diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 16e21a3e883a..96a3e122655b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -906,6 +906,37 @@ static int record__config_off_cpu(struct record *rec)
 	return off_cpu_prepare(rec->evlist, &rec->opts.target, &rec->opts);
 }
 
+static int record__config_tracking_events(struct record *rec)
+{
+	struct record_opts *opts = &rec->opts;
+	struct evlist *evlist = rec->evlist;
+	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) {
+		evsel = evlist__findnew_tracking_event(evlist, false);
+		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];
@@ -1286,28 +1317,6 @@ 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__findnew_tracking_event(evlist, false);
-		if (!pos)
-			return -ENOMEM;
-
-		/*
-		 * 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) {
@@ -4171,6 +4180,12 @@ 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");
diff --git a/tools/perf/tests/attr/system-wide-dummy b/tools/perf/tests/attr/system-wide-dummy
index 2f3e3eb728eb..a1e1d6a263bf 100644
--- a/tools/perf/tests/attr/system-wide-dummy
+++ b/tools/perf/tests/attr/system-wide-dummy
@@ -9,8 +9,10 @@ flags=8
 type=1
 size=136
 config=9
-sample_period=4000
-sample_type=455
+sample_period=1
+# PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_TIME |
+# PERF_SAMPLE_CPU | PERF_SAMPLE_IDENTIFIER
+sample_type=65671
 read_format=4|20
 # Event will be enabled right away.
 disabled=0
@@ -18,12 +20,12 @@ inherit=1
 pinned=0
 exclusive=0
 exclude_user=0
-exclude_kernel=0
-exclude_hv=0
+exclude_kernel=1
+exclude_hv=1
 exclude_idle=0
 mmap=1
 comm=1
-freq=1
+freq=0
 inherit_stat=0
 enable_on_exec=0
 task=1
@@ -32,7 +34,7 @@ precise_ip=0
 mmap_data=0
 sample_id_all=1
 exclude_host=0
-exclude_guest=0
+exclude_guest=1
 exclude_callchain_kernel=0
 exclude_callchain_user=0
 mmap2=1
diff --git a/tools/perf/tests/attr/test-record-C0 b/tools/perf/tests/attr/test-record-C0
index 317730b906dd..198e8429a1bf 100644
--- a/tools/perf/tests/attr/test-record-C0
+++ b/tools/perf/tests/attr/test-record-C0
@@ -10,9 +10,9 @@ cpu=0
 enable_on_exec=0
 
 # PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_TIME |
-# PERF_SAMPLE_ID | PERF_SAMPLE_PERIOD
+# PERF_SAMPLE_PERIOD | PERF_SAMPLE_IDENTIFIER
 # + PERF_SAMPLE_CPU added by -C 0
-sample_type=455
+sample_type=65927
 
 # Dummy event handles mmaps, comm and task.
 mmap=0