4 files changed, 61 insertions, 13 deletions

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index ed6f7fd5b90b..b3a5daaf1a8f 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1076,6 +1076,35 @@ bool cs_etm__etmq_is_timeless(struct cs_etm_queue *etmq)
 	return !!etmq->etm->timeless_decoding;
 }
 
+static void cs_etm__copy_insn(struct cs_etm_queue *etmq,
+			      u64 trace_chan_id,
+			      const struct cs_etm_packet *packet,
+			      struct perf_sample *sample)
+{
+	/*
+	 * It's pointless to read instructions for the CS_ETM_DISCONTINUITY
+	 * packet, so directly bail out with 'insn_len' = 0.
+	 */
+	if (packet->sample_type == CS_ETM_DISCONTINUITY) {
+		sample->insn_len = 0;
+		return;
+	}
+
+	/*
+	 * T32 instruction size might be 32-bit or 16-bit, decide by calling
+	 * cs_etm__t32_instr_size().
+	 */
+	if (packet->isa == CS_ETM_ISA_T32)
+		sample->insn_len = cs_etm__t32_instr_size(etmq, trace_chan_id,
+							  sample->ip);
+	/* Otherwise, A64 and A32 instruction size are always 32-bit. */
+	else
+		sample->insn_len = 4;
+
+	cs_etm__mem_access(etmq, trace_chan_id, sample->ip,
+			   sample->insn_len, (void *)sample->insn);
+}
+
 static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 					    struct cs_etm_traceid_queue *tidq,
 					    u64 addr, u64 period)
@@ -1097,9 +1126,10 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 	sample.period = period;
 	sample.cpu = tidq->packet->cpu;
 	sample.flags = tidq->prev_packet->flags;
-	sample.insn_len = 1;
 	sample.cpumode = event->sample.header.misc;
 
+	cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->packet, &sample);
+
 	if (etm->synth_opts.last_branch) {
 		cs_etm__copy_last_branch_rb(etmq, tidq);
 		sample.branch_stack = tidq->last_branch;
@@ -1159,6 +1189,9 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
 	sample.flags = tidq->prev_packet->flags;
 	sample.cpumode = event->sample.header.misc;
 
+	cs_etm__copy_insn(etmq, tidq->trace_chan_id, tidq->prev_packet,
+			  &sample);
+
 	/*
 	 * perf report cannot handle events without a branch stack
 	 */
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 9cd6e3ae479a..efe08065838f 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -23,6 +23,13 @@ struct perf_sample_id {
 	struct hlist_node 	node;
 	u64		 	id;
 	struct evsel		*evsel;
+       /*
+	* 'idx' will be used for AUX area sampling. A sample will have AUX area
+	* data that will be queued for decoding, where there are separate
+	* queues for each CPU (per-cpu tracing) or task (per-thread tracing).
+	* The sample ID can be used to lookup 'idx' which is effectively the
+	* queue number.
+	*/
 	int			idx;
 	int			cpu;
 	pid_t			tid;
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
index 726e8d9e8c54..4ed20c833d44 100644
--- a/tools/perf/util/parse-branch-options.c
+++ b/tools/perf/util/parse-branch-options.c
@@ -30,6 +30,7 @@ static const struct branch_mode branch_modes[] = {
 	BRANCH_OPT("ind_jmp", PERF_SAMPLE_BRANCH_IND_JUMP),
 	BRANCH_OPT("call", PERF_SAMPLE_BRANCH_CALL),
 	BRANCH_OPT("save_type", PERF_SAMPLE_BRANCH_TYPE_SAVE),
+	BRANCH_OPT("stack", PERF_SAMPLE_BRANCH_CALL_STACK),
 	BRANCH_END
 };
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index b9fe71d11bf6..82e0438a9160 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1051,23 +1051,30 @@ static void callchain__printf(struct evsel *evsel,
 		       i, callchain->ips[i]);
 }
 
-static void branch_stack__printf(struct perf_sample *sample)
+static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 {
 	uint64_t i;
 
-	printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr);
+	printf("%s: nr:%" PRIu64 "\n",
+		!callstack ? "... branch stack" : "... branch callstack",
+		sample->branch_stack->nr);
 
 	for (i = 0; i < sample->branch_stack->nr; i++) {
 		struct branch_entry *e = &sample->branch_stack->entries[i];
 
-		printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
-			i, e->from, e->to,
-			(unsigned short)e->flags.cycles,
-			e->flags.mispred ? "M" : " ",
-			e->flags.predicted ? "P" : " ",
-			e->flags.abort ? "A" : " ",
-			e->flags.in_tx ? "T" : " ",
-			(unsigned)e->flags.reserved);
+		if (!callstack) {
+			printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
+				i, e->from, e->to,
+				(unsigned short)e->flags.cycles,
+				e->flags.mispred ? "M" : " ",
+				e->flags.predicted ? "P" : " ",
+				e->flags.abort ? "A" : " ",
+				e->flags.in_tx ? "T" : " ",
+				(unsigned)e->flags.reserved);
+		} else {
+			printf("..... %2"PRIu64": %016" PRIx64 "\n",
+				i, i > 0 ? e->from : e->to);
+		}
 	}
 }
 
@@ -1217,8 +1224,8 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
 	if (evsel__has_callchain(evsel))
 		callchain__printf(evsel, sample);
 
-	if ((sample_type & PERF_SAMPLE_BRANCH_STACK) && !perf_evsel__has_branch_callstack(evsel))
-		branch_stack__printf(sample);
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK)
+		branch_stack__printf(sample, perf_evsel__has_branch_callstack(evsel));
 
 	if (sample_type & PERF_SAMPLE_REGS_USER)
 		regs_user__printf(sample);