aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/sched_rt.c
blob: 8afb953e31c6c1ba9a263a78929a04a0d82ff2c7 (plain) (blame)
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
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
/*
 * Real-Time Scheduling Class (mapped to the SCHED_FIFO and SCHED_RR
 * policies)
 */

#ifdef CONFIG_RT_GROUP_SCHED

#define rt_entity_is_task(rt_se) (!(rt_se)->my_q)

static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
{
#ifdef CONFIG_SCHED_DEBUG
	WARN_ON_ONCE(!rt_entity_is_task(rt_se));
#endif
	return container_of(rt_se, struct task_struct, rt);
}

static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
{
	return rt_rq->rq;
}

static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
{
	return rt_se->rt_rq;
}

#else /* CONFIG_RT_GROUP_SCHED */

#define rt_entity_is_task(rt_se) (1)

static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
{
	return container_of(rt_se, struct task_struct, rt);
}

static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
{
	return container_of(rt_rq, struct rq, rt);
}

static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
{
	struct task_struct *p = rt_task_of(rt_se);
	struct rq *rq = task_rq(p);

	return &rq->rt;
}

#endif /* CONFIG_RT_GROUP_SCHED */

#ifdef CONFIG_SMP

static inline int rt_overloaded(struct rq *rq)
{
	return atomic_read(&rq->rd->rto_count);
}

static inline void rt_set_overload(struct rq *rq)
{
	if (!rq->online)
		return;

	cpumask_set_cpu(rq->cpu, rq->rd->rto_mask);
	/*
	 * Make sure the mask is visible before we set
	 * the overload count. That is checked to determine
	 * if we should look at the mask. It would be a shame
	 * if we looked at the mask, but the mask was not
	 * updated yet.
	 */
	wmb();
	atomic_inc(&rq->rd->rto_count);
}

static inline void rt_clear_overload(struct rq *rq)
{
	if (!rq->online)
		return;

	/* the order here really doesn't matter */
	atomic_dec(&rq->rd->rto_count);
	cpumask_clear_cpu(rq->cpu, rq->rd->rto_mask);
}

static void update_rt_migration(struct rt_rq *rt_rq)
{
	if (rt_rq->rt_nr_migratory && rt_rq->rt_nr_total > 1) {
		if (!rt_rq->overloaded) {
			rt_set_overload(rq_of_rt_rq(rt_rq));
			rt_rq->overloaded = 1;
		}
	} else if (rt_rq->overloaded) {
		rt_clear_overload(rq_of_rt_rq(rt_rq));
		rt_rq->overloaded = 0;
	}
}

static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
	if (!rt_entity_is_task(rt_se))
		return;

	rt_rq = &rq_of_rt_rq(rt_rq)->rt;

	rt_rq->rt_nr_total++;
	if (rt_se->nr_cpus_allowed > 1)
		rt_rq->rt_nr_migratory++;

	update_rt_migration(rt_rq);
}

static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
	if (!rt_entity_is_task(rt_se))
		return;

	rt_rq = &rq_of_rt_rq(rt_rq)->rt;

	rt_rq->rt_nr_total--;
	if (rt_se->nr_cpus_allowed > 1)
		rt_rq->rt_nr_migratory--;

	update_rt_migration(rt_rq);
}

static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
{
	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
	plist_node_init(&p->pushable_tasks, p->prio);
	plist_add(&p->pushable_tasks, &rq->rt.pushable_tasks);
}

static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
{
	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
}

static inline int has_pushable_tasks(struct rq *rq)
{
	return !plist_head_empty(&rq->rt.pushable_tasks);
}

#else

static inline void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
{
}

static inline void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
{
}

static inline
void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
}

static inline
void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
}

#endif /* CONFIG_SMP */

static inline int on_rt_rq(struct sched_rt_entity *rt_se)
{
	return !list_empty(&rt_se->run_list);
}

#ifdef CONFIG_RT_GROUP_SCHED

static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
{
	if (!rt_rq->tg)
		return RUNTIME_INF;

	return rt_rq->rt_runtime;
}

static inline u64 sched_rt_period(struct rt_rq *rt_rq)
{
	return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period);
}

#define for_each_leaf_rt_rq(rt_rq, rq) \
	list_for_each_entry_rcu(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list)

#define for_each_sched_rt_entity(rt_se) \
	for (; rt_se; rt_se = rt_se->parent)

static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
{
	return rt_se->my_q;
}

static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head);
static void dequeue_rt_entity(struct sched_rt_entity *rt_se);

static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
{
	int this_cpu = smp_processor_id();
	struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
	struct sched_rt_entity *rt_se;

	rt_se = rt_rq->tg->rt_se[this_cpu];

	if (rt_rq->rt_nr_running) {
		if (rt_se && !on_rt_rq(rt_se))
			enqueue_rt_entity(rt_se, false);
		if (rt_rq->highest_prio.curr < curr->prio)
			resched_task(curr);
	}
}

static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
{
	int this_cpu = smp_processor_id();
	struct sched_rt_entity *rt_se;

	rt_se = rt_rq->tg->rt_se[this_cpu];

	if (rt_se && on_rt_rq(rt_se))
		dequeue_rt_entity(rt_se);
}

static inline int rt_rq_throttled(struct rt_rq *rt_rq)
{
	return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted;
}

static int rt_se_boosted(struct sched_rt_entity *rt_se)
{
	struct rt_rq *rt_rq = group_rt_rq(rt_se);
	struct task_struct *p;

	if (rt_rq)
		return !!rt_rq->rt_nr_boosted;

	p = rt_task_of(rt_se);
	return p->prio != p->normal_prio;
}

#ifdef CONFIG_SMP
static inline const struct cpumask *sched_rt_period_mask(void)
{
	return cpu_rq(smp_processor_id())->rd->span;
}
#else
static inline const struct cpumask *sched_rt_period_mask(void)
{
	return cpu_online_mask;
}
#endif

static inline
struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu)
{
	return container_of(rt_b, struct task_group, rt_bandwidth)->rt_rq[cpu];
}

static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
{
	return &rt_rq->tg->rt_bandwidth;
}

