Merge branch 'origin' into devel-stable

Conflicts:
	arch/arm/mach-mx2/devices.c
	arch/arm/mach-mx2/devices.h
	sound/soc/pxa/pxa-ssp.c

12 files changed, 2604 insertions, 267 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index dd00f747e2ad..26d302c28e13 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -17,6 +17,7 @@ obj-y		:= compat.o elf.o entry-armv.o entry-common.o irq.o \
 		   process.o ptrace.o return_address.o setup.o signal.o \
 		   sys_arm.o stacktrace.o time.o traps.o
 
+obj-$(CONFIG_LEDS)		+= leds.o
 obj-$(CONFIG_OC_ETM)		+= etm.o
 
 obj-$(CONFIG_ISA_DMA_API)	+= dma.o
@@ -46,6 +47,8 @@ obj-$(CONFIG_CPU_XSCALE)	+= xscale-cp0.o
 obj-$(CONFIG_CPU_XSC3)		+= xscale-cp0.o
 obj-$(CONFIG_CPU_MOHAWK)	+= xscale-cp0.o
 obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
+obj-$(CONFIG_CPU_HAS_PMU)	+= pmu.o
+obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
 
 ifneq ($(CONFIG_ARCH_EBSA110),y)
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 4a881258bb17..883511522fca 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -12,6 +12,7 @@
  */
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/dma-mapping.h>
 #include <asm/mach/arch.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
@@ -112,5 +113,9 @@ int main(void)
 #ifdef MULTI_PABORT
   DEFINE(PROCESSOR_PABT_FUNC,	offsetof(struct processor, _prefetch_abort));
 #endif
+  BLANK();
+  DEFINE(DMA_BIDIRECTIONAL,	DMA_BIDIRECTIONAL);
+  DEFINE(DMA_TO_DEVICE,		DMA_TO_DEVICE);
+  DEFINE(DMA_FROM_DEVICE,	DMA_FROM_DEVICE);
   return 0; 
 }
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index 809681900ec8..bd397e0b663e 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -616,15 +616,17 @@ char * __init pcibios_setup(char *str)
  * but we want to try to avoid allocating at 0x2900-0x2bff
  * which might be mirrored at 0x0100-0x03ff..
  */
-void pcibios_align_resource(void *data, struct resource *res,
-			    resource_size_t size, resource_size_t align)
+resource_size_t pcibios_align_resource(void *data, const struct resource *res,
+				resource_size_t size, resource_size_t align)
 {
 	resource_size_t start = res->start;
 
 	if (res->flags & IORESOURCE_IO && start & 0x300)
 		start = (start + 0x3ff) & ~0x3ff;
 
-	res->start = (start + align - 1) & ~(align - 1);
+	start = (start + align - 1) & ~(align - 1);
+
+	return start;
 }
 
 /**
diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index 5c91addcaebc..a38b4879441d 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -24,7 +24,7 @@
 
 #if defined(CONFIG_CPU_V6)
 
-		.macro	addruart, rx
+		.macro	addruart, rx, tmp
 		.endm
 
 		.macro	senduart, rd, rx
@@ -51,7 +51,7 @@
 
 #elif defined(CONFIG_CPU_V7)
 
-		.macro	addruart, rx
+		.macro	addruart, rx, tmp
 		.endm
 
 		.macro	senduart, rd, rx
@@ -71,7 +71,7 @@ wait:		mrc	p14, 0, pc, c0, c1, 0
 
 #elif defined(CONFIG_CPU_XSCALE)
 
-		.macro	addruart, rx
+		.macro	addruart, rx, tmp
 		.endm
 
 		.macro	senduart, rd, rx
@@ -98,7 +98,7 @@ wait:		mrc	p14, 0, pc, c0, c1, 0
 
 #else
 
-		.macro	addruart, rx
+		.macro	addruart, rx, tmp
 		.endm
 
 		.macro	senduart, rd, rx
@@ -164,7 +164,7 @@ ENDPROC(printhex2)
 		.ltorg
 
 ENTRY(printascii)
-		addruart r3
+		addruart r3, r1
 		b	2f
 1:		waituart r2, r3
 		senduart r1, r3
@@ -180,7 +180,7 @@ ENTRY(printascii)
 ENDPROC(printascii)
 
