summaryrefslogtreecommitdiffstats
path: root/kernel/time/tick-sched.c
blob: 2ec7c00228f3c981568b1dc911b4a91a83148d91 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
/*
 *  linux/kernel/time/tick-sched.c
 *
 *  Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
 *  Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
 *  Copyright(C) 2006-2007  Timesys Corp., Thomas Gleixner
 *
 *  No idle tick implementation for low and high resolution timers
 *
 *  Started by: Thomas Gleixner and Ingo Molnar
 *
 *  Distribute under GPLv2.
 */
#include <linux/cpu.h>
#include <linux/err.h>
#include <linux/hrtimer.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/percpu.h>
#include <linux/profile.h>
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/irq_work.h>
#include <linux/posix-timers.h>
#include <linux/context_tracking.h>

#include <asm/irq_regs.h>

#include "tick-internal.h"

#include <trace/events/timer.h>

/*
 * Per-CPU nohz control structure
 */
static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);

struct tick_sched *tick_get_tick_sched(int cpu)
{
	return &per_cpu(tick_cpu_sched, cpu);
}

#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
/*
 * The time, when the last jiffy update happened. Protected by jiffies_lock.
 */
static ktime_t last_jiffies_update;

/*
 * Must be called with interrupts disabled !
 */
static void tick_do_update_jiffies64(ktime_t now)
{
	unsigned long ticks = 0;
	ktime_t delta;

	/*
	 * Do a quick check without holding jiffies_lock:
	 */
	delta = ktime_sub(now, last_jiffies_update);
	if (delta.tv64 < tick_period.tv64)
		return;

	/* Reevaluate with jiffies_lock held */
	write_seqlock(&jiffies_lock);

	delta = ktime_sub(now, last_jiffies_update);
	if (delta.tv64 >= tick_period.tv64) {

		delta = ktime_sub(delta, tick_period);
		last_jiffies_update = ktime_add(last_jiffies_update,
						tick_period);

		/* Slow path for long timeouts */
		if (unlikely(delta.tv64 >= tick_period.tv64)) {
			s64 incr = ktime_to_ns(tick_period);

			ticks = ktime_divns(delta, incr);

			last_jiffies_update = ktime_add_ns(last_jiffies_update,
							   incr * ticks);
		}
		do_timer(++ticks);

		/* Keep the tick_next_period variable up to date */
		tick_next_period = ktime_add(last_jiffies_update, tick_period);
	} else {
		write_sequnlock(&jiffies_lock);
		return;
	}
	write_sequnlock(&jiffies_lock);
	update_wall_time();
}

/*
 * Initialize and return retrieve the jiffies update.
 */
static ktime_t tick_init_jiffy_update(void)
{
	ktime_t period;

	write_seqlock(&jiffies_lock);
	/* Did we start the jiffies update yet ? */
	if (last_jiffies_update.tv64 == 0)
		last_jiffies_update = tick_next_period;
	period = last_jiffies_update;
	write_sequnlock(&jiffies_lock);
	return period;
}


static void tick_sched_do_timer(ktime_t now)
{
	int cpu = smp_processor_id();

#ifdef CONFIG_NO_HZ_COMMON
	/*
	 * Check if the do_timer duty was dropped. We don't care about
	 * concurrency: This happens only when the CPU in charge went
	 * into a long sleep. If two CPUs happen to assign themselves to
	 * this duty, then the jiffies update is still serialized by
	 * jiffies_lock.
	 */
	if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)
	    && !tick_nohz_full_cpu(cpu))
		tick_do_timer_cpu = cpu;
#endif

	/* Check, if the jiffies need an update */
	if (tick_do_timer_cpu == cpu)
		tick_do_update_jiffies64(now);
}

static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
{
#ifdef CONFIG_NO_HZ_COMMON
	/*
	 * When we are idle and the tick is stopped, we have to touch
	 * the watchdog as we might not schedule for a really long
	 * time. This happens on complete idle SMP systems while
	 * waiting on the login prompt. We also increment the "start of
	 * idle" jiffy stamp so the idle accounting adjustment we do
	 * when we go busy again does not account too much ticks.
	 */
	if (ts->tick_stopped) {
		touch_softlockup_watchdog_sched();
		if (is_idle_task(current))
			ts->idle_jiffies++;
	}
#endif
	update_process_times(user_mode(regs));
	profile_tick(CPU_PROFILING);
}
#endif

