1 files changed, 414 insertions, 30 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index fe65be0b9d9c..853fe073bab3 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2563,6 +2563,44 @@ static void intel_pmu_disable_fixed(struct perf_event *event)
 	cpuc->fixed_ctrl_val &= ~mask;
 }
 
+static inline void __intel_pmu_update_event_ext(int idx, u64 ext)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	u32 msr;
+
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		msr = MSR_IA32_PMC_V6_GP0_CFG_C +
+		      x86_pmu.addr_offset(idx, false);
+	} else {
+		msr = MSR_IA32_PMC_V6_FX0_CFG_C +
+		      x86_pmu.addr_offset(idx - INTEL_PMC_IDX_FIXED, false);
+	}
+
+	cpuc->cfg_c_val[idx] = ext;
+	wrmsrq(msr, ext);
+}
+
+static void intel_pmu_disable_event_ext(struct perf_event *event)
+{
+	/*
+	 * Only clear CFG_C MSR for PEBS counter group events,
+	 * it avoids the HW counter's value to be added into
+	 * other PEBS records incorrectly after PEBS counter
+	 * group events are disabled.
+	 *
+	 * For other events, it's unnecessary to clear CFG_C MSRs
+	 * since CFG_C doesn't take effect if counter is in
+	 * disabled state. That helps to reduce the WRMSR overhead
+	 * in context switches.
+	 */
+	if (!is_pebs_counter_event_group(event))
+		return;
+
+	__intel_pmu_update_event_ext(event->hw.idx, 0);
+}
+
+DEFINE_STATIC_CALL_NULL(intel_pmu_disable_event_ext, intel_pmu_disable_event_ext);
+
 static void intel_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -2571,9 +2609,12 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	switch (idx) {
 	case 0 ... INTEL_PMC_IDX_FIXED - 1:
 		intel_clear_masks(event, idx);
+		static_call_cond(intel_pmu_disable_event_ext)(event);
 		x86_pmu_disable_event(event);
 		break;
 	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1:
+		static_call_cond(intel_pmu_disable_event_ext)(event);
+		fallthrough;
 	case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END:
 		intel_pmu_disable_fixed(event);
 		break;
@@ -2940,6 +2981,79 @@ static void intel_pmu_enable_acr(struct perf_event *event)
 
 DEFINE_STATIC_CALL_NULL(intel_pmu_enable_acr_event, intel_pmu_enable_acr);
 
+static void intel_pmu_enable_event_ext(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	union arch_pebs_index old, new;
+	struct arch_pebs_cap cap;
+	u64 ext = 0;
+
+	cap = hybrid(cpuc->pmu, arch_pebs_cap);
+
+	if (event->attr.precise_ip) {
+		u64 pebs_data_cfg = intel_get_arch_pebs_data_config(event);
+
+		ext |= ARCH_PEBS_EN;
+		if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD)
+			ext |= (-hwc->sample_period) & ARCH_PEBS_RELOAD;
+
+		if (pebs_data_cfg && cap.caps) {
+			if (pebs_data_cfg & PEBS_DATACFG_MEMINFO)
+				ext |= ARCH_PEBS_AUX & cap.caps;
+
+			if (pebs_data_cfg & PEBS_DATACFG_GP)
+				ext |= ARCH_PEBS_GPR & cap.caps;
+
+			if (pebs_data_cfg & PEBS_DATACFG_XMMS)
+				ext |= ARCH_PEBS_VECR_XMM & cap.caps;
+
+			if (pebs_data_cfg & PEBS_DATACFG_LBRS)
+				ext |= ARCH_PEBS_LBR & cap.caps;
+
+			if (pebs_data_cfg &
+			    (PEBS_DATACFG_CNTR_MASK << PEBS_DATACFG_CNTR_SHIFT))
+				ext |= ARCH_PEBS_CNTR_GP & cap.caps;
+
+			if (pebs_data_cfg &
+			    (PEBS_DATACFG_FIX_MASK << PEBS_DATACFG_FIX_SHIFT))
+				ext |= ARCH_PEBS_CNTR_FIXED & cap.caps;
+
+			if (pebs_data_cfg & PEBS_DATACFG_METRICS)
+				ext |= ARCH_PEBS_CNTR_METRICS & cap.caps;
+		}
+
+		if (cpuc->n_pebs == cpuc->n_large_pebs)
+			new.thresh = ARCH_PEBS_THRESH_MULTI;
+		else
+			new.thresh = ARCH_PEBS_THRESH_SINGLE;
+
+		rdmsrq(MSR_IA32_PEBS_INDEX, old.whole);
+		if (new.thresh != old.thresh || !old.en) {
+			if (old.thresh == ARCH_PEBS_THRESH_MULTI && old.wr > 0) {
+				/*
+				 * Large PEBS was enabled.
+				 * Drain PEBS buffer before applying the single PEBS.
+				 */
+				intel_pmu_drain_pebs_buffer();
+			} else {
+				new.wr = 0;
+				new.full = 0;
+				new.en = 1;
+				wrmsrq(MSR_IA32_PEBS_INDEX, new.whole);
+			}
+		}
+	}
+
+	if (is_pebs_counter_event_group(event))
+		ext |= ARCH_PEBS_CNTR_ALLOW;
+
+	if (cpuc->cfg_c_val[hwc->idx] != ext)
+		__intel_pmu_update_event_ext(hwc->idx, ext);
+}
+
+DEFINE_STATIC_CALL_NULL(intel_pmu_enable_event_ext, intel_pmu_enable_event_ext);
+
 static void intel_pmu_enable_event(struct perf_event *event)
 {
 	u64 enable_mask = ARCH_PERFMON_EVENTSEL_ENABLE;
@@ -2955,10 +3069,12 @@ static void intel_pmu_enable_event(struct perf_event *event)
 			enable_mask |= ARCH_PERFMON_EVENTSEL_BR_CNTR;
 		intel_set_masks(event, idx);
 		static_call_cond(intel_pmu_enable_acr_event)(event);
+		static_call_cond(intel_pmu_enable_event_ext)(event);
 		__x86_pmu_enable_event(hwc, enable_mask);
 		break;
 	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1:
 		static_call_cond(intel_pmu_enable_acr_event)(event);
+		static_call_cond(intel_pmu_enable_event_ext)(event);
 		fallthrough;
 	case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END:
 		intel_pmu_enable_fixed(event);
@@ -3216,6 +3332,19 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	}
 
