1 files changed, 346 insertions, 252 deletions

diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 8d98d468b976..043f0a0b1e00 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -39,6 +39,10 @@
  *	  event: rapl_energy_psys
  *    perf code: 0x5
  *
+ *  core counter: consumption of a single physical core
+ *	  event: rapl_energy_core (power_core PMU)
+ *    perf code: 0x1
+ *
  * We manage those counters as free running (read-only). They may be
  * use simultaneously by other tools, such as turbostat.
  *
@@ -64,23 +68,28 @@
 #include "perf_event.h"
 #include "probe.h"
 
+MODULE_DESCRIPTION("Support Intel/AMD RAPL energy consumption counters");
 MODULE_LICENSE("GPL");
 
 /*
  * RAPL energy status counters
  */
-enum perf_rapl_events {
+enum perf_rapl_pkg_events {
 	PERF_RAPL_PP0 = 0,		/* all cores */
 	PERF_RAPL_PKG,			/* entire package */
 	PERF_RAPL_RAM,			/* DRAM */
 	PERF_RAPL_PP1,			/* gpu */
 	PERF_RAPL_PSYS,			/* psys */
 
-	PERF_RAPL_MAX,
-	NR_RAPL_DOMAINS = PERF_RAPL_MAX,
+	PERF_RAPL_PKG_EVENTS_MAX,
+	NR_RAPL_PKG_DOMAINS = PERF_RAPL_PKG_EVENTS_MAX,
 };
 
-static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
+#define PERF_RAPL_CORE			0		/* single core */
+#define PERF_RAPL_CORE_EVENTS_MAX	1
+#define NR_RAPL_CORE_DOMAINS		PERF_RAPL_CORE_EVENTS_MAX
+
+static const char *const rapl_pkg_domain_names[NR_RAPL_PKG_DOMAINS] __initconst = {
 	"pp0-core",
 	"package",
 	"dram",
@@ -88,6 +97,8 @@ static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
 	"psys",
 };
 
+static const char *const rapl_core_domain_name __initconst = "core";
+
 /*
  * event code: LSB 8 bits, passed in attr->config
  * any other bit is reserved
@@ -102,6 +113,19 @@ static struct perf_pmu_events_attr event_attr_##v = {				\
 	.event_str	= str,							\
 };
 
+/*
+ * RAPL Package energy counter scope:
+ * 1. AMD/HYGON platforms have a per-PKG package energy counter
+ * 2. For Intel platforms
+ *	2.1. CLX-AP is multi-die and its RAPL MSRs are die-scope
+ *	2.2. Other Intel platforms are single die systems so the scope can be
+ *	     considered as either pkg-scope or die-scope, and we are considering
+ *	     them as die-scope.
+ */
+#define rapl_pkg_pmu_is_pkg_scope()				\
+	(boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||	\
+	 boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
+
 struct rapl_pmu {
 	raw_spinlock_t		lock;
 	int			n_active;
@@ -114,8 +138,9 @@ struct rapl_pmu {
 
 struct rapl_pmus {
 	struct pmu		pmu;
-	unsigned int		maxdie;
-	struct rapl_pmu		*pmus[] __counted_by(maxdie);
+	unsigned int		nr_rapl_pmu;
+	unsigned int		cntr_mask;
+	struct rapl_pmu		*rapl_pmu[] __counted_by(nr_rapl_pmu);
 };
 
 enum rapl_unit_quirk {
@@ -125,29 +150,43 @@ enum rapl_unit_quirk {
 };
 
 struct rapl_model {
-	struct perf_msr *rapl_msrs;
-	unsigned long	events;
+	struct perf_msr *rapl_pkg_msrs;
+	struct perf_msr *rapl_core_msrs;
+	unsigned long	pkg_events;
+	unsigned long	core_events;
 	unsigned int	msr_power_unit;
 	enum rapl_unit_quirk	unit_quirk;
 };
 
  /* 1/2^hw_unit Joule */
-static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly;
-static struct rapl_pmus *rapl_pmus;
-static cpumask_t rapl_cpu_mask;
-static unsigned int rapl_cntr_mask;
+static int rapl_pkg_hw_unit[NR_RAPL_PKG_DOMAINS] __read_mostly;
+static int rapl_core_hw_unit __read_mostly;
+static struct rapl_pmus *rapl_pmus_pkg;
+static struct rapl_pmus *rapl_pmus_core;
 static u64 rapl_timer_ms;
-static struct perf_msr *rapl_msrs;
+static struct rapl_model *rapl_model;
 
-static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
+/*
+ * Helper function to get the correct topology id according to the
+ * RAPL PMU scope.
+ */
+static inline unsigned int get_rapl_pmu_idx(int cpu, int scope)
 {
-	unsigned int dieid = topology_logical_die_id(cpu);
-
 	/*
-	 * The unsigned check also catches the '-1' return value for non
-	 * existent mappings in the topology map.
+	 * Returns unsigned int, which converts the '-1' return value
+	 * (for non-existent mappings in topology map) to UINT_MAX, so
+	 * the error check in the caller is simplified.
 	 */
-	return dieid < rapl_pmus->maxdie ? rapl_pmus->pmus[dieid] : NULL;
+	switch (scope) {
+	case PERF_PMU_SCOPE_PKG:
+		return topology_logical_package_id(cpu);
+	case PERF_PMU_SCOPE_DIE:
+		return topology_logical_die_id(cpu);
+	case PERF_PMU_SCOPE_CORE:
+		return topology_logical_core_id(cpu);
+	default:
+		return -EINVAL;
+	}
 }
 
 static inline u64 rapl_read_counter(struct perf_event *event)
@@ -157,19 +196,20 @@ static inline u64 rapl_read_counter(struct perf_event *event)
 	return raw;
 }
 
