Adding upstream version 6.10.6.upstream/6.10.6upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

16 files changed, 281 insertions, 222 deletions

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 1fc4ce44e7..920e3a640c 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 5a4bfe9aea..0bfde2ea5c 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;
 	}
 
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index acd367c453..83d12dd3f8 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)) {
@@ -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;
@@ -1519,19 +1521,22 @@ static void x86_pmu_start(struct perf_event *event, int flags)
 void perf_event_print_debug(void)
 {
 	u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed;
+	unsigned long *cntr_mask, *fixed_cntr_mask;
+	struct event_constraint *pebs_constraints;
+	struct cpu_hw_events *cpuc;
 	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);
-	struct event_constraint *pebs_constraints = hybrid(cpuc->pmu, pebs_constraints);
-	unsigned long flags;
-	int idx;
+	int cpu, idx;
 
-	if (!num_counters)
-		return;
+	guard(irqsave)();
+
+	cpu = smp_processor_id();
+	cpuc = &per_cpu(cpu_hw_events, cpu);
+	cntr_mask = hybrid(cpuc->pmu, cntr_mask);
+	fixed_cntr_mask = hybrid(cpuc->pmu, fixed_cntr_mask);
+	pebs_constraints = hybrid(cpuc->pmu, pebs_constraints);
 
-	local_irq_save(flags);
+	if (!*(u64 *)cntr_mask)
+		return;
 
 	if (x86_pmu.version >= 2) {
 		rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, ctrl);
@@ -1555,7 +1560,7 @@ 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);
 
@@ -1568,7 +1573,7 @@ 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);
@@ -1576,7 +1581,6 @@ void perf_event_print_debug(void)
 		pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
 			cpu, idx, pmc_count);
 	}
-	local_irq_restore(flags);
 }
 
 void x86_pmu_stop(struct perf_event *event, int flags)
@@ -1682,7 +1686,7 @@ 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 +2042,15 @@ 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 +2087,7 @@ 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 +2098,14 @@ 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;
 
 	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;
@@ -2481,7 +2479,7 @@ 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);
@@ -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 101a21fe9c..f25205d047 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2874,23 +2874,23 @@ 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);
@@ -2940,8 +2940,7 @@ 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;
@@ -4199,7 +4198,7 @@ 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);
@@ -4217,7 +4216,7 @@ 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;
 }
 
@@ -4232,7 +4231,7 @@ 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) ||
@@ -4684,13 +4683,33 @@ 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);
@@ -4713,11 +4732,10 @@ static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
 	if (sub_bitmaps & ARCH_PERFMON_NUM_COUNTER_LEAF_BIT) {
 		cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF,
 			    &eax, &ebx, &ecx, &edx);
-		pmu->num_counters = fls(eax);
-		pmu->num_counters_fixed = fls(ebx);
+		pmu->cntr_mask64 = eax;
+		pmu->fixed_cntr_mask64 = ebx;
 	}
 
-
 	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);
@@ -4726,12 +4744,12 @@ static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
 
 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;
@@ -4744,8 +4762,8 @@ 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);
@@ -4806,7 +4824,7 @@ static bool init_hybrid_pmu(int cpu)
 
 	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);
@@ -4816,8 +4834,7 @@ 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);
@@ -5955,29 +5972,9 @@ 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;
@@ -6014,10 +6011,9 @@ 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);
 	}
 }
@@ -6068,12 +6064,12 @@ 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->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) {
@@ -6186,14 +6182,14 @@ __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;
 
 	/*
@@ -6203,12 +6199,10 @@ __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;
@@ -6807,11 +6801,13 @@ __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;
 		}
 