#ifdef CONFIG_NO_HZ_FULL
cpumask_var_t tick_nohz_full_mask;
cpumask_var_t housekeeping_mask;
bool tick_nohz_full_running;
static atomic_t tick_dep_mask;

static bool check_tick_dependency(atomic_t *dep)
{
	int val = atomic_read(dep);

	if (val & TICK_DEP_MASK_POSIX_TIMER) {
		trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER);
		return true;
	}

	if (val & TICK_DEP_MASK_PERF_EVENTS) {
		trace_tick_stop(0, TICK_DEP_MASK_PERF_EVENTS);
		return true;
	}

	if (val & TICK_DEP_MASK_SCHED) {
		trace_tick_stop(0, TICK_DEP_MASK_SCHED);
		return true;
	}

	if (val & TICK_DEP_MASK_CLOCK_UNSTABLE) {
		trace_tick_stop(0, TICK_DEP_MASK_CLOCK_UNSTABLE);
		return true;
	}

	return false;
}

static bool can_stop_full_tick(struct tick_sched *ts)
{
	WARN_ON_ONCE(!irqs_disabled());

	if (check_tick_dependency(&tick_dep_mask))
		return false;

	if (check_tick_dependency(&ts->tick_dep_mask))
		return false;

	if (check_tick_dependency(&current->tick_dep_mask))
		return false;

	if (check_tick_dependency(&current->signal->tick_dep_mask))
		return false;

	return true;
}

static void nohz_full_kick_func(struct irq_work *work)
{
	/* Empty, the tick restart happens on tick_nohz_irq_exit() */
}

static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
	.func = nohz_full_kick_func,
};

/*
 * Kick this CPU if it's full dynticks in order to force it to
 * re-evaluate its dependency on the tick and restart it if necessary.
 * This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(),
 * is NMI safe.
 */
static void tick_nohz_full_kick(void)
{
	if (!tick_nohz_full_cpu(smp_processor_id()))
		return;

	irq_work_queue(this_cpu_ptr(&nohz_full_kick_work));
}

/*
 * Kick the CPU if it's full dynticks in order to force it to
 * re-evaluate its dependency on the tick and restart it if necessary.
 */
void tick_nohz_full_kick_cpu(int cpu)
{
	if (!tick_nohz_full_cpu(cpu))
		return;

	irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu);
}

/*
 * Kick all full dynticks CPUs in order to force these to re-evaluate
 * their dependency on the tick and restart it if necessary.
 */
static void tick_nohz_full_kick_all(void)
{
	int cpu;

	if (!tick_nohz_full_running)
		return;

	preempt_disable();
	for_each_cpu_and(cpu, tick_nohz_full_mask, cpu_online_mask)
		tick_nohz_full_kick_cpu(cpu);
	preempt_enable();
}

static void tick_nohz_dep_set_all(atomic_t *dep,
				  enum tick_dep_bits bit)
{
	int prev;

	prev = atomic_fetch_or(BIT(bit), dep);
	if (!prev)
		tick_nohz_full_kick_all();
}

/*
 * Set a global tick dependency. Used by perf events that rely on freq and
 * by unstable clock.
 */
void tick_nohz_dep_set(enum tick_dep_bits bit)
{
	tick_nohz_dep_set_all(&tick_dep_mask, bit);
}

void tick_nohz_dep_clear(enum tick_dep_bits bit)
{
	atomic_andnot(BIT(bit), &tick_dep_mask);
}

/*
 * Set per-CPU tick dependency. Used by scheduler and perf events in order to
 * manage events throttling.
 */
void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit)
{
	int prev;
	struct tick_sched *ts;

	ts = per_cpu_ptr(&tick_cpu_sched, cpu);

	prev = atomic_fetch_or(BIT(bit), &ts->tick_dep_mask);
	if (!prev) {
		preempt_disable();
		/* Perf needs local kick that is NMI safe */
		if (cpu == smp_processor_id()) {
			tick_nohz_full_kick();
		} else {
			/* Remote irq work not NMI-safe */
			if (!WARN_ON_ONCE(in_nmi()))
				tick_nohz_full_kick_cpu(cpu);
		}
		preempt_enable();
	}
}

void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
{
	struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu);

	atomic_andnot(BIT(bit), &ts->tick_dep_mask);
}

/*
 * Set a per-task tick dependency. Posix CPU timers need this in order to elapse
 * per task timers.
 */
void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit)
{
	/*
	 * We could optimize this with just kicking the target running the task
	 * if that noise matters for nohz full users.
	 */
	tick_nohz_dep_set_all(&tsk->tick_dep_mask, bit);
}

void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit)
{
	atomic_andnot(BIT(bit), &tsk->tick_dep_mask);
}

