diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index f5e5906ae36c9dc9b8cdaabb6c630983096c0126..e7edce877878f4cdd66febf633e2348774cc63cf 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -435,7 +435,7 @@ static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc,
 	 * be removed on one CPU at a time AND PMU is disabled
 	 * when we come here
 	 */
-	for (i = 0; i < x86_pmu.num_counters; i++) {
+	for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		if (cmpxchg(nb->owners + i, event, NULL) == event)
 			break;
 	}
@@ -502,7 +502,7 @@ __amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *ev
 	 * because of successive calls to x86_schedule_events() from
 	 * hw_perf_group_sched_in() without hw_perf_enable()
 	 */
-	for_each_set_bit(idx, c->idxmsk, x86_pmu.num_counters) {
+	for_each_set_bit(idx, c->idxmsk, x86_pmu_max_num_counters(NULL)) {
 		if (new == -1 || hwc->idx == idx)
 			/* assign free slot, prefer hwc->idx */
 			old = cmpxchg(nb->owners + idx, NULL, event);
@@ -545,7 +545,7 @@ static struct amd_nb *amd_alloc_nb(int cpu)
 	/*
 	 * initialize all possible NB constraints
 	 */
-	for (i = 0; i < x86_pmu.num_counters; i++) {
+	for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		__set_bit(i, nb->event_constraints[i].idxmsk);
 		nb->event_constraints[i].weight = 1;
 	}
@@ -738,7 +738,7 @@ static void amd_pmu_check_overflow(void)
 	 * counters are always enabled when this function is called and
 	 * ARCH_PERFMON_EVENTSEL_INT is always set.
 	 */
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
 
@@ -758,7 +758,7 @@ static void amd_pmu_enable_all(int added)
 
 	amd_brs_enable_all();
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		/* only activate events which are marked as active */
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
@@ -951,7 +951,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 	/* Clear any reserved bits set by buggy microcode */
 	status &= amd_pmu_global_cntr_mask;
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
 
@@ -1291,7 +1291,7 @@ static __initconst const struct x86_pmu amd_pmu = {
 	.addr_offset            = amd_pmu_addr_offset,
 	.event_map		= amd_pmu_event_map,
 	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
-	.num_counters		= AMD64_NUM_COUNTERS,
+	.cntr_mask64		= GENMASK_ULL(AMD64_NUM_COUNTERS - 1, 0),
 	.add			= amd_pmu_add_event,
 	.del			= amd_pmu_del_event,
 	.cntval_bits		= 48,
@@ -1390,7 +1390,7 @@ static int __init amd_core_pmu_init(void)
 	 */
 	x86_pmu.eventsel	= MSR_F15H_PERF_CTL;
 	x86_pmu.perfctr		= MSR_F15H_PERF_CTR;
-	x86_pmu.num_counters	= AMD64_NUM_COUNTERS_CORE;
+	x86_pmu.cntr_mask64	= GENMASK_ULL(AMD64_NUM_COUNTERS_CORE - 1, 0);
 
 	/* Check for Performance Monitoring v2 support */
 	if (boot_cpu_has(X86_FEATURE_PERFMON_V2)) {
@@ -1400,9 +1400,9 @@ static int __init amd_core_pmu_init(void)
 		x86_pmu.version = 2;
 
 		/* Find the number of available Core PMCs */
-		x86_pmu.num_counters = ebx.split.num_core_pmc;
+		x86_pmu.cntr_mask64 = GENMASK_ULL(ebx.split.num_core_pmc - 1, 0);
 
-		amd_pmu_global_cntr_mask = (1ULL << x86_pmu.num_counters) - 1;
+		amd_pmu_global_cntr_mask = x86_pmu.cntr_mask64;
 
 		/* Update PMC handling functions */
 		x86_pmu.enable_all = amd_pmu_v2_enable_all;
@@ -1430,12 +1430,12 @@ static int __init amd_core_pmu_init(void)
 		 * even numbered counter that has a consecutive adjacent odd
 		 * numbered counter following it.
 		 */
-		for (i = 0; i < x86_pmu.num_counters - 1; i += 2)
+		for (i = 0; i < x86_pmu_max_num_counters(NULL) - 1; i += 2)
 			even_ctr_mask |= BIT_ULL(i);
 
 		pair_constraint = (struct event_constraint)
 				    __EVENT_CONSTRAINT(0, even_ctr_mask, 0,
-				    x86_pmu.num_counters / 2, 0,
+				    x86_pmu_max_num_counters(NULL) / 2, 0,
 				    PERF_X86_EVENT_PAIR);
 
 		x86_pmu.get_event_constraints = amd_get_event_constraints_f17h;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 26f83ad47726076024cc7f33bc547cf1c0c98fa2..84f8c0bc15a09087cc60e967de73bd37a98d9e44 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -94,6 +94,8 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_aliases, *x86_pmu.pebs_aliases);
 
 DEFINE_STATIC_CALL_NULL(x86_pmu_filter, *x86_pmu.filter);
 
+DEFINE_STATIC_CALL_NULL(x86_pmu_late_setup, *x86_pmu.late_setup);
+
 /*
  * This one is magic, it will get called even when PMU init fails (because
  * there is no PMU), in which case it should simply return NULL.
@@ -191,29 +193,31 @@ static DEFINE_MUTEX(pmc_reserve_mutex);
 
 #ifdef CONFIG_X86_LOCAL_APIC
 
-static inline int get_possible_num_counters(void)
+static inline u64 get_possible_counter_mask(void)
 {
-	int i, num_counters = x86_pmu.num_counters;
+	u64 cntr_mask = x86_pmu.cntr_mask64;
+	int i;
 
 	if (!is_hybrid())
-		return num_counters;
+		return cntr_mask;
 
 	for (i = 0; i < x86_pmu.num_hybrid_pmus; i++)
-		num_counters = max_t(int, num_counters, x86_pmu.hybrid_pmu[i].num_counters);
+		cntr_mask |= x86_pmu.hybrid_pmu[i].cntr_mask64;
 
-	return num_counters;
+	return cntr_mask;
 }
 
 static bool reserve_pmc_hardware(void)
 {
-	int i, num_counters = get_possible_num_counters();
+	u64 cntr_mask = get_possible_counter_mask();
+	int i, end;
 
-	for (i = 0; i < num_counters; i++) {
+	for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) {
 		if (!reserve_perfctr_nmi(x86_pmu_event_addr(i)))
 			goto perfctr_fail;
 	}
 
-	for (i = 0; i < num_counters; i++) {
+	for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) {
 		if (!reserve_evntsel_nmi(x86_pmu_config_addr(i)))
 			goto eventsel_fail;
 	}
@@ -221,13 +225,14 @@ static bool reserve_pmc_hardware(void)
 	return true;
 
 eventsel_fail:
-	for (i--; i >= 0; i--)
+	end = i;
+	for_each_set_bit(i, (unsigned long *)&cntr_mask, end)
 		release_evntsel_nmi(x86_pmu_config_addr(i));
-
-	i = num_counters;
+	i = X86_PMC_IDX_MAX;
 
 perfctr_fail:
-	for (i--; i >= 0; i--)
+	end = i;
+	for_each_set_bit(i, (unsigned long *)&cntr_mask, end)
 		release_perfctr_nmi(x86_pmu_event_addr(i));
 
 	return false;
@@ -235,9 +240,10 @@ static bool reserve_pmc_hardware(void)
 
 static void release_pmc_hardware(void)
 {
-	int i, num_counters = get_possible_num_counters();
+	u64 cntr_mask = get_possible_counter_mask();
+	int i;
 
-	for (i = 0; i < num_counters; i++) {
+	for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) {
 		release_perfctr_nmi(x86_pmu_event_addr(i));
 		release_evntsel_nmi(x86_pmu_config_addr(i));
 	}
@@ -250,7 +256,8 @@ static void release_pmc_hardware(void) {}
 
 #endif
 
-bool check_hw_exists(struct pmu *pmu, int num_counters, int num_counters_fixed)
+bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
+		     unsigned long *fixed_cntr_mask)
 {
 	u64 val, val_fail = -1, val_new= ~0;
 	int i, reg, reg_fail = -1, ret = 0;
@@ -261,7 +268,7 @@ bool check_hw_exists(struct pmu *pmu, int num_counters, int num_counters_fixed)
 	 * Check to see if the BIOS enabled any of the counters, if so
 	 * complain and bail.
 	 */
-	for (i = 0; i < num_counters; i++) {
+	for_each_set_bit(i, cntr_mask, X86_PMC_IDX_MAX) {
 		reg = x86_pmu_config_addr(i);
 		ret = rdmsrl_safe(reg, &val);
 		if (ret)
@@ -275,12 +282,12 @@ bool check_hw_exists(struct pmu *pmu, int num_counters, int num_counters_fixed)
 		}
 	}
 
-	if (num_counters_fixed) {
+	if (*(u64 *)fixed_cntr_mask) {
 		reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
 		ret = rdmsrl_safe(reg, &val);
 		if (ret)
 			goto msr_fail;
-		for (i = 0; i < num_counters_fixed; i++) {
+		for_each_set_bit(i, fixed_cntr_mask, X86_PMC_IDX_MAX) {
 			if (fixed_counter_disabled(i, pmu))
 				continue;
 			if (val & (0x03ULL << i*4)) {
@@ -621,7 +628,7 @@ int x86_pmu_hw_config(struct perf_event *event)
 		event->hw.config |= ARCH_PERFMON_EVENTSEL_OS;
 
 	if (event->attr.type == event->pmu->type)
-		event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK;
+		event->hw.config |= x86_pmu_get_event_config(event);
 
 	if (is_sampling_event(event) && !event->attr.freq && x86_pmu.limit_period) {
 		s64 left = event->attr.sample_period;
@@ -668,6 +675,7 @@ static int __x86_pmu_event_init(struct perf_event *event)
 	event->hw.idx = -1;
 	event->hw.last_cpu = -1;
 	event->hw.last_tag = ~0ULL;
+	event->hw.dyn_constraint = ~0ULL;
 
 	/* mark unused */
 	event->hw.extra_reg.idx = EXTRA_REG_NONE;
@@ -681,7 +689,7 @@ void x86_pmu_disable_all(void)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
 		u64 val;
 
@@ -738,7 +746,7 @@ void x86_pmu_enable_all(int added)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
 
 		if (!test_bit(idx, cpuc->active_mask))
@@ -748,17 +756,18 @@ void x86_pmu_enable_all(int added)
 	}
 }
 
-static inline int is_x86_event(struct perf_event *event)
+int is_x86_event(struct perf_event *event)
 {
-	int i;
-
-	if (!is_hybrid())
-		return event->pmu == &pmu;
-
-	for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) {
-		if (event->pmu == &x86_pmu.hybrid_pmu[i].pmu)
-			return true;
-	}
+	/*
+	 * For a non-hybrid platforms, the type of X86 pmu is
+	 * always PERF_TYPE_RAW.
+	 * For a hybrid platform, the PERF_PMU_CAP_EXTENDED_HW_TYPE
+	 * is a unique capability for the X86 PMU.
+	 * Use them to detect a X86 event.
+	 */
+	if (event->pmu->type == PERF_TYPE_RAW ||
+	    event->pmu->capabilities & PERF_PMU_CAP_EXTENDED_HW_TYPE)
+		return true;
 
 	return false;
 }
@@ -977,7 +986,6 @@ EXPORT_SYMBOL_GPL(perf_assign_events);
 
 int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 {
-	int num_counters = hybrid(cpuc->pmu, num_counters);
 	struct event_constraint *c;
 	struct perf_event *e;
 	int n0, i, wmin, wmax, unsched = 0;
@@ -1053,7 +1061,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 
 	/* slow path */
 	if (i != n) {
-		int gpmax = num_counters;
+		int gpmax = x86_pmu_max_num_counters(cpuc->pmu);
 
 		/*
 		 * Do not allow scheduling of more than half the available
@@ -1074,7 +1082,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 		 * the extra Merge events needed by large increment events.
 		 */
 		if (x86_pmu.flags & PMU_FL_PAIR) {
-			gpmax = num_counters - cpuc->n_pair;
+			gpmax -= cpuc->n_pair;
 			WARN_ON(gpmax <= 0);
 		}
 
@@ -1159,12 +1167,10 @@ static int collect_event(struct cpu_hw_events *cpuc, struct perf_event *event,
  */
 static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, bool dogrp)
 {
-	int num_counters = hybrid(cpuc->pmu, num_counters);
-	int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
 	struct perf_event *event;
 	int n, max_count;
 
-	max_count = num_counters + num_counters_fixed;
+	max_count = x86_pmu_num_counters(cpuc->pmu) + x86_pmu_num_counters_fixed(cpuc->pmu);
 
 	/* current number of events already accepted */
 	n = cpuc->n_events;
@@ -1236,8 +1242,7 @@ static inline void x86_assign_hw_event(struct perf_event *event,
 		fallthrough;
 	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS-1:
 		hwc->config_base = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
-		hwc->event_base = MSR_ARCH_PERFMON_FIXED_CTR0 +
-				(idx - INTEL_PMC_IDX_FIXED);
+		hwc->event_base = x86_pmu_fixed_ctr_addr(idx - INTEL_PMC_IDX_FIXED);
 		hwc->event_base_rdpmc = (idx - INTEL_PMC_IDX_FIXED) |
 					INTEL_PMC_FIXED_RDPMC_BASE;
 		break;
@@ -1297,6 +1302,15 @@ static void x86_pmu_enable(struct pmu *pmu)
 
 	if (cpuc->n_added) {
 		int n_running = cpuc->n_events - cpuc->n_added;
+
+		/*
+		 * The late setup (after counters are scheduled)
+		 * is required for some cases, e.g., PEBS counters
+		 * snapshotting. Because an accurate counter index
+		 * is needed.
+		 */
+		static_call_cond(x86_pmu_late_setup)();
+
 		/*
 		 * apply assignment obtained either from
 		 * hw_perf_group_sched_in() or x86_pmu_enable()
@@ -1524,13 +1538,13 @@ void perf_event_print_debug(void)
 	u64 pebs, debugctl;
 	int cpu = smp_processor_id();
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
-	int num_counters = hybrid(cpuc->pmu, num_counters);
-	int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
+	unsigned long *cntr_mask = hybrid(cpuc->pmu, cntr_mask);
+	unsigned long *fixed_cntr_mask = hybrid(cpuc->pmu, fixed_cntr_mask);
 	struct event_constraint *pebs_constraints = hybrid(cpuc->pmu, pebs_constraints);
 	unsigned long flags;
 	int idx;
 
-	if (!num_counters)
+	if (!*(u64 *)cntr_mask)
 		return;
 
 	local_irq_save(flags);
@@ -1557,7 +1571,7 @@ void perf_event_print_debug(void)
 	}
 	pr_info("CPU#%d: active:     %016llx\n", cpu, *(u64 *)cpuc->active_mask);
 
-	for (idx = 0; idx < num_counters; idx++) {
+	for_each_set_bit(idx, cntr_mask, X86_PMC_IDX_MAX) {
 		rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl);
 		rdmsrl(x86_pmu_event_addr(idx), pmc_count);
 
@@ -1570,10 +1584,10 @@ void perf_event_print_debug(void)
 		pr_info("CPU#%d:   gen-PMC%d left:  %016llx\n",
 			cpu, idx, prev_left);
 	}
-	for (idx = 0; idx < num_counters_fixed; idx++) {
+	for_each_set_bit(idx, fixed_cntr_mask, X86_PMC_IDX_MAX) {
 		if (fixed_counter_disabled(idx, cpuc->pmu))
 			continue;
-		rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);
+		rdmsrl(x86_pmu_fixed_ctr_addr(idx), pmc_count);
 
 		pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
 			cpu, idx, pmc_count);
@@ -1684,7 +1698,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 	 */
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
 
@@ -2033,6 +2047,8 @@ static void x86_pmu_static_call_update(void)
 
 	static_call_update(x86_pmu_guest_get_msrs, x86_pmu.guest_get_msrs);
 	static_call_update(x86_pmu_filter, x86_pmu.filter);
+
+	static_call_update(x86_pmu_late_setup, x86_pmu.late_setup);
 }
 
 static void _x86_pmu_read(struct perf_event *event)
@@ -2040,18 +2056,15 @@ static void _x86_pmu_read(struct perf_event *event)
 	static_call(x86_pmu_update)(event);
 }
 
-void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed,
-			  u64 intel_ctrl)
+void x86_pmu_show_pmu_cap(struct pmu *pmu)
 {
 	pr_info("... version:                %d\n",     x86_pmu.version);
 	pr_info("... bit width:              %d\n",     x86_pmu.cntval_bits);
-	pr_info("... generic registers:      %d\n",     num_counters);
+	pr_info("... generic registers:      %d\n",     x86_pmu_num_counters(pmu));
 	pr_info("... value mask:             %016Lx\n", x86_pmu.cntval_mask);
 	pr_info("... max period:             %016Lx\n", x86_pmu.max_period);
-	pr_info("... fixed-purpose events:   %lu\n",
-			hweight64((((1ULL << num_counters_fixed) - 1)
-					<< INTEL_PMC_IDX_FIXED) & intel_ctrl));
-	pr_info("... event mask:             %016Lx\n", intel_ctrl);
+	pr_info("... fixed-purpose events:   %d\n",     x86_pmu_num_counters_fixed(pmu));
+	pr_info("... event mask:             %016Lx\n", hybrid(pmu, intel_ctrl));
 }
 
 static int __init init_hw_perf_events(void)
@@ -2088,7 +2101,7 @@ static int __init init_hw_perf_events(void)
 	pmu_check_apic();
 
 	/* sanity check that the hardware exists or is emulated */
-	if (!check_hw_exists(&pmu, x86_pmu.num_counters, x86_pmu.num_counters_fixed))
+	if (!check_hw_exists(&pmu, x86_pmu.cntr_mask, x86_pmu.fixed_cntr_mask))
 		goto out_bad_pmu;
 
 	pr_cont("%s PMU driver.\n", x86_pmu.name);
@@ -2099,14 +2112,17 @@ static int __init init_hw_perf_events(void)
 		quirk->func();
 
 	if (!x86_pmu.intel_ctrl)
-		x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
+		x86_pmu.intel_ctrl = x86_pmu.cntr_mask64;
+
+	if (!x86_pmu.config_mask)
+		x86_pmu.config_mask = X86_RAW_EVENT_MASK;
 
 	perf_events_lapic_init();
 	register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI");
 
 	unconstrained = (struct event_constraint)
-		__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
-				   0, x86_pmu.num_counters, 0, 0);
+		__EVENT_CONSTRAINT(0, x86_pmu.cntr_mask64,
+				   0, x86_pmu_num_counters(NULL), 0, 0);
 
 	x86_pmu_format_group.attrs = x86_pmu.format_attrs;
 
@@ -2115,11 +2131,8 @@ static int __init init_hw_perf_events(void)
 
 	pmu.attr_update = x86_pmu.attr_update;
 
-	if (!is_hybrid()) {
-		x86_pmu_show_pmu_cap(x86_pmu.num_counters,
-				     x86_pmu.num_counters_fixed,
-				     x86_pmu.intel_ctrl);
-	}
+	if (!is_hybrid())
+		x86_pmu_show_pmu_cap(NULL);
 
 	if (!x86_pmu.read)
 		x86_pmu.read = _x86_pmu_read;
@@ -2483,10 +2496,10 @@ void perf_clear_dirty_counters(void)
 	for_each_set_bit(i, cpuc->dirty, X86_PMC_IDX_MAX) {
 		if (i >= INTEL_PMC_IDX_FIXED) {
 			/* Metrics and fake events don't have corresponding HW counters. */
-			if ((i - INTEL_PMC_IDX_FIXED) >= hybrid(cpuc->pmu, num_counters_fixed))
+			if (!test_bit(i - INTEL_PMC_IDX_FIXED, hybrid(cpuc->pmu, fixed_cntr_mask)))
 				continue;
 
-			wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + (i - INTEL_PMC_IDX_FIXED), 0);
+			wrmsrl(x86_pmu_fixed_ctr_addr(i - INTEL_PMC_IDX_FIXED), 0);
 		} else {
 			wrmsrl(x86_pmu_event_addr(i), 0);
 		}
@@ -3049,8 +3062,8 @@ void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
 	 * base PMU holds the correct number of counters for P-cores.
 	 */
 	cap->version		= x86_pmu.version;
-	cap->num_counters_gp	= x86_pmu.num_counters;
-	cap->num_counters_fixed	= x86_pmu.num_counters_fixed;
+	cap->num_counters_gp	= x86_pmu_num_counters(NULL);
+	cap->num_counters_fixed	= x86_pmu_num_counters_fixed(NULL);
 	cap->bit_width_gp	= x86_pmu.cntval_bits;
 	cap->bit_width_fixed	= x86_pmu.cntval_bits;
 	cap->events_mask	= (unsigned int)x86_pmu.events_maskl;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a5046c19c7ef2cb3d8792378743461650926b64f..a6b5259d4404cea5753e56f325837abf60b87011 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -211,6 +211,17 @@ static struct event_constraint intel_slm_event_constraints[] __read_mostly =
 	EVENT_CONSTRAINT_END
 };
 
