Merge branch 'devel' of master.kernel.org:/home/rmk/linux-2.6-arm

* 'devel' of master.kernel.org:/home/rmk/linux-2.6-arm: (224 commits)
  ARM: remove 'select GENERIC_TIME'
  ARM: 6136/1: ARCH_REQUIRE_GPIOLIB selects GENERIC_GPIO
  ARM: 6074/1: oprofile: convert from sysdev to platform device
  ARM: 6073/1: oprofile: remove old files and update KConfig
  ARM: 6072/1: oprofile: use perf-events framework as backend
  ARM: 6071/1: perf-events: allow modules to query the number of hardware counters
  ARM: 6070/1: perf-events: add support for xscale PMUs
  ARM: 6069/1: perf-events: use numeric ID to identify PMU
  ARM: 6064/1: pmu: register IRQs at runtime
  ARM: Optionally allow ARMv6 to use 'normal, bufferable' memory for DMA
  ARM: 6134/1: Handle instruction cache maintenance fault properly
  ARM: nwfpe: allow debugging output to be configured at runtime
  ARM: rename mach_cpu_disable() to platform_cpu_disable()
  ARM: 6132/1: PL330: Add common core driver
  ARM: 6094/1: Extend cache-l2x0 to support the 16-way PL310
  ARM: Move memory mapping into mmu.c
  ARM: Ensure meminfo is sorted prior to sanity_check_meminfo
  ARM: Remove useless linux/bootmem.h includes
  ARM: convert /proc/cpu/aligment to seq_file
  arm: use asm-generic/scatterlist.h
  ...

6 files changed, 1021 insertions, 145 deletions

diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index bd397e0b663e..c6273a3bfc25 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -527,6 +527,9 @@ static void __init pcibios_init_hw(struct hw_pci *hw)
 		if (!sys)
 			panic("PCI: unable to allocate sys data!");
 
+#ifdef CONFIG_PCI_DOMAINS
+		sys->domain  = hw->domain;
+#endif
 		sys->hw      = hw;
 		sys->busnr   = busnr;
 		sys->swizzle = hw->swizzle;
diff --git a/arch/arm/kernel/dma.c b/arch/arm/kernel/dma.c
index 7d5b9fb01e71..2c4a185f92cd 100644
--- a/arch/arm/kernel/dma.c
+++ b/arch/arm/kernel/dma.c
@@ -16,6 +16,8 @@
 #include <linux/spinlock.h>
 #include <linux/errno.h>
 #include <linux/scatterlist.h>
+#include <linux/seq_file.h>
+#include <linux/proc_fs.h>
 
 #include <asm/dma.h>
 
@@ -264,3 +266,37 @@ int get_dma_residue(unsigned int chan)
 	return ret;
 }
 EXPORT_SYMBOL(get_dma_residue);
+
+#ifdef CONFIG_PROC_FS
+static int proc_dma_show(struct seq_file *m, void *v)
+{
+	int i;
+
+	for (i = 0 ; i < MAX_DMA_CHANNELS ; i++) {
+		dma_t *dma = dma_channel(i);
+		if (dma && dma->lock)
+			seq_printf(m, "%2d: %s\n", i, dma->device_id);
+	}
+	return 0;
+}
+
+static int proc_dma_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, proc_dma_show, NULL);
+}
+
+static const struct file_operations proc_dma_operations = {
+	.open		= proc_dma_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init proc_dma_init(void)
+{
+	proc_create("dma", 0, NULL, &proc_dma_operations);
+	return 0;
+}
+
+__initcall(proc_dma_init);
+#endif
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 9e70f2053f9a..c45768614c8a 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -16,7 +16,9 @@
 
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/perf_event.h>
+#include <linux/platform_device.h>
 #include <linux/spinlock.h>
 #include <linux/uaccess.h>
 
@@ -26,7 +28,7 @@
 #include <asm/pmu.h>
 #include <asm/stacktrace.h>
 
-static const struct pmu_irqs *pmu_irqs;
+static struct platform_device *pmu_device;
 
 /*
  * Hardware lock to serialize accesses to PMU registers. Needed for the
@@ -67,8 +69,18 @@ struct cpu_hw_events {
 };
 DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
 
+/* PMU names. */
+static const char *arm_pmu_names[] = {
+	[ARM_PERF_PMU_ID_XSCALE1] = "xscale1",
+	[ARM_PERF_PMU_ID_XSCALE2] = "xscale2",
+	[ARM_PERF_PMU_ID_V6]	  = "v6",
+	[ARM_PERF_PMU_ID_V6MP]	  = "v6mpcore",
+	[ARM_PERF_PMU_ID_CA8]	  = "ARMv7 Cortex-A8",
+	[ARM_PERF_PMU_ID_CA9]	  = "ARMv7 Cortex-A9",
+};
+
 struct arm_pmu {
-	char		*name;
+	enum arm_perf_pmu_ids id;
 	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);
@@ -87,6 +99,30 @@ struct arm_pmu {
 /* Set at runtime when we know what CPU type we are. */
 static const struct arm_pmu *armpmu;
 
+enum arm_perf_pmu_ids
+armpmu_get_pmu_id(void)
+{
+	int id = -ENODEV;
+
+	if (armpmu != NULL)
+		id = armpmu->id;
+
+	return id;
+}
+EXPORT_SYMBOL_GPL(armpmu_get_pmu_id);
+
+int
+armpmu_get_max_events(void)
+{
+	int max_events = 0;
+
+	if (armpmu != NULL)
+		max_events = armpmu->num_events;
+
+	return max_events;
+}
+EXPORT_SYMBOL_GPL(armpmu_get_max_events);
+
 #define HW_OP_UNSUPPORTED		0xFFFF
 