#else /* !CONFIG_RT_GROUP_SCHED */

static inline u64 sched_rt_runtime(struct rt_rq *rt_rq)
{
	return rt_rq->rt_runtime;
}

static inline u64 sched_rt_period(struct rt_rq *rt_rq)
{
	return ktime_to_ns(def_rt_bandwidth.rt_period);
}

#define for_each_leaf_rt_rq(rt_rq, rq) \
	for (rt_rq = &rq->rt; rt_rq; rt_rq = NULL)

#define for_each_sched_rt_entity(rt_se) \
	for (; rt_se; rt_se = NULL)

static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se)
{
	return NULL;
}

static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
{
	if (rt_rq->rt_nr_running)
		resched_task(rq_of_rt_rq(rt_rq)->curr);
}

static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
{
}

static inline int rt_rq_throttled(struct rt_rq *rt_rq)
{
	return rt_rq->rt_throttled;
}

static inline const struct cpumask *sched_rt_period_mask(void)
{
	return cpu_online_mask;
}

static inline
struct rt_rq *sched_rt_period_rt_rq(struct rt_bandwidth *rt_b, int cpu)
{
	return &cpu_rq(cpu)->rt;
}

static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq)
{
	return &def_rt_bandwidth;
}

#endif /* CONFIG_RT_GROUP_SCHED */

#ifdef CONFIG_SMP
/*
 * We ran out of runtime, see if we can borrow some from our neighbours.
 */
static int do_balance_runtime(struct rt_rq *rt_rq)
{
	struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
	struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
	int i, weight, more = 0;
	u64 rt_period;

	weight = cpumask_weight(rd->span);

	raw_spin_lock(&rt_b->rt_runtime_lock);
	rt_period = ktime_to_ns(rt_b->rt_period);
	for_each_cpu(i, rd->span) {
		struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
		s64 diff;

		if (iter == rt_rq)
			continue;

		raw_spin_lock(&iter->rt_runtime_lock);
		/*
		 * Either all rqs have inf runtime and there's nothing to steal
		 * or __disable_runtime() below sets a specific rq to inf to
		 * indicate its been disabled and disalow stealing.
		 */
		if (iter->rt_runtime == RUNTIME_INF)
			goto next;

		/*
		 * From runqueues with spare time, take 1/n part of their
		 * spare time, but no more than our period.
		 */
		diff = iter->rt_runtime - iter->rt_time;
		if (diff > 0) {
			diff = div_u64((u64)diff, weight);
			if (rt_rq->rt_runtime + diff > rt_period)
				diff = rt_period - rt_rq->rt_runtime;
			iter->rt_runtime -= diff;
			rt_rq->rt_runtime += diff;
			more = 1;
			if (rt_rq->rt_runtime == rt_period) {
				raw_spin_unlock(&iter->rt_runtime_lock);
				break;
			}
		}
next:
		raw_spin_unlock(&iter->rt_runtime_lock);
	}
	raw_spin_unlock(&rt_b->rt_runtime_lock);

	return more;
}

/*
 * Ensure this RQ takes back all the runtime it lend to its neighbours.
 */
static void __disable_runtime(struct rq *rq)
{
	struct root_domain *rd = rq->rd;
	struct rt_rq *rt_rq;

	if (unlikely(!scheduler_running))
		return;

	for_each_leaf_rt_rq(rt_rq, rq) {
		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
		s64 want;
		int i;

		raw_spin_lock(&rt_b->rt_runtime_lock);
		raw_spin_lock(&rt_rq->rt_runtime_lock);
		/*
		 * Either we're all inf and nobody needs to borrow, or we're
		 * already disabled and thus have nothing to do, or we have
		 * exactly the right amount of runtime to take out.
		 */
		if (rt_rq->rt_runtime == RUNTIME_INF ||
				rt_rq->rt_runtime == rt_b->rt_runtime)
			goto balanced;
		raw_spin_unlock(&rt_rq->rt_runtime_lock);

		/*
		 * Calculate the difference between what we started out with
		 * and what we current have, that's the amount of runtime
		 * we lend and now have to reclaim.
		 */
		want = rt_b->rt_runtime - rt_rq->rt_runtime;

		/*
		 * Greedy reclaim, take back as much as we can.
		 */
		for_each_cpu(i, rd->span) {
			struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i);
			s64 diff;

			/*
			 * Can't reclaim from ourselves or disabled runqueues.
			 */
			if (iter == rt_rq || iter->rt_runtime == RUNTIME_INF)
				continue;

			raw_spin_lock(&iter->rt_runtime_lock);
			if (want > 0) {
				diff = min_t(s64, iter->rt_runtime, want);
				iter->rt_runtime -= diff;
				want -= diff;
			} else {
				iter->rt_runtime -= want;
				want -= want;
			}
			raw_spin_unlock(&iter->rt_runtime_lock);

			if (!want)
				break;
		}

		raw_spin_lock(&rt_rq->rt_runtime_lock);
		/*
		 * We cannot be left wanting - that would mean some runtime
		 * leaked out of the system.
		 */
		BUG_ON(want);
balanced:
		/*
		 * Disable all the borrow logic by pretending we have inf
		 * runtime - in which case borrowing doesn't make sense.
		 */
		rt_rq->rt_runtime = RUNTIME_INF;
		raw_spin_unlock(&rt_rq->rt_runtime_lock);
		raw_spin_unlock(&rt_b->rt_runtime_lock);
	}
}

static void disable_runtime(struct rq *rq)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&rq->lock, flags);
	__disable_runtime(rq);
	raw_spin_unlock_irqrestore(&rq->lock, flags);
}

static void __enable_runtime(struct rq *rq)
{
	struct rt_rq *rt_rq;

	if (unlikely(!scheduler_running))
		return;

