[PATCH v8 09/21] drivers/perf: apple_m1: Add Apple A8/A8X support

[Nick Chan <towinchenmi@gmail.com>]

Add support for the CPU PMU found on the Apple A8, A8X SoCs.

Tested-by: Ivaylo Ivanov <ivo.ivanov.ivanov1@gmail.com>
Signed-off-by: Nick Chan <towinchenmi@gmail.com>
---
 drivers/perf/apple_m1_cpu_pmu.c | 124 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 124 insertions(+)

diff --git a/drivers/perf/apple_m1_cpu_pmu.c b/drivers/perf/apple_m1_cpu_pmu.c
index afcf7c951379698ceff21c1a99cca31b3a6177b1..a95f4b717857b30284470487827954dd4b139010 100644
--- a/drivers/perf/apple_m1_cpu_pmu.c
+++ b/drivers/perf/apple_m1_cpu_pmu.c
@@ -28,6 +28,7 @@
 #define ANY_BUT_0_1			GENMASK(9, 2)
 #define ONLY_2_TO_7			GENMASK(7, 2)
 #define ONLY_2_4_6			(BIT(2) | BIT(4) | BIT(6))
+#define ONLY_3_5_7			(BIT(3) | BIT(5) | BIT(7))
 #define ONLY_5_6_7			(BIT(5) | BIT(6) | BIT(7))
 
 /*
@@ -183,6 +184,111 @@ static const u16 a7_pmu_event_affinity[A7_PMU_PERFCTR_LAST + 1] = {
 	[A7_PMU_PERFCTR_UNKNOWN_fd]				= ONLY_2_4_6,
 };
 
