summaryrefslogtreecommitdiff
path: root/block/blk-cgroup.c
blob: 1f7127b03490db873a6a631a9ca17d349995ac81 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Common Block IO controller cgroup interface
 *
 * Based on ideas and code from CFQ, CFS and BFQ:
 * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
 *
 * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
 *		      Paolo Valente <paolo.valente@unimore.it>
 *
 * Copyright (C) 2009 Vivek Goyal <vgoyal@redhat.com>
 * 	              Nauman Rafique <nauman@google.com>
 *
 * For policy-specific per-blkcg data:
 * Copyright (C) 2015 Paolo Valente <paolo.valente@unimore.it>
 *                    Arianna Avanzini <avanzini.arianna@gmail.com>
 */
#include <linux/ioprio.h>
#include <linux/kdev_t.h>
#include <linux/module.h>
#include <linux/sched/signal.h>
#include <linux/err.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/slab.h>
#include <linux/genhd.h>
#include <linux/delay.h>
#include <linux/atomic.h>
#include <linux/ctype.h>
#include <linux/blk-cgroup.h>
#include <linux/tracehook.h>
#include "blk.h"

#define MAX_KEY_LEN 100

/*
 * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation.
 * blkcg_pol_register_mutex nests outside of it and synchronizes entire
 * policy [un]register operations including cgroup file additions /
 * removals.  Putting cgroup file registration outside blkcg_pol_mutex
 * allows grabbing it from cgroup callbacks.
 */
static DEFINE_MUTEX(blkcg_pol_register_mutex);
static DEFINE_MUTEX(blkcg_pol_mutex);

struct blkcg blkcg_root;
EXPORT_SYMBOL_GPL(blkcg_root);

struct cgroup_subsys_state * const blkcg_root_css = &blkcg_root.css;

static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];

static LIST_HEAD(all_blkcgs);		/* protected by blkcg_pol_mutex */

static bool blkcg_debug_stats = false;

static bool blkcg_policy_enabled(struct request_queue *q,
				 const struct blkcg_policy *pol)
{
	return pol && test_bit(pol->plid, q->blkcg_pols);
}

/**
 * blkg_free - free a blkg
 * @blkg: blkg to free
 *
 * Free @blkg which may be partially allocated.
 */
static void blkg_free(struct blkcg_gq *blkg)
{
	int i;

	if (!blkg)
		return;

	for (i = 0; i < BLKCG_MAX_POLS; i++)
		if (blkg->pd[i])
			blkcg_policy[i]->pd_free_fn(blkg->pd[i]);

	blkg_rwstat_exit(&blkg->stat_ios);
	blkg_rwstat_exit(&blkg->stat_bytes);
	kfree(blkg);
}

static void __blkg_release(struct rcu_head *rcu)
{
	struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head);

	percpu_ref_exit(&blkg->refcnt);

	/* release the blkcg and parent blkg refs this blkg has been holding */
	css_put(&blkg->blkcg->css);
	if (blkg->parent)
		blkg_put(blkg->parent);

	wb_congested_put(blkg->wb_congested);

	blkg_free(blkg);
}

/*
 * A group is RCU protected, but having an rcu lock does not mean that one
 * can access all the fields of blkg and assume these are valid.  For
 * example, don't try to follow throtl_data and request queue links.
 *
 * Having a reference to blkg under an rcu allows accesses to only values
 * local to groups like group stats and group rate limits.
 */
static void blkg_release(struct percpu_ref *ref)
{
	struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt);

	call_rcu(&blkg->rcu_head, __blkg_release);
}

/**
 * blkg_alloc - allocate a blkg
 * @blkcg: block cgroup the new blkg is associated with
 * @q: request_queue the new blkg is associated with
 * @gfp_mask: allocation mask to use
 *
 * Allocate a new blkg assocating @blkcg and @q.
 */
static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
				   gfp_t gfp_mask)
{
	struct blkcg_gq *blkg;
	int i;

