Merge branch 'devel-pmu' into devel

18 files changed, 1316 insertions, 1950 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 9e938a79a3b2..2b3157b5089a 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -13,7 +13,7 @@ config ARM
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
 	select GENERIC_ATOMIC64 if (!CPU_32v6K)
-	select HAVE_OPROFILE
+	select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
 	select HAVE_ARCH_KGDB
 	select HAVE_KPROBES if (!XIP_KERNEL)
 	select HAVE_KRETPROBES if (HAVE_KPROBES)
@@ -181,28 +181,6 @@ config ARM_L1_CACHE_SHIFT_6
 	help
 	  Setting ARM L1 cache line size to 64 Bytes.
 
-if OPROFILE
-
-config OPROFILE_ARMV6
-	def_bool y
-	depends on CPU_V6 && !SMP
-	select OPROFILE_ARM11_CORE
-
-config OPROFILE_MPCORE
-	def_bool y
-	depends on CPU_V6 && SMP
-	select OPROFILE_ARM11_CORE
-
-config OPROFILE_ARM11_CORE
-	bool
-
-config OPROFILE_ARMV7
-	def_bool y
-	depends on CPU_V7 && !SMP
-	bool
-
-endif
-
 config VECTORS_BASE
 	hex
 	default 0xffff0000 if MMU || CPU_HIGH_VECTOR
@@ -1314,7 +1292,7 @@ config HIGHPTE
 
 config HW_PERF_EVENTS
 	bool "Enable hardware performance counter support for perf events"
-	depends on PERF_EVENTS && CPU_HAS_PMU && (CPU_V6 || CPU_V7)
+	depends on PERF_EVENTS && CPU_HAS_PMU
 	default y
 	help
 	  Enable hardware performance counter support for perf events. If
diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
index 49e3049aba32..48837e6d8887 100644
--- a/arch/arm/include/asm/perf_event.h
+++ b/arch/arm/include/asm/perf_event.h
@@ -28,4 +28,21 @@ set_perf_event_pending(void)
  * same indexes here for consistency. */
 #define PERF_EVENT_INDEX_OFFSET 1
 
+/* ARM perf PMU IDs for use by internal perf clients. */
+enum arm_perf_pmu_ids {
+	ARM_PERF_PMU_ID_XSCALE1	= 0,
+	ARM_PERF_PMU_ID_XSCALE2,
+	ARM_PERF_PMU_ID_V6,
+	ARM_PERF_PMU_ID_V6MP,
+	ARM_PERF_PMU_ID_CA8,
+	ARM_PERF_PMU_ID_CA9,
+	ARM_NUM_PMU_IDS,
+};
+
+extern enum arm_perf_pmu_ids
+armpmu_get_pmu_id(void);
+
+extern int
+armpmu_get_max_events(void);
+
 #endif /* __ARM_PERF_EVENT_H__ */
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index 44bec1f02cb0..8ccea012722c 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -19,31 +19,26 @@ enum arm_pmu_type {
 
 #ifdef CONFIG_CPU_HAS_PMU
 
-struct pmu_irqs {
-	const int   *irqs;
-	int	    num_irqs;
-};
-
 /**
  * reserve_pmu() - reserve the hardware performance counters
  *
  * Reserve the hardware performance counters in the system for exclusive use.
- * The 'struct pmu_irqs' for the system is returned on success, ERR_PTR()
+ * The platform_device for the system is returned on success, ERR_PTR()
  * encoded error on failure.
  */
-extern const struct pmu_irqs *
-reserve_pmu(void);
+extern struct platform_device *
+reserve_pmu(enum arm_pmu_type device);
 
 /**
  * release_pmu() - Relinquish control of the performance counters
  *
  * Release the performance counters and allow someone else to use them.
  * Callers must have disabled the counters and released IRQs before calling
- * this. The 'struct pmu_irqs' returned from reserve_pmu() must be passed as
+ * this. The platform_device returned from reserve_pmu() must be passed as
  * a cookie.
  */
 extern int
-release_pmu(const struct pmu_irqs *irqs);
+release_pmu(struct platform_device *pdev);
 
 /**
  * init_pmu() - Initialise the PMU.
@@ -53,24 +48,26 @@ release_pmu(const struct pmu_irqs *irqs);
  * the actual hardware initialisation.
  */
 extern int
-init_pmu(void);
+init_pmu(enum arm_pmu_type device);
 
 #else /* CONFIG_CPU_HAS_PMU */
 
-static inline const struct pmu_irqs *
-reserve_pmu(void)
+#include <linux/err.h>
+
+static inline struct platform_device *
+reserve_pmu(enum arm_pmu_type device)
 {
 	return ERR_PTR(-ENODEV);
 }
 
 static inline int
-release_pmu(const struct pmu_irqs *irqs)
+release_pmu(struct platform_device *pdev)
 {
 	return -ENODEV;
 }
 
 static inline int
-init_pmu(void)
+init_pmu(enum arm_pmu_type device)
 {
 	return -ENODEV;
 }
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