[PATCH v9 6/9] perf cs-etm: Flush thread stacks after decoder reset

[Leo Yan]

Perf resets the CoreSight decoder when moving to a new AUX trace buffer,
this causes trace discontinunity globally.

For callchain synthesis, keeping thread-stack state after decoder reset
can leave stale call/return history attached to threads that are decoded
later, producing incorrect synthesized callchains.

Flush all host thread stacks after a decoder reset. When virtualization
is present, flush the guest thread stacks as well.

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 | 45 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 51b05a0bc1898128ad66d82bef6e09b5c853463c..d41aad583a26fe9f2f74c52630bd01c2a5bbe0e4 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -2006,6 +2006,45 @@ static int cs_etm__end_block(struct cs_etm_queue *etmq,
 
 	return 0;
 }
+
+static int cs_etm__flush_stack_cb(struct thread *thread,
+				  void *data __maybe_unused)
+{
+	thread_stack__flush(thread);
+	return 0;
+}
+
+static void cs_etm__flush_machine_stack(struct cs_etm_queue *etmq, pid_t pid)
+{
+	struct machine *machine;
+
+	machine = machines__find(&etmq->etm->session->machines, pid);
+	if (machine)
+		machine__for_each_thread(machine, cs_etm__flush_stack_cb, NULL);
+}
+
+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)
+		return;
+
+	switch (pid_fmt) {
+	case CS_ETM_PIDFMT_CTXTID2:
+		/* Clear the guest stack if virtualization is supported */
+		cs_etm__flush_machine_stack(etmq, DEFAULT_GUEST_KERNEL_ID);
+		fallthrough;
+	case CS_ETM_PIDFMT_CTXTID:
+		cs_etm__flush_machine_stack(etmq, HOST_KERNEL_ID);
+		break;
+	case CS_ETM_PIDFMT_NONE:
+	default:
+		break;
+
+	}
+}
+
 /*
  * cs_etm__get_data_block: Fetch a block from the auxtrace_buffer queue
  *			   if need be.
@@ -2028,6 +2067,12 @@ static int cs_etm__get_data_block(struct cs_etm_queue *etmq)
 		ret = cs_etm_decoder__reset(etmq->decoder);
 		if (ret)
 			return ret;
+
+		/*
+		 * Since the decoder is reset, this causes a global trace
+		 * discontinuity. Flush all thread stacks.
+		 */
+		cs_etm__flush_all_stack(etmq);
 	}
 
 	return etmq->buf_len;

-- 
2.34.1