KVM: x86/pmu: Add IA32_DS_AREA MSR emulation to support guest DS

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>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Message-Id: <20220411101946.20262-11-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/events/intel/core.c

@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 #include <linux/nmi.h>
+#include <linux/kvm_host.h>
 
 #include <asm/cpufeature.h>
 #include <asm/hardirq.h>
@@ -3990,6 +3991,7 @@ 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 kvm_pmu *kvm_pmu = (struct kvm_pmu *)data;
 	u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl);
 	u64 pebs_mask = cpuc->pebs_enabled & x86_pmu.pebs_capable;
 	int global_ctrl, pebs_enable;
@@ -4022,9 +4024,15 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
 		return arr;
 	}
 
-	if (!x86_pmu.pebs_ept)
+	if (!kvm_pmu || !x86_pmu.pebs_ept)
 		return arr;
 
+	arr[(*nr)++] = (struct perf_guest_switch_msr){
+		.msr = MSR_IA32_DS_AREA,
+		.host = (unsigned long)cpuc->ds,
+		.guest = kvm_pmu->ds_area,
+	};
+
 	pebs_enable = (*nr)++;
 	arr[pebs_enable] = (struct perf_guest_switch_msr){
 		.msr = MSR_IA32_PEBS_ENABLE,

arch/x86/include/asm/kvm_host.h

@@ -521,6 +521,7 @@ 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;
 

arch/x86/kvm/vmx/pmu_intel.c

@@ -217,6 +217,9 @@ 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) ||
@@ -367,6 +370,9 @@ 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))) {
@@ -435,6 +441,11 @@ 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))) {

arch/x86/kvm/x86.c

@@ -1448,7 +1448,7 @@ static const u32 msrs_to_save_all[] = {
 	MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
-	MSR_IA32_PEBS_ENABLE,
+	MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA,
 
 	MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3,
 	MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3,