 		/*
@@ -6821,15 +6817,16 @@ __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.*/
@@ -6896,9 +6893,9 @@ __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+";
@@ -6925,18 +6922,17 @@ __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);
+	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.
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index dd18320558..9f116dfc47 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -41,7 +41,7 @@
  *	MSR_CORE_C1_RES: CORE C1 Residency Counter
  *			 perf code: 0x00
  *			 Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL
- *					  MTL,SRF,GRR
+ *					  MTL,SRF,GRR,ARL,LNL
  *			 Scope: Core (each processor core has a MSR)
  *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
  *			       perf code: 0x01
@@ -53,30 +53,31 @@
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
  *						SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
  *						TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF,
- *						GRR
+ *						GRR,ARL,LNL
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
  *			       Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML,
- *						ICL,TGL,RKL,ADL,RPL,MTL
+ *						ICL,TGL,RKL,ADL,RPL,MTL,ARL,LNL
  *			       Scope: Core
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
  *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
  *						KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL,
- *						RPL,SPR,MTL
+ *						RPL,SPR,MTL,ARL,LNL,SRF
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
  *						GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL,
- *						ADL,RPL,MTL
+ *						ADL,RPL,MTL,ARL,LNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
  *						SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
- *						TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF
+ *						TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF,
+ *						ARL,LNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
@@ -86,7 +87,7 @@
  *	MSR_PKG_C8_RESIDENCY:  Package C8 Residency Counter.
  *			       perf code: 0x04
  *			       Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- *						ADL,RPL,MTL
+ *						ADL,RPL,MTL,ARL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C9_RESIDENCY:  Package C9 Residency Counter.
  *			       perf code: 0x05
@@ -95,7 +96,7 @@
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
  *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
- *						TNT,RKL,ADL,RPL,MTL
+ *						TNT,RKL,ADL,RPL,MTL,ARL,LNL
  *			       Scope: Package (physical package)
  *	MSR_MODULE_C6_RES_MS:  Module C6 Residency Counter.
  *			       perf code: 0x00
@@ -640,6 +641,17 @@ static const struct cstate_model adl_cstates __initconst = {
 				  BIT(PERF_CSTATE_PKG_C10_RES),
 };
 
+static const struct cstate_model lnl_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
+				  BIT(PERF_CSTATE_CORE_C6_RES) |
+				  BIT(PERF_CSTATE_CORE_C7_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C3_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES) |
+				  BIT(PERF_CSTATE_PKG_C10_RES),
+};
+
 static const struct cstate_model slm_cstates __initconst = {
 	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
 				  BIT(PERF_CSTATE_CORE_C6_RES),
@@ -681,7 +693,8 @@ static const struct cstate_model srf_cstates __initconst = {
 	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
 				  BIT(PERF_CSTATE_CORE_C6_RES),
 
-	.pkg_events		= BIT(PERF_CSTATE_PKG_C6_RES),
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES),
 
 	.module_events		= BIT(PERF_CSTATE_MODULE_C6_RES),
 };
@@ -760,6 +773,10 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_MATCH_VFM(INTEL_RAPTORLAKE_S,	&adl_cstates),
 	X86_MATCH_VFM(INTEL_METEORLAKE,		&adl_cstates),
 	X86_MATCH_VFM(INTEL_METEORLAKE_L,	&adl_cstates),
+	X86_MATCH_VFM(INTEL_ARROWLAKE,		&adl_cstates),
+	X86_MATCH_VFM(INTEL_ARROWLAKE_H,	&adl_cstates),
+	X86_MATCH_VFM(INTEL_ARROWLAKE_U,	&adl_cstates),
+	X86_MATCH_VFM(INTEL_LUNARLAKE_M,	&lnl_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 80a4f71221..9212053f6f 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1137,8 +1137,7 @@ 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;
 
@@ -1146,7 +1145,7 @@ 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;
 
@@ -2161,6 +2160,7 @@ 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;
 
@@ -2172,11 +2172,11 @@ 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)) {
@@ -2212,8 +2212,9 @@ 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;
 
 		/*
@@ -2271,12 +2272,10 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 {
 	short counts[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 perf_event *event;
 	void *base, *at, *top;
-	int bit, size;
+	int bit;
 	u64 mask;
 
 	if (!x86_pmu.pebs_active)
@@ -2287,12 +2286,11 @@ 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;
 	}
 
@@ -2302,11 +2300,11 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 		pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
 		pebs_status &= mask;
 
-		for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
+		for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX)
 			counts[bit]++;
 	}
 
-	for_each_set_bit(bit, (unsigned long *)&mask, size) {
+	for_each_set_bit(bit, (unsigned long *)&mask, X86_PMC_IDX_MAX) {
 		if (counts[bit] == 0)
 			continue;
 
diff --git a/arch/x86/events/intel/knc.c b/arch/x86/events/intel/knc.c
index 618001c208..034a1f6a45 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/p4.c b/arch/x86/events/intel/p4.c
index 35936188db..844bc4fc47 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 408879b0c0..a6cffb4f4e 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/perf_event.h b/arch/x86/events/perf_event.h
index 72b022a1e1..745c174fc8 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -684,9 +684,15 @@ 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;
+	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)];
+	};
 	struct event_constraint		unconstrained;
 
 	u64				hw_cache_event_ids
@@ -774,8 +780,14 @@ struct x86_pmu {
 	int		(*rdpmc_index)(int index);
 	u64		(*event_map)(int);
 	int		max_events;
-	int		num_counters;
-	int		num_counters_fixed;
+	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)];
+	};
 	int		cntval_bits;
 	u64		cntval_mask;
 	union {
@@ -852,7 +864,7 @@ 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);
@@ -1125,8 +1137,8 @@ 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);
 
