perf tools: Flush remaining samples w/o deferred callchains

It's possible that some kernel samples don't have matching deferred
callchain records when the profiling session was ended before the
threads came back to userspace.  Let's flush the samples before
finish the session.

Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index dc570ad47ccc2c637cc992f384763c88605f42de..4236503c8f6c1350e98c374a3a46663ffaaf3b88 100644 (file)
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1295,6 +1295,10 @@ struct deferred_event {
        union perf_event *event;
 };
 
+/*
+ * This is called when a deferred callchain record comes up.  Find all matching
+ * samples, merge the callchains and process them.
+ */
 static int evlist__deliver_deferred_callchain(struct evlist *evlist,
                                              const struct perf_tool *tool,
                                              union  perf_event *event,
@@ -1345,6 +1349,42 @@ static int evlist__deliver_deferred_callchain(struct evlist *evlist,
        return ret;
 }
 
+/*
+ * This is called at the end of the data processing for the session.  Flush the
+ * remaining samples as there's no hope for matching deferred callchains.
+ */
+static int session__flush_deferred_samples(struct perf_session *session,
+                                          const struct perf_tool *tool)
+{
+       struct evlist *evlist = session->evlist;
+       struct machine *machine = &session->machines.host;
+       struct deferred_event *de, *tmp;
+       struct evsel *evsel;
+       int ret = 0;
+
+       list_for_each_entry_safe(de, tmp, &evlist->deferred_samples, list) {
+               struct perf_sample sample;
+
+               ret = evlist__parse_sample(evlist, de->event, &sample);
+               if (ret < 0) {
+                       pr_err("failed to parse original sample\n");
+                       break;
+               }
+
+               evsel = evlist__id2evsel(evlist, sample.id);
+               ret = evlist__deliver_sample(evlist, tool, de->event,
+                                            &sample, evsel, machine);
+
+               list_del(&de->list);
+               free(de->event);
+               free(de);
+
+               if (ret)
+                       break;
+       }
+       return ret;
+}
+
 static int machines__deliver_event(struct machines *machines,
                                   struct evlist *evlist,
                                   union perf_event *event,
@@ -2038,6 +2078,9 @@ more:
 done:
        /* do the final flush for ordered samples */
        err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+       if (err)
+               goto out_err;
+       err = session__flush_deferred_samples(session, tool);
        if (err)
                goto out_err;
        err = auxtrace__flush_events(session, tool);
@@ -2384,6 +2427,9 @@ static int __perf_session__process_events(struct perf_session *session)
        if (err)
                goto out_err;
        err = auxtrace__flush_events(session, tool);
+       if (err)
+               goto out_err;
+       err = session__flush_deferred_samples(session, tool);
        if (err)
                goto out_err;
        err = perf_session__flush_thread_stacks(session);
@@ -2506,6 +2552,10 @@ static int __perf_session__process_dir_events(struct perf_session *session)
        if (ret)
                goto out_err;
 
+       ret = session__flush_deferred_samples(session, tool);
+       if (ret)
+               goto out_err;
+
        ret = perf_session__flush_thread_stacks(session);
 out_err:
        ui_progress__finish();