From cf20ae8cfcb3ab4013b7766abe22d251c99fee15 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 30 May 2014 17:46:13 +0100 Subject: [PATCH] arm: perf: armv6: condense event maps Now that we have macros for declaring fully invalid event maps, put them to work for all the ARMv6 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. Acked-by: Will Deacon Signed-off-by: Mark Rutland Signed-off-by: Will Deacon --- arch/arm/kernel/perf_event_v6.c | 271 ++++++-------------------------- 1 file changed, 47 insertions(+), 224 deletions(-) diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c index 03664b0e8fa4..0fd4290f911f 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 -- 2.20.1