 #define C(_x) \
@@ -314,38 +350,44 @@ validate_group(struct perf_event *event)
 static int
 armpmu_reserve_hardware(void)
 {
-	int i;
-	int err;
+	int i, err = -ENODEV, irq;
 
-	pmu_irqs = reserve_pmu();
-	if (IS_ERR(pmu_irqs)) {
+	pmu_device = reserve_pmu(ARM_PMU_DEVICE_CPU);
+	if (IS_ERR(pmu_device)) {
 		pr_warning("unable to reserve pmu\n");
-		return PTR_ERR(pmu_irqs);
+		return PTR_ERR(pmu_device);
 	}
 
-	init_pmu();
+	init_pmu(ARM_PMU_DEVICE_CPU);
 
-	if (pmu_irqs->num_irqs < 1) {
+	if (pmu_device->num_resources < 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,
+	for (i = 0; i < pmu_device->num_resources; ++i) {
+		irq = platform_get_irq(pmu_device, i);
+		if (irq < 0)
+			continue;
+
+		err = request_irq(irq, armpmu->handle_irq,
 				  IRQF_DISABLED | IRQF_NOBALANCING,
 				  "armpmu", NULL);
 		if (err) {
-			pr_warning("unable to request IRQ%d for ARM "
-				   "perf counters\n", pmu_irqs->irqs[i]);
+			pr_warning("unable to request IRQ%d for ARM perf "
+				"counters\n", irq);
 			break;
 		}
 	}
 
 	if (err) {
-		for (i = i - 1; i >= 0; --i)
-			free_irq(pmu_irqs->irqs[i], NULL);
-		release_pmu(pmu_irqs);
-		pmu_irqs = NULL;
+		for (i = i - 1; i >= 0; --i) {
+			irq = platform_get_irq(pmu_device, i);
+			if (irq >= 0)
+				free_irq(irq, NULL);
+		}
+		release_pmu(pmu_device);
+		pmu_device = NULL;
 	}
 
 	return err;
@@ -354,14 +396,17 @@ armpmu_reserve_hardware(void)
 static void
 armpmu_release_hardware(void)
 {
-	int i;
+	int i, irq;
 
-	for (i = pmu_irqs->num_irqs - 1; i >= 0; --i)
-		free_irq(pmu_irqs->irqs[i], NULL);
+	for (i = pmu_device->num_resources - 1; i >= 0; --i) {
+		irq = platform_get_irq(pmu_device, i);
+		if (irq >= 0)
+			free_irq(irq, NULL);
+	}
 	armpmu->stop();
 
-	release_pmu(pmu_irqs);
-	pmu_irqs = NULL;
+	release_pmu(pmu_device);
+	pmu_device = NULL;
 }
 
 static atomic_t active_events = ATOMIC_INIT(0);
@@ -1144,7 +1189,7 @@ armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
 }
 
 static const struct arm_pmu armv6pmu = {
-	.name			= "v6",
+	.id			= ARM_PERF_PMU_ID_V6,
 	.handle_irq		= armv6pmu_handle_irq,
 	.enable			= armv6pmu_enable_event,
 	.disable		= armv6pmu_disable_event,
@@ -1167,7 +1212,7 @@ static const struct arm_pmu armv6pmu = {
  * reset the period and enable the interrupt reporting.
  */
 static const struct arm_pmu armv6mpcore_pmu = {
-	.name			= "v6mpcore",
+	.id			= ARM_PERF_PMU_ID_V6MP,
 	.handle_irq		= armv6pmu_handle_irq,
 	.enable			= armv6pmu_enable_event,
 	.disable		= armv6mpcore_pmu_disable_event,
@@ -1197,10 +1242,6 @@ static const struct arm_pmu armv6mpcore_pmu = {
  *  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,
@@ -2079,6 +2120,803 @@ static u32 __init armv7_reset_read_pmnc(void)
 	return nb_cnt + 1;
 }
 
