perf arm-spe: Add SPE total latency as PERF_SAMPLE_WEIGHT

Use total latency info in the SPE counter packet as sample weight so
that we can see it in local_weight and (global) weight sort keys.

Maybe we can use PERF_SAMPLE_WEIGHT_STRUCT to support ins_lat as well
but I'm not sure which latency it matches.  So just adding total latency
first.

Reviewed-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: German Gomez <german.gomez@arm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211201220855.1260688-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

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 3fc528c9270c2b196d9837eaaefa684395bfafd3..5e390a1a79abfd09516d6c18a926adea22fd761a 100644 (file)
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
@@ -179,6 +179,8 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
                                decoder->record.phys_addr = ip;
                        break;
                case ARM_SPE_COUNTER:
+                       if (idx == SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT)
+                               decoder->record.latency = payload;
                        break;
                case ARM_SPE_CONTEXT:
                        decoder->record.context_id = payload;

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 46a8556a9e956a313cb81afbb1cc72c098f532ff..69b31084d6be58a53482521af7f646fa158a9ec4 100644 (file)
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
@@ -33,6 +33,7 @@ struct arm_spe_record {
        enum arm_spe_sample_type type;
        int err;
        u32 op;
+       u32 latency;
        u64 from_ip;
        u64 to_ip;
        u64 timestamp;

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index fccac06b573a8f221f81c8b254fbf24877594c73..8a3828f86901a01d85705c84e0c0fb465e1691df 100644 (file)
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -330,6 +330,7 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq,
        sample.addr = record->virt_addr;
        sample.phys_addr = record->phys_addr;
        sample.data_src = data_src;
+       sample.weight = record->latency;
 
        return arm_spe_deliver_synth_event(spe, speq, event, &sample);
 }
@@ -347,6 +348,7 @@ static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq,
        sample.id = spe_events_id;
        sample.stream_id = spe_events_id;
        sample.addr = record->to_ip;
+       sample.weight = record->latency;
 
        return arm_spe_deliver_synth_event(spe, speq, event, &sample);
 }
@@ -993,7 +995,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
        attr.type = PERF_TYPE_HARDWARE;
        attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
        attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
-                           PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC;
+                           PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
+                           PERF_SAMPLE_WEIGHT;
        if (spe->timeless_decoding)
                attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
        else