5.15-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ali Saidi alisaidi@amazon.com
[ Upstream commit 4e6430cbb1a9f1dc0a698f93026b6178da437798 ]
When synthesizing data from SPE, augment the type with source information for Arm Neoverse cores. The field is IMPLDEF but the Neoverse cores all use the same encoding. I can't find encoding information for any other SPE implementations to unify their choices with Arm's thus that is left for future work.
This change populates the mem_lvl_num for Neoverse cores as well as the deprecated mem_lvl namespace.
Reviewed-by: German Gomez german.gomez@arm.com Reviewed-by: Leo Yan leo.yan@linaro.org Signed-off-by: Ali Saidi alisaidi@amazon.com Tested-by: Leo Yan leo.yan@linaro.org Cc: Adrian Hunter adrian.hunter@intel.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Anshuman Khandual anshuman.khandual@arm.com Cc: Gustavo A. R. Silva gustavoars@kernel.org Cc: Ian Rogers irogers@google.com Cc: Ingo Molnar mingo@redhat.com Cc: James Clark james.clark@arm.com Cc: Jiri Olsa jolsa@kernel.org Cc: John Garry john.garry@huawei.com Cc: Kajol Jain kjain@linux.ibm.com Cc: Like Xu likexu@tencent.com Cc: Mark Rutland mark.rutland@arm.com Cc: Mike Leach mike.leach@linaro.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Timothy Hayes timothy.hayes@arm.com Cc: Will Deacon will@kernel.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20220811062451.435810-4-leo.yan@linaro.org Signed-off-by: Leo Yan leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Stable-dep-of: 039fd0634a06 ("perf arm_spe: Correct setting remote access") Signed-off-by: Sasha Levin sashal@kernel.org --- .../util/arm-spe-decoder/arm-spe-decoder.c | 1 + .../util/arm-spe-decoder/arm-spe-decoder.h | 12 ++ tools/perf/util/arm-spe.c | 130 +++++++++++++++--- 3 files changed, 127 insertions(+), 16 deletions(-)
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c index 3fc528c9270c2..3e36934477154 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c @@ -218,6 +218,7 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
break; case ARM_SPE_DATA_SOURCE: + decoder->record.source = payload; break; case ARM_SPE_BAD: break; 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 46a8556a9e956..c3943eb95e305 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h +++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h @@ -29,6 +29,17 @@ enum arm_spe_op_type { ARM_SPE_ST = 1 << 1, };
+enum arm_spe_neoverse_data_source { + ARM_SPE_NV_L1D = 0x0, + ARM_SPE_NV_L2 = 0x8, + ARM_SPE_NV_PEER_CORE = 0x9, + ARM_SPE_NV_LOCAL_CLUSTER = 0xa, + ARM_SPE_NV_SYS_CACHE = 0xb, + ARM_SPE_NV_PEER_CLUSTER = 0xc, + ARM_SPE_NV_REMOTE = 0xd, + ARM_SPE_NV_DRAM = 0xe, +}; + struct arm_spe_record { enum arm_spe_sample_type type; int err; @@ -39,6 +50,7 @@ struct arm_spe_record { u64 virt_addr; u64 phys_addr; u64 context_id; + u16 source; };
struct arm_spe_insn; diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index 569e1b8ad0abc..7b16898af4e7f 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -34,6 +34,7 @@ #include "arm-spe-decoder/arm-spe-decoder.h" #include "arm-spe-decoder/arm-spe-pkt-decoder.h"
+#include "../../arch/arm64/include/asm/cputype.h" #define MAX_TIMESTAMP (~0ULL)
struct arm_spe { @@ -45,6 +46,7 @@ struct arm_spe { struct perf_session *session; struct machine *machine; u32 pmu_type; + u64 midr;
struct perf_tsc_conversion tc;
@@ -312,35 +314,128 @@ static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq, return arm_spe_deliver_synth_event(spe, speq, event, &sample); }
-static u64 arm_spe__synth_data_source(const struct arm_spe_record *record) +static const struct midr_range neoverse_spe[] = { + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1), + {}, +}; + +static void arm_spe__synth_data_source_neoverse(const struct arm_spe_record *record, + union perf_mem_data_src *data_src) { - union perf_mem_data_src data_src = { 0 }; + /* + * Even though four levels of cache hierarchy are possible, no known + * production Neoverse systems currently include more than three levels + * so for the time being we assume three exist. If a production system + * is built with four the this function would have to be changed to + * detect the number of levels for reporting. + */
