1 files changed, 154 insertions, 86 deletions

diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 8d7d8d4de9d..af9e35e8836 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -23,7 +23,10 @@
 #include <linux/kernel.h>
 #include <linux/of.h>
 #include <linux/platform_device.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>
@@ -32,6 +35,7 @@
 /* Set at runtime when we know what CPU type we are. */
 static struct arm_pmu *cpu_pmu;
 
+static DEFINE_PER_CPU(struct arm_pmu *, percpu_pmu);
 static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events);
 static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask);
 static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events);
@@ -45,7 +49,7 @@ const char *perf_pmu_name(void)
 	if (!cpu_pmu)
 		return NULL;
 
-	return cpu_pmu->pmu.name;
+	return cpu_pmu->name;
 }
 EXPORT_SYMBOL_GPL(perf_pmu_name);
 
@@ -67,26 +71,52 @@ EXPORT_SYMBOL_GPL(perf_num_counters);
 
 static struct pmu_hw_events *cpu_pmu_get_cpu_events(void)
 {
-	return &__get_cpu_var(cpu_hw_events);
+	return this_cpu_ptr(&cpu_hw_events);
 }
 
-static void cpu_pmu_free_irq(void)
+static void cpu_pmu_enable_percpu_irq(void *data)
+{
+	struct arm_pmu *cpu_pmu = data;
+	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	int irq = platform_get_irq(pmu_device, 0);
+
+	enable_percpu_irq(irq, IRQ_TYPE_NONE);
+	cpumask_set_cpu(smp_processor_id(), &cpu_pmu->active_irqs);
+}
+
+static void cpu_pmu_disable_percpu_irq(void *data)
+{
+	struct arm_pmu *cpu_pmu = data;
+	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	int irq = platform_get_irq(pmu_device, 0);
+
+	cpumask_clear_cpu(smp_processor_id(), &cpu_pmu->active_irqs);
+	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;
 
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
 
-	for (i = 0; i < irqs; ++i) {
-		if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs))
-			continue;
-		irq = platform_get_irq(pmu_device, i);
-		if (irq >= 0)
-			free_irq(irq, cpu_pmu);
+	irq = platform_get_irq(pmu_device, 0);
+	if (irq >= 0 && irq_is_percpu(irq)) {
+		on_each_cpu(cpu_pmu_disable_percpu_irq, cpu_pmu, 1);
+		free_percpu_irq(irq, &percpu_pmu);
+	} else {
+		for (i = 0; i < irqs; ++i) {
+			if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs))
+				continue;
+			irq = platform_get_irq(pmu_device, i);
+			if (irq >= 0)
+				free_irq(irq, cpu_pmu);
+		}
 	}
 }
 
-static int cpu_pmu_request_irq(irq_handler_t handler)
+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;
@@ -96,42 +126,54 @@ static int cpu_pmu_request_irq(irq_handler_t handler)
 
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
 	if (irqs < 1) {
-		pr_err("no irqs for PMUs defined\n");
-		return -ENODEV;
+		printk_once("perf/ARM: No irqs for PMU defined, sampling events not supported\n");
+		return 0;
 	}
 
-	for (i = 0; i < irqs; ++i) {
-		err = 0;
-		irq = platform_get_irq(pmu_device, i);
-		if (irq < 0)
-			continue;
-
-		/*
-		 * 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(i)) && irqs > 1) {
-			pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
-				    irq, i);
-			continue;
-		}
-
-		err = request_irq(irq, handler, IRQF_NOBALANCING, "arm-pmu",
-				  cpu_pmu);
+	irq = platform_get_irq(pmu_device, 0);
+	if (irq >= 0 && irq_is_percpu(irq)) {
+		err = request_percpu_irq(irq, handler, "arm-pmu", &percpu_pmu);
 		if (err) {
 			pr_err("unable to request IRQ%d for ARM PMU counters\n",
 				irq);
 			return err;
 		}
-
-		cpumask_set_cpu(i, &cpu_pmu->active_irqs);
+		on_each_cpu(cpu_pmu_enable_percpu_irq, cpu_pmu, 1);
+	} else {
+		for (i = 0; i < irqs; ++i) {
+			err = 0;
+			irq = platform_get_irq(pmu_device, i);
+			if (irq < 0)
+				continue;
+
+			/*
+			 * 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(i)) && irqs > 1) {
+				pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
+					    irq, i);
+				continue;
+			}
+
+			err = request_irq(irq, handler,
+					  IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
+					  cpu_pmu);
+			if (err) {
+				pr_err("unable to request IRQ%d for ARM PMU counters\n",
+					irq);
+				return err;
+			}
+
+			cpumask_set_cpu(i, &cpu_pmu->active_irqs);
+		}
 	}
 
