diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 55addc85eaa7..6cc6521881aa 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -123,6 +123,12 @@ armpmu_get_max_events(void)
 }
 EXPORT_SYMBOL_GPL(armpmu_get_max_events);
 
+int perf_num_counters(void)
+{
+	return armpmu_get_max_events();
+}
+EXPORT_SYMBOL_GPL(perf_num_counters);
+
 #define HW_OP_UNSUPPORTED		0xFFFF
 
 #define C(_x) \
diff --git a/arch/arm/oprofile/Makefile b/arch/arm/oprofile/Makefile
index e666eafed152..b2215c61cdf0 100644
--- a/arch/arm/oprofile/Makefile
+++ b/arch/arm/oprofile/Makefile
@@ -6,4 +6,8 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
 		oprofilefs.o oprofile_stats.o \
 		timer_int.o )
 
+ifeq ($(CONFIG_HW_PERF_EVENTS),y)
+DRIVER_OBJS += $(addprefix ../../../drivers/oprofile/, oprofile_perf.o)
+endif
+
 oprofile-y				:= $(DRIVER_OBJS) common.o
diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c
index d1fb5b2f5218..8aa974491dfc 100644
--- a/arch/arm/oprofile/common.c
+++ b/arch/arm/oprofile/common.c
@@ -25,139 +25,10 @@
 #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 int op_arm_enabled;
-static DEFINE_MUTEX(op_arm_mutex);
-
-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)
+char *op_name_from_perf_id(void)
 {
-	int id;
-	u32 cpu = smp_processor_id();
+	enum arm_perf_pmu_ids id = armpmu_get_pmu_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, NULL,
-						  op_overflow_handler);
-
-	if (IS_ERR(pevent)) {
-		ret = PTR_ERR(pevent);
-	} else 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);
-		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";
@@ -176,116 +47,6 @@ static char *op_name_from_perf_id(enum arm_perf_pmu_ids id)
 	}
 }
 
-static int op_arm_create_files(struct super_block *sb, struct dentry *root)
-{
-	unsigned int i;
-
-	for (i = 0; i < perf_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 op_arm_setup(void)
-{
-	spin_lock(&oprofilefs_lock);
-	op_perf_setup();
-	spin_unlock(&oprofilefs_lock);
-	return 0;
-}
-
-static int op_arm_start(void)
-{
-	int ret = -EBUSY;
-
-	mutex_lock(&op_arm_mutex);
-	if (!op_arm_enabled) {
-		ret = 0;
-		op_perf_start();
-		op_arm_enabled = 1;
-	}
-	mutex_unlock(&op_arm_mutex);
-	return ret;
-}
-
-static void op_arm_stop(void)
-{
-	mutex_lock(&op_arm_mutex);
-	if (op_arm_enabled)
-		op_perf_stop();
-	op_arm_enabled = 0;
-	mutex_unlock(&op_arm_mutex);
-}
-
-#ifdef CONFIG_PM
-static int op_arm_suspend(struct platform_device *dev, pm_message_t state)
-{
-	mutex_lock(&op_arm_mutex);
-	if (op_arm_enabled)
-		op_perf_stop();
-	mutex_unlock(&op_arm_mutex);
-	return 0;
-}
-
-static int op_arm_resume(struct platform_device *dev)
-{
-	mutex_lock(&op_arm_mutex);
-	if (op_arm_enabled && op_perf_start())
-		op_arm_enabled = 0;
-	mutex_unlock(&op_arm_mutex);
-	return 0;
-}
-
-static struct platform_driver oprofile_driver = {
-	.driver		= {
-		.name		= "arm-oprofile",
-	},
-	.resume		= op_arm_resume,
-	.suspend	= op_arm_suspend,
-};
-
-static struct platform_device *oprofile_pdev;
-
-static int __init init_driverfs(void)
-{
-	int ret;
-
-	ret = platform_driver_register(&oprofile_driver);
-	if (ret)
-		goto out;
-
-	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);
-	}
-
-out:
-	return ret;
-}
-
-static void  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 */
-
 static int report_trace(struct stackframe *frame, void *d)
 {
 	unsigned int *depth = d;
@@ -350,74 +111,14 @@ static void arm_backtrace(struct pt_regs * const regs, unsigned int depth)
 
