Merge branch 'devel-stable' into for-next

Conflicts:
	arch/arm/kernel/perf_event_cpu.c

10 files changed, 362 insertions, 1107 deletions

diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 04ccf1c..e731018 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -91,9 +91,7 @@
  * of this define that was meant to.
  * Fortunately, there is no reference for this in noMMU mode, for now.
  */
-#ifndef TASK_SIZE
-#define TASK_SIZE		(CONFIG_DRAM_SIZE)
-#endif
+#define TASK_SIZE		UL(0xffffffff)
 
 #ifndef TASK_UNMAPPED_BASE
 #define TASK_UNMAPPED_BASE	UL(0x00000000)
diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
index 7558775..c3a8369 100644
--- a/arch/arm/include/asm/perf_event.h
+++ b/arch/arm/include/asm/perf_event.h
@@ -12,15 +12,6 @@
 #ifndef __ARM_PERF_EVENT_H__
 #define __ARM_PERF_EVENT_H__
 
-/*
- * The ARMv7 CPU PMU supports up to 32 event counters.
- */
-#define ARMPMU_MAX_HWEVENTS		32
-
-#define HW_OP_UNSUPPORTED		0xFFFF
-#define C(_x)				PERF_COUNT_HW_CACHE_##_x
-#define CACHE_OP_UNSUPPORTED		0xFFFF
-
 #ifdef CONFIG_HW_PERF_EVENTS
 struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index ae1919b..0b648c5 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -42,6 +42,25 @@ struct arm_pmu_platdata {
 
 #ifdef CONFIG_HW_PERF_EVENTS
 
+/*
+ * The ARMv7 CPU PMU supports up to 32 event counters.
+ */
+#define ARMPMU_MAX_HWEVENTS		32
+
+#define HW_OP_UNSUPPORTED		0xFFFF
+#define C(_x)				PERF_COUNT_HW_CACHE_##_x
+#define CACHE_OP_UNSUPPORTED		0xFFFF
+
+#define PERF_MAP_ALL_UNSUPPORTED					\
+	[0 ... PERF_COUNT_HW_MAX - 1] = HW_OP_UNSUPPORTED
+
+#define PERF_CACHE_MAP_ALL_UNSUPPORTED					\
+[0 ... C(MAX) - 1] = {							\
+	[0 ... C(OP_MAX) - 1] = {					\
+		[0 ... C(RESULT_MAX) - 1] = CACHE_OP_UNSUPPORTED,	\
+	},								\
+}
+
 /* The events for a given PMU register set. */
 struct pmu_hw_events {
 	/*
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 7057cf8..a4cd7af 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -242,7 +242,7 @@ static inline void set_fs(mm_segment_t fs)
 #define access_ok(type,addr,size)	(__range_ok(addr,size) == 0)
 
 #define user_addr_max() \
-	(segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
+	(segment_eq(get_fs(), KERNEL_DS) ? ~0UL : get_fs())
 
 /*
  * The "__xxx" versions of the user access functions do not verify the
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index ae3e216..266cba4 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -560,11 +560,16 @@ user_backtrace(struct frame_tail __user *tail,
 	       struct perf_callchain_entry *entry)
 {
 	struct frame_tail buftail;
+	unsigned long err;
 
-	/* 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)))
+
+	pagefault_disable();
+	err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+	pagefault_enable();
+
+	if (err)
 		return NULL;
 
 	perf_callchain_store(entry, buftail.lr);
@@ -590,6 +595,10 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 	}
 
 	perf_callchain_store(entry, regs->ARM_pc);
+
+	if (!current->mm)
+		return;
+
 	tail = (struct frame_tail __user *)regs->ARM_fp - 1;
 
