aboutsummaryrefslogtreecommitdiff
path: root/kernel/sched_fair.c
blob: ee3771850aaf1548e41bdcf224e95301d797a5e1 (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
/*
 * Completely Fair Scheduling (CFS) Class (SCHED_NORMAL/SCHED_BATCH)
 *
 *  Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
 *
 *  Interactivity improvements by Mike Galbraith
 *  (C) 2007 Mike Galbraith <efault@gmx.de>
 *
 *  Various enhancements by Dmitry Adamushko.
 *  (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com>
 *
 *  Group scheduling enhancements by Srivatsa Vaddagiri
 *  Copyright IBM Corporation, 2007
 *  Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
 *
 *  Scaled math optimizations by Thomas Gleixner
 *  Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
 *
 *  Adaptive scheduling granularity, math enhancements by Peter Zijlstra
 *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
 */

/*
 * Targeted preemption latency for CPU-bound tasks:
 * (default: 20ms, units: nanoseconds)
 *
 * NOTE: this latency value is not the same as the concept of
 * 'timeslice length' - timeslices in CFS are of variable length.
 * (to see the precise effective timeslice length of your workload,
 *  run vmstat and monitor the context-switches field)
 *
 * On SMP systems the value of this is multiplied by the log2 of the
 * number of CPUs. (i.e. factor 2x on 2-way systems, 3x on 4-way
 * systems, 4x on 8-way systems, 5x on 16-way systems, etc.)
 * Targeted preemption latency for CPU-bound tasks:
 */
unsigned int sysctl_sched_latency __read_mostly = 20000000ULL;

/*
 * Minimal preemption granularity for CPU-bound tasks:
 * (default: 2 msec, units: nanoseconds)
 */
unsigned int sysctl_sched_min_granularity __read_mostly = 2000000ULL;

/*
 * SCHED_BATCH wake-up granularity.
 * (default: 25 msec, units: nanoseconds)
 *
 * This option delays the preemption effects of decoupled workloads
 * and reduces their over-scheduling. Synchronous workloads will still
 * have immediate wakeup/sleep latencies.
 */
unsigned int sysctl_sched_batch_wakeup_granularity __read_mostly = 25000000UL;

/*
 * SCHED_OTHER wake-up granularity.
 * (default: 1 msec, units: nanoseconds)
 *
 * This option delays the preemption effects of decoupled workloads
 * and reduces their over-scheduling. Synchronous workloads will still
 * have immediate wakeup/sleep latencies.
 */
unsigned int sysctl_sched_wakeup_granularity __read_mostly = 1000000UL;

unsigned int sysctl_sched_stat_granularity __read_mostly;

/*
 * Initialized in sched_init_granularity() [to 5 times the base granularity]:
 */
unsigned int sysctl_sched_runtime_limit __read_mostly;

/*
 * Debugging: various feature bits
 */
enum {
	SCHED_FEAT_FAIR_SLEEPERS	= 1,
	SCHED_FEAT_SLEEPER_AVG		= 2,
	SCHED_FEAT_SLEEPER_LOAD_AVG	= 4,
	SCHED_FEAT_PRECISE_CPU_LOAD	= 8,
	SCHED_FEAT_START_DEBIT		= 16,
	SCHED_FEAT_SKIP_INITIAL		= 32,
};

unsigned int sysctl_sched_features __read_mostly =
		SCHED_FEAT_FAIR_SLEEPERS	*1 |
		SCHED_FEAT_SLEEPER_AVG		*0 |
		SCHED_FEAT_SLEEPER_LOAD_AVG	*1 |
		SCHED_FEAT_PRECISE_CPU_LOAD	*1 |
		SCHED_FEAT_START_DEBIT		*1 |
		SCHED_FEAT_SKIP_INITIAL		*0;

extern struct sched_class fair_sched_class;

/**************************************************************
 * CFS operations on generic schedulable entities:
 */

#ifdef CONFIG_FAIR_GROUP_SCHED

/* cpu runqueue to which this cfs_rq is attached */
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
{
	return cfs_rq->rq;
}

/* currently running entity (if any) on this cfs_rq */
static inline struct sched_entity *cfs_rq_curr(struct cfs_rq *cfs_rq)
{
	return cfs_rq->curr;
}