/*
 * Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse
 * per process timers.
 */
void tick_nohz_dep_set_signal(struct signal_struct *sig, enum tick_dep_bits bit)
{
	tick_nohz_dep_set_all(&sig->tick_dep_mask, bit);
}

void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit)
{
	atomic_andnot(BIT(bit), &sig->tick_dep_mask);
}

/*
 * Re-evaluate the need for the tick as we switch the current task.
 * It might need the tick due to per task/process properties:
 * perf events, posix CPU timers, ...
 */
void __tick_nohz_task_switch(void)
{
	unsigned long flags;
	struct tick_sched *ts;

	local_irq_save(flags);

	if (!tick_nohz_full_cpu(smp_processor_id()))
		goto out;

	ts = this_cpu_ptr(&tick_cpu_sched);

	if (ts->tick_stopped) {
		if (atomic_read(&current->tick_dep_mask) ||
		    atomic_read(&current->signal->tick_dep_mask))
			tick_nohz_full_kick();
	}
out:
	local_irq_restore(flags);
}

/* Parse the boot-time nohz CPU list from the kernel parameters. */
static int __init tick_nohz_full_setup(char *str)
{
	alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
	if (cpulist_parse(str, tick_nohz_full_mask) < 0) {
		pr_warn("NO_HZ: Incorrect nohz_full cpumask\n");
		free_bootmem_cpumask_var(tick_nohz_full_mask);
		return 1;
	}
	tick_nohz_full_running = true;

	return 1;
}
__setup("nohz_full=", tick_nohz_full_setup);

static int tick_nohz_cpu_down_callback(struct notifier_block *nfb,
				       unsigned long action,
				       void *hcpu)
{
	unsigned int cpu = (unsigned long)hcpu;

	switch (action & ~CPU_TASKS_FROZEN) {
	case CPU_DOWN_PREPARE:
		/*
		 * The boot CPU handles housekeeping duty (unbound timers,
		 * workqueues, timekeeping, ...) on behalf of full dynticks
		 * CPUs. It must remain online when nohz full is enabled.
		 */
		if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
			return NOTIFY_BAD;
		break;
	}
	return NOTIFY_OK;
}

static int tick_nohz_init_all(void)
{
	int err = -1;

#ifdef CONFIG_NO_HZ_FULL_ALL
	if (!alloc_cpumask_var(&tick_nohz_full_mask, GFP_KERNEL)) {
		WARN(1, "NO_HZ: Can't allocate full dynticks cpumask\n");
		return err;
	}
	err = 0;
	cpumask_setall(tick_nohz_full_mask);
	tick_nohz_full_running = true;
#endif
	return err;
}

void __init tick_nohz_init(void)
{
	int cpu;

	if (!tick_nohz_full_running) {
		if (tick_nohz_init_all() < 0)
			return;
	}

	if (!alloc_cpumask_var(&housekeeping_mask, GFP_KERNEL)) {
		WARN(1, "NO_HZ: Can't allocate not-full dynticks cpumask\n");
		cpumask_clear(tick_nohz_full_mask);
		tick_nohz_full_running = false;
		return;
	}

	/*
	 * Full dynticks uses irq work to drive the tick rescheduling on safe
	 * locking contexts. But then we need irq work to raise its own
	 * interrupts to avoid circular dependency on the tick
	 */
	if (!arch_irq_work_has_interrupt()) {
		pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support irq work self-IPIs\n");
		cpumask_clear(tick_nohz_full_mask);
		cpumask_copy(housekeeping_mask, cpu_possible_mask);
		tick_nohz_full_running = false;
		return;
	}

	cpu = smp_processor_id();

	if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
		pr_warn("NO_HZ: Clearing %d from nohz_full range for timekeeping\n",
			cpu);
		cpumask_clear_cpu(cpu, tick_nohz_full_mask);
	}

	cpumask_andnot(housekeeping_mask,
		       cpu_possible_mask, tick_nohz_full_mask);

	for_each_cpu(cpu, tick_nohz_full_mask)
		context_tracking_cpu_set(cpu);

	cpu_notifier(tick_nohz_cpu_down_callback, 0);
	pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n",
		cpumask_pr_args(tick_nohz_full_mask));