 	while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index c02c2e8..e6a6edb 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -233,14 +233,17 @@ static struct of_device_id cpu_pmu_of_device_ids[] = {
 	{.compatible = "arm,cortex-a7-pmu",	.data = armv7_a7_pmu_init},
 	{.compatible = "arm,cortex-a5-pmu",	.data = armv7_a5_pmu_init},
 	{.compatible = "arm,arm11mpcore-pmu",	.data = armv6mpcore_pmu_init},
-	{.compatible = "arm,arm1176-pmu",	.data = armv6pmu_init},
-	{.compatible = "arm,arm1136-pmu",	.data = armv6pmu_init},
+	{.compatible = "arm,arm1176-pmu",	.data = armv6_1176_pmu_init},
+	{.compatible = "arm,arm1136-pmu",	.data = armv6_1136_pmu_init},
 	{.compatible = "qcom,krait-pmu",	.data = krait_pmu_init},
 	{},
 };
 
 static struct platform_device_id cpu_pmu_plat_device_ids[] = {
 	{.name = "arm-pmu"},
+	{.name = "armv6-pmu"},
+	{.name = "armv7-pmu"},
+	{.name = "xscale-pmu"},
 	{},
 };
 
@@ -257,9 +260,13 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 	switch (read_cpuid_part()) {
 	/* ARM Ltd CPUs. */
 	case ARM_CPU_PART_ARM1136:
+		ret = armv6_1136_pmu_init(pmu);
+		break;
 	case ARM_CPU_PART_ARM1156:
+		ret = armv6_1156_pmu_init(pmu);
+		break;
 	case ARM_CPU_PART_ARM1176:
-		ret = armv6pmu_init(pmu);
+		ret = armv6_1176_pmu_init(pmu);
 		break;
 	case ARM_CPU_PART_ARM11MPCORE:
 		ret = armv6mpcore_pmu_init(pmu);
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index 03664b0..abfeb04 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -65,13 +65,11 @@ enum armv6_counters {
  * accesses/misses in hardware.
  */
 static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV6_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV6_PERFCTR_INSTR_EXEC,
-	[PERF_COUNT_HW_CACHE_REFERENCES]	= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_CACHE_MISSES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV6_PERFCTR_BR_EXEC,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV6_PERFCTR_BR_MISPREDICT,
-	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV6_PERFCTR_IBUF_STALL,
 	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= ARMV6_PERFCTR_LSU_FULL_STALL,
 };
@@ -79,116 +77,31 @@ static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
 static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					  [PERF_COUNT_HW_CACHE_OP_MAX]
 					  [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		/*
-		 * The performance counters don't differentiate between read
-		 * and write accesses/misses so this isn't strictly correct,
-		 * but it's the best we can do. Writes and reads get
-		 * combined.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV6_PERFCTR_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DCACHE_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV6_PERFCTR_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DCACHE_MISS,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ICACHE_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(DTLB)] = {
-		/*
-		 * The ARM performance counters can count micro DTLB misses,
-		 * micro ITLB misses and main TLB misses. There isn't an event
-		 * for TLB misses, so use the micro misses here and if users
-		 * want the main TLB misses they can use a raw counter.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DTLB_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DTLB_MISS,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ITLB_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ITLB_MISS,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[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,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	/*
+	 * The performance counters don't differentiate between read and write
+	 * accesses/misses so this isn't strictly correct, but it's the best we
+	 * can do. Writes and reads get combined.
+	 */
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV6_PERFCTR_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6_PERFCTR_DCACHE_MISS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV6_PERFCTR_DCACHE_ACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV6_PERFCTR_DCACHE_MISS,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6_PERFCTR_ICACHE_MISS,
+
+	/*
+	 * The ARM performance counters can count micro DTLB misses, micro ITLB
+	 * misses and main TLB misses. There isn't an event for TLB misses, so
+	 * use the micro misses here and if users want the main TLB misses they
+	 * can use a raw counter.
+	 */
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6_PERFCTR_DTLB_MISS,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV6_PERFCTR_DTLB_MISS,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6_PERFCTR_ITLB_MISS,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV6_PERFCTR_ITLB_MISS,
 };
 
