ARM: oprofile: use perf-events framework as backend [v3]

index 49e3049..fa4b326 100644
@@ -28,4 +28,18 @@ 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);
+
 #endif /* __ARM_PERF_EVENT_H__ */

index 89a77fc..10a0bcd 100644
@@ -16,6 +16,7 @@
 
 #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>

@@ -68,8 +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);

@@ -88,6 +99,18 @@ 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);
+
 #define HW_OP_UNSUPPORTED		0xFFFF
 
 #define C(_x) \

@@ -1154,7 +1177,7 @@ 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,

@@ -1177,7 +1200,7 @@ 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,

@@ -1207,10 +1230,6 @@ 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,

@@ -2115,7 +2134,7 @@ 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;

@@ -2127,7 +2146,7 @@ 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;

@@ -2146,7 +2165,7 @@ init_hw_perf_events(void)
 
 	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);
 
 	return 0;
 }

index 10a0bcd..381f121 100644
@@ -2108,6 +2108,803 @@ 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)
 {

@@ -2115,7 +2912,7 @@ 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 */

@@ -2157,15 +2954,33 @@ 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",
-			arm_pmu_names[armpmu->id], 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;
 }

index 9547703..a197bc5 100644
@@ -751,6 +751,7 @@ struct perf_output_handle {
  * Set by architecture code:
  */
 extern int perf_max_events;
+extern int perf_get_max_events(void);
 
 extern const struct pmu *hw_perf_event_init(struct perf_event *event);
 

index 574ee58..464bda6 100644
@@ -39,6 +39,12 @@
 static DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context);
 
 int perf_max_events __read_mostly = 1;
+int perf_get_max_events(void)
+{
+	return perf_max_events;
+}
+EXPORT_SYMBOL_GPL(perf_get_max_events);
+
 static int perf_reserved_percpu __read_mostly;
 static int perf_overcommit __read_mostly = 1;
 

index 3fcd752..aa36307 100644
@@ -2,32 +2,183 @@
  * @file common.c
  *
  * @remark Copyright 2004 Oprofile Authors
+ * @remark Copyright 2010 ARM Ltd.
  * @remark Read the file COPYING
  *
  * @author Zwane Mwaikambo
+ * @author Will Deacon [move to perf]
  */
 
+#include <linux/cpumask.h>
+#include <linux/errno.h>
 #include <linux/init.h>
+#include <linux/mutex.h>
 #include <linux/oprofile.h>
-#include <linux/errno.h>
+#include <linux/perf_event.h>
 #include <linux/slab.h>
 #include <linux/sysdev.h>
-#include <linux/mutex.h>
+#include <asm/stacktrace.h>
+#include <linux/uaccess.h>
+
+#include <asm/perf_event.h>
+#include <asm/ptrace.h>
 
-#include "op_counter.h"
-#include "op_arm_model.h"
+#ifdef CONFIG_HW_PERF_EVENTS
+/*
+ * Per performance monitor configuration as set via oprofilefs.
+ */
+struct op_counter_config {
+	unsigned long count;
+	unsigned long enabled;
+	unsigned long event;
+	unsigned long unit_mask;
+	unsigned long kernel;
+	unsigned long user;
+	struct perf_event_attr attr;
+};
 
-static struct op_arm_model_spec *op_arm_model;
 static int op_arm_enabled;
 static DEFINE_MUTEX(op_arm_mutex);
 
