perf stat: Measure 't0' and 'ref_time' after enable_counters()

Take measurements of 't0' and 'ref_time' after enable_counters(), so
that they only measure the time consumed when the counters are enabled.
Signed-off-by: Song Liu <songliubraving@fb.com>
Acked-by: Andi Kleen <andi@firstfloor.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: kernel-team@fb.com
Link: http://lore.kernel.org/lkml/20210316211837.910506-3-songliubraving@fb.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-stat.c

@@ -931,15 +931,15 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	/*
 	 * Enable counters and exec the command:
 	 */
-	t0 = rdclock();
-	clock_gettime(CLOCK_MONOTONIC, &ref_time);
-
 	if (forks) {
 		evlist__start_workload(evsel_list);
 		err = enable_counters();
 		if (err)
 			return -1;
 
+		t0 = rdclock();
+		clock_gettime(CLOCK_MONOTONIC, &ref_time);
+
 		if (interval || timeout || evlist__ctlfd_initialized(evsel_list))
 			status = dispatch_events(forks, timeout, interval, &times);
 		if (child_pid != -1) {
@@ -960,6 +960,10 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 		err = enable_counters();
 		if (err)
 			return -1;
+
+		t0 = rdclock();
+		clock_gettime(CLOCK_MONOTONIC, &ref_time);
+
 		status = dispatch_events(forks, timeout, interval, &times);
 	}