 	return 0;
 }
 
-static void __devinit cpu_pmu_init(struct arm_pmu *cpu_pmu)
+static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	int cpu;
 	for_each_possible_cpu(cpu) {
@@ -139,6 +181,7 @@ static void __devinit cpu_pmu_init(struct arm_pmu *cpu_pmu)
 		events->events = per_cpu(hw_events, cpu);
 		events->used_mask = per_cpu(used_mask, cpu);
 		raw_spin_lock_init(&events->pmu_lock);
+		per_cpu(percpu_pmu, cpu) = cpu_pmu;
 	}
 
 	cpu_pmu->get_hw_events	= cpu_pmu_get_cpu_events;
@@ -146,8 +189,12 @@ static void __devinit cpu_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->free_irq	= cpu_pmu_free_irq;
 
 	/* Ensure the PMU has sane values out of reset. */
-	if (cpu_pmu && cpu_pmu->reset)
-		on_each_cpu(cpu_pmu->reset, NULL, 1);
+	if (cpu_pmu->reset)
+		on_each_cpu(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;
 }
 
 /*
@@ -156,27 +203,31 @@ static void __devinit cpu_pmu_init(struct arm_pmu *cpu_pmu)
  * UNKNOWN at reset, the PMU must be explicitly reset to avoid reading
  * junk values out of them.
  */
-static int __cpuinit cpu_pmu_notify(struct notifier_block *b,
-				    unsigned long action, void *hcpu)
+static int cpu_pmu_notify(struct notifier_block *b, unsigned long action,
+			  void *hcpu)
 {
 	if ((action & ~CPU_TASKS_FROZEN) != CPU_STARTING)
 		return NOTIFY_DONE;
 
 	if (cpu_pmu && cpu_pmu->reset)
-		cpu_pmu->reset(NULL);
+		cpu_pmu->reset(cpu_pmu);
+	else
+		return NOTIFY_DONE;
 
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata cpu_pmu_hotplug_notifier = {
+static struct notifier_block cpu_pmu_hotplug_notifier = {
 	.notifier_call = cpu_pmu_notify,
 };
 
 /*
  * PMU platform driver and devicetree bindings.
  */
-static struct of_device_id __devinitdata cpu_pmu_of_device_ids[] = {
+static struct of_device_id cpu_pmu_of_device_ids[] = {
+	{.compatible = "arm,cortex-a17-pmu",	.data = armv7_a17_pmu_init},
 	{.compatible = "arm,cortex-a15-pmu",	.data = armv7_a15_pmu_init},
+	{.compatible = "arm,cortex-a12-pmu",	.data = armv7_a12_pmu_init},
 	{.compatible = "arm,cortex-a9-pmu",	.data = armv7_a9_pmu_init},
 	{.compatible = "arm,cortex-a8-pmu",	.data = armv7_a8_pmu_init},
 	{.compatible = "arm,cortex-a7-pmu",	.data = armv7_a7_pmu_init},
@@ -184,10 +235,11 @@ static struct of_device_id __devinitdata cpu_pmu_of_device_ids[] = {
 	{.compatible = "arm,arm11mpcore-pmu",	.data = armv6mpcore_pmu_init},
 	{.compatible = "arm,arm1176-pmu",	.data = armv6pmu_init},
 	{.compatible = "arm,arm1136-pmu",	.data = armv6pmu_init},
+	{.compatible = "qcom,krait-pmu",	.data = krait_pmu_init},
 	{},
 };
 
-static struct platform_device_id __devinitdata cpu_pmu_plat_device_ids[] = {
+static struct platform_device_id cpu_pmu_plat_device_ids[] = {
 	{.name = "arm-pmu"},
 	{},
 };
@@ -195,87 +247,93 @@ static struct platform_device_id __devinitdata cpu_pmu_plat_device_ids[] = {
 /*
  * CPU PMU identification and probing.
  */
-static struct arm_pmu *__devinit probe_current_pmu(void)
+static int probe_current_pmu(struct arm_pmu *pmu)
 {
-	struct arm_pmu *pmu = NULL;
 	int cpu = get_cpu();
-	unsigned long cpuid = read_cpuid_id();
-	unsigned long implementor = (cpuid & 0xFF000000) >> 24;
-	unsigned long part_number = (cpuid & 0xFFF0);
+	unsigned long implementor = read_cpuid_implementor();
+	unsigned long part_number = read_cpuid_part_number();
+	int ret = -ENODEV;
 
 	pr_info("probing PMU on CPU %d\n", cpu);
 