+/*
+ * ARMv5 [xscale] Performance counter handling code.
+ *
+ * Based on xscale OProfile code.
+ *
+ * There are two variants of the xscale PMU that we support:
+ * 	- xscale1pmu: 2 event counters and a cycle counter
+ * 	- xscale2pmu: 4 event counters and a cycle counter
+ * The two variants share event definitions, but have different
+ * PMU structures.
+ */
+
+enum xscale_perf_types {
+	XSCALE_PERFCTR_ICACHE_MISS		= 0x00,
+	XSCALE_PERFCTR_ICACHE_NO_DELIVER	= 0x01,
+	XSCALE_PERFCTR_DATA_STALL		= 0x02,
+	XSCALE_PERFCTR_ITLB_MISS		= 0x03,
+	XSCALE_PERFCTR_DTLB_MISS		= 0x04,
+	XSCALE_PERFCTR_BRANCH			= 0x05,
+	XSCALE_PERFCTR_BRANCH_MISS		= 0x06,
+	XSCALE_PERFCTR_INSTRUCTION		= 0x07,
+	XSCALE_PERFCTR_DCACHE_FULL_STALL	= 0x08,
+	XSCALE_PERFCTR_DCACHE_FULL_STALL_CONTIG	= 0x09,
+	XSCALE_PERFCTR_DCACHE_ACCESS		= 0x0A,
+	XSCALE_PERFCTR_DCACHE_MISS		= 0x0B,
+	XSCALE_PERFCTR_DCACHE_WRITE_BACK	= 0x0C,
+	XSCALE_PERFCTR_PC_CHANGED		= 0x0D,
+	XSCALE_PERFCTR_BCU_REQUEST		= 0x10,
+	XSCALE_PERFCTR_BCU_FULL			= 0x11,
+	XSCALE_PERFCTR_BCU_DRAIN		= 0x12,
+	XSCALE_PERFCTR_BCU_ECC_NO_ELOG		= 0x14,
+	XSCALE_PERFCTR_BCU_1_BIT_ERR		= 0x15,
+	XSCALE_PERFCTR_RMW			= 0x16,
+	/* XSCALE_PERFCTR_CCNT is not hardware defined */
+	XSCALE_PERFCTR_CCNT			= 0xFE,
+	XSCALE_PERFCTR_UNUSED			= 0xFF,
+};
+
+enum xscale_counters {
+	XSCALE_CYCLE_COUNTER	= 1,
+	XSCALE_COUNTER0,
+	XSCALE_COUNTER1,
+	XSCALE_COUNTER2,
+	XSCALE_COUNTER3,
+};
+
+static const unsigned xscale_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]	    = XSCALE_PERFCTR_CCNT,
+	[PERF_COUNT_HW_INSTRUCTIONS]	    = XSCALE_PERFCTR_INSTRUCTION,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = XSCALE_PERFCTR_BRANCH,
+	[PERF_COUNT_HW_BRANCH_MISSES]	    = XSCALE_PERFCTR_BRANCH_MISS,
+	[PERF_COUNT_HW_BUS_CYCLES]	    = HW_OP_UNSUPPORTED,
+};
+
+static const unsigned xscale_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)]	= XSCALE_PERFCTR_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= XSCALE_PERFCTR_DCACHE_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= XSCALE_PERFCTR_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= XSCALE_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)]	= XSCALE_PERFCTR_ICACHE_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= XSCALE_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)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= XSCALE_PERFCTR_DTLB_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= XSCALE_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)]	= XSCALE_PERFCTR_ITLB_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= XSCALE_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,
+		},
+	},
+};
+
+#define	XSCALE_PMU_ENABLE	0x001
+#define XSCALE_PMN_RESET	0x002
+#define	XSCALE_CCNT_RESET	0x004
+#define	XSCALE_PMU_RESET	(CCNT_RESET | PMN_RESET)
+#define XSCALE_PMU_CNT64	0x008
+
+static inline int
+xscalepmu_event_map(int config)
+{
+	int mapping = xscale_perf_map[config];
+	if (HW_OP_UNSUPPORTED == mapping)
+		mapping = -EOPNOTSUPP;
+	return mapping;
+}
+
+static u64
+xscalepmu_raw_event(u64 config)
+{
+	return config & 0xff;
+}
+
+#define XSCALE1_OVERFLOWED_MASK	0x700
+#define XSCALE1_CCOUNT_OVERFLOW	0x400
+#define XSCALE1_COUNT0_OVERFLOW	0x100
+#define XSCALE1_COUNT1_OVERFLOW	0x200
+#define XSCALE1_CCOUNT_INT_EN	0x040
+#define XSCALE1_COUNT0_INT_EN	0x010
+#define XSCALE1_COUNT1_INT_EN	0x020
+#define XSCALE1_COUNT0_EVT_SHFT	12
+#define XSCALE1_COUNT0_EVT_MASK	(0xff << XSCALE1_COUNT0_EVT_SHFT)
+#define XSCALE1_COUNT1_EVT_SHFT	20
+#define XSCALE1_COUNT1_EVT_MASK	(0xff << XSCALE1_COUNT1_EVT_SHFT)
+
+static inline u32
+xscale1pmu_read_pmnc(void)
+{
+	u32 val;
+	asm volatile("mrc p14, 0, %0, c0, c0, 0" : "=r" (val));
+	return val;
+}
+
+static inline void
+xscale1pmu_write_pmnc(u32 val)
+{
+	/* upper 4bits and 7, 11 are write-as-0 */
+	val &= 0xffff77f;
+	asm volatile("mcr p14, 0, %0, c0, c0, 0" : : "r" (val));
+}
+
+static inline int
+xscale1_pmnc_counter_has_overflowed(unsigned long pmnc,
+					enum xscale_counters counter)
+{
+	int ret = 0;
+
+	switch (counter) {
+	case XSCALE_CYCLE_COUNTER:
+		ret = pmnc & XSCALE1_CCOUNT_OVERFLOW;
+		break;
+	case XSCALE_COUNTER0:
+		ret = pmnc & XSCALE1_COUNT0_OVERFLOW;
+		break;
+	case XSCALE_COUNTER1:
+		ret = pmnc & XSCALE1_COUNT1_OVERFLOW;
+		break;
+	default:
+		WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+	}
+
+	return ret;
+}
+
+static irqreturn_t
+xscale1pmu_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;
+
+	/*
+	 * NOTE: there's an A stepping erratum that states if an overflow
+	 *       bit already exists and another occurs, the previous
+	 *       Overflow bit gets cleared. There's no workaround.
+	 *	 Fixed in B stepping or later.
+	 */
+	pmnc = xscale1pmu_read_pmnc();
+
+	/*
+	 * Write the value back to clear the overflow flags. Overflow
+	 * flags remain in pmnc for use below. We also disable the PMU
+	 * while we process the interrupt.
+	 */
+	xscale1pmu_write_pmnc(pmnc & ~XSCALE_PMU_ENABLE);
+
+	if (!(pmnc & XSCALE1_OVERFLOWED_MASK))
+		return IRQ_NONE;
+
+	regs = get_irq_regs();
+
+	perf_sample_data_init(&data, 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;
+
+		if (!xscale1_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);
+	}
+
+	perf_event_do_pending();
+
+	/*
+	 * Re-enable the PMU.
+	 */
+	pmnc = xscale1pmu_read_pmnc() | XSCALE_PMU_ENABLE;
+	xscale1pmu_write_pmnc(pmnc);
+
+	return IRQ_HANDLED;
+}
+
+static void
+xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx)
+{
+	unsigned long val, mask, evt, flags;
+
+	switch (idx) {
+	case XSCALE_CYCLE_COUNTER:
+		mask = 0;
+		evt = XSCALE1_CCOUNT_INT_EN;
+		break;
+	case XSCALE_COUNTER0:
+		mask = XSCALE1_COUNT0_EVT_MASK;
+		evt = (hwc->config_base << XSCALE1_COUNT0_EVT_SHFT) |
+			XSCALE1_COUNT0_INT_EN;
+		break;
+	case XSCALE_COUNTER1:
+		mask = XSCALE1_COUNT1_EVT_MASK;
+		evt = (hwc->config_base << XSCALE1_COUNT1_EVT_SHFT) |
+			XSCALE1_COUNT1_INT_EN;
+		break;
+	default:
+		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+		return;