+static struct event_constraint intel_skt_event_constraints[] __read_mostly = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */
+	FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF_TSC_P */
+	FIXED_EVENT_CONSTRAINT(0x0073, 4), /* TOPDOWN_BAD_SPECULATION.ALL */
+	FIXED_EVENT_CONSTRAINT(0x019c, 5), /* TOPDOWN_FE_BOUND.ALL */
+	FIXED_EVENT_CONSTRAINT(0x02c2, 6), /* TOPDOWN_RETIRING.ALL */
+	EVENT_CONSTRAINT_END
+};
+
 static struct event_constraint intel_skl_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
@@ -360,6 +371,55 @@ static struct extra_reg intel_rwc_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+static struct event_constraint intel_lnc_event_constraints[] = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x0100, 0),	/* INST_RETIRED.PREC_DIST */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
+	FIXED_EVENT_CONSTRAINT(0x013c, 2),	/* CPU_CLK_UNHALTED.REF_TSC_P */
+	FIXED_EVENT_CONSTRAINT(0x0400, 3),	/* SLOTS */
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_RETIRING, 0),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BAD_SPEC, 1),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FE_BOUND, 2),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BE_BOUND, 3),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_HEAVY_OPS, 4),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BR_MISPREDICT, 5),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FETCH_LAT, 6),
+	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_MEM_BOUND, 7),
+
+	INTEL_UEVENT_CONSTRAINT(0x0148, 0x4),
+	INTEL_UEVENT_CONSTRAINT(0x0175, 0x4),
+
+	INTEL_EVENT_CONSTRAINT(0x2e, 0x3ff),
+	INTEL_EVENT_CONSTRAINT(0x3c, 0x3ff),
+	/*
+	 * Generally event codes < 0x90 are restricted to counters 0-3.
+	 * The 0x2E and 0x3C are exception, which has no restriction.
+	 */
+	INTEL_EVENT_CONSTRAINT_RANGE(0x01, 0x8f, 0xf),
+
+	INTEL_UEVENT_CONSTRAINT(0x01a3, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4),
+	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4),
+	INTEL_UEVENT_CONSTRAINT(0x04a4, 0x1),
+	INTEL_UEVENT_CONSTRAINT(0x08a4, 0x1),
+	INTEL_UEVENT_CONSTRAINT(0x10a4, 0x1),
+	INTEL_UEVENT_CONSTRAINT(0x01b1, 0x8),
+	INTEL_UEVENT_CONSTRAINT(0x02cd, 0x3),
+	INTEL_EVENT_CONSTRAINT(0xce, 0x1),
+
+	INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xdf, 0xf),
+	/*
+	 * Generally event codes >= 0x90 are likely to have no restrictions.
+	 * The exception are defined as above.
+	 */
+	INTEL_EVENT_CONSTRAINT_RANGE(0x90, 0xfe, 0x3ff),
+
+	EVENT_CONSTRAINT_END
+};
+
+
 EVENT_ATTR_STR(mem-loads,	mem_ld_nhm,	"event=0x0b,umask=0x10,ldlat=3");
 EVENT_ATTR_STR(mem-loads,	mem_ld_snb,	"event=0xcd,umask=0x1,ldlat=3");
 EVENT_ATTR_STR(mem-stores,	mem_st_snb,	"event=0xcd,umask=0x2");
@@ -2150,6 +2210,18 @@ static struct extra_reg intel_cmt_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+EVENT_ATTR_STR(topdown-fe-bound,       td_fe_bound_skt,        "event=0x9c,umask=0x01");
+EVENT_ATTR_STR(topdown-retiring,       td_retiring_skt,        "event=0xc2,umask=0x02");
+EVENT_ATTR_STR(topdown-be-bound,       td_be_bound_skt,        "event=0xa4,umask=0x02");
+
+static struct attribute *skt_events_attrs[] = {
+	EVENT_PTR(td_fe_bound_skt),
+	EVENT_PTR(td_retiring_skt),
+	EVENT_PTR(td_bad_spec_cmt),
+	EVENT_PTR(td_be_bound_skt),
+	NULL,
+};
+
 #define KNL_OT_L2_HITE		BIT_ULL(19) /* Other Tile L2 Hit */
 #define KNL_OT_L2_HITF		BIT_ULL(20) /* Other Tile L2 Hit */
 #define KNL_MCDRAM_LOCAL	BIT_ULL(21)
@@ -2529,6 +2601,9 @@ static void intel_pmu_del_event(struct perf_event *event)
 		intel_pmu_lbr_del(event);
 	if (event->attr.precise_ip)
 		intel_pmu_pebs_del(event);
+	if (is_pebs_counter_event_group(event) ||
+	    is_acr_event_group(event))
+		this_cpu_ptr(&cpu_hw_events)->n_late_setup--;
 }
 
 static int icl_set_topdown_event_period(struct perf_event *event)
@@ -2640,7 +2715,7 @@ static void update_saved_topdown_regs(struct perf_event *event, u64 slots,
  * modify by a NMI. PMU has to be disabled before calling this function.
  */
 
-static u64 intel_update_topdown_event(struct perf_event *event, int metric_end)
+static u64 intel_update_topdown_event(struct perf_event *event, int metric_end, u64 *val)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *other;
@@ -2648,13 +2723,24 @@ static u64 intel_update_topdown_event(struct perf_event *event, int metric_end)
 	bool reset = true;
 	int idx;
 
-	/* read Fixed counter 3 */
-	rdpmcl((3 | INTEL_PMC_FIXED_RDPMC_BASE), slots);
-	if (!slots)
-		return 0;
+	if (!val) {
+		/* read Fixed counter 3 */
+		rdpmcl((3 | INTEL_PMC_FIXED_RDPMC_BASE), slots);
+		if (!slots)
+			return 0;
 
-	/* read PERF_METRICS */
-	rdpmcl(INTEL_PMC_FIXED_RDPMC_METRICS, metrics);
+		/* read PERF_METRICS */
+		rdpmcl(INTEL_PMC_FIXED_RDPMC_METRICS, metrics);
+	} else {
+		slots = val[0];
+		metrics = val[1];
+		/*
+		 * Don't reset the PERF_METRICS and Fixed counter 3
+		 * for each PEBS record read. Utilize the RDPMC metrics
+		 * clear mode.
+		 */
+		reset = false;
+	}
 
 	for_each_set_bit(idx, cpuc->active_mask, metric_end + 1) {
 		if (!is_topdown_idx(idx))
@@ -2697,17 +2783,19 @@ static u64 intel_update_topdown_event(struct perf_event *event, int metric_end)
 	return slots;
 }
 
-static u64 icl_update_topdown_event(struct perf_event *event)
+static u64 icl_update_topdown_event(struct perf_event *event, u64 *val)
 {
 	return intel_update_topdown_event(event, INTEL_PMC_IDX_METRIC_BASE +
-						 x86_pmu.num_topdown_events - 1);
+						 x86_pmu.num_topdown_events - 1,
+					  val);
 }
 
-DEFINE_STATIC_CALL(intel_pmu_update_topdown_event, x86_perf_event_update);
+DEFINE_STATIC_CALL(intel_pmu_update_topdown_event, intel_pmu_topdown_event_update);
 
 static void intel_pmu_read_event(struct perf_event *event)
 {
-	if (event->hw.flags & (PERF_X86_EVENT_AUTO_RELOAD | PERF_X86_EVENT_TOPDOWN)) {
+	if (event->hw.flags & (PERF_X86_EVENT_AUTO_RELOAD | PERF_X86_EVENT_TOPDOWN) ||
+	    is_pebs_counter_event_group(event)) {
 		struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 		bool pmu_enabled = cpuc->enabled;
 
@@ -2719,8 +2807,12 @@ static void intel_pmu_read_event(struct perf_event *event)
 		if (pmu_enabled)
 			intel_pmu_disable_all();
 
-		if (is_topdown_event(event))
-			static_call(intel_pmu_update_topdown_event)(event);
+		/*
+		 * If the PEBS counters snapshotting is enabled,
+		 * the topdown event is available in PEBS records.
+		 */
+		if (is_topdown_event(event) && !is_pebs_counter_event_group(event))
+			static_call(intel_pmu_update_topdown_event)(event, NULL);
 		else
 			intel_pmu_drain_pebs_buffer();
 
@@ -2751,6 +2843,9 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 			return;
 
 		idx = INTEL_PMC_IDX_FIXED_SLOTS;
+
+		if (event->attr.config1 & INTEL_TD_CFG_METRIC_CLEAR)
+			bits |= INTEL_FIXED_3_METRICS_CLEAR;
 	}
 
 	intel_set_masks(event, idx);
@@ -2786,6 +2881,52 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 	cpuc->fixed_ctrl_val |= bits;
 }
 
+static void intel_pmu_config_acr(int idx, u64 mask, u32 reload)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int msr_b, msr_c;
+
+	if (!mask && !cpuc->acr_cfg_b[idx])
+		return;
+
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		msr_b = MSR_IA32_PMC_V6_GP0_CFG_B;
+		msr_c = MSR_IA32_PMC_V6_GP0_CFG_C;
+	} else {
+		msr_b = MSR_IA32_PMC_V6_FX0_CFG_B;
+		msr_c = MSR_IA32_PMC_V6_FX0_CFG_C;
+		idx -= INTEL_PMC_IDX_FIXED;
+	}
+
+	if (cpuc->acr_cfg_b[idx] != mask) {
+		wrmsrl(msr_b + x86_pmu.addr_offset(idx, false), mask);
+		cpuc->acr_cfg_b[idx] = mask;
+	}
+	/* Only need to update the reload value when there is a valid config value. */
+	if (mask && cpuc->acr_cfg_c[idx] != reload) {
+		wrmsrl(msr_c + x86_pmu.addr_offset(idx, false), reload);
+		cpuc->acr_cfg_c[idx] = reload;
+	}
+}
+
+static void intel_pmu_enable_acr(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!is_acr_event_group(event) || !event->attr.config2) {
+		/*
+		 * The disable doesn't clear the ACR CFG register.
+		 * Check and clear the ACR CFG register.
+		 */
+		intel_pmu_config_acr(hwc->idx, 0, 0);
+		return;
+	}
+
+	intel_pmu_config_acr(hwc->idx, hwc->config1, -hwc->sample_period);
+}
+
+DEFINE_STATIC_CALL_NULL(intel_pmu_enable_acr_event, intel_pmu_enable_acr);
+
 static void intel_pmu_enable_event(struct perf_event *event)
 {
 	u64 enable_mask = ARCH_PERFMON_EVENTSEL_ENABLE;
@@ -2800,9 +2941,12 @@ static void intel_pmu_enable_event(struct perf_event *event)
 		if (branch_sample_counters(event))
 			enable_mask |= ARCH_PERFMON_EVENTSEL_BR_CNTR;
 		intel_set_masks(event, idx);
+		static_call_cond(intel_pmu_enable_acr_event)(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);
+		fallthrough;
 	case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END:
 		intel_pmu_enable_fixed(event);
 		break;
@@ -2820,12 +2964,51 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	}
 }
 
+static void intel_pmu_acr_late_setup(struct cpu_hw_events *cpuc)
+{
+	struct perf_event *event, *leader;
+	int i, j, idx;
+
+	for (i = 0; i < cpuc->n_events; i++) {
+		leader = cpuc->event_list[i];
+		if (!is_acr_event_group(leader))
+			continue;
+
+		/* The ACR events must be contiguous. */
+		for (j = i; j < cpuc->n_events; j++) {
+			event = cpuc->event_list[j];
+			if (event->group_leader != leader->group_leader)
+				break;
+			for_each_set_bit(idx, (unsigned long *)&event->attr.config2, X86_PMC_IDX_MAX) {
+				if (WARN_ON_ONCE(i + idx > cpuc->n_events))
+					return;
+				__set_bit(cpuc->assign[i + idx], (unsigned long *)&event->hw.config1);
+			}
+		}
+		i = j - 1;
+	}
+}
+
+void intel_pmu_late_setup(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (!cpuc->n_late_setup)
+		return;
+
+	intel_pmu_pebs_late_setup(cpuc);
+	intel_pmu_acr_late_setup(cpuc);
+}
+
 static void intel_pmu_add_event(struct perf_event *event)
 {
 	if (event->attr.precise_ip)
 		intel_pmu_pebs_add(event);
 	if (intel_pmu_needs_branch_stack(event))
 		intel_pmu_lbr_add(event);
+	if (is_pebs_counter_event_group(event) ||
+	    is_acr_event_group(event))
+		this_cpu_ptr(&cpu_hw_events)->n_late_setup++;
 }
 
 /*
@@ -2860,7 +3043,7 @@ static int intel_pmu_set_period(struct perf_event *event)
 static u64 intel_pmu_update(struct perf_event *event)
 {
 	if (unlikely(is_topdown_count(event)))
-		return static_call(intel_pmu_update_topdown_event)(event);
+		return static_call(intel_pmu_update_topdown_event)(event, NULL);
 
 	return x86_perf_event_update(event);
 }
@@ -2869,26 +3052,26 @@ static void intel_pmu_reset(void)
 {
 	struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
-	int num_counters = hybrid(cpuc->pmu, num_counters);
+	unsigned long *cntr_mask = hybrid(cpuc->pmu, cntr_mask);
+	unsigned long *fixed_cntr_mask = hybrid(cpuc->pmu, fixed_cntr_mask);
 	unsigned long flags;
 	int idx;
 
-	if (!num_counters)
+	if (!*(u64 *)cntr_mask)
 		return;
 
 	local_irq_save(flags);
 
 	pr_info("clearing PMU state on CPU#%d\n", smp_processor_id());
 
-	for (idx = 0; idx < num_counters; idx++) {
+	for_each_set_bit(idx, cntr_mask, INTEL_PMC_MAX_GENERIC) {
 		wrmsrl_safe(x86_pmu_config_addr(idx), 0ull);
 		wrmsrl_safe(x86_pmu_event_addr(idx),  0ull);
 	}
-	for (idx = 0; idx < num_counters_fixed; idx++) {
+	for_each_set_bit(idx, fixed_cntr_mask, INTEL_PMC_MAX_FIXED) {
 		if (fixed_counter_disabled(idx, cpuc->pmu))
 			continue;
-		wrmsrl_safe(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
+		wrmsrl_safe(x86_pmu_fixed_ctr_addr(idx), 0ull);
 	}
 
 	if (ds)
@@ -2935,8 +3118,7 @@ static void x86_pmu_handle_guest_pebs(struct pt_regs *regs,
 	    !guest_pebs_idxs)
 		return;
 
-	for_each_set_bit(bit, (unsigned long *)&guest_pebs_idxs,
-			 INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed) {
+	for_each_set_bit(bit, (unsigned long *)&guest_pebs_idxs, X86_PMC_IDX_MAX) {
 		event = cpuc->events[bit];
 		if (!event->attr.precise_ip)
 			continue;
@@ -2956,7 +3138,6 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int bit;
 	int handled = 0;
-	u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl);
 
 	inc_irq_stat(apic_perf_irqs);
 
@@ -3000,7 +3181,6 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 		handled++;
 		x86_pmu_handle_guest_pebs(regs, &data);
 		static_call(x86_pmu_drain_pebs)(regs, &data);
-		status &= intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI;
 
 		/*
 		 * PMI throttle may be triggered, which stops the PEBS event.
@@ -3011,6 +3191,15 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 		 */
 		if (pebs_enabled != cpuc->pebs_enabled)
 			wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+
+		/*
+		 * Above PEBS handler (PEBS counters snapshotting) has updated fixed
+		 * counter 3 and perf metrics counts if they are in counter group,
+		 * unnecessary to update again.
+		 */
+		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;
 	}
 
 	/*
@@ -3027,9 +3216,11 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 	 */
 	if (__test_and_clear_bit(GLOBAL_STATUS_PERF_METRICS_OVF_BIT, (unsigned long *)&status)) {
 		handled++;
-		static_call(intel_pmu_update_topdown_event)(NULL);
+		static_call(intel_pmu_update_topdown_event)(NULL, NULL);
 	}
 
+	status &= hybrid(cpuc->pmu, intel_ctrl);
+
 	/*
 	 * Checkpointed counters can lead to 'spurious' PMIs because the
 	 * rollback caused by the PMI will have cleared the overflow status
@@ -3045,6 +3236,27 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 		if (!test_bit(bit, cpuc->active_mask))
 			continue;
 
+		/*
+		 * There may be unprocessed PEBS records in the PEBS buffer,
+		 * which still stores the previous values.
+		 * Process those records first before handling the latest value.
+		 * For example,
+		 * A is a regular counter
+		 * B is a PEBS event which reads A
+		 * C is a PEBS event
+		 *
+		 * The following can happen:
+		 * B-assist			A=1
+		 * C				A=2
+		 * B-assist			A=3
+		 * A-overflow-PMI		A=4
+		 * C-assist-PMI (PEBS buffer)	A=5
+		 *
+		 * 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);
+
 		if (!intel_pmu_save_and_restart(event))
 			continue;
 
@@ -3616,10 +3828,9 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	if (cpuc->excl_cntrs)
 		return intel_get_excl_constraints(cpuc, event, idx, c2);
 
-	/* Not all counters support the branch counter feature. */
-	if (branch_sample_counters(event)) {
+	if (event->hw.dyn_constraint != ~0ULL) {
 		c2 = dyn_constraint(cpuc, c2, idx);
-		c2->idxmsk64 &= x86_pmu.lbr_counters;
+		c2->idxmsk64 &= event->hw.dyn_constraint;
 		c2->weight = hweight64(c2->idxmsk64);
 	}
 
@@ -3960,6 +4171,39 @@ static u64 intel_pmu_freq_start_period(struct perf_event *event)
 	return start;
 }
 
+static inline bool intel_pmu_has_acr(struct pmu *pmu)
+{
+	return !!hybrid(pmu, acr_cause_mask64);
+}
+
+static bool intel_pmu_is_acr_group(struct perf_event *event)
+{
+	/* The group leader has the ACR flag set */
+	if (is_acr_event_group(event))
+		return true;
+
+	/* The acr_mask is set */
+	if (event->attr.config2)
+		return true;
+
+	return false;
+}
+
+static inline void intel_pmu_set_acr_cntr_constr(struct perf_event *event,
+						 u64 *cause_mask, int *num)
+{
+	event->hw.dyn_constraint &= hybrid(event->pmu, acr_cntr_mask64);
+	*cause_mask |= event->attr.config2;
+	*num += 1;
+}
+
+static inline void intel_pmu_set_acr_caused_constr(struct perf_event *event,
+						   int idx, u64 cause_mask)
+{
+	if (test_bit(idx, (unsigned long *)&cause_mask))
+		event->hw.dyn_constraint &= hybrid(event->pmu, acr_cause_mask64);
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
@@ -4017,15 +4261,19 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		leader = event->group_leader;
 		if (branch_sample_call_stack(leader))
 			return -EINVAL;
-		if (branch_sample_counters(leader))
+		if (branch_sample_counters(leader)) {
 			num++;
+			leader->hw.dyn_constraint &= x86_pmu.lbr_counters;
+		}
 		leader->hw.flags |= PERF_X86_EVENT_BRANCH_COUNTERS;
 
 		for_each_sibling_event(sibling, leader) {
 			if (branch_sample_call_stack(sibling))
 				return -EINVAL;
-			if (branch_sample_counters(sibling))
+			if (branch_sample_counters(sibling)) {
 				num++;
+				sibling->hw.dyn_constraint &= x86_pmu.lbr_counters;
+			}
 		}
 
 		if (num > fls(x86_pmu.lbr_counters))
@@ -4073,6 +4321,101 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		event->hw.flags |= PERF_X86_EVENT_PEBS_VIA_PT;
 	}
 
+	if ((event->attr.sample_type & PERF_SAMPLE_READ) &&
+	    (x86_pmu.intel_cap.pebs_format >= 6) &&
+	    x86_pmu.intel_cap.pebs_baseline &&
+	    is_sampling_event(event) &&
+	    event->attr.precise_ip)
+		event->group_leader->hw.flags |= PERF_X86_EVENT_PEBS_CNTR;
+
+	if (intel_pmu_has_acr(event->pmu) && intel_pmu_is_acr_group(event)) {
+		struct perf_event *sibling, *leader = event->group_leader;
+		struct pmu *pmu = event->pmu;
+		bool has_sw_event = false;
+		int num = 0, idx = 0;
+		u64 cause_mask = 0;
+
+		/* Not support perf metrics */
+		if (is_metric_event(event))
+			return -EINVAL;
+
+		/* Not support freq mode */
+		if (event->attr.freq)
+			return -EINVAL;
+
+		/* PDist is not supported */
+		if (event->attr.config2 && event->attr.precise_ip > 2)
+			return -EINVAL;
+
+		/* The reload value cannot exceeds the max period */
+		if (event->attr.sample_period > x86_pmu.max_period)
+			return -EINVAL;
+		/*
+		 * The counter-constraints of each event cannot be finalized
+		 * unless the whole group is scanned. However, it's hard
+		 * to know whether the event is the last one of the group.
+		 * Recalculate the counter-constraints for each event when
+		 * adding a new event.
+		 *
+		 * The group is traversed twice, which may be optimized later.
+		 * In the first round,
+		 * - Find all events which do reload when other events
+		 *   overflow and set the corresponding counter-constraints
+		 * - Add all events, which can cause other events reload,
+		 *   in the cause_mask
+		 * - Error out if the number of events exceeds the HW limit
+		 * - The ACR events must be contiguous.
+		 *   Error out if there are non-X86 events between ACR events.
+		 *   This is not a HW limit, but a SW limit.
+		 *   With the assumption, the intel_pmu_acr_late_setup() can
+		 *   easily convert the event idx to counter idx without
+		 *   traversing the whole event list.
+		 */
+		if (!is_x86_event(leader))
+			return -EINVAL;
+
+		if (leader->attr.config2)
+			intel_pmu_set_acr_cntr_constr(leader, &cause_mask, &num);
+
+		if (leader->nr_siblings) {
+			for_each_sibling_event(sibling, leader) {
+				if (!is_x86_event(sibling)) {
+					has_sw_event = true;
+					continue;
+				}
+				if (!sibling->attr.config2)
+					continue;
+				if (has_sw_event)
+					return -EINVAL;
+				intel_pmu_set_acr_cntr_constr(sibling, &cause_mask, &num);
+			}
+		}
+		if (leader != event && event->attr.config2) {
+			if (has_sw_event)
+				return -EINVAL;
+			intel_pmu_set_acr_cntr_constr(event, &cause_mask, &num);
+		}
+
+		if (hweight64(cause_mask) > hweight64(hybrid(pmu, acr_cause_mask64)) ||
+		    num > hweight64(hybrid(event->pmu, acr_cntr_mask64)))
+			return -EINVAL;
+		/*
+		 * In the second round, apply the counter-constraints for
+		 * the events which can cause other events reload.
+		 */
+		intel_pmu_set_acr_caused_constr(leader, idx++, cause_mask);
+
+		if (leader->nr_siblings) {
+			for_each_sibling_event(sibling, leader)
+				intel_pmu_set_acr_caused_constr(sibling, idx++, cause_mask);
+		}
+
+		if (leader != event)
+			intel_pmu_set_acr_caused_constr(event, idx, cause_mask);
+
+		leader->hw.flags |= PERF_X86_EVENT_ACR;
+	}
+
 	if ((event->attr.type == PERF_TYPE_HARDWARE) ||
 	    (event->attr.type == PERF_TYPE_HW_CACHE))
 		return 0;
@@ -4088,7 +4431,12 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	 * is used in a metrics group, it too cannot support sampling.
 	 */
 	if (intel_pmu_has_cap(event, PERF_CAP_METRICS_IDX) && is_topdown_event(event)) {
-		if (event->attr.config1 || event->attr.config2)
+		/* The metrics_clear can only be set for the slots event */
+		if (event->attr.config1 &&
+		    (!is_slots_event(event) || (event->attr.config1 & ~INTEL_TD_CFG_METRIC_CLEAR)))
+			return -EINVAL;
+
+		if (event->attr.config2)
 			return -EINVAL;
 
