1 files changed, 257 insertions, 75 deletions

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 4c31cae4707e..8e509325c2c3 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -45,13 +45,16 @@
 #include "perf_event.h"
 
 struct x86_pmu x86_pmu __read_mostly;
+static struct pmu pmu;
 
 DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
 	.enabled = 1,
+	.pmu = &pmu,
 };
 
 DEFINE_STATIC_KEY_FALSE(rdpmc_never_available_key);
 DEFINE_STATIC_KEY_FALSE(rdpmc_always_available_key);
+DEFINE_STATIC_KEY_FALSE(perf_is_hybrid);
 
 /*
  * This here uses DEFINE_STATIC_CALL_NULL() to get a static_call defined
@@ -151,15 +154,16 @@ again:
  */
 static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
 {
+	struct extra_reg *extra_regs = hybrid(event->pmu, extra_regs);
 	struct hw_perf_event_extra *reg;
 	struct extra_reg *er;
 
 	reg = &event->hw.extra_reg;
 
-	if (!x86_pmu.extra_regs)
+	if (!extra_regs)
 		return 0;
 
-	for (er = x86_pmu.extra_regs; er->msr; er++) {
+	for (er = extra_regs; er->msr; er++) {
 		if (er->event != (config & er->config_mask))
 			continue;
 		if (event->attr.config1 & ~er->valid_mask)
@@ -182,16 +186,29 @@ static DEFINE_MUTEX(pmc_reserve_mutex);
 
 #ifdef CONFIG_X86_LOCAL_APIC
 
+static inline int get_possible_num_counters(void)
+{
+	int i, num_counters = x86_pmu.num_counters;
+
+	if (!is_hybrid())
+		return num_counters;
+
+	for (i = 0; i < x86_pmu.num_hybrid_pmus; i++)
+		num_counters = max_t(int, num_counters, x86_pmu.hybrid_pmu[i].num_counters);
+
+	return num_counters;
+}
+
 static bool reserve_pmc_hardware(void)
 {
-	int i;
+	int i, num_counters = get_possible_num_counters();
 
-	for (i = 0; i < x86_pmu.num_counters; i++) {
+	for (i = 0; i < num_counters; i++) {
 		if (!reserve_perfctr_nmi(x86_pmu_event_addr(i)))
 			goto perfctr_fail;
 	}
 
-	for (i = 0; i < x86_pmu.num_counters; i++) {
+	for (i = 0; i < num_counters; i++) {
 		if (!reserve_evntsel_nmi(x86_pmu_config_addr(i)))
 			goto eventsel_fail;
 	}
@@ -202,7 +219,7 @@ eventsel_fail:
 	for (i--; i >= 0; i--)
 		release_evntsel_nmi(x86_pmu_config_addr(i));
 
-	i = x86_pmu.num_counters;
+	i = num_counters;
 
 perfctr_fail:
 	for (i--; i >= 0; i--)
@@ -213,9 +230,9 @@ perfctr_fail:
 
 static void release_pmc_hardware(void)
 {
-	int i;
+	int i, num_counters = get_possible_num_counters();
 
-	for (i = 0; i < x86_pmu.num_counters; i++) {
+	for (i = 0; i < num_counters; i++) {
 		release_perfctr_nmi(x86_pmu_event_addr(i));
 		release_evntsel_nmi(x86_pmu_config_addr(i));
 	}
@@ -228,7 +245,7 @@ static void release_pmc_hardware(void) {}
 
 #endif
 
-static bool check_hw_exists(void)
+bool check_hw_exists(struct pmu *pmu, int num_counters, int num_counters_fixed)
 {
 	u64 val, val_fail = -1, val_new= ~0;
 	int i, reg, reg_fail = -1, ret = 0;
@@ -239,7 +256,7 @@ static bool check_hw_exists(void)
 	 * Check to see if the BIOS enabled any of the counters, if so
 	 * complain and bail.
 	 */
-	for (i = 0; i < x86_pmu.num_counters; i++) {
+	for (i = 0; i < num_counters; i++) {
 		reg = x86_pmu_config_addr(i);
 		ret = rdmsrl_safe(reg, &val);
 		if (ret)
@@ -253,15 +270,15 @@ static bool check_hw_exists(void)
 		}
 	}
 