/* An entity is a task if it doesn't "own" a runqueue */
#define entity_is_task(se)	(!se->my_q)

static inline void
set_cfs_rq_curr(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	cfs_rq->curr = se;
}

#else	/* CONFIG_FAIR_GROUP_SCHED */

static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
{
	return container_of(cfs_rq, struct rq, cfs);
}

static inline struct sched_entity *cfs_rq_curr(struct cfs_rq *cfs_rq)
{
	struct rq *rq = rq_of(cfs_rq);

	if (unlikely(rq->curr->sched_class != &fair_sched_class))
		return NULL;

	return &rq->curr->se;
}

#define entity_is_task(se)	1

static inline void
set_cfs_rq_curr(struct cfs_rq *cfs_rq, struct sched_entity *se) { }

#endif	/* CONFIG_FAIR_GROUP_SCHED */

static inline struct task_struct *task_of(struct sched_entity *se)
{
	return container_of(se, struct task_struct, se);
}


/**************************************************************
 * Scheduling class tree data structure manipulation methods:
 */

/*
 * Enqueue an entity into the rb-tree:
 */
static inline void
__enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
	struct rb_node *parent = NULL;
	struct sched_entity *entry;
	s64 key = se->fair_key;
	int leftmost = 1;

	/*
	 * Find the right place in the rbtree:
	 */
	while (*link) {
		parent = *link;
		entry = rb_entry(parent, struct sched_entity, run_node);
		/*
		 * We dont care about collisions. Nodes with
		 * the same key stay together.
		 */
		if (key - entry->fair_key < 0) {
			link = &parent->rb_left;
		} else {
			link = &parent->rb_right;
			leftmost = 0;
		}
	}

	/*
	 * Maintain a cache of leftmost tree entries (it is frequently
	 * used):
	 */
	if (leftmost)
		cfs_rq->rb_leftmost = &se->run_node;

	rb_link_node(&se->run_node, parent, link);
	rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
	update_load_add(&cfs_rq->load, se->load.weight);
	cfs_rq->nr_running++;
	se->on_rq = 1;
}

static inline void
__dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	if (cfs_rq->rb_leftmost == &se->run_node)
		cfs_rq->rb_leftmost = rb_next(&se->run_node);
	rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
	update_load_sub(&cfs_rq->load, se->load.weight);
	cfs_rq->nr_running--;
	se->on_rq = 0;
}

static inline struct rb_node *first_fair(struct cfs_rq *cfs_rq)
{
	return cfs_rq->rb_leftmost;
}

static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
{
	return rb_entry(first_fair(cfs_rq), struct sched_entity, run_node);
}

/**************************************************************
 * Scheduling class statistics methods:
 */

/*
 * Calculate the preemption granularity needed to schedule every
 * runnable task once per sysctl_sched_latency amount of time.
 * (down to a sensible low limit on granularity)
 *
 * For example, if there are 2 tasks running and latency is 10 msecs,
 * we switch tasks every 5 msecs. If we have 3 tasks running, we have
 * to switch tasks every 3.33 msecs to get a 10 msecs observed latency
 * for each task. We do finer and finer scheduling up to until we
 * reach the minimum granularity value.
 *
 * To achieve this we use the following dynamic-granularity rule:
 *
 *    gran = lat/nr - lat/nr/nr
 *
 * This comes out of the following equations:
 *
 *    kA1 + gran = kB1
 *    kB2 + gran = kA2
 *    kA2 = kA1
 *    kB2 = kB1 - d + d/nr
 *    lat = d * nr
 *
 * Where 'k' is key, 'A' is task A (waiting), 'B' is task B (running),
 * '1' is start of time, '2' is end of time, 'd' is delay between
 * 1 and 2 (during which task B was running), 'nr' is number of tasks
 * running, 'lat' is the the period of each task. ('lat' is the
 * sched_latency that we aim for.)
 */
static long
sched_granularity(struct cfs_rq *cfs_rq)
{
	unsigned int gran = sysctl_sched_latency;
	unsigned int nr = cfs_rq->nr_running;

