ARM: 6072/1: oprofile: use perf-events framework as backend

There are currently two hardware performance monitoring subsystems in
the kernel for ARM: OProfile and perf-events. This creates the
following problems:

1.) Duplicate PMU accessor code. Inevitable code drift may lead to
bugs in one framework that are fixed in the other.

2.) Locking issues. OProfile doesn't reprogram hardware counters
between profiling runs if the events to be monitored have not been
changed. This means that other profiling frameworks cannot use the
counters if OProfile is in use.

3.) Due to differences in the two frameworks, it may not be possible to
compare the results obtained by OProfile with those obtained by perf.

This patch removes the OProfile PMU driver code and replaces it with
calls to perf, therefore solving the issues mentioned above.

The only userspace-visible change is the lack of SCU counter support
for 11MPCore. This is currently unsupported by OProfile userspace tools anyway and therefore shouldn't cause any problems.

Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Jamie Iles <jamie.iles@picochip.com>
Cc: Jean Pihet <jpihet@mvista.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/oprofile/common.c

@@ -2,32 +2,183 @@
  * @file common.c
  *
  * @remark Copyright 2004 Oprofile Authors
+ * @remark Copyright 2010 ARM Ltd.
  * @remark Read the file COPYING
  *
  * @author Zwane Mwaikambo
+ * @author Will Deacon [move to perf]
  */
 
-#include <linux/init.h>
-#include <linux/oprofile.h>
+#include <linux/cpumask.h>
 #include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/oprofile.h>
+#include <linux/perf_event.h>
 #include <linux/slab.h>
 #include <linux/sysdev.h>
-#include <linux/mutex.h>
+#include <asm/stacktrace.h>
+#include <linux/uaccess.h>
 
-#include "op_counter.h"
-#include "op_arm_model.h"
+#include <asm/perf_event.h>
+#include <asm/ptrace.h>
+
+#ifdef CONFIG_HW_PERF_EVENTS
+/*
+ * 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 struct op_arm_model_spec *op_arm_model;
 static int op_arm_enabled;
 static DEFINE_MUTEX(op_arm_mutex);
 
-struct op_counter_config *counter_config;
+static struct op_counter_config *counter_config;
+static struct perf_event **perf_events[nr_cpumask_bits];
+static int perf_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 < perf_num_counters; ++id)
+		if (perf_events[cpu][id] == event)
+			break;
+
+	if (id != perf_num_counters)
+		oprofile_add_sample(regs, id);
+	else
+		pr_warning("oprofile: ignoring spurious overflow "
+				"on cpu %u\n", cpu);
+}
+
+/*
+ * Called by op_arm_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 < perf_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)
+{
+	int ret = 0;
+	struct perf_event *pevent;
+
+	if (!counter_config[event].enabled || (perf_events[cpu][event] != NULL))
+		return ret;
+
+	pevent = perf_event_create_kernel_counter(&counter_config[event].attr,
+						  cpu, -1,
+						  op_overflow_handler);
+
+	if (IS_ERR(pevent)) {
+		ret = PTR_ERR(pevent);
+	} else if (pevent->state != PERF_EVENT_STATE_ACTIVE) {
+		pr_warning("oprofile: failed to enable event %d "
+				"on CPU %d\n", event, cpu);
+		ret = -EBUSY;
+	} else {
+		perf_events[cpu][event] = pevent;
+	}
+
+	return ret;
+}
+
+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 op_arm_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 < perf_num_counters; ++event) {
+			ret = op_create_counter(cpu, event);
+			if (ret)
+				goto out;
+		}
+	}
+
+out:
+	return ret;
+}
+
+/*
+ * Called by op_arm_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 < perf_num_counters; ++event)
+			op_destroy_counter(cpu, event);
+}
+
+
+static char *op_name_from_perf_id(enum arm_perf_pmu_ids id)
+{
+	switch (id) {
+	case ARM_PERF_PMU_ID_XSCALE1:
+		return "arm/xscale1";
+	case ARM_PERF_PMU_ID_XSCALE2:
+		return "arm/xscale2";
+	case ARM_PERF_PMU_ID_V6:
+		return "arm/armv6";
+	case ARM_PERF_PMU_ID_V6MP:
+		return "arm/mpcore";
+	case ARM_PERF_PMU_ID_CA8:
+		return "arm/armv7";
+	case ARM_PERF_PMU_ID_CA9:
+		return "arm/armv7-ca9";
+	default:
+		return NULL;
+	}
+}
 
 static int op_arm_create_files(struct super_block *sb, struct dentry *root)
 {
 	unsigned int i;
 
