diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 5cacc4f..d3b5f5f 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -51,6 +51,9 @@
 #define SYM_LEN			129
 #define MAX_PID			1024000
 
+static const char *cpu_list;
+static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+
 struct sched_atom;
 
 struct task_desc {
@@ -127,7 +130,8 @@
 	struct thread		*thread;
 	struct rb_node		node;
 	u64			max_lat;
-	u64			max_lat_at;
+	u64			max_lat_start;
+	u64			max_lat_end;
 	u64			total_lat;
 	u64			nb_atoms;
 	u64			total_runtime;
@@ -808,8 +812,8 @@
 		    struct evsel *evsel, struct perf_sample *sample,
 		    struct machine *machine __maybe_unused)
 {
-	const char *comm = perf_evsel__strval(evsel, sample, "comm");
-	const u32 pid	 = perf_evsel__intval(evsel, sample, "pid");
+	const char *comm = evsel__strval(evsel, sample, "comm");
+	const u32 pid	 = evsel__intval(evsel, sample, "pid");
 	struct task_desc *waker, *wakee;
 
 	if (verbose > 0) {
@@ -830,11 +834,11 @@
 			       struct perf_sample *sample,
 			       struct machine *machine __maybe_unused)
 {
-	const char *prev_comm  = perf_evsel__strval(evsel, sample, "prev_comm"),
-		   *next_comm  = perf_evsel__strval(evsel, sample, "next_comm");
-	const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
-		  next_pid = perf_evsel__intval(evsel, sample, "next_pid");
-	const u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
+	const char *prev_comm  = evsel__strval(evsel, sample, "prev_comm"),
+		   *next_comm  = evsel__strval(evsel, sample, "next_comm");
+	const u32 prev_pid = evsel__intval(evsel, sample, "prev_pid"),
+		  next_pid = evsel__intval(evsel, sample, "next_pid");
+	const u64 prev_state = evsel__intval(evsel, sample, "prev_state");
 	struct task_desc *prev, __maybe_unused *next;
 	u64 timestamp0, timestamp = sample->time;
 	int cpu = sample->cpu;
@@ -1093,7 +1097,8 @@
 	atoms->total_lat += delta;
 	if (delta > atoms->max_lat) {
 		atoms->max_lat = delta;
-		atoms->max_lat_at = timestamp;
+		atoms->max_lat_start = atom->wake_up_time;
+		atoms->max_lat_end = timestamp;
 	}
 	atoms->nb_atoms++;
 }
@@ -1103,9 +1108,9 @@
 				struct perf_sample *sample,
 				struct machine *machine)
 {
-	const u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
-		  next_pid = perf_evsel__intval(evsel, sample, "next_pid");
-	const u64 prev_state = perf_evsel__intval(evsel, sample, "prev_state");
+	const u32 prev_pid = evsel__intval(evsel, sample, "prev_pid"),
+		  next_pid = evsel__intval(evsel, sample, "next_pid");
+	const u64 prev_state = evsel__intval(evsel, sample, "prev_state");
 	struct work_atoms *out_events, *in_events;
 	struct thread *sched_out, *sched_in;
 	u64 timestamp0, timestamp = sample->time;
@@ -1173,8 +1178,8 @@
 				 struct perf_sample *sample,
 				 struct machine *machine)
 {
-	const u32 pid	   = perf_evsel__intval(evsel, sample, "pid");
-	const u64 runtime  = perf_evsel__intval(evsel, sample, "runtime");
+	const u32 pid	   = evsel__intval(evsel, sample, "pid");
+	const u64 runtime  = evsel__intval(evsel, sample, "runtime");
 	struct thread *thread = machine__findnew_thread(machine, -1, pid);
 	struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
 	u64 timestamp = sample->time;
@@ -1208,7 +1213,7 @@
 				struct perf_sample *sample,
 				struct machine *machine)
 {
-	const u32 pid	  = perf_evsel__intval(evsel, sample, "pid");
+	const u32 pid	  = evsel__intval(evsel, sample, "pid");
 	struct work_atoms *atoms;
 	struct work_atom *atom;
 	struct thread *wakee;
@@ -1269,7 +1274,7 @@
 				      struct perf_sample *sample,
 				      struct machine *machine)
 {
-	const u32 pid = perf_evsel__intval(evsel, sample, "pid");
+	const u32 pid = evsel__intval(evsel, sample, "pid");
 	u64 timestamp = sample->time;
 	struct work_atoms *atoms;
 	struct work_atom *atom;
@@ -1319,7 +1324,7 @@
 	int i;
 	int ret;
 	u64 avg;
-	char max_lat_at[32];
+	char max_lat_start[32], max_lat_end[32];
 