-struct op_counter_config *counter_config;
+static struct op_counter_config *counter_config;
+static struct perf_event **perf_events[nr_cpumask_bits];
+static int perf_num_counters;
+
+/*
+ * Overflow callback for oprofile.
+ */
+static void op_overflow_handler(struct perf_event *event, int unused,
+			struct perf_sample_data *data, struct pt_regs *regs)
+{
+	int id;
+	u32 cpu = smp_processor_id();
+
+	for (id = 0; id < perf_num_counters; ++id)
+		if (perf_events[cpu][id] == event)
+			break;
+
+	if (id != perf_num_counters)
+		oprofile_add_sample(regs, id);
+	else
+		pr_warning("oprofile: ignoring spurious overflow "
+				"on cpu %u\n", cpu);
+}
+
+/*
+ * Called by op_arm_setup to create perf attributes to mirror the oprofile
+ * settings in counter_config. Attributes are created as `pinned' events and
+ * so are permanently scheduled on the PMU.
+ */
+static void op_perf_setup(void)
+{
+	int i;
+	u32 size = sizeof(struct perf_event_attr);
+	struct perf_event_attr *attr;
+
+	for (i = 0; i < perf_num_counters; ++i) {
+		attr = &counter_config[i].attr;
+		memset(attr, 0, size);
+		attr->type		= PERF_TYPE_RAW;
+		attr->size		= size;
+		attr->config		= counter_config[i].event;
+		attr->sample_period	= counter_config[i].count;
+		attr->pinned		= 1;
+	}
+}
+
+static int op_create_counter(int cpu, int event)
+{
+	int ret = 0;
+	struct perf_event *pevent;
+
+	if (!counter_config[event].enabled || (perf_events[cpu][event] != NULL))
+		return ret;
+
+	pevent = perf_event_create_kernel_counter(&counter_config[event].attr,
+						  cpu, -1,
+						  op_overflow_handler);
+
+	if (IS_ERR(pevent)) {
+		ret = PTR_ERR(pevent);
+	} else if (pevent->state != PERF_EVENT_STATE_ACTIVE) {
+		pr_warning("oprofile: failed to enable event %d "
+				"on CPU %d\n", event, cpu);
+		ret = -EBUSY;
+	} else {
+		perf_events[cpu][event] = pevent;
+	}
+
+	return ret;
+}
+
+static void op_destroy_counter(int cpu, int event)
+{
+	struct perf_event *pevent = perf_events[cpu][event];
+
+	if (pevent) {
+		perf_event_release_kernel(pevent);
+		perf_events[cpu][event] = NULL;
+	}
+}
+
+/*
+ * Called by op_arm_start to create active perf events based on the
+ * perviously configured attributes.
+ */
+static int op_perf_start(void)
+{
+	int cpu, event, ret = 0;
+
+	for_each_online_cpu(cpu) {
+		for (event = 0; event < perf_num_counters; ++event) {
+			ret = op_create_counter(cpu, event);
+			if (ret)
+				goto out;
+		}
+	}
+
+out:
+	return ret;
+}
+
+/*
+ * Called by op_arm_stop@the end of a profiling run.
+ */
+static void op_perf_stop(void)
+{
+	int cpu, event;
+
+	for_each_online_cpu(cpu)
+		for (event = 0; event < perf_num_counters; ++event)
+			op_destroy_counter(cpu, event);
+}
+
+
+static char *op_name_from_perf_id(enum arm_perf_pmu_ids id)
+{
+	switch (id) {
+	case ARM_PERF_PMU_ID_XSCALE1:
+		return "arm/xscale1";
+	case ARM_PERF_PMU_ID_XSCALE2:
+		return "arm/xscale2";
+	case ARM_PERF_PMU_ID_V6:
+		return "arm/armv6";
+	case ARM_PERF_PMU_ID_V6MP:
+		return "arm/mpcore";
+	case ARM_PERF_PMU_ID_CA8:
+		return "arm/armv7";
+	case ARM_PERF_PMU_ID_CA9:
+		return "arm/armv7-ca9";
+	default:
+		return NULL;
+	}
+}
 
 static int op_arm_create_files(struct super_block *sb, struct dentry *root)
 {
 	unsigned int i;
 
-	for (i = 0; i < op_arm_model->num_counters; i++) {
+	for (i = 0; i < perf_num_counters; i++) {
 		struct dentry *dir;
 		char buf[4];
 

@@ -46,12 +197,10 @@ static int op_arm_create_files(struct super_block *sb, struct dentry *root)
 
 static int op_arm_setup(void)
 {
-	int ret;
-
 	spin_lock(&oprofilefs_lock);
-	ret = op_arm_model->setup_ctrs();
+	op_perf_setup();
 	spin_unlock(&oprofilefs_lock);
-	return ret;
+	return 0;
 }
 
 static int op_arm_start(void)

@@ -60,8 +209,9 @@ static int op_arm_start(void)
 
 	mutex_lock(&op_arm_mutex);
 	if (!op_arm_enabled) {
-		ret = op_arm_model->start();
-		op_arm_enabled = !ret;
+		ret = 0;
+		op_perf_start();
+		op_arm_enabled = 1;
 	}
 	mutex_unlock(&op_arm_mutex);
 	return ret;