	/*
	 * Reset each runqueue's bandwidth settings
	 */
	for_each_leaf_rt_rq(rt_rq, rq) {
		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);

		raw_spin_lock(&rt_b->rt_runtime_lock);
		raw_spin_lock(&rt_rq->rt_runtime_lock);
		rt_rq->rt_runtime = rt_b->rt_runtime;
		rt_rq->rt_time = 0;
		rt_rq->rt_throttled = 0;
		raw_spin_unlock(&rt_rq->rt_runtime_lock);
		raw_spin_unlock(&rt_b->rt_runtime_lock);
	}
}

static void enable_runtime(struct rq *rq)
{
	unsigned long flags;

	raw_spin_lock_irqsave(&rq->lock, flags);
	__enable_runtime(rq);
	raw_spin_unlock_irqrestore(&rq->lock, flags);
}

static int balance_runtime(struct rt_rq *rt_rq)
{
	int more = 0;

	if (rt_rq->rt_time > rt_rq->rt_runtime) {
		raw_spin_unlock(&rt_rq->rt_runtime_lock);
		more = do_balance_runtime(rt_rq);
		raw_spin_lock(&rt_rq->rt_runtime_lock);
	}

	return more;
}
#else /* !CONFIG_SMP */
static inline int balance_runtime(struct rt_rq *rt_rq)
{
	return 0;
}
#endif /* CONFIG_SMP */

static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
{
	int i, idle = 1;
	const struct cpumask *span;

	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
		return 1;

	span = sched_rt_period_mask();
	for_each_cpu(i, span) {
		int enqueue = 0;
		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
		struct rq *rq = rq_of_rt_rq(rt_rq);

		raw_spin_lock(&rq->lock);
		if (rt_rq->rt_time) {
			u64 runtime;

			raw_spin_lock(&rt_rq->rt_runtime_lock);
			if (rt_rq->rt_throttled)
				balance_runtime(rt_rq);
			runtime = rt_rq->rt_runtime;
			rt_rq->rt_time -= min(rt_rq->rt_time, overrun*runtime);
			if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) {
				rt_rq->rt_throttled = 0;
				enqueue = 1;
			}
			if (rt_rq->rt_time || rt_rq->rt_nr_running)
				idle = 0;
			raw_spin_unlock(&rt_rq->rt_runtime_lock);
		} else if (rt_rq->rt_nr_running)
			idle = 0;

		if (enqueue)
			sched_rt_rq_enqueue(rt_rq);
		raw_spin_unlock(&rq->lock);
	}

	return idle;
}

static inline int rt_se_prio(struct sched_rt_entity *rt_se)
{
#ifdef CONFIG_RT_GROUP_SCHED
	struct rt_rq *rt_rq = group_rt_rq(rt_se);

	if (rt_rq)
		return rt_rq->highest_prio.curr;
#endif

	return rt_task_of(rt_se)->prio;
}

static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq)
{
	u64 runtime = sched_rt_runtime(rt_rq);

	if (rt_rq->rt_throttled)
		return rt_rq_throttled(rt_rq);

	if (sched_rt_runtime(rt_rq) >= sched_rt_period(rt_rq))
		return 0;

	balance_runtime(rt_rq);
	runtime = sched_rt_runtime(rt_rq);
	if (runtime == RUNTIME_INF)
		return 0;

	if (rt_rq->rt_time > runtime) {
		rt_rq->rt_throttled = 1;
		if (rt_rq_throttled(rt_rq)) {
			sched_rt_rq_dequeue(rt_rq);
			return 1;
		}
	}

	return 0;
}

/*
 * Update the current task's runtime statistics. Skip current tasks that
 * are not in our scheduling class.
 */
static void update_curr_rt(struct rq *rq)
{
	struct task_struct *curr = rq->curr;
	struct sched_rt_entity *rt_se = &curr->rt;
	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
	u64 delta_exec;

	if (!task_has_rt_policy(curr))
		return;

	delta_exec = rq->clock - curr->se.exec_start;
	if (unlikely((s64)delta_exec < 0))
		delta_exec = 0;

	schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec));

	curr->se.sum_exec_runtime += delta_exec;
	account_group_exec_runtime(curr, delta_exec);

	curr->se.exec_start = rq->clock;
	cpuacct_charge(curr, delta_exec);

	sched_rt_avg_update(rq, delta_exec);

	if (!rt_bandwidth_enabled())
		return;

	for_each_sched_rt_entity(rt_se) {
		rt_rq = rt_rq_of_se(rt_se);

		if (sched_rt_runtime(rt_rq) != RUNTIME_INF) {
			raw_spin_lock(&rt_rq->rt_runtime_lock);
			rt_rq->rt_time += delta_exec;
			if (sched_rt_runtime_exceeded(rt_rq))
				resched_task(curr);
			raw_spin_unlock(&rt_rq->rt_runtime_lock);
		}
	}
}

#if defined CONFIG_SMP

static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu);

static inline int next_prio(struct rq *rq)
{
	struct task_struct *next = pick_next_highest_task_rt(rq, rq->cpu);

	if (next && rt_prio(next->prio))
		return next->prio;
	else
		return MAX_RT_PRIO;
}

static void
inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
{
	struct rq *rq = rq_of_rt_rq(rt_rq);

	if (prio < prev_prio) {

		/*
		 * If the new task is higher in priority than anything on the
		 * run-queue, we know that the previous high becomes our
		 * next-highest.
		 */
		rt_rq->highest_prio.next = prev_prio;

		if (rq->online)
			cpupri_set(&rq->rd->cpupri, rq->cpu, prio);