 ENTRY(printch)
-		addruart r3
+		addruart r3, r1
 		mov	r1, r0
 		mov	r0, #0
 		b	1b
diff --git a/arch/arm/kernel/leds.c b/arch/arm/kernel/leds.c
new file mode 100644
index 000000000000..31a316c1777b
--- /dev/null
+++ b/arch/arm/kernel/leds.c
@@ -0,0 +1,115 @@
+/*
+ * LED support code, ripped out of arch/arm/kernel/time.c
+ *
+ *  Copyright (C) 1994-2001 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sysdev.h>
+
+#include <asm/leds.h>
+
+static void dummy_leds_event(led_event_t evt)
+{
+}
+
+void (*leds_event)(led_event_t) = dummy_leds_event;
+
+struct leds_evt_name {
+	const char	name[8];
+	int		on;
+	int		off;
+};
+
+static const struct leds_evt_name evt_names[] = {
+	{ "amber", led_amber_on, led_amber_off },
+	{ "blue",  led_blue_on,  led_blue_off  },
+	{ "green", led_green_on, led_green_off },
+	{ "red",   led_red_on,   led_red_off   },
+};
+
+static ssize_t leds_store(struct sys_device *dev,
+			struct sysdev_attribute *attr,
+			const char *buf, size_t size)
+{
+	int ret = -EINVAL, len = strcspn(buf, " ");
+
+	if (len > 0 && buf[len] == '\0')
+		len--;
+
+	if (strncmp(buf, "claim", len) == 0) {
+		leds_event(led_claim);
+		ret = size;
+	} else if (strncmp(buf, "release", len) == 0) {
+		leds_event(led_release);
+		ret = size;
+	} else {
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(evt_names); i++) {
+			if (strlen(evt_names[i].name) != len ||
+			    strncmp(buf, evt_names[i].name, len) != 0)
+				continue;
+			if (strncmp(buf+len, " on", 3) == 0) {
+				leds_event(evt_names[i].on);
+				ret = size;
+			} else if (strncmp(buf+len, " off", 4) == 0) {
+				leds_event(evt_names[i].off);
+				ret = size;
+			}
+			break;
+		}
+	}
+	return ret;
+}
+
+static SYSDEV_ATTR(event, 0200, NULL, leds_store);
+
+static int leds_suspend(struct sys_device *dev, pm_message_t state)
+{
+	leds_event(led_stop);
+	return 0;
+}
+
+static int leds_resume(struct sys_device *dev)
+{
+	leds_event(led_start);
+	return 0;
+}
+
+static int leds_shutdown(struct sys_device *dev)
+{
+	leds_event(led_halted);
+	return 0;
+}
+
+static struct sysdev_class leds_sysclass = {
+	.name		= "leds",
+	.shutdown	= leds_shutdown,
+	.suspend	= leds_suspend,
+	.resume		= leds_resume,
+};
+
+static struct sys_device leds_device = {
+	.id		= 0,
+	.cls		= &leds_sysclass,
+};
+
+static int __init leds_init(void)
+{
+	int ret;
+	ret = sysdev_class_register(&leds_sysclass);
+	if (ret == 0)
+		ret = sysdev_register(&leds_device);
+	if (ret == 0)
+		ret = sysdev_create_file(&leds_device, &attr_event);
+	return ret;
+}
+
+device_initcall(leds_init);
+
+EXPORT_SYMBOL(leds_event);
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
new file mode 100644
index 000000000000..c54ceb3d1f97
--- /dev/null
+++ b/arch/arm/kernel/perf_event.c
@@ -0,0 +1,2276 @@
+#undef DEBUG
+
+/*
+ * ARM performance counter support.
+ *
+ * Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles
+ *
+ * ARMv7 support: Jean Pihet <jpihet@mvista.com>
+ * 2010 (c) MontaVista Software, LLC.
+ *
+ * This code is based on the sparc64 perf event code, which is in turn based
+ * on the x86 code. Callchain code is based on the ARM OProfile backtrace
+ * code.
+ */
+#define pr_fmt(fmt) "hw perfevents: " fmt
+
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/spinlock.h>
+#include <linux/uaccess.h>
+
+#include <asm/cputype.h>
+#include <asm/irq.h>
+#include <asm/irq_regs.h>
+#include <asm/pmu.h>
+#include <asm/stacktrace.h>
+
+static const struct pmu_irqs *pmu_irqs;
+
+/*
+ * Hardware lock to serialize accesses to PMU registers. Needed for the
+ * read/modify/write sequences.
+ */
+DEFINE_SPINLOCK(pmu_lock);
+
+/*
+ * ARMv6 supports a maximum of 3 events, starting from index 1. If we add
+ * another platform that supports more, we need to increase this to be the
+ * largest of all platforms.
+ *
+ * ARMv7 supports up to 32 events:
+ *  cycle counter CCNT + 31 events counters CNT0..30.
+ *  Cortex-A8 has 1+4 counters, Cortex-A9 has 1+6 counters.
+ */
+#define ARMPMU_MAX_HWEVENTS		33
+
+/* The events for a given CPU. */
+struct cpu_hw_events {
+	/*
+	 * The events that are active on the CPU for the given index. Index 0
+	 * is reserved.
+	 */
+	struct perf_event	*events[ARMPMU_MAX_HWEVENTS];
+
+	/*
+	 * A 1 bit for an index indicates that the counter is being used for
+	 * an event. A 0 means that the counter can be used.
+	 */
+	unsigned long		used_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)];
+
+	/*
+	 * A 1 bit for an index indicates that the counter is actively being
+	 * used.
+	 */
+	unsigned long		active_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)];
+};
+DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
+
+struct arm_pmu {
+	char		*name;
+	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
+	void		(*enable)(struct hw_perf_event *evt, int idx);
+	void		(*disable)(struct hw_perf_event *evt, int idx);
+	int		(*event_map)(int evt);
+	u64		(*raw_event)(u64);
+	int		(*get_event_idx)(struct cpu_hw_events *cpuc,
+					 struct hw_perf_event *hwc);
+	u32		(*read_counter)(int idx);
+	void		(*write_counter)(int idx, u32 val);
+	void		(*start)(void);
+	void		(*stop)(void);
+	int		num_events;
+	u64		max_period;
+};
+
+/* Set at runtime when we know what CPU type we are. */
+static const struct arm_pmu *armpmu;
+
+#define HW_OP_UNSUPPORTED		0xFFFF
+
+#define C(_x) \
+	PERF_COUNT_HW_CACHE_##_x
+
+#define CACHE_OP_UNSUPPORTED		0xFFFF
+
+static unsigned armpmu_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+				     [PERF_COUNT_HW_CACHE_OP_MAX]
+				     [PERF_COUNT_HW_CACHE_RESULT_MAX];
+
+static int
+armpmu_map_cache_event(u64 config)
+{
+	unsigned int cache_type, cache_op, cache_result, ret;
+
+	cache_type = (config >>  0) & 0xff;
+	if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
+		return -EINVAL;
+
+	cache_op = (config >>  8) & 0xff;
+	if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
+		return -EINVAL;
+
+	cache_result = (config >> 16) & 0xff;
+	if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
+		return -EINVAL;
+
+	ret = (int)armpmu_perf_cache_map[cache_type][cache_op][cache_result];
+
+	if (ret == CACHE_OP_UNSUPPORTED)
+		return -ENOENT;
+
+	return ret;
+}
+
+static int
+armpmu_event_set_period(struct perf_event *event,
+			struct hw_perf_event *hwc,
+			int idx)
+{
+	s64 left = atomic64_read(&hwc->period_left);
+	s64 period = hwc->sample_period;
+	int ret = 0;
+
+	if (unlikely(left <= -period)) {
+		left = period;
+		atomic64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+		ret = 1;
+	}
+
+	if (unlikely(left <= 0)) {
+		left += period;
+		atomic64_set(&hwc->period_left, left);
+		hwc->last_period = period;
+		ret = 1;
+	}
+
+	if (left > (s64)armpmu->max_period)
+		left = armpmu->max_period;
+
+	atomic64_set(&hwc->prev_count, (u64)-left);
+
+	armpmu->write_counter(idx, (u64)(-left) & 0xffffffff);
+
+	perf_event_update_userpage(event);
+
+	return ret;
+}
+
+static u64
+armpmu_event_update(struct perf_event *event,
+		    struct hw_perf_event *hwc,
+		    int idx)
+{
+	int shift = 64 - 32;
+	s64 prev_raw_count, new_raw_count;
+	s64 delta;
+
+again:
+	prev_raw_count = atomic64_read(&hwc->prev_count);
+	new_raw_count = armpmu->read_counter(idx);
+
+	if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count,
+			     new_raw_count) != prev_raw_count)
+		goto again;
+
+	delta = (new_raw_count << shift) - (prev_raw_count << shift);
+	delta >>= shift;
+
+	atomic64_add(delta, &event->count);
+	atomic64_sub(delta, &hwc->period_left);
+
+	return new_raw_count;
+}
+
+static void
+armpmu_disable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	WARN_ON(idx < 0);
+
+	clear_bit(idx, cpuc->active_mask);
+	armpmu->disable(hwc, idx);
+
+	barrier();
+
+	armpmu_event_update(event, hwc, idx);
+	cpuc->events[idx] = NULL;
+	clear_bit(idx, cpuc->used_mask);
+
+	perf_event_update_userpage(event);
+}
+
+static void
+armpmu_read(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	/* Don't read disabled counters! */
+	if (hwc->idx < 0)
+		return;
+
+	armpmu_event_update(event, hwc, hwc->idx);
+}
+
+static void
+armpmu_unthrottle(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	/*
+	 * Set the period again. Some counters can't be stopped, so when we
+	 * were throttled we simply disabled the IRQ source and the counter
+	 * may have been left counting. If we don't do this step then we may
+	 * get an interrupt too soon or *way* too late if the overflow has
+	 * happened since disabling.
+	 */
+	armpmu_event_set_period(event, hwc, hwc->idx);
+	armpmu->enable(hwc, hwc->idx);
+}
+
+static int
+armpmu_enable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx;
+	int err = 0;
+
+	/* If we don't have a space for the counter then finish early. */
+	idx = armpmu->get_event_idx(cpuc, hwc);
+	if (idx < 0) {
+		err = idx;
+		goto out;
+	}
+
+	/*
+	 * If there is an event in the counter we are going to use then make
+	 * sure it is disabled.
+	 */
+	event->hw.idx = idx;
+	armpmu->disable(hwc, idx);
+	cpuc->events[idx] = event;
+	set_bit(idx, cpuc->active_mask);
+
+	/* Set the period for the event. */
+	armpmu_event_set_period(event, hwc, idx);
+
+	/* Enable the event. */
+	armpmu->enable(hwc, idx);
+
+	/* Propagate our changes to the userspace mapping. */
+	perf_event_update_userpage(event);
+
+out:
+	return err;
+}
+
+static struct pmu pmu = {
+	.enable	    = armpmu_enable,
+	.disable    = armpmu_disable,
+	.unthrottle = armpmu_unthrottle,
+	.read	    = armpmu_read,
+};
+
+static int
+validate_event(struct cpu_hw_events *cpuc,
+	       struct perf_event *event)
+{
+	struct hw_perf_event fake_event = event->hw;
+
+	if (event->pmu && event->pmu != &pmu)
+		return 0;
+
+	return armpmu->get_event_idx(cpuc, &fake_event) >= 0;
+}
+
+static int
+validate_group(struct perf_event *event)
+{
+	struct perf_event *sibling, *leader = event->group_leader;
+	struct cpu_hw_events fake_pmu;
+
+	memset(&fake_pmu, 0, sizeof(fake_pmu));
+
+	if (!validate_event(&fake_pmu, leader))
+		return -ENOSPC;
+
+	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
+		if (!validate_event(&fake_pmu, sibling))
+			return -ENOSPC;
+	}
+
+	if (!validate_event(&fake_pmu, event))
+		return -ENOSPC;
+
+	return 0;
+}
+
+static int
+armpmu_reserve_hardware(void)
+{
+	int i;
+	int err;
+
+	pmu_irqs = reserve_pmu();
+	if (IS_ERR(pmu_irqs)) {
+		pr_warning("unable to reserve pmu\n");
+		return PTR_ERR(pmu_irqs);
+	}
+
+	init_pmu();
+
+	if (pmu_irqs->num_irqs < 1) {
+		pr_err("no irqs for PMUs defined\n");
+		return -ENODEV;
+	}
+
+	for (i = 0; i < pmu_irqs->num_irqs; ++i) {
+		err = request_irq(pmu_irqs->irqs[i], armpmu->handle_irq,
+				  IRQF_DISABLED, "armpmu", NULL);
+		if (err) {
+			pr_warning("unable to request IRQ%d for ARM "
+				   "perf counters\n", pmu_irqs->irqs[i]);
+			break;
+		}
+	}
+
+	if (err) {
+		for (i = i - 1; i >= 0; --i)
+			free_irq(pmu_irqs->irqs[i], NULL);
+		release_pmu(pmu_irqs);
+		pmu_irqs = NULL;
+	}
+
+	return err;
+}
+
+static void
+armpmu_release_hardware(void)
+{
+	int i;
+
+	for (i = pmu_irqs->num_irqs - 1; i >= 0; --i)
+		free_irq(pmu_irqs->irqs[i], NULL);
+	armpmu->stop();
+
+	release_pmu(pmu_irqs);
+	pmu_irqs = NULL;
+}
+
+static atomic_t active_events = ATOMIC_INIT(0);
+static DEFINE_MUTEX(pmu_reserve_mutex);
+
+static void
+hw_perf_event_destroy(struct perf_event *event)
+{
+	if (atomic_dec_and_mutex_lock(&active_events, &pmu_reserve_mutex)) {
+		armpmu_release_hardware();
+		mutex_unlock(&pmu_reserve_mutex);
+	}
+}
+
+static int
+__hw_perf_event_init(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int mapping, err;
+
+	/* Decode the generic type into an ARM event identifier. */
+	if (PERF_TYPE_HARDWARE == event->attr.type) {
+		mapping = armpmu->event_map(event->attr.config);
+	} else if (PERF_TYPE_HW_CACHE == event->attr.type) {
+		mapping = armpmu_map_cache_event(event->attr.config);
+	} else if (PERF_TYPE_RAW == event->attr.type) {
+		mapping = armpmu->raw_event(event->attr.config);
+	} else {
+		pr_debug("event type %x not supported\n", event->attr.type);
+		return -EOPNOTSUPP;
+	}
+
+	if (mapping < 0) {
+		pr_debug("event %x:%llx not supported\n", event->attr.type,
+			 event->attr.config);
+		return mapping;
+	}
+
+	/*
+	 * Check whether we need to exclude the counter from certain modes.
+	 * The ARM performance counters are on all of the time so if someone
+	 * has asked us for some excludes then we have to fail.
+	 */
+	if (event->attr.exclude_kernel || event->attr.exclude_user ||
+	    event->attr.exclude_hv || event->attr.exclude_idle) {
+		pr_debug("ARM performance counters do not support "
+			 "mode exclusion\n");
+		return -EPERM;
+	}
+
+	/*
+	 * We don't assign an index until we actually place the event onto
+	 * hardware. Use -1 to signify that we haven't decided where to put it
+	 * yet. For SMP systems, each core has it's own PMU so we can't do any
+	 * clever allocation or constraints checking at this point.
+	 */
+	hwc->idx = -1;
+
+	/*
+	 * Store the event encoding into the config_base field. config and
+	 * event_base are unused as the only 2 things we need to know are
+	 * the event mapping and the counter to use. The counter to use is
+	 * also the indx and the config_base is the event type.
+	 */
+	hwc->config_base	    = (unsigned long)mapping;
+	hwc->config		    = 0;
+	hwc->event_base		    = 0;
+
+	if (!hwc->sample_period) {
+		hwc->sample_period  = armpmu->max_period;
+		hwc->last_period    = hwc->sample_period;
+		atomic64_set(&hwc->period_left, hwc->sample_period);
+	}
+
+	err = 0;
+	if (event->group_leader != event) {
+		err = validate_group(event);
+		if (err)
+			return -EINVAL;
+	}
+
+	return err;
+}
+
+const struct pmu *
+hw_perf_event_init(struct perf_event *event)
+{
+	int err = 0;
+
+	if (!armpmu)
+		return ERR_PTR(-ENODEV);
+
+	event->destroy = hw_perf_event_destroy;
+
+	if (!atomic_inc_not_zero(&active_events)) {
+		if (atomic_read(&active_events) > perf_max_events) {
+			atomic_dec(&active_events);
+			return ERR_PTR(-ENOSPC);
+		}
+
+		mutex_lock(&pmu_reserve_mutex);
+		if (atomic_read(&active_events) == 0) {
+			err = armpmu_reserve_hardware();
+		}
+
+		if (!err)
+			atomic_inc(&active_events);
+		mutex_unlock(&pmu_reserve_mutex);
+	}
+
+	if (err)
+		return ERR_PTR(err);
+
+	err = __hw_perf_event_init(event);
+	if (err)
+		hw_perf_event_destroy(event);
+
+	return err ? ERR_PTR(err) : &pmu;
+}
+
+void
+hw_perf_enable(void)
+{
+	/* Enable all of the perf events on hardware. */
+	int idx;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+	if (!armpmu)
+		return;
+
+	for (idx = 0; idx <= armpmu->num_events; ++idx) {
+		struct perf_event *event = cpuc->events[idx];
+
+		if (!event)
+			continue;
+
+		armpmu->enable(&event->hw, idx);
+	}
+
+	armpmu->start();
+}
+
+void
+hw_perf_disable(void)
+{
+	if (armpmu)
+		armpmu->stop();
+}
+
+/*
+ * ARMv6 Performance counter handling code.
+ *
+ * ARMv6 has 2 configurable performance counters and a single cycle counter.