-static inline u64 rapl_scale(u64 v, int cfg)
+static inline u64 rapl_scale(u64 v, struct perf_event *event)
 {
-	if (cfg > NR_RAPL_DOMAINS) {
-		pr_warn("Invalid domain %d, failed to scale data\n", cfg);
-		return v;
-	}
+	int hw_unit = rapl_pkg_hw_unit[event->hw.config - 1];
+
+	if (event->pmu->scope == PERF_PMU_SCOPE_CORE)
+		hw_unit = rapl_core_hw_unit;
+
 	/*
 	 * scale delta to smallest unit (1/2^32)
 	 * users must then scale back: count * 1/(1e9*2^32) to get Joules
 	 * or use ldexp(count, -32).
 	 * Watts = Joules/Time delta
 	 */
-	return v << (32 - rapl_hw_unit[cfg - 1]);
+	return v << (32 - hw_unit);
 }
 
 static u64 rapl_event_update(struct perf_event *event)
@@ -196,7 +236,7 @@ static u64 rapl_event_update(struct perf_event *event)
 	delta = (new_raw_count << shift) - (prev_raw_count << shift);
 	delta >>= shift;
 
-	sdelta = rapl_scale(delta, event->hw.config);
+	sdelta = rapl_scale(delta, event);
 
 	local64_add(sdelta, &event->count);
 
@@ -211,34 +251,34 @@ static void rapl_start_hrtimer(struct rapl_pmu *pmu)
 
 static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer)
 {
-	struct rapl_pmu *pmu = container_of(hrtimer, struct rapl_pmu, hrtimer);
+	struct rapl_pmu *rapl_pmu = container_of(hrtimer, struct rapl_pmu, hrtimer);
 	struct perf_event *event;
 	unsigned long flags;
 
-	if (!pmu->n_active)
+	if (!rapl_pmu->n_active)
 		return HRTIMER_NORESTART;
 
-	raw_spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&rapl_pmu->lock, flags);
 
-	list_for_each_entry(event, &pmu->active_list, active_entry)
+	list_for_each_entry(event, &rapl_pmu->active_list, active_entry)
 		rapl_event_update(event);
 
-	raw_spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags);
 
-	hrtimer_forward_now(hrtimer, pmu->timer_interval);
+	hrtimer_forward_now(hrtimer, rapl_pmu->timer_interval);
 
 	return HRTIMER_RESTART;
 }
 
-static void rapl_hrtimer_init(struct rapl_pmu *pmu)
+static void rapl_hrtimer_init(struct rapl_pmu *rapl_pmu)
 {
-	struct hrtimer *hr = &pmu->hrtimer;
+	struct hrtimer *hr = &rapl_pmu->hrtimer;
 
 	hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hr->function = rapl_hrtimer_handle;
 }
 
-static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
+static void __rapl_pmu_event_start(struct rapl_pmu *rapl_pmu,
 				   struct perf_event *event)
 {
 	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
@@ -246,39 +286,39 @@ static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
 
 	event->hw.state = 0;
 
-	list_add_tail(&event->active_entry, &pmu->active_list);
+	list_add_tail(&event->active_entry, &rapl_pmu->active_list);
 
 	local64_set(&event->hw.prev_count, rapl_read_counter(event));
 
-	pmu->n_active++;
-	if (pmu->n_active == 1)
-		rapl_start_hrtimer(pmu);
+	rapl_pmu->n_active++;
+	if (rapl_pmu->n_active == 1)
+		rapl_start_hrtimer(rapl_pmu);
 }
 
 static void rapl_pmu_event_start(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = event->pmu_private;
+	struct rapl_pmu *rapl_pmu = event->pmu_private;
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&pmu->lock, flags);
-	__rapl_pmu_event_start(pmu, event);
-	raw_spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&rapl_pmu->lock, flags);
+	__rapl_pmu_event_start(rapl_pmu, event);
+	raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags);
 }
 
 static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = event->pmu_private;
+	struct rapl_pmu *rapl_pmu = event->pmu_private;
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&rapl_pmu->lock, flags);
 
 	/* mark event as deactivated and stopped */
 	if (!(hwc->state & PERF_HES_STOPPED)) {
-		WARN_ON_ONCE(pmu->n_active <= 0);
-		pmu->n_active--;
-		if (pmu->n_active == 0)
-			hrtimer_cancel(&pmu->hrtimer);
+		WARN_ON_ONCE(rapl_pmu->n_active <= 0);
+		rapl_pmu->n_active--;
+		if (rapl_pmu->n_active == 0)
+			hrtimer_cancel(&rapl_pmu->hrtimer);
 
 		list_del(&event->active_entry);
 
@@ -296,23 +336,23 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 		hwc->state |= PERF_HES_UPTODATE;
 	}
 
