ARM: perf: add support for the Cortex-A12 PMU

Cortex-A12 implements Performance Monitors compliant with the PMUv2
architecture.

This patch adds support for the Cortex-A12 PMU to the ARM perf backend.

Signed-off-by: Albin Tonnerre <albin.tonnerre@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

diff --git a/Documentation/devicetree/bindings/arm/pmu.txt b/Documentation/devicetree/bindings/arm/pmu.txt
index ce731441e64fcda32aaba17e3c1817967bb84a23..fe5cef8976cb0724833b292ab17d25fa779423c5 100644 (file)
--- a/Documentation/devicetree/bindings/arm/pmu.txt
+++ b/Documentation/devicetree/bindings/arm/pmu.txt
@@ -9,6 +9,7 @@ Required properties:
 - compatible : should be one of
        "arm,armv8-pmuv3"
        "arm,cortex-a15-pmu"
+       "arm,cortex-a12-pmu"
        "arm,cortex-a9-pmu"
        "arm,cortex-a8-pmu"
        "arm,cortex-a7-pmu"

diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 326cb58de2f8ced39ae2502c755da5c81ef9da54..51798d7854aca9b9109abba97c1cc22a6efc5a33 100644 (file)
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -222,6 +222,7 @@ static struct notifier_block cpu_pmu_hotplug_notifier = {
  */
 static struct of_device_id cpu_pmu_of_device_ids[] = {
        {.compatible = "arm,cortex-a15-pmu",    .data = armv7_a15_pmu_init},
+       {.compatible = "arm,cortex-a12-pmu",    .data = armv7_a12_pmu_init},
        {.compatible = "arm,cortex-a9-pmu",     .data = armv7_a9_pmu_init},
        {.compatible = "arm,cortex-a8-pmu",     .data = armv7_a8_pmu_init},
        {.compatible = "arm,cortex-a7-pmu",     .data = armv7_a7_pmu_init},

diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 2fce4751f4c0bdf2e243fd87dfd032c2fb0a01f3..f4ef3981ed0293a6ebcc887cf3428e8c848294ca 100644 (file)
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -113,6 +113,19 @@ enum armv7_a15_perf_types {
        ARMV7_A15_PERFCTR_PC_WRITE_SPEC                 = 0x76,
 };
 
+/* ARMv7 Cortex-A12 specific event types */
+enum armv7_a12_perf_types {
+       ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ         = 0x40,
+       ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE        = 0x41,
+
+       ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ          = 0x50,
+       ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE         = 0x51,
+
+       ARMV7_A12_PERFCTR_PC_WRITE_SPEC                 = 0x76,
+
+       ARMV7_A12_PERFCTR_PF_TLB_REFILL                 = 0xe7,
+};
+
 /* ARMv7 Krait specific event types */
 enum krait_perf_types {
        KRAIT_PMRESR0_GROUP0                            = 0xcc,
@@ -749,6 +762,130 @@ static const unsigned armv7_a7_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
        },
 };
 
+/*
+ * Cortex-A12 HW events mapping
+ */
+static const unsigned armv7_a12_perf_map[PERF_COUNT_HW_MAX] = {
+       [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_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,
+               },
+       },
+};
+
 /*
  * Krait HW events mapping
  */
@@ -1362,6 +1499,12 @@ static int armv7_a7_map_event(struct perf_event *event)
                                &armv7_a7_perf_cache_map, 0xFF);
 }
 
+static int armv7_a12_map_event(struct perf_event *event)
+{
+       return armpmu_map_event(event, &armv7_a12_perf_map,
+                               &armv7_a12_perf_cache_map, 0xFF);
+}
+
 static int krait_map_event(struct perf_event *event)
 {
        return armpmu_map_event(event, &krait_perf_map,
@@ -1446,6 +1589,16 @@ static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
        return 0;
 }
 
+static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
+{
+       armv7pmu_init(cpu_pmu);
+       cpu_pmu->name           = "ARMv7 Cortex-A12";
+       cpu_pmu->map_event      = armv7_a12_map_event;
+       cpu_pmu->num_events     = armv7_read_num_pmnc_events();
+       cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
+       return 0;
+}
+
 /*
  * Krait Performance Monitor Region Event Selection Register (PMRESRn)
  *
@@ -1863,6 +2016,11 @@ static inline int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
        return -ENODEV;
 }
 
+static inline int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
+{
+       return -ENODEV;
+}
+
 static inline int krait_pmu_init(struct arm_pmu *cpu_pmu)
 {
        return -ENODEV;