-	if (x86_pmu.num_counters_fixed) {
+	if (num_counters_fixed) {
 		reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
 		ret = rdmsrl_safe(reg, &val);
 		if (ret)
 			goto msr_fail;
-		for (i = 0; i < x86_pmu.num_counters_fixed; i++) {
-			if (fixed_counter_disabled(i))
+		for (i = 0; i < num_counters_fixed; i++) {
+			if (fixed_counter_disabled(i, pmu))
 				continue;
-			if (val & (0x03 << i*4)) {
+			if (val & (0x03ULL << i*4)) {
 				bios_fail = 1;
 				val_fail = val;
 				reg_fail = reg;
@@ -360,8 +377,7 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event)
 		return -EINVAL;
 	cache_result = array_index_nospec(cache_result, PERF_COUNT_HW_CACHE_RESULT_MAX);
 
-	val = hw_cache_event_ids[cache_type][cache_op][cache_result];
-
+	val = hybrid_var(event->pmu, hw_cache_event_ids)[cache_type][cache_op][cache_result];
 	if (val == 0)
 		return -ENOENT;
 
@@ -369,7 +385,7 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event)
 		return -EINVAL;
 
 	hwc->config |= val;
-	attr->config1 = hw_cache_extra_regs[cache_type][cache_op][cache_result];
+	attr->config1 = hybrid_var(event->pmu, hw_cache_extra_regs)[cache_type][cache_op][cache_result];
 	return x86_pmu_extra_regs(val, event);
 }
 
@@ -462,7 +478,7 @@ int x86_setup_perfctr(struct perf_event *event)
 		local64_set(&hwc->period_left, hwc->sample_period);
 	}
 
-	if (attr->type == PERF_TYPE_RAW)
+	if (attr->type == event->pmu->type)
 		return x86_pmu_extra_regs(event->attr.config, event);
 
 	if (attr->type == PERF_TYPE_HW_CACHE)
@@ -597,7 +613,7 @@ int x86_pmu_hw_config(struct perf_event *event)
 	if (!event->attr.exclude_kernel)
 		event->hw.config |= ARCH_PERFMON_EVENTSEL_OS;
 
-	if (event->attr.type == PERF_TYPE_RAW)
+	if (event->attr.type == event->pmu->type)
 		event->hw.config |= event->attr.config & X86_RAW_EVENT_MASK;
 
 	if (event->attr.sample_period && x86_pmu.limit_period) {
@@ -724,16 +740,33 @@ void x86_pmu_enable_all(int added)
 	}
 }
 
-static struct pmu pmu;
-
 static inline int is_x86_event(struct perf_event *event)
 {
-	return event->pmu == &pmu;
+	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;
+	}
+
+	return false;
 }
 
-struct pmu *x86_get_pmu(void)
+struct pmu *x86_get_pmu(unsigned int cpu)
 {
-	return &pmu;
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+
+	/*
+	 * All CPUs of the hybrid type have been offline.
+	 * The x86_get_pmu() should not be invoked.
+	 */
+	if (WARN_ON_ONCE(!cpuc->pmu))
+		return &pmu;
+
+	return cpuc->pmu;
 }
 /*
  * Event scheduler state:
@@ -936,6 +969,7 @@ 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;
@@ -1011,7 +1045,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 
 	/* slow path */
 	if (i != n) {
-		int gpmax = x86_pmu.num_counters;
+		int gpmax = num_counters;
 
 		/*
 		 * Do not allow scheduling of more than half the available
@@ -1032,7 +1066,7 @@ 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 = x86_pmu.num_counters - cpuc->n_pair;
+			gpmax = num_counters - cpuc->n_pair;
 			WARN_ON(gpmax <= 0);
 		}
 
