KVM: x86/pmu: Add IA32_PEBS_ENABLE MSR emulation for extended PEBS

If IA32_PERF_CAPABILITIES.PEBS_BASELINE [bit 14] is set, the
IA32_PEBS_ENABLE MSR exists and all architecturally enumerated fixed
and general-purpose counters have corresponding bits in IA32_PEBS_ENABLE
that enable generation of PEBS records. The general-purpose counter bits
start at bit IA32_PEBS_ENABLE[0], and the fixed counter bits start at
bit IA32_PEBS_ENABLE[32].

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

Based on whether the platform supports x86_pmu.pebs_ept, it has also
refactored the way to add more msrs to arr[] in intel_guest_get_msrs()
for extensibility.

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>
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>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Message-Id: <20220411101946.20262-8-likexu@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/events/intel/core.c

@@ -3969,33 +3969,72 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	return 0;
 }
 
+/*
+ * Currently, the only caller of this function is the atomic_switch_perf_msrs().
+ * The host perf conext helps to prepare the values of the real hardware for
+ * a set of msrs that need to be switched atomically in a vmx transaction.
+ *
+ * For example, the pseudocode needed to add a new msr should look like:
+ *
+ * arr[(*nr)++] = (struct perf_guest_switch_msr){
+ *	.msr = the hardware msr address,
+ *	.host = the value the hardware has when it doesn't run a guest,
+ *	.guest = the value the hardware has when it runs a guest,
+ * };
+ *
+ * These values have nothing to do with the emulated values the guest sees
+ * when it uses {RD,WR}MSR, which should be handled by the KVM context,
+ * specifically in the intel_pmu_{get,set}_msr().
+ */
 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;
 	u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl);
+	u64 pebs_mask = cpuc->pebs_enabled & x86_pmu.pebs_capable;
+	int global_ctrl, pebs_enable;
 
-	arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
+	*nr = 0;
-	arr[0].host = intel_ctrl & ~cpuc->intel_ctrl_guest_mask;
+	global_ctrl = (*nr)++;
-	arr[0].guest = intel_ctrl & ~cpuc->intel_ctrl_host_mask;
+	arr[global_ctrl] = (struct perf_guest_switch_msr){
-	arr[0].guest &= ~(cpuc->pebs_enabled & x86_pmu.pebs_capable);
+		.msr = MSR_CORE_PERF_GLOBAL_CTRL,
-	*nr = 1;
+		.host = intel_ctrl & ~cpuc->intel_ctrl_guest_mask,
+		.guest = intel_ctrl & (~cpuc->intel_ctrl_host_mask | ~pebs_mask),
+	};
 
-	if (x86_pmu.pebs && x86_pmu.pebs_no_isolation) {
+	if (!x86_pmu.pebs)
-		/*
+		return arr;
-		 * If PMU counter has PEBS enabled it is not enough to
+
-		 * disable counter on a guest entry since PEBS memory
+	/*
-		 * write can overshoot guest entry and corrupt guest
+	 * If PMU counter has PEBS enabled it is not enough to
-		 * memory. Disabling PEBS solves the problem.
+	 * disable counter on a guest entry since PEBS memory
-		 *
+	 * write can overshoot guest entry and corrupt guest
-		 * Don't do this if the CPU already enforces it.
+	 * memory. Disabling PEBS solves the problem.
-		 */
+	 *
-		arr[1].msr = MSR_IA32_PEBS_ENABLE;
+	 * Don't do this if the CPU already enforces it.
-		arr[1].host = cpuc->pebs_enabled;
+	 */
-		arr[1].guest = 0;
+	if (x86_pmu.pebs_no_isolation) {
-		*nr = 2;
+		arr[(*nr)++] = (struct perf_guest_switch_msr){
+			.msr = MSR_IA32_PEBS_ENABLE,
+			.host = cpuc->pebs_enabled,
+			.guest = 0,
+		};
+		return arr;
 	}
 
