4 files changed, 14 insertions, 7 deletions
diff --git a/tools/perf/util/bpf_skel/off_cpu.bpf.c b/tools/perf/util/bpf_skel/off_cpu.bpf.c
index 38e3b287dbb2..d877a0a9731f 100644
--- a/tools/perf/util/bpf_skel/off_cpu.bpf.c
+++ b/tools/perf/util/bpf_skel/off_cpu.bpf.c
@@ -277,7 +277,7 @@ int on_switch(u64 *ctx)
 	else
 		prev_state = get_task_state(prev);
 
-	return off_cpu_stat(ctx, prev, next, prev_state);
+	return off_cpu_stat(ctx, prev, next, prev_state & 0xff);
 }
 
 char LICENSE[] SEC("license") = "Dual BSD/GPL";
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 534d36d26fc3..a07473703c6d 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -842,11 +842,7 @@ int create_perf_stat_counter(struct evsel *evsel,
 	if (evsel__is_group_leader(evsel)) {
 		attr->disabled = 1;
 
-		/*
-		 * In case of initial_delay we enable tracee
-		 * events manually.
-		 */
-		if (target__none(target) && !config->initial_delay)
+		if (target__enable_on_exec(target))
 			attr->enable_on_exec = 1;
 	}
 
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index b1c29156c560..bf1794ebc916 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -166,7 +166,6 @@ struct perf_stat_config {
 	FILE			*output;
 	unsigned int		 interval;
 	unsigned int		 timeout;
-	int			 initial_delay;
 	unsigned int		 unit_width;
 	unsigned int		 metric_only_len;
 	int			 times;
diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
index daec6cba500d..880f1af7f6ad 100644
--- a/tools/perf/util/target.h
+++ b/tools/perf/util/target.h
@@ -18,6 +18,7 @@ struct target {
 	bool	     per_thread;
 	bool	     use_bpf;
 	bool	     hybrid;
+	int	     initial_delay;
 	const char   *attr_map;
 };
 
@@ -72,6 +73,17 @@ static inline bool target__none(struct target *target)
 	return !target__has_task(target) && !target__has_cpu(target);
 }
 
+static inline bool target__enable_on_exec(struct target *target)
+{
+	/*
+	 * Normally enable_on_exec should be set if:
+	 *  1) The tracee process is forked (not attaching to existed task or cpu).
+	 *  2) And initial_delay is not configured.
+	 * Otherwise, we enable tracee events manually.
+	 */
+	return target__none(target) && !target->initial_delay;
+}
+
 static inline bool target__has_per_thread(struct target *target)
 {
 	return target->system_wide && target->per_thread;