[RFC PATCH 2/5] arm64/perf: Add Cavium ThunderX PMU support

[Jan Glauber]

Support PMU events on Caviums ThunderX SOC. ThunderX supports
some additional counters compared to the default ARMv8 PMUv3:

- branch instructions counter
- stall frontend & backend counters
- L1 dcache load & store counters
- L1 icache counters
- iTLB & dTLB counters
- L1 dcache & icache prefetch counters

Signed-off-by: Jan Glauber <jglauber@xxxxxxxxxx>
---
 arch/arm64/kernel/perf_event.c | 69 +++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 68 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 32fe656..cf2cc39 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -94,10 +94,19 @@
 #define ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL_ST			0x43
 #define ARMV8_PMUV3_PERFCTR_DTLB_REFILL_LD			0x4C
 #define ARMV8_PMUV3_PERFCTR_DTLB_REFILL_ST			0x4D
+#define ARMV8_PMUV3_PERFCTR_DTLB_ACCESS_LD			0x4E
+#define ARMV8_PMUV3_PERFCTR_DTLB_ACCESS_ST			0x4F
 
 /* ARMv8 Cortex-A53 specific event types. */
 #define ARMV8_A53_PERFCTR_PREFETCH_LINEFILL			0xC2
 
+/* ARMv8 Cavium ThunderX specific event types. */
+#define ARMV8_THUNDERX_PERFCTR_L1_DCACHE_MISS_ST		0xE9
+#define ARMV8_THUNDERX_PERFCTR_L1_DCACHE_PREF_ACCESS		0xEA
+#define ARMV8_THUNDERX_PERFCTR_L1_DCACHE_PREF_MISS		0xEB
+#define ARMV8_THUNDERX_PERFCTR_L1_ICACHE_PREF_ACCESS		0xEC
+#define ARMV8_THUNDERX_PERFCTR_L1_ICACHE_PREF_MISS		0xED
+
 /* PMUv3 HW events mapping. */
 static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
 	PERF_MAP_ALL_UNSUPPORTED,
@@ -131,6 +140,18 @@ static const unsigned armv8_a57_perf_map[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
 };
 
+static const unsigned armv8_thunderx_perf_map[PERF_COUNT_HW_MAX] = {
+	PERF_MAP_ALL_UNSUPPORTED,
+	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS,
+	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV8_PMUV3_PERFCTR_PC_WRITE,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV8_PMUV3_PERFCTR_STALL_FRONTEND,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= ARMV8_PMUV3_PERFCTR_STALL_BACKEND,
+};
+
 static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 						[PERF_COUNT_HW_CACHE_OP_MAX]
 						[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
@@ -193,6 +214,36 @@ static const unsigned armv8_a57_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
 };
 
+static const unsigned armv8_thunderx_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+						   [PERF_COUNT_HW_CACHE_OP_MAX]
+						   [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+	[C(L1D)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS_LD,
+	[C(L1D)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL_LD,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS_ST,
+	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_THUNDERX_PERFCTR_L1_DCACHE_MISS_ST,
+	[C(L1D)][C(OP_PREFETCH)][C(RESULT_ACCESS)] = ARMV8_THUNDERX_PERFCTR_L1_DCACHE_PREF_ACCESS,
+	[C(L1D)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_THUNDERX_PERFCTR_L1_DCACHE_PREF_MISS,
+
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL,
+	[C(L1I)][C(OP_PREFETCH)][C(RESULT_ACCESS)] = ARMV8_THUNDERX_PERFCTR_L1_ICACHE_PREF_ACCESS,
+	[C(L1I)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_THUNDERX_PERFCTR_L1_ICACHE_PREF_MISS,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_DTLB_ACCESS_LD,
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_DTLB_REFILL_LD,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_DTLB_ACCESS_ST,
+	[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_DTLB_REFILL_ST,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_ITLB_REFILL,
+
+	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED,
+	[C(BPU)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED,
+};
+
 #define ARMV8_EVENT_ATTR_RESOLVE(m) #m
 #define ARMV8_EVENT_ATTR(name, config) \
 	PMU_EVENT_ATTR_STRING(name, armv8_event_attr_##name, \
@@ -324,7 +375,6 @@ static const struct attribute_group *armv8_pmuv3_attr_groups[] = {
 	NULL,
 };
 
-
 /*
  * Perf Events' indices
  */
@@ -743,6 +793,13 @@ static int armv8_a57_map_event(struct perf_event *event)
 				ARMV8_EVTYPE_EVENT);
 }
 
+static int armv8_thunderx_map_event(struct perf_event *event)
+{
+	return armpmu_map_event(event, &armv8_thunderx_perf_map,
+				&armv8_thunderx_perf_cache_map,
+				ARMV8_EVTYPE_EVENT);
+}
+
 static void armv8pmu_read_num_pmnc_events(void *info)
 {
 	int *nb_cnt = info;
@@ -811,11 +868,21 @@ static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
 	return armv8pmu_probe_num_events(cpu_pmu);
 }
 
+static int armv8_thunderx_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv8_pmu_init(cpu_pmu);
+	cpu_pmu->name			= "armv8_cavium_thunderx";
+	cpu_pmu->map_event		= armv8_thunderx_map_event;
+	cpu_pmu->pmu.attr_groups	= armv8_pmuv3_attr_groups;
+	return armv8pmu_probe_num_events(cpu_pmu);
+}
+
 static const struct of_device_id armv8_pmu_of_device_ids[] = {
 	{.compatible = "arm,armv8-pmuv3",	.data = armv8_pmuv3_init},
 	{.compatible = "arm,cortex-a53-pmu",	.data = armv8_a53_pmu_init},
 	{.compatible = "arm,cortex-a57-pmu",	.data = armv8_a57_pmu_init},
 	{.compatible = "arm,cortex-a72-pmu",	.data = armv8_a72_pmu_init},
+	{.compatible = "cavium,thunderx-pmu",	.data = armv8_thunderx_pmu_init},
 	{},
 };
 
-- 
1.9.1