1 files changed, 67 insertions, 92 deletions

diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index b985ca79cf97..a8defc813c36 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -103,6 +103,19 @@ 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_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;
@@ -135,14 +148,29 @@ struct rapl_model {
  /* 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 u64 rapl_timer_ms;
 static struct perf_msr *rapl_msrs;
 
+/*
+ * Helper functions to get the correct topology macros according to the
+ * RAPL PMU scope.
+ */
+static inline unsigned int get_rapl_pmu_idx(int cpu)
+{
+	return rapl_pmu_is_pkg_scope() ? topology_logical_package_id(cpu) :
+					 topology_logical_die_id(cpu);
+}
+
+static inline const struct cpumask *get_rapl_pmu_cpumask(int cpu)
+{
+	return rapl_pmu_is_pkg_scope() ? topology_core_cpumask(cpu) :
+					 topology_die_cpumask(cpu);
+}
+
 static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
 {
-	unsigned int rapl_pmu_idx = topology_logical_die_id(cpu);
+	unsigned int rapl_pmu_idx = get_rapl_pmu_idx(cpu);
 
 	/*
 	 * The unsigned check also catches the '-1' return value for non
@@ -340,8 +368,6 @@ 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)
 		return -EINVAL;
 
@@ -360,7 +386,6 @@ static int rapl_pmu_event_init(struct perf_event *event)
 	pmu = cpu_to_rapl_pmu(event->cpu);
 	if (!pmu)
 		return -EINVAL;
-	event->cpu = pmu->cpu;
 	event->pmu_private = pmu;
 	event->hw.event_base = rapl_msrs[bit].msr;
 	event->hw.config = cfg;
@@ -374,23 +399,6 @@ 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");
@@ -438,7 +446,6 @@ 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,
@@ -541,60 +548,6 @@ 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 int rapl_check_hw_unit(struct rapl_model *rm)
 {
 	u64 msr_rapl_power_unit_bits;
@@ -673,9 +626,41 @@ static const struct attribute_group *rapl_attr_update[] = {
 	NULL,
 };
 
+static int __init init_rapl_pmu(void)
+{
+	struct rapl_pmu *pmu;
+	int idx;
+
+	for (idx = 0; idx < rapl_pmus->nr_rapl_pmu; idx++) {
+		pmu = kzalloc(sizeof(*pmu), GFP_KERNEL);
+		if (!pmu)
+			goto free;
+
+		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[idx] = pmu;
+	}
+
+	return 0;
+free:
+	for (; idx > 0; idx--)
+		kfree(rapl_pmus->pmus[idx - 1]);
+	return -ENOMEM;
+}
+
 static int __init init_rapl_pmus(void)
 {
-	int nr_rapl_pmu = topology_max_packages() * topology_max_dies_per_package();
+	int nr_rapl_pmu = topology_max_packages();
+	int rapl_pmu_scope = PERF_PMU_SCOPE_PKG;
+
+	if (!rapl_pmu_is_pkg_scope()) {
+		nr_rapl_pmu *= topology_max_dies_per_package();
+		rapl_pmu_scope = PERF_PMU_SCOPE_DIE;
+	}
 
 	rapl_pmus = kzalloc(struct_size(rapl_pmus, pmus, nr_rapl_pmu), GFP_KERNEL);
 	if (!rapl_pmus)
@@ -691,9 +676,11 @@ 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;
+
+	return init_rapl_pmu();
 }
 
 static struct rapl_model model_snb = {
@@ -839,24 +826,13 @@ static int __init rapl_pmu_init(void)
 	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);
-	if (ret)
-		goto out;
-
 	ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
 	if (ret)
-		goto out1;
+		goto out;
 
 	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();
@@ -866,7 +842,6 @@ 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();
 }