Merge tag 'perf-core-2024-07-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull performance events updates from Ingo Molnar:

 - Intel PT support enhancements & fixes

 - Fix leaked SIGTRAP events

 - Improve and fix the Intel uncore driver

 - Add support for Intel HBM and CXL uncore counters

 - Add Intel Lake and Arrow Lake support

 - AMD uncore driver fixes

 - Make SIGTRAP and __perf_pending_irq() work on RT

 - Micro-optimizations

 - Misc cleanups and fixes

* tag 'perf-core-2024-07-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits)
  perf/x86/intel: Add a distinct name for Granite Rapids
  perf/x86/intel/ds: Fix non 0 retire latency on Raptorlake
  perf/x86/intel: Hide Topdown metrics events if the feature is not enumerated
  perf/x86/intel/uncore: Fix the bits of the CHA extended umask for SPR
  perf: Split __perf_pending_irq() out of perf_pending_irq()
  perf: Don't disable preemption in perf_pending_task().
  perf: Move swevent_htable::recursion into task_struct.
  perf: Shrink the size of the recursion counter.
  perf: Enqueue SIGTRAP always via task_work.
  task_work: Add TWA_NMI_CURRENT as an additional notify mode.
  perf: Move irq_work_queue() where the event is prepared.
  perf: Fix event leak upon exec and file release
  perf: Fix event leak upon exit
  task_work: Introduce task_work_cancel() again
  task_work: s/task_work_cancel()/task_work_cancel_func()/
  perf/x86/amd/uncore: Fix DF and UMC domain identification
  perf/x86/amd/uncore: Avoid PMU registration if counters are unavailable
  perf/x86/intel: Support Perfmon MSRs aliasing
  perf/x86/intel: Support PERFEVTSEL extension
  perf/x86: Add config_mask to represent EVENTSEL bitmask
  ...

32 files changed, 1256 insertions, 507 deletions

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 1fc4ce44e743..920e3a640cad 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -432,8 +432,10 @@ 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++) {
-		if (cmpxchg(nb->owners + i, event, NULL) == event)
+	for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+		struct perf_event *tmp = event;
+
+		if (try_cmpxchg(nb->owners + i, &tmp, NULL))
 			break;
 	}
 }
@@ -499,7 +501,7 @@ __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);
@@ -542,7 +544,7 @@ 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;
 	}
@@ -735,7 +737,7 @@ 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;
 
@@ -755,7 +757,7 @@ 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;
@@ -978,7 +980,7 @@ 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;
 
@@ -1313,7 +1315,7 @@ 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,
@@ -1412,7 +1414,7 @@ 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)) {
@@ -1422,9 +1424,9 @@ 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;
@@ -1452,12 +1454,12 @@ 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/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 4ccb8fa483e6..0bfde2ea5cb8 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -162,7 +162,9 @@ static int amd_uncore_add(struct perf_event *event, int flags)
 	/* if not, take the first available counter */
 	hwc->idx = -1;
 	for (i = 0; i < pmu->num_counters; i++) {
-		if (cmpxchg(&ctx->events[i], NULL, event) == NULL) {
+		struct perf_event *tmp = NULL;
+
+		if (try_cmpxchg(&ctx->events[i], &tmp, event)) {
 			hwc->idx = i;
 			break;
 		}
@@ -196,7 +198,9 @@ static void amd_uncore_del(struct perf_event *event, int flags)
 	event->pmu->stop(event, PERF_EF_UPDATE);
 
 	for (i = 0; i < pmu->num_counters; i++) {
-		if (cmpxchg(&ctx->events[i], event, NULL) == event)
+		struct perf_event *tmp = event;
+
+		if (try_cmpxchg(&ctx->events[i], &tmp, NULL))
 			break;
 	}
 
@@ -639,7 +643,7 @@ void amd_uncore_df_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
 	info.split.aux_data = 0;
 	info.split.num_pmcs = NUM_COUNTERS_NB;
 	info.split.gid = 0;
-	info.split.cid = topology_die_id(cpu);
+	info.split.cid = topology_logical_package_id(cpu);
 
 	if (pmu_version >= 2) {
 		ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES);
@@ -654,17 +658,20 @@ int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 {
 	struct attribute **df_attr = amd_uncore_df_format_attr;
 	struct amd_uncore_pmu *pmu;
+	int num_counters;
 
