[PATCH v8 6/8] perf cs-etm: Support call indentation

Leo Yan leo.yan at arm.com
Thu Jun 11 07:50:52 PDT 2026


From: Leo Yan <leo.yan at linaro.org>

The perf script callindent is derived from call stack in thread context,
CS ETM ignores the requirement for callindent without pushing and poping
call stack.

Enable thread-stack when either itrace thread-stack support or last branch
entries are requested, allocate the branch stack storage accordingly, and
feed taken branches to thread_stack__event() whenever thread-stack state
is needed.

When callindent is requested, pass callstack=true to thread_stack__event()
so the common thread-stack code maintains call depth for branch samples.

Before:

  perf script -F +callindent

  callchain_test    6543 [002]          1 branches: main                                 ffff93252258 __libc_start_call_main+0x78 (/usr/lib/aarch64-linux-gnu/libc.so.6)
  callchain_test    6543 [002]          1 branches: foo                                  aaaad6b607c4 main+0x8 (/home/kernel/leoy/test_cs_callchain/callchain_test)
  callchain_test    6543 [002]          1 branches: print                                aaaad6b607ac foo+0x8 (/home/kernel/leoy/test_cs_callchain/callchain_test)
  callchain_test    6543 [002]          1 branches: do_svc                               aaaad6b60794 print+0x8 (/home/kernel/leoy/test_cs_callchain/callchain_test)
  callchain_test    6543 [002]          1 branches: vectors                              aaaad6b60780 do_svc+0x18 (/home/kernel/leoy/test_cs_callchain/callchain_test)
  callchain_test    6543 [002]          1 branches: el0t_64_sync_handler             ffff80008001159c el0t_64_sync+0x194 ([kernel.kallsyms])
  callchain_test    6543 [002]          1 branches: el0_svc                          ffff800081829194 el0t_64_sync_handler+0x9c ([kernel.kallsyms])
  callchain_test    6543 [002]          1 branches: lockdep_hardirqs_off             ffff800081828794 el0_svc+0x24 ([kernel.kallsyms])
  callchain_test    6543 [002]          1 branches: __this_cpu_preempt_check         ffff80008182b348 lockdep_hardirqs_off+0xf0 ([kernel.kallsyms])

After:

  callchain_test    6543 [002]          1 branches:                 main                                                 ffff93252258 __libc_start_call_main+0x78 (/usr/lib/aarch64-linux-gnu/libc.so.6)
  callchain_test    6543 [002]          1 branches:                     foo                                              aaaad6b607c4 main+0x8 (/home/kernel/leoy/test_cs_callchain/callchain_test)
  callchain_test    6543 [002]          1 branches:                         print                                        aaaad6b607ac foo+0x8 (/home/kernel/leoy/test_cs_callchain/callchain_test)
  callchain_test    6543 [002]          1 branches:                             do_svc                                   aaaad6b60794 print+0x8 (/home/kernel/leoy/test_cs_callchain/callchain_test)
  callchain_test    6543 [002]          1 branches:                                 vectors                              aaaad6b60780 do_svc+0x18 (/home/kernel/leoy/test_cs_callchain/callchain_test)
  callchain_test    6543 [002]          1 branches:                                     el0t_64_sync_handler         ffff80008001159c el0t_64_sync+0x194 ([kernel.kallsyms])
  callchain_test    6543 [002]          1 branches:                                         el0_svc                  ffff800081829194 el0t_64_sync_handler+0x9c ([kernel.kallsyms])
  callchain_test    6543 [002]          1 branches:                                             lockdep_hardirqs_off ffff800081828794 el0_svc+0x24 ([kernel.kallsyms])
  callchain_test    6543 [002]          1 branches:                                                 __this_cpu_preempt_check                         ffff80008182b348 lockdep_hardirqs_off+0xf0 ([kernel.kallsyms])