+ * They all share a single reset bit but can be written to zero so we can use
+ * that for a reset.
+ *
+ * The counters can't be individually enabled or disabled so when we remove
+ * one event and replace it with another we could get spurious counts from the
+ * wrong event. However, we can take advantage of the fact that the
+ * performance counters can export events to the event bus, and the event bus
+ * itself can be monitored. This requires that we *don't* export the events to
+ * the event bus. The procedure for disabling a configurable counter is:
+ *	- change the counter to count the ETMEXTOUT[0] signal (0x20). This
+ *	  effectively stops the counter from counting.
+ *	- disable the counter's interrupt generation (each counter has it's
+ *	  own interrupt enable bit).
+ * Once stopped, the counter value can be written as 0 to reset.
+ *
+ * To enable a counter:
+ *	- enable the counter's interrupt generation.
+ *	- set the new event type.
+ *
+ * Note: the dedicated cycle counter only counts cycles and can't be
+ * enabled/disabled independently of the others. When we want to disable the
+ * cycle counter, we have to just disable the interrupt reporting and start
+ * ignoring that counter. When re-enabling, we have to reset the value and
+ * enable the interrupt.
+ */
+
+enum armv6_perf_types {
+	ARMV6_PERFCTR_ICACHE_MISS	    = 0x0,
+	ARMV6_PERFCTR_IBUF_STALL	    = 0x1,
+	ARMV6_PERFCTR_DDEP_STALL	    = 0x2,
+	ARMV6_PERFCTR_ITLB_MISS		    = 0x3,
+	ARMV6_PERFCTR_DTLB_MISS		    = 0x4,
+	ARMV6_PERFCTR_BR_EXEC		    = 0x5,
+	ARMV6_PERFCTR_BR_MISPREDICT	    = 0x6,
+	ARMV6_PERFCTR_INSTR_EXEC	    = 0x7,
+	ARMV6_PERFCTR_DCACHE_HIT	    = 0x9,
+	ARMV6_PERFCTR_DCACHE_ACCESS	    = 0xA,
+	ARMV6_PERFCTR_DCACHE_MISS	    = 0xB,
+	ARMV6_PERFCTR_DCACHE_WBACK	    = 0xC,
+	ARMV6_PERFCTR_SW_PC_CHANGE	    = 0xD,
+	ARMV6_PERFCTR_MAIN_TLB_MISS	    = 0xF,
+	ARMV6_PERFCTR_EXPL_D_ACCESS	    = 0x10,
+	ARMV6_PERFCTR_LSU_FULL_STALL	    = 0x11,
+	ARMV6_PERFCTR_WBUF_DRAINED	    = 0x12,
+	ARMV6_PERFCTR_CPU_CYCLES	    = 0xFF,
+	ARMV6_PERFCTR_NOP		    = 0x20,
+};
+
+enum armv6_counters {
+	ARMV6_CYCLE_COUNTER = 1,
+	ARMV6_COUNTER0,
+	ARMV6_COUNTER1,
+};
+
+/*
+ * The hardware events that we support. We do support cache operations but
+ * we have harvard caches and no way to combine instruction and data
+ * accesses/misses in hardware.
+ */
+static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV6_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV6_PERFCTR_INSTR_EXEC,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6_PERFCTR_BR_EXEC,
+	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV6_PERFCTR_BR_MISPREDICT,
+	[PERF_COUNT_HW_BUS_CYCLES]	    = HW_OP_UNSUPPORTED,
+};
+
+static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					  [PERF_COUNT_HW_CACHE_OP_MAX]
+					  [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		/*
+		 * The performance counters don't differentiate between read
+		 * and write accesses/misses so this isn't strictly correct,
+		 * but it's the best we can do. Writes and reads get
+		 * combined.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV6_PERFCTR_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DCACHE_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV6_PERFCTR_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DCACHE_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ICACHE_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ICACHE_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(DTLB)] = {
+		/*
+		 * The ARM performance counters can count micro DTLB misses,
+		 * micro ITLB misses and main TLB misses. There isn't an event
+		 * for TLB misses, so use the micro misses here and if users
+		 * want the main TLB misses they can use a raw counter.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DTLB_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DTLB_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ITLB_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ITLB_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+};
+
+enum armv6mpcore_perf_types {
+	ARMV6MPCORE_PERFCTR_ICACHE_MISS	    = 0x0,
+	ARMV6MPCORE_PERFCTR_IBUF_STALL	    = 0x1,
+	ARMV6MPCORE_PERFCTR_DDEP_STALL	    = 0x2,
+	ARMV6MPCORE_PERFCTR_ITLB_MISS	    = 0x3,
+	ARMV6MPCORE_PERFCTR_DTLB_MISS	    = 0x4,
+	ARMV6MPCORE_PERFCTR_BR_EXEC	    = 0x5,
+	ARMV6MPCORE_PERFCTR_BR_NOTPREDICT   = 0x6,
+	ARMV6MPCORE_PERFCTR_BR_MISPREDICT   = 0x7,
+	ARMV6MPCORE_PERFCTR_INSTR_EXEC	    = 0x8,
+	ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS = 0xA,
+	ARMV6MPCORE_PERFCTR_DCACHE_RDMISS   = 0xB,
+	ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS = 0xC,
+	ARMV6MPCORE_PERFCTR_DCACHE_WRMISS   = 0xD,
+	ARMV6MPCORE_PERFCTR_DCACHE_EVICTION = 0xE,
+	ARMV6MPCORE_PERFCTR_SW_PC_CHANGE    = 0xF,
+	ARMV6MPCORE_PERFCTR_MAIN_TLB_MISS   = 0x10,
+	ARMV6MPCORE_PERFCTR_EXPL_MEM_ACCESS = 0x11,
+	ARMV6MPCORE_PERFCTR_LSU_FULL_STALL  = 0x12,
+	ARMV6MPCORE_PERFCTR_WBUF_DRAINED    = 0x13,
+	ARMV6MPCORE_PERFCTR_CPU_CYCLES	    = 0xFF,
+};
+
+/*
+ * The hardware events that we support. We do support cache operations but
+ * we have harvard caches and no way to combine instruction and data
+ * accesses/misses in hardware.
+ */
+static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV6MPCORE_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV6MPCORE_PERFCTR_INSTR_EXEC,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_BR_EXEC,
+	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV6MPCORE_PERFCTR_BR_MISPREDICT,
+	[PERF_COUNT_HW_BUS_CYCLES]	    = HW_OP_UNSUPPORTED,
+};
+
+static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					[PERF_COUNT_HW_CACHE_OP_MAX]
+					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]  =
+				ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
+			[C(RESULT_MISS)]    =
+				ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]  =
+				ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
+			[C(RESULT_MISS)]    =
+				ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(DTLB)] = {
+		/*
+		 * The ARM performance counters can count micro DTLB misses,
+		 * micro ITLB misses and main TLB misses. There isn't an event
+		 * for TLB misses, so use the micro misses here and if users
+		 * want the main TLB misses they can use a raw counter.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_DTLB_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_DTLB_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ITLB_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ITLB_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
+		},
+	},
+};
+
+static inline unsigned long
+armv6_pmcr_read(void)
+{
+	u32 val;
+	asm volatile("mrc   p15, 0, %0, c15, c12, 0" : "=r"(val));
+	return val;
+}
+
+static inline void
+armv6_pmcr_write(unsigned long val)
+{
+	asm volatile("mcr   p15, 0, %0, c15, c12, 0" : : "r"(val));
+}
+
+#define ARMV6_PMCR_ENABLE		(1 << 0)
+#define ARMV6_PMCR_CTR01_RESET		(1 << 1)
+#define ARMV6_PMCR_CCOUNT_RESET		(1 << 2)
+#define ARMV6_PMCR_CCOUNT_DIV		(1 << 3)
+#define ARMV6_PMCR_COUNT0_IEN		(1 << 4)
+#define ARMV6_PMCR_COUNT1_IEN		(1 << 5)
+#define ARMV6_PMCR_CCOUNT_IEN		(1 << 6)
+#define ARMV6_PMCR_COUNT0_OVERFLOW	(1 << 8)
+#define ARMV6_PMCR_COUNT1_OVERFLOW	(1 << 9)
+#define ARMV6_PMCR_CCOUNT_OVERFLOW	(1 << 10)
+#define ARMV6_PMCR_EVT_COUNT0_SHIFT	20
+#define ARMV6_PMCR_EVT_COUNT0_MASK	(0xFF << ARMV6_PMCR_EVT_COUNT0_SHIFT)
+#define ARMV6_PMCR_EVT_COUNT1_SHIFT	12
+#define ARMV6_PMCR_EVT_COUNT1_MASK	(0xFF << ARMV6_PMCR_EVT_COUNT1_SHIFT)
+
+#define ARMV6_PMCR_OVERFLOWED_MASK \
+	(ARMV6_PMCR_COUNT0_OVERFLOW | ARMV6_PMCR_COUNT1_OVERFLOW | \
+	 ARMV6_PMCR_CCOUNT_OVERFLOW)
+
+static inline int
+armv6_pmcr_has_overflowed(unsigned long pmcr)
+{
+	return (pmcr & ARMV6_PMCR_OVERFLOWED_MASK);
+}
+
+static inline int
+armv6_pmcr_counter_has_overflowed(unsigned long pmcr,
+				  enum armv6_counters counter)
+{
+	int ret = 0;
+
+	if (ARMV6_CYCLE_COUNTER == counter)
+		ret = pmcr & ARMV6_PMCR_CCOUNT_OVERFLOW;
+	else if (ARMV6_COUNTER0 == counter)
+		ret = pmcr & ARMV6_PMCR_COUNT0_OVERFLOW;
+	else if (ARMV6_COUNTER1 == counter)
+		ret = pmcr & ARMV6_PMCR_COUNT1_OVERFLOW;
+	else
+		WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+
+	return ret;
+}
+
+static inline u32
+armv6pmu_read_counter(int counter)
+{
+	unsigned long value = 0;
+
+	if (ARMV6_CYCLE_COUNTER == counter)
+		asm volatile("mrc   p15, 0, %0, c15, c12, 1" : "=r"(value));
+	else if (ARMV6_COUNTER0 == counter)
+		asm volatile("mrc   p15, 0, %0, c15, c12, 2" : "=r"(value));
+	else if (ARMV6_COUNTER1 == counter)
+		asm volatile("mrc   p15, 0, %0, c15, c12, 3" : "=r"(value));
+	else
+		WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+
+	return value;
+}
+
+static inline void
+armv6pmu_write_counter(int counter,
+		       u32 value)
+{
+	if (ARMV6_CYCLE_COUNTER == counter)
+		asm volatile("mcr   p15, 0, %0, c15, c12, 1" : : "r"(value));
+	else if (ARMV6_COUNTER0 == counter)
+		asm volatile("mcr   p15, 0, %0, c15, c12, 2" : : "r"(value));
+	else if (ARMV6_COUNTER1 == counter)
+		asm volatile("mcr   p15, 0, %0, c15, c12, 3" : : "r"(value));
+	else
+		WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+}
+
+void
+armv6pmu_enable_event(struct hw_perf_event *hwc,
+		      int idx)
+{
+	unsigned long val, mask, evt, flags;
+
+	if (ARMV6_CYCLE_COUNTER == idx) {
+		mask	= 0;
+		evt	= ARMV6_PMCR_CCOUNT_IEN;
+	} else if (ARMV6_COUNTER0 == idx) {
+		mask	= ARMV6_PMCR_EVT_COUNT0_MASK;
+		evt	= (hwc->config_base << ARMV6_PMCR_EVT_COUNT0_SHIFT) |
+			  ARMV6_PMCR_COUNT0_IEN;
+	} else if (ARMV6_COUNTER1 == idx) {
+		mask	= ARMV6_PMCR_EVT_COUNT1_MASK;
+		evt	= (hwc->config_base << ARMV6_PMCR_EVT_COUNT1_SHIFT) |
+			  ARMV6_PMCR_COUNT1_IEN;
+	} else {
+		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+		return;
+	}
+
+	/*
+	 * Mask out the current event and set the counter to count the event
+	 * that we're interested in.
+	 */
+	spin_lock_irqsave(&pmu_lock, flags);
+	val = armv6_pmcr_read();
+	val &= ~mask;
+	val |= evt;
+	armv6_pmcr_write(val);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static irqreturn_t
+armv6pmu_handle_irq(int irq_num,
+		    void *dev)
+{
+	unsigned long pmcr = armv6_pmcr_read();
+	struct perf_sample_data data;
+	struct cpu_hw_events *cpuc;
+	struct pt_regs *regs;
+	int idx;
+
+	if (!armv6_pmcr_has_overflowed(pmcr))
+		return IRQ_NONE;
+
+	regs = get_irq_regs();
+
+	/*
+	 * The interrupts are cleared by writing the overflow flags back to
+	 * the control register. All of the other bits don't have any effect
+	 * if they are rewritten, so write the whole value back.
+	 */
+	armv6_pmcr_write(pmcr);
+
+	data.addr = 0;
+
+	cpuc = &__get_cpu_var(cpu_hw_events);
+	for (idx = 0; idx <= armpmu->num_events; ++idx) {
+		struct perf_event *event = cpuc->events[idx];
+		struct hw_perf_event *hwc;
+
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+
+		/*
+		 * We have a single interrupt for all counters. Check that
+		 * each counter has overflowed before we process it.
+		 */
+		if (!armv6_pmcr_counter_has_overflowed(pmcr, idx))
+			continue;
+
+		hwc = &event->hw;
+		armpmu_event_update(event, hwc, idx);
+		data.period = event->hw.last_period;
+		if (!armpmu_event_set_period(event, hwc, idx))
+			continue;
+
+		if (perf_event_overflow(event, 0, &data, regs))
+			armpmu->disable(hwc, idx);
+	}
+
+	/*
+	 * Handle the pending perf events.
+	 *
+	 * Note: this call *must* be run with interrupts enabled. For
+	 * platforms that can have the PMU interrupts raised as a PMI, this
+	 * will not work.
+	 */
+	perf_event_do_pending();
+
+	return IRQ_HANDLED;
+}
+
+static void
+armv6pmu_start(void)
+{
+	unsigned long flags, val;
+
+	spin_lock_irqsave(&pmu_lock, flags);
+	val = armv6_pmcr_read();
+	val |= ARMV6_PMCR_ENABLE;
+	armv6_pmcr_write(val);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+void
+armv6pmu_stop(void)
+{
+	unsigned long flags, val;
+
+	spin_lock_irqsave(&pmu_lock, flags);
+	val = armv6_pmcr_read();
+	val &= ~ARMV6_PMCR_ENABLE;
+	armv6_pmcr_write(val);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static inline int
+armv6pmu_event_map(int config)
+{
+	int mapping = armv6_perf_map[config];
+	if (HW_OP_UNSUPPORTED == mapping)
+		mapping = -EOPNOTSUPP;
+	return mapping;
+}
+
+static inline int
+armv6mpcore_pmu_event_map(int config)
+{
+	int mapping = armv6mpcore_perf_map[config];
+	if (HW_OP_UNSUPPORTED == mapping)
+		mapping = -EOPNOTSUPP;
+	return mapping;
+}
+
+static u64
+armv6pmu_raw_event(u64 config)
+{
+	return config & 0xff;
+}
+
+static int
+armv6pmu_get_event_idx(struct cpu_hw_events *cpuc,
+		       struct hw_perf_event *event)
+{
+	/* Always place a cycle counter into the cycle counter. */
+	if (ARMV6_PERFCTR_CPU_CYCLES == event->config_base) {
+		if (test_and_set_bit(ARMV6_CYCLE_COUNTER, cpuc->used_mask))
+			return -EAGAIN;
+
+		return ARMV6_CYCLE_COUNTER;
+	} else {
+		/*
+		 * For anything other than a cycle counter, try and use
+		 * counter0 and counter1.
+		 */
+		if (!test_and_set_bit(ARMV6_COUNTER1, cpuc->used_mask)) {
+			return ARMV6_COUNTER1;
+		}
+
+		if (!test_and_set_bit(ARMV6_COUNTER0, cpuc->used_mask)) {
+			return ARMV6_COUNTER0;
+		}
+
+		/* The counters are all in use. */
+		return -EAGAIN;
+	}
+}
+
+static void
+armv6pmu_disable_event(struct hw_perf_event *hwc,
+		       int idx)
+{
+	unsigned long val, mask, evt, flags;
+
+	if (ARMV6_CYCLE_COUNTER == idx) {
+		mask	= ARMV6_PMCR_CCOUNT_IEN;
+		evt	= 0;
+	} else if (ARMV6_COUNTER0 == idx) {
+		mask	= ARMV6_PMCR_COUNT0_IEN | ARMV6_PMCR_EVT_COUNT0_MASK;
+		evt	= ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT0_SHIFT;
+	} else if (ARMV6_COUNTER1 == idx) {
+		mask	= ARMV6_PMCR_COUNT1_IEN | ARMV6_PMCR_EVT_COUNT1_MASK;
+		evt	= ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT1_SHIFT;
+	} else {
+		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+		return;
+	}
+
+	/*
+	 * Mask out the current event and set the counter to count the number
+	 * of ETM bus signal assertion cycles. The external reporting should
+	 * be disabled and so this should never increment.
+	 */
+	spin_lock_irqsave(&pmu_lock, flags);
+	val = armv6_pmcr_read();
+	val &= ~mask;
+	val |= evt;
+	armv6_pmcr_write(val);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
+			      int idx)
+{
+	unsigned long val, mask, flags, evt = 0;
+
+	if (ARMV6_CYCLE_COUNTER == idx) {
+		mask	= ARMV6_PMCR_CCOUNT_IEN;
+	} else if (ARMV6_COUNTER0 == idx) {
+		mask	= ARMV6_PMCR_COUNT0_IEN;
+	} else if (ARMV6_COUNTER1 == idx) {
+		mask	= ARMV6_PMCR_COUNT1_IEN;
+	} else {
+		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+		return;
+	}
+
+	/*
+	 * Unlike UP ARMv6, we don't have a way of stopping the counters. We
+	 * simply disable the interrupt reporting.
+	 */
+	spin_lock_irqsave(&pmu_lock, flags);
+	val = armv6_pmcr_read();
+	val &= ~mask;