-	raw_spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags);
 }
 
 static int rapl_pmu_event_add(struct perf_event *event, int mode)
 {
-	struct rapl_pmu *pmu = event->pmu_private;
+	struct rapl_pmu *rapl_pmu = event->pmu_private;
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&rapl_pmu->lock, flags);
 
 	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
 
 	if (mode & PERF_EF_START)
-		__rapl_pmu_event_start(pmu, event);
+		__rapl_pmu_event_start(rapl_pmu, event);
 
-	raw_spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags);
 
 	return 0;
 }
@@ -325,13 +365,19 @@ static void rapl_pmu_event_del(struct perf_event *event, int flags)
 static int rapl_pmu_event_init(struct perf_event *event)
 {
 	u64 cfg = event->attr.config & RAPL_EVENT_MASK;
-	int bit, ret = 0;
-	struct rapl_pmu *pmu;
+	int bit, rapl_pmus_scope, ret = 0;
+	struct rapl_pmu *rapl_pmu;
+	unsigned int rapl_pmu_idx;
+	struct rapl_pmus *rapl_pmus;
 
 	/* only look at RAPL events */
-	if (event->attr.type != rapl_pmus->pmu.type)
+	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
 
+	/* unsupported modes and filters */
+	if (event->attr.sample_period) /* no sampling */
+		return -EINVAL;
+
 	/* check only supported bits are set */
 	if (event->attr.config & ~RAPL_EVENT_MASK)
 		return -EINVAL;
@@ -339,29 +385,41 @@ static int rapl_pmu_event_init(struct perf_event *event)
 	if (event->cpu < 0)
 		return -EINVAL;
 
-	event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
-
-	if (!cfg || cfg >= NR_RAPL_DOMAINS + 1)
+	rapl_pmus = container_of(event->pmu, struct rapl_pmus, pmu);
+	if (!rapl_pmus)
+		return -EINVAL;
+	rapl_pmus_scope = rapl_pmus->pmu.scope;
+
+	if (rapl_pmus_scope == PERF_PMU_SCOPE_PKG || rapl_pmus_scope == PERF_PMU_SCOPE_DIE) {
+		cfg = array_index_nospec((long)cfg, NR_RAPL_PKG_DOMAINS + 1);
+		if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1)
+			return -EINVAL;
+
+		bit = cfg - 1;
+		event->hw.event_base = rapl_model->rapl_pkg_msrs[bit].msr;
+	} else if (rapl_pmus_scope == PERF_PMU_SCOPE_CORE) {
+		cfg = array_index_nospec((long)cfg, NR_RAPL_CORE_DOMAINS + 1);
+		if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1)
+			return -EINVAL;
+
+		bit = cfg - 1;
+		event->hw.event_base = rapl_model->rapl_core_msrs[bit].msr;
+	} else
 		return -EINVAL;
-
-	cfg = array_index_nospec((long)cfg, NR_RAPL_DOMAINS + 1);
-	bit = cfg - 1;
 
 	/* check event supported */
-	if (!(rapl_cntr_mask & (1 << bit)))
+	if (!(rapl_pmus->cntr_mask & (1 << bit)))
 		return -EINVAL;
 
-	/* unsupported modes and filters */
-	if (event->attr.sample_period) /* no sampling */
+	rapl_pmu_idx = get_rapl_pmu_idx(event->cpu, rapl_pmus_scope);
+	if (rapl_pmu_idx >= rapl_pmus->nr_rapl_pmu)
 		return -EINVAL;
-
 	/* must be done before validate_group */
-	pmu = cpu_to_rapl_pmu(event->cpu);
-	if (!pmu)
+	rapl_pmu = rapl_pmus->rapl_pmu[rapl_pmu_idx];
+	if (!rapl_pmu)
 		return -EINVAL;
-	event->cpu = pmu->cpu;
-	event->pmu_private = pmu;
-	event->hw.event_base = rapl_msrs[bit].msr;
+
+	event->pmu_private = rapl_pmu;
 	event->hw.config = cfg;
 	event->hw.idx = bit;
 
@@ -373,34 +431,19 @@ static void rapl_pmu_event_read(struct perf_event *event)
 	rapl_event_update(event);
 }
 
-static ssize_t rapl_get_attr_cpumask(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	return cpumap_print_to_pagebuf(true, buf, &rapl_cpu_mask);
-}
-
-static DEVICE_ATTR(cpumask, S_IRUGO, rapl_get_attr_cpumask, NULL);
-
-static struct attribute *rapl_pmu_attrs[] = {
-	&dev_attr_cpumask.attr,
-	NULL,
-};
-
-static struct attribute_group rapl_pmu_attr_group = {
-	.attrs = rapl_pmu_attrs,
-};
-
 RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
 RAPL_EVENT_ATTR_STR(energy-pkg  ,   rapl_pkg, "event=0x02");
 RAPL_EVENT_ATTR_STR(energy-ram  ,   rapl_ram, "event=0x03");
 RAPL_EVENT_ATTR_STR(energy-gpu  ,   rapl_gpu, "event=0x04");
 RAPL_EVENT_ATTR_STR(energy-psys,   rapl_psys, "event=0x05");
+RAPL_EVENT_ATTR_STR(energy-core,   rapl_core, "event=0x01");
 
 RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
 RAPL_EVENT_ATTR_STR(energy-pkg.unit  ,   rapl_pkg_unit, "Joules");
 RAPL_EVENT_ATTR_STR(energy-ram.unit  ,   rapl_ram_unit, "Joules");
 RAPL_EVENT_ATTR_STR(energy-gpu.unit  ,   rapl_gpu_unit, "Joules");
 RAPL_EVENT_ATTR_STR(energy-psys.unit,   rapl_psys_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-core.unit,   rapl_core_unit, "Joules");
 
 /*
  * we compute in 0.23 nJ increments regardless of MSR
@@ -410,6 +453,7 @@ RAPL_EVENT_ATTR_STR(energy-pkg.scale,     rapl_pkg_scale, "2.3283064365386962890
 RAPL_EVENT_ATTR_STR(energy-ram.scale,     rapl_ram_scale, "2.3283064365386962890625e-10");
 RAPL_EVENT_ATTR_STR(energy-gpu.scale,     rapl_gpu_scale, "2.3283064365386962890625e-10");
 RAPL_EVENT_ATTR_STR(energy-psys.scale,   rapl_psys_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-core.scale,   rapl_core_scale, "2.3283064365386962890625e-10");
 
 /*
  * There are no default events, but we need to create
@@ -437,7 +481,12 @@ static struct attribute_group rapl_pmu_format_group = {
 };
 
 static const struct attribute_group *rapl_attr_groups[] = {
-	&rapl_pmu_attr_group,
+	&rapl_pmu_format_group,
+	&rapl_pmu_events_group,
+	NULL,
+};
+
+static const struct attribute_group *rapl_core_attr_groups[] = {
 	&rapl_pmu_format_group,
 	&rapl_pmu_events_group,
 	NULL,
@@ -503,6 +552,18 @@ static struct attribute_group rapl_events_psys_group = {
 	.attrs = rapl_events_psys,
 };
 
+static struct attribute *rapl_events_core[] = {
+	EVENT_PTR(rapl_core),
+	EVENT_PTR(rapl_core_unit),
+	EVENT_PTR(rapl_core_scale),
+	NULL,
+};
+
+static struct attribute_group rapl_events_core_group = {
+	.name  = "events",
+	.attrs = rapl_events_core,
+};
+
 static bool test_msr(int idx, void *data)
 {
 	return test_bit(idx, (unsigned long *) data);
@@ -528,11 +589,11 @@ static struct perf_msr intel_rapl_spr_msrs[] = {
 };
 
 /*
- * Force to PERF_RAPL_MAX size due to:
- * - perf_msr_probe(PERF_RAPL_MAX)
+ * Force to PERF_RAPL_PKG_EVENTS_MAX size due to:
+ * - perf_msr_probe(PERF_RAPL_PKG_EVENTS_MAX)
  * - want to use same event codes across both architectures
  */
-static struct perf_msr amd_rapl_msrs[] = {
+static struct perf_msr amd_rapl_pkg_msrs[] = {
 	[PERF_RAPL_PP0]  = { 0, &rapl_events_cores_group, NULL, false, 0 },
 	[PERF_RAPL_PKG]  = { MSR_AMD_PKG_ENERGY_STATUS,  &rapl_events_pkg_group,   test_msr, false, RAPL_MSR_MASK },
 	[PERF_RAPL_RAM]  = { 0, &rapl_events_ram_group,   NULL, false, 0 },
@@ -540,72 +601,25 @@ static struct perf_msr amd_rapl_msrs[] = {
 	[PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group,  NULL, false, 0 },
 };
 
-static int rapl_cpu_offline(unsigned int cpu)
-{
-	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
-	int target;
-
-	/* Check if exiting cpu is used for collecting rapl events */
-	if (!cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask))
-		return 0;
-
-	pmu->cpu = -1;
-	/* Find a new cpu to collect rapl events */
-	target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
-
-	/* Migrate rapl events to the new target */
-	if (target < nr_cpu_ids) {
-		cpumask_set_cpu(target, &rapl_cpu_mask);
-		pmu->cpu = target;
-		perf_pmu_migrate_context(pmu->pmu, cpu, target);
-	}
-	return 0;
-}
-
-static int rapl_cpu_online(unsigned int cpu)
-{
-	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
-	int target;
-
-	if (!pmu) {
-		pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
-		if (!pmu)
-			return -ENOMEM;
-
-		raw_spin_lock_init(&pmu->lock);
-		INIT_LIST_HEAD(&pmu->active_list);
-		pmu->pmu = &rapl_pmus->pmu;
-		pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
-		rapl_hrtimer_init(pmu);
-
-		rapl_pmus->pmus[topology_logical_die_id(cpu)] = pmu;
-	}
-
-	/*
-	 * Check if there is an online cpu in the package which collects rapl
-	 * events already.
-	 */
-	target = cpumask_any_and(&rapl_cpu_mask, topology_die_cpumask(cpu));
-	if (target < nr_cpu_ids)
-		return 0;
-
-	cpumask_set_cpu(cpu, &rapl_cpu_mask);
-	pmu->cpu = cpu;
-	return 0;
-}
+static struct perf_msr amd_rapl_core_msrs[] = {
+	[PERF_RAPL_CORE] = { MSR_AMD_CORE_ENERGY_STATUS, &rapl_events_core_group,
+				 test_msr, false, RAPL_MSR_MASK },
+};
 