	if (nr > 1) {
		gran = gran/nr - gran/nr/nr;
		gran = max(gran, sysctl_sched_min_granularity);
	}

	return gran;
}

/*
 * We rescale the rescheduling granularity of tasks according to their
 * nice level, but only linearly, not exponentially:
 */
static long
niced_granularity(struct sched_entity *curr, unsigned long granularity)
{
	u64 tmp;

	if (likely(curr->load.weight == NICE_0_LOAD))
		return granularity;
	/*
	 * Positive nice levels get the same granularity as nice-0:
	 */
	if (likely(curr->load.weight < NICE_0_LOAD)) {
		tmp = curr->load.weight * (u64)granularity;
		return (long) (tmp >> NICE_0_SHIFT);
	}
	/*
	 * Negative nice level tasks get linearly finer
	 * granularity:
	 */
	tmp = curr->load.inv_weight * (u64)granularity;

	/*
	 * It will always fit into 'long':
	 */
	return (long) (tmp >> WMULT_SHIFT);
}

static inline void
limit_wait_runtime(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	long limit = sysctl_sched_runtime_limit;

	/*
	 * Niced tasks have the same history dynamic range as
	 * non-niced tasks:
	 */
	if (unlikely(se->wait_runtime > limit)) {
		se->wait_runtime = limit;
		schedstat_inc(se, wait_runtime_overruns);
		schedstat_inc(cfs_rq, wait_runtime_overruns);
	}
	if (unlikely(se->wait_runtime < -limit)) {
		se->wait_runtime = -limit;
		schedstat_inc(se, wait_runtime_underruns);
		schedstat_inc(cfs_rq, wait_runtime_underruns);
	}
}

static inline void
__add_wait_runtime(struct cfs_rq *cfs_rq, struct sched_entity *se, long delta)
{
	se->wait_runtime += delta;
	schedstat_add(se, sum_wait_runtime, delta);
	limit_wait_runtime(cfs_rq, se);
}

static void
add_wait_runtime(struct cfs_rq *cfs_rq, struct sched_entity *se, long delta)
{
	schedstat_add(cfs_rq, wait_runtime, -se->wait_runtime);
	__add_wait_runtime(cfs_rq, se, delta);
	schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
}

/*
 * Update the current task's runtime statistics. Skip current tasks that
 * are not in our scheduling class.
 */
static inline void
__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
	unsigned long delta, delta_exec, delta_fair, delta_mine;
	struct load_weight *lw = &cfs_rq->load;
	unsigned long load = lw->weight;

	delta_exec = curr->delta_exec;
	schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));

	curr->sum_exec_runtime += delta_exec;
	cfs_rq->exec_clock += delta_exec;

	if (unlikely(!load))
		return;

	delta_fair = calc_delta_fair(delta_exec, lw);
	delta_mine = calc_delta_mine(delta_exec, curr->load.weight, lw);

	if (cfs_rq->sleeper_bonus > sysctl_sched_latency) {
		delta = min((u64)delta_mine, cfs_rq->sleeper_bonus);
		delta = min(delta, (unsigned long)(
			(long)sysctl_sched_runtime_limit - curr->wait_runtime));
		cfs_rq->sleeper_bonus -= delta;
		delta_mine -= delta;
	}

	cfs_rq->fair_clock += delta_fair;
	/*
	 * We executed delta_exec amount of time on the CPU,
	 * but we were only entitled to delta_mine amount of
	 * time during that period (if nr_running == 1 then
	 * the two values are equal)
	 * [Note: delta_mine - delta_exec is negative]:
	 */
	add_wait_runtime(cfs_rq, curr, delta_mine - delta_exec);
}

static void update_curr(struct cfs_rq *cfs_rq)
{
	struct sched_entity *curr = cfs_rq_curr(cfs_rq);
	unsigned long delta_exec;

	if (unlikely(!curr))
		return;

	/*
	 * Get the amount of time the current task was running
	 * since the last time we changed load (this cannot
	 * overflow on 32 bits):
	 */
	delta_exec = (unsigned long)(rq_of(cfs_rq)->clock - curr->exec_start);

	curr->delta_exec += delta_exec;

	if (unlikely(curr->delta_exec > sysctl_sched_stat_granularity)) {
		__update_curr(cfs_rq, curr);
		curr->delta_exec = 0;
	}
	curr->exec_start = rq_of(cfs_rq)->clock;
}

static inline void
update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	se->wait_start_fair = cfs_rq->fair_clock;
	schedstat_set(se->wait_start, rq_of(cfs_rq)->clock);
}

