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 <[e-mail]>
Signed-off-by: Namhyung Kim <[e-mail]>
Cc: Andi Kleen <[e-mail]>
Cc: German Gomez <[e-mail]>
Cc: Ian Rogers <[e-mail]>
Cc: James Clark <[e-mail]>
Cc: Jiri Olsa <[e-mail]>
Cc: Mark Rutland <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Stephane Eranian <[e-mail]>
Link: http://lore.kernel.org/lkml/[e-mail]
Signed-off-by: Arnaldo Carvalho de Melo <[e-mail]>

tools/perf/util/arm-spe-decoder/arm-spe-decoder.c

···
 				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;

tools/perf/util/arm-spe-decoder/arm-spe-decoder.h

···
 	enum arm_spe_sample_type type;
 	int err;
 	u32 op;
+	u32 latency;
 	u64 from_ip;
 	u64 to_ip;
 	u64 timestamp;

tools/perf/util/arm-spe.c

···
 	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);
 }
···
 	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);
 }
···
 	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