-static int rapl_check_hw_unit(struct rapl_model *rm)
+static int rapl_check_hw_unit(void)
 {
 	u64 msr_rapl_power_unit_bits;
 	int i;
 
 	/* protect rdmsrl() to handle virtualization */
-	if (rdmsrl_safe(rm->msr_power_unit, &msr_rapl_power_unit_bits))
+	if (rdmsrl_safe(rapl_model->msr_power_unit, &msr_rapl_power_unit_bits))
 		return -1;
-	for (i = 0; i < NR_RAPL_DOMAINS; i++)
-		rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
+	for (i = 0; i < NR_RAPL_PKG_DOMAINS; i++)
+		rapl_pkg_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
+
+	rapl_core_hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
 
-	switch (rm->unit_quirk) {
+	switch (rapl_model->unit_quirk) {
 	/*
 	 * DRAM domain on HSW server and KNL has fixed energy unit which can be
 	 * different than the unit from power unit MSR. See
@@ -613,17 +627,16 @@ static int rapl_check_hw_unit(struct rapl_model *rm)
 	 * of 2. Datasheet, September 2014, Reference Number: 330784-001 "
 	 */
 	case RAPL_UNIT_QUIRK_INTEL_HSW:
-		rapl_hw_unit[PERF_RAPL_RAM] = 16;
+		rapl_pkg_hw_unit[PERF_RAPL_RAM] = 16;
 		break;
 	/* SPR uses a fixed energy unit for Psys domain. */
 	case RAPL_UNIT_QUIRK_INTEL_SPR:
-		rapl_hw_unit[PERF_RAPL_PSYS] = 0;
+		rapl_pkg_hw_unit[PERF_RAPL_PSYS] = 0;
 		break;
 	default:
 		break;
 	}
 
-
 	/*
 	 * Calculate the timer rate:
 	 * Use reference of 200W for scaling the timeout to avoid counter
@@ -632,9 +645,9 @@ static int rapl_check_hw_unit(struct rapl_model *rm)
 	 * if hw unit is 32, then we use 2 ms 1/200/2
 	 */
 	rapl_timer_ms = 2;
-	if (rapl_hw_unit[0] < 32) {
+	if (rapl_pkg_hw_unit[0] < 32) {
 		rapl_timer_ms = (1000 / (2 * 100));
-		rapl_timer_ms *= (1ULL << (32 - rapl_hw_unit[0] - 1));
+		rapl_timer_ms *= (1ULL << (32 - rapl_pkg_hw_unit[0] - 1));
 	}
 	return 0;
 }
@@ -642,24 +655,32 @@ static int rapl_check_hw_unit(struct rapl_model *rm)
 static void __init rapl_advertise(void)
 {
 	int i;
+	int num_counters = hweight32(rapl_pmus_pkg->cntr_mask);
+
+	if (rapl_pmus_core)
+		num_counters += hweight32(rapl_pmus_core->cntr_mask);
 
 	pr_info("API unit is 2^-32 Joules, %d fixed counters, %llu ms ovfl timer\n",
-		hweight32(rapl_cntr_mask), rapl_timer_ms);
+		num_counters, rapl_timer_ms);
 
-	for (i = 0; i < NR_RAPL_DOMAINS; i++) {
-		if (rapl_cntr_mask & (1 << i)) {
+	for (i = 0; i < NR_RAPL_PKG_DOMAINS; i++) {
+		if (rapl_pmus_pkg->cntr_mask & (1 << i)) {
 			pr_info("hw unit of domain %s 2^-%d Joules\n",
-				rapl_domain_names[i], rapl_hw_unit[i]);
+				rapl_pkg_domain_names[i], rapl_pkg_hw_unit[i]);
 		}
 	}
+
+	if (rapl_pmus_core && (rapl_pmus_core->cntr_mask & (1 << PERF_RAPL_CORE)))
+		pr_info("hw unit of domain %s 2^-%d Joules\n",
+			rapl_core_domain_name, rapl_core_hw_unit);
 }
 
-static void cleanup_rapl_pmus(void)
+static void cleanup_rapl_pmus(struct rapl_pmus *rapl_pmus)
 {
 	int i;
 
-	for (i = 0; i < rapl_pmus->maxdie; i++)
-		kfree(rapl_pmus->pmus[i]);
+	for (i = 0; i < rapl_pmus->nr_rapl_pmu; i++)
+		kfree(rapl_pmus->rapl_pmu[i]);
 	kfree(rapl_pmus);
 }
 
@@ -672,17 +693,62 @@ static const struct attribute_group *rapl_attr_update[] = {
 	NULL,
 };
 