/*
 * We calculate fair deltas here, so protect against the random effects
 * of a multiplication overflow by capping it to the runtime limit:
 */
#if BITS_PER_LONG == 32
static inline unsigned long
calc_weighted(unsigned long delta, unsigned long weight, int shift)
{
	u64 tmp = (u64)delta * weight >> shift;

	if (unlikely(tmp > sysctl_sched_runtime_limit*2))
		return sysctl_sched_runtime_limit*2;
	return tmp;
}
#else
static inline unsigned long
calc_weighted(unsigned long delta, unsigned long weight, int shift)
{
	return delta * weight >> shift;
}
#endif

/*
 * Task is being enqueued - update stats:
 */
static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	s64 key;

	/*
	 * Are we enqueueing a waiting task? (for current tasks
	 * a dequeue/enqueue event is a NOP)
	 */
	if (se != cfs_rq_curr(cfs_rq))
		update_stats_wait_start(cfs_rq, se);
	/*
	 * Update the key:
	 */
	key = cfs_rq->fair_clock;

	/*
	 * Optimize the common nice 0 case:
	 */
	if (likely(se->load.weight == NICE_0_LOAD)) {
		key -= se->wait_runtime;
	} else {
		u64 tmp;

		if (se->wait_runtime < 0) {
			tmp = -se->wait_runtime;
			key += (tmp * se->load.inv_weight) >>
					(WMULT_SHIFT - NICE_0_SHIFT);
		} else {
			tmp = se->wait_runtime;
			key -= (tmp * se->load.inv_weight) >>
					(WMULT_SHIFT - NICE_0_SHIFT);
		}
	}

	se->fair_key = key;
}

/*
 * Note: must be called with a freshly updated rq->fair_clock.
 */
static inline void
__update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	unsigned long delta_fair = se->delta_fair_run;

	schedstat_set(se->wait_max, max(se->wait_max,
			rq_of(cfs_rq)->clock - se->wait_start));

	if (unlikely(se->load.weight != NICE_0_LOAD))
		delta_fair = calc_weighted(delta_fair, se->load.weight,
							NICE_0_SHIFT);

	add_wait_runtime(cfs_rq, se, delta_fair);
}

static void
update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	unsigned long delta_fair;

	delta_fair = (unsigned long)min((u64)(2*sysctl_sched_runtime_limit),
			(u64)(cfs_rq->fair_clock - se->wait_start_fair));

	se->delta_fair_run += delta_fair;
	if (unlikely(abs(se->delta_fair_run) >=
				sysctl_sched_stat_granularity)) {
		__update_stats_wait_end(cfs_rq, se);
		se->delta_fair_run = 0;
	}

	se->wait_start_fair = 0;
	schedstat_set(se->wait_start, 0);
}

static inline void
update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	update_curr(cfs_rq);
	/*
	 * Mark the end of the wait period if dequeueing a
	 * waiting task:
	 */
	if (se != cfs_rq_curr(cfs_rq))
		update_stats_wait_end(cfs_rq, se);
}

/*
 * We are picking a new current task - update its stats:
 */
static inline void
update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	/*
	 * We are starting a new run period:
	 */
	se->exec_start = rq_of(cfs_rq)->clock;
}

/*
 * We are descheduling a task - update its stats:
 */
static inline void
update_stats_curr_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	se->exec_start = 0;
}

/**************************************************
 * Scheduling class queueing methods:
 */

static void __enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	unsigned long load = cfs_rq->load.weight, delta_fair;
	long prev_runtime;

	/*
	 * Do not boost sleepers if there's too much bonus 'in flight'
	 * already:
	 */
	if (unlikely(cfs_rq->sleeper_bonus > sysctl_sched_runtime_limit))
		return;

	if (sysctl_sched_features & SCHED_FEAT_SLEEPER_LOAD_AVG)
		load = rq_of(cfs_rq)->cpu_load[2];

	delta_fair = se->delta_fair_sleep;