+	val |= evt;
+	armv6_pmcr_write(val);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static const struct arm_pmu armv6pmu = {
+	.name			= "v6",
+	.handle_irq		= armv6pmu_handle_irq,
+	.enable			= armv6pmu_enable_event,
+	.disable		= armv6pmu_disable_event,
+	.event_map		= armv6pmu_event_map,
+	.raw_event		= armv6pmu_raw_event,
+	.read_counter		= armv6pmu_read_counter,
+	.write_counter		= armv6pmu_write_counter,
+	.get_event_idx		= armv6pmu_get_event_idx,
+	.start			= armv6pmu_start,
+	.stop			= armv6pmu_stop,
+	.num_events		= 3,
+	.max_period		= (1LLU << 32) - 1,
+};
+
+/*
+ * ARMv6mpcore is almost identical to single core ARMv6 with the exception
+ * that some of the events have different enumerations and that there is no
+ * *hack* to stop the programmable counters. To stop the counters we simply
+ * disable the interrupt reporting and update the event. When unthrottling we
+ * reset the period and enable the interrupt reporting.
+ */
+static const struct arm_pmu armv6mpcore_pmu = {
+	.name			= "v6mpcore",
+	.handle_irq		= armv6pmu_handle_irq,
+	.enable			= armv6pmu_enable_event,
+	.disable		= armv6mpcore_pmu_disable_event,
+	.event_map		= armv6mpcore_pmu_event_map,
+	.raw_event		= armv6pmu_raw_event,
+	.read_counter		= armv6pmu_read_counter,
+	.write_counter		= armv6pmu_write_counter,
+	.get_event_idx		= armv6pmu_get_event_idx,
+	.start			= armv6pmu_start,
+	.stop			= armv6pmu_stop,
+	.num_events		= 3,
+	.max_period		= (1LLU << 32) - 1,
+};
+
+/*
+ * ARMv7 Cortex-A8 and Cortex-A9 Performance Events handling code.
+ *
+ * Copied from ARMv6 code, with the low level code inspired
+ *  by the ARMv7 Oprofile code.
+ *
+ * Cortex-A8 has up to 4 configurable performance counters and
+ *  a single cycle counter.
+ * Cortex-A9 has up to 31 configurable performance counters and
+ *  a single cycle counter.
+ *
+ * All counters can be enabled/disabled and IRQ masked separately. The cycle
+ *  counter and all 4 performance counters together can be reset separately.
+ */
+
+#define ARMV7_PMU_CORTEX_A8_NAME		"ARMv7 Cortex-A8"
+
+#define ARMV7_PMU_CORTEX_A9_NAME		"ARMv7 Cortex-A9"
+
+/* Common ARMv7 event types */
+enum armv7_perf_types {
+	ARMV7_PERFCTR_PMNC_SW_INCR		= 0x00,
+	ARMV7_PERFCTR_IFETCH_MISS		= 0x01,
+	ARMV7_PERFCTR_ITLB_MISS			= 0x02,
+	ARMV7_PERFCTR_DCACHE_REFILL		= 0x03,
+	ARMV7_PERFCTR_DCACHE_ACCESS		= 0x04,
+	ARMV7_PERFCTR_DTLB_REFILL		= 0x05,
+	ARMV7_PERFCTR_DREAD			= 0x06,
+	ARMV7_PERFCTR_DWRITE			= 0x07,
+
+	ARMV7_PERFCTR_EXC_TAKEN			= 0x09,
+	ARMV7_PERFCTR_EXC_EXECUTED		= 0x0A,
+	ARMV7_PERFCTR_CID_WRITE			= 0x0B,
+	/* ARMV7_PERFCTR_PC_WRITE is equivalent to HW_BRANCH_INSTRUCTIONS.
+	 * It counts:
+	 *  - all branch instructions,
+	 *  - instructions that explicitly write the PC,
+	 *  - exception generating instructions.
+	 */
+	ARMV7_PERFCTR_PC_WRITE			= 0x0C,
+	ARMV7_PERFCTR_PC_IMM_BRANCH		= 0x0D,
+	ARMV7_PERFCTR_UNALIGNED_ACCESS		= 0x0F,
+	ARMV7_PERFCTR_PC_BRANCH_MIS_PRED	= 0x10,
+	ARMV7_PERFCTR_CLOCK_CYCLES		= 0x11,
+
+	ARMV7_PERFCTR_PC_BRANCH_MIS_USED	= 0x12,
+
+	ARMV7_PERFCTR_CPU_CYCLES		= 0xFF
+};
+
+/* ARMv7 Cortex-A8 specific event types */
+enum armv7_a8_perf_types {
+	ARMV7_PERFCTR_INSTR_EXECUTED		= 0x08,
+
+	ARMV7_PERFCTR_PC_PROC_RETURN		= 0x0E,
+
+	ARMV7_PERFCTR_WRITE_BUFFER_FULL		= 0x40,
+	ARMV7_PERFCTR_L2_STORE_MERGED		= 0x41,
+	ARMV7_PERFCTR_L2_STORE_BUFF		= 0x42,
+	ARMV7_PERFCTR_L2_ACCESS			= 0x43,
+	ARMV7_PERFCTR_L2_CACH_MISS		= 0x44,
+	ARMV7_PERFCTR_AXI_READ_CYCLES		= 0x45,
+	ARMV7_PERFCTR_AXI_WRITE_CYCLES		= 0x46,
+	ARMV7_PERFCTR_MEMORY_REPLAY		= 0x47,
+	ARMV7_PERFCTR_UNALIGNED_ACCESS_REPLAY	= 0x48,
+	ARMV7_PERFCTR_L1_DATA_MISS		= 0x49,
+	ARMV7_PERFCTR_L1_INST_MISS		= 0x4A,
+	ARMV7_PERFCTR_L1_DATA_COLORING		= 0x4B,
+	ARMV7_PERFCTR_L1_NEON_DATA		= 0x4C,
+	ARMV7_PERFCTR_L1_NEON_CACH_DATA		= 0x4D,
+	ARMV7_PERFCTR_L2_NEON			= 0x4E,
+	ARMV7_PERFCTR_L2_NEON_HIT		= 0x4F,
+	ARMV7_PERFCTR_L1_INST			= 0x50,
+	ARMV7_PERFCTR_PC_RETURN_MIS_PRED	= 0x51,
+	ARMV7_PERFCTR_PC_BRANCH_FAILED		= 0x52,
+	ARMV7_PERFCTR_PC_BRANCH_TAKEN		= 0x53,
+	ARMV7_PERFCTR_PC_BRANCH_EXECUTED	= 0x54,
+	ARMV7_PERFCTR_OP_EXECUTED		= 0x55,
+	ARMV7_PERFCTR_CYCLES_INST_STALL		= 0x56,
+	ARMV7_PERFCTR_CYCLES_INST		= 0x57,
+	ARMV7_PERFCTR_CYCLES_NEON_DATA_STALL	= 0x58,
+	ARMV7_PERFCTR_CYCLES_NEON_INST_STALL	= 0x59,
+	ARMV7_PERFCTR_NEON_CYCLES		= 0x5A,
+
+	ARMV7_PERFCTR_PMU0_EVENTS		= 0x70,
+	ARMV7_PERFCTR_PMU1_EVENTS		= 0x71,
+	ARMV7_PERFCTR_PMU_EVENTS		= 0x72,
+};
+
+/* ARMv7 Cortex-A9 specific event types */
+enum armv7_a9_perf_types {
+	ARMV7_PERFCTR_JAVA_HW_BYTECODE_EXEC	= 0x40,
+	ARMV7_PERFCTR_JAVA_SW_BYTECODE_EXEC	= 0x41,
+	ARMV7_PERFCTR_JAZELLE_BRANCH_EXEC	= 0x42,
+
+	ARMV7_PERFCTR_COHERENT_LINE_MISS	= 0x50,
+	ARMV7_PERFCTR_COHERENT_LINE_HIT		= 0x51,
+
+	ARMV7_PERFCTR_ICACHE_DEP_STALL_CYCLES	= 0x60,
+	ARMV7_PERFCTR_DCACHE_DEP_STALL_CYCLES	= 0x61,
+	ARMV7_PERFCTR_TLB_MISS_DEP_STALL_CYCLES	= 0x62,
+	ARMV7_PERFCTR_STREX_EXECUTED_PASSED	= 0x63,
+	ARMV7_PERFCTR_STREX_EXECUTED_FAILED	= 0x64,
+	ARMV7_PERFCTR_DATA_EVICTION		= 0x65,
+	ARMV7_PERFCTR_ISSUE_STAGE_NO_INST	= 0x66,
+	ARMV7_PERFCTR_ISSUE_STAGE_EMPTY		= 0x67,
+	ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE	= 0x68,
+
+	ARMV7_PERFCTR_PREDICTABLE_FUNCT_RETURNS	= 0x6E,
+
+	ARMV7_PERFCTR_MAIN_UNIT_EXECUTED_INST	= 0x70,
+	ARMV7_PERFCTR_SECOND_UNIT_EXECUTED_INST	= 0x71,
+	ARMV7_PERFCTR_LD_ST_UNIT_EXECUTED_INST	= 0x72,
+	ARMV7_PERFCTR_FP_EXECUTED_INST		= 0x73,
+	ARMV7_PERFCTR_NEON_EXECUTED_INST	= 0x74,
+
+	ARMV7_PERFCTR_PLD_FULL_DEP_STALL_CYCLES	= 0x80,
+	ARMV7_PERFCTR_DATA_WR_DEP_STALL_CYCLES	= 0x81,
+	ARMV7_PERFCTR_ITLB_MISS_DEP_STALL_CYCLES	= 0x82,
+	ARMV7_PERFCTR_DTLB_MISS_DEP_STALL_CYCLES	= 0x83,
+	ARMV7_PERFCTR_MICRO_ITLB_MISS_DEP_STALL_CYCLES	= 0x84,
+	ARMV7_PERFCTR_MICRO_DTLB_MISS_DEP_STALL_CYCLES 	= 0x85,
+	ARMV7_PERFCTR_DMB_DEP_STALL_CYCLES	= 0x86,
+
+	ARMV7_PERFCTR_INTGR_CLK_ENABLED_CYCLES	= 0x8A,
+	ARMV7_PERFCTR_DATA_ENGINE_CLK_EN_CYCLES	= 0x8B,
+
+	ARMV7_PERFCTR_ISB_INST			= 0x90,
+	ARMV7_PERFCTR_DSB_INST			= 0x91,
+	ARMV7_PERFCTR_DMB_INST			= 0x92,
+	ARMV7_PERFCTR_EXT_INTERRUPTS		= 0x93,
+
+	ARMV7_PERFCTR_PLE_CACHE_LINE_RQST_COMPLETED	= 0xA0,
+	ARMV7_PERFCTR_PLE_CACHE_LINE_RQST_SKIPPED	= 0xA1,
+	ARMV7_PERFCTR_PLE_FIFO_FLUSH		= 0xA2,
+	ARMV7_PERFCTR_PLE_RQST_COMPLETED	= 0xA3,
+	ARMV7_PERFCTR_PLE_FIFO_OVERFLOW		= 0xA4,
+	ARMV7_PERFCTR_PLE_RQST_PROG		= 0xA5
+};
+
+/*
+ * Cortex-A8 HW events mapping
+ *
+ * The hardware events that we support. We do support cache operations but
+ * we have harvard caches and no way to combine instruction and data
+ * accesses/misses in hardware.
+ */
+static const unsigned armv7_a8_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV7_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV7_PERFCTR_INSTR_EXECUTED,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
+	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]	    = ARMV7_PERFCTR_CLOCK_CYCLES,
+};
+
+static const unsigned armv7_a8_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					  [PERF_COUNT_HW_CACHE_OP_MAX]
+					  [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		/*
+		 * The performance counters don't differentiate between read
+		 * and write accesses/misses so this isn't strictly correct,
+		 * but it's the best we can do. Writes and reads get
+		 * combined.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DCACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DCACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_INST,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_INST_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_INST,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_INST_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACH_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACH_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(DTLB)] = {
+		/*
+		 * Only ITLB misses and DTLB refills are supported.
+		 * If users want the DTLB refills misses a raw counter
+		 * must be used.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_WRITE,
+			[C(RESULT_MISS)]
+					= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_WRITE,
+			[C(RESULT_MISS)]
+					= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+};
+
+/*
+ * Cortex-A9 HW events mapping
+ */
+static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV7_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]	    =
+					ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = ARMV7_PERFCTR_COHERENT_LINE_HIT,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = ARMV7_PERFCTR_COHERENT_LINE_MISS,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
+	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]	    = ARMV7_PERFCTR_CLOCK_CYCLES,
+};
+
+static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					  [PERF_COUNT_HW_CACHE_OP_MAX]
+					  [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		/*
+		 * The performance counters don't differentiate between read
+		 * and write accesses/misses so this isn't strictly correct,
+		 * but it's the best we can do. Writes and reads get
+		 * combined.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DCACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DCACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_IFETCH_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_IFETCH_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(DTLB)] = {
+		/*
+		 * Only ITLB misses and DTLB refills are supported.
+		 * If users want the DTLB refills misses a raw counter
+		 * must be used.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_WRITE,
+			[C(RESULT_MISS)]
+					= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_WRITE,
+			[C(RESULT_MISS)]
+					= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+};
+
+/*
+ * Perf Events counters
+ */
+enum armv7_counters {
+	ARMV7_CYCLE_COUNTER 		= 1,	/* Cycle counter */
+	ARMV7_COUNTER0			= 2,	/* First event counter */
+};
+
+/*
+ * The cycle counter is ARMV7_CYCLE_COUNTER.
+ * The first event counter is ARMV7_COUNTER0.
+ * The last event counter is (ARMV7_COUNTER0 + armpmu->num_events - 1).
+ */
+#define	ARMV7_COUNTER_LAST	(ARMV7_COUNTER0 + armpmu->num_events - 1)
+
+/*
+ * ARMv7 low level PMNC access
+ */
+
+/*
+ * Per-CPU PMNC: config reg
+ */
+#define ARMV7_PMNC_E		(1 << 0) /* Enable all counters */
+#define ARMV7_PMNC_P		(1 << 1) /* Reset all counters */
+#define ARMV7_PMNC_C		(1 << 2) /* Cycle counter reset */
+#define ARMV7_PMNC_D		(1 << 3) /* CCNT counts every 64th cpu cycle */
+#define ARMV7_PMNC_X		(1 << 4) /* Export to ETM */
+#define ARMV7_PMNC_DP		(1 << 5) /* Disable CCNT if non-invasive debug*/
+#define	ARMV7_PMNC_N_SHIFT	11	 /* Number of counters supported */
+#define	ARMV7_PMNC_N_MASK	0x1f
+#define	ARMV7_PMNC_MASK		0x3f	 /* Mask for writable bits */
+
+/*
+ * Available counters
+ */
+#define ARMV7_CNT0 		0	/* First event counter */
+#define ARMV7_CCNT 		31	/* Cycle counter */
+
+/* Perf Event to low level counters mapping */
+#define ARMV7_EVENT_CNT_TO_CNTx	(ARMV7_COUNTER0 - ARMV7_CNT0)
+
+/*
+ * CNTENS: counters enable reg
+ */
+#define ARMV7_CNTENS_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
+#define ARMV7_CNTENS_C		(1 << ARMV7_CCNT)
+
+/*
+ * CNTENC: counters disable reg
+ */
+#define ARMV7_CNTENC_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
+#define ARMV7_CNTENC_C		(1 << ARMV7_CCNT)
+
+/*
+ * INTENS: counters overflow interrupt enable reg
+ */
+#define ARMV7_INTENS_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
+#define ARMV7_INTENS_C		(1 << ARMV7_CCNT)
+
+/*
+ * INTENC: counters overflow interrupt disable reg
+ */
+#define ARMV7_INTENC_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
+#define ARMV7_INTENC_C		(1 << ARMV7_CCNT)
+
+/*
+ * EVTSEL: Event selection reg
+ */
+#define	ARMV7_EVTSEL_MASK	0x7f		/* Mask for writable bits */
+
+/*
+ * SELECT: Counter selection reg
+ */
+#define	ARMV7_SELECT_MASK	0x1f		/* Mask for writable bits */
+
+/*
+ * FLAG: counters overflow flag status reg
+ */
+#define ARMV7_FLAG_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
+#define ARMV7_FLAG_C		(1 << ARMV7_CCNT)
+#define	ARMV7_FLAG_MASK		0xffffffff	/* Mask for writable bits */
+#define	ARMV7_OVERFLOWED_MASK	ARMV7_FLAG_MASK
+
+static inline unsigned long armv7_pmnc_read(void)
+{
+	u32 val;
+	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r"(val));
+	return val;
+}
+
+static inline void armv7_pmnc_write(unsigned long val)
+{
+	val &= ARMV7_PMNC_MASK;
+	asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r"(val));
+}
+
+static inline int armv7_pmnc_has_overflowed(unsigned long pmnc)
+{
+	return pmnc & ARMV7_OVERFLOWED_MASK;
+}
+
+static inline int armv7_pmnc_counter_has_overflowed(unsigned long pmnc,
+					enum armv7_counters counter)
+{
+	int ret;
+
+	if (counter == ARMV7_CYCLE_COUNTER)
+		ret = pmnc & ARMV7_FLAG_C;
+	else if ((counter >= ARMV7_COUNTER0) && (counter <= ARMV7_COUNTER_LAST))
+		ret = pmnc & ARMV7_FLAG_P(counter);
+	else
+		pr_err("CPU%u checking wrong counter %d overflow status\n",
+			smp_processor_id(), counter);
+
+	return ret;
+}
+
+static inline int armv7_pmnc_select_counter(unsigned int idx)
+{
+	u32 val;
+
+	if ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST)) {
+		pr_err("CPU%u selecting wrong PMNC counter"
+			" %d\n", smp_processor_id(), idx);
+		return -1;
+	}
+
+	val = (idx - ARMV7_EVENT_CNT_TO_CNTx) & ARMV7_SELECT_MASK;
+	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));
+
+	return idx;
+}
+
+static inline u32 armv7pmu_read_counter(int idx)
+{
+	unsigned long value = 0;
+
+	if (idx == ARMV7_CYCLE_COUNTER)
+		asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value));
+	else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
+		if (armv7_pmnc_select_counter(idx) == idx)
+			asm volatile("mrc p15, 0, %0, c9, c13, 2"
+				     : "=r" (value));
+	} else
+		pr_err("CPU%u reading wrong counter %d\n",
+			smp_processor_id(), idx);
+
+	return value;
+}
+
+static inline void armv7pmu_write_counter(int idx, u32 value)
+{
+	if (idx == ARMV7_CYCLE_COUNTER)
+		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value));
+	else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
+		if (armv7_pmnc_select_counter(idx) == idx)
+			asm volatile("mcr p15, 0, %0, c9, c13, 2"
+				     : : "r" (value));
+	} else
+		pr_err("CPU%u writing wrong counter %d\n",
+			smp_processor_id(), idx);
+}
+
+static inline void armv7_pmnc_write_evtsel(unsigned int idx, u32 val)
+{
+	if (armv7_pmnc_select_counter(idx) == idx) {
+		val &= ARMV7_EVTSEL_MASK;
+		asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
+	}
+}
+
+static inline u32 armv7_pmnc_enable_counter(unsigned int idx)
+{
+	u32 val;
+
+	if ((idx != ARMV7_CYCLE_COUNTER) &&
+	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
+		pr_err("CPU%u enabling wrong PMNC counter"
+			" %d\n", smp_processor_id(), idx);
+		return -1;
+	}
+
+	if (idx == ARMV7_CYCLE_COUNTER)