@@ -71,7 +221,7 @@ static void op_arm_stop(void)
 {
 	mutex_lock(&op_arm_mutex);
 	if (op_arm_enabled)
-		op_arm_model->stop();
+		op_perf_stop();
 	op_arm_enabled = 0;
 	mutex_unlock(&op_arm_mutex);
 }

@@ -81,7 +231,7 @@ static int op_arm_suspend(struct sys_device *dev, pm_message_t state)
 {
 	mutex_lock(&op_arm_mutex);
 	if (op_arm_enabled)
-		op_arm_model->stop();
+		op_perf_stop();
 	mutex_unlock(&op_arm_mutex);
 	return 0;
 }

@@ -89,7 +239,7 @@ static int op_arm_suspend(struct sys_device *dev, pm_message_t state)
 static int op_arm_resume(struct sys_device *dev)
 {
 	mutex_lock(&op_arm_mutex);
-	if (op_arm_enabled && op_arm_model->start())
+	if (op_arm_enabled && op_perf_start())
 		op_arm_enabled = 0;
 	mutex_unlock(&op_arm_mutex);
 	return 0;

@@ -126,58 +276,137 @@ static void  exit_driverfs(void)
 #define exit_driverfs() do { } while (0)
 #endif /* CONFIG_PM */
 
-int __init oprofile_arch_init(struct oprofile_operations *ops)
+static int report_trace(struct stackframe *frame, void *d)
 {
-	struct op_arm_model_spec *spec = NULL;
-	int ret = -ENODEV;
+	unsigned int *depth = d;
 
-	ops->backtrace = arm_backtrace;
+	if (*depth) {
+		oprofile_add_trace(frame->pc);
+		(*depth)--;
+	}
 
-#ifdef CONFIG_CPU_XSCALE
-	spec = &op_xscale_spec;
-#endif
+	return *depth == 0;
+}
 
-#ifdef CONFIG_OPROFILE_ARMV6
-	spec = &op_armv6_spec;
-#endif
+/*
+ * The registers we're interested in are at the end of the variable
+ * length saved register structure. The fp points at the end of this
+ * structure so the address of this struct is:
+ * (struct frame_tail *)(xxx->fp)-1
+ */
+struct frame_tail {
+	struct frame_tail *fp;
+	unsigned long sp;
+	unsigned long lr;
+} __attribute__((packed));
 
-#ifdef CONFIG_OPROFILE_MPCORE
-	spec = &op_mpcore_spec;
-#endif
+static struct frame_tail* user_backtrace(struct frame_tail *tail)
+{
+	struct frame_tail buftail[2];
 
-#ifdef CONFIG_OPROFILE_ARMV7
-	spec = &op_armv7_spec;
-#endif
+	/* 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;
 
-	if (spec) {
-		ret = spec->init();
-		if (ret < 0)
-			return ret;
+	oprofile_add_trace(buftail[0].lr);
 
-		counter_config = kcalloc(spec->num_counters, sizeof(struct op_counter_config),
-					 GFP_KERNEL);
-		if (!counter_config)
-			return -ENOMEM;
+	/* frame pointers should strictly progress back up the stack
+	 * (towards higher addresses) */
+	if (tail >= buftail[0].fp)
+		return NULL;
+
+	return buftail[0].fp-1;
+}
+
+static void arm_backtrace(struct pt_regs * const regs, unsigned int depth)
+{
+	struct frame_tail *tail = ((struct frame_tail *) regs->ARM_fp) - 1;
+
+	if (!user_mode(regs)) {
+		struct stackframe frame;
+		frame.fp = regs->ARM_fp;
+		frame.sp = regs->ARM_sp;
+		frame.lr = regs->ARM_lr;
+		frame.pc = regs->ARM_pc;
+		walk_stackframe(&frame, report_trace, &depth);
+		return;
+	}
+
+	while (depth-- && tail && !((unsigned long) tail & 3))
+		tail = user_backtrace(tail);
+}
+
+int __init oprofile_arch_init(struct oprofile_operations *ops)
+{
+	int cpu, ret = 0;
+
+	perf_num_counters = perf_get_max_events();
+
+	counter_config = kcalloc(perf_num_counters,
+			sizeof(struct op_counter_config), GFP_KERNEL);
 
