1 files changed, 65 insertions, 27 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 34bb31f08bb5..dcf288a4fb9a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -906,6 +906,65 @@ static int record__config_off_cpu(struct record *rec)
 	return off_cpu_prepare(rec->evlist, &rec->opts.target, &rec->opts);
 }
 
+static bool record__tracking_system_wide(struct record *rec)
+{
+	struct evlist *evlist = rec->evlist;
+	struct evsel *evsel;
+
+	/*
+	 * If non-dummy evsel exists, system_wide sideband is need to
+	 * help parse sample information.
+	 * For example, PERF_EVENT_MMAP event to help parse symbol,
+	 * and PERF_EVENT_COMM event to help parse task executable name.
+	 */
+	evlist__for_each_entry(evlist, evsel) {
+		if (!evsel__is_dummy_event(evsel))
+			return true;
+	}
+
+	return false;
+}
+
+static int record__config_tracking_events(struct record *rec)
+{
+	struct record_opts *opts = &rec->opts;
+	struct evlist *evlist = rec->evlist;
+	bool system_wide = false;
+	struct evsel *evsel;
+
+	/*
+	 * For initial_delay, system wide or a hybrid system, we need to add
+	 * tracking event so that we can track PERF_RECORD_MMAP to cover the
+	 * delay of waiting or event synthesis.
+	 */
+	if (opts->target.initial_delay || target__has_cpu(&opts->target) ||
+	    perf_pmus__num_core_pmus() > 1) {
+
+		/*
+		 * User space tasks can migrate between CPUs, so when tracing
+		 * selected CPUs, sideband for all CPUs is still needed.
+		 */
+		if (!!opts->target.cpu_list && record__tracking_system_wide(rec))
+			system_wide = true;
+
+		evsel = evlist__findnew_tracking_event(evlist, system_wide);
+		if (!evsel)
+			return -ENOMEM;
+
+		/*
+		 * Enable the tracking event when the process is forked for
+		 * initial_delay, immediately for system wide.
+		 */
+		if (opts->target.initial_delay && !evsel->immediate &&
+		    !target__has_cpu(&opts->target))
+			evsel->core.attr.enable_on_exec = 1;
+		else
+			evsel->immediate = 1;
+	}
+
+	return 0;
+}
+
 static bool record__kcore_readable(struct machine *machine)
 {
 	char kcore[PATH_MAX];
@@ -1286,33 +1345,6 @@ static int record__open(struct record *rec)
 	struct record_opts *opts = &rec->opts;
 	int rc = 0;
 
-	/*
-	 * For initial_delay, system wide or a hybrid system, we need to add a
-	 * dummy event so that we can track PERF_RECORD_MMAP to cover the delay
-	 * of waiting or event synthesis.
-	 */
-	if (opts->target.initial_delay || target__has_cpu(&opts->target) ||
-	    perf_pmus__num_core_pmus() > 1) {
-		pos = evlist__get_tracking_event(evlist);
-		if (!evsel__is_dummy_event(pos)) {
-			/* Set up dummy event. */
-			if (evlist__add_dummy(evlist))
-				return -ENOMEM;
-			pos = evlist__last(evlist);
-			evlist__set_tracking_event(evlist, pos);
-		}
-
-		/*
-		 * Enable the dummy event when the process is forked for
-		 * initial_delay, immediately for system wide.
-		 */
-		if (opts->target.initial_delay && !pos->immediate &&
-		    !target__has_cpu(&opts->target))
-			pos->core.attr.enable_on_exec = 1;
-		else
-			pos->immediate = 1;
-	}
-
 	evlist__config(evlist, opts, &callchain_param);
 
 	evlist__for_each_entry(evlist, pos) {
@@ -4195,6 +4227,12 @@ int cmd_record(int argc, const char **argv)
 		goto out;
 	}
 
+	err = record__config_tracking_events(rec);
+	if (err) {
+		pr_err("record__config_tracking_events failed, error %d\n", err);
+		goto out;
+	}
+
 	err = record__init_thread_masks(rec);
 	if (err) {
 		pr_err("Failed to initialize parallel data streaming masks\n");