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
-	int cpu, ret = 0;
-
-	perf_num_counters = armpmu_get_max_events();
-
-	counter_config = kcalloc(perf_num_counters,
-			sizeof(struct op_counter_config), GFP_KERNEL);
-
-	if (!counter_config) {
-		pr_info("oprofile: failed to allocate %d "
-				"counters\n", perf_num_counters);
-		return -ENOMEM;
-	}
-
-	ret = init_driverfs();
-	if (ret) {
-		kfree(counter_config);
-		counter_config = NULL;
-		return ret;
-	}
-
-	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;
-		}
-	}
-
 	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;
+	return oprofile_perf_init(ops);
 }
 
-void oprofile_arch_exit(void)
+void __exit oprofile_arch_exit(void)
 {
-	int cpu, id;
-	struct perf_event *event;
-
-	if (*perf_events) {
-		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]);
-		}
-	}
-
-	if (counter_config) {
-		kfree(counter_config);
-		exit_driverfs();
-	}
+	oprofile_perf_exit();
 }
 #else
 int __init oprofile_arch_init(struct oprofile_operations *ops)
@@ -425,5 +126,5 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	pr_info("oprofile: hardware counters not available\n");
 	return -ENODEV;
 }
-void oprofile_arch_exit(void) {}
+void __exit oprofile_arch_exit(void) {}
 #endif /* CONFIG_HW_PERF_EVENTS */
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 33990fa95af0..35b6c3f85173 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -249,6 +249,11 @@ config ARCH_SHMOBILE
 	select PM
 	select PM_RUNTIME
 
+config CPU_HAS_PMU
+       depends on CPU_SH4 || CPU_SH4A
+       default y
+       bool
+
 if SUPERH32
 
 choice
@@ -738,6 +743,14 @@ config GUSA_RB
 	  LLSC, this should be more efficient than the other alternative of
 	  disabling interrupts around the atomic sequence.
 
+config HW_PERF_EVENTS
+	bool "Enable hardware performance counter support for perf events"
+	depends on PERF_EVENTS && CPU_HAS_PMU
+	default y
+	help
+	  Enable hardware performance counter support for perf events. If
+	  disabled, perf events will use software events only.
+
 source "drivers/sh/Kconfig"
 
 endmenu
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 036f7a9296fa..5a4b33435650 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -59,6 +59,24 @@ static inline int sh_pmu_initialized(void)
 	return !!sh_pmu;
 }
 
+const char *perf_pmu_name(void)
+{
+	if (!sh_pmu)
+		return NULL;
+
+	return sh_pmu->name;
+}
+EXPORT_SYMBOL_GPL(perf_pmu_name);
+
+int perf_num_counters(void)
+{
+	if (!sh_pmu)
+		return 0;
+
+	return sh_pmu->num_events;
+}
+EXPORT_SYMBOL_GPL(perf_num_counters);
+
 /*
  * Release the PMU if this is the last perf_event.
  */
diff --git a/arch/sh/oprofile/Makefile b/arch/sh/oprofile/Makefile
index 4886c5c1786c..e85aae73e3dc 100644
--- a/arch/sh/oprofile/Makefile
+++ b/arch/sh/oprofile/Makefile
@@ -6,4 +6,8 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
 		oprofilefs.o oprofile_stats.o \
 		timer_int.o )
 
