From: Robert Richter <robert.richter@amd.com>
Date: Fri, 15 Oct 2010 10:45:00 +0000 (+0200)
Subject: Merge remote branch 'tip/perf/core' into oprofile/core
X-Git-Tag: v2.6.37-rc1~214^2~18^2~3
X-Git-Url: https://openfabrics.org/gitweb/?a=commitdiff_plain;h=6268464b370e234e0255330190f9bd5d19386ad7;p=~shefty%2Frdma-dev.git

Merge remote branch 'tip/perf/core' into oprofile/core

Conflicts:
	arch/arm/oprofile/common.c
	kernel/perf_event.c
---

6268464b370e234e0255330190f9bd5d19386ad7
diff --cc drivers/oprofile/oprofile_perf.c
index b17235a24a4,00000000000..79c0005134a
mode 100644,000000..100644
--- a/drivers/oprofile/oprofile_perf.c
+++ b/drivers/oprofile/oprofile_perf.c
@@@ -1,323 -1,0 +1,323 @@@
 +/*
 + * Copyright 2010 ARM Ltd.
 + *
 + * Perf-events backend for OProfile.
 + */
 +#include <linux/perf_event.h>
 +#include <linux/oprofile.h>
 +#include <linux/slab.h>
 +
 +/*
 + * Per performance monitor configuration as set via oprofilefs.
 + */
 +struct op_counter_config {
 +	unsigned long count;
 +	unsigned long enabled;
 +	unsigned long event;
 +	unsigned long unit_mask;
 +	unsigned long kernel;
 +	unsigned long user;
 +	struct perf_event_attr attr;
 +};
 +
 +static int oprofile_perf_enabled;
 +static DEFINE_MUTEX(oprofile_perf_mutex);
 +
 +static struct op_counter_config *counter_config;
 +static struct perf_event **perf_events[nr_cpumask_bits];
 +static int num_counters;
 +
 +/*
 + * Overflow callback for oprofile.
 + */
 +static void op_overflow_handler(struct perf_event *event, int unused,
 +			struct perf_sample_data *data, struct pt_regs *regs)
 +{
 +	int id;
 +	u32 cpu = smp_processor_id();
 +
 +	for (id = 0; id < num_counters; ++id)
 +		if (perf_events[cpu][id] == event)
 +			break;
 +
 +	if (id != num_counters)
 +		oprofile_add_sample(regs, id);
 +	else
 +		pr_warning("oprofile: ignoring spurious overflow "
 +				"on cpu %u\n", cpu);
 +}
 +
 +/*
 + * Called by oprofile_perf_setup to create perf attributes to mirror the oprofile
 + * settings in counter_config. Attributes are created as `pinned' events and
 + * so are permanently scheduled on the PMU.
 + */
 +static void op_perf_setup(void)
 +{
 +	int i;
 +	u32 size = sizeof(struct perf_event_attr);
 +	struct perf_event_attr *attr;
 +
 +	for (i = 0; i < num_counters; ++i) {
 +		attr = &counter_config[i].attr;
 +		memset(attr, 0, size);
 +		attr->type		= PERF_TYPE_RAW;
 +		attr->size		= size;
 +		attr->config		= counter_config[i].event;
 +		attr->sample_period	= counter_config[i].count;
 +		attr->pinned		= 1;
 +	}
 +}
 +
 +static int op_create_counter(int cpu, int event)
 +{
 +	struct perf_event *pevent;
 +
 +	if (!counter_config[event].enabled || perf_events[cpu][event])
 +		return 0;
 +
 +	pevent = perf_event_create_kernel_counter(&counter_config[event].attr,
- 						  cpu, -1,
++						  cpu, NULL,
 +						  op_overflow_handler);
 +
 +	if (IS_ERR(pevent))
 +		return PTR_ERR(pevent);
 +
 +	if (pevent->state != PERF_EVENT_STATE_ACTIVE) {
 +		perf_event_release_kernel(pevent);
 +		pr_warning("oprofile: failed to enable event %d "
 +				"on CPU %d\n", event, cpu);
 +		return -EBUSY;
 +	}
 +
 +	perf_events[cpu][event] = pevent;
 +
 +	return 0;
 +}
 +
 +static void op_destroy_counter(int cpu, int event)
 +{
 +	struct perf_event *pevent = perf_events[cpu][event];
 +
 +	if (pevent) {
 +		perf_event_release_kernel(pevent);
 +		perf_events[cpu][event] = NULL;
 +	}
 +}
 +
 +/*
 + * Called by oprofile_perf_start to create active perf events based on the
 + * perviously configured attributes.
 + */
 +static int op_perf_start(void)
 +{
 +	int cpu, event, ret = 0;
 +
 +	for_each_online_cpu(cpu) {
 +		for (event = 0; event < num_counters; ++event) {
 +			ret = op_create_counter(cpu, event);
 +			if (ret)
 +				return ret;
 +		}
 +	}
 +
 +	return ret;
 +}
 +
 +/*
 + * Called by oprofile_perf_stop at the end of a profiling run.
 + */
 +static void op_perf_stop(void)
 +{
 +	int cpu, event;
 +
 +	for_each_online_cpu(cpu)
 +		for (event = 0; event < num_counters; ++event)
 +			op_destroy_counter(cpu, event);
 +}
 +
 +static int oprofile_perf_create_files(struct super_block *sb, struct dentry *root)
 +{
 +	unsigned int i;
 +
 +	for (i = 0; i < num_counters; i++) {
 +		struct dentry *dir;
 +		char buf[4];
 +
 +		snprintf(buf, sizeof buf, "%d", i);
 +		dir = oprofilefs_mkdir(sb, root, buf);