 		/*
@@ -4279,7 +4627,7 @@ static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr, void *data)
 	struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
 	int idx;
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++)  {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[idx];
 
 		arr[idx].msr = x86_pmu_config_addr(idx);
@@ -4297,7 +4645,7 @@ static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr, void *data)
 			arr[idx].guest &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
 	}
 
-	*nr = x86_pmu.num_counters;
+	*nr = x86_pmu_max_num_counters(cpuc->pmu);
 	return arr;
 }
 
@@ -4312,7 +4660,7 @@ static void core_pmu_enable_all(int added)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
 
 		if (!test_bit(idx, cpuc->active_mask) ||
@@ -4671,8 +5019,65 @@ PMU_FORMAT_ATTR(pc,	"config:19"	);
 PMU_FORMAT_ATTR(any,	"config:21"	); /* v3 + */
 PMU_FORMAT_ATTR(inv,	"config:23"	);
 PMU_FORMAT_ATTR(cmask,	"config:24-31"	);
-PMU_FORMAT_ATTR(in_tx,  "config:32");
-PMU_FORMAT_ATTR(in_tx_cp, "config:33");
+PMU_FORMAT_ATTR(in_tx,  "config:32"	);
+PMU_FORMAT_ATTR(in_tx_cp, "config:33"	);
+PMU_FORMAT_ATTR(eq,	"config:36"	); /* v6 + */
+
+PMU_FORMAT_ATTR(metrics_clear,	"config1:0"); /* PERF_CAPABILITIES.RDPMC_METRICS_CLEAR */
+
+static ssize_t umask2_show(struct device *dev,
+			   struct device_attribute *attr,
+			   char *page)
+{
+	u64 mask = hybrid(dev_get_drvdata(dev), config_mask) & ARCH_PERFMON_EVENTSEL_UMASK2;
+
+	if (mask == ARCH_PERFMON_EVENTSEL_UMASK2)
+		return sprintf(page, "config:8-15,40-47\n");
+
+	/* Roll back to the old format if umask2 is not supported. */
+	return sprintf(page, "config:8-15\n");
+}
+
+static struct device_attribute format_attr_umask2  =
+		__ATTR(umask, 0444, umask2_show, NULL);
+
+static struct attribute *format_evtsel_ext_attrs[] = {
+	&format_attr_umask2.attr,
+	&format_attr_eq.attr,
+	&format_attr_metrics_clear.attr,
+	NULL
+};
+
+static umode_t
+evtsel_ext_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	u64 mask;
+
+	/*
+	 * The umask and umask2 have different formats but share the
+	 * same attr name. In update mode, the previous value of the
+	 * umask is unconditionally removed before is_visible. If
+	 * umask2 format is not enumerated, it's impossible to roll
+	 * back to the old format.
+	 * Does the check in umask2_show rather than is_visible.
+	 */
+	if (i == 0)
+		return attr->mode;
+
+	mask = hybrid(dev_get_drvdata(dev), config_mask);
+	if (i == 1)
+		return (mask & ARCH_PERFMON_EVENTSEL_EQ) ? attr->mode : 0;
+
+	/* PERF_CAPABILITIES.RDPMC_METRICS_CLEAR */
+	if (i == 2) {
+		union perf_capabilities intel_cap = hybrid(dev_get_drvdata(dev), intel_cap);
+
+		return intel_cap.rdpmc_metrics_clear ? attr->mode : 0;
+	}
+
+	return 0;
+}
 
 static struct attribute *intel_arch_formats_attr[] = {
 	&format_attr_event.attr,
@@ -4734,7 +5139,7 @@ int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
 			goto err;
 	}
 
-	if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA | PMU_FL_BR_CNTR)) {
+	if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA | PMU_FL_DYN_CONSTRAINT)) {
 		size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint);
 
 		cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
@@ -4782,13 +5187,33 @@ static void flip_smm_bit(void *data)
 	}
 }
 
-static void intel_pmu_check_num_counters(int *num_counters,
-					 int *num_counters_fixed,
-					 u64 *intel_ctrl, u64 fixed_mask);
+static void intel_pmu_check_counters_mask(u64 *cntr_mask,
+					  u64 *fixed_cntr_mask,
+					  u64 *intel_ctrl)
+{
+	unsigned int bit;
+
+	bit = fls64(*cntr_mask);
+	if (bit > INTEL_PMC_MAX_GENERIC) {
+		WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
+		     bit, INTEL_PMC_MAX_GENERIC);
+		*cntr_mask &= GENMASK_ULL(INTEL_PMC_MAX_GENERIC - 1, 0);
+	}
+	*intel_ctrl = *cntr_mask;
+
+	bit = fls64(*fixed_cntr_mask);
+	if (bit > INTEL_PMC_MAX_FIXED) {
+		WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
+		     bit, INTEL_PMC_MAX_FIXED);
+		*fixed_cntr_mask &= GENMASK_ULL(INTEL_PMC_MAX_FIXED - 1, 0);
+	}
+
+	*intel_ctrl |= *fixed_cntr_mask << INTEL_PMC_IDX_FIXED;
+}
 
 static void intel_pmu_check_event_constraints(struct event_constraint *event_constraints,
-					      int num_counters,
-					      int num_counters_fixed,
+					      u64 cntr_mask,
+					      u64 fixed_cntr_mask,
 					      u64 intel_ctrl);
 
 static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs);
@@ -4796,14 +5221,14 @@ static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs);
 static inline bool intel_pmu_broken_perf_cap(void)
 {
 	/* The Perf Metric (Bit 15) is always cleared */
-	if ((boot_cpu_data.x86_model == INTEL_FAM6_METEORLAKE) ||
-	    (boot_cpu_data.x86_model == INTEL_FAM6_METEORLAKE_L))
+	if (boot_cpu_data.x86_vfm == INTEL_METEORLAKE ||
+	    boot_cpu_data.x86_vfm == INTEL_METEORLAKE_L)
 		return true;
 
 	return false;
 }
 
-static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
+static void update_pmu_cap(struct pmu *pmu)
 {
 	unsigned int cntr, fixed_cntr, ecx, edx;
 	union cpuid35_eax eax;
@@ -4811,27 +5236,42 @@ static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
 
 	cpuid(ARCH_PERFMON_EXT_LEAF, &eax.full, &ebx.full, &ecx, &edx);
 
+	if (ebx.split.umask2)
+		hybrid(pmu, config_mask) |= ARCH_PERFMON_EVENTSEL_UMASK2;
+	if (ebx.split.eq)
+		hybrid(pmu, config_mask) |= ARCH_PERFMON_EVENTSEL_EQ;
+
 	if (eax.split.cntr_subleaf) {
 		cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF,
 			    &cntr, &fixed_cntr, &ecx, &edx);
-		pmu->num_counters = fls(cntr);
-		pmu->num_counters_fixed = fls(fixed_cntr);
+		hybrid(pmu, cntr_mask64) = cntr;
+		hybrid(pmu, fixed_cntr_mask64) = fixed_cntr;
+	}
+
+	if (eax.split.acr_subleaf) {
+		cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_ACR_LEAF,
+			    &cntr, &fixed_cntr, &ecx, &edx);
+		/* The mask of the counters which can be reloaded */
+		hybrid(pmu, acr_cntr_mask64) = cntr | ((u64)fixed_cntr << INTEL_PMC_IDX_FIXED);
+
+		/* 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);
 	}
 
 	if (!intel_pmu_broken_perf_cap()) {
 		/* Perf Metric (Bit 15) and PEBS via PT (Bit 16) are hybrid enumeration */
-		rdmsrl(MSR_IA32_PERF_CAPABILITIES, pmu->intel_cap.capabilities);
+		rdmsrl(MSR_IA32_PERF_CAPABILITIES, hybrid(pmu, intel_cap).capabilities);
 	}
 }
 
 static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
 {
-	intel_pmu_check_num_counters(&pmu->num_counters, &pmu->num_counters_fixed,
-				     &pmu->intel_ctrl, (1ULL << pmu->num_counters_fixed) - 1);
-	pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
+	intel_pmu_check_counters_mask(&pmu->cntr_mask64, &pmu->fixed_cntr_mask64,
+				      &pmu->intel_ctrl);
+	pmu->pebs_events_mask = intel_pmu_pebs_mask(pmu->cntr_mask64);
 	pmu->unconstrained = (struct event_constraint)
-			     __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
-						0, pmu->num_counters, 0, 0);
+			     __EVENT_CONSTRAINT(0, pmu->cntr_mask64,
+						0, x86_pmu_num_counters(&pmu->pmu), 0, 0);
 
 	if (pmu->intel_cap.perf_metrics)
 		pmu->intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
@@ -4844,8 +5284,8 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
 		pmu->pmu.capabilities &= ~PERF_PMU_CAP_AUX_OUTPUT;
 
 	intel_pmu_check_event_constraints(pmu->event_constraints,
-					  pmu->num_counters,
-					  pmu->num_counters_fixed,
+					  pmu->cntr_mask64,
+					  pmu->fixed_cntr_mask64,
 					  pmu->intel_ctrl);
 
 	intel_pmu_check_extra_regs(pmu->extra_regs);
@@ -4902,11 +5342,11 @@ static bool init_hybrid_pmu(int cpu)
 		goto end;
 
 	if (this_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT))
-		update_pmu_cap(pmu);
+		update_pmu_cap(&pmu->pmu);
 
 	intel_pmu_check_hybrid_pmus(pmu);
 
-	if (!check_hw_exists(&pmu->pmu, pmu->num_counters, pmu->num_counters_fixed))
+	if (!check_hw_exists(&pmu->pmu, pmu->cntr_mask, pmu->fixed_cntr_mask))
 		return false;
 
 	pr_info("%s PMU driver: ", pmu->name);
@@ -4916,8 +5356,7 @@ static bool init_hybrid_pmu(int cpu)
 
 	pr_cont("\n");
 
-	x86_pmu_show_pmu_cap(pmu->num_counters, pmu->num_counters_fixed,
-			     pmu->intel_ctrl);
+	x86_pmu_show_pmu_cap(&pmu->pmu);
 
 end:
 	cpumask_set_cpu(cpu, &pmu->supported_cpus);
@@ -5161,6 +5600,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
 	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
+	.fixedctr		= MSR_ARCH_PERFMON_FIXED_CTR0,
 	.event_map		= intel_pmu_event_map,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
@@ -5214,6 +5654,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
 	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
+	.fixedctr		= MSR_ARCH_PERFMON_FIXED_CTR0,
 	.event_map		= intel_pmu_event_map,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
@@ -5821,6 +6262,21 @@ td_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 	return attr->mode;
 }
 
+PMU_FORMAT_ATTR(acr_mask,	"config2:0-63");
+
+static struct attribute *format_acr_attrs[] = {
+	&format_attr_acr_mask.attr,
+	NULL
+};
+
+static umode_t
+acr_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	struct device *dev = kobj_to_dev(kobj);
+
+	return intel_pmu_has_acr(dev_get_drvdata(dev)) ? attr->mode : 0;
+}
+
 static struct attribute_group group_events_td  = {
 	.name = "events",
 	.is_visible = td_is_visible,
@@ -5857,6 +6313,18 @@ static struct attribute_group group_format_extra_skl = {
 	.is_visible = exra_is_visible,
 };
 
+static struct attribute_group group_format_evtsel_ext = {
+	.name       = "format",
+	.attrs      = format_evtsel_ext_attrs,
+	.is_visible = evtsel_ext_is_visible,
+};
+
+static struct attribute_group group_format_acr = {
+	.name       = "format",
+	.attrs      = format_acr_attrs,
+	.is_visible = acr_is_visible,
+};
+
 static struct attribute_group group_default = {
 	.attrs      = intel_pmu_attrs,
 	.is_visible = default_is_visible,
@@ -5870,6 +6338,8 @@ static const struct attribute_group *attr_update[] = {
 	&group_caps_lbr,
 	&group_format_extra,
 	&group_format_extra_skl,
+	&group_format_evtsel_ext,
+	&group_format_acr,
 	&group_default,
 	NULL,
 };
@@ -5897,6 +6367,23 @@ static struct attribute *adl_hybrid_events_attrs[] = {
 	NULL,
 };
 
+EVENT_ATTR_STR_HYBRID(topdown-retiring,      td_retiring_lnl,  "event=0xc2,umask=0x02;event=0x00,umask=0x80", hybrid_big_small);
+EVENT_ATTR_STR_HYBRID(topdown-fe-bound,      td_fe_bound_lnl,  "event=0x9c,umask=0x01;event=0x00,umask=0x82", hybrid_big_small);
+EVENT_ATTR_STR_HYBRID(topdown-be-bound,      td_be_bound_lnl,  "event=0xa4,umask=0x02;event=0x00,umask=0x83", hybrid_big_small);
+
+static struct attribute *lnl_hybrid_events_attrs[] = {
+	EVENT_PTR(slots_adl),
+	EVENT_PTR(td_retiring_lnl),
+	EVENT_PTR(td_bad_spec_adl),
+	EVENT_PTR(td_fe_bound_lnl),
+	EVENT_PTR(td_be_bound_lnl),
+	EVENT_PTR(td_heavy_ops_adl),
+	EVENT_PTR(td_br_mis_adl),
+	EVENT_PTR(td_fetch_lat_adl),
+	EVENT_PTR(td_mem_bound_adl),
+	NULL
+};
+
 /* Must be in IDX order */
 EVENT_ATTR_STR_HYBRID(mem-loads,     mem_ld_adl,     "event=0xd0,umask=0x5,ldlat=3;event=0xcd,umask=0x1,ldlat=3", hybrid_big_small);
 EVENT_ATTR_STR_HYBRID(mem-stores,    mem_st_adl,     "event=0xd0,umask=0x6;event=0xcd,umask=0x2",                 hybrid_big_small);
@@ -6090,6 +6577,8 @@ static const struct attribute_group *hybrid_attr_update[] = {
 	&group_caps_gen,
 	&group_caps_lbr,
 	&hybrid_group_format_extra,
+	&group_format_evtsel_ext,
+	&group_format_acr,
 	&group_default,
 	&hybrid_group_cpus,
 	NULL,
@@ -6097,29 +6586,9 @@ static const struct attribute_group *hybrid_attr_update[] = {
 
 static struct attribute *empty_attrs;
 
-static void intel_pmu_check_num_counters(int *num_counters,
-					 int *num_counters_fixed,
-					 u64 *intel_ctrl, u64 fixed_mask)
-{
-	if (*num_counters > INTEL_PMC_MAX_GENERIC) {
-		WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
-		     *num_counters, INTEL_PMC_MAX_GENERIC);
-		*num_counters = INTEL_PMC_MAX_GENERIC;
-	}
-	*intel_ctrl = (1ULL << *num_counters) - 1;
-
-	if (*num_counters_fixed > INTEL_PMC_MAX_FIXED) {
-		WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
-		     *num_counters_fixed, INTEL_PMC_MAX_FIXED);
-		*num_counters_fixed = INTEL_PMC_MAX_FIXED;
-	}
-
-	*intel_ctrl |= fixed_mask << INTEL_PMC_IDX_FIXED;
-}
-
 static void intel_pmu_check_event_constraints(struct event_constraint *event_constraints,
-					      int num_counters,
-					      int num_counters_fixed,
+					      u64 cntr_mask,
+					      u64 fixed_cntr_mask,
 					      u64 intel_ctrl)
 {
 	struct event_constraint *c;
@@ -6156,10 +6625,9 @@ static void intel_pmu_check_event_constraints(struct event_constraint *event_con
 			 * generic counters
 			 */
 			if (!use_fixed_pseudo_encoding(c->code))
-				c->idxmsk64 |= (1ULL << num_counters) - 1;
+				c->idxmsk64 |= cntr_mask;
 		}
-		c->idxmsk64 &=
-			~(~0ULL << (INTEL_PMC_IDX_FIXED + num_counters_fixed));
+		c->idxmsk64 &= cntr_mask | (fixed_cntr_mask << INTEL_PMC_IDX_FIXED);
 		c->weight = hweight64(c->idxmsk64);
 	}
 }
@@ -6184,6 +6652,11 @@ static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs)
 	}
 }
 
+static inline int intel_pmu_v6_addr_offset(int index, bool eventsel)
+{
+	return MSR_IA32_PMC_V6_STEP * index;
+}
+
 static const struct { enum hybrid_pmu_type id; char *name; } intel_hybrid_pmu_type_map[] __initconst = {
 	{ hybrid_small, "cpu_atom" },
 	{ hybrid_big, "cpu_core" },
@@ -6210,12 +6683,13 @@ static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus)
 		pmu->pmu_type = intel_hybrid_pmu_type_map[bit].id;
 		pmu->name = intel_hybrid_pmu_type_map[bit].name;
 
-		pmu->num_counters = x86_pmu.num_counters;
-		pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
-		pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
+		pmu->cntr_mask64 = x86_pmu.cntr_mask64;
+		pmu->fixed_cntr_mask64 = x86_pmu.fixed_cntr_mask64;
+		pmu->pebs_events_mask = intel_pmu_pebs_mask(pmu->cntr_mask64);
+		pmu->config_mask = X86_RAW_EVENT_MASK;
 		pmu->unconstrained = (struct event_constraint)
-				     __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
-							0, pmu->num_counters, 0, 0);
+				     __EVENT_CONSTRAINT(0, pmu->cntr_mask64,
+							0, x86_pmu_num_counters(&pmu->pmu), 0, 0);
 
 		pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities;
 		if (pmu->pmu_type & hybrid_small) {
@@ -6275,6 +6749,22 @@ static __always_inline void intel_pmu_init_grt(struct pmu *pmu)
 	hybrid(pmu, extra_regs) = intel_grt_extra_regs;
 }
 
+static __always_inline void intel_pmu_init_lnc(struct pmu *pmu)
+{
+	intel_pmu_init_glc(pmu);
+	hybrid(pmu, event_constraints) = intel_lnc_event_constraints;
+	hybrid(pmu, pebs_constraints) = intel_lnc_pebs_event_constraints;
+	hybrid(pmu, extra_regs) = intel_rwc_extra_regs;
+}
+
+static __always_inline void intel_pmu_init_skt(struct pmu *pmu)
+{
+	intel_pmu_init_grt(pmu);
+	hybrid(pmu, event_constraints) = intel_skt_event_constraints;
+	hybrid(pmu, extra_regs) = intel_cmt_extra_regs;
+	static_call_update(intel_pmu_enable_acr_event, intel_pmu_enable_acr);
+}
+
 __init int intel_pmu_init(void)
 {
 	struct attribute **extra_skl_attr = &empty_attrs;
@@ -6318,15 +6808,16 @@ __init int intel_pmu_init(void)
 		x86_pmu = intel_pmu;
 
 	x86_pmu.version			= version;
-	x86_pmu.num_counters		= eax.split.num_counters;
+	x86_pmu.cntr_mask64		= GENMASK_ULL(eax.split.num_counters - 1, 0);
 	x86_pmu.cntval_bits		= eax.split.bit_width;
 	x86_pmu.cntval_mask		= (1ULL << eax.split.bit_width) - 1;
 
 	x86_pmu.events_maskl		= ebx.full;
 	x86_pmu.events_mask_len		= eax.split.mask_length;
 
-	x86_pmu.max_pebs_events		= min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters);
+	x86_pmu.pebs_events_mask	= intel_pmu_pebs_mask(x86_pmu.cntr_mask64);
 	x86_pmu.pebs_capable		= PEBS_COUNTER_MASK;
+	x86_pmu.config_mask		= X86_RAW_EVENT_MASK;
 
 	/*
 	 * Quirk: v2 perfmon does not report fixed-purpose events, so
@@ -6335,12 +6826,10 @@ __init int intel_pmu_init(void)
 	if (version > 1 && version < 5) {
 		int assume = 3 * !boot_cpu_has(X86_FEATURE_HYPERVISOR);
 
-		x86_pmu.num_counters_fixed =
-			max((int)edx.split.num_counters_fixed, assume);
-
-		fixed_mask = (1L << x86_pmu.num_counters_fixed) - 1;
+		x86_pmu.fixed_cntr_mask64 =
+			GENMASK_ULL(max((int)edx.split.num_counters_fixed, assume) - 1, 0);
 	} else if (version >= 5)
-		x86_pmu.num_counters_fixed = fls(fixed_mask);
+		x86_pmu.fixed_cntr_mask64 = fixed_mask;
 
 	if (boot_cpu_has(X86_FEATURE_PDCM)) {
 		u64 capabilities;
@@ -6367,22 +6856,28 @@ __init int intel_pmu_init(void)
 			pr_cont(" AnyThread deprecated, ");
 	}
 
+	/*
+	 * Many features on and after V6 require dynamic constraint,
+	 * e.g., Arch PEBS, ACR.
+	 */
+	if (version >= 6)
+		x86_pmu.flags |= PMU_FL_DYN_CONSTRAINT;
 	/*
 	 * Install the hw-cache-events table:
 	 */
-	switch (boot_cpu_data.x86_model) {
-	case INTEL_FAM6_CORE_YONAH:
+	switch (boot_cpu_data.x86_vfm) {
+	case INTEL_CORE_YONAH:
 		pr_cont("Core events, ");
 		name = "core";
 		break;
 
-	case INTEL_FAM6_CORE2_MEROM:
+	case INTEL_CORE2_MEROM:
 		x86_add_quirk(intel_clovertown_quirk);
 		fallthrough;
 