-	for (i = 0; i < op_arm_model->num_counters; i++) {
+	for (i = 0; i < perf_num_counters; i++) {
 		struct dentry *dir;
 		char buf[4];
 
@@ -46,12 +197,10 @@ static int op_arm_create_files(struct super_block *sb, struct dentry *root)
 
 static int op_arm_setup(void)
 {
-	int ret;
-
 	spin_lock(&oprofilefs_lock);
-	ret = op_arm_model->setup_ctrs();
+	op_perf_setup();
 	spin_unlock(&oprofilefs_lock);
-	return ret;
+	return 0;
 }
 
 static int op_arm_start(void)
@@ -60,8 +209,9 @@ static int op_arm_start(void)
 
 	mutex_lock(&op_arm_mutex);
 	if (!op_arm_enabled) {
-		ret = op_arm_model->start();
-		op_arm_enabled = !ret;
+		ret = 0;
+		op_perf_start();
+		op_arm_enabled = 1;
 	}
 	mutex_unlock(&op_arm_mutex);
 	return ret;
@@ -71,7 +221,7 @@ static void op_arm_stop(void)
 {
 	mutex_lock(&op_arm_mutex);
 	if (op_arm_enabled)
-		op_arm_model->stop();
+		op_perf_stop();
 	op_arm_enabled = 0;
 	mutex_unlock(&op_arm_mutex);
 }
@@ -81,7 +231,7 @@ static int op_arm_suspend(struct sys_device *dev, pm_message_t state)
 {
 	mutex_lock(&op_arm_mutex);
 	if (op_arm_enabled)
-		op_arm_model->stop();
+		op_perf_stop();
 	mutex_unlock(&op_arm_mutex);
 	return 0;
 }
@@ -89,7 +239,7 @@ static int op_arm_suspend(struct sys_device *dev, pm_message_t state)
 static int op_arm_resume(struct sys_device *dev)
 {
 	mutex_lock(&op_arm_mutex);
-	if (op_arm_enabled && op_arm_model->start())
+	if (op_arm_enabled && op_perf_start())
 		op_arm_enabled = 0;
 	mutex_unlock(&op_arm_mutex);
 	return 0;
@@ -126,58 +276,137 @@ static void  exit_driverfs(void)
 #define exit_driverfs() do { } while (0)
 #endif /* CONFIG_PM */
 
+static int report_trace(struct stackframe *frame, void *d)
+{
+	unsigned int *depth = d;
+
+	if (*depth) {
+		oprofile_add_trace(frame->pc);
+		(*depth)--;
+	}
+
+	return *depth == 0;
+}
+
+/*
+ * The registers we're interested in are at the end of the variable
+ * length saved register structure. The fp points at the end of this
+ * structure so the address of this struct is:
+ * (struct frame_tail *)(xxx->fp)-1
+ */
+struct frame_tail {
+	struct frame_tail *fp;
+	unsigned long sp;
+	unsigned long lr;
+} __attribute__((packed));
+
+static struct frame_tail* user_backtrace(struct frame_tail *tail)
+{
+	struct frame_tail buftail[2];
+
+	/* Also check accessibility of one struct frame_tail beyond */
+	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
+		return NULL;
+	if (__copy_from_user_inatomic(buftail, tail, sizeof(buftail)))
+		return NULL;
+
+	oprofile_add_trace(buftail[0].lr);
+
+	/* frame pointers should strictly progress back up the stack
+	 * (towards higher addresses) */
+	if (tail >= buftail[0].fp)
+		return NULL;
+
+	return buftail[0].fp-1;
+}
+
+static void arm_backtrace(struct pt_regs * const regs, unsigned int depth)
+{
+	struct frame_tail *tail = ((struct frame_tail *) regs->ARM_fp) - 1;
+
+	if (!user_mode(regs)) {
+		struct stackframe frame;
+		frame.fp = regs->ARM_fp;
+		frame.sp = regs->ARM_sp;
+		frame.lr = regs->ARM_lr;
+		frame.pc = regs->ARM_pc;
+		walk_stackframe(&frame, report_trace, &depth);
+		return;
+	}
+
+	while (depth-- && tail && !((unsigned long) tail & 3))
+		tail = user_backtrace(tail);
+}
+
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
-	struct op_arm_model_spec *spec = NULL;
-	int ret = -ENODEV;
+	int cpu, ret = 0;
 