+	}
+
+	spin_lock_irqsave(&pmu_lock, flags);
+	val = xscale1pmu_read_pmnc();
+	val &= ~mask;
+	val |= evt;
+	xscale1pmu_write_pmnc(val);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx)
+{
+	unsigned long val, mask, evt, flags;
+
+	switch (idx) {
+	case XSCALE_CYCLE_COUNTER:
+		mask = XSCALE1_CCOUNT_INT_EN;
+		evt = 0;
+		break;
+	case XSCALE_COUNTER0:
+		mask = XSCALE1_COUNT0_INT_EN | XSCALE1_COUNT0_EVT_MASK;
+		evt = XSCALE_PERFCTR_UNUSED << XSCALE1_COUNT0_EVT_SHFT;
+		break;
+	case XSCALE_COUNTER1:
+		mask = XSCALE1_COUNT1_INT_EN | XSCALE1_COUNT1_EVT_MASK;
+		evt = XSCALE_PERFCTR_UNUSED << XSCALE1_COUNT1_EVT_SHFT;
+		break;
+	default:
+		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+		return;
+	}
+
+	spin_lock_irqsave(&pmu_lock, flags);
+	val = xscale1pmu_read_pmnc();
+	val &= ~mask;
+	val |= evt;
+	xscale1pmu_write_pmnc(val);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static int
+xscale1pmu_get_event_idx(struct cpu_hw_events *cpuc,
+			struct hw_perf_event *event)
+{
+	if (XSCALE_PERFCTR_CCNT == event->config_base) {
+		if (test_and_set_bit(XSCALE_CYCLE_COUNTER, cpuc->used_mask))
+			return -EAGAIN;
+
+		return XSCALE_CYCLE_COUNTER;
+	} else {
+		if (!test_and_set_bit(XSCALE_COUNTER1, cpuc->used_mask)) {
+			return XSCALE_COUNTER1;
+		}
+
+		if (!test_and_set_bit(XSCALE_COUNTER0, cpuc->used_mask)) {
+			return XSCALE_COUNTER0;
+		}
+
+		return -EAGAIN;
+	}
+}
+
+static void
+xscale1pmu_start(void)
+{
+	unsigned long flags, val;
+
+	spin_lock_irqsave(&pmu_lock, flags);
+	val = xscale1pmu_read_pmnc();
+	val |= XSCALE_PMU_ENABLE;
+	xscale1pmu_write_pmnc(val);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+xscale1pmu_stop(void)
+{
+	unsigned long flags, val;
+
+	spin_lock_irqsave(&pmu_lock, flags);
+	val = xscale1pmu_read_pmnc();
+	val &= ~XSCALE_PMU_ENABLE;
+	xscale1pmu_write_pmnc(val);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static inline u32
+xscale1pmu_read_counter(int counter)
+{
+	u32 val = 0;
+
+	switch (counter) {
+	case XSCALE_CYCLE_COUNTER:
+		asm volatile("mrc p14, 0, %0, c1, c0, 0" : "=r" (val));
+		break;
+	case XSCALE_COUNTER0:
+		asm volatile("mrc p14, 0, %0, c2, c0, 0" : "=r" (val));
+		break;
+	case XSCALE_COUNTER1:
+		asm volatile("mrc p14, 0, %0, c3, c0, 0" : "=r" (val));
+		break;
+	}
+
+	return val;
+}
+
+static inline void
+xscale1pmu_write_counter(int counter, u32 val)
+{
+	switch (counter) {
+	case XSCALE_CYCLE_COUNTER:
+		asm volatile("mcr p14, 0, %0, c1, c0, 0" : : "r" (val));
+		break;
+	case XSCALE_COUNTER0:
+		asm volatile("mcr p14, 0, %0, c2, c0, 0" : : "r" (val));
+		break;
+	case XSCALE_COUNTER1:
+		asm volatile("mcr p14, 0, %0, c3, c0, 0" : : "r" (val));
+		break;
+	}
+}
+
+static const struct arm_pmu xscale1pmu = {
+	.id		= ARM_PERF_PMU_ID_XSCALE1,
+	.handle_irq	= xscale1pmu_handle_irq,
+	.enable		= xscale1pmu_enable_event,
+	.disable	= xscale1pmu_disable_event,
+	.event_map	= xscalepmu_event_map,
+	.raw_event	= xscalepmu_raw_event,
+	.read_counter	= xscale1pmu_read_counter,
+	.write_counter	= xscale1pmu_write_counter,
+	.get_event_idx	= xscale1pmu_get_event_idx,
+	.start		= xscale1pmu_start,
+	.stop		= xscale1pmu_stop,
+	.num_events	= 3,
+	.max_period	= (1LLU << 32) - 1,
+};
+
+#define XSCALE2_OVERFLOWED_MASK	0x01f
+#define XSCALE2_CCOUNT_OVERFLOW	0x001
+#define XSCALE2_COUNT0_OVERFLOW	0x002
+#define XSCALE2_COUNT1_OVERFLOW	0x004
+#define XSCALE2_COUNT2_OVERFLOW	0x008
+#define XSCALE2_COUNT3_OVERFLOW	0x010
+#define XSCALE2_CCOUNT_INT_EN	0x001
+#define XSCALE2_COUNT0_INT_EN	0x002
+#define XSCALE2_COUNT1_INT_EN	0x004
+#define XSCALE2_COUNT2_INT_EN	0x008
+#define XSCALE2_COUNT3_INT_EN	0x010
+#define XSCALE2_COUNT0_EVT_SHFT	0
+#define XSCALE2_COUNT0_EVT_MASK	(0xff << XSCALE2_COUNT0_EVT_SHFT)
+#define XSCALE2_COUNT1_EVT_SHFT	8
+#define XSCALE2_COUNT1_EVT_MASK	(0xff << XSCALE2_COUNT1_EVT_SHFT)
+#define XSCALE2_COUNT2_EVT_SHFT	16
+#define XSCALE2_COUNT2_EVT_MASK	(0xff << XSCALE2_COUNT2_EVT_SHFT)
+#define XSCALE2_COUNT3_EVT_SHFT	24
+#define XSCALE2_COUNT3_EVT_MASK	(0xff << XSCALE2_COUNT3_EVT_SHFT)
+
+static inline u32
+xscale2pmu_read_pmnc(void)
+{
+	u32 val;
+	asm volatile("mrc p14, 0, %0, c0, c1, 0" : "=r" (val));
+	/* bits 1-2 and 4-23 are read-unpredictable */
+	return val & 0xff000009;
+}
+
+static inline void
+xscale2pmu_write_pmnc(u32 val)
+{
+	/* bits 4-23 are write-as-0, 24-31 are write ignored */
+	val &= 0xf;
+	asm volatile("mcr p14, 0, %0, c0, c1, 0" : : "r" (val));
+}
+
+static inline u32
+xscale2pmu_read_overflow_flags(void)
+{
+	u32 val;
+	asm volatile("mrc p14, 0, %0, c5, c1, 0" : "=r" (val));
+	return val;
+}
+
+static inline void
+xscale2pmu_write_overflow_flags(u32 val)
+{
+	asm volatile("mcr p14, 0, %0, c5, c1, 0" : : "r" (val));
+}
+
+static inline u32
+xscale2pmu_read_event_select(void)
+{
+	u32 val;
+	asm volatile("mrc p14, 0, %0, c8, c1, 0" : "=r" (val));
+	return val;
+}
+
+static inline void
+xscale2pmu_write_event_select(u32 val)
+{
+	asm volatile("mcr p14, 0, %0, c8, c1, 0" : : "r"(val));
+}
+
+static inline u32
+xscale2pmu_read_int_enable(void)
+{
+	u32 val;
+	asm volatile("mrc p14, 0, %0, c4, c1, 0" : "=r" (val));
+	return val;
+}
+
+static void
+xscale2pmu_write_int_enable(u32 val)
+{
+	asm volatile("mcr p14, 0, %0, c4, c1, 0" : : "r" (val));
+}
+
+static inline int
+xscale2_pmnc_counter_has_overflowed(unsigned long of_flags,
+					enum xscale_counters counter)
+{
+	int ret = 0;
+
+	switch (counter) {
+	case XSCALE_CYCLE_COUNTER:
+		ret = of_flags & XSCALE2_CCOUNT_OVERFLOW;
+		break;
+	case XSCALE_COUNTER0:
+		ret = of_flags & XSCALE2_COUNT0_OVERFLOW;
+		break;
+	case XSCALE_COUNTER1:
+		ret = of_flags & XSCALE2_COUNT1_OVERFLOW;
+		break;
+	case XSCALE_COUNTER2:
+		ret = of_flags & XSCALE2_COUNT2_OVERFLOW;
+		break;
+	case XSCALE_COUNTER3:
+		ret = of_flags & XSCALE2_COUNT3_OVERFLOW;
+		break;
+	default:
+		WARN_ONCE(1, "invalid counter number (%d)\n", counter);
+	}
+
+	return ret;
+}
+
+static irqreturn_t
+xscale2pmu_handle_irq(int irq_num, void *dev)
+{
+	unsigned long pmnc, of_flags;
