summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYicong Yang <yangyicong@hisilicon.com>2025-04-25 11:38:44 +0800
committerArnaldo Carvalho de Melo <acme@redhat.com>2025-05-27 17:57:58 -0300
commit846b62b3433d2e87018576ab386f7a96390f66e4 (patch)
tree53bf267d65b7792c5c24de1abe41404767cb94c1
parent628e124404b3db5e10e17228e680a2999018ab33 (diff)
perf arm-spe: Add support for SPE Data Source packet on HiSilicon HIP12
Add data source encoding for HiSilicon HIP12 and coresponding mapping to the perf's memory data source. This will help to synthesize the data and support upper layer tools like perf-mem and perf-c2c. Reviewed-by: Leo Yan <leo.yan@arm.com> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Cc: CaiJingtao <caijingtao@huawei.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@linaro.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Jonathan Cameron <jonathan.cameron@huawei.com> Cc: Junhao He <hejunhao3@huawei.com> Cc: Leo Yan <leo.yan@linux.dev> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Will Deacon <will@kernel.org> Cc: Yushan Wang <wangyushan12@huawei.com> Cc: Zeng Tao <prime.zeng@hisilicon.com> Cc: xueshan2@huawei.com Link: https://lore.kernel.org/r/20250425033845.57671-3-yangyicong@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
-rw-r--r--tools/arch/arm64/include/asm/cputype.h2
-rw-r--r--tools/perf/util/arm-spe-decoder/arm-spe-decoder.h17
-rw-r--r--tools/perf/util/arm-spe.c96
3 files changed, 115 insertions, 0 deletions
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
index 488f8e751349..9a5d85cfd1fb 100644
--- a/tools/arch/arm64/include/asm/cputype.h
+++ b/tools/arch/arm64/include/asm/cputype.h
@@ -129,6 +129,7 @@
#define FUJITSU_CPU_PART_A64FX 0x001
#define HISI_CPU_PART_TSV110 0xD01
+#define HISI_CPU_PART_HIP12 0xD06
#define APPLE_CPU_PART_M1_ICESTORM 0x022
#define APPLE_CPU_PART_M1_FIRESTORM 0x023
@@ -202,6 +203,7 @@
#define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
#define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX)
#define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110)
+#define MIDR_HISI_HIP12 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_HIP12)
#define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM)
#define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM)
#define MIDR_APPLE_M1_ICESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_PRO)
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
index 5d232188643b..881d9f29c138 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
@@ -82,6 +82,23 @@ enum arm_spe_ampereone_data_source {
ARM_SPE_AMPEREONE_L2D = 0x9,
};
+enum arm_spe_hisi_hip_data_source {
+ ARM_SPE_HISI_HIP_PEER_CPU = 0,
+ ARM_SPE_HISI_HIP_PEER_CPU_HITM = 1,
+ ARM_SPE_HISI_HIP_L3 = 2,
+ ARM_SPE_HISI_HIP_L3_HITM = 3,
+ ARM_SPE_HISI_HIP_PEER_CLUSTER = 4,
+ ARM_SPE_HISI_HIP_PEER_CLUSTER_HITM = 5,
+ ARM_SPE_HISI_HIP_REMOTE_SOCKET = 6,
+ ARM_SPE_HISI_HIP_REMOTE_SOCKET_HITM = 7,
+ ARM_SPE_HISI_HIP_LOCAL_MEM = 8,
+ ARM_SPE_HISI_HIP_REMOTE_MEM = 9,
+ ARM_SPE_HISI_HIP_NC_DEV = 13,
+ ARM_SPE_HISI_HIP_L2 = 16,
+ ARM_SPE_HISI_HIP_L2_HITM = 17,
+ ARM_SPE_HISI_HIP_L1 = 18,
+};
+
struct arm_spe_record {
enum arm_spe_sample_type type;
int err;
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index 2a9775649cc2..d46e0cccac99 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -571,6 +571,11 @@ static const struct midr_range ampereone_ds_encoding_cpus[] = {
{},
};
+static const struct midr_range hisi_hip_ds_encoding_cpus[] = {
+ MIDR_ALL_VERSIONS(MIDR_HISI_HIP12),
+ {},
+};
+
static void arm_spe__sample_flags(struct arm_spe_queue *speq)
{
const struct arm_spe_record *record = &speq->decoder->record;
@@ -718,9 +723,100 @@ static void arm_spe__synth_data_source_ampereone(const struct arm_spe_record *re