-	case INTEL_FAM6_CORE2_MEROM_L:
-	case INTEL_FAM6_CORE2_PENRYN:
-	case INTEL_FAM6_CORE2_DUNNINGTON:
+	case INTEL_CORE2_MEROM_L:
+	case INTEL_CORE2_PENRYN:
+	case INTEL_CORE2_DUNNINGTON:
 		memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -6394,9 +6889,9 @@ __init int intel_pmu_init(void)
 		name = "core2";
 		break;
 
-	case INTEL_FAM6_NEHALEM:
-	case INTEL_FAM6_NEHALEM_EP:
-	case INTEL_FAM6_NEHALEM_EX:
+	case INTEL_NEHALEM:
+	case INTEL_NEHALEM_EP:
+	case INTEL_NEHALEM_EX:
 		memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
@@ -6428,11 +6923,11 @@ __init int intel_pmu_init(void)
 		name = "nehalem";
 		break;
 
-	case INTEL_FAM6_ATOM_BONNELL:
-	case INTEL_FAM6_ATOM_BONNELL_MID:
-	case INTEL_FAM6_ATOM_SALTWELL:
-	case INTEL_FAM6_ATOM_SALTWELL_MID:
-	case INTEL_FAM6_ATOM_SALTWELL_TABLET:
+	case INTEL_ATOM_BONNELL:
+	case INTEL_ATOM_BONNELL_MID:
+	case INTEL_ATOM_SALTWELL:
+	case INTEL_ATOM_SALTWELL_MID:
+	case INTEL_ATOM_SALTWELL_TABLET:
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -6445,11 +6940,11 @@ __init int intel_pmu_init(void)
 		name = "bonnell";
 		break;
 
-	case INTEL_FAM6_ATOM_SILVERMONT:
-	case INTEL_FAM6_ATOM_SILVERMONT_D:
-	case INTEL_FAM6_ATOM_SILVERMONT_MID:
-	case INTEL_FAM6_ATOM_AIRMONT:
-	case INTEL_FAM6_ATOM_AIRMONT_MID:
+	case INTEL_ATOM_SILVERMONT:
+	case INTEL_ATOM_SILVERMONT_D:
+	case INTEL_ATOM_SILVERMONT_MID:
+	case INTEL_ATOM_AIRMONT:
+	case INTEL_ATOM_AIRMONT_MID:
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
@@ -6467,8 +6962,8 @@ __init int intel_pmu_init(void)
 		name = "silvermont";
 		break;
 
-	case INTEL_FAM6_ATOM_GOLDMONT:
-	case INTEL_FAM6_ATOM_GOLDMONT_D:
+	case INTEL_ATOM_GOLDMONT:
+	case INTEL_ATOM_GOLDMONT_D:
 		memcpy(hw_cache_event_ids, glm_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs,
@@ -6494,7 +6989,7 @@ __init int intel_pmu_init(void)
 		name = "goldmont";
 		break;
 
-	case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
+	case INTEL_ATOM_GOLDMONT_PLUS:
 		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs,
@@ -6523,9 +7018,9 @@ __init int intel_pmu_init(void)
 		name = "goldmont_plus";
 		break;
 
-	case INTEL_FAM6_ATOM_TREMONT_D:
-	case INTEL_FAM6_ATOM_TREMONT:
-	case INTEL_FAM6_ATOM_TREMONT_L:
+	case INTEL_ATOM_TREMONT_D:
+	case INTEL_ATOM_TREMONT:
+	case INTEL_ATOM_TREMONT_L:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
@@ -6552,10 +7047,10 @@ __init int intel_pmu_init(void)
 		name = "Tremont";
 		break;
 
-	case INTEL_FAM6_ATOM_GRACEMONT:
+	case INTEL_ATOM_GRACEMONT:
 		intel_pmu_init_grt(NULL);
 		intel_pmu_pebs_data_source_grt();
-		x86_pmu.pebs_latency_data = adl_latency_data_small;
+		x86_pmu.pebs_latency_data = grt_latency_data;
 		x86_pmu.get_event_constraints = tnt_get_event_constraints;
 		td_attr = tnt_events_attrs;
 		mem_attr = grt_mem_attrs;
@@ -6564,12 +7059,12 @@ __init int intel_pmu_init(void)
 		name = "gracemont";
 		break;
 
-	case INTEL_FAM6_ATOM_CRESTMONT:
-	case INTEL_FAM6_ATOM_CRESTMONT_X:
+	case INTEL_ATOM_CRESTMONT:
+	case INTEL_ATOM_CRESTMONT_X:
 		intel_pmu_init_grt(NULL);
 		x86_pmu.extra_regs = intel_cmt_extra_regs;
 		intel_pmu_pebs_data_source_cmt();
-		x86_pmu.pebs_latency_data = mtl_latency_data_small;
+		x86_pmu.pebs_latency_data = cmt_latency_data;
 		x86_pmu.get_event_constraints = cmt_get_event_constraints;
 		td_attr = cmt_events_attrs;
 		mem_attr = grt_mem_attrs;
@@ -6578,9 +7073,21 @@ __init int intel_pmu_init(void)
 		name = "crestmont";
 		break;
 
-	case INTEL_FAM6_WESTMERE:
-	case INTEL_FAM6_WESTMERE_EP:
-	case INTEL_FAM6_WESTMERE_EX:
+	case INTEL_ATOM_DARKMONT_X:
+		intel_pmu_init_skt(NULL);
+		intel_pmu_pebs_data_source_cmt();
+		x86_pmu.pebs_latency_data = cmt_latency_data;
+		x86_pmu.get_event_constraints = cmt_get_event_constraints;
+		td_attr = skt_events_attrs;
+		mem_attr = grt_mem_attrs;
+		extra_attr = cmt_format_attr;
+		pr_cont("Darkmont events, ");
+		name = "darkmont";
+		break;
+
+	case INTEL_WESTMERE:
+	case INTEL_WESTMERE_EP:
+	case INTEL_WESTMERE_EX:
 		memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
@@ -6609,8 +7116,8 @@ __init int intel_pmu_init(void)
 		name = "westmere";
 		break;
 
-	case INTEL_FAM6_SANDYBRIDGE:
-	case INTEL_FAM6_SANDYBRIDGE_X:
+	case INTEL_SANDYBRIDGE:
+	case INTEL_SANDYBRIDGE_X:
 		x86_add_quirk(intel_sandybridge_quirk);
 		x86_add_quirk(intel_ht_bug);
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
@@ -6623,7 +7130,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
-		if (boot_cpu_data.x86_model == INTEL_FAM6_SANDYBRIDGE_X)
+		if (boot_cpu_data.x86_vfm == INTEL_SANDYBRIDGE_X)
 			x86_pmu.extra_regs = intel_snbep_extra_regs;
 		else
 			x86_pmu.extra_regs = intel_snb_extra_regs;
@@ -6649,8 +7156,8 @@ __init int intel_pmu_init(void)
 		name = "sandybridge";
 		break;
 
-	case INTEL_FAM6_IVYBRIDGE:
-	case INTEL_FAM6_IVYBRIDGE_X:
+	case INTEL_IVYBRIDGE:
+	case INTEL_IVYBRIDGE_X:
 		x86_add_quirk(intel_ht_bug);
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
@@ -6666,7 +7173,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_ivb;
 		x86_pmu.pebs_prec_dist = true;
-		if (boot_cpu_data.x86_model == INTEL_FAM6_IVYBRIDGE_X)
+		if (boot_cpu_data.x86_vfm == INTEL_IVYBRIDGE_X)
 			x86_pmu.extra_regs = intel_snbep_extra_regs;
 		else
 			x86_pmu.extra_regs = intel_snb_extra_regs;
@@ -6688,10 +7195,10 @@ __init int intel_pmu_init(void)
 		break;
 
 
-	case INTEL_FAM6_HASWELL:
-	case INTEL_FAM6_HASWELL_X:
-	case INTEL_FAM6_HASWELL_L:
-	case INTEL_FAM6_HASWELL_G:
+	case INTEL_HASWELL:
+	case INTEL_HASWELL_X:
+	case INTEL_HASWELL_L:
+	case INTEL_HASWELL_G:
 		x86_add_quirk(intel_ht_bug);
 		x86_add_quirk(intel_pebs_isolation_quirk);
 		x86_pmu.late_ack = true;
@@ -6722,10 +7229,10 @@ __init int intel_pmu_init(void)
 		name = "haswell";
 		break;
 
-	case INTEL_FAM6_BROADWELL:
-	case INTEL_FAM6_BROADWELL_D:
-	case INTEL_FAM6_BROADWELL_G:
-	case INTEL_FAM6_BROADWELL_X:
+	case INTEL_BROADWELL:
+	case INTEL_BROADWELL_D:
+	case INTEL_BROADWELL_G:
+	case INTEL_BROADWELL_X:
 		x86_add_quirk(intel_pebs_isolation_quirk);
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
@@ -6764,8 +7271,8 @@ __init int intel_pmu_init(void)
 		name = "broadwell";
 		break;
 
-	case INTEL_FAM6_XEON_PHI_KNL:
-	case INTEL_FAM6_XEON_PHI_KNM:
+	case INTEL_XEON_PHI_KNL:
+	case INTEL_XEON_PHI_KNM:
 		memcpy(hw_cache_event_ids,
 		       slm_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs,
@@ -6784,15 +7291,15 @@ __init int intel_pmu_init(void)
 		name = "knights-landing";
 		break;
 
-	case INTEL_FAM6_SKYLAKE_X:
+	case INTEL_SKYLAKE_X:
 		pmem = true;
 		fallthrough;
-	case INTEL_FAM6_SKYLAKE_L:
-	case INTEL_FAM6_SKYLAKE:
-	case INTEL_FAM6_KABYLAKE_L:
-	case INTEL_FAM6_KABYLAKE:
-	case INTEL_FAM6_COMETLAKE_L:
-	case INTEL_FAM6_COMETLAKE:
+	case INTEL_SKYLAKE_L:
+	case INTEL_SKYLAKE:
+	case INTEL_KABYLAKE_L:
+	case INTEL_KABYLAKE:
+	case INTEL_COMETLAKE_L:
+	case INTEL_COMETLAKE:
 		x86_add_quirk(intel_pebs_isolation_quirk);
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
@@ -6841,16 +7348,16 @@ __init int intel_pmu_init(void)
 		name = "skylake";
 		break;
 
-	case INTEL_FAM6_ICELAKE_X:
-	case INTEL_FAM6_ICELAKE_D:
+	case INTEL_ICELAKE_X:
+	case INTEL_ICELAKE_D:
 		x86_pmu.pebs_ept = 1;
 		pmem = true;
 		fallthrough;
-	case INTEL_FAM6_ICELAKE_L:
-	case INTEL_FAM6_ICELAKE:
-	case INTEL_FAM6_TIGERLAKE_L:
-	case INTEL_FAM6_TIGERLAKE:
-	case INTEL_FAM6_ROCKETLAKE:
+	case INTEL_ICELAKE_L:
+	case INTEL_ICELAKE:
+	case INTEL_TIGERLAKE_L:
+	case INTEL_TIGERLAKE:
+	case INTEL_ROCKETLAKE:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -6885,16 +7392,16 @@ __init int intel_pmu_init(void)
 		name = "icelake";
 		break;
 
-	case INTEL_FAM6_SAPPHIRERAPIDS_X:
-	case INTEL_FAM6_EMERALDRAPIDS_X:
+	case INTEL_SAPPHIRERAPIDS_X:
+	case INTEL_EMERALDRAPIDS_X:
 		x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
 		x86_pmu.extra_regs = intel_glc_extra_regs;
 		pr_cont("Sapphire Rapids events, ");
 		name = "sapphire_rapids";
 		goto glc_common;
 
-	case INTEL_FAM6_GRANITERAPIDS_X:
-	case INTEL_FAM6_GRANITERAPIDS_D:
+	case INTEL_GRANITERAPIDS_X:
+	case INTEL_GRANITERAPIDS_D:
 		x86_pmu.extra_regs = intel_rwc_extra_regs;
 		pr_cont("Granite Rapids events, ");
 		name = "granite_rapids";
@@ -6913,11 +7420,11 @@ __init int intel_pmu_init(void)
 		intel_pmu_pebs_data_source_skl(true);
 		break;
 
-	case INTEL_FAM6_ALDERLAKE:
-	case INTEL_FAM6_ALDERLAKE_L:
-	case INTEL_FAM6_RAPTORLAKE:
-	case INTEL_FAM6_RAPTORLAKE_P:
-	case INTEL_FAM6_RAPTORLAKE_S:
+	case INTEL_ALDERLAKE:
+	case INTEL_ALDERLAKE_L:
+	case INTEL_RAPTORLAKE:
+	case INTEL_RAPTORLAKE_P:
+	case INTEL_RAPTORLAKE_S:
 		/*
 		 * Alder Lake has 2 types of CPU, core and atom.
 		 *
@@ -6925,7 +7432,7 @@ __init int intel_pmu_init(void)
 		 */
 		intel_pmu_init_hybrid(hybrid_big_small);
 
-		x86_pmu.pebs_latency_data = adl_latency_data_small;
+		x86_pmu.pebs_latency_data = grt_latency_data;
 		x86_pmu.get_event_constraints = adl_get_event_constraints;
 		x86_pmu.hw_config = adl_hw_config;
 		x86_pmu.get_hybrid_cpu_type = adl_get_hybrid_cpu_type;
@@ -6940,11 +7447,13 @@ __init int intel_pmu_init(void)
 		pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
 		intel_pmu_init_glc(&pmu->pmu);
 		if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) {
-			pmu->num_counters = x86_pmu.num_counters + 2;
-			pmu->num_counters_fixed = x86_pmu.num_counters_fixed + 1;
+			pmu->cntr_mask64 <<= 2;
+			pmu->cntr_mask64 |= 0x3;
+			pmu->fixed_cntr_mask64 <<= 1;
+			pmu->fixed_cntr_mask64 |= 0x1;
 		} else {
-			pmu->num_counters = x86_pmu.num_counters;
-			pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
+			pmu->cntr_mask64 = x86_pmu.cntr_mask64;
+			pmu->fixed_cntr_mask64 = x86_pmu.fixed_cntr_mask64;
 		}
 
 		/*
@@ -6954,15 +7463,16 @@ __init int intel_pmu_init(void)
 		 * mistakenly add extra counters for P-cores. Correct the number of
 		 * counters here.
 		 */
-		if ((pmu->num_counters > 8) || (pmu->num_counters_fixed > 4)) {
-			pmu->num_counters = x86_pmu.num_counters;
-			pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
+		if ((x86_pmu_num_counters(&pmu->pmu) > 8) || (x86_pmu_num_counters_fixed(&pmu->pmu) > 4)) {
+			pmu->cntr_mask64 = x86_pmu.cntr_mask64;
+			pmu->fixed_cntr_mask64 = x86_pmu.fixed_cntr_mask64;
 		}
 
-		pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
+		pmu->pebs_events_mask = intel_pmu_pebs_mask(pmu->cntr_mask64);
 		pmu->unconstrained = (struct event_constraint)
-					__EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
-							   0, pmu->num_counters, 0, 0);
+				     __EVENT_CONSTRAINT(0, pmu->cntr_mask64,
+				     0, x86_pmu_num_counters(&pmu->pmu), 0, 0);
+
 		pmu->extra_regs = intel_glc_extra_regs;
 
 		/* Initialize Atom core specific PerfMon capabilities.*/
@@ -6975,11 +7485,11 @@ __init int intel_pmu_init(void)
 		name = "alderlake_hybrid";
 		break;
 
-	case INTEL_FAM6_METEORLAKE:
-	case INTEL_FAM6_METEORLAKE_L:
+	case INTEL_METEORLAKE:
+	case INTEL_METEORLAKE_L:
 		intel_pmu_init_hybrid(hybrid_big_small);
 
-		x86_pmu.pebs_latency_data = mtl_latency_data_small;
+		x86_pmu.pebs_latency_data = cmt_latency_data;
 		x86_pmu.get_event_constraints = mtl_get_event_constraints;
 		x86_pmu.hw_config = adl_hw_config;
 
@@ -7004,6 +7514,33 @@ __init int intel_pmu_init(void)
 		name = "meteorlake_hybrid";
 		break;
 
+	case INTEL_LUNARLAKE_M:
+	case INTEL_ARROWLAKE:
+		intel_pmu_init_hybrid(hybrid_big_small);
+
+		x86_pmu.pebs_latency_data = lnl_latency_data;
+		x86_pmu.get_event_constraints = mtl_get_event_constraints;
+		x86_pmu.hw_config = adl_hw_config;
+
+		td_attr = lnl_hybrid_events_attrs;
+		mem_attr = mtl_hybrid_mem_attrs;
+		tsx_attr = adl_hybrid_tsx_attrs;
+		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+			mtl_hybrid_extra_attr_rtm : mtl_hybrid_extra_attr;
+
+		/* Initialize big core specific PerfMon capabilities.*/
+		pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
+		intel_pmu_init_lnc(&pmu->pmu);
+
+		/* Initialize Atom core specific PerfMon capabilities.*/
+		pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX];
+		intel_pmu_init_skt(&pmu->pmu);
+
+		intel_pmu_pebs_data_source_lnl();
+		pr_cont("Lunarlake Hybrid events, ");
+		name = "lunarlake_hybrid";
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:
@@ -7029,9 +7566,9 @@ __init int intel_pmu_init(void)
 			 * The constraints may be cut according to the CPUID enumeration
 			 * by inserting the EVENT_CONSTRAINT_END.
 			 */
-			if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED)
-				x86_pmu.num_counters_fixed = INTEL_PMC_MAX_FIXED;
-			intel_v5_gen_event_constraints[x86_pmu.num_counters_fixed].weight = -1;
+			if (fls64(x86_pmu.fixed_cntr_mask64) > INTEL_PMC_MAX_FIXED)
+				x86_pmu.fixed_cntr_mask64 &= GENMASK_ULL(INTEL_PMC_MAX_FIXED - 1, 0);
+			intel_v5_gen_event_constraints[fls64(x86_pmu.fixed_cntr_mask64)].weight = -1;
 			x86_pmu.event_constraints = intel_v5_gen_event_constraints;
 			pr_cont("generic architected perfmon, ");
 			name = "generic_arch_v5+";
@@ -7058,18 +7595,29 @@ __init int intel_pmu_init(void)
 		x86_pmu.attr_update = hybrid_attr_update;
 	}
 
-	intel_pmu_check_num_counters(&x86_pmu.num_counters,
-				     &x86_pmu.num_counters_fixed,
-				     &x86_pmu.intel_ctrl,
-				     (u64)fixed_mask);
+	/*
+	 * The archPerfmonExt (0x23) includes an enhanced enumeration of
+	 * PMU architectural features with a per-core view. For non-hybrid,
+	 * each core has the same PMU capabilities. It's good enough to
+	 * update the x86_pmu from the booting CPU. For hybrid, the x86_pmu
+	 * is used to keep the common capabilities. Still keep the values
+	 * from the leaf 0xa. The core specific update will be done later
+	 * when a new type is online.
+	 */
+	if (!is_hybrid() && boot_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT))
+		update_pmu_cap(NULL);
+
+	intel_pmu_check_counters_mask(&x86_pmu.cntr_mask64,
+				      &x86_pmu.fixed_cntr_mask64,
+				      &x86_pmu.intel_ctrl);
 
 	/* AnyThread may be deprecated on arch perfmon v5 or later */
 	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.num_counters,
-					  x86_pmu.num_counters_fixed,
+					  x86_pmu.cntr_mask64,
+					  x86_pmu.fixed_cntr_mask64,
 					  x86_pmu.intel_ctrl);
 	/*
 	 * Access LBR MSR may cause #GP under certain circumstances.
@@ -7110,6 +7658,14 @@ __init int intel_pmu_init(void)
 		pr_cont("full-width counters, ");
 	}
 
+	/* Support V6+ MSR Aliasing */
+	if (x86_pmu.version >= 6) {
+		x86_pmu.perfctr = MSR_IA32_PMC_V6_GP0_CTR;
+		x86_pmu.eventsel = MSR_IA32_PMC_V6_GP0_CFG_A;
+		x86_pmu.fixedctr = MSR_IA32_PMC_V6_FX0_CTR;
+		x86_pmu.addr_offset = intel_pmu_v6_addr_offset;
+	}
+
 	if (!is_hybrid() && x86_pmu.intel_cap.perf_metrics)
 		x86_pmu.intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
 
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 33a0cba6f241fb75bb21613856abd07c57a50dfd..cd8634165bdee8286b93dea1247a31a01db8e907 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -62,6 +62,15 @@ union intel_x86_pebs_dse {
 		unsigned int mtl_fwd_blk:1;
 		unsigned int ld_reserved4:24;
 	};
+	struct {
+		unsigned int lnc_dse:8;
+		unsigned int ld_reserved5:2;
+		unsigned int lnc_stlb_miss:1;
+		unsigned int lnc_locked:1;
+		unsigned int lnc_data_blk:1;
+		unsigned int lnc_addr_blk:1;
+		unsigned int ld_reserved6:18;
+	};
 };
 
 
@@ -76,7 +85,7 @@ union intel_x86_pebs_dse {
 #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
 
 /* Version for Sandy Bridge and later */
-static u64 pebs_data_source[] = {
+static u64 pebs_data_source[PERF_PEBS_DATA_SOURCE_MAX] = {
 	P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
 	OP_LH | P(LVL, L1)  | LEVEL(L1) | P(SNOOP, NONE),  /* 0x01: L1 local */
 	OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */
@@ -172,6 +181,40 @@ void __init intel_pmu_pebs_data_source_cmt(void)
 	__intel_pmu_pebs_data_source_cmt(pebs_data_source);
 }
 