	/* alloc and init base part */
	blkg = kzalloc_node(sizeof(*blkg), gfp_mask, q->node);
	if (!blkg)
		return NULL;

	if (blkg_rwstat_init(&blkg->stat_bytes, gfp_mask) ||
	    blkg_rwstat_init(&blkg->stat_ios, gfp_mask))
		goto err_free;

	blkg->q = q;
	INIT_LIST_HEAD(&blkg->q_node);
	blkg->blkcg = blkcg;

	for (i = 0; i < BLKCG_MAX_POLS; i++) {
		struct blkcg_policy *pol = blkcg_policy[i];
		struct blkg_policy_data *pd;

		if (!blkcg_policy_enabled(q, pol))
			continue;

		/* alloc per-policy data and attach it to blkg */
		pd = pol->pd_alloc_fn(gfp_mask, q->node);
		if (!pd)
			goto err_free;

		blkg->pd[i] = pd;
		pd->blkg = blkg;
		pd->plid = i;
	}

	return blkg;

err_free:
	blkg_free(blkg);
	return NULL;
}

struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg,
				      struct request_queue *q, bool update_hint)
{
	struct blkcg_gq *blkg;

	/*
	 * Hint didn't match.  Look up from the radix tree.  Note that the
	 * hint can only be updated under queue_lock as otherwise @blkg
	 * could have already been removed from blkg_tree.  The caller is
	 * responsible for grabbing queue_lock if @update_hint.
	 */
	blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id);
	if (blkg && blkg->q == q) {
		if (update_hint) {
			lockdep_assert_held(&q->queue_lock);
			rcu_assign_pointer(blkcg->blkg_hint, blkg);
		}
		return blkg;
	}

	return NULL;
}
EXPORT_SYMBOL_GPL(blkg_lookup_slowpath);

/*
 * If @new_blkg is %NULL, this function tries to allocate a new one as
 * necessary using %GFP_NOWAIT.  @new_blkg is always consumed on return.
 */
static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
				    struct request_queue *q,
				    struct blkcg_gq *new_blkg)
{
	struct blkcg_gq *blkg;
	struct bdi_writeback_congested *wb_congested;
	int i, ret;

	WARN_ON_ONCE(!rcu_read_lock_held());
	lockdep_assert_held(&q->queue_lock);

	/* request_queue is dying, do not create/recreate a blkg */
	if (blk_queue_dying(q)) {
		ret = -ENODEV;
		goto err_free_blkg;
	}

	/* blkg holds a reference to blkcg */
	if (!css_tryget_online(&blkcg->css)) {
		ret = -ENODEV;
		goto err_free_blkg;
	}

	wb_congested = wb_congested_get_create(q->backing_dev_info,
					       blkcg->css.id,
					       GFP_NOWAIT | __GFP_NOWARN);
	if (!wb_congested) {
		ret = -ENOMEM;
		goto err_put_css;
	}

	/* allocate */
	if (!new_blkg) {
		new_blkg = blkg_alloc(blkcg, q, GFP_NOWAIT | __GFP_NOWARN);
		if (unlikely(!new_blkg)) {
			ret = -ENOMEM;
			goto err_put_congested;
		}
	}
	blkg = new_blkg;
	blkg->wb_congested = wb_congested;

	/* link parent */
	if (blkcg_parent(blkcg)) {
		blkg->parent = __blkg_lookup(blkcg_parent(blkcg), q, false);
		if (WARN_ON_ONCE(!blkg->parent)) {
			ret = -ENODEV;
			goto err_put_congested;
		}
		blkg_get(blkg->parent);
	}

	ret = percpu_ref_init(&blkg->refcnt, blkg_release, 0,
			      GFP_NOWAIT | __GFP_NOWARN);
	if (ret)
		goto err_cancel_ref;

	/* invoke per-policy init */
	for (i = 0; i < BLKCG_MAX_POLS; i++) {
		struct blkcg_policy *pol = blkcg_policy[i];

		if (blkg->pd[i] && pol->pd_init_fn)
			pol->pd_init_fn(blkg->pd[i]);
	}

	/* insert */
	spin_lock(&blkcg->lock);
	ret = radix_tree_insert(&blkcg->blkg_tree, q->id, blkg);
	if (likely(!ret)) {
		hlist_add_head_rcu(&blkg->blkcg_node, &blkcg->blkg_list);
		list_add(&blkg->q_node, &q->blkg_list);

		for (i = 0; i < BLKCG_MAX_POLS; i++) {
			struct blkcg_policy *pol = blkcg_policy[i];

			if (blkg->pd[i] && pol->pd_online_fn)
				pol->pd_online_fn(blkg->pd[i]);
		}
	}
	blkg->online = true;
	spin_unlock(&blkcg->lock);

	if (!ret)
		return blkg;

