[PATCH 3/8] arm: perf: armv7: condense event maps
Mark Rutland
mark.rutland at arm.com
Tue Jul 1 08:11:13 PDT 2014
Now that we have macros for declaring fully invalid event maps, put them
to work for all the ARMv7 PMU event maps. While this necessitates
repeating common indices, we no longer need to refer to *_UNSUPPORTED
events at all, and it makes it possible for the even maps to fit on a
single page on a reasonably sized monitor.
Signed-off-by: Mark Rutland <mark.rutland at arm.com>
Acked-by: Will Deacon <will.deacon at arm.com>
---
arch/arm/kernel/perf_event_v7.c | 949 +++++++++-------------------------------
1 file changed, 206 insertions(+), 743 deletions(-)
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 1d37568..871c465 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,
};
/*
--
1.9.1
More information about the linux-arm-kernel
mailing list