+enum a8_pmu_events {
+	A8_PMU_PERFCTR_UNKNOWN_1				= 0x1,
+	A8_PMU_PERFCTR_CORE_ACTIVE_CYCLE			= 0x2,
+	A8_PMU_PERFCTR_L2_TLB_MISS_INSTRUCTION			= 0xa,
+	A8_PMU_PERFCTR_L2_TLB_MISS_DATA				= 0xb,
+	A8_PMU_PERFCTR_BIU_UPSTREAM_CYCLE			= 0x13,
+	A8_PMU_PERFCTR_BIU_DOWNSTREAM_CYCLE			= 0x14,
+	A8_PMU_PERFCTR_L2C_AGENT_LD				= 0x1a,
+	A8_PMU_PERFCTR_L2C_AGENT_LD_MISS			= 0x1b,
+	A8_PMU_PERFCTR_L2C_AGENT_ST				= 0x1c,
+	A8_PMU_PERFCTR_L2C_AGENT_ST_MISS			= 0x1d,
+	A8_PMU_PERFCTR_SCHEDULE_UOP				= 0x52,
+	A8_PMU_PERFCTR_MAP_REWIND				= 0x75,
+	A8_PMU_PERFCTR_MAP_STALL				= 0x76,
+	A8_PMU_PERFCTR_MAP_INT_UOP				= 0x7b,
+	A8_PMU_PERFCTR_MAP_LDST_UOP				= 0x7c,
+	A8_PMU_PERFCTR_MAP_SIMD_UOP				= 0x7d,
+	A8_PMU_PERFCTR_FLUSH_RESTART_OTHER_NONSPEC		= 0x84,
+	A8_PMU_PERFCTR_INST_A32					= 0x8a,
+	A8_PMU_PERFCTR_INST_T32					= 0x8b,
+	A8_PMU_PERFCTR_INST_ALL					= 0x8c,
+	A8_PMU_PERFCTR_INST_BRANCH				= 0x8d,
+	A8_PMU_PERFCTR_INST_BRANCH_CALL				= 0x8e,
+	A8_PMU_PERFCTR_INST_BRANCH_RET				= 0x8f,
+	A8_PMU_PERFCTR_INST_BRANCH_TAKEN			= 0x90,
+	A8_PMU_PERFCTR_INST_BRANCH_INDIR			= 0x93,
+	A8_PMU_PERFCTR_INST_BRANCH_COND				= 0x94,
+	A8_PMU_PERFCTR_INST_INT_LD				= 0x95,
+	A8_PMU_PERFCTR_INST_INT_ST				= 0x96,
+	A8_PMU_PERFCTR_INST_INT_ALU				= 0x97,
+	A8_PMU_PERFCTR_INST_SIMD_LD				= 0x98,
+	A8_PMU_PERFCTR_INST_SIMD_ST				= 0x99,
+	A8_PMU_PERFCTR_INST_SIMD_ALU				= 0x9a,
+	A8_PMU_PERFCTR_INST_LDST				= 0x9b,
+	A8_PMU_PERFCTR_UNKNOWN_9c				= 0x9c,
+	A8_PMU_PERFCTR_UNKNOWN_9f				= 0x9f,
+	A8_PMU_PERFCTR_L1D_TLB_ACCESS				= 0xa0,
+	A8_PMU_PERFCTR_L1D_TLB_MISS				= 0xa1,
+	A8_PMU_PERFCTR_L1D_CACHE_MISS_ST			= 0xa2,
+	A8_PMU_PERFCTR_L1D_CACHE_MISS_LD			= 0xa3,
+	A8_PMU_PERFCTR_LD_UNIT_UOP				= 0xa6,
+	A8_PMU_PERFCTR_ST_UNIT_UOP				= 0xa7,
+	A8_PMU_PERFCTR_L1D_CACHE_WRITEBACK			= 0xa8,
+	A8_PMU_PERFCTR_LDST_X64_UOP				= 0xb1,
+	A8_PMU_PERFCTR_L1D_CACHE_MISS_LD_NONSPEC		= 0xbf,
+	A8_PMU_PERFCTR_L1D_CACHE_MISS_ST_NONSPEC		= 0xc0,
+	A8_PMU_PERFCTR_L1D_TLB_MISS_NONSPEC			= 0xc1,
+	A8_PMU_PERFCTR_ST_MEMORY_ORDER_VIOLATION_NONSPEC	= 0xc4,
+	A8_PMU_PERFCTR_BRANCH_COND_MISPRED_NONSPEC		= 0xc5,
+	A8_PMU_PERFCTR_BRANCH_INDIR_MISPRED_NONSPEC		= 0xc6,
+	A8_PMU_PERFCTR_BRANCH_RET_INDIR_MISPRED_NONSPEC		= 0xc8,
+	A8_PMU_PERFCTR_BRANCH_CALL_INDIR_MISPRED_NONSPEC	= 0xca,
+	A8_PMU_PERFCTR_BRANCH_MISPRED_NONSPEC			= 0xcb,
+	A8_PMU_PERFCTR_FED_IC_MISS_DEMAND			= 0xd3,
+	A8_PMU_PERFCTR_L1I_TLB_MISS_DEMAND			= 0xd4,
+	A8_PMU_PERFCTR_FETCH_RESTART				= 0xde,
+	A8_PMU_PERFCTR_UNKNOWN_f5				= 0xf5,
+	A8_PMU_PERFCTR_UNKNOWN_f6				= 0xf6,
+	A8_PMU_PERFCTR_UNKNOWN_f7				= 0xf7,
+	A8_PMU_PERFCTR_LAST					= M1_PMU_CFG_EVENT,
+
+	/*
+	 * From this point onwards, these are not actual HW events,
+	 * but attributes that get stored in hw->config_base.
+	 */
+	A8_PMU_CFG_COUNT_USER					= BIT(8),
+	A8_PMU_CFG_COUNT_KERNEL					= BIT(9),
+};
+
+static const u16 a8_pmu_event_affinity[A8_PMU_PERFCTR_LAST + 1] = {
+	[0 ... A8_PMU_PERFCTR_LAST]				= ANY_BUT_0_1,
+	[A8_PMU_PERFCTR_UNKNOWN_1]				= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_CORE_ACTIVE_CYCLE]			= ANY_BUT_0_1 | BIT(0),
+	[A8_PMU_PERFCTR_INST_A32]				= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_INST_T32]				= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_INST_ALL]				= BIT(7) | BIT(1),
+	[A8_PMU_PERFCTR_INST_BRANCH]				= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_INST_BRANCH_CALL]			= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_INST_BRANCH_RET]			= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_INST_BRANCH_TAKEN]			= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_INST_BRANCH_INDIR]			= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_INST_BRANCH_COND]			= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_INST_INT_LD]				= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_INST_INT_ST]				= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_INST_INT_ALU]				= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_INST_SIMD_LD]				= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_INST_SIMD_ST]				= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_INST_SIMD_ALU]				= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_INST_LDST]				= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_UNKNOWN_9c]				= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_UNKNOWN_9f]				= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_L1D_CACHE_MISS_LD_NONSPEC]		= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_L1D_CACHE_MISS_ST_NONSPEC]		= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_L1D_TLB_MISS_NONSPEC]			= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_ST_MEMORY_ORDER_VIOLATION_NONSPEC]	= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_BRANCH_COND_MISPRED_NONSPEC]		= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_BRANCH_INDIR_MISPRED_NONSPEC]		= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_BRANCH_RET_INDIR_MISPRED_NONSPEC]	= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_BRANCH_CALL_INDIR_MISPRED_NONSPEC]	= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_BRANCH_MISPRED_NONSPEC]			= ONLY_5_6_7,
+	[A8_PMU_PERFCTR_UNKNOWN_f5]				= ANY_BUT_0_1,
+	[A8_PMU_PERFCTR_UNKNOWN_f6]				= ONLY_3_5_7,
+	[A8_PMU_PERFCTR_UNKNOWN_f7]				= ONLY_3_5_7,
+};
+
 enum m1_pmu_events {
 	M1_PMU_PERFCTR_RETIRE_UOP				= 0x1,
 	M1_PMU_PERFCTR_CORE_ACTIVE_CYCLE			= 0x2,
@@ -684,6 +790,12 @@ static int a7_pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	return apple_pmu_get_event_idx(cpuc, event, a7_pmu_event_affinity);
 }
 