	/* @blkg failed fully initialized, use the usual release path */
	blkg_put(blkg);
	return ERR_PTR(ret);

err_cancel_ref:
	percpu_ref_exit(&blkg->refcnt);
err_put_congested:
	wb_congested_put(wb_congested);
err_put_css:
	css_put(&blkcg->css);
err_free_blkg:
	blkg_free(new_blkg);
	return ERR_PTR(ret);
}

/**
 * __blkg_lookup_create - lookup blkg, try to create one if not there
 * @blkcg: blkcg of interest
 * @q: request_queue of interest
 *
 * Lookup blkg for the @blkcg - @q pair.  If it doesn't exist, try to
 * create one.  blkg creation is performed recursively from blkcg_root such
 * that all non-root blkg's have access to the parent blkg.  This function
 * should be called under RCU read lock and @q->queue_lock.
 *
 * Returns the blkg or the closest blkg if blkg_create() fails as it walks
 * down from root.
 */
struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg,
				      struct request_queue *q)
{
	struct blkcg_gq *blkg;

	WARN_ON_ONCE(!rcu_read_lock_held());
	lockdep_assert_held(&q->queue_lock);

	blkg = __blkg_lookup(blkcg, q, true);
	if (blkg)
		return blkg;

	/*
	 * Create blkgs walking down from blkcg_root to @blkcg, so that all
	 * non-root blkgs have access to their parents.  Returns the closest
	 * blkg to the intended blkg should blkg_create() fail.
	 */
	while (true) {
		struct blkcg *pos = blkcg;
		struct blkcg *parent = blkcg_parent(blkcg);
		struct blkcg_gq *ret_blkg = q->root_blkg;

		while (parent) {
			blkg = __blkg_lookup(parent, q, false);
			if (blkg) {
				/* remember closest blkg */
				ret_blkg = blkg;
				break;
			}
			pos = parent;
			parent = blkcg_parent(parent);
		}

		blkg = blkg_create(pos, q, NULL);
		if (IS_ERR(blkg))
			return ret_blkg;
		if (pos == blkcg)
			return blkg;
	}
}

/**
 * blkg_lookup_create - find or create a blkg
 * @blkcg: target block cgroup
 * @q: target request_queue
 *
 * This looks up or creates the blkg representing the unique pair
 * of the blkcg and the request_queue.
 */
struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
				    struct request_queue *q)
{
	struct blkcg_gq *blkg = blkg_lookup(blkcg, q);

	if (unlikely(!blkg)) {
		unsigned long flags;

		spin_lock_irqsave(&q->queue_lock, flags);
		blkg = __blkg_lookup_create(blkcg, q);
		spin_unlock_irqrestore(&q->queue_lock, flags);
	}

	return blkg;
}

static void blkg_destroy(struct blkcg_gq *blkg)
{
	struct blkcg *blkcg = blkg->blkcg;
	struct blkcg_gq *parent = blkg->parent;
	int i;

	lockdep_assert_held(&blkg->q->queue_lock);
	lockdep_assert_held(&blkcg->lock);

	/* Something wrong if we are trying to remove same group twice */
	WARN_ON_ONCE(list_empty(&blkg->q_node));
	WARN_ON_ONCE(hlist_unhashed(&blkg->blkcg_node));

	for (i = 0; i < BLKCG_MAX_POLS; i++) {
		struct blkcg_policy *pol = blkcg_policy[i];

		if (blkg->pd[i] && pol->pd_offline_fn)
			pol->pd_offline_fn(blkg->pd[i]);
	}

	if (parent) {
		blkg_rwstat_add_aux(&parent->stat_bytes, &blkg->stat_bytes);
		blkg_rwstat_add_aux(&parent->stat_ios, &blkg->stat_ios);
	}

	blkg->online = false;

	radix_tree_delete(&blkcg->blkg_tree, blkg->q->id);
	list_del_init(&blkg->q_node);
	hlist_del_init_rcu(&blkg->blkcg_node);

