summaryrefslogtreecommitdiff
path: root/kernel/sched/topology.c
blob: 61a1125c1ae4224e8f69938406f0d08ad47519b7 (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
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
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
// SPDX-License-Identifier: GPL-2.0
/*
 * Scheduler topology setup/handling methods
 */
#include "sched.h"

DEFINE_MUTEX(sched_domains_mutex);

/* Protected by sched_domains_mutex: */
cpumask_var_t sched_domains_tmpmask;
cpumask_var_t sched_domains_tmpmask2;

#ifdef CONFIG_SCHED_DEBUG

static int __init sched_debug_setup(char *str)
{
	sched_debug_enabled = true;

	return 0;
}
early_param("sched_debug", sched_debug_setup);

static inline bool sched_debug(void)
{
	return sched_debug_enabled;
}

static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
				  struct cpumask *groupmask)
{
	struct sched_group *group = sd->groups;

	cpumask_clear(groupmask);

	printk(KERN_DEBUG "%*s domain-%d: ", level, "", level);

	if (!(sd->flags & SD_LOAD_BALANCE)) {
		printk("does not load-balance\n");
		if (sd->parent)
			printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain has parent");
		return -1;
	}

	printk(KERN_CONT "span=%*pbl level=%s\n",
	       cpumask_pr_args(sched_domain_span(sd)), sd->name);

	if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
		printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu);
	}
	if (!cpumask_test_cpu(cpu, sched_group_span(group))) {
		printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu);
	}

	printk(KERN_DEBUG "%*s groups:", level + 1, "");
	do {
		if (!group) {
			printk("\n");
			printk(KERN_ERR "ERROR: group is NULL\n");
			break;
		}

		if (!cpumask_weight(sched_group_span(group))) {
			printk(KERN_CONT "\n");
			printk(KERN_ERR "ERROR: empty group\n");
			break;
		}

		if (!(sd->flags & SD_OVERLAP) &&
		    cpumask_intersects(groupmask, sched_group_span(group))) {
			printk(KERN_CONT "\n");
			printk(KERN_ERR "ERROR: repeated CPUs\n");
			break;
		}

		cpumask_or(groupmask, groupmask, sched_group_span(group));

		printk(KERN_CONT " %d:{ span=%*pbl",
				group->sgc->id,
				cpumask_pr_args(sched_group_span(group)));

		if ((sd->flags & SD_OVERLAP) &&
		    !cpumask_equal(group_balance_mask(group), sched_group_span(group))) {
			printk(KERN_CONT " mask=%*pbl",
				cpumask_pr_args(group_balance_mask(group)));
		}

		if (group->sgc->capacity != SCHED_CAPACITY_SCALE)
			printk(KERN_CONT " cap=%lu", group->sgc->capacity);

		if (group == sd->groups && sd->child &&
		    !cpumask_equal(sched_domain_span(sd->child),
				   sched_group_span(group))) {
			printk(KERN_ERR "ERROR: domain->groups does not match domain->child\n");
		}

		printk(KERN_CONT " }");

		group = group->next;

		if (group != sd->groups)
			printk(KERN_CONT ",");

	} while (group != sd->groups);
	printk(KERN_CONT "\n");

	if (!cpumask_equal(sched_domain_span(sd), groupmask))
		printk(KERN_ERR "ERROR: groups don't span domain->span\n");

	if (sd->parent &&
	    !cpumask_subset(groupmask, sched_domain_span(sd->parent)))
		printk(KERN_ERR "ERROR: parent span is not a superset of domain->span\n");
	return 0;
}

static void sched_domain_debug(struct sched_domain *sd, int cpu)
{
	int level = 0;

	if (!sched_debug_enabled)
		return;

	if (!sd) {
		printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
		return;
	}

	printk(KERN_DEBUG "CPU%d attaching sched-domain(s):\n", cpu);

	for (;;) {
		if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
			break;
		level++;
		sd = sd->parent;
		if (!sd)
			break;
	}
}
#else /* !CONFIG_SCHED_DEBUG */

# define sched_debug_enabled 0
# define sched_domain_debug(sd, cpu) do { } while (0)
static inline bool sched_debug(void)
{
	return false;
}
#endif /* CONFIG_SCHED_DEBUG */

static int sd_degenerate(struct sched_domain *sd)
{
	if (cpumask_weight(sched_domain_span(sd)) == 1)
		return 1;

	/* Following flags need at least 2 groups */
	if (sd->flags & (SD_LOAD_BALANCE |
			 SD_BALANCE_NEWIDLE |
			 SD_BALANCE_FORK |
			 SD_BALANCE_EXEC |
			 SD_SHARE_CPUCAPACITY |
			 SD_ASYM_CPUCAPACITY |
			 SD_SHARE_PKG_RESOURCES |
			 SD_SHARE_POWERDOMAIN)) {
		if (sd->groups != sd->groups->next)
			return 0;
	}

	/* Following flags don't use groups */
	if (sd->flags & (SD_WAKE_AFFINE))
		return 0;

	return 1;
}

static int
sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
{
	unsigned long cflags = sd->flags, pflags = parent->flags;

	if (sd_degenerate(parent))
		return 1;

	if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
		return 0;

	/* Flags needing groups don't count if only 1 group in parent */
	if (parent->groups == parent->groups->next) {
		pflags &= ~(SD_LOAD_BALANCE |
				SD_BALANCE_NEWIDLE |
				SD_BALANCE_FORK |
				SD_BALANCE_EXEC |
				SD_ASYM_CPUCAPACITY |
				SD_SHARE_CPUCAPACITY |
				SD_SHARE_PKG_RESOURCES |
				SD_PREFER_SIBLING |
				SD_SHARE_POWERDOMAIN);
		if (nr_node_ids == 1)
			pflags &= ~SD_SERIALIZE;
	}
	if (~cflags & pflags)
		return 0;

	return 1;
}

static void free_rootdomain(struct rcu_head *rcu)
{
	struct root_domain *rd = container_of(rcu, struct root_domain, rcu);

	cpupri_cleanup(&rd->cpupri);
	cpudl_cleanup(&rd->cpudl);
	free_cpumask_var(rd->dlo_mask);
	free_cpumask_var(rd->rto_mask);
	free_cpumask_var(rd->online);
	free_cpumask_var(rd->span);
	kfree(rd);
}

void rq_attach_root(struct rq *rq, struct root_domain *rd)
{
	struct root_domain *old_rd = NULL;
	unsigned long flags;

	raw_spin_lock_irqsave(&rq->lock, flags);

	if (rq->rd) {
		old_rd = rq->rd;

		if (cpumask_test_cpu(rq->cpu, old_rd->online))
			set_rq_offline(rq);

		cpumask_clear_cpu(rq->cpu, old_rd->span);