@@ -1096,8 +1130,9 @@ static void del_nr_metric_event(struct cpu_hw_events *cpuc,
 static int collect_event(struct cpu_hw_events *cpuc, struct perf_event *event,
 			 int max_count, int n)
 {
+	union perf_capabilities intel_cap = hybrid(cpuc->pmu, intel_cap);
 
-	if (x86_pmu.intel_cap.perf_metrics && add_nr_metric_event(cpuc, event))
+	if (intel_cap.perf_metrics && add_nr_metric_event(cpuc, event))
 		return -EINVAL;
 
 	if (n >= max_count + cpuc->n_metric)
@@ -1118,10 +1153,12 @@ 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 = x86_pmu.num_counters + x86_pmu.num_counters_fixed;
+	max_count = num_counters + num_counters_fixed;
 
 	/* current number of events already accepted */
 	n = cpuc->n_events;
@@ -1480,7 +1517,6 @@ static void x86_pmu_start(struct perf_event *event, int flags)
 
 	cpuc->events[idx] = event;
 	__set_bit(idx, cpuc->active_mask);
-	__set_bit(idx, cpuc->running);
 	static_call(x86_pmu_enable)(event);
 	perf_event_update_userpage(event);
 }
@@ -1489,18 +1525,19 @@ void perf_event_print_debug(void)
 {
 	u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed;
 	u64 pebs, debugctl;
-	struct cpu_hw_events *cpuc;
+	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 cpu, idx;
+	int idx;
 
-	if (!x86_pmu.num_counters)
+	if (!num_counters)
 		return;
 
 	local_irq_save(flags);
 
-	cpu = smp_processor_id();
-	cpuc = &per_cpu(cpu_hw_events, cpu);
-
 	if (x86_pmu.version >= 2) {
 		rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, ctrl);
 		rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
@@ -1512,7 +1549,7 @@ void perf_event_print_debug(void)
 		pr_info("CPU#%d: status:     %016llx\n", cpu, status);
 		pr_info("CPU#%d: overflow:   %016llx\n", cpu, overflow);
 		pr_info("CPU#%d: fixed:      %016llx\n", cpu, fixed);
-		if (x86_pmu.pebs_constraints) {
+		if (pebs_constraints) {
 			rdmsrl(MSR_IA32_PEBS_ENABLE, pebs);
 			pr_info("CPU#%d: pebs:       %016llx\n", cpu, pebs);
 		}
@@ -1523,7 +1560,7 @@ void perf_event_print_debug(void)
 	}
 	pr_info("CPU#%d: active:     %016llx\n", cpu, *(u64 *)cpuc->active_mask);
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for (idx = 0; idx < num_counters; idx++) {
 		rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl);
 		rdmsrl(x86_pmu_event_addr(idx), pmc_count);
 
@@ -1536,8 +1573,8 @@ void perf_event_print_debug(void)
 		pr_info("CPU#%d:   gen-PMC%d left:  %016llx\n",
 			cpu, idx, prev_left);
 	}
-	for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) {
-		if (fixed_counter_disabled(idx))
+	for (idx = 0; idx < num_counters_fixed; idx++) {
+		if (fixed_counter_disabled(idx, cpuc->pmu))
 			continue;
 		rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);
 
@@ -1573,6 +1610,7 @@ void x86_pmu_stop(struct perf_event *event, int flags)
 static void x86_pmu_del(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	union perf_capabilities intel_cap = hybrid(cpuc->pmu, intel_cap);
 	int i;
 
 	/*
@@ -1612,7 +1650,7 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 	}
 	cpuc->event_constraint[i-1] = NULL;
 	--cpuc->n_events;
-	if (x86_pmu.intel_cap.perf_metrics)
+	if (intel_cap.perf_metrics)
 		del_nr_metric_event(cpuc, event);
 
 	perf_event_update_userpage(event);
@@ -1822,6 +1860,49 @@ ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
 			pmu_attr->event_str_noht);
 }
 
