[PATCH v5 4/9] perf cs-etm: Support thread stack

[Leo Yan]

Since Arm CoreSight doesn't support thread stack, the decoding cannot
display symbols with indented spaces to reflect the stack depth.

This patch adds support thread stack for Arm CoreSight, this allows
'perf script' to display properly for option '-F,+callindent'.

Before:

  # perf script -F,+callindent
            main  2808          1          branches: coresight_test1                      ffff8634f5c8 coresight_test1+0x3c (/root/coresight_test/libcstest.so)
            main  2808          1          branches: printf@plt                           aaaaba8d37ec main+0x28 (/root/coresight_test/main)
            main  2808          1          branches: printf@plt                           aaaaba8d36bc printf@plt+0xc (/root/coresight_test/main)
            main  2808          1          branches: _init                                aaaaba8d3650 _init+0x30 (/root/coresight_test/main)
            main  2808          1          branches: _dl_fixup                            ffff86373b4c _dl_runtime_resolve+0x40 (/lib/aarch64-linux-gnu/ld-2.28.so)
            main  2808          1          branches: _dl_lookup_symbol_x                  ffff8636e078 _dl_fixup+0xb8 (/lib/aarch64-linux-gnu/ld-2.28.so)
  [...]

After:

  # perf script -F,+callindent
            main  2808          1          branches:                 coresight_test1                                      ffff8634f5c8 coresight_test1+0x3c (/root/coresight_test/libcstest.so)
            main  2808          1          branches:                 printf@plt                                           aaaaba8d37ec main+0x28 (/root/coresight_test/main)
            main  2808          1          branches:                     printf@plt                                       aaaaba8d36bc printf@plt+0xc (/root/coresight_test/main)
            main  2808          1          branches:                     _init                                            aaaaba8d3650 _init+0x30 (/root/coresight_test/main)
            main  2808          1          branches:                     _dl_fixup                                        ffff86373b4c _dl_runtime_resolve+0x40 (/lib/aarch64-linux-gnu/ld-2.28.s
            main  2808          1          branches:                         _dl_lookup_symbol_x                          ffff8636e078 _dl_fixup+0xb8 (/lib/aarch64-linux-gnu/ld-2.28.so)
  [...]

Signed-off-by: Leo Yan <leo.yan@xxxxxxxxxx>
---
 tools/perf/util/cs-etm.c | 44 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index f3ba2cfb634f..08ca919aa2b1 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1138,6 +1138,45 @@ static void cs_etm__copy_insn(struct cs_etm_queue *etmq,
 			   sample->insn_len, (void *)sample->insn);
 }
 
+static void cs_etm__add_stack_event(struct cs_etm_queue *etmq,
+				    struct cs_etm_traceid_queue *tidq)
+{
+	struct cs_etm_auxtrace *etm = etmq->etm;
+	u8 trace_chan_id = tidq->trace_chan_id;
+	int insn_len;
+	u64 from_ip, to_ip;
+
+	if (etm->synth_opts.thread_stack) {
+		from_ip = cs_etm__last_executed_instr(tidq->prev_packet);
+		to_ip = cs_etm__first_executed_instr(tidq->packet);
+
+		insn_len = cs_etm__instr_size(etmq, trace_chan_id,
+					      tidq->prev_packet->isa, from_ip);
+
+		/*
+		 * Create thread stacks by keeping track of calls and returns;
+		 * any call pushes thread stack, return pops the stack, and
+		 * flush stack when the trace is discontinuous.
+		 */
+		thread_stack__event(tidq->thread, tidq->prev_packet->cpu,
+				    tidq->prev_packet->flags,
+				    from_ip, to_ip, insn_len,
+				    etmq->buffer->buffer_nr + 1);
+	} else {
+		/*
+		 * The thread stack can be output via thread_stack__process();
+		 * thus the detailed information about paired calls and returns
+		 * will be facilitated by Python script for the db-export.
+		 *
+		 * Need to set trace buffer number and flush thread stack if the
+		 * trace buffer number has been alternate.
+		 */
+		thread_stack__set_trace_nr(tidq->thread,
+					   tidq->prev_packet->cpu,
+					   etmq->buffer->buffer_nr + 1);
+	}
+}
+
 static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
 					    struct cs_etm_traceid_queue *tidq,
 					    u64 addr, u64 period)
@@ -1382,6 +1421,9 @@ static int cs_etm__sample(struct cs_etm_queue *etmq,
 	    tidq->prev_packet->last_instr_taken_branch)
 		cs_etm__update_last_branch_rb(etmq, tidq);
 
+	if (tidq->prev_packet->last_instr_taken_branch)
+		cs_etm__add_stack_event(etmq, tidq);
+
 	if (etm->sample_instructions &&
 	    tidq->period_instructions >= etm->instructions_sample_period) {
 		/*
@@ -2730,6 +2772,8 @@ int cs_etm__process_auxtrace_info(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;
 	}
 
 	err = cs_etm__synth_events(etm, session);
-- 
2.17.1