		/*
		 * If we dont want to free the old_rd yet then
		 * set old_rd to NULL to skip the freeing later
		 * in this function:
		 */
		if (!atomic_dec_and_test(&old_rd->refcount))
			old_rd = NULL;
	}

	atomic_inc(&rd->refcount);
	rq->rd = rd;

	cpumask_set_cpu(rq->cpu, rd->span);
	if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
		set_rq_online(rq);

	raw_spin_unlock_irqrestore(&rq->lock, flags);

	if (old_rd)
		call_rcu_sched(&old_rd->rcu, free_rootdomain);
}

void sched_get_rd(struct root_domain *rd)
{
	atomic_inc(&rd->refcount);
}

void sched_put_rd(struct root_domain *rd)
{
	if (!atomic_dec_and_test(&rd->refcount))
		return;

	call_rcu_sched(&rd->rcu, free_rootdomain);
}

static int init_rootdomain(struct root_domain *rd)
{
	if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL))
		goto out;
	if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL))
		goto free_span;
	if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
		goto free_online;
	if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
		goto free_dlo_mask;

#ifdef HAVE_RT_PUSH_IPI
	rd->rto_cpu = -1;
	raw_spin_lock_init(&rd->rto_lock);
	init_irq_work(&rd->rto_push_work, rto_push_irq_work_func);
#endif

	init_dl_bw(&rd->dl_bw);
	if (cpudl_init(&rd->cpudl) != 0)
		goto free_rto_mask;

	if (cpupri_init(&rd->cpupri) != 0)
		goto free_cpudl;
	return 0;

free_cpudl:
	cpudl_cleanup(&rd->cpudl);
free_rto_mask:
	free_cpumask_var(rd->rto_mask);
free_dlo_mask:
	free_cpumask_var(rd->dlo_mask);
free_online:
	free_cpumask_var(rd->online);
free_span:
	free_cpumask_var(rd->span);
out:
	return -ENOMEM;
}

/*
 * By default the system creates a single root-domain with all CPUs as
 * members (mimicking the global state we have today).
 */
struct root_domain def_root_domain;

void init_defrootdomain(void)
{
	init_rootdomain(&def_root_domain);

	atomic_set(&def_root_domain.refcount, 1);
}

static struct root_domain *alloc_rootdomain(void)
{
	struct root_domain *rd;

	rd = kzalloc(sizeof(*rd), GFP_KERNEL);
	if (!rd)
		return NULL;

	if (init_rootdomain(rd) != 0) {
		kfree(rd);
		return NULL;
	}

	return rd;
}

static void free_sched_groups(struct sched_group *sg, int free_sgc)
{
	struct sched_group *tmp, *first;

	if (!sg)
		return;

	first = sg;
	do {
		tmp = sg->next;

		if (free_sgc && atomic_dec_and_test(&sg->sgc->ref))
			kfree(sg->sgc);

		if (atomic_dec_and_test(&sg->ref))
			kfree(sg);
		sg = tmp;
	} while (sg != first);
}

static void destroy_sched_domain(struct sched_domain *sd)
{
	/*
	 * A normal sched domain may have multiple group references, an
	 * overlapping domain, having private groups, only one.  Iterate,
	 * dropping group/capacity references, freeing where none remain.
	 */
	free_sched_groups(sd->groups, 1);

	if (sd->shared && atomic_dec_and_test(&sd->shared->ref))
		kfree(sd->shared);
	kfree(sd);
}

static void destroy_sched_domains_rcu(struct rcu_head *rcu)
{
	struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);

	while (sd) {
		struct sched_domain *parent = sd->parent;
		destroy_sched_domain(sd);
		sd = parent;
	}
}

static void destroy_sched_domains(struct sched_domain *sd)
{
	if (sd)
		call_rcu(&sd->rcu, destroy_sched_domains_rcu);
}

/*
 * Keep a special pointer to the highest sched_domain that has
 * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this
 * allows us to avoid some pointer chasing select_idle_sibling().
 *
 * Also keep a unique ID per domain (we use the first CPU number in
 * the cpumask of the domain), this allows us to quickly tell if
 * two CPUs are in the same cache domain, see cpus_share_cache().
 */
DEFINE_PER_CPU(struct sched_domain *, sd_llc);
DEFINE_PER_CPU(int, sd_llc_size);
DEFINE_PER_CPU(int, sd_llc_id);
DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
DEFINE_PER_CPU(struct sched_domain *, sd_numa);
DEFINE_PER_CPU(struct sched_domain *, sd_asym);

static void update_top_cache_domain(int cpu)
{
	struct sched_domain_shared *sds = NULL;
	struct sched_domain *sd;
	int id = cpu;
	int size = 1;

	sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
	if (sd) {
		id = cpumask_first(sched_domain_span(sd));
		size = cpumask_weight(sched_domain_span(sd));
		sds = sd->shared;
	}

	rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
	per_cpu(sd_llc_size, cpu) = size;
	per_cpu(sd_llc_id, cpu) = id;
	rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds);

	sd = lowest_flag_domain(cpu, SD_NUMA);
	rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);

	sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
	rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
}

/*
 * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
 * hold the hotplug lock.
 */
static void
cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	struct sched_domain *tmp;

	/* Remove the sched domains which do not contribute to scheduling. */
	for (tmp = sd; tmp; ) {
		struct sched_domain *parent = tmp->parent;
		if (!parent)
			break;

		if (sd_parent_degenerate(tmp, parent)) {
			tmp->parent = parent->parent;
			if (parent->parent)
				parent->parent->child = tmp;
			/*
			 * Transfer SD_PREFER_SIBLING down in case of a
			 * degenerate parent; the spans match for this
			 * so the property transfers.
			 */
			if (parent->flags & SD_PREFER_SIBLING)
				tmp->flags |= SD_PREFER_SIBLING;
			destroy_sched_domain(parent);
		} else
			tmp = tmp->parent;
	}

	if (sd && sd_degenerate(sd)) {
		tmp = sd;
		sd = sd->parent;
		destroy_sched_domain(tmp);
		if (sd)
			sd->child = NULL;
	}

	sched_domain_debug(sd, cpu);

	rq_attach_root(rq, rd);
	tmp = rq->sd;
	rcu_assign_pointer(rq->sd, sd);
	dirty_sched_domain_sysctl(cpu);
	destroy_sched_domains(tmp);

	update_top_cache_domain(cpu);
}

struct s_data {
	struct sched_domain ** __percpu sd;
	struct root_domain	*rd;
};

enum s_alloc {
	sa_rootdomain,
	sa_sd,
	sa_sd_storage,
	sa_none,
};

/*
 * Return the canonical balance CPU for this group, this is the first CPU
 * of this group that's also in the balance mask.
 *
 * The balance mask are all those CPUs that could actually end up at this
 * group. See build_balance_mask().
 *
 * Also see should_we_balance().
 */
int group_balance_cpu(struct sched_group *sg)
{
	return cpumask_first(group_balance_mask(sg));
}