-	ops->backtrace = arm_backtrace;
+	perf_num_counters = armpmu_get_max_events();
 
-#ifdef CONFIG_CPU_XSCALE
-	spec = &op_xscale_spec;
-#endif
+	counter_config = kcalloc(perf_num_counters,
+			sizeof(struct op_counter_config), GFP_KERNEL);
 
-#ifdef CONFIG_OPROFILE_ARMV6
-	spec = &op_armv6_spec;
-#endif
-
-#ifdef CONFIG_OPROFILE_MPCORE
-	spec = &op_mpcore_spec;
-#endif
-
-#ifdef CONFIG_OPROFILE_ARMV7
-	spec = &op_armv7_spec;
-#endif
-
-	if (spec) {
-		ret = spec->init();
-		if (ret < 0)
-			return ret;
-
-		counter_config = kcalloc(spec->num_counters, sizeof(struct op_counter_config),
-					 GFP_KERNEL);
-		if (!counter_config)
-			return -ENOMEM;
-
-		op_arm_model = spec;
-		init_driverfs();
-		ops->create_files = op_arm_create_files;
-		ops->setup = op_arm_setup;
-		ops->shutdown = op_arm_stop;
-		ops->start = op_arm_start;
-		ops->stop = op_arm_stop;
-		ops->cpu_type = op_arm_model->name;
-		printk(KERN_INFO "oprofile: using %s\n", spec->name);
+	if (!counter_config) {
+		pr_info("oprofile: failed to allocate %d "
+				"counters\n", perf_num_counters);
+		return -ENOMEM;
 	}
 
+	for_each_possible_cpu(cpu) {
+		perf_events[cpu] = kcalloc(perf_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", perf_num_counters, cpu);
+			while (--cpu >= 0)
+				kfree(perf_events[cpu]);
+			return -ENOMEM;
+		}
+	}
+
+	init_driverfs();
+	ops->backtrace		= arm_backtrace;
+	ops->create_files	= op_arm_create_files;
+	ops->setup		= op_arm_setup;
+	ops->start		= op_arm_start;
+	ops->stop		= op_arm_stop;
+	ops->shutdown		= op_arm_stop;
+	ops->cpu_type		= op_name_from_perf_id(armpmu_get_pmu_id());
+
+	if (!ops->cpu_type)
+		ret = -ENODEV;
+	else
+		pr_info("oprofile: using %s\n", ops->cpu_type);
+
 	return ret;
 }
 
 void oprofile_arch_exit(void)
 {
-	if (op_arm_model) {
+	int cpu, id;
+	struct perf_event *event;
+
+	if (*perf_events) {
 		exit_driverfs();
-		op_arm_model = NULL;
+		for_each_possible_cpu(cpu) {
+			for (id = 0; id < perf_num_counters; ++id) {
+				event = perf_events[cpu][id];
+				if (event != NULL)
+					perf_event_release_kernel(event);
+			}
+			kfree(perf_events[cpu]);
+		}
 	}
-	kfree(counter_config);
+
+	if (counter_config)
+		kfree(counter_config);
 }
+#else
+int __init oprofile_arch_init(struct oprofile_operations *ops)
+{
+	pr_info("oprofile: hardware counters not available\n");
+	return -ENODEV;
+}
+void oprofile_arch_exit(void) {}
+#endif /* CONFIG_HW_PERF_EVENTS */