arm_spe__synth_data_source_common(&common_record, data_src);
}
+static void arm_spe__synth_data_source_hisi_hip(const struct arm_spe_record *record,
+ union perf_mem_data_src *data_src)
+{
+ /* Use common synthesis method to handle store operations */
+ if (record->op & ARM_SPE_OP_ST) {
+ arm_spe__synth_data_source_common(record, data_src);
+ return;
+ }
+
+ switch (record->source) {
+ case ARM_SPE_HISI_HIP_PEER_CPU:
+ data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2;
+ data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
+ break;
+ case ARM_SPE_HISI_HIP_PEER_CPU_HITM:
+ data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2;
+ data_src->mem_snoop = PERF_MEM_SNOOP_HITM;
+ data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
+ break;
+ case ARM_SPE_HISI_HIP_L3:
+ data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_HIT;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3;
+ data_src->mem_snoop = PERF_MEM_SNOOP_HIT;
+ break;
+ case ARM_SPE_HISI_HIP_L3_HITM:
+ data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_HIT;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3;
+ data_src->mem_snoop = PERF_MEM_SNOOP_HITM;
+ break;
+ case ARM_SPE_HISI_HIP_PEER_CLUSTER:
+ data_src->mem_lvl = PERF_MEM_LVL_REM_CCE1 | PERF_MEM_LVL_HIT;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3;
+ data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
+ break;
+ case ARM_SPE_HISI_HIP_PEER_CLUSTER_HITM:
+ data_src->mem_lvl = PERF_MEM_LVL_REM_CCE1 | PERF_MEM_LVL_HIT;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3;
+ data_src->mem_snoop = PERF_MEM_SNOOP_HITM;
+ data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
+ break;
+ case ARM_SPE_HISI_HIP_REMOTE_SOCKET:
+ data_src->mem_lvl = PERF_MEM_LVL_REM_CCE2;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_ANY_CACHE;
+ data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
+ data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
+ break;
+ case ARM_SPE_HISI_HIP_REMOTE_SOCKET_HITM:
+ data_src->mem_lvl = PERF_MEM_LVL_REM_CCE2;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_ANY_CACHE;
+ data_src->mem_snoop = PERF_MEM_SNOOP_HITM;
+ data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
+ data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER;
+ break;
+ case ARM_SPE_HISI_HIP_LOCAL_MEM:
+ data_src->mem_lvl = PERF_MEM_LVL_LOC_RAM | PERF_MEM_LVL_HIT;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_RAM;
+ data_src->mem_snoop = PERF_MEM_SNOOP_NONE;
+ break;
+ case ARM_SPE_HISI_HIP_REMOTE_MEM:
+ data_src->mem_lvl = PERF_MEM_LVL_REM_RAM1 | PERF_MEM_LVL_HIT;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_RAM;
+ data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
+ break;
+ case ARM_SPE_HISI_HIP_NC_DEV:
+ data_src->mem_lvl = PERF_MEM_LVL_IO | PERF_MEM_LVL_HIT;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_IO;
+ data_src->mem_snoop = PERF_MEM_SNOOP_NONE;
+ break;
+ case ARM_SPE_HISI_HIP_L2:
+ data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2;
+ data_src->mem_snoop = PERF_MEM_SNOOP_NONE;
+ break;
+ case ARM_SPE_HISI_HIP_L2_HITM:
+ data_src->mem_lvl = PERF_MEM_LVL_L2 | PERF_MEM_LVL_HIT;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_L2;
+ data_src->mem_snoop = PERF_MEM_SNOOP_HITM;
+ break;
+ case ARM_SPE_HISI_HIP_L1:
+ data_src->mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_L1;
+ data_src->mem_snoop = PERF_MEM_SNOOP_NONE;
+ break;
+ default:
+ break;
+ }
+}
+
static const struct data_source_handle data_source_handles[] = {
DS(common_ds_encoding_cpus, data_source_common),
DS(ampereone_ds_encoding_cpus, data_source_ampereone),
+ DS(hisi_hip_ds_encoding_cpus, data_source_hisi_hip),
};
static void arm_spe__synth_memory_level(const struct arm_spe_record *record,