 enum armv6mpcore_perf_types {
@@ -220,13 +133,11 @@ enum armv6mpcore_perf_types {
  * accesses/misses in hardware.
  */
 static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV6MPCORE_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV6MPCORE_PERFCTR_INSTR_EXEC,
-	[PERF_COUNT_HW_CACHE_REFERENCES]	= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_CACHE_MISSES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV6MPCORE_PERFCTR_BR_EXEC,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV6MPCORE_PERFCTR_BR_MISPREDICT,
-	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV6MPCORE_PERFCTR_IBUF_STALL,
 	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= ARMV6MPCORE_PERFCTR_LSU_FULL_STALL,
 };
@@ -234,114 +145,26 @@ static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
 static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					[PERF_COUNT_HW_CACHE_OP_MAX]
 					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]  =
-				ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
-			[C(RESULT_MISS)]    =
-				ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]  =
-				ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
-			[C(RESULT_MISS)]    =
-				ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(DTLB)] = {
-		/*
-		 * The ARM performance counters can count micro DTLB misses,
-		 * micro ITLB misses and main TLB misses. There isn't an event
-		 * for TLB misses, so use the micro misses here and if users
-		 * want the main TLB misses they can use a raw counter.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_DTLB_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_DTLB_MISS,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ITLB_MISS,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ITLB_MISS,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[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,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_ICACHE_MISS,
+
+	/*
+	 * The ARM performance counters can count micro DTLB misses, micro ITLB
+	 * misses and main TLB misses. There isn't an event for TLB misses, so
+	 * use the micro misses here and if users want the main TLB misses they
+	 * can use a raw counter.
+	 */
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_DTLB_MISS,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_DTLB_MISS,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_ITLB_MISS,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV6MPCORE_PERFCTR_ITLB_MISS,
 };
 
 static inline unsigned long
@@ -653,9 +476,8 @@ static int armv6_map_event(struct perf_event *event)
 				&armv6_perf_cache_map, 0xFF);
 }
 
-static int armv6pmu_init(struct arm_pmu *cpu_pmu)
+static void armv6pmu_init(struct arm_pmu *cpu_pmu)
 {
-	cpu_pmu->name		= "v6";
 	cpu_pmu->handle_irq	= armv6pmu_handle_irq;
 	cpu_pmu->enable		= armv6pmu_enable_event;
 	cpu_pmu->disable	= armv6pmu_disable_event;
@@ -667,7 +489,26 @@ static int armv6pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->map_event	= armv6_map_event;
 	cpu_pmu->num_events	= 3;
 	cpu_pmu->max_period	= (1LLU << 32) - 1;
+}
+
+static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv6pmu_init(cpu_pmu);
+	cpu_pmu->name		= "armv6_1136";
+	return 0;
+}
 
+static int armv6_1156_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv6pmu_init(cpu_pmu);
+	cpu_pmu->name		= "armv6_1156";
+	return 0;
+}
+
+static int armv6_1176_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv6pmu_init(cpu_pmu);
+	cpu_pmu->name		= "armv6_1176";
 	return 0;
 }
 
@@ -687,7 +528,7 @@ static int armv6mpcore_map_event(struct perf_event *event)
 