/*
 * NUMA topology (first read the regular topology blurb below)
 *
 * Given a node-distance table, for example:
 *
 *   node   0   1   2   3
 *     0:  10  20  30  20
 *     1:  20  10  20  30
 *     2:  30  20  10  20
 *     3:  20  30  20  10
 *
 * which represents a 4 node ring topology like:
 *
 *   0 ----- 1
 *   |       |
 *   |       |
 *   |       |
 *   3 ----- 2
 *
 * We want to construct domains and groups to represent this. The way we go
 * about doing this is to build the domains on 'hops'. For each NUMA level we
 * construct the mask of all nodes reachable in @level hops.
 *
 * For the above NUMA topology that gives 3 levels:
 *
 * NUMA-2	0-3		0-3		0-3		0-3
 *  groups:	{0-1,3},{1-3}	{0-2},{0,2-3}	{1-3},{0-1,3}	{0,2-3},{0-2}
 *
 * NUMA-1	0-1,3		0-2		1-3		0,2-3
 *  groups:	{0},{1},{3}	{0},{1},{2}	{1},{2},{3}	{0},{2},{3}
 *
 * NUMA-0	0		1		2		3
 *
 *
 * As can be seen; things don't nicely line up as with the regular topology.
 * When we iterate a domain in child domain chunks some nodes can be
 * represented multiple times -- hence the "overlap" naming for this part of
 * the topology.
 *
 * In order to minimize this overlap, we only build enough groups to cover the
 * domain. For instance Node-0 NUMA-2 would only get groups: 0-1,3 and 1-3.
 *
 * Because:
 *
 *  - the first group of each domain is its child domain; this
 *    gets us the first 0-1,3
 *  - the only uncovered node is 2, who's child domain is 1-3.
 *
 * However, because of the overlap, computing a unique CPU for each group is
 * more complicated. Consider for instance the groups of NODE-1 NUMA-2, both
 * groups include the CPUs of Node-0, while those CPUs would not in fact ever
 * end up at those groups (they would end up in group: 0-1,3).
 *
 * To correct this we have to introduce the group balance mask. This mask
 * will contain those CPUs in the group that can reach this group given the
 * (child) domain tree.
 *
 * With this we can once again compute balance_cpu and sched_group_capacity
 * relations.
 *
 * XXX include words on how balance_cpu is unique and therefore can be
 * used for sched_group_capacity links.
 *
 *
 * Another 'interesting' topology is:
 *
 *   node   0   1   2   3
 *     0:  10  20  20  30
 *     1:  20  10  20  20
 *     2:  20  20  10  20
 *     3:  30  20  20  10
 *
 * Which looks a little like:
 *
 *   0 ----- 1
 *   |     / |
 *   |   /   |
 *   | /     |
 *   2 ----- 3
 *
 * This topology is asymmetric, nodes 1,2 are fully connected, but nodes 0,3
 * are not.
 *
 * This leads to a few particularly weird cases where the sched_domain's are
 * not of the same number for each CPU. Consider:
 *
 * NUMA-2	0-3						0-3
 *  groups:	{0-2},{1-3}					{1-3},{0-2}
 *
 * NUMA-1	0-2		0-3		0-3		1-3
 *
 * NUMA-0	0		1		2		3
 *
 */


/*
 * Build the balance mask; it contains only those CPUs that can arrive at this
 * group and should be considered to continue balancing.
 *
 * We do this during the group creation pass, therefore the group information
 * isn't complete yet, however since each group represents a (child) domain we
 * can fully construct this using the sched_domain bits (which are already
 * complete).
 */
static void
build_balance_mask(struct sched_domain *sd, struct sched_group *sg, struct cpumask *mask)
{
	const struct cpumask *sg_span = sched_group_span(sg);
	struct sd_data *sdd = sd->private;
	struct sched_domain *sibling;
	int i;

	cpumask_clear(mask);

	for_each_cpu(i, sg_span) {
		sibling = *per_cpu_ptr(sdd->sd, i);

		/*
		 * Can happen in the asymmetric case, where these siblings are
		 * unused. The mask will not be empty because those CPUs that
		 * do have the top domain _should_ span the domain.
		 */
		if (!sibling->child)
			continue;

		/* If we would not end up here, we can't continue from here */
		if (!cpumask_equal(sg_span, sched_domain_span(sibling->child)))
			continue;

		cpumask_set_cpu(i, mask);
	}

	/* We must not have empty masks here */
	WARN_ON_ONCE(cpumask_empty(mask));
}

/*
 * XXX: This creates per-node group entries; since the load-balancer will
 * immediately access remote memory to construct this group's load-balance
 * statistics having the groups node local is of dubious benefit.
 */
static struct sched_group *
build_group_from_child_sched_domain(struct sched_domain *sd, int cpu)
{
	struct sched_group *sg;
	struct cpumask *sg_span;

	sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
			GFP_KERNEL, cpu_to_node(cpu));

	if (!sg)
		return NULL;

	sg_span = sched_group_span(sg);
	if (sd->child)
		cpumask_copy(sg_span, sched_domain_span(sd->child));
	else
		cpumask_copy(sg_span, sched_domain_span(sd));

	atomic_inc(&sg->ref);
	return sg;
}

static void init_overlap_sched_group(struct sched_domain *sd,
				     struct sched_group *sg)
{
	struct cpumask *mask = sched_domains_tmpmask2;
	struct sd_data *sdd = sd->private;
	struct cpumask *sg_span;
	int cpu;

	build_balance_mask(sd, sg, mask);
	cpu = cpumask_first_and(sched_group_span(sg), mask);

	sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
	if (atomic_inc_return(&sg->sgc->ref) == 1)
		cpumask_copy(group_balance_mask(sg), mask);
	else
		WARN_ON_ONCE(!cpumask_equal(group_balance_mask(sg), mask));

	/*
	 * Initialize sgc->capacity such that even if we mess up the
	 * domains and no possible iteration will get us here, we won't
	 * die on a /0 trap.
	 */
	sg_span = sched_group_span(sg);
	sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
	sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
}

static int
build_overlap_sched_groups(struct sched_domain *sd, int cpu)
{
	struct sched_group *first = NULL, *last = NULL, *sg;
	const struct cpumask *span = sched_domain_span(sd);
	struct cpumask *covered = sched_domains_tmpmask;
	struct sd_data *sdd = sd->private;
	struct sched_domain *sibling;
	int i;

	cpumask_clear(covered);

	for_each_cpu_wrap(i, span, cpu) {
		struct cpumask *sg_span;

		if (cpumask_test_cpu(i, covered))
			continue;

		sibling = *per_cpu_ptr(sdd->sd, i);