-		op_arm_model = spec;
-		init_driverfs();
-		ops->create_files = op_arm_create_files;
-		ops->setup = op_arm_setup;
-		ops->shutdown = op_arm_stop;
-		ops->start = op_arm_start;
-		ops->stop = op_arm_stop;
-		ops->cpu_type = op_arm_model->name;
-		printk(KERN_INFO "oprofile: using %s\n", spec->name);
+	if (!counter_config) {
+		pr_info("oprofile: failed to allocate %d "
+				"counters\n", perf_num_counters);
+		return -ENOMEM;
 	}
 
+	for_each_possible_cpu(cpu) {
+		perf_events[cpu] = kcalloc(perf_num_counters,
+				sizeof(struct perf_event *), GFP_KERNEL);
+		if (!perf_events[cpu]) {
+			pr_info("oprofile: failed to allocate %d perf events "
+					"for cpu %d\n", perf_num_counters, cpu);
+			while (--cpu >= 0)
+				kfree(perf_events[cpu]);
+			return -ENOMEM;
+		}
+	}
+
+	init_driverfs();
+	ops->backtrace		= arm_backtrace;
+	ops->create_files	= op_arm_create_files;
+	ops->setup		= op_arm_setup;
+	ops->start		= op_arm_start;
+	ops->stop		= op_arm_stop;
+	ops->shutdown		= op_arm_stop;
+	ops->cpu_type		= op_name_from_perf_id(armpmu_get_pmu_id());
+
+	if (!ops->cpu_type)
+		ret = -ENODEV;
+	else
+		pr_info("oprofile: using %s\n", ops->cpu_type);
+
 	return ret;
 }
 
 void oprofile_arch_exit(void)
 {
-	if (op_arm_model) {
+	int cpu, id;
+	struct perf_event *event;
+
+	if (*perf_events) {
 		exit_driverfs();
-		op_arm_model = NULL;
+		for_each_possible_cpu(cpu) {
+			for (id = 0; id < perf_num_counters; ++id) {
+				event = perf_events[cpu][id];
+				if (event != NULL)
+					perf_event_release_kernel(event);
+			}
+			kfree(perf_events[cpu]);
+		}
 	}
-	kfree(counter_config);
+
+	if (counter_config)
+		kfree(counter_config);
+}
+#else
+int __init oprofile_arch_init(struct oprofile_operations *ops)
+{
+	pr_info("oprofile: hardware counters not available\n");
+	return -ENODEV;
 }
+void oprofile_arch_exit(void) {}
+#endif /* CONFIG_HW_PERF_EVENTS */

83 lines not on this page · raw message

deleted file mode 100644
index 8c4e4f6..0000000
@@ -1,35 +0,0 @@
-/**
- * @file op_arm_model.h
- * interface to ARM machine specific operations
- *
- * @remark Copyright 2004 Oprofile Authors
- * @remark Read the file COPYING
- *
- * @author Zwane Mwaikambo
- */
-
-#ifndef OP_ARM_MODEL_H
-#define OP_ARM_MODEL_H
-
-struct op_arm_model_spec {
-	int (*init)(void);
-	unsigned int num_counters;
-	int (*setup_ctrs)(void);
-	int (*start)(void);
-	void (*stop)(void);
-	char *name;
-};
-
-#ifdef CONFIG_CPU_XSCALE
-extern struct op_arm_model_spec op_xscale_spec;
-#endif
-
-extern struct op_arm_model_spec op_armv6_spec;
-extern struct op_arm_model_spec op_mpcore_spec;
-extern struct op_arm_model_spec op_armv7_spec;
-
-extern void arm_backtrace(struct pt_regs * const regs, unsigned int depth);
-
-extern int __init op_arm_init(struct oprofile_operations *ops, struct op_arm_model_spec *spec);
-extern void op_arm_exit(void);
-#endif /* OP_ARM_MODEL_H */

deleted file mode 100644
index ca942a6..0000000
@@ -1,27 +0,0 @@
-/**
- * @file op_counter.h
- *
- * @remark Copyright 2004 Oprofile Authors
- * @remark Read the file COPYING
- *
- * @author Zwane Mwaikambo
- */
-
-#ifndef OP_COUNTER_H
-#define OP_COUNTER_H
-
-/* Per performance monitor configuration as set via
- * oprofilefs.
- */
-struct op_counter_config {
-	unsigned long count;
-	unsigned long enabled;
-	unsigned long event;
-	unsigned long unit_mask;
-	unsigned long kernel;
-	unsigned long user;
-};
-
-extern struct op_counter_config *counter_config;
-
-#endif /* OP_COUNTER_H */