	} else if (prio == rt_rq->highest_prio.curr)
		/*
		 * If the next task is equal in priority to the highest on
		 * the run-queue, then we implicitly know that the next highest
		 * task cannot be any lower than current
		 */
		rt_rq->highest_prio.next = prio;
	else if (prio < rt_rq->highest_prio.next)
		/*
		 * Otherwise, we need to recompute next-highest
		 */
		rt_rq->highest_prio.next = next_prio(rq);
}

static void
dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio)
{
	struct rq *rq = rq_of_rt_rq(rt_rq);

	if (rt_rq->rt_nr_running && (prio <= rt_rq->highest_prio.next))
		rt_rq->highest_prio.next = next_prio(rq);

	if (rq->online && rt_rq->highest_prio.curr != prev_prio)
		cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr);
}

#else /* CONFIG_SMP */

static inline
void inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) {}
static inline
void dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) {}

#endif /* CONFIG_SMP */

#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
static void
inc_rt_prio(struct rt_rq *rt_rq, int prio)
{
	int prev_prio = rt_rq->highest_prio.curr;

	if (prio < prev_prio)
		rt_rq->highest_prio.curr = prio;

	inc_rt_prio_smp(rt_rq, prio, prev_prio);
}

static void
dec_rt_prio(struct rt_rq *rt_rq, int prio)
{
	int prev_prio = rt_rq->highest_prio.curr;

	if (rt_rq->rt_nr_running) {

		WARN_ON(prio < prev_prio);

		/*
		 * This may have been our highest task, and therefore
		 * we may have some recomputation to do
		 */
		if (prio == prev_prio) {
			struct rt_prio_array *array = &rt_rq->active;

			rt_rq->highest_prio.curr =
				sched_find_first_bit(array->bitmap);
		}

	} else
		rt_rq->highest_prio.curr = MAX_RT_PRIO;

	dec_rt_prio_smp(rt_rq, prio, prev_prio);
}

#else

static inline void inc_rt_prio(struct rt_rq *rt_rq, int prio) {}
static inline void dec_rt_prio(struct rt_rq *rt_rq, int prio) {}

#endif /* CONFIG_SMP || CONFIG_RT_GROUP_SCHED */

#ifdef CONFIG_RT_GROUP_SCHED

static void
inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
	if (rt_se_boosted(rt_se))
		rt_rq->rt_nr_boosted++;

	if (rt_rq->tg)
		start_rt_bandwidth(&rt_rq->tg->rt_bandwidth);
}

static void
dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
	if (rt_se_boosted(rt_se))
		rt_rq->rt_nr_boosted--;

	WARN_ON(!rt_rq->rt_nr_running && rt_rq->rt_nr_boosted);
}

#else /* CONFIG_RT_GROUP_SCHED */

static void
inc_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
	start_rt_bandwidth(&def_rt_bandwidth);
}

static inline
void dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) {}

#endif /* CONFIG_RT_GROUP_SCHED */

static inline
void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
	int prio = rt_se_prio(rt_se);

	WARN_ON(!rt_prio(prio));
	rt_rq->rt_nr_running++;

	inc_rt_prio(rt_rq, prio);
	inc_rt_migration(rt_se, rt_rq);
	inc_rt_group(rt_se, rt_rq);
}

static inline
void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
{
	WARN_ON(!rt_prio(rt_se_prio(rt_se)));
	WARN_ON(!rt_rq->rt_nr_running);
	rt_rq->rt_nr_running--;

	dec_rt_prio(rt_rq, rt_se_prio(rt_se));
	dec_rt_migration(rt_se, rt_rq);
	dec_rt_group(rt_se, rt_rq);
}

static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
{
	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
	struct rt_prio_array *array = &rt_rq->active;
	struct rt_rq *group_rq = group_rt_rq(rt_se);
	struct list_head *queue = array->queue + rt_se_prio(rt_se);

	/*
	 * Don't enqueue the group if its throttled, or when empty.
	 * The latter is a consequence of the former when a child group
	 * get throttled and the current group doesn't have any other
	 * active members.
	 */
	if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
		return;

	if (head)
		list_add(&rt_se->run_list, queue);
	else
		list_add_tail(&rt_se->run_list, queue);
	__set_bit(rt_se_prio(rt_se), array->bitmap);

	inc_rt_tasks(rt_se, rt_rq);
}

static void __dequeue_rt_entity(struct sched_rt_entity *rt_se)
{
	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
	struct rt_prio_array *array = &rt_rq->active;

	list_del_init(&rt_se->run_list);
	if (list_empty(array->queue + rt_se_prio(rt_se)))
		__clear_bit(rt_se_prio(rt_se), array->bitmap);

	dec_rt_tasks(rt_se, rt_rq);
}

/*
 * Because the prio of an upper entry depends on the lower
 * entries, we must remove entries top - down.
 */
static void dequeue_rt_stack(struct sched_rt_entity *rt_se)
{
	struct sched_rt_entity *back = NULL;

	for_each_sched_rt_entity(rt_se) {
		rt_se->back = back;
		back = rt_se;
	}

	for (rt_se = back; rt_se; rt_se = rt_se->back) {
		if (on_rt_rq(rt_se))
			__dequeue_rt_entity(rt_se);
	}
}

static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
{
	dequeue_rt_stack(rt_se);
	for_each_sched_rt_entity(rt_se)
		__enqueue_rt_entity(rt_se, head);
}

static void dequeue_rt_entity(struct sched_rt_entity *rt_se)
{
	dequeue_rt_stack(rt_se);

	for_each_sched_rt_entity(rt_se) {
		struct rt_rq *rt_rq = group_rt_rq(rt_se);

		if (rt_rq && rt_rq->rt_nr_running)
			__enqueue_rt_entity(rt_se, false);
	}
}

/*
 * Adding/removing a task to/from a priority array:
 */
static void
enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
{
	struct sched_rt_entity *rt_se = &p->rt;

	if (flags & ENQUEUE_WAKEUP)
		rt_se->timeout = 0;

	enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD);

	if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
		enqueue_pushable_task(rq, p);
}

static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
{
	struct sched_rt_entity *rt_se = &p->rt;

	update_curr_rt(rq);
	dequeue_rt_entity(rt_se);