Signed-off-by: Leo Yan <leo.yan at linaro.org>
Reviewed-by: James Clark <james.clark at linaro.org>
Signed-off-by: Leo Yan <leo.yan at arm.com>
---
 tools/perf/util/cs-etm.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 7069b4990e6107fdece3cc5451142714f1d627ef..830618763d8b1bdcc015c492d7b2354d862566ca 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -66,6 +66,8 @@ struct cs_etm_auxtrace {
 	bool snapshot_mode;
 	bool data_queued;
 	bool has_virtual_ts; /* Virtual/Kernel timestamps in the trace. */
+	bool use_thread_stack;
+	bool use_callchain;
 
 	int num_cpu;
 	u64 latest_kernel_timestamp;
@@ -635,7 +637,7 @@ static int cs_etm__init_traceid_queue(struct cs_etm_queue *etmq,
 	if (!tidq->prev_packet)
 		goto out_free;
 
-	if (etm->synth_opts.last_branch) {
+	if (etm->use_thread_stack) {
 		size_t sz = sizeof(struct branch_stack);
 
 		sz += etm->synth_opts.last_branch_sz *
@@ -1545,7 +1547,7 @@ static void cs_etm__add_stack_event(struct cs_etm_queue *etmq,
 	if (!cs_etm__packet_has_taken_branch(tidq->prev_packet))
 		return;
 
-	if (etmq->etm->synth_opts.last_branch) {
+	if (etmq->etm->use_thread_stack) {
 		from = cs_etm__last_executed_instr(tidq->prev_packet);
 		to = cs_etm__first_executed_instr(tidq->packet);
 
@@ -1554,7 +1556,8 @@ static void cs_etm__add_stack_event(struct cs_etm_queue *etmq,
 		/* Enable callchain so thread stack entry can be allocated */
 		thread_stack__event(tidq->frontend_thread, tidq->prev_packet->cpu,
 				    tidq->prev_packet->flags, from, to, size,
-				    etmq->buffer->buffer_nr + 1, false,
+				    etmq->buffer->buffer_nr + 1,
+				    etmq->etm->use_callchain,
 				    tidq->br_stack_sz, 0);
 	} else {
 		thread_stack__set_trace_nr(tidq->frontend_thread,
@@ -1955,7 +1958,7 @@ static int cs_etm__flush(struct cs_etm_queue *etmq,
 	cs_etm__packet_swap(etm, tidq);
 
 	/* Reset last branches after flush the trace */
-	if (etm->synth_opts.last_branch)
+	if (etm->use_thread_stack)
 		thread_stack__flush(tidq->frontend_thread);
 
 	return err;
@@ -2018,7 +2021,7 @@ static void cs_etm__flush_all_stack(struct cs_etm_queue *etmq)
 {
 	enum cs_etm_pid_fmt pid_fmt = cs_etm__get_pid_fmt(etmq);
 
-	if (!etmq->etm->synth_opts.last_branch)
+	if (!etmq->etm->use_thread_stack)
 		return;
 
 	cs_etm__flush_machine_stack(etmq, HOST_KERNEL_ID);
@@ -3491,6 +3494,7 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
 		itrace_synth_opts__set_default(&etm->synth_opts,
 				session->itrace_synth_opts->default_no_sample);
 		etm->synth_opts.callchain = false;
+		etm->synth_opts.thread_stack = session->itrace_synth_opts->thread_stack;
 	}
 
 	if (etm->synth_opts.calls)
@@ -3552,6 +3556,12 @@ int cs_etm__process_auxtrace_info_full(union perf_event *event,
 		etm->tc.cap_user_time_zero = tc->cap_user_time_zero;
 		etm->tc.cap_user_time_short = tc->cap_user_time_short;
 	}
+
+	etm->use_thread_stack = etm->synth_opts.thread_stack ||
+				etm->synth_opts.last_branch;
+
+	etm->use_callchain = etm->synth_opts.thread_stack;
+
 	err = cs_etm__synth_events(etm, session);
 	if (err)
 		goto err_free_queues;

-- 
2.34.1




More information about the linux-arm-kernel mailing list