	/*
	 * We need at least one CPU to handle housekeeping work such
	 * as timekeeping, unbound timers, workqueues, ...
	 */
	WARN_ON_ONCE(cpumask_empty(housekeeping_mask));
}
#endif

/*
 * NOHZ - aka dynamic tick functionality
 */
#ifdef CONFIG_NO_HZ_COMMON
/*
 * NO HZ enabled ?
 */
bool tick_nohz_enabled __read_mostly  = true;
unsigned long tick_nohz_active  __read_mostly;
/*
 * Enable / Disable tickless mode
 */
static int __init setup_tick_nohz(char *str)
{
	return (kstrtobool(str, &tick_nohz_enabled) == 0);
}

__setup("nohz=", setup_tick_nohz);

int tick_nohz_tick_stopped(void)
{
	return __this_cpu_read(tick_cpu_sched.tick_stopped);
}

/**
 * tick_nohz_update_jiffies - update jiffies when idle was interrupted
 *
 * Called from interrupt entry when the CPU was idle
 *
 * In case the sched_tick was stopped on this CPU, we have to check if jiffies
 * must be updated. Otherwise an interrupt handler could use a stale jiffy
 * value. We do this unconditionally on any CPU, as we don't know whether the
 * CPU, which has the update task assigned is in a long sleep.
 */
static void tick_nohz_update_jiffies(ktime_t now)
{
	unsigned long flags;

	__this_cpu_write(tick_cpu_sched.idle_waketime, now);

	local_irq_save(flags);
	tick_do_update_jiffies64(now);
	local_irq_restore(flags);

	touch_softlockup_watchdog_sched();
}

/*
 * Updates the per-CPU time idle statistics counters
 */
static void
update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_update_time)
{
	ktime_t delta;

	if (ts->idle_active) {
		delta = ktime_sub(now, ts->idle_entrytime);
		if (nr_iowait_cpu(cpu) > 0)
			ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
		else
			ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
		ts->idle_entrytime = now;
	}

	if (last_update_time)
		*last_update_time = ktime_to_us(now);

}

static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
{
	update_ts_time_stats(smp_processor_id(), ts, now, NULL);
	ts->idle_active = 0;

	sched_clock_idle_wakeup_event(0);
}

static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
{
	ktime_t now = ktime_get();

	ts->idle_entrytime = now;
	ts->idle_active = 1;
	sched_clock_idle_sleep_event();
	return now;
}

/**
 * get_cpu_idle_time_us - get the total idle time of a CPU
 * @cpu: CPU number to query
 * @last_update_time: variable to store update time in. Do not update
 * counters if NULL.
 *
 * Return the cumulative idle time (since boot) for a given
 * CPU, in microseconds.
 *
 * This time is measured via accounting rather than sampling,
 * and is as accurate as ktime_get() is.
 *
 * This function returns -1 if NOHZ is not enabled.
 */
u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
{
	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
	ktime_t now, idle;

	if (!tick_nohz_active)
		return -1;

	now = ktime_get();
	if (last_update_time) {
		update_ts_time_stats(cpu, ts, now, last_update_time);
		idle = ts->idle_sleeptime;
	} else {
		if (ts->idle_active && !nr_iowait_cpu(cpu)) {
			ktime_t delta = ktime_sub(now, ts->idle_entrytime);

			idle = ktime_add(ts->idle_sleeptime, delta);
		} else {
			idle = ts->idle_sleeptime;
		}
	}

	return ktime_to_us(idle);

}
EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);

/**
 * get_cpu_iowait_time_us - get the total iowait time of a CPU
 * @cpu: CPU number to query
 * @last_update_time: variable to store update time in. Do not update
 * counters if NULL.
 *
 * Return the cumulative iowait time (since boot) for a given
 * CPU, in microseconds.
 *
 * This time is measured via accounting rather than sampling,
 * and is as accurate as ktime_get() is.
 *
 * This function returns -1 if NOHZ is not enabled.
 */
u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
{
	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
	ktime_t now, iowait;

	if (!tick_nohz_active)
		return -1;

	now = ktime_get();
	if (last_update_time) {
		update_ts_time_stats(cpu, ts, now, last_update_time);
		iowait = ts->iowait_sleeptime;
	} else {
		if (ts->idle_active && nr_iowait_cpu(cpu) > 0) {
			ktime_t delta = ktime_sub(now, ts->idle_entrytime);

			iowait = ktime_add(ts->iowait_sleeptime, delta);
		} else {
			iowait = ts->iowait_sleeptime;
		}
	}

	return ktime_to_us(iowait);
}
EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);

static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
{
	hrtimer_cancel(&ts->sched_timer);
	hrtimer_set_expires(&ts->sched_timer, ts->last_tick);