+		val = ARMV7_CNTENS_C;
+	else
+		val = ARMV7_CNTENS_P(idx);
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));
+
+	return idx;
+}
+
+static inline u32 armv7_pmnc_disable_counter(unsigned int idx)
+{
+	u32 val;
+
+
+	if ((idx != ARMV7_CYCLE_COUNTER) &&
+	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
+		pr_err("CPU%u disabling wrong PMNC counter"
+			" %d\n", smp_processor_id(), idx);
+		return -1;
+	}
+
+	if (idx == ARMV7_CYCLE_COUNTER)
+		val = ARMV7_CNTENC_C;
+	else
+		val = ARMV7_CNTENC_P(idx);
+
+	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));
+
+	return idx;
+}
+
+static inline u32 armv7_pmnc_enable_intens(unsigned int idx)
+{
+	u32 val;
+
+	if ((idx != ARMV7_CYCLE_COUNTER) &&
+	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
+		pr_err("CPU%u enabling wrong PMNC counter"
+			" interrupt enable %d\n", smp_processor_id(), idx);
+		return -1;
+	}
+
+	if (idx == ARMV7_CYCLE_COUNTER)
+		val = ARMV7_INTENS_C;
+	else
+		val = ARMV7_INTENS_P(idx);
+
+	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (val));
+
+	return idx;
+}
+
+static inline u32 armv7_pmnc_disable_intens(unsigned int idx)
+{
+	u32 val;
+
+	if ((idx != ARMV7_CYCLE_COUNTER) &&
+	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
+		pr_err("CPU%u disabling wrong PMNC counter"
+			" interrupt enable %d\n", smp_processor_id(), idx);
+		return -1;
+	}
+
+	if (idx == ARMV7_CYCLE_COUNTER)
+		val = ARMV7_INTENC_C;
+	else
+		val = ARMV7_INTENC_P(idx);
+
+	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (val));
+
+	return idx;
+}
+
+static inline u32 armv7_pmnc_getreset_flags(void)
+{
+	u32 val;
+
+	/* Read */
+	asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val));
+
+	/* Write to clear flags */
+	val &= ARMV7_FLAG_MASK;
+	asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (val));
+
+	return val;
+}
+
+#ifdef DEBUG
+static void armv7_pmnc_dump_regs(void)
+{
+	u32 val;
+	unsigned int cnt;
+
+	printk(KERN_INFO "PMNC registers dump:\n");
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
+	printk(KERN_INFO "PMNC  =0x%08x\n", val);
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (val));
+	printk(KERN_INFO "CNTENS=0x%08x\n", val);
+
+	asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (val));
+	printk(KERN_INFO "INTENS=0x%08x\n", val);
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val));
+	printk(KERN_INFO "FLAGS =0x%08x\n", val);
+
+	asm volatile("mrc p15, 0, %0, c9, c12, 5" : "=r" (val));
+	printk(KERN_INFO "SELECT=0x%08x\n", val);
+
+	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
+	printk(KERN_INFO "CCNT  =0x%08x\n", val);
+
+	for (cnt = ARMV7_COUNTER0; cnt < ARMV7_COUNTER_LAST; cnt++) {
+		armv7_pmnc_select_counter(cnt);
+		asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val));
+		printk(KERN_INFO "CNT[%d] count =0x%08x\n",
+			cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
+		asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val));
+		printk(KERN_INFO "CNT[%d] evtsel=0x%08x\n",
+			cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
+	}
+}
+#endif
+
+void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
+{
+	unsigned long flags;
+
+	/*
+	 * Enable counter and interrupt, and set the counter to count
+	 * the event that we're interested in.
+	 */
+	spin_lock_irqsave(&pmu_lock, flags);
+
+	/*
+	 * Disable counter
+	 */
+	armv7_pmnc_disable_counter(idx);
+
+	/*
+	 * Set event (if destined for PMNx counters)
+	 * We don't need to set the event if it's a cycle count
+	 */
+	if (idx != ARMV7_CYCLE_COUNTER)
+		armv7_pmnc_write_evtsel(idx, hwc->config_base);
+
+	/*
+	 * Enable interrupt for this counter
+	 */
+	armv7_pmnc_enable_intens(idx);
+
+	/*
+	 * Enable counter
+	 */
+	armv7_pmnc_enable_counter(idx);
+
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
+{
+	unsigned long flags;
+
+	/*
+	 * Disable counter and interrupt
+	 */
+	spin_lock_irqsave(&pmu_lock, flags);
+
+	/*
+	 * Disable counter
+	 */
+	armv7_pmnc_disable_counter(idx);
+
+	/*
+	 * Disable interrupt for this counter
+	 */
+	armv7_pmnc_disable_intens(idx);
+
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
+{
+	unsigned long pmnc;
+	struct perf_sample_data data;
+	struct cpu_hw_events *cpuc;
+	struct pt_regs *regs;
+	int idx;
+
+	/*
+	 * Get and reset the IRQ flags
+	 */
+	pmnc = armv7_pmnc_getreset_flags();
+
+	/*
+	 * Did an overflow occur?
+	 */
+	if (!armv7_pmnc_has_overflowed(pmnc))
+		return IRQ_NONE;
+
+	/*
+	 * Handle the counter(s) overflow(s)
+	 */
+	regs = get_irq_regs();
+
+	data.addr = 0;
+
+	cpuc = &__get_cpu_var(cpu_hw_events);
+	for (idx = 0; idx <= armpmu->num_events; ++idx) {
+		struct perf_event *event = cpuc->events[idx];
+		struct hw_perf_event *hwc;
+
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+
+		/*
+		 * We have a single interrupt for all counters. Check that
+		 * each counter has overflowed before we process it.
+		 */
+		if (!armv7_pmnc_counter_has_overflowed(pmnc, idx))
+			continue;
+
+		hwc = &event->hw;
+		armpmu_event_update(event, hwc, idx);
+		data.period = event->hw.last_period;
+		if (!armpmu_event_set_period(event, hwc, idx))
+			continue;
+
+		if (perf_event_overflow(event, 0, &data, regs))
+			armpmu->disable(hwc, idx);
+	}
+
+	/*
+	 * Handle the pending perf events.
+	 *
+	 * Note: this call *must* be run with interrupts enabled. For
+	 * platforms that can have the PMU interrupts raised as a PMI, this
+	 * will not work.
+	 */
+	perf_event_do_pending();
+
+	return IRQ_HANDLED;
+}
+
+static void armv7pmu_start(void)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&pmu_lock, flags);
+	/* Enable all counters */
+	armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void armv7pmu_stop(void)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&pmu_lock, flags);
+	/* Disable all counters */
+	armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static inline int armv7_a8_pmu_event_map(int config)
+{
+	int mapping = armv7_a8_perf_map[config];
+	if (HW_OP_UNSUPPORTED == mapping)
+		mapping = -EOPNOTSUPP;
+	return mapping;
+}
+
+static inline int armv7_a9_pmu_event_map(int config)
+{
+	int mapping = armv7_a9_perf_map[config];
+	if (HW_OP_UNSUPPORTED == mapping)
+		mapping = -EOPNOTSUPP;
+	return mapping;
+}
+
+static u64 armv7pmu_raw_event(u64 config)
+{
+	return config & 0xff;
+}
+
+static int armv7pmu_get_event_idx(struct cpu_hw_events *cpuc,
+				  struct hw_perf_event *event)
+{
+	int idx;
+
+	/* Always place a cycle counter into the cycle counter. */
+	if (event->config_base == ARMV7_PERFCTR_CPU_CYCLES) {
+		if (test_and_set_bit(ARMV7_CYCLE_COUNTER, cpuc->used_mask))
+			return -EAGAIN;
+
+		return ARMV7_CYCLE_COUNTER;
+	} else {
+		/*
+		 * For anything other than a cycle counter, try and use
+		 * the events counters
+		 */
+		for (idx = ARMV7_COUNTER0; idx <= armpmu->num_events; ++idx) {
+			if (!test_and_set_bit(idx, cpuc->used_mask))
+				return idx;
+		}
+
+		/* The counters are all in use. */
+		return -EAGAIN;
+	}
+}
+
+static struct arm_pmu armv7pmu = {
+	.handle_irq		= armv7pmu_handle_irq,
+	.enable			= armv7pmu_enable_event,
+	.disable		= armv7pmu_disable_event,
+	.raw_event		= armv7pmu_raw_event,
+	.read_counter		= armv7pmu_read_counter,
+	.write_counter		= armv7pmu_write_counter,
+	.get_event_idx		= armv7pmu_get_event_idx,
+	.start			= armv7pmu_start,
+	.stop			= armv7pmu_stop,
+	.max_period		= (1LLU << 32) - 1,
+};
+
+static u32 __init armv7_reset_read_pmnc(void)
+{
+	u32 nb_cnt;
+
+	/* Initialize & Reset PMNC: C and P bits */
+	armv7_pmnc_write(ARMV7_PMNC_P | ARMV7_PMNC_C);
+
+	/* Read the nb of CNTx counters supported from PMNC */
+	nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK;
+
+	/* Add the CPU cycles counter and return */
+	return nb_cnt + 1;
+}
+
+static int __init
+init_hw_perf_events(void)
+{
+	unsigned long cpuid = read_cpuid_id();
+	unsigned long implementor = (cpuid & 0xFF000000) >> 24;
+	unsigned long part_number = (cpuid & 0xFFF0);
+
+	/* We only support ARM CPUs implemented by ARM at the moment. */
+	if (0x41 == implementor) {
+		switch (part_number) {
+		case 0xB360:	/* ARM1136 */
+		case 0xB560:	/* ARM1156 */
+		case 0xB760:	/* ARM1176 */
+			armpmu = &armv6pmu;
+			memcpy(armpmu_perf_cache_map, armv6_perf_cache_map,
+					sizeof(armv6_perf_cache_map));
+			perf_max_events	= armv6pmu.num_events;
+			break;
+		case 0xB020:	/* ARM11mpcore */
+			armpmu = &armv6mpcore_pmu;
+			memcpy(armpmu_perf_cache_map,
+			       armv6mpcore_perf_cache_map,
+			       sizeof(armv6mpcore_perf_cache_map));
+			perf_max_events = armv6mpcore_pmu.num_events;
+			break;
+		case 0xC080:	/* Cortex-A8 */
+			armv7pmu.name = ARMV7_PMU_CORTEX_A8_NAME;
+			memcpy(armpmu_perf_cache_map, armv7_a8_perf_cache_map,
+				sizeof(armv7_a8_perf_cache_map));
+			armv7pmu.event_map = armv7_a8_pmu_event_map;
+			armpmu = &armv7pmu;
+
+			/* Reset PMNC and read the nb of CNTx counters
+			    supported */
+			armv7pmu.num_events = armv7_reset_read_pmnc();
+			perf_max_events = armv7pmu.num_events;
+			break;
+		case 0xC090:	/* Cortex-A9 */
+			armv7pmu.name = ARMV7_PMU_CORTEX_A9_NAME;
+			memcpy(armpmu_perf_cache_map, armv7_a9_perf_cache_map,
+				sizeof(armv7_a9_perf_cache_map));
+			armv7pmu.event_map = armv7_a9_pmu_event_map;
+			armpmu = &armv7pmu;
+
+			/* Reset PMNC and read the nb of CNTx counters
+			    supported */
+			armv7pmu.num_events = armv7_reset_read_pmnc();
+			perf_max_events = armv7pmu.num_events;
+			break;
+		default:
+			pr_info("no hardware support available\n");
+			perf_max_events = -1;
+		}
+	}
+
+	if (armpmu)
+		pr_info("enabled with %s PMU driver, %d counters available\n",
+			armpmu->name, armpmu->num_events);
+
+	return 0;
+}
+arch_initcall(init_hw_perf_events);
+
+/*
+ * Callchain handling code.
+ */
+static inline void
+callchain_store(struct perf_callchain_entry *entry,
+		u64 ip)
+{
+	if (entry->nr < PERF_MAX_STACK_DEPTH)
+		entry->ip[entry->nr++] = ip;
+}
+
+/*
+ * 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
+ *
+ * This code has been adapted from the ARM OProfile support.
+ */
+struct frame_tail {
+	struct frame_tail   *fp;
+	unsigned long	    sp;
+	unsigned long	    lr;
+} __attribute__((packed));
+
+/*
+ * Get the return address for a single stackframe and return a pointer to the
+ * next frame tail.
+ */
+static struct frame_tail *
+user_backtrace(struct frame_tail *tail,
+	       struct perf_callchain_entry *entry)
+{
+	struct frame_tail buftail;
+
+	/* 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;
+
+	callchain_store(entry, buftail.lr);
+
+	/*
+	 * Frame pointers should strictly progress back up the stack
+	 * (towards higher addresses).
+	 */
+	if (tail >= buftail.fp)
+		return NULL;
+
+	return buftail.fp - 1;
+}
+
+static void
+perf_callchain_user(struct pt_regs *regs,
+		    struct perf_callchain_entry *entry)
+{
+	struct frame_tail *tail;
+
+	callchain_store(entry, PERF_CONTEXT_USER);
+
+	if (!user_mode(regs))
+		regs = task_pt_regs(current);
+
+	tail = (struct frame_tail *)regs->ARM_fp - 1;
+
+	while (tail && !((unsigned long)tail & 0x3))
+		tail = user_backtrace(tail, entry);
+}
+
+/*
+ * Gets called by walk_stackframe() for every stackframe. This will be called
+ * whist unwinding the stackframe and is like a subroutine return so we use
+ * the PC.
+ */
+static int
+callchain_trace(struct stackframe *fr,
+		void *data)
+{
+	struct perf_callchain_entry *entry = data;
+	callchain_store(entry, fr->pc);
+	return 0;
+}
+
+static void
+perf_callchain_kernel(struct pt_regs *regs,
+		      struct perf_callchain_entry *entry)
+{
+	struct stackframe fr;
+
+	callchain_store(entry, PERF_CONTEXT_KERNEL);
+	fr.fp = regs->ARM_fp;
+	fr.sp = regs->ARM_sp;
+	fr.lr = regs->ARM_lr;
+	fr.pc = regs->ARM_pc;
+	walk_stackframe(&fr, callchain_trace, entry);
+}
+
+static void
+perf_do_callchain(struct pt_regs *regs,
+		  struct perf_callchain_entry *entry)
+{
+	int is_user;
+
+	if (!regs)
+		return;
+
+	is_user = user_mode(regs);
+
+	if (!current || !current->pid)
+		return;
+
+	if (is_user && current->state != TASK_RUNNING)
+		return;
+
+	if (!is_user)
+		perf_callchain_kernel(regs, entry);
+
+	if (current->mm)
+		perf_callchain_user(regs, entry);
+}
+
+static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);
+
+struct perf_callchain_entry *
+perf_callchain(struct pt_regs *regs)
+{
+	struct perf_callchain_entry *entry = &__get_cpu_var(pmc_irq_entry);
+
+	entry->nr = 0;
+	perf_do_callchain(regs, entry);
+	return entry;
+}
diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c
new file mode 100644
index 000000000000..a124312e343f
--- /dev/null
+++ b/arch/arm/kernel/pmu.c
@@ -0,0 +1,103 @@
+/*
+ *  linux/arch/arm/kernel/pmu.c
+ *
+ *  Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/cpumask.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/pmu.h>
+
+/*
+ * Define the IRQs for the system. We could use something like a platform
+ * device but that seems fairly heavyweight for this. Also, the performance
+ * counters can't be removed or hotplugged.
+ *
+ * Ordering is important: init_pmu() will use the ordering to set the affinity
+ * to the corresponding core. e.g. the first interrupt will go to cpu 0, the
+ * second goes to cpu 1 etc.
+ */
+static const int irqs[] = {
+#if defined(CONFIG_ARCH_OMAP2)
+	3,
+#elif defined(CONFIG_ARCH_BCMRING)
+	IRQ_PMUIRQ,
+#elif defined(CONFIG_MACH_REALVIEW_EB)
+	IRQ_EB11MP_PMU_CPU0,
+	IRQ_EB11MP_PMU_CPU1,
+	IRQ_EB11MP_PMU_CPU2,
+	IRQ_EB11MP_PMU_CPU3,
+#elif defined(CONFIG_ARCH_OMAP3)
+	INT_34XX_BENCH_MPU_EMUL,
+#elif defined(CONFIG_ARCH_IOP32X)
+	IRQ_IOP32X_CORE_PMU,
+#elif defined(CONFIG_ARCH_IOP33X)
+	IRQ_IOP33X_CORE_PMU,
+#elif defined(CONFIG_ARCH_PXA)
+	IRQ_PMU,
+#endif
+};
+
+static const struct pmu_irqs pmu_irqs = {
+	.irqs	    = irqs,
+	.num_irqs   = ARRAY_SIZE(irqs),
+};
+
+static volatile long pmu_lock;
+
+const struct pmu_irqs *
+reserve_pmu(void)
+{
+	return test_and_set_bit_lock(0, &pmu_lock) ? ERR_PTR(-EBUSY) :
+		&pmu_irqs;
+}
+EXPORT_SYMBOL_GPL(reserve_pmu);
+
+int
+release_pmu(const struct pmu_irqs *irqs)
+{
+	if (WARN_ON(irqs != &pmu_irqs))
+		return -EINVAL;
+	clear_bit_unlock(0, &pmu_lock);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(release_pmu);
+
+static int
+set_irq_affinity(int irq,
+		 unsigned int cpu)
+{
+#ifdef CONFIG_SMP
+	int err = irq_set_affinity(irq, cpumask_of(cpu));
+	if (err)
+		pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
+			   irq, cpu);
+	return err;
+#else
+	return 0;
+#endif
+}
+
+int
+init_pmu(void)
+{
+	int i, err = 0;
+
+	for (i = 0; i < pmu_irqs.num_irqs; ++i) {
+		err = set_irq_affinity(pmu_irqs.irqs[i], i);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(init_pmu);
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index a2ea3854cb3c..08f899fb76a6 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -499,10 +499,41 @@ static struct undef_hook thumb_break_hook = {
 	.fn		= break_trap,
 };
 