 	if (!work_list->nb_atoms)
 		return;
@@ -1341,13 +1346,14 @@
 		printf(" ");
 
 	avg = work_list->total_lat / work_list->nb_atoms;
-	timestamp__scnprintf_usec(work_list->max_lat_at, max_lat_at, sizeof(max_lat_at));
+	timestamp__scnprintf_usec(work_list->max_lat_start, max_lat_start, sizeof(max_lat_start));
+	timestamp__scnprintf_usec(work_list->max_lat_end, max_lat_end, sizeof(max_lat_end));
 
-	printf("|%11.3f ms |%9" PRIu64 " | avg:%9.3f ms | max:%9.3f ms | max at: %13s s\n",
+	printf("|%11.3f ms |%9" PRIu64 " | avg:%8.3f ms | max:%8.3f ms | max start: %12s s | max end: %12s s\n",
 	      (double)work_list->total_runtime / NSEC_PER_MSEC,
 		 work_list->nb_atoms, (double)avg / NSEC_PER_MSEC,
 		 (double)work_list->max_lat / NSEC_PER_MSEC,
-		 max_lat_at);
+		 max_lat_start, max_lat_end);
 }
 
 static int pid_cmp(struct work_atoms *l, struct work_atoms *r)
@@ -1523,7 +1529,7 @@
 static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
 			    struct perf_sample *sample, struct machine *machine)
 {
-	const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	const u32 next_pid = evsel__intval(evsel, sample, "next_pid");
 	struct thread *sched_in;
 	struct thread_runtime *tr;
 	int new_shortname;
@@ -1667,8 +1673,8 @@
 {
 	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
 	int this_cpu = sample->cpu, err = 0;
-	u32 prev_pid = perf_evsel__intval(evsel, sample, "prev_pid"),
-	    next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	u32 prev_pid = evsel__intval(evsel, sample, "prev_pid"),
+	    next_pid = evsel__intval(evsel, sample, "next_pid");
 
 	if (sched->curr_pid[this_cpu] != (u32)-1) {
 		/*
@@ -1845,7 +1851,7 @@
  * returns runtime data for event, allocating memory for it the
  * first time it is used.
  */
-static struct evsel_runtime *perf_evsel__get_runtime(struct evsel *evsel)
+static struct evsel_runtime *evsel__get_runtime(struct evsel *evsel)
 {
 	struct evsel_runtime *r = evsel->priv;
 
@@ -1860,10 +1866,9 @@
 /*
  * save last time event was seen per cpu
  */
-static void perf_evsel__save_time(struct evsel *evsel,
-				  u64 timestamp, u32 cpu)
+static void evsel__save_time(struct evsel *evsel, u64 timestamp, u32 cpu)
 {
-	struct evsel_runtime *r = perf_evsel__get_runtime(evsel);
+	struct evsel_runtime *r = evsel__get_runtime(evsel);
 
 	if (r == NULL)
 		return;
@@ -1887,9 +1892,9 @@
 }
 
 /* returns last time this event was seen on the given cpu */
-static u64 perf_evsel__get_time(struct evsel *evsel, u32 cpu)
+static u64 evsel__get_time(struct evsel *evsel, u32 cpu)
 {
-	struct evsel_runtime *r = perf_evsel__get_runtime(evsel);
+	struct evsel_runtime *r = evsel__get_runtime(evsel);
 
 	if ((r == NULL) || (r->last_time == NULL) || (cpu >= r->ncpu))
 		return 0;
@@ -2001,13 +2006,16 @@
 				  u64 t, int state)
 {
 	struct thread_runtime *tr = thread__priv(thread);
-	const char *next_comm = perf_evsel__strval(evsel, sample, "next_comm");
-	const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid");
+	const char *next_comm = evsel__strval(evsel, sample, "next_comm");
+	const u32 next_pid = evsel__intval(evsel, sample, "next_pid");
 	u32 max_cpus = sched->max_cpu + 1;
 	char tstr[64];
 	char nstr[30];
 	u64 wait_time;
 