+ssize_t events_hybrid_sysfs_show(struct device *dev,
+				 struct device_attribute *attr,
+				 char *page)
+{
+	struct perf_pmu_events_hybrid_attr *pmu_attr =
+		container_of(attr, struct perf_pmu_events_hybrid_attr, attr);
+	struct x86_hybrid_pmu *pmu;
+	const char *str, *next_str;
+	int i;
+
+	if (hweight64(pmu_attr->pmu_type) == 1)
+		return sprintf(page, "%s", pmu_attr->event_str);
+
+	/*
+	 * Hybrid PMUs may support the same event name, but with different
+	 * event encoding, e.g., the mem-loads event on an Atom PMU has
+	 * different event encoding from a Core PMU.
+	 *
+	 * The event_str includes all event encodings. Each event encoding
+	 * is divided by ";". The order of the event encodings must follow
+	 * the order of the hybrid PMU index.
+	 */
+	pmu = container_of(dev_get_drvdata(dev), struct x86_hybrid_pmu, pmu);
+
+	str = pmu_attr->event_str;
+	for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) {
+		if (!(x86_pmu.hybrid_pmu[i].cpu_type & pmu_attr->pmu_type))
+			continue;
+		if (x86_pmu.hybrid_pmu[i].cpu_type & pmu->cpu_type) {
+			next_str = strchr(str, ';');
+			if (next_str)
+				return snprintf(page, next_str - str + 1, "%s", str);
+			else
+				return sprintf(page, "%s", str);
+		}
+		str = strchr(str, ';');
+		str++;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(events_hybrid_sysfs_show);
+
 EVENT_ATTR(cpu-cycles,			CPU_CYCLES		);
 EVENT_ATTR(instructions,		INSTRUCTIONS		);
 EVENT_ATTR(cache-references,		CACHE_REFERENCES	);
@@ -1948,6 +2029,37 @@ static void _x86_pmu_read(struct perf_event *event)
 	x86_perf_event_update(event);
 }
 
+void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed,
+			  u64 intel_ctrl)
+{
+	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("... 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);
+}
+
+/*
+ * The generic code is not hybrid friendly. The hybrid_pmu->pmu
+ * of the first registered PMU is unconditionally assigned to
+ * each possible cpuctx->ctx.pmu.
+ * Update the correct hybrid PMU to the cpuctx->ctx.pmu.
+ */
+void x86_pmu_update_cpu_context(struct pmu *pmu, int cpu)
+{
+	struct perf_cpu_context *cpuctx;
+
+	if (!pmu->pmu_cpu_context)
+		return;
+
+	cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
+	cpuctx->ctx.pmu = pmu;
+}
+
 static int __init init_hw_perf_events(void)
 {
 	struct x86_pmu_quirk *quirk;
@@ -1981,7 +2093,7 @@ static int __init init_hw_perf_events(void)
 	pmu_check_apic();
 
 	/* sanity check that the hardware exists or is emulated */
-	if (!check_hw_exists())
+	if (!check_hw_exists(&pmu, x86_pmu.num_counters, x86_pmu.num_counters_fixed))
 		return 0;
 
 	pr_cont("%s PMU driver.\n", x86_pmu.name);
@@ -2008,15 +2120,11 @@ static int __init init_hw_perf_events(void)
 
 	pmu.attr_update = x86_pmu.attr_update;
 