	/* Forward the time to expire in the future */
	hrtimer_forward(&ts->sched_timer, now, tick_period);

	if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
		hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
	else
		tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
}

static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
					 ktime_t now, int cpu)
{
	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
	u64 basemono, next_tick, next_tmr, next_rcu, delta, expires;
	unsigned long seq, basejiff;
	ktime_t	tick;

	/* Read jiffies and the time when jiffies were updated last */
	do {
		seq = read_seqbegin(&jiffies_lock);
		basemono = last_jiffies_update.tv64;
		basejiff = jiffies;
	} while (read_seqretry(&jiffies_lock, seq));
	ts->last_jiffies = basejiff;

	if (rcu_needs_cpu(basemono, &next_rcu) ||
	    arch_needs_cpu() || irq_work_needs_cpu()) {
		next_tick = basemono + TICK_NSEC;
	} else {
		/*
		 * Get the next pending timer. If high resolution
		 * timers are enabled this only takes the timer wheel
		 * timers into account. If high resolution timers are
		 * disabled this also looks at the next expiring
		 * hrtimer.
		 */
		next_tmr = get_next_timer_interrupt(basejiff, basemono);
		ts->next_timer = next_tmr;
		/* Take the next rcu event into account */
		next_tick = next_rcu < next_tmr ? next_rcu : next_tmr;
	}

	/*
	 * If the tick is due in the next period, keep it ticking or
	 * force prod the timer.
	 */
	delta = next_tick - basemono;
	if (delta <= (u64)TICK_NSEC) {
		tick.tv64 = 0;

		/*
		 * Tell the timer code that the base is not idle, i.e. undo
		 * the effect of get_next_timer_interrupt():
		 */
		timer_clear_idle();
		/*
		 * We've not stopped the tick yet, and there's a timer in the
		 * next period, so no point in stopping it either, bail.
		 */
		if (!ts->tick_stopped)
			goto out;

		/*
		 * If, OTOH, we did stop it, but there's a pending (expired)
		 * timer reprogram the timer hardware to fire now.
		 *
		 * We will not restart the tick proper, just prod the timer
		 * hardware into firing an interrupt to process the pending
		 * timers. Just like tick_irq_exit() will not restart the tick
		 * for 'normal' interrupts.
		 *
		 * Only once we exit the idle loop will we re-enable the tick,
		 * see tick_nohz_idle_exit().
		 */
		if (delta == 0) {
			tick_nohz_restart(ts, now);
			goto out;
		}
	}

	/*
	 * If this CPU is the one which updates jiffies, then give up
	 * the assignment and let it be taken by the CPU which runs
	 * the tick timer next, which might be this CPU as well. If we
	 * don't drop this here the jiffies might be stale and
	 * do_timer() never invoked. Keep track of the fact that it
	 * was the one which had the do_timer() duty last. If this CPU
	 * is the one which had the do_timer() duty last, we limit the
	 * sleep time to the timekeeping max_deferment value.
	 * Otherwise we can sleep as long as we want.
	 */
	delta = timekeeping_max_deferment();
	if (cpu == tick_do_timer_cpu) {
		tick_do_timer_cpu = TICK_DO_TIMER_NONE;
		ts->do_timer_last = 1;
	} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
		delta = KTIME_MAX;
		ts->do_timer_last = 0;
	} else if (!ts->do_timer_last) {
		delta = KTIME_MAX;
	}

#ifdef CONFIG_NO_HZ_FULL
	/* Limit the tick delta to the maximum scheduler deferment */
	if (!ts->inidle)
		delta = min(delta, scheduler_tick_max_deferment());
#endif

	/* Calculate the next expiry time */
	if (delta < (KTIME_MAX - basemono))
		expires = basemono + delta;
	else
		expires = KTIME_MAX;

	expires = min_t(u64, expires, next_tick);
	tick.tv64 = expires;