-static int __init init_rapl_pmus(void)
+static const struct attribute_group *rapl_core_attr_update[] = {
+	&rapl_events_core_group,
+	NULL,
+};
+
+static int __init init_rapl_pmu(struct rapl_pmus *rapl_pmus)
+{
+	struct rapl_pmu *rapl_pmu;
+	int idx;
+
+	for (idx = 0; idx < rapl_pmus->nr_rapl_pmu; idx++) {
+		rapl_pmu = kzalloc(sizeof(*rapl_pmu), GFP_KERNEL);
+		if (!rapl_pmu)
+			goto free;
+
+		raw_spin_lock_init(&rapl_pmu->lock);
+		INIT_LIST_HEAD(&rapl_pmu->active_list);
+		rapl_pmu->pmu = &rapl_pmus->pmu;
+		rapl_pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
+		rapl_hrtimer_init(rapl_pmu);
+
+		rapl_pmus->rapl_pmu[idx] = rapl_pmu;
+	}
+
+	return 0;
+free:
+	for (; idx > 0; idx--)
+		kfree(rapl_pmus->rapl_pmu[idx - 1]);
+	return -ENOMEM;
+}
+
+static int __init init_rapl_pmus(struct rapl_pmus **rapl_pmus_ptr, int rapl_pmu_scope,
+				 const struct attribute_group **rapl_attr_groups,
+				 const struct attribute_group **rapl_attr_update)
 {
-	int maxdie = topology_max_packages() * topology_max_die_per_package();
-	size_t size;
+	int nr_rapl_pmu = topology_max_packages();
+	struct rapl_pmus *rapl_pmus;
+	int ret;
+
+	/*
+	 * rapl_pmu_scope must be either PKG, DIE or CORE
+	 */
+	if (rapl_pmu_scope == PERF_PMU_SCOPE_DIE)
+		nr_rapl_pmu	*= topology_max_dies_per_package();
+	else if (rapl_pmu_scope == PERF_PMU_SCOPE_CORE)
+		nr_rapl_pmu	*= topology_num_cores_per_package();
+	else if (rapl_pmu_scope != PERF_PMU_SCOPE_PKG)
+		return -EINVAL;
 
-	size = sizeof(*rapl_pmus) + maxdie * sizeof(struct rapl_pmu *);
-	rapl_pmus = kzalloc(size, GFP_KERNEL);
+	rapl_pmus = kzalloc(struct_size(rapl_pmus, rapl_pmu, nr_rapl_pmu), GFP_KERNEL);
 	if (!rapl_pmus)
 		return -ENOMEM;
 
-	rapl_pmus->maxdie		= maxdie;
+	*rapl_pmus_ptr = rapl_pmus;
+
+	rapl_pmus->nr_rapl_pmu		= nr_rapl_pmu;
 	rapl_pmus->pmu.attr_groups	= rapl_attr_groups;
 	rapl_pmus->pmu.attr_update	= rapl_attr_update;
 	rapl_pmus->pmu.task_ctx_nr	= perf_invalid_context;
@@ -692,122 +758,134 @@ static int __init init_rapl_pmus(void)
 	rapl_pmus->pmu.start		= rapl_pmu_event_start;
 	rapl_pmus->pmu.stop		= rapl_pmu_event_stop;
 	rapl_pmus->pmu.read		= rapl_pmu_event_read;
+	rapl_pmus->pmu.scope		= rapl_pmu_scope;
 	rapl_pmus->pmu.module		= THIS_MODULE;
 	rapl_pmus->pmu.capabilities	= PERF_PMU_CAP_NO_EXCLUDE;
-	return 0;
+
+	ret = init_rapl_pmu(rapl_pmus);
+	if (ret)
+		kfree(rapl_pmus);
+
+	return ret;
 }
 
 static struct rapl_model model_snb = {
-	.events		= BIT(PERF_RAPL_PP0) |
+	.pkg_events	= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_PP1),
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
-	.rapl_msrs      = intel_rapl_msrs,
+	.rapl_pkg_msrs	= intel_rapl_msrs,
 };
 
 static struct rapl_model model_snbep = {
-	.events		= BIT(PERF_RAPL_PP0) |
+	.pkg_events	= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
-	.rapl_msrs      = intel_rapl_msrs,
+	.rapl_pkg_msrs	= intel_rapl_msrs,
 };
 
 static struct rapl_model model_hsw = {
-	.events		= BIT(PERF_RAPL_PP0) |
+	.pkg_events	= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM) |
 			  BIT(PERF_RAPL_PP1),
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
-	.rapl_msrs      = intel_rapl_msrs,
+	.rapl_pkg_msrs	= intel_rapl_msrs,
 };
 
 static struct rapl_model model_hsx = {
-	.events		= BIT(PERF_RAPL_PP0) |
+	.pkg_events	= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
 	.unit_quirk	= RAPL_UNIT_QUIRK_INTEL_HSW,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
-	.rapl_msrs      = intel_rapl_msrs,
+	.rapl_pkg_msrs	= intel_rapl_msrs,
 };
 
 static struct rapl_model model_knl = {
-	.events		= BIT(PERF_RAPL_PKG) |
+	.pkg_events	= BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
 	.unit_quirk	= RAPL_UNIT_QUIRK_INTEL_HSW,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
-	.rapl_msrs      = intel_rapl_msrs,
+	.rapl_pkg_msrs	= intel_rapl_msrs,
 };
 
 static struct rapl_model model_skl = {
-	.events		= BIT(PERF_RAPL_PP0) |
+	.pkg_events	= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM) |
 			  BIT(PERF_RAPL_PP1) |
 			  BIT(PERF_RAPL_PSYS),
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
-	.rapl_msrs      = intel_rapl_msrs,
+	.rapl_pkg_msrs      = intel_rapl_msrs,
 };
 