	dequeue_pushable_task(rq, p);
}

/*
 * Put task to the end of the run list without the overhead of dequeue
 * followed by enqueue.
 */
static void
requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se, int head)
{
	if (on_rt_rq(rt_se)) {
		struct rt_prio_array *array = &rt_rq->active;
		struct list_head *queue = array->queue + rt_se_prio(rt_se);

		if (head)
			list_move(&rt_se->run_list, queue);
		else
			list_move_tail(&rt_se->run_list, queue);
	}
}

static void requeue_task_rt(struct rq *rq, struct task_struct *p, int head)
{
	struct sched_rt_entity *rt_se = &p->rt;
	struct rt_rq *rt_rq;

	for_each_sched_rt_entity(rt_se) {
		rt_rq = rt_rq_of_se(rt_se);
		requeue_rt_entity(rt_rq, rt_se, head);
	}
}

static void yield_task_rt(struct rq *rq)
{
	requeue_task_rt(rq, rq->curr, 0);
}

#ifdef CONFIG_SMP
static int find_lowest_rq(struct task_struct *task);

static int
select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
{
	if (sd_flag != SD_BALANCE_WAKE)
		return smp_processor_id();

	/*
	 * If the current task is an RT task, then
	 * try to see if we can wake this RT task up on another
	 * runqueue. Otherwise simply start this RT task
	 * on its current runqueue.
	 *
	 * We want to avoid overloading runqueues. Even if
	 * the RT task is of higher priority than the current RT task.
	 * RT tasks behave differently than other tasks. If
	 * one gets preempted, we try to push it off to another queue.
	 * So trying to keep a preempting RT task on the same
	 * cache hot CPU will force the running RT task to
	 * a cold CPU. So we waste all the cache for the lower
	 * RT task in hopes of saving some of a RT task
	 * that is just being woken and probably will have
	 * cold cache anyway.
	 */
	if (unlikely(rt_task(rq->curr)) &&
	    (p->rt.nr_cpus_allowed > 1)) {
		int cpu = find_lowest_rq(p);

		return (cpu == -1) ? task_cpu(p) : cpu;
	}

	/*
	 * Otherwise, just let it ride on the affined RQ and the
	 * post-schedule router will push the preempted task away
	 */
	return task_cpu(p);
}

static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
{
	if (rq->curr->rt.nr_cpus_allowed == 1)
		return;

	if (p->rt.nr_cpus_allowed != 1
	    && cpupri_find(&rq->rd->cpupri, p, NULL))
		return;

	if (!cpupri_find(&rq->rd->cpupri, rq->curr, NULL))
		return;

	/*
	 * There appears to be other cpus that can accept
	 * current and none to run 'p', so lets reschedule
	 * to try and push current away:
	 */
	requeue_task_rt(rq, p, 1);
	resched_task(rq->curr);
}

#endif /* CONFIG_SMP */

/*
 * Preempt the current task with a newly woken task if needed:
 */
static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flags)
{
	if (p->prio < rq->curr->prio) {
		resched_task(rq->curr);
		return;
	}

#ifdef CONFIG_SMP
	/*
	 * If:
	 *
	 * - the newly woken task is of equal priority to the current task
	 * - the newly woken task is non-migratable while current is migratable
	 * - current will be preempted on the next reschedule
	 *
	 * we should check to see if current can readily move to a different
	 * cpu.  If so, we will reschedule to allow the push logic to try
	 * to move current somewhere else, making room for our non-migratable
	 * task.
	 */
	if (p->prio == rq->curr->prio && !need_resched())
		check_preempt_equal_prio(rq, p);
#endif
}

static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
						   struct rt_rq *rt_rq)
{
	struct rt_prio_array *array = &rt_rq->active;
	struct sched_rt_entity *next = NULL;
	struct list_head *queue;
	int idx;

	idx = sched_find_first_bit(array->bitmap);
	BUG_ON(idx >= MAX_RT_PRIO);

	queue = array->queue + idx;
	next = list_entry(queue->next, struct sched_rt_entity, run_list);

	return next;
}

static struct task_struct *_pick_next_task_rt(struct rq *rq)
{
	struct sched_rt_entity *rt_se;
	struct task_struct *p;
	struct rt_rq *rt_rq;

	rt_rq = &rq->rt;

	if (unlikely(!rt_rq->rt_nr_running))
		return NULL;

	if (rt_rq_throttled(rt_rq))
		return NULL;

	do {
		rt_se = pick_next_rt_entity(rq, rt_rq);
		BUG_ON(!rt_se);
		rt_rq = group_rt_rq(rt_se);
	} while (rt_rq);

	p = rt_task_of(rt_se);
	p->se.exec_start = rq->clock;

	return p;
}

static struct task_struct *pick_next_task_rt(struct rq *rq)
{
	struct task_struct *p = _pick_next_task_rt(rq);

	/* The running task is never eligible for pushing */
	if (p)
		dequeue_pushable_task(rq, p);

#ifdef CONFIG_SMP
	/*
	 * We detect this state here so that we can avoid taking the RQ
	 * lock again later if there is no need to push
	 */
	rq->post_schedule = has_pushable_tasks(rq);
#endif

	return p;
}

static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
{
	update_curr_rt(rq);
	p->se.exec_start = 0;

	/*
	 * The previous task needs to be made eligible for pushing
	 * if it is still active
	 */
	if (p->se.on_rq && p->rt.nr_cpus_allowed > 1)
		enqueue_pushable_task(rq, p);
}

#ifdef CONFIG_SMP

/* Only try algorithms three times */
#define RT_MAX_TRIES 3

static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep);

static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
{
	if (!task_running(rq, p) &&
	    (cpu < 0 || cpumask_test_cpu(cpu, &p->cpus_allowed)) &&
	    (p->rt.nr_cpus_allowed > 1))
		return 1;
	return 0;
}