- if (record->op == ARM_SPE_LD) - data_src.mem_op = PERF_MEM_OP_LOAD; - else if (record->op == ARM_SPE_ST) - data_src.mem_op = PERF_MEM_OP_STORE; - else - return 0; + /* + * We have no data on the hit level or data source for stores in the + * Neoverse SPE records. + */ + if (record->op & ARM_SPE_ST) { + data_src->mem_lvl = PERF_MEM_LVL_NA; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_NA; + data_src->mem_snoop = PERF_MEM_SNOOP_NA; + return; + } + + switch (record->source) { + case ARM_SPE_NV_L1D: + 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; + case ARM_SPE_NV_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_NV_PEER_CORE: + 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; + /* + * We don't know if this is L1, L2 but we do know it was a cache-2-cache + * transfer, so set SNOOPX_PEER + */ + case ARM_SPE_NV_LOCAL_CLUSTER: + case ARM_SPE_NV_PEER_CLUSTER: + data_src->mem_lvl = PERF_MEM_LVL_L3 | PERF_MEM_LVL_HIT; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_L3; + data_src->mem_snoopx = PERF_MEM_SNOOPX_PEER; + break; + /* + * System cache is assumed to be L3 + */ + case ARM_SPE_NV_SYS_CACHE: + 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; + /* + * We don't know what level it hit in, except it came from the other + * socket + */ + case ARM_SPE_NV_REMOTE: + data_src->mem_lvl = PERF_MEM_LVL_REM_CCE1; + 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_NV_DRAM: + 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; + default: + break; + } +}
+static void arm_spe__synth_data_source_generic(const struct arm_spe_record *record, + union perf_mem_data_src *data_src) +{ if (record->type & (ARM_SPE_LLC_ACCESS | ARM_SPE_LLC_MISS)) { - data_src.mem_lvl = PERF_MEM_LVL_L3; + data_src->mem_lvl = PERF_MEM_LVL_L3;
if (record->type & ARM_SPE_LLC_MISS) - data_src.mem_lvl |= PERF_MEM_LVL_MISS; + data_src->mem_lvl |= PERF_MEM_LVL_MISS; else - data_src.mem_lvl |= PERF_MEM_LVL_HIT; + data_src->mem_lvl |= PERF_MEM_LVL_HIT; } else if (record->type & (ARM_SPE_L1D_ACCESS | ARM_SPE_L1D_MISS)) { - data_src.mem_lvl = PERF_MEM_LVL_L1; + data_src->mem_lvl = PERF_MEM_LVL_L1;
if (record->type & ARM_SPE_L1D_MISS) - data_src.mem_lvl |= PERF_MEM_LVL_MISS; + data_src->mem_lvl |= PERF_MEM_LVL_MISS; else - data_src.mem_lvl |= PERF_MEM_LVL_HIT; + data_src->mem_lvl |= PERF_MEM_LVL_HIT; }
if (record->type & ARM_SPE_REMOTE_ACCESS) - data_src.mem_lvl |= PERF_MEM_LVL_REM_CCE1; + data_src->mem_lvl |= PERF_MEM_LVL_REM_CCE1; +} + +static u64 arm_spe__synth_data_source(const struct arm_spe_record *record, u64 midr) +{ + union perf_mem_data_src data_src = { 0 }; + bool is_neoverse = is_midr_in_range(midr, neoverse_spe); + + if (record->op == ARM_SPE_LD) + data_src.mem_op = PERF_MEM_OP_LOAD; + else if (record->op == ARM_SPE_ST) + data_src.mem_op = PERF_MEM_OP_STORE; + else + return 0; + + if (is_neoverse) + arm_spe__synth_data_source_neoverse(record, &data_src); + else + arm_spe__synth_data_source_generic(record, &data_src);
if (record->type & (ARM_SPE_TLB_ACCESS | ARM_SPE_TLB_MISS)) { data_src.mem_dtlb = PERF_MEM_TLB_WK; @@ -361,7 +456,7 @@ static int arm_spe_sample(struct arm_spe_queue *speq) u64 data_src; int err;
- data_src = arm_spe__synth_data_source(record); + data_src = arm_spe__synth_data_source(record, spe->midr);
if (spe->sample_flc) { if (record->type & ARM_SPE_L1D_MISS) { @@ -1047,6 +1142,8 @@ int arm_spe_process_auxtrace_info(union perf_event *event, struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info; size_t min_sz = sizeof(u64) * ARM_SPE_AUXTRACE_PRIV_MAX; struct perf_record_time_conv *tc = &session->time_conv; + const char *cpuid = perf_env__cpuid(session->evlist->env); + u64 midr = strtol(cpuid, NULL, 16); struct arm_spe *spe; int err;
@@ -1066,6 +1163,7 @@ int arm_spe_process_auxtrace_info(union perf_event *event, spe->machine = &session->machines.host; /* No kvm support */ spe->auxtrace_type = auxtrace_info->type; spe->pmu_type = auxtrace_info->priv[ARM_SPE_PMU_TYPE]; + spe->midr = midr;
spe->timeless_decoding = arm_spe__is_timeless_decoding(spe);