+	struct perf_sample_data data;
+	struct cpu_hw_events *cpuc;
+	struct pt_regs *regs;
+	int idx;
+
+	/* Disable the PMU. */
+	pmnc = xscale2pmu_read_pmnc();
+	xscale2pmu_write_pmnc(pmnc & ~XSCALE_PMU_ENABLE);
+
+	/* Check the overflow flag register. */
+	of_flags = xscale2pmu_read_overflow_flags();
+	if (!(of_flags & XSCALE2_OVERFLOWED_MASK))
+		return IRQ_NONE;
+
+	/* Clear the overflow bits. */
+	xscale2pmu_write_overflow_flags(of_flags);
+
+	regs = get_irq_regs();
+
+	perf_sample_data_init(&data, 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;
+
+		if (!xscale2_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);
+	}
+
+	perf_event_do_pending();
+
+	/*
+	 * Re-enable the PMU.
+	 */
+	pmnc = xscale2pmu_read_pmnc() | XSCALE_PMU_ENABLE;
+	xscale2pmu_write_pmnc(pmnc);
+
+	return IRQ_HANDLED;
+}
+
+static void
+xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
+{
+	unsigned long flags, ien, evtsel;
+
+	ien = xscale2pmu_read_int_enable();
+	evtsel = xscale2pmu_read_event_select();
+
+	switch (idx) {
+	case XSCALE_CYCLE_COUNTER:
+		ien |= XSCALE2_CCOUNT_INT_EN;
+		break;
+	case XSCALE_COUNTER0:
+		ien |= XSCALE2_COUNT0_INT_EN;
+		evtsel &= ~XSCALE2_COUNT0_EVT_MASK;
+		evtsel |= hwc->config_base << XSCALE2_COUNT0_EVT_SHFT;
+		break;
+	case XSCALE_COUNTER1:
+		ien |= XSCALE2_COUNT1_INT_EN;
+		evtsel &= ~XSCALE2_COUNT1_EVT_MASK;
+		evtsel |= hwc->config_base << XSCALE2_COUNT1_EVT_SHFT;
+		break;
+	case XSCALE_COUNTER2:
+		ien |= XSCALE2_COUNT2_INT_EN;
+		evtsel &= ~XSCALE2_COUNT2_EVT_MASK;
+		evtsel |= hwc->config_base << XSCALE2_COUNT2_EVT_SHFT;
+		break;
+	case XSCALE_COUNTER3:
+		ien |= XSCALE2_COUNT3_INT_EN;
+		evtsel &= ~XSCALE2_COUNT3_EVT_MASK;
+		evtsel |= hwc->config_base << XSCALE2_COUNT3_EVT_SHFT;
+		break;
+	default:
+		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+		return;
+	}
+
+	spin_lock_irqsave(&pmu_lock, flags);
+	xscale2pmu_write_event_select(evtsel);
+	xscale2pmu_write_int_enable(ien);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
+{
+	unsigned long flags, ien, evtsel;
+
+	ien = xscale2pmu_read_int_enable();
+	evtsel = xscale2pmu_read_event_select();
+
+	switch (idx) {
+	case XSCALE_CYCLE_COUNTER:
+		ien &= ~XSCALE2_CCOUNT_INT_EN;
+		break;
+	case XSCALE_COUNTER0:
+		ien &= ~XSCALE2_COUNT0_INT_EN;
+		evtsel &= ~XSCALE2_COUNT0_EVT_MASK;
+		evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT0_EVT_SHFT;
+		break;
+	case XSCALE_COUNTER1:
+		ien &= ~XSCALE2_COUNT1_INT_EN;
+		evtsel &= ~XSCALE2_COUNT1_EVT_MASK;
+		evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT1_EVT_SHFT;
+		break;
+	case XSCALE_COUNTER2:
+		ien &= ~XSCALE2_COUNT2_INT_EN;
+		evtsel &= ~XSCALE2_COUNT2_EVT_MASK;
+		evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT2_EVT_SHFT;
+		break;
+	case XSCALE_COUNTER3:
+		ien &= ~XSCALE2_COUNT3_INT_EN;
+		evtsel &= ~XSCALE2_COUNT3_EVT_MASK;
+		evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT3_EVT_SHFT;
+		break;
+	default:
+		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
+		return;
+	}
+
+	spin_lock_irqsave(&pmu_lock, flags);
+	xscale2pmu_write_event_select(evtsel);
+	xscale2pmu_write_int_enable(ien);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static int
+xscale2pmu_get_event_idx(struct cpu_hw_events *cpuc,
+			struct hw_perf_event *event)
+{
+	int idx = xscale1pmu_get_event_idx(cpuc, event);
+	if (idx >= 0)
+		goto out;
+
+	if (!test_and_set_bit(XSCALE_COUNTER3, cpuc->used_mask))
+		idx = XSCALE_COUNTER3;
+	else if (!test_and_set_bit(XSCALE_COUNTER2, cpuc->used_mask))
+		idx = XSCALE_COUNTER2;
+out:
+	return idx;
+}
+
+static void
+xscale2pmu_start(void)
+{
+	unsigned long flags, val;
+
+	spin_lock_irqsave(&pmu_lock, flags);
+	val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64;
+	val |= XSCALE_PMU_ENABLE;
+	xscale2pmu_write_pmnc(val);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static void
+xscale2pmu_stop(void)
+{
+	unsigned long flags, val;
+
+	spin_lock_irqsave(&pmu_lock, flags);
+	val = xscale2pmu_read_pmnc();
+	val &= ~XSCALE_PMU_ENABLE;
+	xscale2pmu_write_pmnc(val);
+	spin_unlock_irqrestore(&pmu_lock, flags);
+}
+
+static inline u32
+xscale2pmu_read_counter(int counter)
+{
+	u32 val = 0;
+
+	switch (counter) {
+	case XSCALE_CYCLE_COUNTER:
+		asm volatile("mrc p14, 0, %0, c1, c1, 0" : "=r" (val));
+		break;
+	case XSCALE_COUNTER0:
+		asm volatile("mrc p14, 0, %0, c0, c2, 0" : "=r" (val));
+		break;
+	case XSCALE_COUNTER1:
+		asm volatile("mrc p14, 0, %0, c1, c2, 0" : "=r" (val));
+		break;
+	case XSCALE_COUNTER2:
+		asm volatile("mrc p14, 0, %0, c2, c2, 0" : "=r" (val));
+		break;
+	case XSCALE_COUNTER3:
+		asm volatile("mrc p14, 0, %0, c3, c2, 0" : "=r" (val));
+		break;
+	}
+
+	return val;
+}
+
+static inline void
+xscale2pmu_write_counter(int counter, u32 val)
+{
+	switch (counter) {
+	case XSCALE_CYCLE_COUNTER:
+		asm volatile("mcr p14, 0, %0, c1, c1, 0" : : "r" (val));
+		break;
+	case XSCALE_COUNTER0:
+		asm volatile("mcr p14, 0, %0, c0, c2, 0" : : "r" (val));
+		break;
+	case XSCALE_COUNTER1:
+		asm volatile("mcr p14, 0, %0, c1, c2, 0" : : "r" (val));
+		break;
+	case XSCALE_COUNTER2:
+		asm volatile("mcr p14, 0, %0, c2, c2, 0" : : "r" (val));
+		break;
+	case XSCALE_COUNTER3:
+		asm volatile("mcr p14, 0, %0, c3, c2, 0" : : "r" (val));
+		break;
+	}
+}
+
+static const struct arm_pmu xscale2pmu = {
+	.id		= ARM_PERF_PMU_ID_XSCALE2,
+	.handle_irq	= xscale2pmu_handle_irq,
+	.enable		= xscale2pmu_enable_event,
+	.disable	= xscale2pmu_disable_event,
+	.event_map	= xscalepmu_event_map,
+	.raw_event	= xscalepmu_raw_event,
+	.read_counter	= xscale2pmu_read_counter,
+	.write_counter	= xscale2pmu_write_counter,
+	.get_event_idx	= xscale2pmu_get_event_idx,
+	.start		= xscale2pmu_start,
+	.stop		= xscale2pmu_stop,
+	.num_events	= 5,
+	.max_period	= (1LLU << 32) - 1,
+};
+
 static int __init
 init_hw_perf_events(void)
 {
@@ -2086,7 +2924,7 @@ init_hw_perf_events(void)
 	unsigned long implementor = (cpuid & 0xFF000000) >> 24;
 	unsigned long part_number = (cpuid & 0xFFF0);
 