+static int thumb2_break_trap(struct pt_regs *regs, unsigned int instr)
+{
+	unsigned int instr2;
+	void __user *pc;
+
+	/* Check the second half of the instruction.  */
+	pc = (void __user *)(instruction_pointer(regs) + 2);
+
+	if (processor_mode(regs) == SVC_MODE) {
+		instr2 = *(u16 *) pc;
+	} else {
+		get_user(instr2, (u16 __user *)pc);
+	}
+
+	if (instr2 == 0xa000) {
+		ptrace_break(current, regs);
+		return 0;
+	} else {
+		return 1;
+	}
+}
+
+static struct undef_hook thumb2_break_hook = {
+	.instr_mask	= 0xffff,
+	.instr_val	= 0xf7f0,
+	.cpsr_mask	= PSR_T_BIT,
+	.cpsr_val	= PSR_T_BIT,
+	.fn		= thumb2_break_trap,
+};
+
 static int __init ptrace_break_init(void)
 {
 	register_undef_hook(&arm_break_hook);
 	register_undef_hook(&thumb_break_hook);
+	register_undef_hook(&thumb2_break_hook);
 	return 0;
 }
 
@@ -669,7 +700,7 @@ static int ptrace_getvfpregs(struct task_struct *tsk, void __user *data)
 	union vfp_state *vfp = &thread->vfpstate;
 	struct user_vfp __user *ufp = data;
 