	/*
	 * Fix up delta_fair with the effect of us running
	 * during the whole sleep period:
	 */
	if (sysctl_sched_features & SCHED_FEAT_SLEEPER_AVG)
		delta_fair = div64_likely32((u64)delta_fair * load,
						load + se->load.weight);

	if (unlikely(se->load.weight != NICE_0_LOAD))
		delta_fair = calc_weighted(delta_fair, se->load.weight,
							NICE_0_SHIFT);

	prev_runtime = se->wait_runtime;
	__add_wait_runtime(cfs_rq, se, delta_fair);
	schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
	delta_fair = se->wait_runtime - prev_runtime;

	/*
	 * Track the amount of bonus we've given to sleepers:
	 */
	cfs_rq->sleeper_bonus += delta_fair;
}

static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	struct task_struct *tsk = task_of(se);
	unsigned long delta_fair;

	if ((entity_is_task(se) && tsk->policy == SCHED_BATCH) ||
			 !(sysctl_sched_features & SCHED_FEAT_FAIR_SLEEPERS))
		return;

	delta_fair = (unsigned long)min((u64)(2*sysctl_sched_runtime_limit),
		(u64)(cfs_rq->fair_clock - se->sleep_start_fair));

	se->delta_fair_sleep += delta_fair;
	if (unlikely(abs(se->delta_fair_sleep) >=
				sysctl_sched_stat_granularity)) {
		__enqueue_sleeper(cfs_rq, se);
		se->delta_fair_sleep = 0;
	}

	se->sleep_start_fair = 0;

#ifdef CONFIG_SCHEDSTATS
	if (se->sleep_start) {
		u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;

		if ((s64)delta < 0)
			delta = 0;

		if (unlikely(delta > se->sleep_max))
			se->sleep_max = delta;

		se->sleep_start = 0;
		se->sum_sleep_runtime += delta;
	}
	if (se->block_start) {
		u64 delta = rq_of(cfs_rq)->clock - se->block_start;

		if ((s64)delta < 0)
			delta = 0;

		if (unlikely(delta > se->block_max))
			se->block_max = delta;

		se->block_start = 0;
		se->sum_sleep_runtime += delta;
	}
#endif
}

static void
enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
{
	/*
	 * Update the fair clock.
	 */
	update_curr(cfs_rq);

	if (wakeup)
		enqueue_sleeper(cfs_rq, se);

	update_stats_enqueue(cfs_rq, se);
	__enqueue_entity(cfs_rq, se);
}

static void
dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
{
	update_stats_dequeue(cfs_rq, se);
	if (sleep) {
		se->sleep_start_fair = cfs_rq->fair_clock;
#ifdef CONFIG_SCHEDSTATS
		if (entity_is_task(se)) {
			struct task_struct *tsk = task_of(se);

			if (tsk->state & TASK_INTERRUPTIBLE)
				se->sleep_start = rq_of(cfs_rq)->clock;
			if (tsk->state & TASK_UNINTERRUPTIBLE)
				se->block_start = rq_of(cfs_rq)->clock;
		}
		cfs_rq->wait_runtime -= se->wait_runtime;
#endif
	}
	__dequeue_entity(cfs_rq, se);
}

/*
 * Preempt the current task with a newly woken task if needed:
 */
static void
__check_preempt_curr_fair(struct cfs_rq *cfs_rq, struct sched_entity *se,
			  struct sched_entity *curr, unsigned long granularity)
{
	s64 __delta = curr->fair_key - se->fair_key;