+ifeq ($(CONFIG_HW_PERF_EVENTS),y)
+DRIVER_OBJS += $(addprefix ../../../drivers/oprofile/, oprofile_perf.o)
+endif
+
 oprofile-y	:= $(DRIVER_OBJS) common.o backtrace.o
diff --git a/arch/sh/oprofile/common.c b/arch/sh/oprofile/common.c
index ac604937f3ee..e10d89376f9b 100644
--- a/arch/sh/oprofile/common.c
+++ b/arch/sh/oprofile/common.c
@@ -17,114 +17,45 @@
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/smp.h>
+#include <linux/perf_event.h>
 #include <asm/processor.h>
-#include "op_impl.h"
-
-static struct op_sh_model *model;
-
-static struct op_counter_config ctr[20];
 
+#ifdef CONFIG_HW_PERF_EVENTS
 extern void sh_backtrace(struct pt_regs * const regs, unsigned int depth);
 
-static int op_sh_setup(void)
+char *op_name_from_perf_id(void)
 {
-	/* Pre-compute the values to stuff in the hardware registers.  */
-	model->reg_setup(ctr);
+	const char *pmu;
+	char buf[20];
+	int size;
 
-	/* Configure the registers on all cpus.  */
-	on_each_cpu(model->cpu_setup, NULL, 1);
+	pmu = perf_pmu_name();
+	if (!pmu)
+		return NULL;
 
-        return 0;
-}
+	size = snprintf(buf, sizeof(buf), "sh/%s", pmu);
+	if (size > -1 && size < sizeof(buf))
+		return buf;
 
-static int op_sh_create_files(struct super_block *sb, struct dentry *root)
-{
-	int i, ret = 0;
-
-	for (i = 0; i < model->num_counters; i++) {
-		struct dentry *dir;
-		char buf[4];
-
-		snprintf(buf, sizeof(buf), "%d", i);
-		dir = oprofilefs_mkdir(sb, root, buf);
-
-		ret |= oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
-		ret |= oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
-		ret |= oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel);
-		ret |= oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user);
-
-		if (model->create_files)
-			ret |= model->create_files(sb, dir);
-		else
-			ret |= oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count);
-
-		/* Dummy entries */
-		ret |= oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask);
-	}
-
-	return ret;
-}
-
-static int op_sh_start(void)
-{
-	/* Enable performance monitoring for all counters.  */
-	on_each_cpu(model->cpu_start, NULL, 1);
-
-	return 0;
-}
-
-static void op_sh_stop(void)
-{
-	/* Disable performance monitoring for all counters.  */
-	on_each_cpu(model->cpu_stop, NULL, 1);
+	return NULL;
 }
 
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
-	struct op_sh_model *lmodel = NULL;
-	int ret;
-
-	/*
-	 * Always assign the backtrace op. If the counter initialization
-	 * fails, we fall back to the timer which will still make use of
-	 * this.
-	 */
 	ops->backtrace = sh_backtrace;
 
-	/*
-	 * XXX
-	 *
-	 * All of the SH7750/SH-4A counters have been converted to perf,
-	 * this infrastructure hook is left for other users until they've
-	 * had a chance to convert over, at which point all of this
-	 * will be deleted.
-	 */
-
-	if (!lmodel)
-		return -ENODEV;
-	if (!(current_cpu_data.flags & CPU_HAS_PERF_COUNTER))
-		return -ENODEV;
-
-	ret = lmodel->init();
-	if (unlikely(ret != 0))
-		return ret;
-
-	model = lmodel;
-
-	ops->setup		= op_sh_setup;
-	ops->create_files	= op_sh_create_files;
-	ops->start		= op_sh_start;
-	ops->stop		= op_sh_stop;
-	ops->cpu_type		= lmodel->cpu_type;
-
-	printk(KERN_INFO "oprofile: using %s performance monitoring.\n",
-	       lmodel->cpu_type);
-
-	return 0;
+	return oprofile_perf_init(ops);
 }
 