-	vfp_sync_state(thread);
+	vfp_sync_hwstate(thread);
 
 	/* copy the floating point registers */
 	if (copy_to_user(&ufp->fpregs, &vfp->hard.fpregs,
@@ -692,7 +723,7 @@ static int ptrace_setvfpregs(struct task_struct *tsk, void __user *data)
 	union vfp_state *vfp = &thread->vfpstate;
 	struct user_vfp __user *ufp = data;
 
-	vfp_sync_state(thread);
+	vfp_sync_hwstate(thread);
 
 	/* copy the floating point registers */
 	if (copy_from_user(&vfp->hard.fpregs, &ufp->fpregs,
@@ -703,6 +734,8 @@ static int ptrace_setvfpregs(struct task_struct *tsk, void __user *data)
 	if (get_user(vfp->hard.fpscr, &ufp->fpscr))
 		return -EFAULT;
 
+	vfp_flush_hwstate(thread);
+
 	return 0;
 }
 #endif
@@ -712,26 +745,10 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 	int ret;
 
 	switch (request) {
-		/*
-		 * read word at location "addr" in the child process.
-		 */
-		case PTRACE_PEEKTEXT:
-		case PTRACE_PEEKDATA:
-			ret = generic_ptrace_peekdata(child, addr, data);
-			break;
-
 		case PTRACE_PEEKUSR:
 			ret = ptrace_read_user(child, addr, (unsigned long __user *)data);
 			break;
 
-		/*
-		 * write the word at location addr.
-		 */
-		case PTRACE_POKETEXT:
-		case PTRACE_POKEDATA:
-			ret = generic_ptrace_pokedata(child, addr, data);
-			break;
-
 		case PTRACE_POKEUSR:
 			ret = ptrace_write_user(child, addr, data);
 			break;
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 621acad8ea43..c91c77b54dea 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -24,6 +24,7 @@
 #include <linux/interrupt.h>
 #include <linux/smp.h>
 #include <linux/fs.h>
+#include <linux/proc_fs.h>
 
 #include <asm/unified.h>
 #include <asm/cpu.h>
@@ -118,7 +119,7 @@ EXPORT_SYMBOL(elf_platform);
 
 static const char *cpu_name;
 static const char *machine_name;
-static char __initdata command_line[COMMAND_LINE_SIZE];
+static char __initdata cmd_line[COMMAND_LINE_SIZE];
 
 static char default_command_line[COMMAND_LINE_SIZE] __initdata = CONFIG_CMDLINE;
 static union { char c[4]; unsigned long l; } endian_test __initdata = { { 'l', '?', '?', 'b' } };
@@ -418,10 +419,11 @@ static int __init arm_add_memory(unsigned long start, unsigned long size)
  * Pick out the memory size.  We look for mem=size@start,
  * where start and size are "size[KkMm]"
  */
-static void __init early_mem(char **p)
+static int __init early_mem(char *p)
 {
 	static int usermem __initdata = 0;
 	unsigned long size, start;
+	char *endp;
 
 	/*
 	 * If the user specifies memory size, we
@@ -434,52 +436,15 @@ static void __init early_mem(char **p)
 	}
 
 	start = PHYS_OFFSET;
-	size  = memparse(*p, p);
-	if (**p == '@')
-		start = memparse(*p + 1, p);
+	size  = memparse(p, &endp);
+	if (*endp == '@')
+		start = memparse(endp + 1, NULL);
 
 	arm_add_memory(start, size);
-}
-__early_param("mem=", early_mem);
 