	/*
	 * Take scheduling granularity into account - do not
	 * preempt the current task unless the best task has
	 * a larger than sched_granularity fairness advantage:
	 */
	if (__delta > niced_granularity(curr, granularity))
		resched_task(rq_of(cfs_rq)->curr);
}

static inline void
set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
	/*
	 * Any task has to be enqueued before it get to execute on
	 * a CPU. So account for the time it spent waiting on the
	 * runqueue. (note, here we rely on pick_next_task() having
	 * done a put_prev_task_fair() shortly before this, which
	 * updated rq->fair_clock - used by update_stats_wait_end())
	 */
	update_stats_wait_end(cfs_rq, se);
	update_stats_curr_start(cfs_rq, se);
	set_cfs_rq_curr(cfs_rq, se);
}

static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
	struct sched_entity *se = __pick_next_entity(cfs_rq);

	set_next_entity(cfs_rq, se);

	return se;
}

static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
{
	/*
	 * If still on the runqueue then deactivate_task()
	 * was not called and update_curr() has to be done:
	 */
	if (prev->on_rq)
		update_curr(cfs_rq);

	update_stats_curr_end(cfs_rq, prev);

	if (prev->on_rq)
		update_stats_wait_start(cfs_rq, prev);
	set_cfs_rq_curr(cfs_rq, NULL);
}

static void entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
	struct sched_entity *next;

	/*
	 * Dequeue and enqueue the task to update its
	 * position within the tree:
	 */
	dequeue_entity(cfs_rq, curr, 0);
	enqueue_entity(cfs_rq, curr, 0);

	/*
	 * Reschedule if another task tops the current one.
	 */
	next = __pick_next_entity(cfs_rq);
	if (next == curr)
		return;

	__check_preempt_curr_fair(cfs_rq, next, curr,
			sched_granularity(cfs_rq));
}

/**************************************************
 * CFS operations on tasks:
 */

#ifdef CONFIG_FAIR_GROUP_SCHED

/* Walk up scheduling entities hierarchy */
#define for_each_sched_entity(se) \
		for (; se; se = se->parent)

static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
{
	return p->se.cfs_rq;
}

/* runqueue on which this entity is (to be) queued */
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
{
	return se->cfs_rq;
}

/* runqueue "owned" by this group */
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
	return grp->my_q;
}

/* Given a group's cfs_rq on one cpu, return its corresponding cfs_rq on
 * another cpu ('this_cpu')
 */
static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
{
	/* A later patch will take group into account */
	return &cpu_rq(this_cpu)->cfs;
}

/* Iterate thr' all leaf cfs_rq's on a runqueue */
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
	list_for_each_entry(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)

/* Do the two (enqueued) tasks belong to the same group ? */
static inline int is_same_group(struct task_struct *curr, struct task_struct *p)
{
	if (curr->se.cfs_rq == p->se.cfs_rq)
		return 1;

	return 0;
}

#else	/* CONFIG_FAIR_GROUP_SCHED */

#define for_each_sched_entity(se) \
		for (; se; se = NULL)

static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
{
	return &task_rq(p)->cfs;
}

static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
{
	struct task_struct *p = task_of(se);
	struct rq *rq = task_rq(p);

	return &rq->cfs;
}

/* runqueue "owned" by this group */
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
	return NULL;
}

static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
{
	return &cpu_rq(this_cpu)->cfs;
}

#define for_each_leaf_cfs_rq(rq, cfs_rq) \
		for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)

static inline int is_same_group(struct task_struct *curr, struct task_struct *p)
{
	return 1;
}

#endif	/* CONFIG_FAIR_GROUP_SCHED */

/*
 * The enqueue_task method is called before nr_running is
 * increased. Here we update the fair scheduling stats and
 * then put the task into the rbtree:
 */
static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
{
	struct cfs_rq *cfs_rq;
	struct sched_entity *se = &p->se;

	for_each_sched_entity(se) {
		if (se->on_rq)
			break;
		cfs_rq = cfs_rq_of(se);
		enqueue_entity(cfs_rq, se, wakeup);
	}
}

/*
 * The dequeue_task method is called before nr_running is
 * decreased. We remove the task from the rbtree and
 * update the fair scheduling stats:
 */
static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
{
	struct cfs_rq *cfs_rq;
	struct sched_entity *se = &p->se;

	for_each_sched_entity(se) {
		cfs_rq = cfs_rq_of(se);
		dequeue_entity(cfs_rq, se, sleep);
		/* Don't dequeue parent if it has other entities besides us */
		if (cfs_rq->load.weight)
			break;
	}
}

/*
 * sched_yield() support is very simple - we dequeue and enqueue
 */
static void yield_task_fair(struct rq *rq, struct task_struct *p)
{
	struct cfs_rq *cfs_rq = task_cfs_rq(p);