-void oprofile_arch_exit(void)
+void __exit oprofile_arch_exit(void)
 {
-	if (model && model->exit)
-		model->exit();
+	oprofile_perf_exit();
 }
+#else
+int __init oprofile_arch_init(struct oprofile_operations *ops)
+{
+	pr_info("oprofile: hardware counters not available\n");
+	return -ENODEV;
+}
+void __exit oprofile_arch_exit(void) {}
+#endif /* CONFIG_HW_PERF_EVENTS */
diff --git a/arch/sh/oprofile/op_impl.h b/arch/sh/oprofile/op_impl.h
deleted file mode 100644
index 1244479ceb29..000000000000
--- a/arch/sh/oprofile/op_impl.h
+++ /dev/null
@@ -1,33 +0,0 @@
-#ifndef __OP_IMPL_H
-#define __OP_IMPL_H
-
-/* Per-counter configuration as set via oprofilefs.  */
-struct op_counter_config {
-	unsigned long enabled;
-	unsigned long event;
-
-	unsigned long count;
-
-	/* Dummy values for userspace tool compliance */
-	unsigned long kernel;
-	unsigned long user;
-	unsigned long unit_mask;
-};
-
-/* Per-architecture configury and hooks.  */
-struct op_sh_model {
-	void (*reg_setup)(struct op_counter_config *);
-	int (*create_files)(struct super_block *sb, struct dentry *dir);
-	void (*cpu_setup)(void *dummy);
-	int (*init)(void);
-	void (*exit)(void);
-	void (*cpu_start)(void *args);
-	void (*cpu_stop)(void *args);
-	char *cpu_type;
-	unsigned char num_counters;
-};
-
-/* arch/sh/oprofile/common.c */
-extern void sh_backtrace(struct pt_regs * const regs, unsigned int depth);
-
-#endif /* __OP_IMPL_H */
diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c
index 3855096c59b8..2d49d4e19a36 100644
--- a/arch/x86/oprofile/backtrace.c
+++ b/arch/x86/oprofile/backtrace.c
@@ -14,6 +14,7 @@
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>
 #include <asm/stacktrace.h>
+#include <linux/compat.h>
 
 static void backtrace_warning_symbol(void *data, char *msg,
 				     unsigned long symbol)
@@ -48,14 +49,12 @@ static struct stacktrace_ops backtrace_ops = {
 	.walk_stack	= print_context_stack,
 };
 
-struct frame_head {
-	struct frame_head *bp;
-	unsigned long ret;
-} __attribute__((packed));
-
-static struct frame_head *dump_user_backtrace(struct frame_head *head)
+#ifdef CONFIG_COMPAT
+static struct stack_frame_ia32 *
+dump_user_backtrace_32(struct stack_frame_ia32 *head)
 {
-	struct frame_head bufhead[2];
+	struct stack_frame_ia32 bufhead[2];
+	struct stack_frame_ia32 *fp;
 
 	/* Also check accessibility of one struct frame_head beyond */
 	if (!access_ok(VERIFY_READ, head, sizeof(bufhead)))
@@ -63,20 +62,66 @@ static struct frame_head *dump_user_backtrace(struct frame_head *head)
 	if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead)))
 		return NULL;
 
-	oprofile_add_trace(bufhead[0].ret);
+	fp = (struct stack_frame_ia32 *) compat_ptr(bufhead[0].next_frame);
+
+	oprofile_add_trace(bufhead[0].return_address);
+
+	/* frame pointers should strictly progress back up the stack
+	* (towards higher addresses) */
+	if (head >= fp)
+		return NULL;
+
+	return fp;
+}
+
+static inline int
+x86_backtrace_32(struct pt_regs * const regs, unsigned int depth)
+{
+	struct stack_frame_ia32 *head;
+
+	/* User process is 32-bit */
+	if (!current || !test_thread_flag(TIF_IA32))
+		return 0;
+
+	head = (struct stack_frame_ia32 *) regs->bp;
+	while (depth-- && head)
+		head = dump_user_backtrace_32(head);
+
+	return 1;
+}
+
+#else
+static inline int
+x86_backtrace_32(struct pt_regs * const regs, unsigned int depth)
+{
+	return 0;
+}
+#endif /* CONFIG_COMPAT */
+
+static struct stack_frame *dump_user_backtrace(struct stack_frame *head)
+{
+	struct stack_frame bufhead[2];
+
+	/* Also check accessibility of one struct stack_frame beyond */
+	if (!access_ok(VERIFY_READ, head, sizeof(bufhead)))
+		return NULL;
+	if (__copy_from_user_inatomic(bufhead, head, sizeof(bufhead)))
+		return NULL;
+
+	oprofile_add_trace(bufhead[0].return_address);
 