-/*
- * Initial parsing of the command line.
- */
-static void __init parse_cmdline(char **cmdline_p, char *from)
-{
-	char c = ' ', *to = command_line;
-	int len = 0;
-
-	for (;;) {
-		if (c == ' ') {
-			extern struct early_params __early_begin, __early_end;
-			struct early_params *p;
-
-			for (p = &__early_begin; p < &__early_end; p++) {
-				int arglen = strlen(p->arg);
-
-				if (memcmp(from, p->arg, arglen) == 0) {
-					if (to != command_line)
-						to -= 1;
-					from += arglen;
-					p->fn(&from);
-
-					while (*from != ' ' && *from != '\0')
-						from++;
-					break;
-				}
-			}
-		}
-		c = *from++;
-		if (!c)
-			break;
-		if (COMMAND_LINE_SIZE <= ++len)
-			break;
-		*to++ = c;
-	}
-	*to = '\0';
-	*cmdline_p = command_line;
+	return 0;
 }
+early_param("mem", early_mem);
 
 static void __init
 setup_ramdisk(int doload, int prompt, int image_start, unsigned int rd_sz)
@@ -740,9 +705,15 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.end_data   = (unsigned long) _edata;
 	init_mm.brk	   = (unsigned long) _end;
 
-	memcpy(boot_command_line, from, COMMAND_LINE_SIZE);
-	boot_command_line[COMMAND_LINE_SIZE-1] = '\0';
-	parse_cmdline(cmdline_p, from);
+	/* parse_early_param needs a boot_command_line */
+	strlcpy(boot_command_line, from, COMMAND_LINE_SIZE);
+
+	/* populate cmd_line too for later use, preserving boot_command_line */
+	strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE);
+	*cmdline_p = cmd_line;
+
+	parse_early_param();
+
 	paging_init(mdesc);
 	request_standard_resources(&meminfo, mdesc);
 
@@ -783,9 +754,21 @@ static int __init topology_init(void)
 
 	return 0;
 }
-
 subsys_initcall(topology_init);
 
+#ifdef CONFIG_HAVE_PROC_CPU
+static int __init proc_cpu_init(void)
+{
+	struct proc_dir_entry *res;
+
+	res = proc_mkdir("cpu", NULL);
+	if (!res)
+		return -ENOMEM;
+	return 0;
+}
+fs_initcall(proc_cpu_init);
+#endif
+
 static const char *hwcap_str[] = {
 	"swp",
 	"half",
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index d38cdf2c8276..28753805d2d1 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -10,11 +10,6 @@
  *
  *  This file contains the ARM-specific time handling details:
  *  reading the RTC at bootup, etc...
- *
- *  1994-07-02  Alan Modra
- *              fixed set_rtc_mmss, fixed time.year for >= 2000, new mktime
- *  1998-12-20  Updated NTP code according to technical memorandum Jan '96
- *              "A Kernel Model for Precision Timekeeping" by Dave Mills
  */
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -77,11 +72,6 @@ unsigned long profile_pc(struct pt_regs *regs)
 EXPORT_SYMBOL(profile_pc);
 #endif
 
-/*
- * hook for setting the RTC's idea of the current time.
- */
-int (*set_rtc)(void);
-
 #ifndef CONFIG_GENERIC_TIME
 static unsigned long dummy_gettimeoffset(void)
 {
@@ -89,140 +79,6 @@ static unsigned long dummy_gettimeoffset(void)
 }
 #endif
 
-static unsigned long next_rtc_update;
-
-/*
- * If we have an externally synchronized linux clock, then update
- * CMOS clock accordingly every ~11 minutes.  set_rtc() has to be
- * called as close as possible to 500 ms before the new second
- * starts.
- */
-static inline void do_set_rtc(void)
-{
-	if (!ntp_synced() || set_rtc == NULL)
-		return;
-
-	if (next_rtc_update &&
-	    time_before((unsigned long)xtime.tv_sec, next_rtc_update))
-		return;
-
-	if (xtime.tv_nsec < 500000000 - ((unsigned) tick_nsec >> 1) &&
-	    xtime.tv_nsec >= 500000000 + ((unsigned) tick_nsec >> 1))
-		return;
-
-	if (set_rtc())
-		/*
-		 * rtc update failed.  Try again in 60s
-		 */
-		next_rtc_update = xtime.tv_sec + 60;
-	else
-		next_rtc_update = xtime.tv_sec + 660;
-}
-
-#ifdef CONFIG_LEDS
-
-static void dummy_leds_event(led_event_t evt)
-{
-}
-
-void (*leds_event)(led_event_t) = dummy_leds_event;
-
-struct leds_evt_name {
-	const char	name[8];
-	int		on;
-	int		off;
-};
-
-static const struct leds_evt_name evt_names[] = {
-	{ "amber", led_amber_on, led_amber_off },
-	{ "blue",  led_blue_on,  led_blue_off  },
-	{ "green", led_green_on, led_green_off },
-	{ "red",   led_red_on,   led_red_off   },
-};
-
-static ssize_t leds_store(struct sys_device *dev,
-			struct sysdev_attribute *attr,
-			const char *buf, size_t size)
-{
-	int ret = -EINVAL, len = strcspn(buf, " ");
-
-	if (len > 0 && buf[len] == '\0')
-		len--;
-
-	if (strncmp(buf, "claim", len) == 0) {
-		leds_event(led_claim);
-		ret = size;
-	} else if (strncmp(buf, "release", len) == 0) {
-		leds_event(led_release);
-		ret = size;
-	} else {
-		int i;
-
-		for (i = 0; i < ARRAY_SIZE(evt_names); i++) {
-			if (strlen(evt_names[i].name) != len ||
-			    strncmp(buf, evt_names[i].name, len) != 0)
-				continue;
-			if (strncmp(buf+len, " on", 3) == 0) {
-				leds_event(evt_names[i].on);
-				ret = size;
-			} else if (strncmp(buf+len, " off", 4) == 0) {
-				leds_event(evt_names[i].off);
-				ret = size;
-			}
-			break;
-		}
-	}
-	return ret;
-}
-
-static SYSDEV_ATTR(event, 0200, NULL, leds_store);
-
-static int leds_suspend(struct sys_device *dev, pm_message_t state)
-{
-	leds_event(led_stop);
-	return 0;
-}
-
-static int leds_resume(struct sys_device *dev)
-{
-	leds_event(led_start);
-	return 0;
-}
-
-static int leds_shutdown(struct sys_device *dev)
-{
-	leds_event(led_halted);
-	return 0;
-}
-
-static struct sysdev_class leds_sysclass = {
-	.name		= "leds",
-	.shutdown	= leds_shutdown,
-	.suspend	= leds_suspend,
-	.resume		= leds_resume,
-};
-
-static struct sys_device leds_device = {
-	.id		= 0,
-	.cls		= &leds_sysclass,
-};
-
-static int __init leds_init(void)
-{
-	int ret;
-	ret = sysdev_class_register(&leds_sysclass);
-	if (ret == 0)
-		ret = sysdev_register(&leds_device);
-	if (ret == 0)
-		ret = sysdev_create_file(&leds_device, &attr_event);
-	return ret;
-}
-
-device_initcall(leds_init);
-
-EXPORT_SYMBOL(leds_event);
-#endif
-
 #ifdef CONFIG_LEDS_TIMER
 static inline void do_leds(void)
 {
@@ -295,39 +151,6 @@ int do_settimeofday(struct timespec *tv)
 EXPORT_SYMBOL(do_settimeofday);
 #endif /* !CONFIG_GENERIC_TIME */
 
-/**
- * save_time_delta - Save the offset between system time and RTC time
- * @delta: pointer to timespec to store delta
- * @rtc: pointer to timespec for current RTC time
- *
- * Return a delta between the system time and the RTC time, such
- * that system time can be restored later with restore_time_delta()
- */
-void save_time_delta(struct timespec *delta, struct timespec *rtc)
-{
-	set_normalized_timespec(delta,
-				xtime.tv_sec - rtc->tv_sec,
-				xtime.tv_nsec - rtc->tv_nsec);
-}
-EXPORT_SYMBOL(save_time_delta);
-
-/**
- * restore_time_delta - Restore the current system time
- * @delta: delta returned by save_time_delta()
- * @rtc: pointer to timespec for current RTC time
- */
-void restore_time_delta(struct timespec *delta, struct timespec *rtc)
-{
-	struct timespec ts;
-
-	set_normalized_timespec(&ts,
-				delta->tv_sec + rtc->tv_sec,
-				delta->tv_nsec + rtc->tv_nsec);
-
-	do_settimeofday(&ts);
-}
-EXPORT_SYMBOL(restore_time_delta);
-
 #ifndef CONFIG_GENERIC_CLOCKEVENTS
 /*
  * Kernel system timer support.
@@ -336,7 +159,6 @@ void timer_tick(void)
 {
 	profile_tick(CPU_PROFILING);
 	do_leds();
-	do_set_rtc();
 	write_seqlock(&xtime_lock);
 	do_timer(1);
 	write_sequnlock(&xtime_lock);
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 3f361a783f43..1621e5327b2a 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -12,15 +12,17 @@
  *  'linux/arch/arm/lib/traps.S'.  Mostly a debugging aid, but will probably
  *  kill the offending process.
  */
-#include <linux/module.h>
 #include <linux/signal.h>
-#include <linux/spinlock.h>
 #include <linux/personality.h>
 #include <linux/kallsyms.h>
-#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/uaccess.h>
 #include <linux/hardirq.h>
+#include <linux/kdebug.h>
+#include <linux/module.h>
+#include <linux/kexec.h>
+#include <linux/delay.h>
 #include <linux/init.h>
-#include <linux/uaccess.h>
 
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
@@ -224,14 +226,21 @@ void show_stack(struct task_struct *tsk, unsigned long *sp)
 #define S_SMP ""
 #endif
 
-static void __die(const char *str, int err, struct thread_info *thread, struct pt_regs *regs)
+static int __die(const char *str, int err, struct thread_info *thread, struct pt_regs *regs)
 {
 	struct task_struct *tsk = thread->task;
 	static int die_counter;
+	int ret;
 
 	printk(KERN_EMERG "Internal error: %s: %x [#%d]" S_PREEMPT S_SMP "\n",
 	       str, err, ++die_counter);
 	sysfs_printk_last_file();
+
+	/* trap and error numbers are mostly meaningless on ARM */
+	ret = notify_die(DIE_OOPS, str, regs, err, tsk->thread.trap_no, SIGSEGV);
+	if (ret == NOTIFY_STOP)
+		return ret;
+
 	print_modules();
 	__show_regs(regs);
 	printk(KERN_EMERG "Process %.*s (pid: %d, stack limit = 0x%p)\n",
@@ -243,6 +252,8 @@ static void __die(const char *str, int err, struct thread_info *thread, struct p
 		dump_backtrace(regs, tsk);
 		dump_instr(KERN_EMERG, regs);
 	}
+
+	return ret;
 }
 
 DEFINE_SPINLOCK(die_lock);
@@ -250,16 +261,21 @@ DEFINE_SPINLOCK(die_lock);
 /*
  * This function is protected against re-entrancy.
  */
-NORET_TYPE void die(const char *str, struct pt_regs *regs, int err)
+void die(const char *str, struct pt_regs *regs, int err)
 {
 	struct thread_info *thread = current_thread_info();
+	int ret;
 
 	oops_enter();
 
 	spin_lock_irq(&die_lock);
 	console_verbose();
 	bust_spinlocks(1);
-	__die(str, err, thread, regs);
+	ret = __die(str, err, thread, regs);
+
+	if (regs && kexec_should_crash(thread->task))
+		crash_kexec(regs);
+
 	bust_spinlocks(0);
 	add_taint(TAINT_DIE);
 	spin_unlock_irq(&die_lock);
@@ -267,11 +283,10 @@ NORET_TYPE void die(const char *str, struct pt_regs *regs, int err)
 
 	if (in_interrupt())
 		panic("Fatal exception in interrupt");
-
 	if (panic_on_oops)
 		panic("Fatal exception");
-
-	do_exit(SIGSEGV);
+	if (ret != NOTIFY_STOP)
+		do_exit(SIGSEGV);
 }
 
 void arm_notify_die(const char *str, struct pt_regs *regs,
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 4957e13ef55b..b16c07914b55 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -43,10 +43,6 @@ SECTIONS
 
 		INIT_SETUP(16)
 
-		__early_begin = .;
-			*(.early_param.init)
-		__early_end = .;
-
 		INIT_CALLS
 		CON_INITCALL
 		SECURITY_INITCALL