	/* Skip reprogram of event if its not changed */
	if (ts->tick_stopped && (expires == dev->next_event.tv64))
		goto out;

	/*
	 * nohz_stop_sched_tick can be called several times before
	 * the nohz_restart_sched_tick is called. This happens when
	 * interrupts arrive which do not cause a reschedule. In the
	 * first call we save the current tick time, so we can restart
	 * the scheduler tick in nohz_restart_sched_tick.
	 */
	if (!ts->tick_stopped) {
		nohz_balance_enter_idle(cpu);
		calc_load_enter_idle();
		cpu_load_update_nohz_start();

		ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
		ts->tick_stopped = 1;
		trace_tick_stop(1, TICK_DEP_MASK_NONE);
	}

	/*
	 * If the expiration time == KTIME_MAX, then we simply stop
	 * the tick timer.
	 */
	if (unlikely(expires == KTIME_MAX)) {
		if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
			hrtimer_cancel(&ts->sched_timer);
		goto out;
	}

	if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
		hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED);
	else
		tick_program_event(tick, 1);
out:
	/* Update the estimated sleep length */
	ts->sleep_length = ktime_sub(dev->next_event, now);
	return tick;
}

static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
{
	/* Update jiffies first */
	tick_do_update_jiffies64(now);
	cpu_load_update_nohz_stop();

	/*
	 * Clear the timer idle flag, so we avoid IPIs on remote queueing and
	 * the clock forward checks in the enqueue path:
	 */
	timer_clear_idle();

	calc_load_exit_idle();
	touch_softlockup_watchdog_sched();
	/*
	 * Cancel the scheduled timer and restore the tick
	 */
	ts->tick_stopped  = 0;
	ts->idle_exittime = now;

	tick_nohz_restart(ts, now);
}

static void tick_nohz_full_update_tick(struct tick_sched *ts)
{
#ifdef CONFIG_NO_HZ_FULL
	int cpu = smp_processor_id();

	if (!tick_nohz_full_cpu(cpu))
		return;

	if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE)
		return;

	if (can_stop_full_tick(ts))
		tick_nohz_stop_sched_tick(ts, ktime_get(), cpu);
	else if (ts->tick_stopped)
		tick_nohz_restart_sched_tick(ts, ktime_get());
#endif
}

static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
{
	/*
	 * If this CPU is offline and it is the one which updates
	 * jiffies, then give up the assignment and let it be taken by
	 * the CPU which runs the tick timer next. If we don't drop
	 * this here the jiffies might be stale and do_timer() never
	 * invoked.
	 */
	if (unlikely(!cpu_online(cpu))) {
		if (cpu == tick_do_timer_cpu)
			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
		return false;
	}

	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) {
		ts->sleep_length = (ktime_t) { .tv64 = NSEC_PER_SEC/HZ };
		return false;
	}

	if (need_resched())
		return false;

	if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
		static int ratelimit;

		if (ratelimit < 10 &&
		    (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
			pr_warn("NOHZ: local_softirq_pending %02x\n",
				(unsigned int) local_softirq_pending());
			ratelimit++;
		}
		return false;
	}

	if (tick_nohz_full_enabled()) {
		/*
		 * Keep the tick alive to guarantee timekeeping progression
		 * if there are full dynticks CPUs around
		 */
		if (tick_do_timer_cpu == cpu)
			return false;
		/*
		 * Boot safety: make sure the timekeeping duty has been
		 * assigned before entering dyntick-idle mode,
		 */
		if (tick_do_timer_cpu == TICK_DO_TIMER_NONE)
			return false;
	}

	return true;
}

static void __tick_nohz_idle_enter(struct tick_sched *ts)
{
	ktime_t now, expires;
	int cpu = smp_processor_id();

	now = tick_nohz_start_idle(ts);

	if (can_stop_idle_tick(cpu, ts)) {
		int was_stopped = ts->tick_stopped;

		ts->idle_calls++;

		expires = tick_nohz_stop_sched_tick(ts, now, cpu);
		if (expires.tv64 > 0LL) {
			ts->idle_sleeps++;
			ts->idle_expires = expires;
		}

		if (!was_stopped && ts->tick_stopped)
			ts->idle_jiffies = ts->last_jiffies;
	}
}