 	/*
+	 * Arch PEBS sets bit 54 in the global status register
+	 */
+	if (__test_and_clear_bit(GLOBAL_STATUS_ARCH_PEBS_THRESHOLD_BIT,
+				 (unsigned long *)&status)) {
+		handled++;
+		static_call(x86_pmu_drain_pebs)(regs, &data);
+
+		if (cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS] &&
+		    is_pebs_counter_event_group(cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS]))
+			status &= ~GLOBAL_STATUS_PERF_METRICS_OVF_BIT;
+	}
+
+	/*
 	 * Intel PT
 	 */
 	if (__test_and_clear_bit(GLOBAL_STATUS_TRACE_TOPAPMI_BIT, (unsigned long *)&status)) {
@@ -3269,7 +3398,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 		 * The PEBS buffer has to be drained before handling the A-PMI
 		 */
 		if (is_pebs_counter_event_group(event))
-			x86_pmu.drain_pebs(regs, &data);
+			static_call(x86_pmu_drain_pebs)(regs, &data);
 
 		last_period = event->hw.last_period;
 
@@ -4029,7 +4158,9 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
 	if (!event->attr.exclude_kernel)
 		flags &= ~PERF_SAMPLE_REGS_USER;
 	if (event->attr.sample_regs_user & ~PEBS_GP_REGS)
-		flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR);
+		flags &= ~PERF_SAMPLE_REGS_USER;
+	if (event->attr.sample_regs_intr & ~PEBS_GP_REGS)
+		flags &= ~PERF_SAMPLE_REGS_INTR;
 	return flags;
 }
 
@@ -4204,6 +4335,20 @@ static bool intel_pmu_is_acr_group(struct perf_event *event)
 	return false;
 }
 
+static inline bool intel_pmu_has_pebs_counter_group(struct pmu *pmu)
+{
+	u64 caps;
+
+	if (x86_pmu.intel_cap.pebs_format >= 6 && x86_pmu.intel_cap.pebs_baseline)
+		return true;
+
+	caps = hybrid(pmu, arch_pebs_cap).caps;
+	if (x86_pmu.arch_pebs && (caps & ARCH_PEBS_CNTR_MASK))
+		return true;
+
+	return false;
+}
+
 static inline void intel_pmu_set_acr_cntr_constr(struct perf_event *event,
 						 u64 *cause_mask, int *num)
 {
@@ -4237,6 +4382,8 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	}
 
 	if (event->attr.precise_ip) {
+		struct arch_pebs_cap pebs_cap = hybrid(event->pmu, arch_pebs_cap);
+
 		if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT)
 			return -EINVAL;
 