	__update_rq_clock(rq);
	/*
	 * Dequeue and enqueue the task to update its
	 * position within the tree:
	 */
	dequeue_entity(cfs_rq, &p->se, 0);
	enqueue_entity(cfs_rq, &p->se, 0);
}

/*
 * Preempt the current task with a newly woken task if needed:
 */
static void check_preempt_curr_fair(struct rq *rq, struct task_struct *p)
{
	struct task_struct *curr = rq->curr;
	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
	unsigned long gran;

	if (unlikely(rt_prio(p->prio))) {
		update_rq_clock(rq);
		update_curr(cfs_rq);
		resched_task(curr);
		return;
	}

	gran = sysctl_sched_wakeup_granularity;
	/*
	 * Batch tasks prefer throughput over latency:
	 */
	if (unlikely(p->policy == SCHED_BATCH))
		gran = sysctl_sched_batch_wakeup_granularity;

	if (is_same_group(curr, p))
		__check_preempt_curr_fair(cfs_rq, &p->se, &curr->se, gran);
}

static struct task_struct *pick_next_task_fair(struct rq *rq)
{
	struct cfs_rq *cfs_rq = &rq->cfs;
	struct sched_entity *se;

	if (unlikely(!cfs_rq->nr_running))
		return NULL;

	do {
		se = pick_next_entity(cfs_rq);
		cfs_rq = group_cfs_rq(se);
	} while (cfs_rq);

	return task_of(se);
}

/*
 * Account for a descheduled task:
 */
static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
{
	struct sched_entity *se = &prev->se;
	struct cfs_rq *cfs_rq;

	for_each_sched_entity(se) {
		cfs_rq = cfs_rq_of(se);
		put_prev_entity(cfs_rq, se);
	}
}

/**************************************************
 * Fair scheduling class load-balancing methods:
 */

/*
 * Load-balancing iterator. Note: while the runqueue stays locked
 * during the whole iteration, the current task might be
 * dequeued so the iterator has to be dequeue-safe. Here we
 * achieve that by always pre-iterating before returning
 * the current task:
 */
static inline struct task_struct *
__load_balance_iterator(struct cfs_rq *cfs_rq, struct rb_node *curr)
{
	struct task_struct *p;

	if (!curr)
		return NULL;

	p = rb_entry(curr, struct task_struct, se.run_node);
	cfs_rq->rb_load_balance_curr = rb_next(curr);

	return p;
}

static struct task_struct *load_balance_start_fair(void *arg)
{
	struct cfs_rq *cfs_rq = arg;

	return __load_balance_iterator(cfs_rq, first_fair(cfs_rq));
}

static struct task_struct *load_balance_next_fair(void *arg)
{
	struct cfs_rq *cfs_rq = arg;

	return __load_balance_iterator(cfs_rq, cfs_rq->rb_load_balance_curr);
}

#ifdef CONFIG_FAIR_GROUP_SCHED
static int cfs_rq_best_prio(struct cfs_rq *cfs_rq)
{
	struct sched_entity *curr;
	struct task_struct *p;

	if (!cfs_rq->nr_running)
		return MAX_PRIO;

	curr = __pick_next_entity(cfs_rq);
	p = task_of(curr);

	return p->prio;
}
#endif

static unsigned long
load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
		  unsigned long max_nr_move, unsigned long max_load_move,
		  struct sched_domain *sd, enum cpu_idle_type idle,
		  int *all_pinned, int *this_best_prio)
{
	struct cfs_rq *busy_cfs_rq;
	unsigned long load_moved, total_nr_moved = 0, nr_moved;
	long rem_load_move = max_load_move;
	struct rq_iterator cfs_rq_iterator;

	cfs_rq_iterator.start = load_balance_start_fair;
	cfs_rq_iterator.next = load_balance_next_fair;

	for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
#ifdef CONFIG_FAIR_GROUP_SCHED
		struct cfs_rq *this_cfs_rq;
		long imbalance;
		unsigned long maxload;

		this_cfs_rq = cpu_cfs_rq(busy_cfs_rq, this_cpu);

		imbalance = busy_cfs_rq->load.weight - this_cfs_rq->load.weight;
		/* Don't pull if this_cfs_rq has more load than busy_cfs_rq */
		if (imbalance <= 0)
			continue;