/* Return the second highest RT task, NULL otherwise */
static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
{
	struct task_struct *next = NULL;
	struct sched_rt_entity *rt_se;
	struct rt_prio_array *array;
	struct rt_rq *rt_rq;
	int idx;

	for_each_leaf_rt_rq(rt_rq, rq) {
		array = &rt_rq->active;
		idx = sched_find_first_bit(array->bitmap);
 next_idx:
		if (idx >= MAX_RT_PRIO)
			continue;
		if (next && next->prio < idx)
			continue;
		list_for_each_entry(rt_se, array->queue + idx, run_list) {
			struct task_struct *p;

			if (!rt_entity_is_task(rt_se))
				continue;

			p = rt_task_of(rt_se);
			if (pick_rt_task(rq, p, cpu)) {
				next = p;
				break;
			}
		}
		if (!next) {
			idx = find_next_bit(array->bitmap, MAX_RT_PRIO, idx+1);
			goto next_idx;
		}
	}

	return next;
}

static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask);

static int find_lowest_rq(struct task_struct *task)
{
	struct sched_domain *sd;
	struct cpumask *lowest_mask = __get_cpu_var(local_cpu_mask);
	int this_cpu = smp_processor_id();
	int cpu      = task_cpu(task);

	if (task->rt.nr_cpus_allowed == 1)
		return -1; /* No other targets possible */

	if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask))
		return -1; /* No targets found */

	/*
	 * At this point we have built a mask of cpus representing the
	 * lowest priority tasks in the system.  Now we want to elect
	 * the best one based on our affinity and topology.
	 *
	 * We prioritize the last cpu that the task executed on since
	 * it is most likely cache-hot in that location.
	 */
	if (cpumask_test_cpu(cpu, lowest_mask))
		return cpu;

	/*
	 * Otherwise, we consult the sched_domains span maps to figure
	 * out which cpu is logically closest to our hot cache data.
	 */
	if (!cpumask_test_cpu(this_cpu, lowest_mask))
		this_cpu = -1; /* Skip this_cpu opt if not among lowest */

	for_each_domain(cpu, sd) {
		if (sd->flags & SD_WAKE_AFFINE) {
			int best_cpu;

			/*
			 * "this_cpu" is cheaper to preempt than a
			 * remote processor.
			 */
			if (this_cpu != -1 &&
			    cpumask_test_cpu(this_cpu, sched_domain_span(sd)))
				return this_cpu;

			best_cpu = cpumask_first_and(lowest_mask,
						     sched_domain_span(sd));
			if (best_cpu < nr_cpu_ids)
				return best_cpu;
		}
	}

	/*
	 * And finally, if there were no matches within the domains
	 * just give the caller *something* to work with from the compatible
	 * locations.
	 */
	if (this_cpu != -1)
		return this_cpu;

	cpu = cpumask_any(lowest_mask);
	if (cpu < nr_cpu_ids)
		return cpu;
	return -1;
}

/* Will lock the rq it finds */
static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
{
	struct rq *lowest_rq = NULL;
	int tries;
	int cpu;

	for (tries = 0; tries < RT_MAX_TRIES; tries++) {
		cpu = find_lowest_rq(task);

		if ((cpu == -1) || (cpu == rq->cpu))
			break;

		lowest_rq = cpu_rq(cpu);

		/* if the prio of this runqueue changed, try again */
		if (double_lock_balance(rq, lowest_rq)) {
			/*
			 * We had to unlock the run queue. In
			 * the mean time, task could have
			 * migrated already or had its affinity changed.
			 * Also make sure that it wasn't scheduled on its rq.
			 */
			if (unlikely(task_rq(task) != rq ||
				     !cpumask_test_cpu(lowest_rq->cpu,
						       &task->cpus_allowed) ||
				     task_running(rq, task) ||
				     !task->se.on_rq)) {

				raw_spin_unlock(&lowest_rq->lock);
				lowest_rq = NULL;
				break;
			}
		}

		/* If this rq is still suitable use it. */
		if (lowest_rq->rt.highest_prio.curr > task->prio)
			break;

		/* try again */
		double_unlock_balance(rq, lowest_rq);
		lowest_rq = NULL;
	}

	return lowest_rq;
}

static struct task_struct *pick_next_pushable_task(struct rq *rq)
{
	struct task_struct *p;

	if (!has_pushable_tasks(rq))
		return NULL;

	p = plist_first_entry(&rq->rt.pushable_tasks,
			      struct task_struct, pushable_tasks);

	BUG_ON(rq->cpu != task_cpu(p));
	BUG_ON(task_current(rq, p));
	BUG_ON(p->rt.nr_cpus_allowed <= 1);

	BUG_ON(!p->se.on_rq);
	BUG_ON(!rt_task(p));

	return p;
}

/*
 * If the current CPU has more than one RT task, see if the non
 * running task can migrate over to a CPU that is running a task
 * of lesser priority.
 */
static int push_rt_task(struct rq *rq)
{
	struct task_struct *next_task;
	struct rq *lowest_rq;

	if (!rq->rt.overloaded)
		return 0;

	next_task = pick_next_pushable_task(rq);
	if (!next_task)
		return 0;

 retry:
	if (unlikely(next_task == rq->curr)) {
		WARN_ON(1);
		return 0;
	}

	/*
	 * It's possible that the next_task slipped in of
	 * higher priority than current. If that's the case
	 * just reschedule current.
	 */
	if (unlikely(next_task->prio < rq->curr->prio)) {
		resched_task(rq->curr);
		return 0;
	}

	/* We might release rq lock */
	get_task_struct(next_task);