@@ -4250,6 +4397,15 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		}
 		if (x86_pmu.pebs_aliases)
 			x86_pmu.pebs_aliases(event);
+
+		if (x86_pmu.arch_pebs) {
+			u64 cntr_mask = hybrid(event->pmu, intel_ctrl) &
+						~GLOBAL_CTRL_EN_PERF_METRICS;
+			u64 pebs_mask = event->attr.precise_ip >= 3 ?
+						pebs_cap.pdists : pebs_cap.counters;
+			if (cntr_mask != pebs_mask)
+				event->hw.dyn_constraint &= pebs_mask;
+		}
 	}
 
 	if (needs_branch_stack(event)) {
@@ -4341,8 +4497,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	}
 
 	if ((event->attr.sample_type & PERF_SAMPLE_READ) &&
-	    (x86_pmu.intel_cap.pebs_format >= 6) &&
-	    x86_pmu.intel_cap.pebs_baseline &&
+	    intel_pmu_has_pebs_counter_group(event->pmu) &&
 	    is_sampling_event(event) &&
 	    event->attr.precise_ip)
 		event->group_leader->hw.flags |= PERF_X86_EVENT_PEBS_CNTR;
@@ -5212,7 +5367,13 @@ err:
 
 static int intel_pmu_cpu_prepare(int cpu)
 {
-	return intel_cpuc_prepare(&per_cpu(cpu_hw_events, cpu), cpu);
+	int ret;
+
+	ret = intel_cpuc_prepare(&per_cpu(cpu_hw_events, cpu), cpu);
+	if (ret)
+		return ret;
+
+	return alloc_arch_pebs_buf_on_cpu(cpu);
 }
 
 static void flip_smm_bit(void *data)
@@ -5257,6 +5418,163 @@ static void intel_pmu_check_event_constraints(struct event_constraint *event_con
 					      u64 fixed_cntr_mask,
 					      u64 intel_ctrl);
 