+static int a8_pmu_get_event_idx(struct pmu_hw_events *cpuc,
+				struct perf_event *event)
+{
+	return apple_pmu_get_event_idx(cpuc, event, a8_pmu_event_affinity);
+}
+
 static int m1_pmu_get_event_idx(struct pmu_hw_events *cpuc,
 				struct perf_event *event)
 {
@@ -862,6 +974,17 @@ static int a7_pmu_cyclone_init(struct arm_pmu *cpu_pmu)
 	return apple_pmu_init(cpu_pmu, A7_PMU_NR_COUNTERS);
 }
 
+static int a8_pmu_typhoon_init(struct arm_pmu *cpu_pmu)
+{
+	cpu_pmu->name = "apple_typhoon_pmu";
+	cpu_pmu->get_event_idx	  = a8_pmu_get_event_idx;
+	cpu_pmu->map_event	  = m1_pmu_map_event;
+	cpu_pmu->reset		  = a7_pmu_reset;
+	cpu_pmu->start		  = a7_pmu_start;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = &m1_pmu_events_attr_group;
+	return apple_pmu_init(cpu_pmu, A7_PMU_NR_COUNTERS);
+}
+
 static int m1_pmu_ice_init(struct arm_pmu *cpu_pmu)
 {
 	cpu_pmu->name = "apple_icestorm_pmu";
@@ -911,6 +1034,7 @@ static const struct of_device_id m1_pmu_of_device_ids[] = {
 	{ .compatible = "apple,blizzard-pmu",	.data = m2_pmu_blizzard_init, },
 	{ .compatible = "apple,icestorm-pmu",	.data = m1_pmu_ice_init, },
 	{ .compatible = "apple,firestorm-pmu",	.data = m1_pmu_fire_init, },
+	{ .compatible = "apple,typhoon-pmu",	.data = a8_pmu_typhoon_init, },
 	{ .compatible = "apple,cyclone-pmu",	.data = a7_pmu_cyclone_init, },
 	{ },
 };

-- 
2.50.1