		/*
		 * Asymmetric node setups can result in situations where the
		 * domain tree is of unequal depth, make sure to skip domains
		 * that already cover the entire range.
		 *
		 * In that case build_sched_domains() will have terminated the
		 * iteration early and our sibling sd spans will be empty.
		 * Domains should always include the CPU they're built on, so
		 * check that.
		 */
		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
			continue;

		sg = build_group_from_child_sched_domain(sibling, cpu);
		if (!sg)
			goto fail;

		sg_span = sched_group_span(sg);
		cpumask_or(covered, covered, sg_span);

		init_overlap_sched_group(sd, sg);

		if (!first)
			first = sg;
		if (last)
			last->next = sg;
		last = sg;
		last->next = first;
	}
	sd->groups = first;

	return 0;

fail:
	free_sched_groups(first, 0);

	return -ENOMEM;
}


/*
 * Package topology (also see the load-balance blurb in fair.c)
 *
 * The scheduler builds a tree structure to represent a number of important
 * topology features. By default (default_topology[]) these include:
 *
 *  - Simultaneous multithreading (SMT)
 *  - Multi-Core Cache (MC)
 *  - Package (DIE)
 *
 * Where the last one more or less denotes everything up to a NUMA node.
 *
 * The tree consists of 3 primary data structures:
 *
 *	sched_domain -> sched_group -> sched_group_capacity
 *	    ^ ^             ^ ^
 *          `-'             `-'
 *
 * The sched_domains are per-CPU and have a two way link (parent & child) and
 * denote the ever growing mask of CPUs belonging to that level of topology.
 *
 * Each sched_domain has a circular (double) linked list of sched_group's, each
 * denoting the domains of the level below (or individual CPUs in case of the
 * first domain level). The sched_group linked by a sched_domain includes the
 * CPU of that sched_domain [*].
 *
 * Take for instance a 2 threaded, 2 core, 2 cache cluster part:
 *
 * CPU   0   1   2   3   4   5   6   7
 *
 * DIE  [                             ]
 * MC   [             ] [             ]
 * SMT  [     ] [     ] [     ] [     ]
 *
 *  - or -
 *
 * DIE  0-7 0-7 0-7 0-7 0-7 0-7 0-7 0-7
 * MC	0-3 0-3 0-3 0-3 4-7 4-7 4-7 4-7
 * SMT  0-1 0-1 2-3 2-3 4-5 4-5 6-7 6-7
 *
 * CPU   0   1   2   3   4   5   6   7
 *
 * One way to think about it is: sched_domain moves you up and down among these
 * topology levels, while sched_group moves you sideways through it, at child
 * domain granularity.
 *
 * sched_group_capacity ensures each unique sched_group has shared storage.
 *
 * There are two related construction problems, both require a CPU that
 * uniquely identify each group (for a given domain):
 *
 *  - The first is the balance_cpu (see should_we_balance() and the
 *    load-balance blub in fair.c); for each group we only want 1 CPU to
 *    continue balancing at a higher domain.
 *
 *  - The second is the sched_group_capacity; we want all identical groups
 *    to share a single sched_group_capacity.
 *
 * Since these topologies are exclusive by construction. That is, its
 * impossible for an SMT thread to belong to multiple cores, and cores to
 * be part of multiple caches. There is a very clear and unique location
 * for each CPU in the hierarchy.
 *
 * Therefore computing a unique CPU for each group is trivial (the iteration
 * mask is redundant and set all 1s; all CPUs in a group will end up at _that_
 * group), we can simply pick the first CPU in each group.
 *
 *
 * [*] in other words, the first group of each domain is its child domain.
 */

static struct sched_group *get_group(int cpu, struct sd_data *sdd)
{
	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
	struct sched_domain *child = sd->child;
	struct sched_group *sg;

	if (child)
		cpu = cpumask_first(sched_domain_span(child));

	sg = *per_cpu_ptr(sdd->sg, cpu);
	sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);

	/* For claim_allocations: */
	atomic_inc(&sg->ref);
	atomic_inc(&sg->sgc->ref);

	if (child) {
		cpumask_copy(sched_group_span(sg), sched_domain_span(child));
		cpumask_copy(group_balance_mask(sg), sched_group_span(sg));
	} else {
		cpumask_set_cpu(cpu, sched_group_span(sg));
		cpumask_set_cpu(cpu, group_balance_mask(sg));
	}

	sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sched_group_span(sg));
	sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;

	return sg;
}

/*
 * build_sched_groups will build a circular linked list of the groups
 * covered by the given span, and will set each group's ->cpumask correctly,
 * and ->cpu_capacity to 0.
 *
 * Assumes the sched_domain tree is fully constructed
 */
static int
build_sched_groups(struct sched_domain *sd, int cpu)
{
	struct sched_group *first = NULL, *last = NULL;
	struct sd_data *sdd = sd->private;
	const struct cpumask *span = sched_domain_span(sd);
	struct cpumask *covered;
	int i;

	lockdep_assert_held(&sched_domains_mutex);
	covered = sched_domains_tmpmask;

	cpumask_clear(covered);

	for_each_cpu_wrap(i, span, cpu) {
		struct sched_group *sg;

		if (cpumask_test_cpu(i, covered))
			continue;

		sg = get_group(i, sdd);

		cpumask_or(covered, covered, sched_group_span(sg));

		if (!first)
			first = sg;
		if (last)
			last->next = sg;
		last = sg;
	}
	last->next = first;
	sd->groups = first;

	return 0;
}

/*
 * Initialize sched groups cpu_capacity.
 *
 * cpu_capacity indicates the capacity of sched group, which is used while
 * distributing the load between different sched groups in a sched domain.
 * Typically cpu_capacity for all the groups in a sched domain will be same
 * unless there are asymmetries in the topology. If there are asymmetries,
 * group having more cpu_capacity will pickup more load compared to the
 * group having less cpu_capacity.
 */
static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
{
	struct sched_group *sg = sd->groups;

	WARN_ON(!sg);

	do {
		int cpu, max_cpu = -1;

		sg->group_weight = cpumask_weight(sched_group_span(sg));

		if (!(sd->flags & SD_ASYM_PACKING))
			goto next;

		for_each_cpu(cpu, sched_group_span(sg)) {
			if (max_cpu < 0)
				max_cpu = cpu;
			else if (sched_asym_prefer(cpu, max_cpu))
				max_cpu = cpu;
		}
		sg->asym_prefer_cpu = max_cpu;

next:
		sg = sg->next;
	} while (sg != sd->groups);

	if (cpu != group_balance_cpu(sg))
		return;

	update_group_capacity(sd, cpu);
}

/*
 * Initializers for schedule domains
 * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
 */

static int default_relax_domain_level = -1;
int sched_domain_level_max;

static int __init setup_relax_domain_level(char *str)
{
	if (kstrtoint(str, 0, &default_relax_domain_level))
		pr_warn("Unable to set relax_domain_level\n");

	return 1;
}
__setup("relax_domain_level=", setup_relax_domain_level);

static void set_domain_attribute(struct sched_domain *sd,
				 struct sched_domain_attr *attr)
{
	int request;