+enum dyn_constr_type {
+	DYN_CONSTR_NONE,
+	DYN_CONSTR_BR_CNTR,
+	DYN_CONSTR_ACR_CNTR,
+	DYN_CONSTR_ACR_CAUSE,
+	DYN_CONSTR_PEBS,
+	DYN_CONSTR_PDIST,
+
+	DYN_CONSTR_MAX,
+};
+
+static const char * const dyn_constr_type_name[] = {
+	[DYN_CONSTR_NONE] = "a normal event",
+	[DYN_CONSTR_BR_CNTR] = "a branch counter logging event",
+	[DYN_CONSTR_ACR_CNTR] = "an auto-counter reload event",
+	[DYN_CONSTR_ACR_CAUSE] = "an auto-counter reload cause event",
+	[DYN_CONSTR_PEBS] = "a PEBS event",
+	[DYN_CONSTR_PDIST] = "a PEBS PDIST event",
+};
+
+static void __intel_pmu_check_dyn_constr(struct event_constraint *constr,
+					 enum dyn_constr_type type, u64 mask)
+{
+	struct event_constraint *c1, *c2;
+	int new_weight, check_weight;
+	u64 new_mask, check_mask;
+
+	for_each_event_constraint(c1, constr) {
+		new_mask = c1->idxmsk64 & mask;
+		new_weight = hweight64(new_mask);
+
+		/* ignore topdown perf metrics event */
+		if (c1->idxmsk64 & INTEL_PMC_MSK_TOPDOWN)
+			continue;
+
+		if (!new_weight && fls64(c1->idxmsk64) < INTEL_PMC_IDX_FIXED) {
+			pr_info("The event 0x%llx is not supported as %s.\n",
+				c1->code, dyn_constr_type_name[type]);
+		}
+
+		if (new_weight <= 1)
+			continue;
+
+		for_each_event_constraint(c2, c1 + 1) {
+			bool check_fail = false;
+
+			check_mask = c2->idxmsk64 & mask;
+			check_weight = hweight64(check_mask);
+
+			if (c2->idxmsk64 & INTEL_PMC_MSK_TOPDOWN ||
+			    !check_weight)
+				continue;
+
+			/* The same constraints or no overlap */
+			if (new_mask == check_mask ||
+			    (new_mask ^ check_mask) == (new_mask | check_mask))
+				continue;
+
+			/*
+			 * A scheduler issue may be triggered in the following cases.
+			 * - Two overlap constraints have the same weight.
+			 *   E.g., A constraints: 0x3, B constraints: 0x6
+			 *   event	counter		failure case
+			 *   B		PMC[2:1]	1
+			 *   A		PMC[1:0]	0
+			 *   A		PMC[1:0]	FAIL
+			 * - Two overlap constraints have different weight.
+			 *   The constraint has a low weight, but has high last bit.
+			 *   E.g., A constraints: 0x7, B constraints: 0xC
+			 *   event	counter		failure case
+			 *   B		PMC[3:2]	2
+			 *   A		PMC[2:0]	0
+			 *   A		PMC[2:0]	1
+			 *   A		PMC[2:0]	FAIL
+			 */
+			if (new_weight == check_weight) {
+				check_fail = true;
+			} else if (new_weight < check_weight) {
+				if ((new_mask | check_mask) != check_mask &&
+				    fls64(new_mask) > fls64(check_mask))
+					check_fail = true;
+			} else {
+				if ((new_mask | check_mask) != new_mask &&
+				    fls64(new_mask) < fls64(check_mask))
+					check_fail = true;
+			}
+
+			if (check_fail) {
+				pr_info("The two events 0x%llx and 0x%llx may not be "
+					"fully scheduled under some circumstances as "
+					"%s.\n",
+					c1->code, c2->code, dyn_constr_type_name[type]);
+			}
+		}
+	}
+}
+
+static void intel_pmu_check_dyn_constr(struct pmu *pmu,
+				       struct event_constraint *constr,
+				       u64 cntr_mask)
+{
+	enum dyn_constr_type i;
+	u64 mask;
+
+	for (i = DYN_CONSTR_NONE; i < DYN_CONSTR_MAX; i++) {
+		mask = 0;
+		switch (i) {
+		case DYN_CONSTR_NONE:
+			mask = cntr_mask;
+			break;
+		case DYN_CONSTR_BR_CNTR:
+			if (x86_pmu.flags & PMU_FL_BR_CNTR)
+				mask = x86_pmu.lbr_counters;
+			break;
+		case DYN_CONSTR_ACR_CNTR:
+			mask = hybrid(pmu, acr_cntr_mask64) & GENMASK_ULL(INTEL_PMC_MAX_GENERIC - 1, 0);
+			break;
+		case DYN_CONSTR_ACR_CAUSE:
+			if (hybrid(pmu, acr_cntr_mask64) == hybrid(pmu, acr_cause_mask64))
+				continue;
+			mask = hybrid(pmu, acr_cause_mask64) & GENMASK_ULL(INTEL_PMC_MAX_GENERIC - 1, 0);
+			break;
+		case DYN_CONSTR_PEBS:
+			if (x86_pmu.arch_pebs)
+				mask = hybrid(pmu, arch_pebs_cap).counters;
+			break;
+		case DYN_CONSTR_PDIST:
+			if (x86_pmu.arch_pebs)
+				mask = hybrid(pmu, arch_pebs_cap).pdists;
+			break;
+		default:
+			pr_warn("Unsupported dynamic constraint type %d\n", i);
+		}
+
+		if (mask)
+			__intel_pmu_check_dyn_constr(constr, i, mask);
+	}
+}
+
+static void intel_pmu_check_event_constraints_all(struct pmu *pmu)
+{
+	struct event_constraint *event_constraints = hybrid(pmu, event_constraints);
+	struct event_constraint *pebs_constraints = hybrid(pmu, pebs_constraints);
+	u64 cntr_mask = hybrid(pmu, cntr_mask64);
+	u64 fixed_cntr_mask = hybrid(pmu, fixed_cntr_mask64);
+	u64 intel_ctrl = hybrid(pmu, intel_ctrl);
+
+	intel_pmu_check_event_constraints(event_constraints, cntr_mask,
+					  fixed_cntr_mask, intel_ctrl);
+
+	if (event_constraints)
+		intel_pmu_check_dyn_constr(pmu, event_constraints, cntr_mask);
+
+	if (pebs_constraints)
+		intel_pmu_check_dyn_constr(pmu, pebs_constraints, cntr_mask);
+}
+
 static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs);
 
 static inline bool intel_pmu_broken_perf_cap(void)
@@ -5269,34 +5587,89 @@ static inline bool intel_pmu_broken_perf_cap(void)
 	return false;
 }
 
