1 files changed, 375 insertions, 33 deletions

diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 4a86a0133ac3..357f57ea83f4 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -11,12 +11,18 @@
  */
 #define pr_fmt(fmt) "hw perfevents: " fmt
 
+#include <linux/bitmap.h>
+#include <linux/cpumask.h>
+#include <linux/export.h>
 #include <linux/kernel.h>
+#include <linux/of.h>
 #include <linux/platform_device.h>
-#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
 #include <linux/irq.h>
 #include <linux/irqdesc.h>
 
+#include <asm/cputype.h>
 #include <asm/irq_regs.h>
 #include <asm/pmu.h>
 
@@ -229,6 +235,10 @@ armpmu_add(struct perf_event *event, int flags)
 	int idx;
 	int err = 0;
 
+	/* An event following a process won't be stopped earlier */
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
+		return -ENOENT;
+
 	perf_pmu_disable(event->pmu);
 
 	/* If we don't have a space for the counter then finish early. */
@@ -344,20 +354,12 @@ static void
 armpmu_release_hardware(struct arm_pmu *armpmu)
 {
 	armpmu->free_irq(armpmu);
-	pm_runtime_put_sync(&armpmu->plat_device->dev);
 }
 
 static int
 armpmu_reserve_hardware(struct arm_pmu *armpmu)
 {
-	int err;
-	struct platform_device *pmu_device = armpmu->plat_device;
-
-	if (!pmu_device)
-		return -ENODEV;
-
-	pm_runtime_get_sync(&pmu_device->dev);
-	err = armpmu->request_irq(armpmu, armpmu_dispatch_irq);
+	int err = armpmu->request_irq(armpmu, armpmu_dispatch_irq);
 	if (err) {
 		armpmu_release_hardware(armpmu);
 		return err;
@@ -454,6 +456,17 @@ static int armpmu_event_init(struct perf_event *event)
 	int err = 0;
 	atomic_t *active_events = &armpmu->active_events;
 
+	/*
+	 * Reject CPU-affine events for CPUs that are of a different class to
+	 * that which this PMU handles. Process-following events (where
+	 * event->cpu == -1) can be migrated between CPUs, and thus we have to
+	 * reject them later (in armpmu_add) if they're scheduled on a
+	 * different class of CPU.
+	 */
+	if (event->cpu != -1 &&
+		!cpumask_test_cpu(event->cpu, &armpmu->supported_cpus))
+		return -ENOENT;
+
 	/* does not support taken branch sampling */
 	if (has_branch_stack(event))
 		return -EOPNOTSUPP;
@@ -489,6 +502,10 @@ static void armpmu_enable(struct pmu *pmu)
 	struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
 	int enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events);
 
+	/* For task-bound events we may be called on other CPUs */
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
+		return;
+
 	if (enabled)
 		armpmu->start(armpmu);
 }
@@ -496,34 +513,25 @@ static void armpmu_enable(struct pmu *pmu)
 static void armpmu_disable(struct pmu *pmu)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(pmu);
-	armpmu->stop(armpmu);
-}
-
-#ifdef CONFIG_PM
-static int armpmu_runtime_resume(struct device *dev)
-{
-	struct arm_pmu_platdata *plat = dev_get_platdata(dev);
 
-	if (plat && plat->runtime_resume)
-		return plat->runtime_resume(dev);
+	/* For task-bound events we may be called on other CPUs */
+	if (!cpumask_test_cpu(smp_processor_id(), &armpmu->supported_cpus))
+		return;
 