	if (!attr || attr->relax_domain_level < 0) {
		if (default_relax_domain_level < 0)
			return;
		else
			request = default_relax_domain_level;
	} else
		request = attr->relax_domain_level;
	if (request < sd->level) {
		/* Turn off idle balance on this domain: */
		sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
	} else {
		/* Turn on idle balance on this domain: */
		sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
	}
}

static void __sdt_free(const struct cpumask *cpu_map);
static int __sdt_alloc(const struct cpumask *cpu_map);

static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
				 const struct cpumask *cpu_map)
{
	switch (what) {
	case sa_rootdomain:
		if (!atomic_read(&d->rd->refcount))
			free_rootdomain(&d->rd->rcu);
		/* Fall through */
	case sa_sd:
		free_percpu(d->sd);
		/* Fall through */
	case sa_sd_storage:
		__sdt_free(cpu_map);
		/* Fall through */
	case sa_none:
		break;
	}
}

static enum s_alloc
__visit_domain_allocation_hell(struct s_data *d, const struct cpumask *cpu_map)
{
	memset(d, 0, sizeof(*d));

	if (__sdt_alloc(cpu_map))
		return sa_sd_storage;
	d->sd = alloc_percpu(struct sched_domain *);
	if (!d->sd)
		return sa_sd_storage;
	d->rd = alloc_rootdomain();
	if (!d->rd)
		return sa_sd;

	return sa_rootdomain;
}

/*
 * NULL the sd_data elements we've used to build the sched_domain and
 * sched_group structure so that the subsequent __free_domain_allocs()
 * will not free the data we're using.
 */
static void claim_allocations(int cpu, struct sched_domain *sd)
{
	struct sd_data *sdd = sd->private;

	WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd);
	*per_cpu_ptr(sdd->sd, cpu) = NULL;

	if (atomic_read(&(*per_cpu_ptr(sdd->sds, cpu))->ref))
		*per_cpu_ptr(sdd->sds, cpu) = NULL;

	if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref))
		*per_cpu_ptr(sdd->sg, cpu) = NULL;

	if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref))
		*per_cpu_ptr(sdd->sgc, cpu) = NULL;
}

#ifdef CONFIG_NUMA
enum numa_topology_type sched_numa_topology_type;

static int			sched_domains_numa_levels;
static int			sched_domains_curr_level;

int				sched_max_numa_distance;
static int			*sched_domains_numa_distance;
static struct cpumask		***sched_domains_numa_masks;
#endif

/*
 * SD_flags allowed in topology descriptions.
 *
 * These flags are purely descriptive of the topology and do not prescribe
 * behaviour. Behaviour is artificial and mapped in the below sd_init()
 * function:
 *
 *   SD_SHARE_CPUCAPACITY   - describes SMT topologies
 *   SD_SHARE_PKG_RESOURCES - describes shared caches
 *   SD_NUMA                - describes NUMA topologies
 *   SD_SHARE_POWERDOMAIN   - describes shared power domain
 *   SD_ASYM_CPUCAPACITY    - describes mixed capacity topologies
 *
 * Odd one out, which beside describing the topology has a quirk also
 * prescribes the desired behaviour that goes along with it:
 *
 *   SD_ASYM_PACKING        - describes SMT quirks
 */
#define TOPOLOGY_SD_FLAGS		\
	(SD_SHARE_CPUCAPACITY	|	\
	 SD_SHARE_PKG_RESOURCES |	\
	 SD_NUMA		|	\
	 SD_ASYM_PACKING	|	\
	 SD_ASYM_CPUCAPACITY	|	\
	 SD_SHARE_POWERDOMAIN)

static struct sched_domain *
sd_init(struct sched_domain_topology_level *tl,
	const struct cpumask *cpu_map,
	struct sched_domain *child, int cpu)
{
	struct sd_data *sdd = &tl->data;
	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
	int sd_id, sd_weight, sd_flags = 0;

#ifdef CONFIG_NUMA
	/*
	 * Ugly hack to pass state to sd_numa_mask()...
	 */
	sched_domains_curr_level = tl->numa_level;
#endif

	sd_weight = cpumask_weight(tl->mask(cpu));

	if (tl->sd_flags)
		sd_flags = (*tl->sd_flags)();
	if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
			"wrong sd_flags in topology description\n"))
		sd_flags &= ~TOPOLOGY_SD_FLAGS;

	*sd = (struct sched_domain){
		.min_interval		= sd_weight,
		.max_interval		= 2*sd_weight,
		.busy_factor		= 32,
		.imbalance_pct		= 125,

		.cache_nice_tries	= 0,
		.busy_idx		= 0,
		.idle_idx		= 0,
		.newidle_idx		= 0,
		.wake_idx		= 0,
		.forkexec_idx		= 0,

		.flags			= 1*SD_LOAD_BALANCE
					| 1*SD_BALANCE_NEWIDLE
					| 1*SD_BALANCE_EXEC
					| 1*SD_BALANCE_FORK
					| 0*SD_BALANCE_WAKE
					| 1*SD_WAKE_AFFINE
					| 0*SD_SHARE_CPUCAPACITY
					| 0*SD_SHARE_PKG_RESOURCES
					| 0*SD_SERIALIZE
					| 0*SD_PREFER_SIBLING
					| 0*SD_NUMA
					| sd_flags
					,

		.last_balance		= jiffies,
		.balance_interval	= sd_weight,
		.smt_gain		= 0,
		.max_newidle_lb_cost	= 0,
		.next_decay_max_lb_cost	= jiffies,
		.child			= child,
#ifdef CONFIG_SCHED_DEBUG
		.name			= tl->name,
#endif
	};

	cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
	sd_id = cpumask_first(sched_domain_span(sd));

	/*
	 * Convert topological properties into behaviour.
	 */

	if (sd->flags & SD_ASYM_CPUCAPACITY) {
		struct sched_domain *t = sd;

		for_each_lower_domain(t)
			t->flags |= SD_BALANCE_WAKE;
	}

	if (sd->flags & SD_SHARE_CPUCAPACITY) {
		sd->flags |= SD_PREFER_SIBLING;
		sd->imbalance_pct = 110;
		sd->smt_gain = 1178; /* ~15% */

	} else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
		sd->flags |= SD_PREFER_SIBLING;
		sd->imbalance_pct = 117;
		sd->cache_nice_tries = 1;
		sd->busy_idx = 2;

#ifdef CONFIG_NUMA
	} else if (sd->flags & SD_NUMA) {
		sd->cache_nice_tries = 2;
		sd->busy_idx = 3;
		sd->idle_idx = 2;

		sd->flags |= SD_SERIALIZE;
		if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
			sd->flags &= ~(SD_BALANCE_EXEC |
				       SD_BALANCE_FORK |
				       SD_WAKE_AFFINE);
		}

#endif
	} else {
		sd->flags |= SD_PREFER_SIBLING;
		sd->cache_nice_tries = 1;
		sd->busy_idx = 2;
		sd->idle_idx = 1;
	}

