diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py
index 8f6fa4a007b4..42579f858684 100755
--- a/tools/perf/scripts/python/arm-cs-trace-disasm.py
+++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py
@@ -31,18 +31,19 @@ from perf_trace_context import perf_sample_srccode, perf_config_get
 #
 # Output disassembly with objdump and auto detect vmlinux
 # (when running on same machine.):
-#  perf script -s scripts/python/arm-cs-trace-disasm.py -d
+#  perf script --itrace=b -s scripts/python/arm-cs-trace-disasm.py \
+#       -- -d
 #
 # Output disassembly with llvm-objdump:
-#  perf script -s scripts/python/arm-cs-trace-disasm.py \
+#  perf script --itrace=b -s scripts/python/arm-cs-trace-disasm.py \
 #		-- -d llvm-objdump-11 -k path/to/vmlinux
 #
 # Output accurate disassembly by passing kcore to script:
-#  perf script -s scripts/python/arm-cs-trace-disasm.py \
+#  perf script --itrace=b -s scripts/python/arm-cs-trace-disasm.py \
 #		-- -d -k perf.data/kcore_dir/kcore
 #
 # Output only source line and symbols:
-#  perf script -s scripts/python/arm-cs-trace-disasm.py
+#  perf script --itrace=b -s scripts/python/arm-cs-trace-disasm.py
 
 def default_objdump():
 	config = perf_config_get("annotate.objdump")
diff --git a/tools/perf/tests/shell/coresight/test_arm_coresight_disasm.sh b/tools/perf/tests/shell/coresight/test_arm_coresight_disasm.sh
index ccb90dda2475..f3ebad596378 100755
--- a/tools/perf/tests/shell/coresight/test_arm_coresight_disasm.sh
+++ b/tools/perf/tests/shell/coresight/test_arm_coresight_disasm.sh
@@ -44,7 +44,7 @@ branch_search='[[:space:]](bl|b(\.(eq|ne|cs|cc|mi|pl|vs|vc|hi|ls|ge|lt|gt|le|al)
 if [ "$(id -u)" == 0 ] && [ -e /proc/kcore ]; then
 	echo "Testing kernel disassembly"
 	perf record -o ${perfdata} -e cs_etm//k --kcore -Se -m,64K -- touch $file > /dev/null 2>&1
-	perf script -i ${perfdata} -s python:${script_path} -- \
+	perf script -i ${perfdata} --itrace=b -s python:${script_path} -- \
 		-d --stop-sample=2 -k ${perfdata}/kcore_dir/kcore 2> /dev/null > ${file}
 	grep -q -E ${branch_search} ${file}
 	echo "Found kernel branches"
@@ -56,7 +56,7 @@ fi
 ## Test user ##
 echo "Testing userspace disassembly"
 perf record -o ${perfdata} -e cs_etm//u -Se -m,64K -- touch $file > /dev/null 2>&1
-perf script -i ${perfdata} -s python:${script_path} -- \
+perf script -i ${perfdata} --itrace=b -s python:${script_path} -- \
 	-d --stop-sample=2 2> /dev/null > ${file}
 grep -q -E ${branch_search} ${file}
 echo "Found userspace branches"
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index deca07d57282..95530e10e010 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -71,6 +71,7 @@ struct cs_etm_auxtrace {
 	int num_cpu;
 	u64 latest_kernel_timestamp;
 	u32 auxtrace_type;
+	u32 branches_filter;
 	u64 branches_sample_type;
 	u64 branches_id;
 	u64 instructions_sample_type;
@@ -1705,6 +1706,10 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
 	} dummy_bs;
 	u64 ip;
 
+	if (etm->branches_filter &&
+		!(etm->branches_filter & tidq->prev_packet->flags))
+		return 0;
+
 	perf_sample__init(&sample, /*all=*/true);
 	ip = cs_etm__last_executed_instr(tidq->prev_packet);
 
@@ -3564,6 +3569,16 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
 		etm->synth_opts.callchain = false;
 	}
 
+	if (etm->synth_opts.calls)
+		etm->branches_filter |= PERF_IP_FLAG_CALL |
+					PERF_IP_FLAG_TRACE_BEGIN |
+					PERF_IP_FLAG_TRACE_END;
+
+	if (etm->synth_opts.returns)
+		etm->branches_filter |= PERF_IP_FLAG_RETURN |
+					PERF_IP_FLAG_TRACE_BEGIN |
+					PERF_IP_FLAG_TRACE_END;
+
 	etm->session = session;
 
 	etm->num_cpu = num_cpu;