 static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	cpu_pmu->name		= "v6mpcore";
+	cpu_pmu->name		= "armv6_11mpcore";
 	cpu_pmu->handle_irq	= armv6pmu_handle_irq;
 	cpu_pmu->enable		= armv6pmu_enable_event;
 	cpu_pmu->disable	= armv6mpcore_pmu_disable_event;
@@ -703,7 +544,17 @@ static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
 	return 0;
 }
 #else
-static int armv6pmu_init(struct arm_pmu *cpu_pmu)
+static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return -ENODEV;
+}
+
+static int armv6_1156_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return -ENODEV;
+}
+
+static int armv6_1176_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	return -ENODEV;
 }
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 1d37568..116758b 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -148,137 +148,62 @@ enum krait_perf_types {
  * accesses/misses in hardware.
  */
 static const unsigned armv7_a8_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
 	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV7_PERFCTR_L1_DCACHE_REFILL,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_PERFCTR_PC_WRITE,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV7_A8_PERFCTR_STALL_ISIDE,
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv7_a8_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					  [PERF_COUNT_HW_CACHE_OP_MAX]
 					  [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		/*
-		 * The performance counters don't differentiate between read
-		 * and write accesses/misses so this isn't strictly correct,
-		 * but it's the best we can do. Writes and reads get
-		 * combined.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A8_PERFCTR_L1_ICACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
-		},
-		[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(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A8_PERFCTR_L2_CACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_A8_PERFCTR_L2_CACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A8_PERFCTR_L2_CACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_A8_PERFCTR_L2_CACHE_REFILL,
-		},
-		[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)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[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,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	/*
+	 * The performance counters don't differentiate between read and write
+	 * accesses/misses so this isn't strictly correct, but it's the best we
+	 * can do. Writes and reads get combined.
+	 */
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_A8_PERFCTR_L1_ICACHE_ACCESS,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+
+	[C(LL)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_A8_PERFCTR_L2_CACHE_ACCESS,
+	[C(LL)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_A8_PERFCTR_L2_CACHE_REFILL,
+	[C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_A8_PERFCTR_L2_CACHE_ACCESS,
+	[C(LL)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_A8_PERFCTR_L2_CACHE_REFILL,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
 /*
  * Cortex-A9 HW events mapping
  */
 static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_A9_PERFCTR_INSTR_CORE_RENAME,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
 	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV7_PERFCTR_L1_DCACHE_REFILL,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_PERFCTR_PC_WRITE,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV7_A9_PERFCTR_STALL_ICACHE,
 	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= ARMV7_A9_PERFCTR_STALL_DISPATCH,
 };
@@ -286,238 +211,83 @@ static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = {
 static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					  [PERF_COUNT_HW_CACHE_OP_MAX]
 					  [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		/*
-		 * The performance counters don't differentiate between read
-		 * and write accesses/misses so this isn't strictly correct,
-		 * but it's the best we can do. Writes and reads get
-		 * combined.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
-		},
-		[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(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)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[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,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	/*
+	 * The performance counters don't differentiate between read and write
+	 * accesses/misses so this isn't strictly correct, but it's the best we
+	 * can do. Writes and reads get combined.
+	 */
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
 /*
  * Cortex-A5 HW events mapping
  */
 static const unsigned armv7_a5_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
 	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV7_PERFCTR_L1_DCACHE_REFILL,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_PERFCTR_PC_WRITE,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-	[PERF_COUNT_HW_BUS_CYCLES]		= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv7_a5_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)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A5_PERFCTR_PREFETCH_LINEFILL,
-			[C(RESULT_MISS)]	= ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		/*
-		 * The prefetch counters don't differentiate between the I
-		 * side and the D side.
-		 */
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A5_PERFCTR_PREFETCH_LINEFILL,
-			[C(RESULT_MISS)]	= ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP,
-		},
-	},