-	/* We only support ARM CPUs implemented by ARM at the moment. */
+	/* ARM Ltd CPUs. */
 	if (0x41 == implementor) {
 		switch (part_number) {
 		case 0xB360:	/* ARM1136 */
@@ -2105,7 +2943,7 @@ init_hw_perf_events(void)
 			perf_max_events = armv6mpcore_pmu.num_events;
 			break;
 		case 0xC080:	/* Cortex-A8 */
-			armv7pmu.name = ARMV7_PMU_CORTEX_A8_NAME;
+			armv7pmu.id = ARM_PERF_PMU_ID_CA8;
 			memcpy(armpmu_perf_cache_map, armv7_a8_perf_cache_map,
 				sizeof(armv7_a8_perf_cache_map));
 			armv7pmu.event_map = armv7_a8_pmu_event_map;
@@ -2117,7 +2955,7 @@ init_hw_perf_events(void)
 			perf_max_events = armv7pmu.num_events;
 			break;
 		case 0xC090:	/* Cortex-A9 */
-			armv7pmu.name = ARMV7_PMU_CORTEX_A9_NAME;
+			armv7pmu.id = ARM_PERF_PMU_ID_CA9;
 			memcpy(armpmu_perf_cache_map, armv7_a9_perf_cache_map,
 				sizeof(armv7_a9_perf_cache_map));
 			armv7pmu.event_map = armv7_a9_pmu_event_map;
@@ -2128,15 +2966,33 @@ init_hw_perf_events(void)
 			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;
+		}
+	/* Intel CPUs [xscale]. */
+	} else if (0x69 == implementor) {
+		part_number = (cpuid >> 13) & 0x7;
+		switch (part_number) {
+		case 1:
+			armpmu = &xscale1pmu;
+			memcpy(armpmu_perf_cache_map, xscale_perf_cache_map,
+					sizeof(xscale_perf_cache_map));
+			perf_max_events	= xscale1pmu.num_events;
+			break;
+		case 2:
+			armpmu = &xscale2pmu;
+			memcpy(armpmu_perf_cache_map, xscale_perf_cache_map,
+					sizeof(xscale_perf_cache_map));
+			perf_max_events	= xscale2pmu.num_events;
+			break;
 		}
 	}
 