-	return 0;
+	armpmu->stop(armpmu);
 }
 
-static int armpmu_runtime_suspend(struct device *dev)
+/*
+ * In heterogeneous systems, events are specific to a particular
+ * microarchitecture, and aren't suitable for another. Thus, only match CPUs of
+ * the same microarchitecture.
+ */
+static int armpmu_filter_match(struct perf_event *event)
 {
-	struct arm_pmu_platdata *plat = dev_get_platdata(dev);
-
-	if (plat && plat->runtime_suspend)
-		return plat->runtime_suspend(dev);
-
-	return 0;
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+	unsigned int cpu = smp_processor_id();
+	return cpumask_test_cpu(cpu, &armpmu->supported_cpus);
 }
-#endif
-
-const struct dev_pm_ops armpmu_dev_pm_ops = {
-	SET_RUNTIME_PM_OPS(armpmu_runtime_suspend, armpmu_runtime_resume, NULL)
-};
 
 static void armpmu_init(struct arm_pmu *armpmu)
 {
@@ -539,15 +547,349 @@ static void armpmu_init(struct arm_pmu *armpmu)
 		.start		= armpmu_start,
 		.stop		= armpmu_stop,
 		.read		= armpmu_read,
+		.filter_match	= armpmu_filter_match,
 	};
 }
 
 int armpmu_register(struct arm_pmu *armpmu, int type)
 {
 	armpmu_init(armpmu);
-	pm_runtime_enable(&armpmu->plat_device->dev);
 	pr_info("enabled with %s PMU driver, %d counters available\n",
 			armpmu->name, armpmu->num_events);
 	return perf_pmu_register(&armpmu->pmu, armpmu->name, type);
 }
 