 	/* frame pointers should strictly progress back up the stack
 	 * (towards higher addresses) */
-	if (head >= bufhead[0].bp)
+	if (head >= bufhead[0].next_frame)
 		return NULL;
 
-	return bufhead[0].bp;
+	return bufhead[0].next_frame;
 }
 
 void
 x86_backtrace(struct pt_regs * const regs, unsigned int depth)
 {
-	struct frame_head *head = (struct frame_head *)frame_pointer(regs);
+	struct stack_frame *head = (struct stack_frame *)frame_pointer(regs);
 
 	if (!user_mode_vm(regs)) {
 		unsigned long stack = kernel_stack_pointer(regs);
@@ -86,6 +131,9 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth)
 		return;
 	}
 
+	if (x86_backtrace_32(regs, depth))
+		return;
+
 	while (depth-- && head)
 		head = dump_user_backtrace(head);
 }
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index f1575c9a2572..bd1489c3ce09 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -695,9 +695,6 @@ static int __init ppro_init(char **cpu_type)
 	return 1;
 }
 
-/* in order to get sysfs right */
-static int using_nmi;
-
 int __init op_nmi_init(struct oprofile_operations *ops)
 {
 	__u8 vendor = boot_cpu_data.x86_vendor;
@@ -705,8 +702,6 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 	char *cpu_type = NULL;
 	int ret = 0;
 
-	using_nmi = 0;
-
 	if (!cpu_has_apic)
 		return -ENODEV;
 
@@ -790,13 +785,11 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 	if (ret)
 		return ret;
 
-	using_nmi = 1;
 	printk(KERN_INFO "oprofile: using NMI interrupt.\n");
 	return 0;
 }
 
 void op_nmi_exit(void)
 {
-	if (using_nmi)
-		exit_sysfs();
+	exit_sysfs();
 }
diff --git a/drivers/oprofile/oprof.c b/drivers/oprofile/oprof.c
index b336cd9ee7a1..f9bda64fcd1b 100644
--- a/drivers/oprofile/oprof.c
+++ b/drivers/oprofile/oprof.c
@@ -225,26 +225,17 @@ post_sync:
 	mutex_unlock(&start_mutex);
 }
 
-int oprofile_set_backtrace(unsigned long val)
+int oprofile_set_ulong(unsigned long *addr, unsigned long val)
 {
-	int err = 0;
+	int err = -EBUSY;
 
 	mutex_lock(&start_mutex);
-
-	if (oprofile_started) {
-		err = -EBUSY;
-		goto out;
+	if (!oprofile_started) {
+		*addr = val;
+		err = 0;
 	}
-
-	if (!oprofile_ops.backtrace) {
-		err = -EINVAL;
-		goto out;
-	}
-
-	oprofile_backtrace_depth = val;
-
-out:
 	mutex_unlock(&start_mutex);
+
 	return err;
 }
 
@@ -257,16 +248,9 @@ static int __init oprofile_init(void)
 		printk(KERN_INFO "oprofile: using timer interrupt.\n");
 		err = oprofile_timer_init(&oprofile_ops);
 		if (err)
-			goto out_arch;
+			return err;
 	}
-	err = oprofilefs_register();
-	if (err)
-		goto out_arch;
-	return 0;
-
-out_arch:
-	oprofile_arch_exit();
-	return err;
+	return oprofilefs_register();
 }
 
 
diff --git a/drivers/oprofile/oprof.h b/drivers/oprofile/oprof.h
index 47e12cb4ee8b..177b73de5e5f 100644
--- a/drivers/oprofile/oprof.h
+++ b/drivers/oprofile/oprof.h
@@ -37,7 +37,7 @@ void oprofile_create_files(struct super_block *sb, struct dentry *root);
 int oprofile_timer_init(struct oprofile_operations *ops);
 void oprofile_timer_exit(void);
 