	/*
	 * For all levels sharing cache; connect a sched_domain_shared
	 * instance.
	 */
	if (sd->flags & SD_SHARE_PKG_RESOURCES) {
		sd->shared = *per_cpu_ptr(sdd->sds, sd_id);
		atomic_inc(&sd->shared->ref);
		atomic_set(&sd->shared->nr_busy_cpus, sd_weight);
	}

	sd->private = sdd;

	return sd;
}

/*
 * Topology list, bottom-up.
 */
static struct sched_domain_topology_level default_topology[] = {
#ifdef CONFIG_SCHED_SMT
	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
#endif
#ifdef CONFIG_SCHED_MC
	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
#endif
	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
	{ NULL, },
};

static struct sched_domain_topology_level *sched_domain_topology =
	default_topology;

#define for_each_sd_topology(tl)			\
	for (tl = sched_domain_topology; tl->mask; tl++)

void set_sched_topology(struct sched_domain_topology_level *tl)
{
	if (WARN_ON_ONCE(sched_smp_initialized))
		return;

	sched_domain_topology = tl;
}

#ifdef CONFIG_NUMA

static const struct cpumask *sd_numa_mask(int cpu)
{
	return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
}

static void sched_numa_warn(const char *str)
{
	static int done = false;
	int i,j;

	if (done)
		return;

	done = true;

	printk(KERN_WARNING "ERROR: %s\n\n", str);

	for (i = 0; i < nr_node_ids; i++) {
		printk(KERN_WARNING "  ");
		for (j = 0; j < nr_node_ids; j++)
			printk(KERN_CONT "%02d ", node_distance(i,j));
		printk(KERN_CONT "\n");
	}
	printk(KERN_WARNING "\n");
}

bool find_numa_distance(int distance)
{
	int i;

	if (distance == node_distance(0, 0))
		return true;

	for (i = 0; i < sched_domains_numa_levels; i++) {
		if (sched_domains_numa_distance[i] == distance)
			return true;
	}

	return false;
}

/*
 * A system can have three types of NUMA topology:
 * NUMA_DIRECT: all nodes are directly connected, or not a NUMA system
 * NUMA_GLUELESS_MESH: some nodes reachable through intermediary nodes
 * NUMA_BACKPLANE: nodes can reach other nodes through a backplane
 *
 * The difference between a glueless mesh topology and a backplane
 * topology lies in whether communication between not directly
 * connected nodes goes through intermediary nodes (where programs
 * could run), or through backplane controllers. This affects
 * placement of programs.
 *
 * The type of topology can be discerned with the following tests:
 * - If the maximum distance between any nodes is 1 hop, the system
 *   is directly connected.
 * - If for two nodes A and B, located N > 1 hops away from each other,
 *   there is an intermediary node C, which is < N hops away from both
 *   nodes A and B, the system is a glueless mesh.
 */
static void init_numa_topology_type(void)
{
	int a, b, c, n;

	n = sched_max_numa_distance;

	if (sched_domains_numa_levels <= 1) {
		sched_numa_topology_type = NUMA_DIRECT;
		return;
	}

	for_each_online_node(a) {
		for_each_online_node(b) {
			/* Find two nodes furthest removed from each other. */
			if (node_distance(a, b) < n)
				continue;

			/* Is there an intermediary node between a and b? */
			for_each_online_node(c) {
				if (node_distance(a, c) < n &&
				    node_distance(b, c) < n) {
					sched_numa_topology_type =
							NUMA_GLUELESS_MESH;
					return;
				}
			}

			sched_numa_topology_type = NUMA_BACKPLANE;
			return;
		}
	}
}

void sched_init_numa(void)
{
	int next_distance, curr_distance = node_distance(0, 0);
	struct sched_domain_topology_level *tl;
	int level = 0;
	int i, j, k;

	sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
	if (!sched_domains_numa_distance)
		return;

	/* Includes NUMA identity node at level 0. */
	sched_domains_numa_distance[level++] = curr_distance;
	sched_domains_numa_levels = level;

	/*
	 * O(nr_nodes^2) deduplicating selection sort -- in order to find the
	 * unique distances in the node_distance() table.
	 *
	 * Assumes node_distance(0,j) includes all distances in
	 * node_distance(i,j) in order to avoid cubic time.
	 */
	next_distance = curr_distance;
	for (i = 0; i < nr_node_ids; i++) {
		for (j = 0; j < nr_node_ids; j++) {
			for (k = 0; k < nr_node_ids; k++) {
				int distance = node_distance(i, k);

				if (distance > curr_distance &&
				    (distance < next_distance ||
				     next_distance == curr_distance))
					next_distance = distance;

				/*
				 * While not a strong assumption it would be nice to know
				 * about cases where if node A is connected to B, B is not
				 * equally connected to A.
				 */
				if (sched_debug() && node_distance(k, i) != distance)
					sched_numa_warn("Node-distance not symmetric");

				if (sched_debug() && i && !find_numa_distance(distance))
					sched_numa_warn("Node-0 not representative");
			}
			if (next_distance != curr_distance) {
				sched_domains_numa_distance[level++] = next_distance;
				sched_domains_numa_levels = level;
				curr_distance = next_distance;
			} else break;
		}

		/*
		 * In case of sched_debug() we verify the above assumption.
		 */
		if (!sched_debug())
			break;
	}

	if (!level)
		return;

	/*
	 * 'level' contains the number of unique distances
	 *
	 * The sched_domains_numa_distance[] array includes the actual distance
	 * numbers.
	 */

	/*
	 * Here, we should temporarily reset sched_domains_numa_levels to 0.
	 * If it fails to allocate memory for array sched_domains_numa_masks[][],
	 * the array will contain less then 'level' members. This could be
	 * dangerous when we use it to iterate array sched_domains_numa_masks[][]
	 * in other functions.
	 *
	 * We reset it to 'level' at the end of this function.
	 */
	sched_domains_numa_levels = 0;

	sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL);
	if (!sched_domains_numa_masks)
		return;

	/*
	 * Now for each level, construct a mask per node which contains all
	 * CPUs of nodes that are that many hops away from us.
	 */
	for (i = 0; i < level; i++) {
		sched_domains_numa_masks[i] =
			kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL);
		if (!sched_domains_numa_masks[i])
			return;

		for (j = 0; j < nr_node_ids; j++) {
			struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
			if (!mask)
				return;

			sched_domains_numa_masks[i][j] = mask;

			for_each_node(k) {
				if (node_distance(j, k) > sched_domains_numa_distance[i])
					continue;

				cpumask_or(mask, mask, cpumask_of_node(k));
			}
		}
	}

	/* Compute default topology size */
	for (i = 0; sched_domain_topology[i].mask; i++);

	tl = kzalloc((i + level + 1) *
			sizeof(struct sched_domain_topology_level), GFP_KERNEL);
	if (!tl)
		return;

	/*
	 * Copy the default topology bits..
	 */
	for (i = 0; sched_domain_topology[i].mask; i++)
		tl[i] = sched_domain_topology[i];