-	if (armpmu)
+	if (armpmu) {
 		pr_info("enabled with %s PMU driver, %d counters available\n",
-			armpmu->name, armpmu->num_events);
+				arm_pmu_names[armpmu->id], armpmu->num_events);
+	} else {
+		pr_info("no hardware support available\n");
+		perf_max_events = -1;
+	}
 
 	return 0;
 }
diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c
index a124312e343f..b8af96ea62e6 100644
--- a/arch/arm/kernel/pmu.c
+++ b/arch/arm/kernel/pmu.c
@@ -2,6 +2,7 @@
  *  linux/arch/arm/kernel/pmu.c
  *
  *  Copyright (C) 2009 picoChip Designs Ltd, Jamie Iles
+ *  Copyright (C) 2010 ARM Ltd, Will Deacon
  *
  * 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
@@ -9,65 +10,78 @@
  *
  */
 
+#define pr_fmt(fmt) "PMU: " fmt
+
 #include <linux/cpumask.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/platform_device.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 volatile long pmu_lock;
+
+static struct platform_device *pmu_devices[ARM_NUM_PMU_DEVICES];
+
+static int __devinit pmu_device_probe(struct platform_device *pdev)
+{
+
+	if (pdev->id < 0 || pdev->id >= ARM_NUM_PMU_DEVICES) {
+		pr_warning("received registration request for unknown "
+				"device %d\n", pdev->id);
+		return -EINVAL;
+	}
+
+	if (pmu_devices[pdev->id])
+		pr_warning("registering new PMU device type %d overwrites "
+				"previous registration!\n", pdev->id);
+	else
+		pr_info("registered new PMU device of type %d\n",
+				pdev->id);
 
-static const struct pmu_irqs pmu_irqs = {
-	.irqs	    = irqs,
-	.num_irqs   = ARRAY_SIZE(irqs),
+	pmu_devices[pdev->id] = pdev;
+	return 0;
+}
+
+static struct platform_driver pmu_driver = {
+	.driver		= {
+		.name	= "arm-pmu",
+	},
+	.probe		= pmu_device_probe,
 };
 
-static volatile long pmu_lock;
+static int __init register_pmu_driver(void)
+{
+	return platform_driver_register(&pmu_driver);
+}
+device_initcall(register_pmu_driver);
 