		/* Don't pull more than imbalance/2 */
		imbalance /= 2;
		maxload = min(rem_load_move, imbalance);

		*this_best_prio = cfs_rq_best_prio(this_cfs_rq);
#else
# define maxload rem_load_move
#endif
		/* pass busy_cfs_rq argument into
		 * load_balance_[start|next]_fair iterators
		 */
		cfs_rq_iterator.arg = busy_cfs_rq;
		nr_moved = balance_tasks(this_rq, this_cpu, busiest,
				max_nr_move, maxload, sd, idle, all_pinned,
				&load_moved, this_best_prio, &cfs_rq_iterator);

		total_nr_moved += nr_moved;
		max_nr_move -= nr_moved;
		rem_load_move -= load_moved;

		if (max_nr_move <= 0 || rem_load_move <= 0)
			break;
	}

	return max_load_move - rem_load_move;
}

/*
 * scheduler tick hitting a task of our scheduling class:
 */
static void task_tick_fair(struct rq *rq, struct task_struct *curr)
{
	struct cfs_rq *cfs_rq;
	struct sched_entity *se = &curr->se;

	for_each_sched_entity(se) {
		cfs_rq = cfs_rq_of(se);
		entity_tick(cfs_rq, se);
	}
}

/*
 * Share the fairness runtime between parent and child, thus the
 * total amount of pressure for CPU stays equal - new tasks
 * get a chance to run but frequent forkers are not allowed to
 * monopolize the CPU. Note: the parent runqueue is locked,
 * the child is not running yet.
 */
static void task_new_fair(struct rq *rq, struct task_struct *p)
{
	struct cfs_rq *cfs_rq = task_cfs_rq(p);
	struct sched_entity *se = &p->se;

	sched_info_queued(p);

	update_stats_enqueue(cfs_rq, se);
	/*
	 * Child runs first: we let it run before the parent
	 * until it reschedules once. We set up the key so that
	 * it will preempt the parent:
	 */
	p->se.fair_key = current->se.fair_key -
		niced_granularity(&rq->curr->se, sched_granularity(cfs_rq)) - 1;
	/*
	 * The first wait is dominated by the child-runs-first logic,
	 * so do not credit it with that waiting time yet:
	 */
	if (sysctl_sched_features & SCHED_FEAT_SKIP_INITIAL)
		p->se.wait_start_fair = 0;

	/*
	 * The statistical average of wait_runtime is about
	 * -granularity/2, so initialize the task with that:
	 */
	if (sysctl_sched_features & SCHED_FEAT_START_DEBIT)
		p->se.wait_runtime = -(sched_granularity(cfs_rq) / 2);

	__enqueue_entity(cfs_rq, se);
}

#ifdef CONFIG_FAIR_GROUP_SCHED
/* Account for a task changing its policy or group.
 *
 * This routine is mostly called to set cfs_rq->curr field when a task
 * migrates between groups/classes.
 */
static void set_curr_task_fair(struct rq *rq)
{
	struct sched_entity *se = &rq->curr->se;

	for_each_sched_entity(se)
		set_next_entity(cfs_rq_of(se), se);
}
#else
static void set_curr_task_fair(struct rq *rq)
{
}
#endif

/*
 * All the scheduling class methods:
 */
struct sched_class fair_sched_class __read_mostly = {
	.enqueue_task		= enqueue_task_fair,
	.dequeue_task		= dequeue_task_fair,
	.yield_task		= yield_task_fair,

	.check_preempt_curr	= check_preempt_curr_fair,

	.pick_next_task		= pick_next_task_fair,
	.put_prev_task		= put_prev_task_fair,

	.load_balance		= load_balance_fair,

	.set_curr_task          = set_curr_task_fair,
	.task_tick		= task_tick_fair,
	.task_new		= task_new_fair,
};

#ifdef CONFIG_SCHED_DEBUG
static void print_cfs_stats(struct seq_file *m, int cpu)
{
	struct cfs_rq *cfs_rq;

	for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
		print_cfs_rq(m, cpu, cfs_rq);
}
#endif