+static inline void __intel_update_pmu_caps(struct pmu *pmu)
+{
+	struct pmu *dest_pmu = pmu ? pmu : x86_get_pmu(smp_processor_id());
+
+	if (hybrid(pmu, arch_pebs_cap).caps & ARCH_PEBS_VECR_XMM)
+		dest_pmu->capabilities |= PERF_PMU_CAP_EXTENDED_REGS;
+}
+
+static inline void __intel_update_large_pebs_flags(struct pmu *pmu)
+{
+	u64 caps = hybrid(pmu, arch_pebs_cap).caps;
+
+	x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
+	if (caps & ARCH_PEBS_LBR)
+		x86_pmu.large_pebs_flags |= PERF_SAMPLE_BRANCH_STACK;
+	if (caps & ARCH_PEBS_CNTR_MASK)
+		x86_pmu.large_pebs_flags |= PERF_SAMPLE_READ;
+
+	if (!(caps & ARCH_PEBS_AUX))
+		x86_pmu.large_pebs_flags &= ~PERF_SAMPLE_DATA_SRC;
+	if (!(caps & ARCH_PEBS_GPR)) {
+		x86_pmu.large_pebs_flags &=
+			~(PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER);
+	}
+}
+
+#define counter_mask(_gp, _fixed) ((_gp) | ((u64)(_fixed) << INTEL_PMC_IDX_FIXED))
+
 static void update_pmu_cap(struct pmu *pmu)
 {
-	unsigned int cntr, fixed_cntr, ecx, edx;
-	union cpuid35_eax eax;
-	union cpuid35_ebx ebx;
+	unsigned int eax, ebx, ecx, edx;
+	union cpuid35_eax eax_0;
+	union cpuid35_ebx ebx_0;
+	u64 cntrs_mask = 0;
+	u64 pebs_mask = 0;
+	u64 pdists_mask = 0;
 
-	cpuid(ARCH_PERFMON_EXT_LEAF, &eax.full, &ebx.full, &ecx, &edx);
+	cpuid(ARCH_PERFMON_EXT_LEAF, &eax_0.full, &ebx_0.full, &ecx, &edx);
 
-	if (ebx.split.umask2)
+	if (ebx_0.split.umask2)
 		hybrid(pmu, config_mask) |= ARCH_PERFMON_EVENTSEL_UMASK2;
-	if (ebx.split.eq)
+	if (ebx_0.split.eq)
 		hybrid(pmu, config_mask) |= ARCH_PERFMON_EVENTSEL_EQ;
 
-	if (eax.split.cntr_subleaf) {
+	if (eax_0.split.cntr_subleaf) {
 		cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF,
-			    &cntr, &fixed_cntr, &ecx, &edx);
-		hybrid(pmu, cntr_mask64) = cntr;
-		hybrid(pmu, fixed_cntr_mask64) = fixed_cntr;
+			    &eax, &ebx, &ecx, &edx);
+		hybrid(pmu, cntr_mask64) = eax;
+		hybrid(pmu, fixed_cntr_mask64) = ebx;
+		cntrs_mask = counter_mask(eax, ebx);
 	}
 
-	if (eax.split.acr_subleaf) {
+	if (eax_0.split.acr_subleaf) {
 		cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_ACR_LEAF,
-			    &cntr, &fixed_cntr, &ecx, &edx);
+			    &eax, &ebx, &ecx, &edx);
 		/* The mask of the counters which can be reloaded */
-		hybrid(pmu, acr_cntr_mask64) = cntr | ((u64)fixed_cntr << INTEL_PMC_IDX_FIXED);
-
+		hybrid(pmu, acr_cntr_mask64) = counter_mask(eax, ebx);
 		/* The mask of the counters which can cause a reload of reloadable counters */
-		hybrid(pmu, acr_cause_mask64) = ecx | ((u64)edx << INTEL_PMC_IDX_FIXED);
+		hybrid(pmu, acr_cause_mask64) = counter_mask(ecx, edx);
+	}
+
+	/* Bits[5:4] should be set simultaneously if arch-PEBS is supported */
+	if (eax_0.split.pebs_caps_subleaf && eax_0.split.pebs_cnts_subleaf) {
+		cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_PEBS_CAP_LEAF,
+			    &eax, &ebx, &ecx, &edx);
+		hybrid(pmu, arch_pebs_cap).caps = (u64)ebx << 32;
+
+		cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_PEBS_COUNTER_LEAF,
+			    &eax, &ebx, &ecx, &edx);
+		pebs_mask   = counter_mask(eax, ecx);
+		pdists_mask = counter_mask(ebx, edx);
+		hybrid(pmu, arch_pebs_cap).counters = pebs_mask;
+		hybrid(pmu, arch_pebs_cap).pdists = pdists_mask;
+
+		if (WARN_ON((pebs_mask | pdists_mask) & ~cntrs_mask)) {
+			x86_pmu.arch_pebs = 0;
+		} else {
+			__intel_update_pmu_caps(pmu);
+			__intel_update_large_pebs_flags(pmu);
+		}
+	} else {
+		WARN_ON(x86_pmu.arch_pebs == 1);
+		x86_pmu.arch_pebs = 0;
 	}
 