-	[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)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[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,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_PREFETCH)][C(RESULT_ACCESS)]	= ARMV7_A5_PERFCTR_PREFETCH_LINEFILL,
+	[C(L1D)][C(OP_PREFETCH)][C(RESULT_MISS)]	= ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+	/*
+	 * The prefetch counters don't differentiate between the I side and the
+	 * D side.
+	 */
+	[C(L1I)][C(OP_PREFETCH)][C(RESULT_ACCESS)]	= ARMV7_A5_PERFCTR_PREFETCH_LINEFILL,
+	[C(L1I)][C(OP_PREFETCH)][C(RESULT_MISS)]	= ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
 /*
  * Cortex-A15 HW events mapping
  */
 static const unsigned armv7_a15_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
@@ -525,123 +295,48 @@ static const unsigned armv7_a15_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_A15_PERFCTR_PC_WRITE_SPEC,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV7_PERFCTR_BUS_CYCLES,
-	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv7_a15_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)]	= ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_READ,
-			[C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_READ,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_WRITE,
-			[C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_WRITE,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		/*
-		 * Not all performance counters differentiate between read
-		 * and write accesses/misses so we're not always strictly
-		 * correct, but it's the best we can do. Writes and reads get
-		 * combined in these cases.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
-		},
-		[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(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_READ,
-			[C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_L2_CACHE_REFILL_READ,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_WRITE,
-			[C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_L2_CACHE_REFILL_WRITE,
-		},
-		[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)]	= ARMV7_A15_PERFCTR_DTLB_REFILL_L1_READ,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_DTLB_REFILL_L1_WRITE,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[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,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_READ,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_READ,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_WRITE,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_WRITE,
+
+	/*
+	 * Not all performance counters differentiate between read and write
+	 * accesses/misses so we're not always strictly correct, but it's the
+	 * best we can do. Writes and reads get combined in these cases.
+	 */
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+
+	[C(LL)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_READ,
+	[C(LL)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_L2_CACHE_REFILL_READ,
+	[C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_WRITE,
+	[C(LL)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_L2_CACHE_REFILL_WRITE,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_DTLB_REFILL_L1_READ,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_A15_PERFCTR_DTLB_REFILL_L1_WRITE,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
 /*
  * Cortex-A7 HW events mapping
  */
 static const unsigned armv7_a7_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
@@ -649,123 +344,48 @@ static const unsigned armv7_a7_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_PERFCTR_PC_WRITE,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV7_PERFCTR_BUS_CYCLES,
-	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv7_a7_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					[PERF_COUNT_HW_CACHE_OP_MAX]
 					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		/*
-		 * The performance counters don't differentiate between read
-		 * and write accesses/misses so this isn't strictly correct,
-		 * but it's the best we can do. Writes and reads get
-		 * combined.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
-		},
-		[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(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_CACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_CACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
-		},
-		[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)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[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,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	/*
+	 * The performance counters don't differentiate between read and write
+	 * accesses/misses so this isn't strictly correct, but it's the best we
+	 * can do. Writes and reads get combined.
+	 */
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+
+	[C(LL)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_CACHE_ACCESS,
+	[C(LL)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+	[C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_CACHE_ACCESS,
+	[C(LL)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
 /*
  * Cortex-A12 HW events mapping
  */
 static const unsigned armv7_a12_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
@@ -773,138 +393,60 @@ static const unsigned armv7_a12_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_A12_PERFCTR_PC_WRITE_SPEC,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV7_PERFCTR_BUS_CYCLES,
-	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
 };
 