	/*
	 * Add the NUMA identity distance, aka single NODE.
	 */
	tl[i++] = (struct sched_domain_topology_level){
		.mask = sd_numa_mask,
		.numa_level = 0,
		SD_INIT_NAME(NODE)
	};

	/*
	 * .. and append 'j' levels of NUMA goodness.
	 */
	for (j = 1; j < level; i++, j++) {
		tl[i] = (struct sched_domain_topology_level){
			.mask = sd_numa_mask,
			.sd_flags = cpu_numa_flags,
			.flags = SDTL_OVERLAP,
			.numa_level = j,
			SD_INIT_NAME(NUMA)
		};
	}

	sched_domain_topology = tl;

	sched_domains_numa_levels = level;
	sched_max_numa_distance = sched_domains_numa_distance[level - 1];

	init_numa_topology_type();
}

void sched_domains_numa_masks_set(unsigned int cpu)
{
	int node = cpu_to_node(cpu);
	int i, j;

	for (i = 0; i < sched_domains_numa_levels; i++) {
		for (j = 0; j < nr_node_ids; j++) {
			if (node_distance(j, node) <= sched_domains_numa_distance[i])
				cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]);
		}
	}
}

void sched_domains_numa_masks_clear(unsigned int cpu)
{
	int i, j;

	for (i = 0; i < sched_domains_numa_levels; i++) {
		for (j = 0; j < nr_node_ids; j++)
			cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]);
	}
}

#endif /* CONFIG_NUMA */

static int __sdt_alloc(const struct cpumask *cpu_map)
{
	struct sched_domain_topology_level *tl;
	int j;

	for_each_sd_topology(tl) {
		struct sd_data *sdd = &tl->data;

		sdd->sd = alloc_percpu(struct sched_domain *);
		if (!sdd->sd)
			return -ENOMEM;

		sdd->sds = alloc_percpu(struct sched_domain_shared *);
		if (!sdd->sds)
			return -ENOMEM;

		sdd->sg = alloc_percpu(struct sched_group *);
		if (!sdd->sg)
			return -ENOMEM;

		sdd->sgc = alloc_percpu(struct sched_group_capacity *);
		if (!sdd->sgc)
			return -ENOMEM;

		for_each_cpu(j, cpu_map) {
			struct sched_domain *sd;
			struct sched_domain_shared *sds;
			struct sched_group *sg;
			struct sched_group_capacity *sgc;

			sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(),
					GFP_KERNEL, cpu_to_node(j));
			if (!sd)
				return -ENOMEM;

			*per_cpu_ptr(sdd->sd, j) = sd;

			sds = kzalloc_node(sizeof(struct sched_domain_shared),
					GFP_KERNEL, cpu_to_node(j));
			if (!sds)
				return -ENOMEM;

			*per_cpu_ptr(sdd->sds, j) = sds;

			sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
					GFP_KERNEL, cpu_to_node(j));
			if (!sg)
				return -ENOMEM;

			sg->next = sg;

			*per_cpu_ptr(sdd->sg, j) = sg;

			sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(),
					GFP_KERNEL, cpu_to_node(j));
			if (!sgc)
				return -ENOMEM;

#ifdef CONFIG_SCHED_DEBUG
			sgc->id = j;
#endif

			*per_cpu_ptr(sdd->sgc, j) = sgc;
		}
	}

	return 0;
}

static void __sdt_free(const struct cpumask *cpu_map)
{
	struct sched_domain_topology_level *tl;
	int j;

	for_each_sd_topology(tl) {
		struct sd_data *sdd = &tl->data;

		for_each_cpu(j, cpu_map) {
			struct sched_domain *sd;

			if (sdd->sd) {
				sd = *per_cpu_ptr(sdd->sd, j);
				if (sd && (sd->flags & SD_OVERLAP))
					free_sched_groups(sd->groups, 0);
				kfree(*per_cpu_ptr(sdd->sd, j));
			}

			if (sdd->sds)
				kfree(*per_cpu_ptr(sdd->sds, j));
			if (sdd->sg)
				kfree(*per_cpu_ptr(sdd->sg, j));
			if (sdd->sgc)
				kfree(*per_cpu_ptr(sdd->sgc, j));
		}
		free_percpu(sdd->sd);
		sdd->sd = NULL;
		free_percpu(sdd->sds);
		sdd->sds = NULL;
		free_percpu(sdd->sg);
		sdd->sg = NULL;
		free_percpu(sdd->sgc);
		sdd->sgc = NULL;
	}
}

static struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
		const struct cpumask *cpu_map, struct sched_domain_attr *attr,
		struct sched_domain *child, int cpu)
{
	struct sched_domain *sd = sd_init(tl, cpu_map, child, cpu);

	if (child) {
		sd->level = child->level + 1;
		sched_domain_level_max = max(sched_domain_level_max, sd->level);
		child->parent = sd;

		if (!cpumask_subset(sched_domain_span(child),
				    sched_domain_span(sd))) {
			pr_err("BUG: arch topology borken\n");
#ifdef CONFIG_SCHED_DEBUG
			pr_err("     the %s domain not a subset of the %s domain\n",
					child->name, sd->name);
#endif
			/* Fixup, ensure @sd has at least @child CPUs. */
			cpumask_or(sched_domain_span(sd),
				   sched_domain_span(sd),
				   sched_domain_span(child));
		}

	}
	set_domain_attribute(sd, attr);

	return sd;
}

/*
 * Build sched domains for a given set of CPUs and attach the sched domains
 * to the individual CPUs
 */
static int
build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr)
{
	enum s_alloc alloc_state;
	struct sched_domain *sd;
	struct s_data d;
	struct rq *rq = NULL;
	int i, ret = -ENOMEM;

	alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
	if (alloc_state != sa_rootdomain)
		goto error;

	/* Set up domains for CPUs specified by the cpu_map: */
	for_each_cpu(i, cpu_map) {
		struct sched_domain_topology_level *tl;

		sd = NULL;
		for_each_sd_topology(tl) {
			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
			if (tl == sched_domain_topology)
				*per_cpu_ptr(d.sd, i) = sd;
			if (tl->flags & SDTL_OVERLAP)
				sd->flags |= SD_OVERLAP;
			if (cpumask_equal(cpu_map, sched_domain_span(sd)))
				break;
		}
	}

	/* Build the groups for the domains */
	for_each_cpu(i, cpu_map) {
		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
			sd->span_weight = cpumask_weight(sched_domain_span(sd));
			if (sd->flags & SD_OVERLAP) {
				if (build_overlap_sched_groups(sd, i))
					goto error;
			} else {
				if (build_sched_groups(sd, i))
					goto error;
			}
		}
	}

	/* Calculate CPU capacity for physical packages and nodes */
	for (i = nr_cpumask_bits-1; i >= 0; i--) {
		if (!cpumask_test_cpu(i, cpu_map))
			continue;