+/* Version for Lion Cove and later */
+static u64 lnc_pebs_data_source[PERF_PEBS_DATA_SOURCE_MAX] = {
+	P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),	/* 0x00: ukn L3 */
+	OP_LH | P(LVL, L1)  | LEVEL(L1) | P(SNOOP, NONE),	/* 0x01: L1 hit */
+	OP_LH | P(LVL, L1)  | LEVEL(L1) | P(SNOOP, NONE),	/* 0x02: L1 hit */
+	OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE),	/* 0x03: LFB/L1 Miss Handling Buffer hit */
+	0,							/* 0x04: Reserved */
+	OP_LH | P(LVL, L2)  | LEVEL(L2) | P(SNOOP, NONE),	/* 0x05: L2 Hit */
+	OP_LH | LEVEL(L2_MHB) | P(SNOOP, NONE),			/* 0x06: L2 Miss Handling Buffer Hit */
+	0,							/* 0x07: Reserved */
+	OP_LH | P(LVL, L3)  | LEVEL(L3) | P(SNOOP, NONE),	/* 0x08: L3 Hit */
+	0,							/* 0x09: Reserved */
+	0,							/* 0x0a: Reserved */
+	0,							/* 0x0b: Reserved */
+	OP_LH | P(LVL, L3)  | LEVEL(L3) | P(SNOOPX, FWD),	/* 0x0c: L3 Hit Snoop Fwd */
+	OP_LH | P(LVL, L3)  | LEVEL(L3) | P(SNOOP, HITM),	/* 0x0d: L3 Hit Snoop HitM */
+	0,							/* 0x0e: Reserved */
+	P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3)  | LEVEL(L3) | P(SNOOP, HITM),	/* 0x0f: L3 Miss Snoop HitM */
+	OP_LH | LEVEL(MSC) | P(SNOOP, NONE),			/* 0x10: Memory-side Cache Hit */
+	OP_LH | P(LVL, LOC_RAM)  | LEVEL(RAM) | P(SNOOP, NONE), /* 0x11: Local Memory Hit */
+};
+
+void __init intel_pmu_pebs_data_source_lnl(void)
+{
+	u64 *data_source;
+
+	data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].pebs_data_source;
+	memcpy(data_source, lnc_pebs_data_source, sizeof(lnc_pebs_data_source));
+
+	data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source;
+	memcpy(data_source, pebs_data_source, sizeof(pebs_data_source));
+	__intel_pmu_pebs_data_source_cmt(data_source);
+}
+
 static u64 precise_store_data(u64 status)
 {
 	union intel_x86_pebs_dse dse;
@@ -256,14 +299,14 @@ static inline void pebs_set_tlb_lock(u64 *val, bool tlb, bool lock)
 }
 
 /* Retrieve the latency data for e-core of ADL */
-static u64 __adl_latency_data_small(struct perf_event *event, u64 status,
-				     u8 dse, bool tlb, bool lock, bool blk)
+static u64 __grt_latency_data(struct perf_event *event, u64 status,
+			       u8 dse, bool tlb, bool lock, bool blk)
 {
 	u64 val;
 
 	WARN_ON_ONCE(hybrid_pmu(event->pmu)->pmu_type == hybrid_big);
 
-	dse &= PERF_PEBS_DATA_SOURCE_MASK;
+	dse &= PERF_PEBS_DATA_SOURCE_GRT_MASK;
 	val = hybrid_var(event->pmu, pebs_data_source)[dse];
 
 	pebs_set_tlb_lock(&val, tlb, lock);
@@ -276,27 +319,72 @@ static u64 __adl_latency_data_small(struct perf_event *event, u64 status,
 	return val;
 }
 
-u64 adl_latency_data_small(struct perf_event *event, u64 status)
+u64 grt_latency_data(struct perf_event *event, u64 status)
 {
 	union intel_x86_pebs_dse dse;
 
 	dse.val = status;
 
-	return __adl_latency_data_small(event, status, dse.ld_dse,
-					dse.ld_locked, dse.ld_stlb_miss,
-					dse.ld_data_blk);
+	return __grt_latency_data(event, status, dse.ld_dse,
+				  dse.ld_locked, dse.ld_stlb_miss,
+				  dse.ld_data_blk);
 }
 
 /* Retrieve the latency data for e-core of MTL */
-u64 mtl_latency_data_small(struct perf_event *event, u64 status)
+u64 cmt_latency_data(struct perf_event *event, u64 status)
 {
 	union intel_x86_pebs_dse dse;
 
 	dse.val = status;
 
-	return __adl_latency_data_small(event, status, dse.mtl_dse,
-					dse.mtl_stlb_miss, dse.mtl_locked,
-					dse.mtl_fwd_blk);
+	return __grt_latency_data(event, status, dse.mtl_dse,
+				  dse.mtl_stlb_miss, dse.mtl_locked,
+				  dse.mtl_fwd_blk);
+}
+
+static u64 lnc_latency_data(struct perf_event *event, u64 status)
+{
+	union intel_x86_pebs_dse dse;
+	union perf_mem_data_src src;
+	u64 val;
+
+	dse.val = status;
+
+	/* LNC core latency data */
+	val = hybrid_var(event->pmu, pebs_data_source)[status & PERF_PEBS_DATA_SOURCE_MASK];
+	if (!val)
+		val = P(OP, LOAD) | LEVEL(NA) | P(SNOOP, NA);
+
+	if (dse.lnc_stlb_miss)
+		val |= P(TLB, MISS) | P(TLB, L2);
+	else
+		val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
+
+	if (dse.lnc_locked)
+		val |= P(LOCK, LOCKED);
+
+	if (dse.lnc_data_blk)
+		val |= P(BLK, DATA);
+	if (dse.lnc_addr_blk)
+		val |= P(BLK, ADDR);
+	if (!dse.lnc_data_blk && !dse.lnc_addr_blk)
+		val |= P(BLK, NA);
+
+	src.val = val;
+	if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW)
+		src.mem_op = P(OP, STORE);
+
+	return src.val;
+}
+
+u64 lnl_latency_data(struct perf_event *event, u64 status)
+{
+	struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
+
+	if (pmu->pmu_type == hybrid_small)
+		return cmt_latency_data(event, status);
+
+	return lnc_latency_data(event, status);
 }
 
 static u64 load_latency_data(struct perf_event *event, u64 status)
@@ -1085,6 +1173,32 @@ struct event_constraint intel_glc_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_lnc_pebs_event_constraints[] = {
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL),	/* INST_RETIRED.PREC_DIST */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),
+
+	INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3ff),
+	INTEL_HYBRID_STLAT_CONSTRAINT(0x2cd, 0x3),
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_STORES */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf),	/* MEM_INST_RETIRED.LOCK_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf),	/* MEM_INST_RETIRED.SPLIT_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf),	/* MEM_INST_RETIRED.SPLIT_STORES */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf),	/* MEM_INST_RETIRED.ALL_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf),	/* MEM_INST_RETIRED.ALL_STORES */
+
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf),
+
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf),
+
+	/*
+	 * Everything else is handled by PMU_FL_PEBS_ALL, because we
+	 * need the full constraints from the main table.
+	 */
+
+	EVENT_CONSTRAINT_END
+};
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 {
 	struct event_constraint *pebs_constraints = hybrid(event->pmu, pebs_constraints);
@@ -1136,8 +1250,7 @@ void intel_pmu_pebs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sche
 static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 {
 	struct debug_store *ds = cpuc->ds;
-	int max_pebs_events = hybrid(cpuc->pmu, max_pebs_events);
-	int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
+	int max_pebs_events = intel_pmu_max_num_pebs(cpuc->pmu);
 	u64 threshold;
 	int reserved;
 
@@ -1145,7 +1258,7 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 		return;
 
 	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
-		reserved = max_pebs_events + num_counters_fixed;
+		reserved = max_pebs_events + x86_pmu_max_num_counters_fixed(cpuc->pmu);
 	else
 		reserved = max_pebs_events;
 
@@ -1159,6 +1272,19 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 	ds->pebs_interrupt_threshold = threshold;
 }
 
+#define PEBS_DATACFG_CNTRS(x)						\
+	((x >> PEBS_DATACFG_CNTR_SHIFT) & PEBS_DATACFG_CNTR_MASK)
+
+#define PEBS_DATACFG_CNTR_BIT(x)					\
+	(((1ULL << x) & PEBS_DATACFG_CNTR_MASK) << PEBS_DATACFG_CNTR_SHIFT)
+
+#define PEBS_DATACFG_FIX(x)						\
+	((x >> PEBS_DATACFG_FIX_SHIFT) & PEBS_DATACFG_FIX_MASK)
+
+#define PEBS_DATACFG_FIX_BIT(x)						\
+	(((1ULL << (x)) & PEBS_DATACFG_FIX_MASK)			\
+	 << PEBS_DATACFG_FIX_SHIFT)
+
 static void adaptive_pebs_record_size_update(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1173,10 +1299,57 @@ static void adaptive_pebs_record_size_update(void)
 		sz += sizeof(struct pebs_xmm);
 	if (pebs_data_cfg & PEBS_DATACFG_LBRS)
 		sz += x86_pmu.lbr_nr * sizeof(struct lbr_entry);
+	if (pebs_data_cfg & (PEBS_DATACFG_METRICS | PEBS_DATACFG_CNTR)) {
+		sz += sizeof(struct pebs_cntr_header);
+
+		/* Metrics base and Metrics Data */
+		if (pebs_data_cfg & PEBS_DATACFG_METRICS)
+			sz += 2 * sizeof(u64);
+
+		if (pebs_data_cfg & PEBS_DATACFG_CNTR) {
+			sz += (hweight64(PEBS_DATACFG_CNTRS(pebs_data_cfg)) +
+			       hweight64(PEBS_DATACFG_FIX(pebs_data_cfg))) *
+			      sizeof(u64);
+		}
+	}
 
 	cpuc->pebs_record_size = sz;
 }
 
+static void __intel_pmu_pebs_update_cfg(struct perf_event *event,
+					int idx, u64 *pebs_data_cfg)
+{
+	if (is_metric_event(event)) {
+		*pebs_data_cfg |= PEBS_DATACFG_METRICS;
+		return;
+	}
+
+	*pebs_data_cfg |= PEBS_DATACFG_CNTR;
+
+	if (idx >= INTEL_PMC_IDX_FIXED)
+		*pebs_data_cfg |= PEBS_DATACFG_FIX_BIT(idx - INTEL_PMC_IDX_FIXED);
+	else
+		*pebs_data_cfg |= PEBS_DATACFG_CNTR_BIT(idx);
+}
+
+
+void intel_pmu_pebs_late_setup(struct cpu_hw_events *cpuc)
+{
+	struct perf_event *event;
+	u64 pebs_data_cfg = 0;
+	int i;
+
+	for (i = 0; i < cpuc->n_events; i++) {
+		event = cpuc->event_list[i];
+		if (!is_pebs_counter_event_group(event))
+			continue;
+		__intel_pmu_pebs_update_cfg(event, cpuc->assign[i], &pebs_data_cfg);
+	}
+
+	if (pebs_data_cfg & ~cpuc->pebs_data_cfg)
+		cpuc->pebs_data_cfg |= pebs_data_cfg | PEBS_UPDATE_DS_SW;
+}
+
 #define PERF_PEBS_MEMINFO_TYPE	(PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC |   \
 				PERF_SAMPLE_PHYS_ADDR |			     \
 				PERF_SAMPLE_WEIGHT_TYPE |		     \
@@ -1783,14 +1956,89 @@ static void adaptive_pebs_save_regs(struct pt_regs *regs,
 #endif
 }
 
+static void intel_perf_event_update_pmc(struct perf_event *event, u64 pmc)
+{
+	int shift = 64 - x86_pmu.cntval_bits;
+	struct hw_perf_event *hwc;
+	u64 delta, prev_pmc;
+
+	/*
+	 * A recorded counter may not have an assigned event in the
+	 * following cases. The value should be dropped.
+	 * - An event is deleted. There is still an active PEBS event.
+	 *   The PEBS record doesn't shrink on pmu::del().
+	 *   If the counter of the deleted event once occurred in a PEBS
+	 *   record, PEBS still records the counter until the counter is
+	 *   reassigned.
+	 * - An event is stopped for some reason, e.g., throttled.
+	 *   During this period, another event is added and takes the
+	 *   counter of the stopped event. The stopped event is assigned
+	 *   to another new and uninitialized counter, since the
+	 *   x86_pmu_start(RELOAD) is not invoked for a stopped event.
+	 *   The PEBS__DATA_CFG is updated regardless of the event state.
+	 *   The uninitialized counter can be recorded in a PEBS record.
+	 *   But the cpuc->events[uninitialized_counter] is always NULL,
+	 *   because the event is stopped. The uninitialized value is
+	 *   safely dropped.
+	 */
+	if (!event)
+		return;
+
+	hwc = &event->hw;
+	prev_pmc = local64_read(&hwc->prev_count);
+
+	/* Only update the count when the PMU is disabled */
+	WARN_ON(this_cpu_read(cpu_hw_events.enabled));
+	local64_set(&hwc->prev_count, pmc);
+
+	delta = (pmc << shift) - (prev_pmc << shift);
+	delta >>= shift;
+
+	local64_add(delta, &event->count);
+	local64_sub(delta, &hwc->period_left);
+}
+
+static inline void __setup_pebs_counter_group(struct cpu_hw_events *cpuc,
+					      struct perf_event *event,
+					      struct pebs_cntr_header *cntr,
+					      void *next_record)
+{
+	int bit;
+
+	for_each_set_bit(bit, (unsigned long *)&cntr->cntr, INTEL_PMC_MAX_GENERIC) {
+		intel_perf_event_update_pmc(cpuc->events[bit], *(u64 *)next_record);
+		next_record += sizeof(u64);
+	}
+
+	for_each_set_bit(bit, (unsigned long *)&cntr->fixed, INTEL_PMC_MAX_FIXED) {
+		/* The slots event will be handled with perf_metric later */
+		if ((cntr->metrics == INTEL_CNTR_METRICS) &&
+		    (bit + INTEL_PMC_IDX_FIXED == INTEL_PMC_IDX_FIXED_SLOTS)) {
+			next_record += sizeof(u64);
+			continue;
+		}
+		intel_perf_event_update_pmc(cpuc->events[bit + INTEL_PMC_IDX_FIXED],
+					    *(u64 *)next_record);
+		next_record += sizeof(u64);
+	}
+
+	/* HW will reload the value right after the overflow. */
+	if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
+		local64_set(&event->hw.prev_count, (u64)-event->hw.sample_period);
+
+	if (cntr->metrics == INTEL_CNTR_METRICS) {
+		static_call(intel_pmu_update_topdown_event)
+			   (cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS],
+			    (u64 *)next_record);
+		next_record += 2 * sizeof(u64);
+	}
+}
+
 #define PEBS_LATENCY_MASK			0xffff
-#define PEBS_CACHE_LATENCY_OFFSET		32
-#define PEBS_RETIRE_LATENCY_OFFSET		32
 
 /*
  * With adaptive PEBS the layout depends on what fields are configured.
  */
-
 static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 					    struct pt_regs *iregs, void *__pebs,
 					    struct perf_sample_data *data,
@@ -1799,8 +2047,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct pebs_basic *basic = __pebs;
 	void *next_record = basic + 1;
-	u64 sample_type;
-	u64 format_size;
+	u64 sample_type, format_group;
 	struct pebs_meminfo *meminfo = NULL;
 	struct pebs_gprs *gprs = NULL;
 	struct x86_perf_regs *perf_regs;
@@ -1812,7 +2059,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	perf_regs->xmm_regs = NULL;
 
 	sample_type = event->attr.sample_type;
-	format_size = basic->format_size;
+	format_group = basic->format_group;
 	perf_sample_data_init(data, 0, event->hw.last_period);
 	data->period = event->hw.last_period;
 
@@ -1834,7 +2081,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 
 	if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) {
 		if (x86_pmu.flags & PMU_FL_RETIRE_LATENCY)
-			data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK;
+			data->weight.var3_w = basic->retire_latency;
 		else
 			data->weight.var3_w = 0;
 	}
@@ -1844,12 +2091,12 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	 * But PERF_SAMPLE_TRANSACTION needs gprs->ax.
 	 * Save the pointer here but process later.
 	 */
-	if (format_size & PEBS_DATACFG_MEMINFO) {
+	if (format_group & PEBS_DATACFG_MEMINFO) {
 		meminfo = next_record;
 		next_record = meminfo + 1;
 	}
 
-	if (format_size & PEBS_DATACFG_GP) {
+	if (format_group & PEBS_DATACFG_GP) {
 		gprs = next_record;
 		next_record = gprs + 1;
 
@@ -1862,14 +2109,13 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 			adaptive_pebs_save_regs(regs, gprs);
 	}
 
-	if (format_size & PEBS_DATACFG_MEMINFO) {
+	if (format_group & PEBS_DATACFG_MEMINFO) {
 		if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) {
-			u64 weight = meminfo->latency;
+			u64 latency = x86_pmu.flags & PMU_FL_INSTR_LATENCY ?
+					meminfo->cache_latency : meminfo->mem_latency;
 
-			if (x86_pmu.flags & PMU_FL_INSTR_LATENCY) {
-				data->weight.var2_w = weight & PEBS_LATENCY_MASK;
-				weight >>= PEBS_CACHE_LATENCY_OFFSET;
-			}
+			if (x86_pmu.flags & PMU_FL_INSTR_LATENCY)
+				data->weight.var2_w = meminfo->instr_latency;
 
 			/*
 			 * Although meminfo::latency is defined as a u64,
@@ -1877,12 +2123,13 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 			 * in practice on Ice Lake and earlier platforms.
 			 */
 			if (sample_type & PERF_SAMPLE_WEIGHT) {
-				data->weight.full = weight ?:
+				data->weight.full = latency ?:
 					intel_get_tsx_weight(meminfo->tsx_tuning);
 			} else {
-				data->weight.var1_dw = (u32)(weight & PEBS_LATENCY_MASK) ?:
+				data->weight.var1_dw = (u32)latency ?:
 					intel_get_tsx_weight(meminfo->tsx_tuning);
 			}
+
 			data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
 		}
 
@@ -1903,16 +2150,16 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 		}
 	}
 
-	if (format_size & PEBS_DATACFG_XMMS) {
+	if (format_group & PEBS_DATACFG_XMMS) {
 		struct pebs_xmm *xmm = next_record;
 
 		next_record = xmm + 1;
 		perf_regs->xmm_regs = xmm->xmm;
 	}
 
-	if (format_size & PEBS_DATACFG_LBRS) {
+	if (format_group & PEBS_DATACFG_LBRS) {
 		struct lbr_entry *lbr = next_record;
-		int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
+		int num_lbr = ((format_group >> PEBS_DATACFG_LBR_SHIFT)
 					& 0xff) + 1;
 		next_record = next_record + num_lbr * sizeof(struct lbr_entry);
 
@@ -1922,11 +2169,33 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 		}
 	}
 
-	WARN_ONCE(next_record != __pebs + (format_size >> 48),
-			"PEBS record size %llu, expected %llu, config %llx\n",
-			format_size >> 48,
+	if (format_group & (PEBS_DATACFG_CNTR | PEBS_DATACFG_METRICS)) {
+		struct pebs_cntr_header *cntr = next_record;
+		unsigned int nr;
+
+		next_record += sizeof(struct pebs_cntr_header);
+		/*
+		 * The PEBS_DATA_CFG is a global register, which is the
+		 * superset configuration for all PEBS events.
+		 * For the PEBS record of non-sample-read group, ignore
+		 * the counter snapshot fields.
+		 */
+		if (is_pebs_counter_event_group(event)) {
+			__setup_pebs_counter_group(cpuc, event, cntr, next_record);
+			data->sample_flags |= PERF_SAMPLE_READ;
+		}
+
+		nr = hweight32(cntr->cntr) + hweight32(cntr->fixed);
+		if (cntr->metrics == INTEL_CNTR_METRICS)
+			nr += 2;
+		next_record += nr * sizeof(u64);
+	}
+
+	WARN_ONCE(next_record != __pebs + basic->format_size,
+			"PEBS record size %u, expected %llu, config %llx\n",
+			basic->format_size,
 			(u64)(next_record - __pebs),
-			basic->format_size);
+			format_group);
 }
 
 static inline void *
@@ -2028,46 +2297,33 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
 	return 0;
 }
 
+typedef void (*setup_fn)(struct perf_event *, struct pt_regs *, void *,
+			 struct perf_sample_data *, struct pt_regs *);
+
+static struct pt_regs dummy_iregs;
+
 static __always_inline void
 __intel_pmu_pebs_event(struct perf_event *event,
 		       struct pt_regs *iregs,
+		       struct pt_regs *regs,
 		       struct perf_sample_data *data,
-		       void *base, void *top,
-		       int bit, int count,
-		       void (*setup_sample)(struct perf_event *,
-					    struct pt_regs *,
-					    void *,
-					    struct perf_sample_data *,
-					    struct pt_regs *))
+		       void *at,
+		       setup_fn setup_sample)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	struct hw_perf_event *hwc = &event->hw;
-	struct x86_perf_regs perf_regs;
-	struct pt_regs *regs = &perf_regs.regs;
-	void *at = get_next_pebs_record_by_bit(base, top, bit);
-	static struct pt_regs dummy_iregs;
-
-	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
-		/*
-		 * Now, auto-reload is only enabled in fixed period mode.
-		 * The reload value is always hwc->sample_period.
-		 * May need to change it, if auto-reload is enabled in
-		 * freq mode later.
-		 */
-		intel_pmu_save_and_restart_reload(event, count);
-	} else if (!intel_pmu_save_and_restart(event))
-		return;
-
-	if (!iregs)
-		iregs = &dummy_iregs;
+	setup_sample(event, iregs, at, data, regs);
+	perf_event_output(event, data, regs);
+}
 