@@ -1197,8 +1209,27 @@ 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));
+}
 
 extern struct event_constraint emptyconstraint;
 
@@ -1661,6 +1692,17 @@ 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/zhaoxin/core.c b/arch/x86/events/zhaoxin/core.c
index 3e9acdaeed..2fd9b0cf9a 100644
--- a/arch/x86/events/zhaoxin/core.c
+++ b/arch/x86/events/zhaoxin/core.c
@@ -530,13 +530,13 @@ __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) {
@@ -604,13 +604,13 @@ __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 2f9eeb5c30..5dbeac48a5 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/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index a053c12939..68da67df30 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -66,13 +66,15 @@ static inline bool vcpu_is_preempted(long cpu)
 
 #ifdef CONFIG_PARAVIRT
 /*
- * virt_spin_lock_key - enables (by default) the virt_spin_lock() hijack.
+ * virt_spin_lock_key - disables by default the virt_spin_lock() hijack.
  *
- * Native (and PV wanting native due to vCPU pinning) should disable this key.
- * It is done in this backwards fashion to only have a single direction change,
- * which removes ordering between native_pv_spin_init() and HV setup.
+ * Native (and PV wanting native due to vCPU pinning) should keep this key
+ * disabled. Native does not touch the key.
+ *
+ * When in a guest then native_pv_lock_init() enables the key first and
+ * KVM/XEN might conditionally disable it later in the boot process again.
  */
-DECLARE_STATIC_KEY_TRUE(virt_spin_lock_key);
+DECLARE_STATIC_KEY_FALSE(virt_spin_lock_key);
 
 /*
  * Shortcut for the queued_spin_lock_slowpath() function that allows
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c
index 767bf1c71a..2a2fc14955 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.c
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.c
@@ -609,7 +609,7 @@ void mtrr_save_state(void)
 {
 	int first_cpu;
 
-	if (!mtrr_enabled())
+	if (!mtrr_enabled() || !mtrr_state.have_fixed)
 		return;
 
 	first_cpu = cpumask_first(cpu_online_mask);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 5358d43886..fec3815335 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -51,13 +51,12 @@ DEFINE_ASM_FUNC(pv_native_irq_enable, "sti", .noinstr.text);
 DEFINE_ASM_FUNC(pv_native_read_cr2, "mov %cr2, %rax", .noinstr.text);
 #endif
 
-DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
+DEFINE_STATIC_KEY_FALSE(virt_spin_lock_key);
 
 void __init native_pv_lock_init(void)
 {
-	if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) &&
-	    !boot_cpu_has(X86_FEATURE_HYPERVISOR))
-		static_branch_disable(&virt_spin_lock_key);
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		static_branch_enable(&virt_spin_lock_key);
 }
 
 static void native_tlb_remove_table(struct mmu_gather *tlb, void *table)
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 2e69abf4f8..bfdf5f45b1 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -374,14 +374,14 @@ pti_clone_pgtable(unsigned long start, unsigned long end,
 			 */
 			*target_pmd = *pmd;
 
-			addr += PMD_SIZE;
+			addr = round_up(addr + 1, PMD_SIZE);
 
 		} else if (level == PTI_CLONE_PTE) {
 
 			/* Walk the page-table down to the pte level */
 			pte = pte_offset_kernel(pmd, addr);
 			if (pte_none(*pte)) {
-				addr += PAGE_SIZE;
+				addr = round_up(addr + 1, PAGE_SIZE);
 				continue;
 			}
 
@@ -401,7 +401,7 @@ pti_clone_pgtable(unsigned long start, unsigned long end,
 			/* Clone the PTE */
 			*target_pte = *pte;
 
-			addr += PAGE_SIZE;
+			addr = round_up(addr + 1, PAGE_SIZE);
 
 		} else {
 			BUG();
@@ -496,7 +496,7 @@ static void pti_clone_entry_text(void)
 {
 	pti_clone_pgtable((unsigned long) __entry_text_start,
 			  (unsigned long) __entry_text_end,
-			  PTI_CLONE_PMD);
+			  PTI_LEVEL_KERNEL_IMAGE);
 }
 
 /*