-	pr_info("... version:                %d\n",     x86_pmu.version);
-	pr_info("... bit width:              %d\n",     x86_pmu.cntval_bits);
-	pr_info("... generic registers:      %d\n",     x86_pmu.num_counters);
-	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 << x86_pmu.num_counters_fixed) - 1)
-					<< INTEL_PMC_IDX_FIXED) & x86_pmu.intel_ctrl));
-	pr_info("... event mask:             %016Lx\n", x86_pmu.intel_ctrl);
+	if (!is_hybrid()) {
+		x86_pmu_show_pmu_cap(x86_pmu.num_counters,
+				     x86_pmu.num_counters_fixed,
+				     x86_pmu.intel_ctrl);
+	}
 
 	if (!x86_pmu.read)
 		x86_pmu.read = _x86_pmu_read;
@@ -2046,9 +2154,46 @@ static int __init init_hw_perf_events(void)
 	if (err)
 		goto out1;
 
-	err = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
-	if (err)
-		goto out2;
+	if (!is_hybrid()) {
+		err = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
+		if (err)
+			goto out2;
+	} else {
+		u8 cpu_type = get_this_hybrid_cpu_type();
+		struct x86_hybrid_pmu *hybrid_pmu;
+		int i, j;
+
+		if (!cpu_type && x86_pmu.get_hybrid_cpu_type)
+			cpu_type = x86_pmu.get_hybrid_cpu_type();
+
+		for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) {
+			hybrid_pmu = &x86_pmu.hybrid_pmu[i];
+
+			hybrid_pmu->pmu = pmu;
+			hybrid_pmu->pmu.type = -1;
+			hybrid_pmu->pmu.attr_update = x86_pmu.attr_update;
+			hybrid_pmu->pmu.capabilities |= PERF_PMU_CAP_HETEROGENEOUS_CPUS;
+			hybrid_pmu->pmu.capabilities |= PERF_PMU_CAP_EXTENDED_HW_TYPE;
+
+			err = perf_pmu_register(&hybrid_pmu->pmu, hybrid_pmu->name,
+						(hybrid_pmu->cpu_type == hybrid_big) ? PERF_TYPE_RAW : -1);
+			if (err)
+				break;
+
+			if (cpu_type == hybrid_pmu->cpu_type)
+				x86_pmu_update_cpu_context(&hybrid_pmu->pmu, raw_smp_processor_id());
+		}
+
+		if (i < x86_pmu.num_hybrid_pmus) {
+			for (j = 0; j < i; j++)
+				perf_pmu_unregister(&x86_pmu.hybrid_pmu[j].pmu);
+			pr_warn("Failed to register hybrid PMUs\n");
+			kfree(x86_pmu.hybrid_pmu);
+			x86_pmu.hybrid_pmu = NULL;
+			x86_pmu.num_hybrid_pmus = 0;
+			goto out2;
+		}
+	}
 
 	return 0;
 
@@ -2173,16 +2318,27 @@ static void free_fake_cpuc(struct cpu_hw_events *cpuc)
 	kfree(cpuc);
 }
 
-static struct cpu_hw_events *allocate_fake_cpuc(void)
+static struct cpu_hw_events *allocate_fake_cpuc(struct pmu *event_pmu)
 {
 	struct cpu_hw_events *cpuc;
-	int cpu = raw_smp_processor_id();
+	int cpu;
 
 	cpuc = kzalloc(sizeof(*cpuc), GFP_KERNEL);
 	if (!cpuc)
 		return ERR_PTR(-ENOMEM);
 	cpuc->is_fake = 1;
 
+	if (is_hybrid()) {
+		struct x86_hybrid_pmu *h_pmu;
+
+		h_pmu = hybrid_pmu(event_pmu);
+		if (cpumask_empty(&h_pmu->supported_cpus))
+			goto error;
+		cpu = cpumask_first(&h_pmu->supported_cpus);
+	} else
+		cpu = raw_smp_processor_id();
+	cpuc->pmu = event_pmu;
+
 	if (intel_cpuc_prepare(cpuc, cpu))
 		goto error;
 
@@ -2201,7 +2357,7 @@ static int validate_event(struct perf_event *event)
 	struct event_constraint *c;
 	int ret = 0;
 