 static const unsigned armv7_a12_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)]	= ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		/*
-		 * Not all performance counters differentiate between read
-		 * and write accesses/misses so we're not always strictly
-		 * correct, but it's the best we can do. Writes and reads get
-		 * combined in these cases.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
-		},
-		[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(LL)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
-		},
-		[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)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_A12_PERFCTR_PF_TLB_REFILL,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[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,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+
+	/*
+	 * Not all performance counters differentiate between read and write
+	 * accesses/misses so we're not always strictly correct, but it's the
+	 * best we can do. Writes and reads get combined in these cases.
+	 */
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+
+	[C(LL)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ,
+	[C(LL)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+	[C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE,
+	[C(LL)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+	[C(DTLB)][C(OP_PREFETCH)][C(RESULT_MISS)]	= ARMV7_A12_PERFCTR_PF_TLB_REFILL,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
 /*
  * Krait HW events mapping
  */
 static const unsigned krait_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV7_PERFCTR_INSTR_EXECUTED,
-	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
 	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 	[PERF_COUNT_HW_BUS_CYCLES]	    = ARMV7_PERFCTR_CLOCK_CYCLES,
 };
 
 static const unsigned krait_perf_map_no_branch[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV7_PERFCTR_INSTR_EXECUTED,
-	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = HW_OP_UNSUPPORTED,
 	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 	[PERF_COUNT_HW_BUS_CYCLES]	    = ARMV7_PERFCTR_CLOCK_CYCLES,
 };
@@ -912,110 +454,31 @@ static const unsigned krait_perf_map_no_branch[PERF_COUNT_HW_MAX] = {
 static const unsigned krait_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 					  [PERF_COUNT_HW_CACHE_OP_MAX]
 					  [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
-	[C(L1D)] = {
-		/*
-		 * The performance counters don't differentiate between read
-		 * and write accesses/misses so this isn't strictly correct,
-		 * but it's the best we can do. Writes and reads get
-		 * combined.
-		 */
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(L1I)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ICACHE_ACCESS,
-			[C(RESULT_MISS)]	= KRAIT_PERFCTR_L1_ICACHE_MISS,
-		},
-		[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(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)]	= KRAIT_PERFCTR_L1_DTLB_ACCESS,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_DTLB_ACCESS,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(ITLB)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ITLB_ACCESS,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ITLB_ACCESS,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(BPU)] = {
-		[C(OP_READ)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_WRITE)] = {
-			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
-			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
-		},
-		[C(OP_PREFETCH)] = {
-			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
-			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
-		},
-	},
-	[C(NODE)] = {
-		[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,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	/*
+	 * The performance counters don't differentiate between read and write
+	 * accesses/misses so this isn't strictly correct, but it's the best we
+	 * can do. Writes and reads get combined.
+	 */
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ICACHE_ACCESS,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= KRAIT_PERFCTR_L1_ICACHE_MISS,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_DTLB_ACCESS,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_DTLB_ACCESS,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ITLB_ACCESS,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ITLB_ACCESS,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
 /*
@@ -1545,7 +1008,7 @@ static u32 armv7_read_num_pmnc_events(void)
 static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A8";
+	cpu_pmu->name		= "armv7_cortex_a8";
 	cpu_pmu->map_event	= armv7_a8_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	return 0;
@@ -1554,7 +1017,7 @@ static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A9";
+	cpu_pmu->name		= "armv7_cortex_a9";
 	cpu_pmu->map_event	= armv7_a9_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	return 0;
@@ -1563,7 +1026,7 @@ static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A5";
+	cpu_pmu->name		= "armv7_cortex_a5";
 	cpu_pmu->map_event	= armv7_a5_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	return 0;
@@ -1572,7 +1035,7 @@ static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A15";
+	cpu_pmu->name		= "armv7_cortex_a15";
 	cpu_pmu->map_event	= armv7_a15_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
@@ -1582,7 +1045,7 @@ static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A7";
+	cpu_pmu->name		= "armv7_cortex_a7";
 	cpu_pmu->map_event	= armv7_a7_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
@@ -1592,7 +1055,7 @@ static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Cortex-A12";
+	cpu_pmu->name		= "armv7_cortex_a12";
 	cpu_pmu->map_event	= armv7_a12_map_event;
 	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
@@ -1602,7 +1065,7 @@ static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
 static int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7_a12_pmu_init(cpu_pmu);
-	cpu_pmu->name = "ARMv7 Cortex-A17";
+	cpu_pmu->name = "armv7_cortex_a17";
 	return 0;
 }
 
@@ -1823,6 +1286,7 @@ static void krait_pmu_disable_event(struct perf_event *event)
 	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	/* Disable counter and interrupt */
@@ -1848,6 +1312,7 @@ static void krait_pmu_enable_event(struct perf_event *event)
 	unsigned long flags;
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
 