-const struct pmu_irqs *
-reserve_pmu(void)
+struct platform_device *
+reserve_pmu(enum arm_pmu_type device)
 {
-	return test_and_set_bit_lock(0, &pmu_lock) ? ERR_PTR(-EBUSY) :
-		&pmu_irqs;
+	struct platform_device *pdev;
+
+	if (test_and_set_bit_lock(device, &pmu_lock)) {
+		pdev = ERR_PTR(-EBUSY);
+	} else if (pmu_devices[device] == NULL) {
+		clear_bit_unlock(device, &pmu_lock);
+		pdev = ERR_PTR(-ENODEV);
+	} else {
+		pdev = pmu_devices[device];
+	}
+
+	return pdev;
 }
 EXPORT_SYMBOL_GPL(reserve_pmu);
 
 int
-release_pmu(const struct pmu_irqs *irqs)
+release_pmu(struct platform_device *pdev)
 {
-	if (WARN_ON(irqs != &pmu_irqs))
+	if (WARN_ON(pdev != pmu_devices[pdev->id]))
 		return -EINVAL;
-	clear_bit_unlock(0, &pmu_lock);
+	clear_bit_unlock(pdev->id, &pmu_lock);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(release_pmu);
@@ -87,17 +101,42 @@ set_irq_affinity(int irq,
 #endif
 }
 
-int
-init_pmu(void)
+static int
+init_cpu_pmu(void)
 {
 	int i, err = 0;
+	struct platform_device *pdev = pmu_devices[ARM_PMU_DEVICE_CPU];
+
+	if (!pdev) {
+		err = -ENODEV;
+		goto out;
+	}
 
-	for (i = 0; i < pmu_irqs.num_irqs; ++i) {
-		err = set_irq_affinity(pmu_irqs.irqs[i], i);
+	for (i = 0; i < pdev->num_resources; ++i) {
+		err = set_irq_affinity(platform_get_irq(pdev, i), i);
 		if (err)
 			break;
 	}
 
+out:
+	return err;
+}
+
+int
+init_pmu(enum arm_pmu_type device)
+{
+	int err = 0;
+
+	switch (device) {
+	case ARM_PMU_DEVICE_CPU:
+		err = init_cpu_pmu();
+		break;
+	default:
+		pr_warning("attempt to initialise unknown device %d\n",
+				device);
+		err = -EINVAL;
+	}
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(init_pmu);
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index a01194e583ff..b8c3d0f689d9 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -168,7 +168,7 @@ int __cpu_disable(void)
 	struct task_struct *p;
 	int ret;
 
-	ret = mach_cpu_disable(cpu);
+	ret = platform_cpu_disable(cpu);
 	if (ret)
 		return ret;
 
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index 28753805d2d1..38c261f9951c 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -72,12 +72,15 @@ unsigned long profile_pc(struct pt_regs *regs)
 EXPORT_SYMBOL(profile_pc);
 #endif
 
-#ifndef CONFIG_GENERIC_TIME
-static unsigned long dummy_gettimeoffset(void)
+#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
+u32 arch_gettimeoffset(void)
 {
+	if (system_timer->offset != NULL)
+		return system_timer->offset() * 1000;
+
 	return 0;
 }
-#endif
+#endif /* CONFIG_ARCH_USES_GETTIMEOFFSET */
 
 #ifdef CONFIG_LEDS_TIMER
 static inline void do_leds(void)
@@ -93,63 +96,6 @@ static inline void do_leds(void)
 #define	do_leds()
 #endif
 
-#ifndef CONFIG_GENERIC_TIME
-void do_gettimeofday(struct timeval *tv)
-{
-	unsigned long flags;
-	unsigned long seq;
-	unsigned long usec, sec;
-
-	do {
-		seq = read_seqbegin_irqsave(&xtime_lock, flags);
-		usec = system_timer->offset();
-		sec = xtime.tv_sec;
-		usec += xtime.tv_nsec / 1000;
-	} while (read_seqretry_irqrestore(&xtime_lock, seq, flags));
-
-	/* usec may have gone up a lot: be safe */
-	while (usec >= 1000000) {
-		usec -= 1000000;
-		sec++;
-	}
-
-	tv->tv_sec = sec;
-	tv->tv_usec = usec;
-}
-
-EXPORT_SYMBOL(do_gettimeofday);
-
-int do_settimeofday(struct timespec *tv)
-{
-	time_t wtm_sec, sec = tv->tv_sec;
-	long wtm_nsec, nsec = tv->tv_nsec;
-
-	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
-		return -EINVAL;
-
-	write_seqlock_irq(&xtime_lock);
-	/*
-	 * This is revolting. We need to set "xtime" correctly. However, the
-	 * value in this location is the value at the most recent update of
-	 * wall time.  Discover what correction gettimeofday() would have
-	 * done, and then undo it!
-	 */
-	nsec -= system_timer->offset() * NSEC_PER_USEC;
-
-	wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
-	wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);
-
-	set_normalized_timespec(&xtime, sec, nsec);
-	set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
-
-	ntp_clear();
-	write_sequnlock_irq(&xtime_lock);
-	clock_was_set();
-	return 0;
-}
-
-EXPORT_SYMBOL(do_settimeofday);
-#endif /* !CONFIG_GENERIC_TIME */
 
 #ifndef CONFIG_GENERIC_CLOCKEVENTS
 /*
@@ -214,10 +160,6 @@ device_initcall(timer_init_sysfs);
 
 void __init time_init(void)
 {
-#ifndef CONFIG_GENERIC_TIME
-	if (system_timer->offset == NULL)
-		system_timer->offset = dummy_gettimeoffset;
-#endif
 	system_timer->init();
 }