162 lines not on this page · raw message

45 lines not on this page · raw message

306 lines not on this page · raw message

61 lines not on this page · raw message

78 lines not on this page · raw message

415 lines not on this page · raw message

103 lines not on this page · raw message

444 lines not on this page · raw message

index aa36307..43467cf 100644
@@ -10,13 +10,14 @@
  */
 
 #include <linux/cpumask.h>
+#include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/mutex.h>
 #include <linux/oprofile.h>
 #include <linux/perf_event.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <linux/sysdev.h>
 #include <asm/stacktrace.h>
 #include <linux/uaccess.h>
 

@@ -227,7 +228,7 @@ static void op_arm_stop(void)
 }
 
 #ifdef CONFIG_PM
-static int op_arm_suspend(struct sys_device *dev, pm_message_t state)
+static int op_arm_suspend(struct platform_device *dev, pm_message_t state)
 {
 	mutex_lock(&op_arm_mutex);
 	if (op_arm_enabled)

@@ -236,7 +237,7 @@ static int op_arm_suspend(struct sys_device *dev, pm_message_t state)
 	return 0;
 }
 
-static int op_arm_resume(struct sys_device *dev)
+static int op_arm_resume(struct platform_device *dev)
 {
 	mutex_lock(&op_arm_mutex);
 	if (op_arm_enabled && op_perf_start())

@@ -245,34 +246,42 @@ static int op_arm_resume(struct sys_device *dev)
 	return 0;
 }
 
-static struct sysdev_class oprofile_sysclass = {
-	.name		= "oprofile",
+static struct platform_driver oprofile_driver = {
+	.driver		= {
+		.name		= "arm-oprofile",
+	},
 	.resume		= op_arm_resume,
 	.suspend	= op_arm_suspend,
 };
 
-static struct sys_device device_oprofile = {
-	.id		= 0,
-	.cls		= &oprofile_sysclass,
-};
+static struct platform_device *oprofile_pdev;
 
 static int __init init_driverfs(void)
 {
 	int ret;
 
-	if (!(ret = sysdev_class_register(&oprofile_sysclass)))
-		ret = sysdev_register(&device_oprofile);
+	ret = platform_driver_register(&oprofile_driver);
+	if (ret)
+		goto out;
+
+	oprofile_pdev =	platform_device_register_simple(
+				oprofile_driver.driver.name, 0, NULL, 0);
+	if (IS_ERR(oprofile_pdev)) {
+		ret = PTR_ERR(oprofile_pdev);
+		platform_driver_unregister(&oprofile_driver);
+	}
 
+out:
 	return ret;
 }
 
 static void  exit_driverfs(void)
 {
-	sysdev_unregister(&device_oprofile);
-	sysdev_class_unregister(&oprofile_sysclass);
+	platform_device_unregister(oprofile_pdev);
+	platform_driver_unregister(&oprofile_driver);
 }
 #else
-#define init_driverfs()	do { } while (0)
+static int __init init_driverfs(void) { return 0; }
 #define exit_driverfs() do { } while (0)
 #endif /* CONFIG_PM */
 

@@ -353,6 +362,12 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 		return -ENOMEM;
 	}
 
+	ret = init_driverfs();
+	if (ret) {
+		kfree(counter_config);
+		return ret;
+	}
+
 	for_each_possible_cpu(cpu) {
 		perf_events[cpu] = kcalloc(perf_num_counters,
 				sizeof(struct perf_event *), GFP_KERNEL);

@@ -365,7 +380,6 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 		}
 	}
 
-	init_driverfs();
 	ops->backtrace		= arm_backtrace;
 	ops->create_files	= op_arm_create_files;
 	ops->setup		= op_arm_setup;