 static struct rapl_model model_spr = {
-	.events		= BIT(PERF_RAPL_PP0) |
+	.pkg_events	= BIT(PERF_RAPL_PP0) |
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM) |
 			  BIT(PERF_RAPL_PSYS),
 	.unit_quirk	= RAPL_UNIT_QUIRK_INTEL_SPR,
 	.msr_power_unit = MSR_RAPL_POWER_UNIT,
-	.rapl_msrs      = intel_rapl_spr_msrs,
+	.rapl_pkg_msrs	= intel_rapl_spr_msrs,
 };
 
 static struct rapl_model model_amd_hygon = {
-	.events		= BIT(PERF_RAPL_PKG),
+	.pkg_events	= BIT(PERF_RAPL_PKG),
+	.core_events	= BIT(PERF_RAPL_CORE),
 	.msr_power_unit = MSR_AMD_RAPL_POWER_UNIT,
-	.rapl_msrs      = amd_rapl_msrs,
+	.rapl_pkg_msrs	= amd_rapl_pkg_msrs,
+	.rapl_core_msrs	= amd_rapl_core_msrs,
 };
 
 static const struct x86_cpu_id rapl_model_match[] __initconst = {
-	X86_MATCH_FEATURE(X86_FEATURE_RAPL,		&model_amd_hygon),
-	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE,		&model_snb),
-	X86_MATCH_INTEL_FAM6_MODEL(SANDYBRIDGE_X,	&model_snbep),
-	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE,		&model_snb),
-	X86_MATCH_INTEL_FAM6_MODEL(IVYBRIDGE_X,		&model_snbep),
-	X86_MATCH_INTEL_FAM6_MODEL(HASWELL,		&model_hsw),
-	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_X,		&model_hsx),
-	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_L,		&model_hsw),
-	X86_MATCH_INTEL_FAM6_MODEL(HASWELL_G,		&model_hsw),
-	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL,		&model_hsw),
-	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_G,		&model_hsw),
-	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_X,		&model_hsx),
-	X86_MATCH_INTEL_FAM6_MODEL(BROADWELL_D,		&model_hsx),
-	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL,	&model_knl),
-	X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM,	&model_knl),
-	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L,		&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE,		&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,		&model_hsx),
-	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L,		&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE,		&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(CANNONLAKE_L,	&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT,	&model_hsw),
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_D,	&model_hsw),
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS,	&model_hsw),
-	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		&model_hsx),
-	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&model_hsx),
-	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT,	&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&model_spr),
-	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X,	&model_spr),
-	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,	&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE,		&model_skl),
-	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L,	&model_skl),
+	X86_MATCH_FEATURE(X86_FEATURE_RAPL,	&model_amd_hygon),
+	X86_MATCH_VFM(INTEL_SANDYBRIDGE,	&model_snb),
+	X86_MATCH_VFM(INTEL_SANDYBRIDGE_X,	&model_snbep),
+	X86_MATCH_VFM(INTEL_IVYBRIDGE,		&model_snb),
+	X86_MATCH_VFM(INTEL_IVYBRIDGE_X,	&model_snbep),
+	X86_MATCH_VFM(INTEL_HASWELL,		&model_hsw),
+	X86_MATCH_VFM(INTEL_HASWELL_X,		&model_hsx),
+	X86_MATCH_VFM(INTEL_HASWELL_L,		&model_hsw),
+	X86_MATCH_VFM(INTEL_HASWELL_G,		&model_hsw),
+	X86_MATCH_VFM(INTEL_BROADWELL,		&model_hsw),
+	X86_MATCH_VFM(INTEL_BROADWELL_G,	&model_hsw),
+	X86_MATCH_VFM(INTEL_BROADWELL_X,	&model_hsx),
+	X86_MATCH_VFM(INTEL_BROADWELL_D,	&model_hsx),
+	X86_MATCH_VFM(INTEL_XEON_PHI_KNL,	&model_knl),
+	X86_MATCH_VFM(INTEL_XEON_PHI_KNM,	&model_knl),
+	X86_MATCH_VFM(INTEL_SKYLAKE_L,		&model_skl),
+	X86_MATCH_VFM(INTEL_SKYLAKE,		&model_skl),
+	X86_MATCH_VFM(INTEL_SKYLAKE_X,		&model_hsx),
+	X86_MATCH_VFM(INTEL_KABYLAKE_L,		&model_skl),
+	X86_MATCH_VFM(INTEL_KABYLAKE,		&model_skl),
+	X86_MATCH_VFM(INTEL_CANNONLAKE_L,	&model_skl),
+	X86_MATCH_VFM(INTEL_ATOM_GOLDMONT,	&model_hsw),
+	X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_D,	&model_hsw),
+	X86_MATCH_VFM(INTEL_ATOM_GOLDMONT_PLUS,	&model_hsw),
+	X86_MATCH_VFM(INTEL_ICELAKE_L,		&model_skl),
+	X86_MATCH_VFM(INTEL_ICELAKE,		&model_skl),
+	X86_MATCH_VFM(INTEL_ICELAKE_D,		&model_hsx),
+	X86_MATCH_VFM(INTEL_ICELAKE_X,		&model_hsx),
+	X86_MATCH_VFM(INTEL_COMETLAKE_L,	&model_skl),
+	X86_MATCH_VFM(INTEL_COMETLAKE,		&model_skl),
+	X86_MATCH_VFM(INTEL_TIGERLAKE_L,	&model_skl),
+	X86_MATCH_VFM(INTEL_TIGERLAKE,		&model_skl),
+	X86_MATCH_VFM(INTEL_ALDERLAKE,		&model_skl),
+	X86_MATCH_VFM(INTEL_ALDERLAKE_L,	&model_skl),
+	X86_MATCH_VFM(INTEL_ATOM_GRACEMONT,	&model_skl),
+	X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X,	&model_spr),
+	X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X,	&model_spr),
+	X86_MATCH_VFM(INTEL_RAPTORLAKE,		&model_skl),
+	X86_MATCH_VFM(INTEL_RAPTORLAKE_P,	&model_skl),
+	X86_MATCH_VFM(INTEL_RAPTORLAKE_S,	&model_skl),
+	X86_MATCH_VFM(INTEL_METEORLAKE,		&model_skl),
+	X86_MATCH_VFM(INTEL_METEORLAKE_L,	&model_skl),
+	X86_MATCH_VFM(INTEL_ARROWLAKE_H,	&model_skl),
+	X86_MATCH_VFM(INTEL_ARROWLAKE,		&model_skl),
+	X86_MATCH_VFM(INTEL_ARROWLAKE_U,	&model_skl),
+	X86_MATCH_VFM(INTEL_LUNARLAKE_M,	&model_skl),
 	{},
 };
 MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
@@ -815,57 +893,73 @@ MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
 static int __init rapl_pmu_init(void)
 {
 	const struct x86_cpu_id *id;
-	struct rapl_model *rm;
+	int rapl_pkg_pmu_scope = PERF_PMU_SCOPE_DIE;
 	int ret;
 