	/* find_lock_lowest_rq locks the rq if found */
	lowest_rq = find_lock_lowest_rq(next_task, rq);
	if (!lowest_rq) {
		struct task_struct *task;
		/*
		 * find lock_lowest_rq releases rq->lock
		 * so it is possible that next_task has migrated.
		 *
		 * We need to make sure that the task is still on the same
		 * run-queue and is also still the next task eligible for
		 * pushing.
		 */
		task = pick_next_pushable_task(rq);
		if (task_cpu(next_task) == rq->cpu && task == next_task) {
			/*
			 * If we get here, the task hasnt moved at all, but
			 * it has failed to push.  We will not try again,
			 * since the other cpus will pull from us when they
			 * are ready.
			 */
			dequeue_pushable_task(rq, next_task);
			goto out;
		}

		if (!task)
			/* No more tasks, just exit */
			goto out;

		/*
		 * Something has shifted, try again.
		 */
		put_task_struct(next_task);
		next_task = task;
		goto retry;
	}

	deactivate_task(rq, next_task, 0);
	set_task_cpu(next_task, lowest_rq->cpu);
	activate_task(lowest_rq, next_task, 0);

	resched_task(lowest_rq->curr);

	double_unlock_balance(rq, lowest_rq);

out:
	put_task_struct(next_task);

	return 1;
}

static void push_rt_tasks(struct rq *rq)
{
	/* push_rt_task will return true if it moved an RT */
	while (push_rt_task(rq))
		;
}

static int pull_rt_task(struct rq *this_rq)
{
	int this_cpu = this_rq->cpu, ret = 0, cpu;
	struct task_struct *p;
	struct rq *src_rq;

	if (likely(!rt_overloaded(this_rq)))
		return 0;

	for_each_cpu(cpu, this_rq->rd->rto_mask) {
		if (this_cpu == cpu)
			continue;

		src_rq = cpu_rq(cpu);

		/*
		 * Don't bother taking the src_rq->lock if the next highest
		 * task is known to be lower-priority than our current task.
		 * This may look racy, but if this value is about to go
		 * logically higher, the src_rq will push this task away.
		 * And if its going logically lower, we do not care
		 */
		if (src_rq->rt.highest_prio.next >=
		    this_rq->rt.highest_prio.curr)
			continue;

		/*
		 * We can potentially drop this_rq's lock in
		 * double_lock_balance, and another CPU could
		 * alter this_rq
		 */
		double_lock_balance(this_rq, src_rq);

		/*
		 * Are there still pullable RT tasks?
		 */
		if (src_rq->rt.rt_nr_running <= 1)
			goto skip;

		p = pick_next_highest_task_rt(src_rq, this_cpu);

		/*
		 * Do we have an RT task that preempts
		 * the to-be-scheduled task?
		 */
		if (p && (p->prio < this_rq->rt.highest_prio.curr)) {
			WARN_ON(p == src_rq->curr);
			WARN_ON(!p->se.on_rq);

			/*
			 * There's a chance that p is higher in priority
			 * than what's currently running on its cpu.
			 * This is just that p is wakeing up and hasn't
			 * had a chance to schedule. We only pull
			 * p if it is lower in priority than the
			 * current task on the run queue
			 */
			if (p->prio < src_rq->curr->prio)
				goto skip;

			ret = 1;

			deactivate_task(src_rq, p, 0);
			set_task_cpu(p, this_cpu);
			activate_task(this_rq, p, 0);
			/*
			 * We continue with the search, just in
			 * case there's an even higher prio task
			 * in another runqueue. (low likelyhood
			 * but possible)
			 */
		}
 skip:
		double_unlock_balance(this_rq, src_rq);
	}

	return ret;
}

static void pre_schedule_rt(struct rq *rq, struct task_struct *prev)
{
	/* Try to pull RT tasks here if we lower this rq's prio */
	if (unlikely(rt_task(prev)) && rq->rt.highest_prio.curr > prev->prio)
		pull_rt_task(rq);
}

static void post_schedule_rt(struct rq *rq)
{
	push_rt_tasks(rq);
}

/*
 * If we are not running and we are not going to reschedule soon, we should
 * try to push tasks away now
 */
static void task_woken_rt(struct rq *rq, struct task_struct *p)
{
	if (!task_running(rq, p) &&
	    !test_tsk_need_resched(rq->curr) &&
	    has_pushable_tasks(rq) &&
	    p->rt.nr_cpus_allowed > 1)
		push_rt_tasks(rq);
}

static void set_cpus_allowed_rt(struct task_struct *p,
				const struct cpumask *new_mask)
{
	int weight = cpumask_weight(new_mask);

	BUG_ON(!rt_task(p));

	/*
	 * Update the migration status of the RQ if we have an RT task
	 * which is running AND changing its weight value.
	 */
	if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) {
		struct rq *rq = task_rq(p);

		if (!task_current(rq, p)) {
			/*
			 * Make sure we dequeue this task from the pushable list
			 * before going further.  It will either remain off of
			 * the list because we are no longer pushable, or it
			 * will be requeued.
			 */
			if (p->rt.nr_cpus_allowed > 1)
				dequeue_pushable_task(rq, p);

			/*
			 * Requeue if our weight is changing and still > 1
			 */
			if (weight > 1)
				enqueue_pushable_task(rq, p);

		}

		if ((p->rt.nr_cpus_allowed <= 1) && (weight > 1)) {
			rq->rt.rt_nr_migratory++;
		} else if ((p->rt.nr_cpus_allowed > 1) && (weight <= 1)) {
			BUG_ON(!rq->rt.rt_nr_migratory);
			rq->rt.rt_nr_migratory--;
		}

		update_rt_migration(&rq->rt);
	}

	cpumask_copy(&p->cpus_allowed, new_mask);
	p->rt.nr_cpus_allowed = weight;
}

/* Assumes rq->lock is held */
static void rq_online_rt(struct rq *rq)
{
	if (rq->rt.overloaded)
		rt_set_overload(rq);

	__enable_runtime(rq);

	cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr);
}

/* Assumes rq->lock is held */
static void rq_offline_rt(struct rq *rq)
{
	if (rq->rt.overloaded)
		rt_clear_overload(rq);