 	/*
@@ -1981,7 +1446,7 @@ static void krait_pmu_clear_event_idx(struct pmu_hw_events *cpuc,
 static int krait_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	armv7pmu_init(cpu_pmu);
-	cpu_pmu->name		= "ARMv7 Krait";
+	cpu_pmu->name		= "armv7_krait";
 	/* Some early versions of Krait don't support PC write events */
 	if (of_property_read_bool(cpu_pmu->plat_device->dev.of_node,
 				  "qcom,no-pc-write"))
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 63990c4..08da0af 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -48,118 +48,31 @@ enum xscale_counters {
 };
 
 static const unsigned xscale_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
 	[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,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= XSCALE_PERFCTR_ICACHE_NO_DELIVER,
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= 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)]	= CACHE_OP_UNSUPPORTED,
-		},
-		[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,
-		},
-	},
-	[C(NODE)] = {
-		[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,
-		},
-	},
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= XSCALE_PERFCTR_DCACHE_ACCESS,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= XSCALE_PERFCTR_DCACHE_MISS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= XSCALE_PERFCTR_DCACHE_ACCESS,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= XSCALE_PERFCTR_DCACHE_MISS,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= XSCALE_PERFCTR_ICACHE_MISS,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= XSCALE_PERFCTR_DTLB_MISS,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= XSCALE_PERFCTR_DTLB_MISS,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= XSCALE_PERFCTR_ITLB_MISS,
+	[C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)]	= XSCALE_PERFCTR_ITLB_MISS,
 };
 
 #define	XSCALE_PMU_ENABLE	0x001
@@ -442,7 +355,7 @@ static int xscale_map_event(struct perf_event *event)
 
 static int xscale1pmu_init(struct arm_pmu *cpu_pmu)
 {
-	cpu_pmu->name		= "xscale1";
+	cpu_pmu->name		= "armv5_xscale1";
 	cpu_pmu->handle_irq	= xscale1pmu_handle_irq;
 	cpu_pmu->enable		= xscale1pmu_enable_event;
 	cpu_pmu->disable	= xscale1pmu_disable_event;
@@ -812,7 +725,7 @@ static inline void xscale2pmu_write_counter(struct perf_event *event, u32 val)
 
 static int xscale2pmu_init(struct arm_pmu *cpu_pmu)
 {
-	cpu_pmu->name		= "xscale2";
+	cpu_pmu->name		= "armv5_xscale2";
 	cpu_pmu->handle_irq	= xscale2pmu_handle_irq;
 	cpu_pmu->enable		= xscale2pmu_enable_event;
 	cpu_pmu->disable	= xscale2pmu_disable_event;
diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c
index e6a3c4c..cc649a1 100644
--- a/arch/arm/oprofile/common.c
+++ b/arch/arm/oprofile/common.c
@@ -33,12 +33,14 @@ static struct op_perf_name {
 	char *perf_name;
 	char *op_name;
 } op_perf_name_map[] = {
-	{ "xscale1",		"arm/xscale1"	},
-	{ "xscale1",		"arm/xscale2"	},
-	{ "v6",			"arm/armv6"	},
-	{ "v6mpcore",		"arm/mpcore"	},
-	{ "ARMv7 Cortex-A8",	"arm/armv7"	},
-	{ "ARMv7 Cortex-A9",	"arm/armv7-ca9"	},
+	{ "armv5_xscale1",	"arm/xscale1"	},
+	{ "armv5_xscale2",	"arm/xscale2"	},
+	{ "armv6_1136",		"arm/armv6"	},
+	{ "armv6_1156",		"arm/armv6"	},
+	{ "armv6_1176",		"arm/armv6"	},
+	{ "armv6_11mpcore",	"arm/mpcore"	},
+	{ "armv7_cortex_a8",	"arm/armv7"	},
+	{ "armv7_cortex_a9",	"arm/armv7-ca9"	},
 };
 
 char *op_name_from_perf_id(void)