ARM: 7117/1: perf: fix HW_CACHE_* events on Cortex-A9

Using COHERENT_LINE_{MISS,HIT} for cache misses and references
respectively is completely wrong. Instead, use the L1D events which
are a better and more useful approximation despite ignoring instruction
traffic.

Reported-by: Alasdair Grant <alasdair.grant@arm.com>
Reported-by: Matt Horsnell <matt.horsnell@arm.com>
Reported-by: Michael Williams <michael.williams@arm.com>
Cc: stable@kernel.org
Cc: Jean Pihet <j-pihet@ti.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/kernel/perf_event_v7.c

@@ -321,8 +321,8 @@ static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV7_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]	    =
 					ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE,
-	[PERF_COUNT_HW_CACHE_REFERENCES]    = ARMV7_PERFCTR_COHERENT_LINE_HIT,
-	[PERF_COUNT_HW_CACHE_MISSES]	    = ARMV7_PERFCTR_COHERENT_LINE_MISS,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = ARMV7_PERFCTR_DCACHE_ACCESS,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = ARMV7_PERFCTR_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]	    = ARMV7_PERFCTR_CLOCK_CYCLES,