		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
			claim_allocations(i, sd);
			init_sched_groups_capacity(i, sd);
		}
	}

	/* Attach the domains */
	rcu_read_lock();
	for_each_cpu(i, cpu_map) {
		rq = cpu_rq(i);
		sd = *per_cpu_ptr(d.sd, i);

		/* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */
		if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity))
			WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig);

		cpu_attach_domain(sd, d.rd, i);
	}
	rcu_read_unlock();

	if (rq && sched_debug_enabled) {
		pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
			cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
	}

	ret = 0;
error:
	__free_domain_allocs(&d, alloc_state, cpu_map);

	return ret;
}

/* Current sched domains: */
static cpumask_var_t			*doms_cur;

/* Number of sched domains in 'doms_cur': */
static int				ndoms_cur;

/* Attribues of custom domains in 'doms_cur' */
static struct sched_domain_attr		*dattr_cur;

/*
 * Special case: If a kmalloc() of a doms_cur partition (array of
 * cpumask) fails, then fallback to a single sched domain,
 * as determined by the single cpumask fallback_doms.
 */
static cpumask_var_t			fallback_doms;

/*
 * arch_update_cpu_topology lets virtualized architectures update the
 * CPU core maps. It is supposed to return 1 if the topology changed
 * or 0 if it stayed the same.
 */
int __weak arch_update_cpu_topology(void)
{
	return 0;
}

cpumask_var_t *alloc_sched_domains(unsigned int ndoms)
{
	int i;
	cpumask_var_t *doms;

	doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL);
	if (!doms)
		return NULL;
	for (i = 0; i < ndoms; i++) {
		if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) {
			free_sched_domains(doms, i);
			return NULL;
		}
	}
	return doms;
}

void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
{
	unsigned int i;
	for (i = 0; i < ndoms; i++)
		free_cpumask_var(doms[i]);
	kfree(doms);
}

/*
 * Set up scheduler domains and groups. Callers must hold the hotplug lock.
 * For now this just excludes isolated CPUs, but could be used to
 * exclude other special cases in the future.
 */
int sched_init_domains(const struct cpumask *cpu_map)
{
	int err;

	zalloc_cpumask_var(&sched_domains_tmpmask, GFP_KERNEL);
	zalloc_cpumask_var(&sched_domains_tmpmask2, GFP_KERNEL);
	zalloc_cpumask_var(&fallback_doms, GFP_KERNEL);

	arch_update_cpu_topology();
	ndoms_cur = 1;
	doms_cur = alloc_sched_domains(ndoms_cur);
	if (!doms_cur)
		doms_cur = &fallback_doms;
	cpumask_and(doms_cur[0], cpu_map, housekeeping_cpumask(HK_FLAG_DOMAIN));
	err = build_sched_domains(doms_cur[0], NULL);
	register_sched_domain_sysctl();

	return err;
}

/*
 * Detach sched domains from a group of CPUs specified in cpu_map
 * These CPUs will now be attached to the NULL domain
 */
static void detach_destroy_domains(const struct cpumask *cpu_map)
{
	int i;

	rcu_read_lock();
	for_each_cpu(i, cpu_map)
		cpu_attach_domain(NULL, &def_root_domain, i);
	rcu_read_unlock();
}

/* handle null as "default" */
static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
			struct sched_domain_attr *new, int idx_new)
{
	struct sched_domain_attr tmp;

	/* Fast path: */
	if (!new && !cur)
		return 1;

	tmp = SD_ATTR_INIT;

	return !memcmp(cur ? (cur + idx_cur) : &tmp,
			new ? (new + idx_new) : &tmp,
			sizeof(struct sched_domain_attr));
}

/*
 * Partition sched domains as specified by the 'ndoms_new'
 * cpumasks in the array doms_new[] of cpumasks. This compares
 * doms_new[] to the current sched domain partitioning, doms_cur[].
 * It destroys each deleted domain and builds each new domain.
 *
 * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'.
 * The masks don't intersect (don't overlap.) We should setup one
 * sched domain for each mask. CPUs not in any of the cpumasks will
 * not be load balanced. If the same cpumask appears both in the
 * current 'doms_cur' domains and in the new 'doms_new', we can leave
 * it as it is.
 *
 * The passed in 'doms_new' should be allocated using
 * alloc_sched_domains.  This routine takes ownership of it and will
 * free_sched_domains it when done with it. If the caller failed the
 * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1,
 * and partition_sched_domains() will fallback to the single partition
 * 'fallback_doms', it also forces the domains to be rebuilt.
 *
 * If doms_new == NULL it will be replaced with cpu_online_mask.
 * ndoms_new == 0 is a special case for destroying existing domains,
 * and it will not create the default domain.
 *
 * Call with hotplug lock held
 */
void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
			     struct sched_domain_attr *dattr_new)
{
	int i, j, n;
	int new_topology;

	mutex_lock(&sched_domains_mutex);

	/* Always unregister in case we don't destroy any domains: */
	unregister_sched_domain_sysctl();

	/* Let the architecture update CPU core mappings: */
	new_topology = arch_update_cpu_topology();

	if (!doms_new) {
		WARN_ON_ONCE(dattr_new);
		n = 0;
		doms_new = alloc_sched_domains(1);
		if (doms_new) {
			n = 1;
			cpumask_and(doms_new[0], cpu_active_mask,
				    housekeeping_cpumask(HK_FLAG_DOMAIN));
		}
	} else {
		n = ndoms_new;
	}

	/* Destroy deleted domains: */
	for (i = 0; i < ndoms_cur; i++) {
		for (j = 0; j < n && !new_topology; j++) {
			if (cpumask_equal(doms_cur[i], doms_new[j])
			    && dattrs_equal(dattr_cur, i, dattr_new, j))
				goto match1;
		}
		/* No match - a current sched domain not in new doms_new[] */
		detach_destroy_domains(doms_cur[i]);
match1:
		;
	}

	n = ndoms_cur;
	if (!doms_new) {
		n = 0;
		doms_new = &fallback_doms;
		cpumask_and(doms_new[0], cpu_active_mask,
			    housekeeping_cpumask(HK_FLAG_DOMAIN));
	}

	/* Build new domains: */
	for (i = 0; i < ndoms_new; i++) {
		for (j = 0; j < n && !new_topology; j++) {
			if (cpumask_equal(doms_new[i], doms_cur[j])
			    && dattrs_equal(dattr_new, i, dattr_cur, j))
				goto match2;
		}
		/* No match - add a new doms_new */
		build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL);
match2:
		;
	}

	/* Remember the new sched domains: */
	if (doms_cur != &fallback_doms)
		free_sched_domains(doms_cur, ndoms_cur);

	kfree(dattr_cur);
	doms_cur = doms_new;
	dattr_cur = dattr_new;
	ndoms_cur = ndoms_new;

	register_sched_domain_sysctl();

	mutex_unlock(&sched_domains_mutex);
}