+	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
+		return;
+
 	timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
 	printf("%15s [%04d] ", tstr, sample->cpu);
 
@@ -2130,8 +2138,8 @@
 			   struct evsel *evsel)
 {
 	/* pid 0 == swapper == idle task */
-	if (strcmp(perf_evsel__name(evsel), "sched:sched_switch") == 0)
-		return perf_evsel__intval(evsel, sample, "prev_pid") == 0;
+	if (strcmp(evsel__name(evsel), "sched:sched_switch") == 0)
+		return evsel__intval(evsel, sample, "prev_pid") == 0;
 
 	return sample->pid == 0;
 }
@@ -2172,7 +2180,7 @@
 		if (node == NULL)
 			break;
 
-		sym = node->sym;
+		sym = node->ms.sym;
 		if (sym) {
 			if (!strcmp(sym->name, "schedule") ||
 			    !strcmp(sym->name, "__schedule") ||
@@ -2328,7 +2336,7 @@
 			itr->last_thread = thread;
 
 			/* copy task callchain when entering to idle */
-			if (perf_evsel__intval(evsel, sample, "next_pid") == 0)
+			if (evsel__intval(evsel, sample, "next_pid") == 0)
 				save_idle_callchain(sched, itr, sample);
 		}
 	}
@@ -2349,10 +2357,10 @@
 	}
 
 	if (sched->idle_hist) {
-		if (strcmp(perf_evsel__name(evsel), "sched:sched_switch"))
+		if (strcmp(evsel__name(evsel), "sched:sched_switch"))
 			rc = true;
-		else if (perf_evsel__intval(evsel, sample, "prev_pid") != 0 &&
-			 perf_evsel__intval(evsel, sample, "next_pid") != 0)
+		else if (evsel__intval(evsel, sample, "prev_pid") != 0 &&
+			 evsel__intval(evsel, sample, "next_pid") != 0)
 			rc = true;
 	}
 
@@ -2393,6 +2401,15 @@
 	printf("\n");
 }
 
+static int timehist_sched_wakeup_ignore(struct perf_tool *tool __maybe_unused,
+					union perf_event *event __maybe_unused,
+					struct evsel *evsel __maybe_unused,
+					struct perf_sample *sample __maybe_unused,
+					struct machine *machine __maybe_unused)
+{
+	return 0;
+}
+
 static int timehist_sched_wakeup_event(struct perf_tool *tool,
 				       union perf_event *event __maybe_unused,
 				       struct evsel *evsel,
@@ -2403,7 +2420,7 @@
 	struct thread *thread;
 	struct thread_runtime *tr = NULL;
 	/* want pid of awakened task not pid in sample */
-	const u32 pid = perf_evsel__intval(evsel, sample, "pid");
+	const u32 pid = evsel__intval(evsel, sample, "pid");
 
 	thread = machine__findnew_thread(machine, 0, pid);
 	if (thread == NULL)
@@ -2439,8 +2456,8 @@
 		return;
 
 	max_cpus = sched->max_cpu + 1;
-	ocpu = perf_evsel__intval(evsel, sample, "orig_cpu");
-	dcpu = perf_evsel__intval(evsel, sample, "dest_cpu");
+	ocpu = evsel__intval(evsel, sample, "orig_cpu");
+	dcpu = evsel__intval(evsel, sample, "dest_cpu");
 