 	/* Run just once */
 	if (uncore->init_done)
 		return amd_uncore_ctx_init(uncore, cpu);
 
+	num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+	if (!num_counters)
+		goto done;
+
 	/* No grouping, single instance for a system */
 	uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
-	if (!uncore->pmus) {
-		uncore->num_pmus = 0;
+	if (!uncore->pmus)
 		goto done;
-	}
 
 	/*
 	 * For Family 17h and above, the Northbridge counters are repurposed
@@ -674,7 +681,7 @@ int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 	pmu = &uncore->pmus[0];
 	strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_df" : "amd_nb",
 		sizeof(pmu->name));
-	pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+	pmu->num_counters = num_counters;
 	pmu->msr_base = MSR_F15H_NB_PERF_CTL;
 	pmu->rdpmc_base = RDPMC_BASE_NB;
 	pmu->group = amd_uncore_ctx_gid(uncore, cpu);
@@ -785,17 +792,20 @@ int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 {
 	struct attribute **l3_attr = amd_uncore_l3_format_attr;
 	struct amd_uncore_pmu *pmu;
+	int num_counters;
 
 	/* Run just once */
 	if (uncore->init_done)
 		return amd_uncore_ctx_init(uncore, cpu);
 
+	num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+	if (!num_counters)
+		goto done;
+
 	/* No grouping, single instance for a system */
 	uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
-	if (!uncore->pmus) {
-		uncore->num_pmus = 0;
+	if (!uncore->pmus)
 		goto done;
-	}
 
 	/*
 	 * For Family 17h and above, L3 cache counters are available instead
@@ -805,7 +815,7 @@ int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 	pmu = &uncore->pmus[0];
 	strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_l3" : "amd_l2",
 		sizeof(pmu->name));
-	pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+	pmu->num_counters = num_counters;
 	pmu->msr_base = MSR_F16H_L2I_PERF_CTL;
 	pmu->rdpmc_base = RDPMC_BASE_LLC;
 	pmu->group = amd_uncore_ctx_gid(uncore, cpu);
@@ -893,8 +903,8 @@ void amd_uncore_umc_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
 	cpuid(EXT_PERFMON_DEBUG_FEATURES, &eax, &ebx.full, &ecx, &edx);
 	info.split.aux_data = ecx;	/* stash active mask */
 	info.split.num_pmcs = ebx.split.num_umc_pmc;
-	info.split.gid = topology_die_id(cpu);
-	info.split.cid = topology_die_id(cpu);
+	info.split.gid = topology_logical_package_id(cpu);
+	info.split.cid = topology_logical_package_id(cpu);
 	*per_cpu_ptr(uncore->info, cpu) = info;
 }
 
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index acd367c45334..12f2a0c14d33 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -189,29 +189,31 @@ 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;
 	}
@@ -219,13 +221,14 @@ 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;
@@ -233,9 +236,10 @@ perfctr_fail:
 
 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));
 	}
@@ -248,7 +252,8 @@ 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;
@@ -259,7 +264,7 @@ 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)
@@ -273,12 +278,12 @@ 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)) {
@@ -619,7 +624,7 @@ 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 (event->attr.sample_period && x86_pmu.limit_period) {
 		s64 left = event->attr.sample_period;
@@ -679,7 +684,7 @@ 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;
 
@@ -736,7 +741,7 @@ 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))
@@ -975,7 +980,6 @@ 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;
@@ -1051,7 +1055,7 @@ 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
@@ -1072,7 +1076,7 @@ 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);
 		}
 
@@ -1157,12 +1161,10 @@ 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;
@@ -1234,8 +1236,7 @@ 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;
@@ -1522,13 +1523,13 @@ 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);
@@ -1555,7 +1556,7 @@ 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);
 
@@ -1568,10 +1569,10 @@ 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);
@@ -1682,7 +1683,7 @@ 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;
 
@@ -2038,18 +2039,15 @@ 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)
@@ -2086,7 +2084,7 @@ 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);
@@ -2097,14 +2095,17 @@ 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;
 
@@ -2113,11 +2114,8 @@ 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;
@@ -2481,10 +2479,10 @@ 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);
 		}
@@ -2986,8 +2984,8 @@ 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 0e835dc134a5..0c9c2706d4ec 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -220,6 +220,17 @@ static struct event_constraint intel_grt_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 */
@@ -370,6 +381,55 @@ 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");
@@ -2874,26 +2934,26 @@ 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_fi