-	while (count > 1) {
-		setup_sample(event, iregs, at, data, regs);
-		perf_event_output(event, data, regs);
-		at += cpuc->pebs_record_size;
-		at = get_next_pebs_record_by_bit(at, top, bit);
-		count--;
-	}
+static __always_inline void
+__intel_pmu_pebs_last_event(struct perf_event *event,
+			    struct pt_regs *iregs,
+			    struct pt_regs *regs,
+			    struct perf_sample_data *data,
+			    void *at,
+			    int count,
+			    setup_fn setup_sample)
+{
+	struct hw_perf_event *hwc = &event->hw;
 
 	setup_sample(event, iregs, at, data, regs);
 	if (iregs == &dummy_iregs) {
@@ -2086,6 +2342,52 @@ __intel_pmu_pebs_event(struct perf_event *event,
 		if (perf_event_overflow(event, data, regs))
 			x86_pmu_stop(event, 0);
 	}
+
+	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
+		if ((is_pebs_counter_event_group(event))) {
+			/*
+			 * The value of each sample has been updated when setup
+			 * the corresponding sample data.
+			 */
+			perf_event_update_userpage(event);
+		} else {
+			/*
+			 * Now, auto-reload is only enabled in fixed period mode.
+			 * The reload value is always hwc->sample_period.
+			 * May need to change it, if auto-reload is enabled in
+			 * freq mode later.
+			 */
+			intel_pmu_save_and_restart_reload(event, count);
+		}
+	} else
+		intel_pmu_save_and_restart(event);
+}
+
+static __always_inline void
+__intel_pmu_pebs_events(struct perf_event *event,
+			struct pt_regs *iregs,
+			struct perf_sample_data *data,
+			void *base, void *top,
+			int bit, int count,
+			setup_fn setup_sample)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct x86_perf_regs perf_regs;
+	struct pt_regs *regs = &perf_regs.regs;
+	void *at = get_next_pebs_record_by_bit(base, top, bit);
+	int cnt = count;
+
+	if (!iregs)
+		iregs = &dummy_iregs;
+
+	while (cnt > 1) {
+		__intel_pmu_pebs_event(event, iregs, regs, data, at, setup_sample);
+		at += cpuc->pebs_record_size;
+		at = get_next_pebs_record_by_bit(at, top, bit);
+		cnt--;
+	}
+
+	__intel_pmu_pebs_last_event(event, iregs, regs, data, at, count, setup_sample);
 }
 
 static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_data *data)
@@ -2122,8 +2424,8 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_
 		return;
 	}
 
-	__intel_pmu_pebs_event(event, iregs, data, at, top, 0, n,
-			       setup_pebs_fixed_sample_data);
+	__intel_pmu_pebs_events(event, iregs, data, at, top, 0, n,
+				setup_pebs_fixed_sample_data);
 }
 
 static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
@@ -2153,6 +2455,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 	void *base, *at, *top;
 	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
 	short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	int max_pebs_events = intel_pmu_max_num_pebs(NULL);
 	int bit, i, size;
 	u64 mask;
 
@@ -2164,11 +2467,11 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 
 	ds->pebs_index = ds->pebs_buffer_base;
 
-	mask = (1ULL << x86_pmu.max_pebs_events) - 1;
-	size = x86_pmu.max_pebs_events;
+	mask = x86_pmu.pebs_events_mask;
+	size = max_pebs_events;
 	if (x86_pmu.flags & PMU_FL_PEBS_ALL) {
-		mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED;
-		size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+		mask |= x86_pmu.fixed_cntr_mask64 << INTEL_PMC_IDX_FIXED;
+		size = INTEL_PMC_IDX_FIXED + x86_pmu_max_num_counters_fixed(NULL);
 	}
 
 	if (unlikely(base >= top)) {
@@ -2204,8 +2507,9 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 			pebs_status = p->status = cpuc->pebs_enabled;
 
 		bit = find_first_bit((unsigned long *)&pebs_status,
-					x86_pmu.max_pebs_events);
-		if (bit >= x86_pmu.max_pebs_events)
+				     max_pebs_events);
+
+		if (!(x86_pmu.pebs_events_mask & (1 << bit)))
 			continue;
 
 		/*
@@ -2252,9 +2556,9 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 		}
 
 		if (counts[bit]) {
-			__intel_pmu_pebs_event(event, iregs, data, base,
-					       top, bit, counts[bit],
-					       setup_pebs_fixed_sample_data);
+			__intel_pmu_pebs_events(event, iregs, data, base,
+						top, bit, counts[bit],
+						setup_pebs_fixed_sample_data);
 		}
 	}
 }
@@ -2262,13 +2566,15 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_data *data)
 {
 	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	void *last[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS];
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
-	int max_pebs_events = hybrid(cpuc->pmu, max_pebs_events);
-	int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
 	struct debug_store *ds = cpuc->ds;
+	struct x86_perf_regs perf_regs;
+	struct pt_regs *regs = &perf_regs.regs;
+	struct pebs_basic *basic;
 	struct perf_event *event;
 	void *base, *at, *top;
-	int bit, size;
+	int bit;
 	u64 mask;
 
 	if (!x86_pmu.pebs_active)
@@ -2279,39 +2585,49 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 
 	ds->pebs_index = ds->pebs_buffer_base;
 
-	mask = ((1ULL << max_pebs_events) - 1) |
-	       (((1ULL << num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED);
-	size = INTEL_PMC_IDX_FIXED + num_counters_fixed;
+	mask = hybrid(cpuc->pmu, pebs_events_mask) |
+	       (hybrid(cpuc->pmu, fixed_cntr_mask64) << INTEL_PMC_IDX_FIXED);
 
 	if (unlikely(base >= top)) {
-		intel_pmu_pebs_event_update_no_drain(cpuc, size);
+		intel_pmu_pebs_event_update_no_drain(cpuc, X86_PMC_IDX_MAX);
 		return;
 	}
 
-	for (at = base; at < top; at += cpuc->pebs_record_size) {
+	if (!iregs)
+		iregs = &dummy_iregs;
+
+	/* Process all but the last event for each counter. */
+	for (at = base; at < top; at += basic->format_size) {
 		u64 pebs_status;
 
-		pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
-		pebs_status &= mask;
+		basic = at;
+		if (basic->format_size != cpuc->pebs_record_size)
+			continue;
+
+		pebs_status = basic->applicable_counters & cpuc->pebs_enabled & mask;
+		for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX) {
+			event = cpuc->events[bit];
 
-		for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
-			counts[bit]++;
+			if (WARN_ON_ONCE(!event) ||
+			    WARN_ON_ONCE(!event->attr.precise_ip))
+				continue;
+
+			if (counts[bit]++) {
+				__intel_pmu_pebs_event(event, iregs, regs, data, last[bit],
+						       setup_pebs_adaptive_sample_data);
+			}
+			last[bit] = at;
+		}
 	}
 
-	for_each_set_bit(bit, (unsigned long *)&mask, size) {
-		if (counts[bit] == 0)
+	for_each_set_bit(bit, (unsigned long *)&mask, X86_PMC_IDX_MAX) {
+		if (!counts[bit])
 			continue;
 
 		event = cpuc->events[bit];
-		if (WARN_ON_ONCE(!event))
-			continue;
 
-		if (WARN_ON_ONCE(!event->attr.precise_ip))
-			continue;
-
-		__intel_pmu_pebs_event(event, iregs, data, base,
-				       top, bit, counts[bit],
-				       setup_pebs_adaptive_sample_data);
+		__intel_pmu_pebs_last_event(event, iregs, regs, data, last[bit],
+					    counts[bit], setup_pebs_adaptive_sample_data);
 	}
 }
 
@@ -2376,6 +2692,12 @@ void __init intel_ds_init(void)
 			x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
 			break;
 
+		case 6:
+			if (x86_pmu.intel_cap.pebs_baseline) {
+				x86_pmu.large_pebs_flags |= PERF_SAMPLE_READ;
+				x86_pmu.late_setup = intel_pmu_late_setup;
+			}
+			fallthrough;
 		case 5:
 			x86_pmu.pebs_ept = 1;
 			fallthrough;
@@ -2400,7 +2722,7 @@ void __init intel_ds_init(void)
 					  PERF_SAMPLE_REGS_USER |
 					  PERF_SAMPLE_REGS_INTR);
 			}
-			pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
+			pr_cont("PEBS fmt%d%c%s, ", format, pebs_type, pebs_qual);
 
 			if (!is_hybrid() && x86_pmu.intel_cap.pebs_output_pt_available) {
 				pr_cont("PEBS-via-PT, ");
diff --git a/arch/x86/events/intel/knc.c b/arch/x86/events/intel/knc.c
index 618001c208e81c185b530053070b69bcbd5b2205..034a1f6a457c6985e44efd2a800db85cc562555b 100644
--- a/arch/x86/events/intel/knc.c
+++ b/arch/x86/events/intel/knc.c
@@ -303,7 +303,7 @@ static const struct x86_pmu knc_pmu __initconst = {
 	.apic			= 1,
 	.max_period		= (1ULL << 39) - 1,
 	.version		= 0,
-	.num_counters		= 2,
+	.cntr_mask64		= 0x3,
 	.cntval_bits		= 40,
 	.cntval_mask		= (1ULL << 40) - 1,
 	.get_event_constraints	= x86_get_event_constraints,
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 4367aa77cb8d9f6f18adabebe39d3ef0ddc4dcf5..a8662143a4d6bbbe3bfce1de0f1aa5497ccdb166 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1608,7 +1608,7 @@ void __init intel_pmu_arch_lbr_init(void)
 	x86_pmu.lbr_nr = lbr_nr;
 
 	if (!!x86_pmu.lbr_counters)
-		x86_pmu.flags |= PMU_FL_BR_CNTR;
+		x86_pmu.flags |= PMU_FL_BR_CNTR | PMU_FL_DYN_CONSTRAINT;
 
 	if (x86_pmu.lbr_mispred)
 		static_branch_enable(&x86_lbr_mispred);
diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c
index 35936188db01bbad5afee72334a1a52b74c4f6d0..844bc4fc4724d75417c73e829fe7f3987141aff8 100644
--- a/arch/x86/events/intel/p4.c
+++ b/arch/x86/events/intel/p4.c
@@ -919,7 +919,7 @@ static void p4_pmu_disable_all(void)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[idx];
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
@@ -998,7 +998,7 @@ static void p4_pmu_enable_all(int added)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[idx];
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
@@ -1040,7 +1040,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 
 	cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		int overflow;
 
 		if (!test_bit(idx, cpuc->active_mask)) {
@@ -1353,7 +1353,7 @@ static __initconst const struct x86_pmu p4_pmu = {
 	 * though leave it restricted at moment assuming
 	 * HT is on
 	 */
-	.num_counters		= ARCH_P4_MAX_CCCR,
+	.cntr_mask64		= GENMASK_ULL(ARCH_P4_MAX_CCCR - 1, 0),
 	.apic			= 1,
 	.cntval_bits		= ARCH_P4_CNTRVAL_BITS,
 	.cntval_mask		= ARCH_P4_CNTRVAL_MASK,
@@ -1395,7 +1395,7 @@ __init int p4_pmu_init(void)
 	 *
 	 * Solve this by zero'ing out the registers to mimic a reset.
 	 */
-	for (i = 0; i < x86_pmu.num_counters; i++) {
+	for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		reg = x86_pmu_config_addr(i);
 		wrmsrl_safe(reg, 0ULL);
 	}
diff --git a/arch/x86/events/intel/p6.c b/arch/x86/events/intel/p6.c
index 408879b0c0d4e41c56906d2464734279c9360f7e..a6cffb4f4ef52eb721e7560bc7f5616023577592 100644
--- a/arch/x86/events/intel/p6.c
+++ b/arch/x86/events/intel/p6.c
@@ -214,7 +214,7 @@ static __initconst const struct x86_pmu p6_pmu = {
 	.apic			= 1,
 	.max_period		= (1ULL << 31) - 1,
 	.version		= 0,
-	.num_counters		= 2,
+	.cntr_mask64		= 0x3,
 	/*
 	 * Events have 40 bits implemented. However they are designed such
 	 * that bits [32-39] are sign extensions of bit 31. As such the
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 4d856b51307f3b183743764e868a18d27a071f9e..428569bde638c86a740777929529529535e03002 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -744,7 +744,7 @@ static int uncore_pmu_event_init(struct perf_event *event)
 
 	pmu = uncore_event_to_pmu(event);
 	/* no device found for this pmu */
-	if (pmu->func_id < 0)
+	if (!pmu->registered)
 		return -ENOENT;
 
 	/* Sampling not supported yet */
@@ -991,7 +991,7 @@ static void uncore_types_exit(struct intel_uncore_type **types)
 		uncore_type_exit(*types);
 }
 
-static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
+static int __init uncore_type_init(struct intel_uncore_type *type)
 {
 	struct intel_uncore_pmu *pmus;
 	size_t size;
@@ -1004,7 +1004,6 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 	size = uncore_max_dies() * sizeof(struct intel_uncore_box *);
 
 	for (i = 0; i < type->num_boxes; i++) {
-		pmus[i].func_id	= setid ? i : -1;
 		pmus[i].pmu_idx	= i;
 		pmus[i].type	= type;
 		pmus[i].boxes	= kzalloc(size, GFP_KERNEL);
@@ -1054,12 +1053,12 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid)
 }
 
 static int __init
-uncore_types_init(struct intel_uncore_type **types, bool setid)
+uncore_types_init(struct intel_uncore_type **types)
 {
 	int ret;
 
 	for (; *types; types++) {
-		ret = uncore_type_init(*types, setid);
+		ret = uncore_type_init(*types);
 		if (ret)
 			return ret;
 	}
@@ -1159,11 +1158,6 @@ static int uncore_pci_pmu_register(struct pci_dev *pdev,
 	if (!box)
 		return -ENOMEM;
 
-	if (pmu->func_id < 0)
-		pmu->func_id = pdev->devfn;
-	else
-		WARN_ON_ONCE(pmu->func_id != pdev->devfn);
-
 	atomic_inc(&box->refcnt);
 	box->dieid = die;
 	box->pci_dev = pdev;
@@ -1409,7 +1403,7 @@ static int __init uncore_pci_init(void)
 		goto err;
 	}
 
-	ret = uncore_types_init(uncore_pci_uncores, false);
+	ret = uncore_types_init(uncore_pci_uncores);
 	if (ret)
 		goto errtype;
 
@@ -1677,7 +1671,7 @@ static int __init uncore_cpu_init(void)
 {
 	int ret;
 
-	ret = uncore_types_init(uncore_msr_uncores, true);
+	ret = uncore_types_init(uncore_msr_uncores);
 	if (ret)
 		goto err;
 
@@ -1696,7 +1690,7 @@ static int __init uncore_mmio_init(void)
 	struct intel_uncore_type **types = uncore_mmio_uncores;
 	int ret;
 
-	ret = uncore_types_init(types, true);
+	ret = uncore_types_init(types);
 	if (ret)
 		goto err;
 
@@ -1850,56 +1844,57 @@ static const struct intel_uncore_init_fun generic_uncore_init __initconst = {
 };
 
 static const struct x86_cpu_id intel_uncore_match[] __initconst = {
-	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EP,		&nhm_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM,		&nhm_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(WESTMERE,		&nhm_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EP,		&nhm_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE,		&snb_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE,		&ivb_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(HASWELL,		&hsw_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L,		&hsw_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G,		&hsw_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL,		&bdw_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G,		&bdw_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X,	&snbep_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(NEHALEM_EX,		&nhmex_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(WESTMERE_EX,		&nhmex_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X,		&ivbep_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X,		&hswep_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X,		&bdx_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D,		&bdx_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL,	&knl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM,	&knl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE,		&skl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L,		&skl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,		&skx_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L,		&skl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE,		&skl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&skl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&skl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&icl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_NNPI,	&icl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&icl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		&icx_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&icx_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		&tgl_l_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		&tgl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ROCKETLAKE,		&rkl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&adl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&adl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&adl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,	&adl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	&adl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE,		&mtl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L,	&mtl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&spr_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X,	&spr_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X,	&gnr_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_D,	&gnr_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D,	&snr_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	&adl_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X,	&gnr_uncore_init),
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT,	&gnr_uncore_init),
+	X86_MATCH_VFM(INTEL_NEHALEM_EP,		&nhm_uncore_init),
+	X86_MATCH_VFM(INTEL_NEHALEM,		&nhm_uncore_init),
+	X86_MATCH_VFM(INTEL_WESTMERE,		&nhm_uncore_init),
+	X86_MATCH_VFM(INTEL_WESTMERE_EP,	&nhm_uncore_init),
+	X86_MATCH_VFM(INTEL_SANDYBRIDGE,	&snb_uncore_init),
+	X86_MATCH_VFM(INTEL_IVYBRIDGE,		&ivb_uncore_init),
+	X86_MATCH_VFM(INTEL_HASWELL,		&hsw_uncore_init),
+	X86_MATCH_VFM(INTEL_HASWELL_L,		&hsw_uncore_init),
+	X86_MATCH_VFM(INTEL_HASWELL_G,		&hsw_uncore_init),
+	X86_MATCH_VFM(INTEL_BROADWELL,		&bdw_uncore_init),
+	X86_MATCH_VFM(INTEL_BROADWELL_G,	&bdw_uncore_init),
+	X86_MATCH_VFM(INTEL_SANDYBRIDGE_X,	&snbep_uncore_init),
+	X86_MATCH_VFM(INTEL_NEHALEM_EX,		&nhmex_uncore_init),
+	X86_MATCH_VFM(INTEL_WESTMERE_EX,	&nhmex_uncore_init),
+	X86_MATCH_VFM(INTEL_IVYBRIDGE_X,	&ivbep_uncore_init),
+	X86_MATCH_VFM(INTEL_HASWELL_X,		&hswep_uncore_init),
+	X86_MATCH_VFM(INTEL_BROADWELL_X,	&bdx_uncore_init),
+	X86_MATCH_VFM(INTEL_BROADWELL_D,	&bdx_uncore_init),
+	X86_MATCH_VFM(INTEL_XEON_PHI_KNL,	&knl_uncore_init),
+	X86_MATCH_VFM(INTEL_XEON_PHI_KNM,	&knl_uncore_init),
+	X86_MATCH_VFM(INTEL_SKYLAKE,		&skl_uncore_init),
+	X86_MATCH_VFM(INTEL_SKYLAKE_L,		&skl_uncore_init),
+	X86_MATCH_VFM(INTEL_SKYLAKE_X,		&skx_uncore_init),
+	X86_MATCH_VFM(INTEL_KABYLAKE_L,		&skl_uncore_init),
+	X86_MATCH_VFM(INTEL_KABYLAKE,		&skl_uncore_init),
+	X86_MATCH_VFM(INTEL_COMETLAKE_L,	&skl_uncore_init),
+	X86_MATCH_VFM(INTEL_COMETLAKE,		&skl_uncore_init),
+	X86_MATCH_VFM(INTEL_ICELAKE_L,		&icl_uncore_init),
+	X86_MATCH_VFM(INTEL_ICELAKE_NNPI,	&icl_uncore_init),
+	X86_MATCH_VFM(INTEL_ICELAKE,		&icl_uncore_init),
+	X86_MATCH_VFM(INTEL_ICELAKE_D,		&icx_uncore_init),
+	X86_MATCH_VFM(INTEL_ICELAKE_X,		&icx_uncore_init),
+	X86_MATCH_VFM(INTEL_TIGERLAKE_L,	&tgl_l_uncore_init),
+	X86_MATCH_VFM(INTEL_TIGERLAKE,		&tgl_uncore_init),
+	X86_MATCH_VFM(INTEL_ROCKETLAKE,		&rkl_uncore_init),
+	X86_MATCH_VFM(INTEL_ALDERLAKE,		&adl_uncore_init),
+	X86_MATCH_VFM(INTEL_ALDERLAKE_L,	&adl_uncore_init),
+	X86_MATCH_VFM(INTEL_RAPTORLAKE,		&adl_uncore_init),
+	X86_MATCH_VFM(INTEL_RAPTORLAKE_P,	&adl_uncore_init),
+	X86_MATCH_VFM(INTEL_RAPTORLAKE_S,	&adl_uncore_init),
+	X86_MATCH_VFM(INTEL_METEORLAKE,		&mtl_uncore_init),
+	X86_MATCH_VFM(INTEL_METEORLAKE_L,	&mtl_uncore_init),
+	X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X,	&spr_uncore_init),
+	X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X,	&spr_uncore_init),
+	X86_MATCH_VFM(INTEL_GRANITERAPIDS_X,	&gnr_uncore_init),
+	X86_MATCH_VFM(INTEL_GRANITERAPIDS_D,	&gnr_uncore_init),
+	X86_MATCH_VFM(INTEL_ATOM_TREMONT_D,	&snr_uncore_init),
+	X86_MATCH_VFM(INTEL_ATOM_GRACEMONT,	&adl_uncore_init),
+	X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X,	&gnr_uncore_init),
+	X86_MATCH_VFM(INTEL_ATOM_CRESTMONT,	&gnr_uncore_init),
+	X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X,	&gnr_uncore_init),
 	{},
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match);
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 027ef292c60223119071fd5ebd1a253a96058fd0..9ba2305c0d9ae4621e136b0e05879abae7aceb34 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -125,7 +125,6 @@ struct intel_uncore_pmu {
 	struct pmu			pmu;
 	char				name[UNCORE_PMU_NAME_LEN];
 	int				pmu_idx;
-	int				func_id;
 	bool				registered;
 	atomic_t			activeboxes;
 	cpumask_t			cpu_mask;
diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c
index 571e44b496910d865b1e89d0d81cb1f4be8bef2c..a543a54fd7140f3e5dfc09040f941964711c512b 100644
--- a/arch/x86/events/intel/uncore_discovery.c
+++ b/arch/x86/events/intel/uncore_discovery.c
@@ -273,32 +273,15 @@ uncore_ignore_unit(struct uncore_unit_discovery *unit, int *ignore)
 	return false;
 }
 
-static int parse_discovery_table(struct pci_dev *dev, int die,
-				 u32 bar_offset, bool *parsed,
-				 int *ignore)
+static int __parse_discovery_table(resource_size_t addr, int die,
+				   bool *parsed, int *ignore)
 {
 	struct uncore_global_discovery global;
 	struct uncore_unit_discovery unit;
 	void __iomem *io_addr;
-	resource_size_t addr;
 	unsigned long size;
-	u32 val;
 	int i;
 