	__disable_runtime(rq);

	cpupri_set(&rq->rd->cpupri, rq->cpu, CPUPRI_INVALID);
}

/*
 * When switch from the rt queue, we bring ourselves to a position
 * that we might want to pull RT tasks from other runqueues.
 */
static void switched_from_rt(struct rq *rq, struct task_struct *p,
			   int running)
{
	/*
	 * If there are other RT tasks then we will reschedule
	 * and the scheduling of the other RT tasks will handle
	 * the balancing. But if we are the last RT task
	 * we may need to handle the pulling of RT tasks
	 * now.
	 */
	if (!rq->rt.rt_nr_running)
		pull_rt_task(rq);
}

static inline void init_sched_rt_class(void)
{
	unsigned int i;

	for_each_possible_cpu(i)
		zalloc_cpumask_var_node(&per_cpu(local_cpu_mask, i),
					GFP_KERNEL, cpu_to_node(i));
}
#endif /* CONFIG_SMP */

/*
 * When switching a task to RT, we may overload the runqueue
 * with RT tasks. In this case we try to push them off to
 * other runqueues.
 */
static void switched_to_rt(struct rq *rq, struct task_struct *p,
			   int running)
{
	int check_resched = 1;

	/*
	 * If we are already running, then there's nothing
	 * that needs to be done. But if we are not running
	 * we may need to preempt the current running task.
	 * If that current running task is also an RT task
	 * then see if we can move to another run queue.
	 */
	if (!running) {
#ifdef CONFIG_SMP
		if (rq->rt.overloaded && push_rt_task(rq) &&
		    /* Don't resched if we changed runqueues */
		    rq != task_rq(p))
			check_resched = 0;
#endif /* CONFIG_SMP */
		if (check_resched && p->prio < rq->curr->prio)
			resched_task(rq->curr);
	}
}

/*
 * Priority of the task has changed. This may cause
 * us to initiate a push or pull.
 */
static void prio_changed_rt(struct rq *rq, struct task_struct *p,
			    int oldprio, int running)
{
	if (running) {
#ifdef CONFIG_SMP
		/*
		 * If our priority decreases while running, we
		 * may need to pull tasks to this runqueue.
		 */
		if (oldprio < p->prio)
			pull_rt_task(rq);
		/*
		 * If there's a higher priority task waiting to run
		 * then reschedule. Note, the above pull_rt_task
		 * can release the rq lock and p could migrate.
		 * Only reschedule if p is still on the same runqueue.
		 */
		if (p->prio > rq->rt.highest_prio.curr && rq->curr == p)
			resched_task(p);
#else
		/* For UP simply resched on drop of prio */
		if (oldprio < p->prio)
			resched_task(p);
#endif /* CONFIG_SMP */
	} else {
		/*
		 * This task is not running, but if it is
		 * greater than the current running task
		 * then reschedule.
		 */
		if (p->prio < rq->curr->prio)
			resched_task(rq->curr);
	}
}

static void watchdog(struct rq *rq, struct task_struct *p)
{
	unsigned long soft, hard;

	if (!p->signal)
		return;

	/* max may change after cur was read, this will be fixed next tick */
	soft = task_rlimit(p, RLIMIT_RTTIME);
	hard = task_rlimit_max(p, RLIMIT_RTTIME);

	if (soft != RLIM_INFINITY) {
		unsigned long next;

		p->rt.timeout++;
		next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ);
		if (p->rt.timeout > next)
			p->cputime_expires.sched_exp = p->se.sum_exec_runtime;
	}
}

static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
{
	update_curr_rt(rq);

	watchdog(rq, p);

	/*
	 * RR tasks need a special form of timeslice management.
	 * FIFO tasks have no timeslices.
	 */
	if (p->policy != SCHED_RR)
		return;

	if (--p->rt.time_slice)
		return;

	p->rt.time_slice = DEF_TIMESLICE;

	/*
	 * Requeue to the end of queue if we are not the only element
	 * on the queue:
	 */
	if (p->rt.run_list.prev != p->rt.run_list.next) {
		requeue_task_rt(rq, p, 0);
		set_tsk_need_resched(p);
	}
}

static void set_curr_task_rt(struct rq *rq)
{
	struct task_struct *p = rq->curr;

	p->se.exec_start = rq->clock;

	/* The running task is never eligible for pushing */
	dequeue_pushable_task(rq, p);
}

static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
{
	/*
	 * Time slice is 0 for SCHED_FIFO tasks
	 */
	if (task->policy == SCHED_RR)
		return DEF_TIMESLICE;
	else
		return 0;
}

static const struct sched_class rt_sched_class = {
	.next			= &fair_sched_class,
	.enqueue_task		= enqueue_task_rt,
	.dequeue_task		= dequeue_task_rt,
	.yield_task		= yield_task_rt,

	.check_preempt_curr	= check_preempt_curr_rt,

	.pick_next_task		= pick_next_task_rt,
	.put_prev_task		= put_prev_task_rt,

#ifdef CONFIG_SMP
	.select_task_rq		= select_task_rq_rt,

	.set_cpus_allowed       = set_cpus_allowed_rt,
	.rq_online              = rq_online_rt,
	.rq_offline             = rq_offline_rt,
	.pre_schedule		= pre_schedule_rt,
	.post_schedule		= post_schedule_rt,
	.task_woken		= task_woken_rt,
	.switched_from		= switched_from_rt,
#endif

	.set_curr_task          = set_curr_task_rt,
	.task_tick		= task_tick_rt,

	.get_rr_interval	= get_rr_interval_rt,

	.prio_changed		= prio_changed_rt,
	.switched_to		= switched_to_rt,
};

#ifdef CONFIG_SCHED_DEBUG
extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);

static void print_rt_stats(struct seq_file *m, int cpu)
{
	struct rt_rq *rt_rq;

	rcu_read_lock();
	for_each_leaf_rt_rq(rt_rq, cpu_rq(cpu))
		print_rt_rq(m, cpu, rt_rq);
	rcu_read_unlock();
}
#endif /* CONFIG_SCHED_DEBUG */