	/*
	 * Both setting lookup hint to and clearing it from @blkg are done
	 * under queue_lock.  If it's not pointing to @blkg now, it never
	 * will.  Hint assignment itself can race safely.
	 */
	if (rcu_access_pointer(blkcg->blkg_hint) == blkg)
		rcu_assign_pointer(blkcg->blkg_hint, NULL);

	/*
	 * Put the reference taken at the time of creation so that when all
	 * queues are gone, group can be destroyed.
	 */
	percpu_ref_kill(&blkg->refcnt);
}

/**
 * blkg_destroy_all - destroy all blkgs associated with a request_queue
 * @q: request_queue of interest
 *
 * Destroy all blkgs associated with @q.
 */
static void blkg_destroy_all(struct request_queue *q)
{
	struct blkcg_gq *blkg, *n;

	spin_lock_irq(&q->queue_lock);
	list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) {
		struct blkcg *blkcg = blkg->blkcg;

		spin_lock(&blkcg->lock);
		blkg_destroy(blkg);
		spin_unlock(&blkcg->lock);
	}

	q->root_blkg = NULL;
	spin_unlock_irq(&q->queue_lock);
}

static int blkcg_reset_stats(struct cgroup_subsys_state *css,
			     struct cftype *cftype, u64 val)
{
	struct blkcg *blkcg = css_to_blkcg(css);
	struct blkcg_gq *blkg;
	int i;

	mutex_lock(&blkcg_pol_mutex);
	spin_lock_irq(&blkcg->lock);

	/*
	 * Note that stat reset is racy - it doesn't synchronize against
	 * stat updates.  This is a debug feature which shouldn't exist
	 * anyway.  If you get hit by a race, retry.
	 */
	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
		blkg_rwstat_reset(&blkg->stat_bytes);
		blkg_rwstat_reset(&blkg->stat_ios);

		for (i = 0; i < BLKCG_MAX_POLS; i++) {
			struct blkcg_policy *pol = blkcg_policy[i];

			if (blkg->pd[i] && pol->pd_reset_stats_fn)
				pol->pd_reset_stats_fn(blkg->pd[i]);
		}
	}

	spin_unlock_irq(&blkcg->lock);
	mutex_unlock(&blkcg_pol_mutex);
	return 0;
}

const char *blkg_dev_name(struct blkcg_gq *blkg)
{
	/* some drivers (floppy) instantiate a queue w/o disk registered */
	if (blkg->q->backing_dev_info->dev)
		return dev_name(blkg->q->backing_dev_info->dev);
	return NULL;
}

/**
 * blkcg_print_blkgs - helper for printing per-blkg data
 * @sf: seq_file to print to
 * @blkcg: blkcg of interest
 * @prfill: fill function to print out a blkg
 * @pol: policy in question
 * @data: data to be passed to @prfill
 * @show_total: to print out sum of prfill return values or not
 *
 * This function invokes @prfill on each blkg of @blkcg if pd for the
 * policy specified by @pol exists.  @prfill is invoked with @sf, the
 * policy data and @data and the matching queue lock held.  If @show_total
 * is %true, the sum of the return values from @prfill is printed with
 * "Total" label at the end.
 *
 * This is to be used to construct print functions for
 * cftype->read_seq_string method.
 */
void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
		       u64 (*prfill)(struct seq_file *,
				     struct blkg_policy_data *, int),
		       const struct blkcg_policy *pol, int data,
		       bool show_total)
{
	struct blkcg_gq *blkg;
	u64 total = 0;

	rcu_read_lock();
	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
		spin_lock_irq(&blkg->q->queue_lock);
		if (blkcg_policy_enabled(blkg->q, pol))
			total += prfill(sf, blkg->pd[pol->plid], data);
		spin_unlock_irq(&blkg->q->queue_lock);
	}
	rcu_read_unlock();

	if (show_total)
		seq_printf(sf, "Total %llu\n", (unsigned long long)total);
}
EXPORT_SYMBOL_GPL(blkcg_print_blkgs);