/**
 * tick_nohz_idle_enter - stop the idle tick from the idle task
 *
 * When the next event is more than a tick into the future, stop the idle tick
 * Called when we start the idle loop.
 *
 * The arch is responsible of calling:
 *
 * - rcu_idle_enter() after its last use of RCU before the CPU is put
 *  to sleep.
 * - rcu_idle_exit() before the first use of RCU after the CPU is woken up.
 */
void tick_nohz_idle_enter(void)
{
	struct tick_sched *ts;

	WARN_ON_ONCE(irqs_disabled());

	/*
	 * Update the idle state in the scheduler domain hierarchy
	 * when tick_nohz_stop_sched_tick() is called from the idle loop.
	 * State will be updated to busy during the first busy tick after
	 * exiting idle.
	 */
	set_cpu_sd_state_idle();

	local_irq_disable();

	ts = this_cpu_ptr(&tick_cpu_sched);
	ts->inidle = 1;
	__tick_nohz_idle_enter(ts);

	local_irq_enable();
}

/**
 * tick_nohz_irq_exit - update next tick event from interrupt exit
 *
 * When an interrupt fires while we are idle and it doesn't cause
 * a reschedule, it may still add, modify or delete a timer, enqueue
 * an RCU callback, etc...
 * So we need to re-calculate and reprogram the next tick event.
 */
void tick_nohz_irq_exit(void)
{
	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);

	if (ts->inidle)
		__tick_nohz_idle_enter(ts);
	else
		tick_nohz_full_update_tick(ts);
}

/**
 * tick_nohz_get_sleep_length - return the length of the current sleep
 *
 * Called from power state control code with interrupts disabled
 */
ktime_t tick_nohz_get_sleep_length(void)
{
	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);

	return ts->sleep_length;
}

static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
{
#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
	unsigned long ticks;

	if (vtime_accounting_cpu_enabled())
		return;
	/*
	 * We stopped the tick in idle. Update process times would miss the
	 * time we slept as update_process_times does only a 1 tick
	 * accounting. Enforce that this is accounted to idle !
	 */
	ticks = jiffies - ts->idle_jiffies;
	/*
	 * We might be one off. Do not randomly account a huge number of ticks!
	 */
	if (ticks && ticks < LONG_MAX)
		account_idle_ticks(ticks);
#endif
}

/**
 * tick_nohz_idle_exit - restart the idle tick from the idle task
 *
 * Restart the idle tick when the CPU is woken up from idle
 * This also exit the RCU extended quiescent state. The CPU
 * can use RCU again after this function is called.
 */
void tick_nohz_idle_exit(void)
{
	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
	ktime_t now;

	local_irq_disable();

	WARN_ON_ONCE(!ts->inidle);

	ts->inidle = 0;

	if (ts->idle_active || ts->tick_stopped)
		now = ktime_get();

	if (ts->idle_active)
		tick_nohz_stop_idle(ts, now);

	if (ts->tick_stopped) {
		tick_nohz_restart_sched_tick(ts, now);
		tick_nohz_account_idle_ticks(ts);
	}

	local_irq_enable();
}

/*
 * The nohz low res interrupt handler
 */
static void tick_nohz_handler(struct clock_event_device *dev)
{
	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
	struct pt_regs *regs = get_irq_regs();
	ktime_t now = ktime_get();

	dev->next_event.tv64 = KTIME_MAX;

	tick_sched_do_timer(now);
	tick_sched_handle(ts, regs);

	/* No need to reprogram if we are running tickless  */
	if (unlikely(ts->tick_stopped))
		return;

	hrtimer_forward(&ts->sched_timer, now, tick_period);
	tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
}

static inline void tick_nohz_activate(struct tick_sched *ts, int mode)
{
	if (!tick_nohz_enabled)
		return;
	ts->nohz_mode = mode;
	/* One update is enough */
	if (!test_and_set_bit(0, &tick_nohz_active))
		timers_update_migration(true);
}

/**
 * tick_nohz_switch_to_nohz - switch to nohz mode
 */
static void tick_nohz_switch_to_nohz(void)
{
	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
	ktime_t next;

	if (!tick_nohz_enabled)
		return;

	if (tick_switch_to_oneshot(tick_nohz_handler))
		return;