+/* Set at runtime when we know what CPU type we are. */
+static struct arm_pmu *__oprofile_cpu_pmu;
+
+/*
+ * Despite the names, these two functions are CPU-specific and are used
+ * by the OProfile/perf code.
+ */
+const char *perf_pmu_name(void)
+{
+	if (!__oprofile_cpu_pmu)
+		return NULL;
+
+	return __oprofile_cpu_pmu->name;
+}
+EXPORT_SYMBOL_GPL(perf_pmu_name);
+
+int perf_num_counters(void)
+{
+	int max_events = 0;
+
+	if (__oprofile_cpu_pmu != NULL)
+		max_events = __oprofile_cpu_pmu->num_events;
+
+	return max_events;
+}
+EXPORT_SYMBOL_GPL(perf_num_counters);
+
+static void cpu_pmu_enable_percpu_irq(void *data)
+{
+	int irq = *(int *)data;
+
+	enable_percpu_irq(irq, IRQ_TYPE_NONE);
+}
+
+static void cpu_pmu_disable_percpu_irq(void *data)
+{
+	int irq = *(int *)data;
+
+	disable_percpu_irq(irq);
+}
+
+static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
+{
+	int i, irq, irqs;
+	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	struct pmu_hw_events __percpu *hw_events = cpu_pmu->hw_events;
+
+	irqs = min(pmu_device->num_resources, num_possible_cpus());
+
+	irq = platform_get_irq(pmu_device, 0);
+	if (irq >= 0 && irq_is_percpu(irq)) {
+		on_each_cpu(cpu_pmu_disable_percpu_irq, &irq, 1);
+		free_percpu_irq(irq, &hw_events->percpu_pmu);
+	} else {
+		for (i = 0; i < irqs; ++i) {
+			int cpu = i;
+
+			if (cpu_pmu->irq_affinity)
+				cpu = cpu_pmu->irq_affinity[i];
+
+			if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs))
+				continue;
+			irq = platform_get_irq(pmu_device, i);
+			if (irq >= 0)
+				free_irq(irq, per_cpu_ptr(&hw_events->percpu_pmu, cpu));
+		}
+	}
+}
+
+static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
+{
+	int i, err, irq, irqs;
+	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	struct pmu_hw_events __percpu *hw_events = cpu_pmu->hw_events;
+
+	if (!pmu_device)
+		return -ENODEV;
+
+	irqs = min(pmu_device->num_resources, num_possible_cpus());
+	if (irqs < 1) {
+		pr_warn_once("perf/ARM: No irqs for PMU defined, sampling events not supported\n");
+		return 0;
+	}
+
+	irq = platform_get_irq(pmu_device, 0);
+	if (irq >= 0 && irq_is_percpu(irq)) {
+		err = request_percpu_irq(irq, handler, "arm-pmu",
+					 &hw_events->percpu_pmu);
+		if (err) {
+			pr_err("unable to request IRQ%d for ARM PMU counters\n",
+				irq);
+			return err;
+		}
+		on_each_cpu(cpu_pmu_enable_percpu_irq, &irq, 1);
+	} else {
+		for (i = 0; i < irqs; ++i) {
+			int cpu = i;
+
+			err = 0;
+			irq = platform_get_irq(pmu_device, i);
+			if (irq < 0)
+				continue;
+
+			if (cpu_pmu->irq_affinity)
+				cpu = cpu_pmu->irq_affinity[i];
+
+			/*
+			 * If we have a single PMU interrupt that we can't shift,
+			 * assume that we're running on a uniprocessor machine and
+			 * continue. Otherwise, continue without this interrupt.
+			 */
+			if (irq_set_affinity(irq, cpumask_of(cpu)) && irqs > 1) {
+				pr_warn("unable to set irq affinity (irq=%d, cpu=%u)\n",
+					irq, cpu);
+				continue;
+			}
+
+			err = request_irq(irq, handler,
+					  IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
+					  per_cpu_ptr(&hw_events->percpu_pmu, cpu));
+			if (err) {
+				pr_err("unable to request IRQ%d for ARM PMU counters\n",
+					irq);
+				return err;
+			}
+
+			cpumask_set_cpu(cpu, &cpu_pmu->active_irqs);
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * PMU hardware loses all context when a CPU goes offline.
+ * When a CPU is hotplugged back in, since some hardware registers are
+ * UNKNOWN at reset, the PMU must be explicitly reset to avoid reading
+ * junk values out of them.
+ */
+static int cpu_pmu_notify(struct notifier_block *b, unsigned long action,
+			  void *hcpu)
+{
+	int cpu = (unsigned long)hcpu;
+	struct arm_pmu *pmu = container_of(b, struct arm_pmu, hotplug_nb);
+
+	if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
+		return NOTIFY_DONE;
+
+	if (!cpumask_test_cpu(cpu, &pmu->supported_cpus))
+		return NOTIFY_DONE;
+
+	if (pmu->reset)
+		pmu->reset(pmu);
+	else
+		return NOTIFY_DONE;
+