 +		oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled);
 +		oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event);
 +		oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count);
 +		oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
 +		oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
 +		oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
 +	}
 +
 +	return 0;
 +}
 +
 +static int oprofile_perf_setup(void)
 +{
 +	spin_lock(&oprofilefs_lock);
 +	op_perf_setup();
 +	spin_unlock(&oprofilefs_lock);
 +	return 0;
 +}
 +
 +static int oprofile_perf_start(void)
 +{
 +	int ret = -EBUSY;
 +
 +	mutex_lock(&oprofile_perf_mutex);
 +	if (!oprofile_perf_enabled) {
 +		ret = 0;
 +		op_perf_start();
 +		oprofile_perf_enabled = 1;
 +	}
 +	mutex_unlock(&oprofile_perf_mutex);
 +	return ret;
 +}
 +
 +static void oprofile_perf_stop(void)
 +{
 +	mutex_lock(&oprofile_perf_mutex);
 +	if (oprofile_perf_enabled)
 +		op_perf_stop();
 +	oprofile_perf_enabled = 0;
 +	mutex_unlock(&oprofile_perf_mutex);
 +}
 +
 +#ifdef CONFIG_PM
 +static int oprofile_perf_suspend(struct platform_device *dev, pm_message_t state)
 +{
 +	mutex_lock(&oprofile_perf_mutex);
 +	if (oprofile_perf_enabled)
 +		op_perf_stop();
 +	mutex_unlock(&oprofile_perf_mutex);
 +	return 0;
 +}
 +
 +static int oprofile_perf_resume(struct platform_device *dev)
 +{
 +	mutex_lock(&oprofile_perf_mutex);
 +	if (oprofile_perf_enabled && op_perf_start())
 +		oprofile_perf_enabled = 0;
 +	mutex_unlock(&oprofile_perf_mutex);
 +	return 0;
 +}
 +
 +static struct platform_driver oprofile_driver = {
 +	.driver		= {
 +		.name		= "oprofile-perf",
 +	},
 +	.resume		= oprofile_perf_resume,
 +	.suspend	= oprofile_perf_suspend,
 +};
 +
 +static struct platform_device *oprofile_pdev;
 +
 +static int __init init_driverfs(void)
 +{
 +	int ret;
 +
 +	ret = platform_driver_register(&oprofile_driver);
 +	if (ret)
 +		return ret;
 +
 +	oprofile_pdev =	platform_device_register_simple(
 +				oprofile_driver.driver.name, 0, NULL, 0);
 +	if (IS_ERR(oprofile_pdev)) {
 +		ret = PTR_ERR(oprofile_pdev);
 +		platform_driver_unregister(&oprofile_driver);
 +	}
 +
 +	return ret;
 +}
 +
 +static void __exit exit_driverfs(void)
 +{
 +	platform_device_unregister(oprofile_pdev);
 +	platform_driver_unregister(&oprofile_driver);
 +}
 +#else
 +static int __init init_driverfs(void) { return 0; }
 +#define exit_driverfs() do { } while (0)
 +#endif /* CONFIG_PM */
 +
 +void oprofile_perf_exit(void)
 +{
 +	int cpu, id;
 +	struct perf_event *event;
 +
 +	for_each_possible_cpu(cpu) {
 +		for (id = 0; id < num_counters; ++id) {
 +			event = perf_events[cpu][id];
 +			if (event)
 +				perf_event_release_kernel(event);
 +		}
 +
 +		kfree(perf_events[cpu]);
 +	}
 +
 +	kfree(counter_config);
 +	exit_driverfs();
 +}
 +
 +int __init oprofile_perf_init(struct oprofile_operations *ops)
 +{
 +	int cpu, ret = 0;
 +
 +	ret = init_driverfs();
 +	if (ret)
 +		return ret;
 +
 +	memset(&perf_events, 0, sizeof(perf_events));
 +
 +	num_counters = perf_num_counters();
 +	if (num_counters <= 0) {
 +		pr_info("oprofile: no performance counters\n");
 +		ret = -ENODEV;
 +		goto out;
 +	}
 +
 +	counter_config = kcalloc(num_counters,
 +			sizeof(struct op_counter_config), GFP_KERNEL);
 +
 +	if (!counter_config) {
 +		pr_info("oprofile: failed to allocate %d "
 +				"counters\n", num_counters);
 +		ret = -ENOMEM;
 +		num_counters = 0;
 +		goto out;
 +	}
 +
 +	for_each_possible_cpu(cpu) {
 +		perf_events[cpu] = kcalloc(num_counters,
 +				sizeof(struct perf_event *), GFP_KERNEL);
 +		if (!perf_events[cpu]) {
 +			pr_info("oprofile: failed to allocate %d perf events "
 +					"for cpu %d\n", num_counters, cpu);
 +			ret = -ENOMEM;
 +			goto out;
 +		}
 +	}
 +
 +	ops->create_files	= oprofile_perf_create_files;
 +	ops->setup		= oprofile_perf_setup;
 +	ops->start		= oprofile_perf_start;
 +	ops->stop		= oprofile_perf_stop;
 +	ops->shutdown		= oprofile_perf_stop;
 +	ops->cpu_type		= op_name_from_perf_id();
 +
 +	if (!ops->cpu_type)
 +		ret = -ENODEV;
 +	else
 +		pr_info("oprofile: using %s\n", ops->cpu_type);
 +
 +out:
 +	if (ret)
 +		oprofile_perf_exit();
 +
 +	return ret;
 +}
diff --cc include/linux/perf_event.h
index 33f08dafda2,61b1e2d760f..a9227e98520
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@@ -842,18 -887,11 +887,13 @@@ struct perf_output_handle 
  