-int oprofile_set_backtrace(unsigned long depth);
+int oprofile_set_ulong(unsigned long *addr, unsigned long val);
 int oprofile_set_timeout(unsigned long time);
 
 #endif /* OPROF_H */
diff --git a/drivers/oprofile/oprofile_files.c b/drivers/oprofile/oprofile_files.c
index bbd7516e0869..ccf099e684a4 100644
--- a/drivers/oprofile/oprofile_files.c
+++ b/drivers/oprofile/oprofile_files.c
@@ -79,14 +79,17 @@ static ssize_t depth_write(struct file *file, char const __user *buf, size_t cou
 	if (*offset)
 		return -EINVAL;
 
+	if (!oprofile_ops.backtrace)
+		return -EINVAL;
+
 	retval = oprofilefs_ulong_from_user(&val, buf, count);
 	if (retval)
 		return retval;
 
-	retval = oprofile_set_backtrace(val);
-
+	retval = oprofile_set_ulong(&oprofile_backtrace_depth, val);
 	if (retval)
 		return retval;
+
 	return count;
 }
 
diff --git a/drivers/oprofile/oprofile_perf.c b/drivers/oprofile/oprofile_perf.c
new file mode 100644
index 000000000000..9046f7b2ed79
--- /dev/null
+++ b/drivers/oprofile/oprofile_perf.c
@@ -0,0 +1,328 @@
+/*
+ * Copyright 2010 ARM Ltd.
+ *
+ * Perf-events backend for OProfile.
+ */
+#include <linux/perf_event.h>
+#include <linux/platform_device.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, 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_driverfs(void)
+{
+	platform_device_unregister(oprofile_pdev);
+	platform_driver_unregister(&oprofile_driver);
+}
+
+#else
+
+static inline int  init_driverfs(void) { return 0; }
+static inline void exit_driverfs(void) { }
+
+#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 --git a/drivers/oprofile/oprofilefs.c b/drivers/oprofile/oprofilefs.c
index 2766a6d3c2e9..1944621930d9 100644
--- a/drivers/oprofile/oprofilefs.c
+++ b/drivers/oprofile/oprofilefs.c
@@ -91,16 +91,20 @@ static ssize_t ulong_read_file(struct file *file, char __user *buf, size_t count
 
 static ssize_t ulong_write_file(struct file *file, char const __user *buf, size_t count, loff_t *offset)
 {
-	unsigned long *value = file->private_data;
+	unsigned long value;
 	int retval;
 
 	if (*offset)
 		return -EINVAL;
 
-	retval = oprofilefs_ulong_from_user(value, buf, count);
-
+	retval = oprofilefs_ulong_from_user(&value, buf, count);
 	if (retval)
 		return retval;
+
+	retval = oprofile_set_ulong(file->private_data, value);
+	if (retval)
+		return retval;
+
 	return count;
 }
 
@@ -126,50 +130,41 @@ static const struct file_operations ulong_ro_fops = {
 };
 
 
-static struct dentry *__oprofilefs_create_file(struct super_block *sb,
+static int __oprofilefs_create_file(struct super_block *sb,
 	struct dentry *root, char const *name, const struct file_operations *fops,
-	int perm)
+	int perm, void *priv)
 {
 	struct dentry *dentry;
 	struct inode *inode;
 
 	dentry = d_alloc_name(root, name);
 	if (!dentry)
-		return NULL;
+		return -ENOMEM;
 	inode = oprofilefs_get_inode(sb, S_IFREG | perm);
 	if (!inode) {
 		dput(dentry);
-		return NULL;
+		return -ENOMEM;
 	}
 	inode->i_fop = fops;
 	d_add(dentry, inode);
-	return dentry;
+	dentry->d_inode->i_private = priv;
+	return 0;
 }
 