 	thread = machine__findnew_thread(machine, sample->pid, sample->tid);
 	if (thread == NULL)
@@ -2487,7 +2504,7 @@
 	struct thread *thread;
 	struct thread_runtime *tr = NULL;
 	/* want pid of migrated task not pid in sample */
-	const u32 pid = perf_evsel__intval(evsel, sample, "pid");
+	const u32 pid = evsel__intval(evsel, sample, "pid");
 
 	thread = machine__findnew_thread(machine, 0, pid);
 	if (thread == NULL)
@@ -2518,8 +2535,7 @@
 	struct thread_runtime *tr = NULL;
 	u64 tprev, t = sample->time;
 	int rc = 0;
-	int state = perf_evsel__intval(evsel, sample, "prev_state");
-
+	int state = evsel__intval(evsel, sample, "prev_state");
 
 	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_err("problem processing %d event. skipping it\n",
@@ -2543,7 +2559,7 @@
 		goto out;
 	}
 
-	tprev = perf_evsel__get_time(evsel, sample->cpu);
+	tprev = evsel__get_time(evsel, sample->cpu);
 
 	/*
 	 * If start time given:
@@ -2571,7 +2587,8 @@
 	}
 
 	if (!sched->idle_hist || thread->tid == 0) {
-		timehist_update_runtime_stats(tr, t, tprev);
+		if (!cpu_list || test_bit(sample->cpu, cpu_bitmap))
+			timehist_update_runtime_stats(tr, t, tprev);
 
 		if (sched->idle_hist) {
 			struct idle_thread_runtime *itr = (void *)tr;
@@ -2626,7 +2643,7 @@
 		tr->ready_to_run = 0;
 	}
 
-	perf_evsel__save_time(evsel, sample->time, sample->cpu);
+	evsel__save_time(evsel, sample->time, sample->cpu);
 
 	return rc;
 }
@@ -2844,6 +2861,9 @@
 
 	printf("\nIdle stats:\n");
 	for (i = 0; i < idle_max_cpu; ++i) {
+		if (cpu_list && !test_bit(i, cpu_bitmap))
+			continue;
+
 		t = idle_threads[i];
 		if (!t)
 			continue;
@@ -2936,7 +2956,7 @@
 	struct evsel_runtime *er;
 
 	list_for_each_entry(evsel, &evlist->core.entries, core.node) {
-		er = perf_evsel__get_runtime(evsel);
+		er = evsel__get_runtime(evsel);
 		if (er == NULL) {
 			pr_err("Failed to allocate memory for evsel runtime data\n");
 			return -1;
@@ -2954,9 +2974,10 @@
 
 static int perf_sched__timehist(struct perf_sched *sched)
 {
-	const struct evsel_str_handler handlers[] = {
+	struct evsel_str_handler handlers[] = {
 		{ "sched:sched_switch",       timehist_sched_switch_event, },
 		{ "sched:sched_wakeup",	      timehist_sched_wakeup_event, },
+		{ "sched:sched_waking",       timehist_sched_wakeup_event, },
 		{ "sched:sched_wakeup_new",   timehist_sched_wakeup_event, },
 	};
 	const struct evsel_str_handler migrate_handlers[] = {
@@ -2994,6 +3015,12 @@
 	if (IS_ERR(session))
 		return PTR_ERR(session);
 
+	if (cpu_list) {
+		err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
+		if (err < 0)
+			goto out;
+	}
+
 	evlist = session->evlist;
 
 	symbol__init(&session->header.env);
@@ -3008,6 +3035,11 @@
 
 	setup_pager();
 
+	/* prefer sched_waking if it is captured */
+	if (perf_evlist__find_tracepoint_by_name(session->evlist,
+						  "sched:sched_waking"))
+		handlers[1].handler = timehist_sched_wakeup_ignore;
+
 	/* setup per-evsel handlers */
 	if (perf_session__set_tracepoints_handlers(session, handlers))
 		goto out;
@@ -3108,7 +3140,8 @@
 			list_splice(&data->work_list, &this->work_list);
 			if (this->max_lat < data->max_lat) {
 				this->max_lat = data->max_lat;
-				this->max_lat_at = data->max_lat_at;
+				this->max_lat_start = data->max_lat_start;
+				this->max_lat_end = data->max_lat_end;
 			}
 			zfree(&data);
 			return;
@@ -3147,9 +3180,9 @@
 	perf_sched__merge_lat(sched);
 	perf_sched__sort_lat(sched);
 