+	return NOTIFY_OK;
+}
+
+static int cpu_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	int err;
+	int cpu;
+	struct pmu_hw_events __percpu *cpu_hw_events;
+
+	cpu_hw_events = alloc_percpu(struct pmu_hw_events);
+	if (!cpu_hw_events)
+		return -ENOMEM;
+
+	cpu_pmu->hotplug_nb.notifier_call = cpu_pmu_notify;
+	err = register_cpu_notifier(&cpu_pmu->hotplug_nb);
+	if (err)
+		goto out_hw_events;
+
+	for_each_possible_cpu(cpu) {
+		struct pmu_hw_events *events = per_cpu_ptr(cpu_hw_events, cpu);
+		raw_spin_lock_init(&events->pmu_lock);
+		events->percpu_pmu = cpu_pmu;
+	}
+
+	cpu_pmu->hw_events	= cpu_hw_events;
+	cpu_pmu->request_irq	= cpu_pmu_request_irq;
+	cpu_pmu->free_irq	= cpu_pmu_free_irq;
+
+	/* Ensure the PMU has sane values out of reset. */
+	if (cpu_pmu->reset)
+		on_each_cpu_mask(&cpu_pmu->supported_cpus, cpu_pmu->reset,
+			 cpu_pmu, 1);
+
+	/* If no interrupts available, set the corresponding capability flag */
+	if (!platform_get_irq(cpu_pmu->plat_device, 0))
+		cpu_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
+
+	return 0;
+
+out_hw_events:
+	free_percpu(cpu_hw_events);
+	return err;
+}
+
+static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
+{
+	unregister_cpu_notifier(&cpu_pmu->hotplug_nb);
+	free_percpu(cpu_pmu->hw_events);
+}
+
+/*
+ * CPU PMU identification and probing.
+ */
+static int probe_current_pmu(struct arm_pmu *pmu,
+			     const struct pmu_probe_info *info)
+{
+	int cpu = get_cpu();
+	unsigned int cpuid = read_cpuid_id();
+	int ret = -ENODEV;
+
+	pr_info("probing PMU on CPU %d\n", cpu);
+
+	for (; info->init != NULL; info++) {
+		if ((cpuid & info->mask) != info->cpuid)
+			continue;
+		ret = info->init(pmu);
+		break;
+	}
+
+	put_cpu();
+	return ret;
+}
+
+static int of_pmu_irq_cfg(struct arm_pmu *pmu)
+{
+	int i, irq, *irqs;
+	struct platform_device *pdev = pmu->plat_device;
+
+	/* Don't bother with PPIs; they're already affine */
+	irq = platform_get_irq(pdev, 0);
+	if (irq >= 0 && irq_is_percpu(irq))
+		return 0;
+
+	irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
+	if (!irqs)
+		return -ENOMEM;
+
+	for (i = 0; i < pdev->num_resources; ++i) {
+		struct device_node *dn;
+		int cpu;
+
+		dn = of_parse_phandle(pdev->dev.of_node, "interrupt-affinity",
+				      i);
+		if (!dn) {
+			pr_warn("Failed to parse %s/interrupt-affinity[%d]\n",
+				of_node_full_name(pdev->dev.of_node), i);
+			break;
+		}
+
+		for_each_possible_cpu(cpu)
+			if (arch_find_n_match_cpu_physical_id(dn, cpu, NULL))
+				break;
+
+		of_node_put(dn);
+		if (cpu >= nr_cpu_ids) {
+			pr_warn("Failed to find logical CPU for %s\n",
+				dn->name);
+			break;
+		}
+
+		irqs[i] = cpu;
+		cpumask_set_cpu(cpu, &pmu->supported_cpus);
+	}
+
+	if (i == pdev->num_resources) {
+		pmu->irq_affinity = irqs;
+	} else {
+		kfree(irqs);
+		cpumask_setall(&pmu->supported_cpus);
+	}
+
+	return 0;
+}
+
+int arm_pmu_device_probe(struct platform_device *pdev,
+			 const struct of_device_id *of_table,
+			 const struct pmu_probe_info *probe_table)
+{
+	const struct of_device_id *of_id;
+	const int (*init_fn)(struct arm_pmu *);
+	struct device_node *node = pdev->dev.of_node;
+	struct arm_pmu *pmu;
+	int ret = -ENODEV;
+
+	pmu = kzalloc(sizeof(struct arm_pmu), GFP_KERNEL);
+	if (!pmu) {
+		pr_info("failed to allocate PMU device!\n");
+		return -ENOMEM;
+	}
+
+	if (!__oprofile_cpu_pmu)
+		__oprofile_cpu_pmu = pmu;
+
+	pmu->plat_device = pdev;
+
+	if (node && (of_id = of_match_node(of_table, pdev->dev.of_node))) {
+		init_fn = of_id->data;
+
+		ret = of_pmu_irq_cfg(pmu);
+		if (!ret)
+			ret = init_fn(pmu);
+	} else {
+		ret = probe_current_pmu(pmu, probe_table);
+		cpumask_setall(&pmu->supported_cpus);
+	}
+
+	if (ret) {
+		pr_info("failed to probe PMU!\n");
+		goto out_free;
+	}
+
+	ret = cpu_pmu_init(pmu);
+	if (ret)
+		goto out_free;
+
+	ret = armpmu_register(pmu, -1);
+	if (ret)
+		goto out_destroy;
+
+	return 0;
+
+out_destroy:
+	cpu_pmu_destroy(pmu);
+out_free:
+	pr_info("failed to register PMU devices!\n");
+	kfree(pmu);
+	return ret;
+}