1 files changed, 34 insertions, 3 deletions

diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index da379328442c..5c5b438584c4 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -434,12 +434,36 @@ static int arm_spe_sample(struct arm_spe_queue *speq)
 static int arm_spe_run_decoder(struct arm_spe_queue *speq, u64 *timestamp)
 {
 	struct arm_spe *spe = speq->spe;
+	struct arm_spe_record *record;
 	int ret;
 
 	if (!spe->kernel_start)
 		spe->kernel_start = machine__kernel_start(spe->machine);
 
 	while (1) {
+		/*
+		 * The usual logic is firstly to decode the packets, and then
+		 * based the record to synthesize sample; but here the flow is
+		 * reversed: it calls arm_spe_sample() for synthesizing samples
+		 * prior to arm_spe_decode().
+		 *
+		 * Two reasons for this code logic:
+		 * 1. Firstly, when setup queue in arm_spe__setup_queue(), it
+		 * has decoded trace data and generated a record, but the record
+		 * is left to generate sample until run to here, so it's correct
+		 * to synthesize sample for the left record.
+		 * 2. After decoding trace data, it needs to compare the record
+		 * timestamp with the coming perf event, if the record timestamp
+		 * is later than the perf event, it needs bail out and pushs the
+		 * record into auxtrace heap, thus the record can be deferred to
+		 * synthesize sample until run to here at the next time; so this
+		 * can correlate samples between Arm SPE trace data and other
+		 * perf events with correct time ordering.
+		 */
+		ret = arm_spe_sample(speq);
+		if (ret)
+			return ret;
+
 		ret = arm_spe_decode(speq->decoder);
 		if (!ret) {
 			pr_debug("No data or all data has been processed.\n");
@@ -453,10 +477,17 @@ static int arm_spe_run_decoder(struct arm_spe_queue *speq, u64 *timestamp)
 		if (ret < 0)
 			continue;
 
-		ret = arm_spe_sample(speq);
-		if (ret)
-			return ret;
+		record = &speq->decoder->record;
 
+		/* Update timestamp for the last record */
+		if (record->timestamp > speq->timestamp)
+			speq->timestamp = record->timestamp;
+
+		/*
+		 * If the timestamp of the queue is later than timestamp of the
+		 * coming perf event, bail out so can allow the perf event to
+		 * be processed ahead.
+		 */
 		if (!spe->timeless_decoding && speq->timestamp >= *timestamp) {
 			*timestamp = speq->timestamp;
 			return 0;