-	printf("\n -----------------------------------------------------------------------------------------------------------------\n");
-	printf("  Task                  |   Runtime ms  | Switches | Average delay ms | Maximum delay ms | Maximum delay at       |\n");
-	printf(" -----------------------------------------------------------------------------------------------------------------\n");
+	printf("\n -------------------------------------------------------------------------------------------------------------------------------------------\n");
+	printf("  Task                  |   Runtime ms  | Switches | Avg delay ms    | Max delay ms    | Max delay start           | Max delay end          |\n");
+	printf(" -------------------------------------------------------------------------------------------------------------------------------------------\n");
 
 	next = rb_first_cached(&sched->sorted_atom_root);
 
@@ -3304,6 +3337,16 @@
 	sort_dimension__add("pid", &sched->cmp_pid);
 }
 
+static bool schedstat_events_exposed(void)
+{
+	/*
+	 * Select "sched:sched_stat_wait" event to check
+	 * whether schedstat tracepoints are exposed.
+	 */
+	return IS_ERR(trace_event__tp_format("sched", "sched_stat_wait")) ?
+		false : true;
+}
+
 static int __cmd_record(int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
@@ -3315,17 +3358,33 @@
 		"-m", "1024",
 		"-c", "1",
 		"-e", "sched:sched_switch",
-		"-e", "sched:sched_stat_wait",
-		"-e", "sched:sched_stat_sleep",
-		"-e", "sched:sched_stat_iowait",
 		"-e", "sched:sched_stat_runtime",
 		"-e", "sched:sched_process_fork",
-		"-e", "sched:sched_wakeup",
 		"-e", "sched:sched_wakeup_new",
 		"-e", "sched:sched_migrate_task",
 	};
 
-	rec_argc = ARRAY_SIZE(record_args) + argc - 1;
+	/*
+	 * The tracepoints trace_sched_stat_{wait, sleep, iowait}
+	 * are not exposed to user if CONFIG_SCHEDSTATS is not set,
+	 * to prevent "perf sched record" execution failure, determine
+	 * whether to record schedstat events according to actual situation.
+	 */
+	const char * const schedstat_args[] = {
+		"-e", "sched:sched_stat_wait",
+		"-e", "sched:sched_stat_sleep",
+		"-e", "sched:sched_stat_iowait",
+	};
+	unsigned int schedstat_argc = schedstat_events_exposed() ?
+		ARRAY_SIZE(schedstat_args) : 0;
+
+	struct tep_event *waking_event;
+
+	/*
+	 * +2 for either "-e", "sched:sched_wakeup" or
+	 * "-e", "sched:sched_waking"
+	 */
+	rec_argc = ARRAY_SIZE(record_args) + 2 + schedstat_argc + argc - 1;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
 	if (rec_argv == NULL)
@@ -3334,6 +3393,16 @@
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
 		rec_argv[i] = strdup(record_args[i]);
 
+	rec_argv[i++] = "-e";
+	waking_event = trace_event__tp_format("sched", "sched_waking");
+	if (!IS_ERR(waking_event))
+		rec_argv[i++] = strdup("sched:sched_waking");
+	else
+		rec_argv[i++] = strdup("sched:sched_wakeup");
+
+	for (j = 0; j < schedstat_argc; j++)
+		rec_argv[i++] = strdup(schedstat_args[j]);
+
 	for (j = 1; j < (unsigned int)argc; j++, i++)
 		rec_argv[i] = argv[j];
 
@@ -3429,6 +3498,7 @@
 		   "analyze events only for given process id(s)"),
 	OPT_STRING('t', "tid", &symbol_conf.tid_list_str, "tid[,tid...]",
 		   "analyze events only for given thread id(s)"),
+	OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
 	OPT_PARENT(sched_options)
 	};