-	pci_read_config_dword(dev, bar_offset, &val);
-
-	if (val & ~PCI_BASE_ADDRESS_MEM_MASK & ~PCI_BASE_ADDRESS_MEM_TYPE_64)
-		return -EINVAL;
-
-	addr = (resource_size_t)(val & PCI_BASE_ADDRESS_MEM_MASK);
-#ifdef CONFIG_PHYS_ADDR_T_64BIT
-	if ((val & PCI_BASE_ADDRESS_MEM_TYPE_MASK) == PCI_BASE_ADDRESS_MEM_TYPE_64) {
-		u32 val2;
-
-		pci_read_config_dword(dev, bar_offset + 4, &val2);
-		addr |= ((resource_size_t)val2) << 32;
-	}
-#endif
 	size = UNCORE_DISCOVERY_GLOBAL_MAP_SIZE;
 	io_addr = ioremap(addr, size);
 	if (!io_addr)
@@ -341,7 +324,32 @@ static int parse_discovery_table(struct pci_dev *dev, int die,
 	return 0;
 }
 
-bool intel_uncore_has_discovery_tables(int *ignore)
+static int parse_discovery_table(struct pci_dev *dev, int die,
+				 u32 bar_offset, bool *parsed,
+				 int *ignore)
+{
+	resource_size_t addr;
+	u32 val;
+
+	pci_read_config_dword(dev, bar_offset, &val);
+
+	if (val & ~PCI_BASE_ADDRESS_MEM_MASK & ~PCI_BASE_ADDRESS_MEM_TYPE_64)
+		return -EINVAL;
+
+	addr = (resource_size_t)(val & PCI_BASE_ADDRESS_MEM_MASK);
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+	if ((val & PCI_BASE_ADDRESS_MEM_TYPE_MASK) == PCI_BASE_ADDRESS_MEM_TYPE_64) {
+		u32 val2;
+
+		pci_read_config_dword(dev, bar_offset + 4, &val2);
+		addr |= ((resource_size_t)val2) << 32;
+	}
+#endif
+
+	return __parse_discovery_table(addr, die, parsed, ignore);
+}
+
+static bool intel_uncore_has_discovery_tables_pci(int *ignore)
 {
 	u32 device, val, entry_id, bar_offset;
 	int die, dvsec = 0, ret = true;
@@ -390,6 +398,45 @@ bool intel_uncore_has_discovery_tables(int *ignore)
 	return ret;
 }
 
+static bool intel_uncore_has_discovery_tables_msr(int *ignore)
+{
+	unsigned long *die_mask;
+	bool parsed = false;
+	int cpu, die;
+	u64 base;
+
+	die_mask = kcalloc(BITS_TO_LONGS(uncore_max_dies()),
+			   sizeof(unsigned long), GFP_KERNEL);
+	if (!die_mask)
+		return false;
+
+	cpus_read_lock();
+	for_each_online_cpu(cpu) {
+		die = topology_logical_die_id(cpu);
+		if (__test_and_set_bit(die, die_mask))
+			continue;
+
+		if (rdmsrl_safe_on_cpu(cpu, UNCORE_DISCOVERY_MSR, &base))
+			continue;
+
+		if (!base)
+			continue;
+
+		__parse_discovery_table(base, die, &parsed, ignore);
+	}
+
+	cpus_read_unlock();
+
+	kfree(die_mask);
+	return parsed;
+}
+
+bool intel_uncore_has_discovery_tables(int *ignore)
+{
+	return intel_uncore_has_discovery_tables_msr(ignore) ||
+	       intel_uncore_has_discovery_tables_pci(ignore);
+}
+
 void intel_uncore_clear_discovery_tables(void)
 {
 	struct intel_uncore_discovery_type *type, *next;
@@ -603,7 +650,7 @@ void intel_generic_uncore_mmio_init_box(struct intel_uncore_box *box)
 	}
 
 	addr = unit->addr;
-	box->io_addr = ioremap(addr, UNCORE_GENERIC_MMIO_SIZE);
+	box->io_addr = ioremap(addr, type->mmio_map_size);
 	if (!box->io_addr) {
 		pr_warn("Uncore type %d box %d: ioremap error for 0x%llx.\n",
 			type->type_id, unit->id, (unsigned long long)addr);
diff --git a/arch/x86/events/intel/uncore_discovery.h b/arch/x86/events/intel/uncore_discovery.h
index 0e94aa7db8e7d7d34c9670637c246d6ecdf5d8e1..690f737e6837b1aa6701367ddb5d8a7ce08e4c1f 100644
--- a/arch/x86/events/intel/uncore_discovery.h
+++ b/arch/x86/events/intel/uncore_discovery.h
@@ -1,5 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 
+/* Store the full address of the global discovery table */
+#define UNCORE_DISCOVERY_MSR			0x201e
+
 /* Generic device ID of a discovery table device */
 #define UNCORE_DISCOVERY_TABLE_DEVICE		0x09a7
 /* Capability ID for a discovery table device */
diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c
index 56eea2c66cfb8cc7d9cc395e58c24a7319afc944..158c24823d9014d14f9aa620d2f5580df4442b7f 100644
--- a/arch/x86/events/intel/uncore_nhmex.c
+++ b/arch/x86/events/intel/uncore_nhmex.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Nehalem-EX/Westmere-EX uncore support */
+#include <asm/cpu_device_id.h>
 #include "uncore.h"
 
 /* NHM-EX event control */
@@ -1217,7 +1218,7 @@ static struct intel_uncore_type *nhmex_msr_uncores[] = {
 
 void nhmex_uncore_cpu_init(void)
 {
-	if (boot_cpu_data.x86_model == 46)
+	if (boot_cpu_data.x86_vfm == INTEL_NEHALEM_EX)
 		uncore_nhmex = true;
 	else
 		nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events;
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 7fd4334e12a172d495bdf9353ac678f2a19f86f6..3725bb6571c48b4aa7a33d0e3cb8c5d824a1bd16 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -881,7 +881,7 @@ static int snb_uncore_imc_event_init(struct perf_event *event)
 
 	pmu = uncore_event_to_pmu(event);
 	/* no device found for this pmu */
-	if (pmu->func_id < 0)
+	if (!pmu->registered)
 		return -ENOENT;
 
 	/* Sampling not supported yet */
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index abb0325b1eb1efefb1118c02ece82ccad2c9f97c..8ca4a816c4cce2e3348b7afeea1f35b21d29c7ab 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* SandyBridge-EP/IvyTown uncore support */
+#include <asm/cpu_device_id.h>
 #include "uncore.h"
 #include "uncore_discovery.h"
 
@@ -3279,7 +3280,7 @@ void bdx_uncore_cpu_init(void)
 	uncore_msr_uncores = bdx_msr_uncores;
 
 	/* Detect systems with no SBOXes */
-	if ((boot_cpu_data.x86_model == 86) || hswep_has_limit_sbox(BDX_PCU_DID))
+	if (boot_cpu_data.x86_vfm == INTEL_BROADWELL_D || hswep_has_limit_sbox(BDX_PCU_DID))
 		uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
 
 	hswep_uncore_pcu.constraints = bdx_uncore_pcu_constraints;
@@ -5388,7 +5389,7 @@ static int icx_iio_get_topology(struct intel_uncore_type *type)
 static void icx_iio_set_mapping(struct intel_uncore_type *type)
 {
 	/* Detect ICX-D system. This case is not supported */
-	if (boot_cpu_data.x86_model == INTEL_FAM6_ICELAKE_D) {
+	if (boot_cpu_data.x86_vfm == INTEL_ICELAKE_D) {
 		pmu_clear_mapping_attr(type->attr_update, &icx_iio_mapping_group);
 		return;
 	}
@@ -6404,6 +6405,8 @@ static void uncore_type_customized_copy(struct intel_uncore_type *to_type,
 		to_type->get_topology = from_type->get_topology;
 	if (from_type->cleanup_mapping)
 		to_type->cleanup_mapping = from_type->cleanup_mapping;
+	if (from_type->mmio_map_size)
+		to_type->mmio_map_size = from_type->mmio_map_size;
 }
 
 static struct intel_uncore_type **
@@ -6593,17 +6596,8 @@ void spr_uncore_mmio_init(void)
 /* GNR uncore support */
 
 #define UNCORE_GNR_NUM_UNCORE_TYPES	23
-#define UNCORE_GNR_TYPE_15		15
-#define UNCORE_GNR_B2UPI		18
-#define UNCORE_GNR_TYPE_21		21
-#define UNCORE_GNR_TYPE_22		22
 
 int gnr_uncore_units_ignore[] = {
-	UNCORE_SPR_UPI,
-	UNCORE_GNR_TYPE_15,
-	UNCORE_GNR_B2UPI,
-	UNCORE_GNR_TYPE_21,
-	UNCORE_GNR_TYPE_22,
 	UNCORE_IGNORE_END
 };
 
@@ -6612,6 +6606,31 @@ static struct intel_uncore_type gnr_uncore_ubox = {
 	.attr_update		= uncore_alias_groups,
 };
 
+static struct intel_uncore_type gnr_uncore_pciex8 = {
+	SPR_UNCORE_PCI_COMMON_FORMAT(),
+	.name			= "pciex8",
+};
+
+static struct intel_uncore_type gnr_uncore_pciex16 = {
+	SPR_UNCORE_PCI_COMMON_FORMAT(),
+	.name			= "pciex16",
+};
+
+static struct intel_uncore_type gnr_uncore_upi = {
+	SPR_UNCORE_PCI_COMMON_FORMAT(),
+	.name			= "upi",
+};
+
+static struct intel_uncore_type gnr_uncore_b2upi = {
+	SPR_UNCORE_PCI_COMMON_FORMAT(),
+	.name			= "b2upi",
+};
+
+static struct intel_uncore_type gnr_uncore_b2hot = {
+	.name			= "b2hot",
+	.attr_update		= uncore_alias_groups,
+};
+
 static struct intel_uncore_type gnr_uncore_b2cmi = {
 	SPR_UNCORE_PCI_COMMON_FORMAT(),
 	.name			= "b2cmi",
@@ -6636,21 +6655,21 @@ static struct intel_uncore_type *gnr_uncores[UNCORE_GNR_NUM_UNCORE_TYPES] = {
 	&gnr_uncore_ubox,
 	&spr_uncore_imc,
 	NULL,
+	&gnr_uncore_upi,
 	NULL,
 	NULL,
 	NULL,
+	&spr_uncore_cxlcm,
+	&spr_uncore_cxldp,
 	NULL,
-	NULL,
-	NULL,
-	NULL,
-	NULL,
+	&gnr_uncore_b2hot,
 	&gnr_uncore_b2cmi,
 	&gnr_uncore_b2cxl,
-	NULL,
+	&gnr_uncore_b2upi,
 	NULL,
 	&gnr_uncore_mdf_sbo,
-	NULL,
-	NULL,
+	&gnr_uncore_pciex16,
+	&gnr_uncore_pciex8,
 };
 
 static struct freerunning_counters gnr_iio_freerunning[] = {
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 79ed3ef2dda1e359b617325b853e2fad95593562..e5237c126e4bcae5270b380733fa17dd9d317c13 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -110,9 +110,26 @@ static inline bool is_topdown_event(struct perf_event *event)
 	return is_metric_event(event) || is_slots_event(event);
 }
 
+int is_x86_event(struct perf_event *event);
+
+static inline bool check_leader_group(struct perf_event *leader, int flags)
+{
+	return is_x86_event(leader) ? !!(leader->hw.flags & flags) : false;
+}
+
 static inline bool is_branch_counters_group(struct perf_event *event)
 {
-	return event->group_leader->hw.flags & PERF_X86_EVENT_BRANCH_COUNTERS;
+	return check_leader_group(event->group_leader, PERF_X86_EVENT_BRANCH_COUNTERS);
+}
+
+static inline bool is_pebs_counter_event_group(struct perf_event *event)
+{
+	return check_leader_group(event->group_leader, PERF_X86_EVENT_PEBS_CNTR);
+}
+
+static inline bool is_acr_event_group(struct perf_event *event)
+{
+	return check_leader_group(event->group_leader, PERF_X86_EVENT_ACR);
 }
 
 struct amd_nb {
@@ -256,6 +273,7 @@ struct cpu_hw_events {
 	struct event_constraint	*event_constraint[X86_PMC_IDX_MAX];
 
 	int			n_excl; /* the number of exclusive events */
+	int			n_late_setup; /* the num of events needs late setup */
 
 	unsigned int		txn_flags;
 	int			is_fake;
@@ -281,6 +299,10 @@ struct cpu_hw_events {
 	u64			fixed_ctrl_val;
 	u64			active_fixed_ctrl_val;
 
+	/* Intel ACR configuration */
+	u64			acr_cfg_b[X86_PMC_IDX_MAX];
+	u64			acr_cfg_c[X86_PMC_IDX_MAX];
+
 	/*
 	 * Intel LBR bits
 	 */
@@ -476,6 +498,14 @@ struct cpu_hw_events {
 	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID)
 
+#define INTEL_HYBRID_LDLAT_CONSTRAINT(c, n)	\
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID|PERF_X86_EVENT_PEBS_LD_HSW)
+
+#define INTEL_HYBRID_STLAT_CONSTRAINT(c, n)	\
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID|PERF_X86_EVENT_PEBS_ST_HSW)
+
 /* Event constraint, but match on all event flags too. */
 #define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
 	EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS)
@@ -616,6 +646,7 @@ union perf_capabilities {
 		u64	pebs_output_pt_available:1;
 		u64	pebs_timing_info:1;
 		u64	anythread_deprecated:1;
+		u64	rdpmc_metrics_clear:1;
 	};
 	u64	capabilities;
 };
@@ -655,8 +686,10 @@ enum {
 	x86_lbr_exclusive_max,
 };
 
-#define PERF_PEBS_DATA_SOURCE_MAX	0x10
+#define PERF_PEBS_DATA_SOURCE_MAX	0x100
 #define PERF_PEBS_DATA_SOURCE_MASK	(PERF_PEBS_DATA_SOURCE_MAX - 1)
+#define PERF_PEBS_DATA_SOURCE_GRT_MAX	0x10
+#define PERF_PEBS_DATA_SOURCE_GRT_MASK	(PERF_PEBS_DATA_SOURCE_GRT_MAX - 1)
 
 enum hybrid_cpu_type {
 	HYBRID_INTEL_NONE,
@@ -684,9 +717,25 @@ struct x86_hybrid_pmu {
 	cpumask_t			supported_cpus;
 	union perf_capabilities		intel_cap;
 	u64				intel_ctrl;
-	int				max_pebs_events;
-	int				num_counters;
-	int				num_counters_fixed;
+	u64				pebs_events_mask;
+	u64				config_mask;
+	union {
+			u64		cntr_mask64;
+			unsigned long	cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		fixed_cntr_mask64;
+			unsigned long	fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+
+	union {
+			u64		acr_cntr_mask64;
+			unsigned long	acr_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		acr_cause_mask64;
+			unsigned long	acr_cause_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
 	struct event_constraint		unconstrained;
 
 	u64				hw_cache_event_ids
@@ -768,14 +817,31 @@ struct x86_pmu {
 	u64		(*update)(struct perf_event *event);
 	int		(*hw_config)(struct perf_event *event);
 	int		(*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
+	void		(*late_setup)(void);
 	unsigned	eventsel;
 	unsigned	perfctr;
+	unsigned	fixedctr;
 	int		(*addr_offset)(int index, bool eventsel);
 	int		(*rdpmc_index)(int index);
 	u64		(*event_map)(int);
 	int		max_events;
-	int		num_counters;
-	int		num_counters_fixed;
+	u64		config_mask;
+	union {
+			u64		cntr_mask64;
+			unsigned long	cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		fixed_cntr_mask64;
+			unsigned long	fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		acr_cntr_mask64;
+			unsigned long	acr_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		acr_cause_mask64;
+			unsigned long	acr_cause_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
 	int		cntval_bits;
 	u64		cntval_mask;
 	union {
@@ -852,7 +918,7 @@ struct x86_pmu {
 			pebs_ept		:1;
 	int		pebs_record_size;
 	int		pebs_buffer_size;
-	int		max_pebs_events;
+	u64		pebs_events_mask;
 	void		(*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data);
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);
@@ -1020,6 +1086,7 @@ do {									\
 #define PMU_FL_MEM_LOADS_AUX	0x100 /* Require an auxiliary event for the complete memory info */
 #define PMU_FL_RETIRE_LATENCY	0x200 /* Support Retire Latency in PEBS */
 #define PMU_FL_BR_CNTR		0x400 /* Support branch counter logging */
+#define PMU_FL_DYN_CONSTRAINT	0x800 /* Needs dynamic constraint */
 
 #define EVENT_VAR(_id)  event_attr_##_id
 #define EVENT_PTR(_id) &event_attr_##_id.attr.attr
@@ -1062,12 +1129,14 @@ static struct perf_pmu_format_hybrid_attr format_attr_hybrid_##_name = {\
 	.pmu_type	= _pmu,						\
 }
 
+int is_x86_event(struct perf_event *event);
 struct pmu *x86_get_pmu(unsigned int cpu);
 extern struct x86_pmu x86_pmu __read_mostly;
 
 DECLARE_STATIC_CALL(x86_pmu_set_period, *x86_pmu.set_period);
 DECLARE_STATIC_CALL(x86_pmu_update,     *x86_pmu.update);
 DECLARE_STATIC_CALL(x86_pmu_drain_pebs,	*x86_pmu.drain_pebs);
+DECLARE_STATIC_CALL(x86_pmu_late_setup,	*x86_pmu.late_setup);
 
 static __always_inline struct x86_perf_task_context_opt *task_context_opt(void *ctx)
 {
@@ -1109,6 +1178,12 @@ extern u64 __read_mostly hw_cache_extra_regs
 
 u64 x86_perf_event_update(struct perf_event *event);
 
+static inline u64 intel_pmu_topdown_event_update(struct perf_event *event, u64 *val)
+{
+	return x86_perf_event_update(event);
+}
+DECLARE_STATIC_CALL(intel_pmu_update_topdown_event, intel_pmu_topdown_event_update);
+
 static inline unsigned int x86_pmu_config_addr(int index)
 {
 	return x86_pmu.eventsel + (x86_pmu.addr_offset ?
@@ -1121,13 +1196,19 @@ static inline unsigned int x86_pmu_event_addr(int index)
 				  x86_pmu.addr_offset(index, false) : index);
 }
 
+static inline unsigned int x86_pmu_fixed_ctr_addr(int index)
+{
+	return x86_pmu.fixedctr + (x86_pmu.addr_offset ?
+				   x86_pmu.addr_offset(index, false) : index);
+}
+
 static inline int x86_pmu_rdpmc_index(int index)
 {
 	return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index;
 }
 
-bool check_hw_exists(struct pmu *pmu, int num_counters,
-		     int num_counters_fixed);
+bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
+		     unsigned long *fixed_cntr_mask);
 
 int x86_add_exclusive(unsigned int what);
 
@@ -1198,8 +1279,32 @@ void x86_pmu_enable_event(struct perf_event *event);
 
 int x86_pmu_handle_irq(struct pt_regs *regs);
 
-void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed,
-			  u64 intel_ctrl);
+void x86_pmu_show_pmu_cap(struct pmu *pmu);
+
+static inline int x86_pmu_num_counters(struct pmu *pmu)
+{
+	return hweight64(hybrid(pmu, cntr_mask64));
+}
+
+static inline int x86_pmu_max_num_counters(struct pmu *pmu)
+{
+	return fls64(hybrid(pmu, cntr_mask64));
+}
+
+static inline int x86_pmu_num_counters_fixed(struct pmu *pmu)
+{
+	return hweight64(hybrid(pmu, fixed_cntr_mask64));
+}
+
+static inline int x86_pmu_max_num_counters_fixed(struct pmu *pmu)
+{
+	return fls64(hybrid(pmu, fixed_cntr_mask64));
+}
+
+static inline u64 x86_pmu_get_event_config(struct perf_event *event)
+{
+	return event->attr.config & hybrid(event->pmu, config_mask);
+}
 
 extern struct event_constraint emptyconstraint;
 
@@ -1505,9 +1610,13 @@ void intel_pmu_disable_bts(void);
 
 int intel_pmu_drain_bts_buffer(void);
 
-u64 adl_latency_data_small(struct perf_event *event, u64 status);
+void intel_pmu_late_setup(void);
+
+u64 grt_latency_data(struct perf_event *event, u64 status);
 
-u64 mtl_latency_data_small(struct perf_event *event, u64 status);
+u64 cmt_latency_data(struct perf_event *event, u64 status);
+
+u64 lnl_latency_data(struct perf_event *event, u64 status);
 
 extern struct event_constraint intel_core2_pebs_event_constraints[];
 
@@ -1539,6 +1648,8 @@ extern struct event_constraint intel_icl_pebs_event_constraints[];
 
 extern struct event_constraint intel_glc_pebs_event_constraints[];
 
+extern struct event_constraint intel_lnc_pebs_event_constraints[];
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
 
 void intel_pmu_pebs_add(struct perf_event *event);
@@ -1555,6 +1666,8 @@ void intel_pmu_pebs_disable_all(void);
 
 void intel_pmu_pebs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in);
 
+void intel_pmu_pebs_late_setup(struct cpu_hw_events *cpuc);
+
 void intel_pmu_drain_pebs_buffer(void);
 
 void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);
@@ -1628,6 +1741,8 @@ void intel_pmu_pebs_data_source_mtl(void);
 
 void intel_pmu_pebs_data_source_cmt(void);
 
+void intel_pmu_pebs_data_source_lnl(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 void intel_pt_interrupt(void);
@@ -1649,6 +1764,17 @@ static inline int is_ht_workaround_enabled(void)
 	return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED);
 }
 