 
 int oprofilefs_create_ulong(struct super_block *sb, struct dentry *root,
 	char const *name, unsigned long *val)
 {
-	struct dentry *d = __oprofilefs_create_file(sb, root, name,
-						     &ulong_fops, 0644);
-	if (!d)
-		return -EFAULT;
-
-	d->d_inode->i_private = val;
-	return 0;
+	return __oprofilefs_create_file(sb, root, name,
+					&ulong_fops, 0644, val);
 }
 
 
 int oprofilefs_create_ro_ulong(struct super_block *sb, struct dentry *root,
 	char const *name, unsigned long *val)
 {
-	struct dentry *d = __oprofilefs_create_file(sb, root, name,
-						     &ulong_ro_fops, 0444);
-	if (!d)
-		return -EFAULT;
-
-	d->d_inode->i_private = val;
-	return 0;
+	return __oprofilefs_create_file(sb, root, name,
+					&ulong_ro_fops, 0444, val);
 }
 
 
@@ -189,31 +184,22 @@ static const struct file_operations atomic_ro_fops = {
 int oprofilefs_create_ro_atomic(struct super_block *sb, struct dentry *root,
 	char const *name, atomic_t *val)
 {
-	struct dentry *d = __oprofilefs_create_file(sb, root, name,
-						     &atomic_ro_fops, 0444);
-	if (!d)
-		return -EFAULT;
-
-	d->d_inode->i_private = val;
-	return 0;
+	return __oprofilefs_create_file(sb, root, name,
+					&atomic_ro_fops, 0444, val);
 }
 
 
 int oprofilefs_create_file(struct super_block *sb, struct dentry *root,
 	char const *name, const struct file_operations *fops)
 {
-	if (!__oprofilefs_create_file(sb, root, name, fops, 0644))
-		return -EFAULT;
-	return 0;
+	return __oprofilefs_create_file(sb, root, name, fops, 0644, NULL);
 }
 
 
 int oprofilefs_create_file_perm(struct super_block *sb, struct dentry *root,
 	char const *name, const struct file_operations *fops, int perm)
 {
-	if (!__oprofilefs_create_file(sb, root, name, fops, perm))
-		return -EFAULT;
-	return 0;
+	return __oprofilefs_create_file(sb, root, name, fops, perm, NULL);
 }
 
 
diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h
index 5171639ecf0f..32fb81212fd1 100644
--- a/include/linux/oprofile.h
+++ b/include/linux/oprofile.h
@@ -15,6 +15,7 @@
 
 #include <linux/types.h>
 #include <linux/spinlock.h>
+#include <linux/init.h>
 #include <asm/atomic.h>
  
 /* Each escaped entry is prefixed by ESCAPE_CODE
@@ -185,4 +186,10 @@ int oprofile_add_data(struct op_entry *entry, unsigned long val);
 int oprofile_add_data64(struct op_entry *entry, u64 val);
 int oprofile_write_commit(struct op_entry *entry);
 
+#ifdef CONFIG_PERF_EVENTS
+int __init oprofile_perf_init(struct oprofile_operations *ops);
+void oprofile_perf_exit(void);
+char *op_name_from_perf_id(void);
+#endif /* CONFIG_PERF_EVENTS */
+
 #endif /* OPROFILE_H */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 61b1e2d760fd..a9227e985207 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -890,6 +890,8 @@ struct perf_output_handle {
 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 int perf_event_init_task(struct task_struct *child);
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 64507eaa2d9e..1ec3916ffef0 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -63,6 +63,11 @@ static atomic64_t perf_event_id;
 
 void __weak perf_event_print_debug(void)	{ }
 
+extern __weak const char *perf_pmu_name(void)
+{
+	return "pmu";
+}
+
 void perf_pmu_disable(struct pmu *pmu)
 {
 	int *count = this_cpu_ptr(pmu->pmu_disable_count);