-	fake_cpuc = allocate_fake_cpuc();
+	fake_cpuc = allocate_fake_cpuc(event->pmu);
 	if (IS_ERR(fake_cpuc))
 		return PTR_ERR(fake_cpuc);
 
@@ -2235,7 +2391,27 @@ static int validate_group(struct perf_event *event)
 	struct cpu_hw_events *fake_cpuc;
 	int ret = -EINVAL, n;
 
-	fake_cpuc = allocate_fake_cpuc();
+	/*
+	 * Reject events from different hybrid PMUs.
+	 */
+	if (is_hybrid()) {
+		struct perf_event *sibling;
+		struct pmu *pmu = NULL;
+
+		if (is_x86_event(leader))
+			pmu = leader->pmu;
+
+		for_each_sibling_event(sibling, leader) {
+			if (!is_x86_event(sibling))
+				continue;
+			if (!pmu)
+				pmu = sibling->pmu;
+			else if (pmu != sibling->pmu)
+				return ret;
+		}
+	}
+
+	fake_cpuc = allocate_fake_cpuc(event->pmu);
 	if (IS_ERR(fake_cpuc))
 		return PTR_ERR(fake_cpuc);
 	/*
@@ -2263,35 +2439,26 @@ out:
 
 static int x86_pmu_event_init(struct perf_event *event)
 {
-	struct pmu *tmp;
+	struct x86_hybrid_pmu *pmu = NULL;
 	int err;
 
-	switch (event->attr.type) {
-	case PERF_TYPE_RAW:
-	case PERF_TYPE_HARDWARE:
-	case PERF_TYPE_HW_CACHE:
-		break;
-
-	default:
+	if ((event->attr.type != event->pmu->type) &&
+	    (event->attr.type != PERF_TYPE_HARDWARE) &&
+	    (event->attr.type != PERF_TYPE_HW_CACHE))
 		return -ENOENT;
+
+	if (is_hybrid() && (event->cpu != -1)) {
+		pmu = hybrid_pmu(event->pmu);
+		if (!cpumask_test_cpu(event->cpu, &pmu->supported_cpus))
+			return -ENOENT;
 	}
 
 	err = __x86_pmu_event_init(event);
 	if (!err) {
-		/*
-		 * we temporarily connect event to its pmu
-		 * such that validate_group() can classify
-		 * it as an x86 event using is_x86_event()
-		 */
-		tmp = event->pmu;
-		event->pmu = &pmu;
-
 		if (event->group_leader != event)
 			err = validate_group(event);
 		else
 			err = validate_event(event);
-
-		event->pmu = tmp;
 	}
 	if (err) {
 		if (event->destroy)
@@ -2475,6 +2642,14 @@ static int x86_pmu_aux_output_match(struct perf_event *event)
 	return 0;
 }
 
+static int x86_pmu_filter_match(struct perf_event *event)
+{
+	if (x86_pmu.filter_match)
+		return x86_pmu.filter_match(event);
+
+	return 1;
+}
+
 static struct pmu pmu = {
 	.pmu_enable		= x86_pmu_enable,
 	.pmu_disable		= x86_pmu_disable,
@@ -2502,6 +2677,8 @@ static struct pmu pmu = {
 	.check_period		= x86_pmu_check_period,
 
 	.aux_output_match	= x86_pmu_aux_output_match,
+
+	.filter_match		= x86_pmu_filter_match,
 };
 
 void arch_perf_update_userpage(struct perf_event *event,
@@ -2770,6 +2947,11 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
 void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
 {
 	cap->version		= x86_pmu.version;
+	/*
+	 * KVM doesn't support the hybrid PMU yet.
+	 * Return the common value in global x86_pmu,
+	 * which available for all cores.
+	 */
 	cap->num_counters_gp	= x86_pmu.num_counters;
 	cap->num_counters_fixed	= x86_pmu.num_counters_fixed;
 	cap->bit_width_gp	= x86_pmu.cntval_bits;