	/*
	 * Recycle the hrtimer in ts, so we can share the
	 * hrtimer_forward with the highres code.
	 */
	hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
	/* Get the next period */
	next = tick_init_jiffy_update();

	hrtimer_set_expires(&ts->sched_timer, next);
	hrtimer_forward_now(&ts->sched_timer, tick_period);
	tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
	tick_nohz_activate(ts, NOHZ_MODE_LOWRES);
}

static inline void tick_nohz_irq_enter(void)
{
	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
	ktime_t now;

	if (!ts->idle_active && !ts->tick_stopped)
		return;
	now = ktime_get();
	if (ts->idle_active)
		tick_nohz_stop_idle(ts, now);
	if (ts->tick_stopped)
		tick_nohz_update_jiffies(now);
}

#else

static inline void tick_nohz_switch_to_nohz(void) { }
static inline void tick_nohz_irq_enter(void) { }
static inline void tick_nohz_activate(struct tick_sched *ts, int mode) { }

#endif /* CONFIG_NO_HZ_COMMON */

/*
 * Called from irq_enter to notify about the possible interruption of idle()
 */
void tick_irq_enter(void)
{
	tick_check_oneshot_broadcast_this_cpu();
	tick_nohz_irq_enter();
}

/*
 * High resolution timer specific code
 */
#ifdef CONFIG_HIGH_RES_TIMERS
/*
 * We rearm the timer until we get disabled by the idle code.
 * Called with interrupts disabled.
 */
static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
{
	struct tick_sched *ts =
		container_of(timer, struct tick_sched, sched_timer);
	struct pt_regs *regs = get_irq_regs();
	ktime_t now = ktime_get();

	tick_sched_do_timer(now);

	/*
	 * Do not call, when we are not in irq context and have
	 * no valid regs pointer
	 */
	if (regs)
		tick_sched_handle(ts, regs);

	/* No need to reprogram if we are in idle or full dynticks mode */
	if (unlikely(ts->tick_stopped))
		return HRTIMER_NORESTART;

	hrtimer_forward(timer, now, tick_period);

	return HRTIMER_RESTART;
}

static int sched_skew_tick;

static int __init skew_tick(char *str)
{
	get_option(&str, &sched_skew_tick);

	return 0;
}
early_param("skew_tick", skew_tick);

/**
 * tick_setup_sched_timer - setup the tick emulation timer
 */
void tick_setup_sched_timer(void)
{
	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
	ktime_t now = ktime_get();

	/*
	 * Emulate tick processing via per-CPU hrtimers:
	 */
	hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
	ts->sched_timer.function = tick_sched_timer;

	/* Get the next period (per-CPU) */
	hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());

	/* Offset the tick to avert jiffies_lock contention. */
	if (sched_skew_tick) {
		u64 offset = ktime_to_ns(tick_period) >> 1;
		do_div(offset, num_possible_cpus());
		offset *= smp_processor_id();
		hrtimer_add_expires_ns(&ts->sched_timer, offset);
	}

	hrtimer_forward(&ts->sched_timer, now, tick_period);
	hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED);
	tick_nohz_activate(ts, NOHZ_MODE_HIGHRES);
}
#endif /* HIGH_RES_TIMERS */

#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS
void tick_cancel_sched_timer(int cpu)
{
	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);

# ifdef CONFIG_HIGH_RES_TIMERS
	if (ts->sched_timer.base)
		hrtimer_cancel(&ts->sched_timer);
# endif

	memset(ts, 0, sizeof(*ts));
}
#endif

/**
 * Async notification about clocksource changes
 */
void tick_clock_notify(void)
{
	int cpu;

	for_each_possible_cpu(cpu)
		set_bit(0, &per_cpu(tick_cpu_sched, cpu).check_clocks);
}

/*
 * Async notification about clock event changes
 */
void tick_oneshot_notify(void)
{
	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);

	set_bit(0, &ts->check_clocks);
}

/**
 * Check, if a change happened, which makes oneshot possible.
 *
 * Called cyclic from the hrtimer softirq (driven by the timer
 * softirq) allow_nohz signals, that we can switch into low-res nohz
 * mode, because high resolution timers are disabled (either compile
 * or runtime). Called with interrupts disabled.
 */
int tick_check_oneshot_change(int allow_nohz)
{
	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);

	if (!test_and_clear_bit(0, &ts->check_clocks))
		return 0;

	if (ts->nohz_mode != NOHZ_MODE_INACTIVE)
		return 0;

	if (!timekeeping_valid_for_hres() || !tick_is_oneshot_available())
		return 0;

	if (!allow_nohz)
		return 1;

	tick_nohz_switch_to_nohz();
	return 0;
}
OpenPOWER on IntegriCloud