+	if (!x86_pmu.pebs_ept)
+		return arr;
+	pebs_enable = (*nr)++;
+
+	arr[pebs_enable] = (struct perf_guest_switch_msr){
+		.msr = MSR_IA32_PEBS_ENABLE,
+		.host = cpuc->pebs_enabled & ~cpuc->intel_ctrl_guest_mask,
+		.guest = pebs_mask & ~cpuc->intel_ctrl_host_mask,
+	};
+
+	/* Set hw GLOBAL_CTRL bits for PEBS counter when it runs for guest */
+	arr[0].guest |= arr[*nr].guest;
+
 	return arr;
 }
 

arch/x86/include/asm/kvm_host.h

@@ -521,6 +521,9 @@ struct kvm_pmu {
 	DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX);
 	DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX);
 
+	u64 pebs_enable;
+	u64 pebs_enable_mask;
+
 	/*
 	 * The gate to release perf_events not marked in
 	 * pmc_in_use only once in a vcpu time slice.

arch/x86/include/asm/msr-index.h

@@ -196,6 +196,12 @@
 #define PERF_CAP_PT_IDX			16
 
 #define MSR_PEBS_LD_LAT_THRESHOLD	0x000003f6
+#define PERF_CAP_PEBS_TRAP             BIT_ULL(6)
+#define PERF_CAP_ARCH_REG              BIT_ULL(7)
+#define PERF_CAP_PEBS_FORMAT           0xf00
+#define PERF_CAP_PEBS_BASELINE         BIT_ULL(14)
+#define PERF_CAP_PEBS_MASK	(PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \
+				 PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE)
 
 #define MSR_IA32_RTIT_CTL		0x00000570
 #define RTIT_CTL_TRACEEN		BIT(0)

arch/x86/kvm/vmx/pmu_intel.c

@@ -214,6 +214,9 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 	case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
 		ret = pmu->version > 1;
 		break;
+	case MSR_IA32_PEBS_ENABLE:
+		ret = vcpu->arch.perf_capabilities & PERF_CAP_PEBS_FORMAT;
+		break;
 	default:
 		ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) ||
 			get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) ||
@@ -361,6 +364,9 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
 		msr_info->data = 0;
 		return 0;
+	case MSR_IA32_PEBS_ENABLE:
+		msr_info->data = pmu->pebs_enable;
+		return 0;
 	default:
 		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
 		    (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) {
@@ -421,6 +427,14 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 0;
 		}
 		break;
+	case MSR_IA32_PEBS_ENABLE:
+		if (pmu->pebs_enable == data)
+			return 0;
+		if (!(data & pmu->pebs_enable_mask)) {
+			pmu->pebs_enable = data;
+			return 0;
+		}
+		break;
 	default:
 		if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) ||
 		    (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) {
@@ -489,6 +503,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	pmu->reserved_bits = 0xffffffff00200000ull;
 	pmu->raw_event_mask = X86_RAW_EVENT_MASK;
 	pmu->fixed_ctr_ctrl_mask = ~0ull;
+	pmu->pebs_enable_mask = ~0ull;
 
 	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
 	if (!entry || !vcpu->kvm->arch.enable_pmu)
@@ -560,6 +575,22 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 
 	if (lbr_desc->records.nr)
 		bitmap_set(pmu->all_valid_pmc_idx, INTEL_PMC_IDX_FIXED_VLBR, 1);
+
+	if (vcpu->arch.perf_capabilities & PERF_CAP_PEBS_FORMAT) {
+		if (vcpu->arch.perf_capabilities & PERF_CAP_PEBS_BASELINE) {
+			pmu->pebs_enable_mask = ~pmu->global_ctrl;
+			pmu->reserved_bits &= ~ICL_EVENTSEL_ADAPTIVE;
+			for (i = 0; i < pmu->nr_arch_fixed_counters; i++) {
+				pmu->fixed_ctr_ctrl_mask &=
+					~(1ULL << (INTEL_PMC_IDX_FIXED + i * 4));
+			}
+		} else {
+			pmu->pebs_enable_mask =
+				~((1ull << pmu->nr_arch_gp_counters) - 1);
+		}
+	} else {
+		vcpu->arch.perf_capabilities &= ~PERF_CAP_PEBS_MASK;
+	}
 }
 
 static void intel_pmu_init(struct kvm_vcpu *vcpu)

arch/x86/kvm/x86.c

@@ -1448,6 +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_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3,
 	MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3,