+	if (rapl_pkg_pmu_is_pkg_scope())
+		rapl_pkg_pmu_scope = PERF_PMU_SCOPE_PKG;
+
 	id = x86_match_cpu(rapl_model_match);
 	if (!id)
 		return -ENODEV;
 
-	rm = (struct rapl_model *) id->driver_data;
-
-	rapl_msrs = rm->rapl_msrs;
+	rapl_model = (struct rapl_model *) id->driver_data;
 
-	rapl_cntr_mask = perf_msr_probe(rapl_msrs, PERF_RAPL_MAX,
-					false, (void *) &rm->events);
-
-	ret = rapl_check_hw_unit(rm);
+	ret = rapl_check_hw_unit();
 	if (ret)
 		return ret;
 
-	ret = init_rapl_pmus();
+	ret = init_rapl_pmus(&rapl_pmus_pkg, rapl_pkg_pmu_scope, rapl_attr_groups,
+			     rapl_attr_update);
 	if (ret)
 		return ret;
 
-	/*
-	 * Install callbacks. Core will call them for each online cpu.
-	 */
-	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
-				"perf/x86/rapl:online",
-				rapl_cpu_online, rapl_cpu_offline);
+	rapl_pmus_pkg->cntr_mask = perf_msr_probe(rapl_model->rapl_pkg_msrs,
+						  PERF_RAPL_PKG_EVENTS_MAX, false,
+						  (void *) &rapl_model->pkg_events);
+
+	ret = perf_pmu_register(&rapl_pmus_pkg->pmu, "power", -1);
 	if (ret)
 		goto out;
 
-	ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
-	if (ret)
-		goto out1;
+	if (rapl_model->core_events) {
+		ret = init_rapl_pmus(&rapl_pmus_core, PERF_PMU_SCOPE_CORE,
+				     rapl_core_attr_groups,
+				     rapl_core_attr_update);
+		if (ret) {
+			pr_warn("power-core PMU initialization failed (%d)\n", ret);
+			goto core_init_failed;
+		}
+
+		rapl_pmus_core->cntr_mask = perf_msr_probe(rapl_model->rapl_core_msrs,
+						     PERF_RAPL_CORE_EVENTS_MAX, false,
+						     (void *) &rapl_model->core_events);
+
+		ret = perf_pmu_register(&rapl_pmus_core->pmu, "power_core", -1);
+		if (ret) {
+			pr_warn("power-core PMU registration failed (%d)\n", ret);
+			cleanup_rapl_pmus(rapl_pmus_core);
+		}
+	}
 
+core_init_failed:
 	rapl_advertise();
 	return 0;
 
-out1:
-	cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
 out:
 	pr_warn("Initialization failed (%d), disabled\n", ret);
-	cleanup_rapl_pmus();
+	cleanup_rapl_pmus(rapl_pmus_pkg);
 	return ret;
 }
 module_init(rapl_pmu_init);
 
 static void __exit intel_rapl_exit(void)
 {
-	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE);
-	perf_pmu_unregister(&rapl_pmus->pmu);
-	cleanup_rapl_pmus();
+	if (rapl_pmus_core) {
+		perf_pmu_unregister(&rapl_pmus_core->pmu);
+		cleanup_rapl_pmus(rapl_pmus_core);
+	}
+	perf_pmu_unregister(&rapl_pmus_pkg->pmu);
+	cleanup_rapl_pmus(rapl_pmus_pkg);
 }
 module_exit(intel_rapl_exit);