 	if (!intel_pmu_broken_perf_cap()) {
@@ -5319,10 +5692,7 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
 	else
 		pmu->intel_ctrl &= ~GLOBAL_CTRL_EN_PERF_METRICS;
 
-	intel_pmu_check_event_constraints(pmu->event_constraints,
-					  pmu->cntr_mask64,
-					  pmu->fixed_cntr_mask64,
-					  pmu->intel_ctrl);
+	intel_pmu_check_event_constraints_all(&pmu->pmu);
 
 	intel_pmu_check_extra_regs(pmu->extra_regs);
 }
@@ -5418,6 +5788,7 @@ static void intel_pmu_cpu_starting(int cpu)
 		return;
 
 	init_debug_store_on_cpu(cpu);
+	init_arch_pebs_on_cpu(cpu);
 	/*
 	 * Deal with CPUs that don't clear their LBRs on power-up, and that may
 	 * even boot with LBRs enabled.
@@ -5456,6 +5827,8 @@ static void intel_pmu_cpu_starting(int cpu)
 		}
 	}
 
+	__intel_update_pmu_caps(cpuc->pmu);
+
 	if (!cpuc->shared_regs)
 		return;
 
@@ -5515,6 +5888,7 @@ static void free_excl_cntrs(struct cpu_hw_events *cpuc)
 static void intel_pmu_cpu_dying(int cpu)
 {
 	fini_debug_store_on_cpu(cpu);
+	fini_arch_pebs_on_cpu(cpu);
 }
 
 void intel_cpuc_finish(struct cpu_hw_events *cpuc)
@@ -5535,6 +5909,7 @@ static void intel_pmu_cpu_dead(int cpu)
 {
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
 
+	release_arch_pebs_buf_on_cpu(cpu);
 	intel_cpuc_finish(cpuc);
 
 	if (is_hybrid() && cpuc->pmu)
@@ -6250,7 +6625,7 @@ tsx_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 static umode_t
 pebs_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 {
-	return x86_pmu.ds_pebs ? attr->mode : 0;
+	return intel_pmu_has_pebs() ? attr->mode : 0;
 }
 
 static umode_t
@@ -6940,8 +7315,11 @@ __init int intel_pmu_init(void)
 	 * Many features on and after V6 require dynamic constraint,
 	 * e.g., Arch PEBS, ACR.
 	 */
-	if (version >= 6)
+	if (version >= 6) {
 		x86_pmu.flags |= PMU_FL_DYN_CONSTRAINT;
+		x86_pmu.late_setup = intel_pmu_late_setup;
+	}
+
 	/*
 	 * Install the hw-cache-events table:
 	 */
@@ -7727,6 +8105,14 @@ __init int intel_pmu_init(void)
 	if (!is_hybrid() && boot_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT))
 		update_pmu_cap(NULL);
 
+	if (x86_pmu.arch_pebs) {
+		static_call_update(intel_pmu_disable_event_ext,
+				   intel_pmu_disable_event_ext);
+		static_call_update(intel_pmu_enable_event_ext,
+				   intel_pmu_enable_event_ext);
+		pr_cont("Architectural PEBS, ");
+	}
+
 	intel_pmu_check_counters_mask(&x86_pmu.cntr_mask64,
 				      &x86_pmu.fixed_cntr_mask64,
 				      &x86_pmu.intel_ctrl);
@@ -7735,10 +8121,8 @@ __init int intel_pmu_init(void)
 	if (x86_pmu.intel_cap.anythread_deprecated)
 		x86_pmu.format_attrs = intel_arch_formats_attr;
 
-	intel_pmu_check_event_constraints(x86_pmu.event_constraints,
-					  x86_pmu.cntr_mask64,
-					  x86_pmu.fixed_cntr_mask64,
-					  x86_pmu.intel_ctrl);
+	intel_pmu_check_event_constraints_all(NULL);
+
 	/*
 	 * Access LBR MSR may cause #GP under certain circumstances.
 	 * Check all LBR MSR here.