  #ifdef CONFIG_PERF_EVENTS
  
- /*
-  * Set by architecture code:
-  */
- extern int perf_max_events;
- 
- extern const struct pmu *hw_perf_event_init(struct perf_event *event);
+ extern int perf_pmu_register(struct pmu *pmu);
+ extern void perf_pmu_unregister(struct pmu *pmu);
  
 +extern int perf_num_counters(void);
 +extern const char *perf_pmu_name(void);
  extern void perf_event_task_sched_in(struct task_struct *task);
  extern void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next);
- extern void perf_event_task_tick(struct task_struct *task);
  extern int perf_event_init_task(struct task_struct *child);
  extern void perf_event_exit_task(struct task_struct *child);
  extern void perf_event_free_task(struct task_struct *task);
diff --cc kernel/perf_event.c
index fc512684423,64507eaa2d9..1ec3916ffef
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@@ -67,41 -61,38 +61,43 @@@ int sysctl_perf_event_sample_rate __rea
  
  static atomic64_t perf_event_id;
  
- /*
-  * Lock for (sysadmin-configurable) event reservations:
-  */
- static DEFINE_SPINLOCK(perf_resource_lock);
- 
- /*
-  * Architecture provided APIs - weak aliases:
-  */
- extern __weak const struct pmu *hw_perf_event_init(struct perf_event *event)
- {
- 	return NULL;
- }
- 
- void __weak hw_perf_disable(void)		{ barrier(); }
- void __weak hw_perf_enable(void)		{ barrier(); }
- 
  void __weak perf_event_print_debug(void)	{ }
  
 +extern __weak const char *perf_pmu_name(void)
 +{
 +	return "pmu";
 +}
 +
- static DEFINE_PER_CPU(int, perf_disable_count);
+ void perf_pmu_disable(struct pmu *pmu)
+ {
+ 	int *count = this_cpu_ptr(pmu->pmu_disable_count);
+ 	if (!(*count)++)
+ 		pmu->pmu_disable(pmu);
+ }
  
- void perf_disable(void)
+ void perf_pmu_enable(struct pmu *pmu)
  {
- 	if (!__get_cpu_var(perf_disable_count)++)
- 		hw_perf_disable();
+ 	int *count = this_cpu_ptr(pmu->pmu_disable_count);
+ 	if (!--(*count))
+ 		pmu->pmu_enable(pmu);
  }
  
- void perf_enable(void)
+ static DEFINE_PER_CPU(struct list_head, rotation_list);
+ 
+ /*
+  * perf_pmu_rotate_start() and perf_rotate_context() are fully serialized
+  * because they're strictly cpu affine and rotate_start is called with IRQs
+  * disabled, while rotate_context is called from IRQ context.
+  */
+ static void perf_pmu_rotate_start(struct pmu *pmu)
  {
- 	if (!--__get_cpu_var(perf_disable_count))
- 		hw_perf_enable();
+ 	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+ 	struct list_head *head = &__get_cpu_var(rotation_list);
+ 
+ 	WARN_ON(!irqs_disabled());
+ 
+ 	if (list_empty(&cpuctx->rotation_list))
+ 		list_add(&cpuctx->rotation_list, head);
  }
  
  static void get_ctx(struct perf_event_context *ctx)