 	/* ARM Ltd CPUs. */
-	if (0x41 == implementor) {
+	if (implementor == ARM_CPU_IMP_ARM) {
 		switch (part_number) {
-		case 0xB360:	/* ARM1136 */
-		case 0xB560:	/* ARM1156 */
-		case 0xB760:	/* ARM1176 */
-			pmu = armv6pmu_init();
-			break;
-		case 0xB020:	/* ARM11mpcore */
-			pmu = armv6mpcore_pmu_init();
-			break;
-		case 0xC080:	/* Cortex-A8 */
-			pmu = armv7_a8_pmu_init();
-			break;
-		case 0xC090:	/* Cortex-A9 */
-			pmu = armv7_a9_pmu_init();
+		case ARM_CPU_PART_ARM1136:
+		case ARM_CPU_PART_ARM1156:
+		case ARM_CPU_PART_ARM1176:
+			ret = armv6pmu_init(pmu);
 			break;
-		case 0xC050:	/* Cortex-A5 */
-			pmu = armv7_a5_pmu_init();
+		case ARM_CPU_PART_ARM11MPCORE:
+			ret = armv6mpcore_pmu_init(pmu);
 			break;
-		case 0xC0F0:	/* Cortex-A15 */
-			pmu = armv7_a15_pmu_init();
+		case ARM_CPU_PART_CORTEX_A8:
+			ret = armv7_a8_pmu_init(pmu);
 			break;
-		case 0xC070:	/* Cortex-A7 */
-			pmu = armv7_a7_pmu_init();
+		case ARM_CPU_PART_CORTEX_A9:
+			ret = armv7_a9_pmu_init(pmu);
 			break;
 		}
 	/* Intel CPUs [xscale]. */
-	} else if (0x69 == implementor) {
-		part_number = (cpuid >> 13) & 0x7;
-		switch (part_number) {
-		case 1:
-			pmu = xscale1pmu_init();
+	} else if (implementor == ARM_CPU_IMP_INTEL) {
+		switch (xscale_cpu_arch_version()) {
+		case ARM_CPU_XSCALE_ARCH_V1:
+			ret = xscale1pmu_init(pmu);
 			break;
-		case 2:
-			pmu = xscale2pmu_init();
+		case ARM_CPU_XSCALE_ARCH_V2:
+			ret = xscale2pmu_init(pmu);
 			break;
 		}
 	}
 
 	put_cpu();
-	return pmu;
+	return ret;
 }
 
-static int __devinit cpu_pmu_device_probe(struct platform_device *pdev)
+static int cpu_pmu_device_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id;
-	struct arm_pmu *(*init_fn)(void);
+	const int (*init_fn)(struct arm_pmu *);
 	struct device_node *node = pdev->dev.of_node;
+	struct arm_pmu *pmu;
+	int ret = -ENODEV;
 
 	if (cpu_pmu) {
 		pr_info("attempt to register multiple PMU devices!");
 		return -ENOSPC;
 	}
 
+	pmu = kzalloc(sizeof(struct arm_pmu), GFP_KERNEL);
+	if (!pmu) {
+		pr_info("failed to allocate PMU device!");
+		return -ENOMEM;
+	}
+
+	cpu_pmu = pmu;
+	cpu_pmu->plat_device = pdev;
+
 	if (node && (of_id = of_match_node(cpu_pmu_of_device_ids, pdev->dev.of_node))) {
 		init_fn = of_id->data;
-		cpu_pmu = init_fn();
+		ret = init_fn(pmu);
 	} else {
-		cpu_pmu = probe_current_pmu();
+		ret = probe_current_pmu(pmu);
 	}
 
-	if (!cpu_pmu)
-		return -ENODEV;
+	if (ret) {
+		pr_info("failed to probe PMU!");
+		goto out_free;
+	}
 
-	cpu_pmu->plat_device = pdev;
 	cpu_pmu_init(cpu_pmu);
-	register_cpu_notifier(&cpu_pmu_hotplug_notifier);
-	armpmu_register(cpu_pmu, cpu_pmu->name, PERF_TYPE_RAW);
+	ret = armpmu_register(cpu_pmu, PERF_TYPE_RAW);
 
-	return 0;
+	if (!ret)
+		return 0;
+
+out_free:
+	pr_info("failed to register PMU devices!");
+	kfree(pmu);
+	return ret;
 }
 
 static struct platform_driver cpu_pmu_driver = {
@@ -290,6 +348,16 @@ static struct platform_driver cpu_pmu_driver = {
 
 static int __init register_pmu_driver(void)
 {
-	return platform_driver_register(&cpu_pmu_driver);
+	int err;
+
+	err = register_cpu_notifier(&cpu_pmu_hotplug_notifier);
+	if (err)
+		return err;
+
+	err = platform_driver_register(&cpu_pmu_driver);
+	if (err)
+		unregister_cpu_notifier(&cpu_pmu_hotplug_notifier);
+
+	return err;
 }
 device_initcall(register_pmu_driver);