull;
 
 	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
 	if (!entry)
@@ -580,6 +595,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 				pmu->fixed_ctr_ctrl_mask &=
 					~(1ULL << (INTEL_PMC_IDX_FIXED + i * 4));
 			}
+			pmu->pebs_data_cfg_mask = ~0xff00000full;
 		} else {
 			pmu->pebs_enable_mask =
 				~((1ull << pmu->nr_arch_gp_counters) - 1);
-- 
2.27.0