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;
IronPort-SDR: OGwU1misgQIxZkUHa/XZsHalebpD8m8YUCUsHt6ayvn7Q+YFqS9jJQoDZ/1+3A/qhzu9gCM209
 ij3xSoCewi2g==
IronPort-SDR: qAD80/PhAC7RQ/PpYT2VIbBxoBEfy9BtYzWmHBr+Qk6Jq5LoR8NLWAX+S+5mzCtxNxSv2OTr/p
 liH0jnEOx5VA==
From:   Like Xu <like.xu@linux.intel.com>
To:     Peter Zijlstra <peterz@infradead.org>,
        Paolo Bonzini <pbonzini@redhat.com>
Cc:     Borislav Petkov <bp@alien8.de>,
        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>, weijiang.yang@intel.com,
        Kan Liang <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 <like.xu@linux.intel.com>
Subject: [PATCH v6 08/16] KVM: x86/pmu: Add IA32_DS_AREA MSR emulation to support guest DS
Date:   Tue, 11 May 2021 10:42:06 +0800
Message-Id: <20210511024214.280733-9-like.xu@linux.intel.com>
In-Reply-To: <20210511024214.280733-1-like.xu@linux.intel.com>
References: <20210511024214.280733-1-like.xu@linux.intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

When CPUID.01H:EDX.DS[21] is set, the IA32_DS_AREA MSR exists and points
to the linear address of the first byte of the DS buffer management area,
which is used to manage the PEBS records.

When guest PEBS is enabled, the MSR_IA32_DS_AREA MSR will be added to the
perf_guest_switch_msr() and switched during the VMX transitions just like
CORE_PERF_GLOBAL_CTRL MSR. The WRMSR to IA32_DS_AREA MSR brings a #GP(0)
if the source register contains a non-canonical address.

Originally-by: Andi Kleen <ak@linux.intel.com>
Co-developed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
---
 arch/x86/events/intel/core.c    | 11 ++++++++++-
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/vmx/pmu_intel.c    | 11 +++++++++++
 3 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index c791765f4761..de3bc8dfe85e 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -21,6 +21,7 @@
 #include <asm/intel_pt.h>
 #include <asm/apic.h>
 #include <asm/cpu_device_id.h>
+#include <asm/kvm_host.h>
 
 #include "../perf_event.h"
 
@@ -3897,6 +3898,8 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
+	struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);
+	struct kvm_pmu *pmu = (struct kvm_pmu *)data;
 	u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl);
 	u64 pebs_mask = (x86_pmu.flags & PMU_FL_PEBS_ALL) ?
 		cpuc->pebs_enabled : (cpuc->pebs_enabled & PEBS_COUNTER_MASK);
@@ -3908,7 +3911,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
 		.guest = intel_ctrl & (~cpuc->intel_ctrl_host_mask | ~pebs_mask),
 	};
 
-	if (!x86_pmu.pebs)
+	if (!pmu || !x86_pmu.pebs_vmx)
 		return arr;
 
 	/*
@@ -3931,6 +3934,12 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
 	if (!x86_pmu.pebs_vmx)
 		return arr;
 
+	arr[(*nr)++] = (struct perf_guest_switch_msr){
+		.msr = MSR_IA32_DS_AREA,
+		.host = (unsigned long)ds,
+		.guest = pmu->ds_area,
+	};
+
 	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 0a42079560ac..296bc3eecdc6 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -473,6 +473,7 @@ struct kvm_pmu {
 	DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX);
 	DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX);
 
+	u64 ds_area;
 	u64 pebs_enable;
 	u64 pebs_enable_mask;
 
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 9938b485c31c..5584b8dfadb3 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -223,6 +223,9 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 	case MSR_IA32_PEBS_ENABLE:
 		ret = vcpu->arch.perf_capabilities & PERF_CAP_PEBS_FORMAT;
 		break;
+	case MSR_IA32_DS_AREA:
+		ret = guest_cpuid_has(vcpu, X86_FEATURE_DS);
+		break;
 	default:
 		ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) ||
 			get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) ||
@@ -373,6 +376,9 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_PEBS_ENABLE:
 		msr_info->data = pmu->pebs_enable;
 		return 0;
+	case MSR_IA32_DS_AREA:
+		msr_info->data = pmu->ds_area;
+		return 0;
 	default:
 		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
 		    (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) {
@@ -441,6 +447,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 0;
 		}
 		break;
+	case MSR_IA32_DS_AREA:
+		if (is_noncanonical_address(data, vcpu))
+			return 1;
+		pmu->ds_area = data;
+		return 0;
 	default:
 		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
 		    (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) {
-- 
2.31.1