+static inline u64 intel_pmu_pebs_mask(u64 cntr_mask)
+{
+	return MAX_PEBS_EVENTS_MASK & cntr_mask;
+}
+
+static inline int intel_pmu_max_num_pebs(struct pmu *pmu)
+{
+	static_assert(MAX_PEBS_EVENTS == 32);
+	return fls((u32)hybrid(pmu, pebs_events_mask));
+}
+
 #else /* CONFIG_CPU_SUP_INTEL */
 
 static inline void reserve_ds_buffers(void)
diff --git a/arch/x86/events/perf_event_flags.h b/arch/x86/events/perf_event_flags.h
index 6c977c19f2cd7b0a1c1947611a2b28f72376202e..70078334e4a33820a0b57c58c8cdd1d62c4fe0ad 100644
--- a/arch/x86/events/perf_event_flags.h
+++ b/arch/x86/events/perf_event_flags.h
@@ -2,23 +2,24 @@
 /*
  * struct hw_perf_event.flags flags
  */
-PERF_ARCH(PEBS_LDLAT,		0x00001) /* ld+ldlat data address sampling */
-PERF_ARCH(PEBS_ST,		0x00002) /* st data address sampling */
-PERF_ARCH(PEBS_ST_HSW,		0x00004) /* haswell style datala, store */
-PERF_ARCH(PEBS_LD_HSW,		0x00008) /* haswell style datala, load */
-PERF_ARCH(PEBS_NA_HSW,		0x00010) /* haswell style datala, unknown */
-PERF_ARCH(EXCL,			0x00020) /* HT exclusivity on counter */
-PERF_ARCH(DYNAMIC,		0x00040) /* dynamic alloc'd constraint */
-			/*	0x00080	*/
-PERF_ARCH(EXCL_ACCT,		0x00100) /* accounted EXCL event */
-PERF_ARCH(AUTO_RELOAD,		0x00200) /* use PEBS auto-reload */
-PERF_ARCH(LARGE_PEBS,		0x00400) /* use large PEBS */
-PERF_ARCH(PEBS_VIA_PT,		0x00800) /* use PT buffer for PEBS */
-PERF_ARCH(PAIR,			0x01000) /* Large Increment per Cycle */
-PERF_ARCH(LBR_SELECT,		0x02000) /* Save/Restore MSR_LBR_SELECT */
-PERF_ARCH(TOPDOWN,		0x04000) /* Count Topdown slots/metrics events */
-PERF_ARCH(PEBS_STLAT,		0x08000) /* st+stlat data address sampling */
-PERF_ARCH(AMD_BRS,		0x10000) /* AMD Branch Sampling */
-PERF_ARCH(PEBS_LAT_HYBRID,	0x20000) /* ld and st lat for hybrid */
-PERF_ARCH(NEEDS_BRANCH_STACK,	0x40000) /* require branch stack setup */
-PERF_ARCH(BRANCH_COUNTERS,	0x80000) /* logs the counters in the extra space of each branch */
+PERF_ARCH(PEBS_LDLAT,		0x0000001) /* ld+ldlat data address sampling */
+PERF_ARCH(PEBS_ST,		0x0000002) /* st data address sampling */
+PERF_ARCH(PEBS_ST_HSW,		0x0000004) /* haswell style datala, store */
+PERF_ARCH(PEBS_LD_HSW,		0x0000008) /* haswell style datala, load */
+PERF_ARCH(PEBS_NA_HSW,		0x0000010) /* haswell style datala, unknown */
+PERF_ARCH(EXCL,			0x0000020) /* HT exclusivity on counter */
+PERF_ARCH(DYNAMIC,		0x0000040) /* dynamic alloc'd constraint */
+PERF_ARCH(PEBS_CNTR,		0x0000080) /* PEBS counters snapshot */
+PERF_ARCH(EXCL_ACCT,		0x0000100) /* accounted EXCL event */
+PERF_ARCH(AUTO_RELOAD,		0x0000200) /* use PEBS auto-reload */
+PERF_ARCH(LARGE_PEBS,		0x0000400) /* use large PEBS */
+PERF_ARCH(PEBS_VIA_PT,		0x0000800) /* use PT buffer for PEBS */
+PERF_ARCH(PAIR,			0x0001000) /* Large Increment per Cycle */
+PERF_ARCH(LBR_SELECT,		0x0002000) /* Save/Restore MSR_LBR_SELECT */
+PERF_ARCH(TOPDOWN,		0x0004000) /* Count Topdown slots/metrics events */
+PERF_ARCH(PEBS_STLAT,		0x0008000) /* st+stlat data address sampling */
+PERF_ARCH(AMD_BRS,		0x0010000) /* AMD Branch Sampling */
+PERF_ARCH(PEBS_LAT_HYBRID,	0x0020000) /* ld and st lat for hybrid */
+PERF_ARCH(NEEDS_BRANCH_STACK,	0x0040000) /* require branch stack setup */
+PERF_ARCH(BRANCH_COUNTERS,	0x0080000) /* logs the counters in the extra space of each branch */
+PERF_ARCH(ACR,			0x0100000) /* Auto counter reload */
diff --git a/arch/x86/events/zhaoxin/core.c b/arch/x86/events/zhaoxin/core.c
index e493b176b336ca90936ee0b88e547b3e7ba1f8eb..687c2d8a25ff01e69fa57d9bdab925f8a8e78535 100644
--- a/arch/x86/events/zhaoxin/core.c
+++ b/arch/x86/events/zhaoxin/core.c
@@ -574,13 +574,13 @@ __init int zhaoxin_pmu_init(void)
 	pr_info("Version check pass!\n");
 
 	x86_pmu.version			= version;
-	x86_pmu.num_counters		= eax.split.num_counters;
+	x86_pmu.cntr_mask64		= GENMASK_ULL(eax.split.num_counters - 1, 0);
 	x86_pmu.cntval_bits		= eax.split.bit_width;
 	x86_pmu.cntval_mask		= (1ULL << eax.split.bit_width) - 1;
 	x86_pmu.events_maskl		= ebx.full;
 	x86_pmu.events_mask_len		= eax.split.mask_length;
 
-	x86_pmu.num_counters_fixed = edx.split.num_counters_fixed;
+	x86_pmu.fixed_cntr_mask64	= GENMASK_ULL(edx.split.num_counters_fixed - 1, 0);
 	x86_add_quirk(zhaoxin_arch_events_quirk);
 
 	switch (boot_cpu_data.x86) {
@@ -674,13 +674,13 @@ __init int zhaoxin_pmu_init(void)
 		return -ENODEV;
 	}
 
-	x86_pmu.intel_ctrl = (1 << (x86_pmu.num_counters)) - 1;
-	x86_pmu.intel_ctrl |= ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
+	x86_pmu.intel_ctrl = x86_pmu.cntr_mask64;
+	x86_pmu.intel_ctrl |= x86_pmu.fixed_cntr_mask64 << INTEL_PMC_IDX_FIXED;
 
 	if (x86_pmu.event_constraints) {
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
-			c->weight += x86_pmu.num_counters;
+			c->idxmsk64 |= x86_pmu.cntr_mask64;
+			c->weight += x86_pmu_num_counters(NULL);
 		}
 	}
 
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
index 2f9eeb5c3069a1d705107f429575b2e2e688e3cd..5dbeac48a5b932e4471d23b3642ef58317e44b2c 100644
--- a/arch/x86/include/asm/intel_ds.h
+++ b/arch/x86/include/asm/intel_ds.h
@@ -9,6 +9,7 @@
 /* The maximal number of PEBS events: */
 #define MAX_PEBS_EVENTS_FMT4	8
 #define MAX_PEBS_EVENTS		32
+#define MAX_PEBS_EVENTS_MASK	GENMASK_ULL(MAX_PEBS_EVENTS - 1, 0)
 #define MAX_FIXED_PEBS_EVENTS	16
 
 /*
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e1e023df139e04a82e0272b491597285bef06457..5d63b07acb8a15ce88df068800259ed515067626 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -578,6 +578,16 @@
 #define MSR_RELOAD_PMC0			0x000014c1
 #define MSR_RELOAD_FIXED_CTR0		0x00001309
 
+/* V6 PMON MSR range */
+#define MSR_IA32_PMC_V6_GP0_CTR		0x1900
+#define MSR_IA32_PMC_V6_GP0_CFG_A	0x1901
+#define MSR_IA32_PMC_V6_GP0_CFG_B	0x1902
+#define MSR_IA32_PMC_V6_GP0_CFG_C	0x1903
+#define MSR_IA32_PMC_V6_FX0_CTR		0x1980
+#define MSR_IA32_PMC_V6_FX0_CFG_B	0x1982
+#define MSR_IA32_PMC_V6_FX0_CFG_C	0x1983
+#define MSR_IA32_PMC_V6_STEP		4
+
 /*
  * AMD64 MSRs. Not complete. See the architecture manual for a more
  * complete list.
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 6416b7bde9a52a0f91f3d1c43f9daa3bfd5c1e25..a791553605495006e41a1387931c13bb14ec5faa 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -32,6 +32,8 @@
 #define ARCH_PERFMON_EVENTSEL_INV			(1ULL << 23)
 #define ARCH_PERFMON_EVENTSEL_CMASK			0xFF000000ULL
 #define ARCH_PERFMON_EVENTSEL_BR_CNTR			(1ULL << 35)
+#define ARCH_PERFMON_EVENTSEL_EQ			(1ULL << 36)
+#define ARCH_PERFMON_EVENTSEL_UMASK2			(0xFFULL << 40)
 
 #define INTEL_FIXED_BITS_MASK				0xFULL
 #define INTEL_FIXED_BITS_STRIDE			4
@@ -39,6 +41,7 @@
 #define INTEL_FIXED_0_USER				(1ULL << 1)
 #define INTEL_FIXED_0_ANYTHREAD			(1ULL << 2)
 #define INTEL_FIXED_0_ENABLE_PMI			(1ULL << 3)
+#define INTEL_FIXED_3_METRICS_CLEAR			(1ULL << 2)
 
 #define HSW_IN_TX					(1ULL << 32)
 #define HSW_IN_TX_CHECKPOINTED				(1ULL << 33)
@@ -155,6 +158,12 @@
 #define PEBS_DATACFG_XMMS	BIT_ULL(2)
 #define PEBS_DATACFG_LBRS	BIT_ULL(3)
 #define PEBS_DATACFG_LBR_SHIFT	24
+#define PEBS_DATACFG_CNTR	BIT_ULL(4)
+#define PEBS_DATACFG_CNTR_SHIFT	32
+#define PEBS_DATACFG_CNTR_MASK	GENMASK_ULL(15, 0)
+#define PEBS_DATACFG_FIX_SHIFT	48
+#define PEBS_DATACFG_FIX_MASK	GENMASK_ULL(7, 0)
+#define PEBS_DATACFG_METRICS	BIT_ULL(5)
 
 /* Steal the highest bit of pebs_data_cfg for SW usage */
 #define PEBS_UPDATE_DS_SW	BIT_ULL(63)
@@ -203,6 +212,7 @@ union cpuid10_edx {
  */
 #define ARCH_PERFMON_EXT_LEAF			0x00000023
 #define ARCH_PERFMON_NUM_COUNTER_LEAF		0x1
+#define ARCH_PERFMON_ACR_LEAF			0x2
 
 union cpuid35_eax {
 	struct {
@@ -346,6 +356,10 @@ struct x86_pmu_capability {
 #define INTEL_PMC_IDX_FIXED_SLOTS	(INTEL_PMC_IDX_FIXED + 3)
 #define INTEL_PMC_MSK_FIXED_SLOTS	(1ULL << INTEL_PMC_IDX_FIXED_SLOTS)
 
+/* TOPDOWN_BAD_SPECULATION.ALL: fixed counter 4 (Atom only) */
+/* TOPDOWN_FE_BOUND.ALL: fixed counter 5 (Atom only) */
+/* TOPDOWN_RETIRING.ALL: fixed counter 6 (Atom only) */
+
 static inline bool use_fixed_pseudo_encoding(u64 code)
 {
 	return !(code & 0xff);
@@ -403,6 +417,9 @@ static inline bool use_fixed_pseudo_encoding(u64 code)
 #define INTEL_TD_METRIC_MAX			INTEL_TD_METRIC_MEM_BOUND
 #define INTEL_TD_METRIC_NUM			8
 
+#define INTEL_TD_CFG_METRIC_CLEAR_BIT		0
+#define INTEL_TD_CFG_METRIC_CLEAR		BIT_ULL(INTEL_TD_CFG_METRIC_CLEAR_BIT)
+
 static inline bool is_metric_idx(int idx)
 {
 	return (unsigned)(idx - INTEL_PMC_IDX_METRIC_BASE) < INTEL_TD_METRIC_NUM;
@@ -453,7 +470,9 @@ static inline bool is_topdown_idx(int idx)
  */
 
 struct pebs_basic {
-	u64 format_size;
+	u64 format_group:32,
+	    retire_latency:16,
+	    format_size:16;
 	u64 ip;
 	u64 applicable_counters;
 	u64 tsc;
@@ -462,7 +481,17 @@ struct pebs_basic {
 struct pebs_meminfo {
 	u64 address;
 	u64 aux;
-	u64 latency;
+	union {
+		/* pre Alder Lake */
+		u64 mem_latency;
+		/* Alder Lake and later */
+		struct {
+			u64 instr_latency:16;
+			u64 pad2:16;
+			u64 cache_latency:16;
+			u64 pad3:16;
+		};
+	};
 	u64 tsx_tuning;
 };
 
@@ -475,6 +504,15 @@ struct pebs_xmm {
 	u64 xmm[16*2];	/* two entries for each register */
 };
 
+struct pebs_cntr_header {
+	u32 cntr;
+	u32 fixed;
+	u32 metrics;
+	u32 reserved;
+};
+
+#define INTEL_CNTR_METRICS		0x3
+
 /*
  * AMD Extended Performance Monitoring and Debug cpuid feature detection
  */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 19e0a0a24cec135455a30a028b21a041f5185655..a069a42d54889fab0aeb752d9b29c2b6c9827105 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -145,7 +145,7 @@ struct hw_perf_event_extra {
  * PERF_EVENT_FLAG_ARCH bits are reserved for architecture-specific
  * usage.
  */
-#define PERF_EVENT_FLAG_ARCH			0x000fffff
+#define PERF_EVENT_FLAG_ARCH			0x0fffffff
 #define PERF_EVENT_FLAG_USER_READ_CNT		0x80000000
 
 static_assert((PERF_EVENT_FLAG_USER_READ_CNT & PERF_EVENT_FLAG_ARCH) == 0);
@@ -158,7 +158,9 @@ struct hw_perf_event {
 	union {
 		struct { /* hardware */
 			u64		config;
+			u64		config1;
 			u64		last_tag;
+			u64		dyn_constraint;
 			unsigned long	config_base;
 			unsigned long	event_base;
 			int		event_base_rdpmc;
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 3a64499b0f5d63734d632ab03cd1966211473d8c..4842c36fdf80199696b9e4a77d363fbcd9f3996e 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -1349,12 +1349,14 @@ union perf_mem_data_src {
 #define PERF_MEM_LVLNUM_L2	0x02 /* L2 */
 #define PERF_MEM_LVLNUM_L3	0x03 /* L3 */
 #define PERF_MEM_LVLNUM_L4	0x04 /* L4 */
-/* 5-0x7 available */
+#define PERF_MEM_LVLNUM_L2_MHB	0x05 /* L2 Miss Handling Buffer */
+#define PERF_MEM_LVLNUM_MSC	0x06 /* Memory-side Cache */
+/* 0x7 available */
 #define PERF_MEM_LVLNUM_UNC	0x08 /* Uncached */
 #define PERF_MEM_LVLNUM_CXL	0x09 /* CXL */
 #define PERF_MEM_LVLNUM_IO	0x0a /* I/O */
 #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
-#define PERF_MEM_LVLNUM_LFB	0x0c /* LFB */
+#define PERF_MEM_LVLNUM_LFB	0x0c /* LFB / L1 Miss Handling Buffer */
 #define PERF_MEM_LVLNUM_RAM	0x0d /* RAM */
 #define PERF_MEM_LVLNUM_PMEM	0x0e /* PMEM */
 #define PERF_MEM_LVLNUM_NA	0x0f /* N/A */
diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json
new file mode 100644
index 0000000000000000000000000000000000000000..875361b30f1df9e7467b2bd2d05efc0ff8f4893a
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/cache.json
@@ -0,0 +1,144 @@
+[
+    {
+        "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x2e",
+        "EventName": "LONGEST_LAT_CACHE.MISS",
+        "PublicDescription": "Counts the number of cacheable memory requests that miss in the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the core has access to an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x41"
+    },
+    {
+        "BriefDescription": "Counts the number of cacheable memory requests that access the LLC. Counts on a per core basis.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x2e",
+        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+        "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the core has access to an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x4f"
+    },
+    {
+        "BriefDescription": "Counts the number of load ops retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x81"
+    },
+    {
+        "BriefDescription": "Counts the number of store ops retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x82"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x400",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x80",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x10",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x800",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x100",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x20",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x4",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x200",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x40",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled.",
+        "Counter": "0,1",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8",
+        "MSRIndex": "0x3F6",
+        "MSRValue": "0x8",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of  stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xd0",
+        "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x6"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/counter.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/counter.json
new file mode 100644
index 0000000000000000000000000000000000000000..a0eaf5b6f2bc8dacc9a5c9ad262f98e5d37762f8
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/counter.json
@@ -0,0 +1,7 @@
+[
+    {
+        "Unit": "core",
+        "CountersNumFixed": "3",
+        "CountersNumGeneric": "39"
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/frontend.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/frontend.json
new file mode 100644
index 0000000000000000000000000000000000000000..7a9250e5c8f299fb84d723aa5ad45209d5ce98be
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/frontend.json
@@ -0,0 +1,18 @@
+[
+    {
+        "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x80",
+        "EventName": "ICACHE.ACCESSES",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x3"
+    },
+    {
+        "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are not present. -",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x80",
+        "EventName": "ICACHE.MISSES",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json
new file mode 100644
index 0000000000000000000000000000000000000000..f5007e56f39bbdd26a2dea2418f70c9f02137131
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/memory.json
@@ -0,0 +1,22 @@
+[
+    {
+        "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x33FBFC00001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.L3_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x33FBFC00002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/other.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/other.json
new file mode 100644
index 0000000000000000000000000000000000000000..80454e497f835d6a0e3b0dba52227710af2cdd9d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/other.json
@@ -0,0 +1,22 @@
+[
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json
new file mode 100644
index 0000000000000000000000000000000000000000..6a5faa704b85240f91e7f3a04e2f8b443015c4ed
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/pipeline.json
@@ -0,0 +1,113 @@
+[
+    {
+        "BriefDescription": "Counts the total number of branch instructions retired for all branch types.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc4",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires.  All branch type instructions are accounted for.",
+        "SampleAfterValue": "1000003"
+    },
+    {
+        "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc5",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+        "PublicDescription": "Counts the total number of mispredicted branch instructions retired.  All branch type instructions are accounted for.  Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP.    A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.",
+        "SampleAfterValue": "1000003"
+    },
+    {
+        "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles.",
+        "Counter": "Fixed counter 1",
+        "EventName": "CPU_CLK_UNHALTED.CORE",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Counts the number of unhalted core clock cycles. [This event is alias to CPU_CLK_UNHALTED.THREAD_P]",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x3c",
+        "EventName": "CPU_CLK_UNHALTED.CORE_P",
+        "SampleAfterValue": "1000003"
+    },
+    {
+        "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles.",
+        "Counter": "Fixed counter 2",
+        "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x3"
+    },
+    {
+        "BriefDescription": "Counts the number of unhalted reference clock cycles at TSC frequency.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x3c",
+        "EventName": "CPU_CLK_UNHALTED.REF_TSC_P",
+        "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is not affected by core frequency changes and increments at a fixed frequency that is also used for the Time Stamp Counter (TSC). This event uses a programmable general purpose performance counter.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles.",
+        "Counter": "Fixed counter 1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Counts the number of unhalted core clock cycles. [This event is alias to CPU_CLK_UNHALTED.CORE_P]",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x3c",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
+        "SampleAfterValue": "1000003"
+    },
+    {
+        "BriefDescription": "Fixed Counter: Counts the number of instructions retired.",
+        "Counter": "Fixed counter 0",
+        "EventName": "INST_RETIRED.ANY",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1"
+    },
+    {
+        "BriefDescription": "Counts the number of instructions retired.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xc0",
+        "EventName": "INST_RETIRED.ANY_P",
+        "SampleAfterValue": "1000003"
+    },
+    {
+        "BriefDescription": "Fixed Counter: Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.",
+        "Counter": "36",
+        "EventName": "TOPDOWN_BAD_SPECULATION.ALL",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x5"
+    },
+    {
+        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls. [This event is alias to TOPDOWN_BE_BOUND.ALL_P]",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa4",
+        "EventName": "TOPDOWN_BE_BOUND.ALL",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls. [This event is alias to TOPDOWN_BE_BOUND.ALL]",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0xa4",
+        "EventName": "TOPDOWN_BE_BOUND.ALL_P",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2"
+    },
+    {
+        "BriefDescription": "Fixed Counter: Counts the number of retirement slots not consumed due to front end stalls.",
+        "Counter": "37",
+        "EventName": "TOPDOWN_FE_BOUND.ALL",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x6"
+    },
+    {
+        "BriefDescription": "Fixed Counter: Counts the number of consumed retirement slots.",
+        "Counter": "38",
+        "EventName": "TOPDOWN_RETIRING.ALL",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x7"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/clearwaterforest/virtual-memory.json b/tools/perf/pmu-events/arch/x86/clearwaterforest/virtual-memory.json
new file mode 100644
index 0000000000000000000000000000000000000000..78f2b835c1fa46055f09899d30338a8b721dd9fe
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/clearwaterforest/virtual-memory.json
@@ -0,0 +1,29 @@
+[
+    {
+        "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to any page size.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x08",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0xe"
+    },
+    {
+        "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to any page size.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x49",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size.  Includes page walks that page fault.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0xe"
+    },
+    {
+        "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to any page size.",
+        "Counter": "0,1,2,3,4,5,6,7",
+        "EventCode": "0x85",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED",
+        "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size.  Includes page walks that page fault.",
+        "SampleAfterValue": "1000003",
+        "UMask": "0xe"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 3a8770e29fe80a14ab797120b4a2e4d072535f94..2e7a89c99d76e2bfa6c1fecad38648d3d7607ef9 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -6,6 +6,7 @@ GenuineIntel-6-(3D|47),v28,broadwell,core
 GenuineIntel-6-56,v10,broadwellde,core
 GenuineIntel-6-4F,v21,broadwellx,core
 GenuineIntel-6-55-[56789ABCDEF],v1.19,cascadelakex,core
+GenuineIntel-6-DD,v1.00,clearwaterforest,core
 GenuineIntel-6-9[6C],v1.04,elkhartlake,core
 GenuineIntel-6-5[CF],v13,goldmont,core
 GenuineIntel-6-7A,v1.01,goldmontplus,core