/**
 * __blkg_prfill_u64 - prfill helper for a single u64 value
 * @sf: seq_file to print to
 * @pd: policy private data of interest
 * @v: value to print
 *
 * Print @v to @sf for the device assocaited with @pd.
 */
u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v)
{
	const char *dname = blkg_dev_name(pd->blkg);

	if (!dname)
		return 0;

	seq_printf(sf, "%s %llu\n", dname, (unsigned long long)v);
	return v;
}
EXPORT_SYMBOL_GPL(__blkg_prfill_u64);

/**
 * __blkg_prfill_rwstat - prfill helper for a blkg_rwstat
 * @sf: seq_file to print to
 * @pd: policy private data of interest
 * @rwstat: rwstat to print
 *
 * Print @rwstat to @sf for the device assocaited with @pd.
 */
u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
			 const struct blkg_rwstat *rwstat)
{
	static const char *rwstr[] = {
		[BLKG_RWSTAT_READ]	= "Read",
		[BLKG_RWSTAT_WRITE]	= "Write",
		[BLKG_RWSTAT_SYNC]	= "Sync",
		[BLKG_RWSTAT_ASYNC]	= "Async",
		[BLKG_RWSTAT_DISCARD]	= "Discard",
	};
	const char *dname = blkg_dev_name(pd->blkg);
	u64 v;
	int i;

	if (!dname)
		return 0;

	for (i = 0; i < BLKG_RWSTAT_NR; i++)
		seq_printf(sf, "%s %s %llu\n", dname, rwstr[i],
			   (unsigned long long)atomic64_read(&rwstat->aux_cnt[i]));

	v = atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_READ]) +
		atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_WRITE]) +
		atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_DISCARD]);
	seq_printf(sf, "%s Total %llu\n", dname, (unsigned long long)v);
	return v;
}
EXPORT_SYMBOL_GPL(__blkg_prfill_rwstat);

/**
 * blkg_prfill_stat - prfill callback for blkg_stat
 * @sf: seq_file to print to
 * @pd: policy private data of interest
 * @off: offset to the blkg_stat in @pd
 *
 * prfill callback for printing a blkg_stat.
 */
u64 blkg_prfill_stat(struct seq_file *sf, struct blkg_policy_data *pd, int off)
{
	return __blkg_prfill_u64(sf, pd, blkg_stat_read((void *)pd + off));
}
EXPORT_SYMBOL_GPL(blkg_prfill_stat);

/**
 * blkg_prfill_rwstat - prfill callback for blkg_rwstat
 * @sf: seq_file to print to
 * @pd: policy private data of interest
 * @off: offset to the blkg_rwstat in @pd
 *
 * prfill callback for printing a blkg_rwstat.
 */
u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
		       int off)
{
	struct blkg_rwstat rwstat = blkg_rwstat_read((void *)pd + off);

	return __blkg_prfill_rwstat(sf, pd, &rwstat);
}
EXPORT_SYMBOL_GPL(blkg_prfill_rwstat);

static u64 blkg_prfill_rwstat_field(struct seq_file *sf,
				    struct blkg_policy_data *pd, int off)
{
	struct blkg_rwstat rwstat = blkg_rwstat_read((void *)pd->blkg + off);

	return __blkg_prfill_rwstat(sf, pd, &rwstat);
}

/**
 * blkg_print_stat_bytes - seq_show callback for blkg->stat_bytes
 * @sf: seq_file to print to
 * @v: unused
 *
 * To be used as cftype->seq_show to print blkg->stat_bytes.
 * cftype->private must be set to the blkcg_policy.
 */
int blkg_print_stat_bytes(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private,
			  offsetof(struct blkcg_gq, stat_bytes), true);
	return 0;
}
EXPORT_SYMBOL_GPL(blkg_print_stat_bytes);

/**
 * blkg_print_stat_bytes - seq_show callback for blkg->stat_ios
 * @sf: seq_file to print to
 * @v: unused
 *
 * To be used as cftype->seq_show to print blkg->stat_ios.  cftype->private
 * must be set to the blkcg_policy.
 */
int blkg_print_stat_ios(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  blkg_prfill_rwstat_field, (void *)seq_cft(sf)->private,
			  offsetof(struct blkcg_gq, stat_ios), true);
	return 0;
}
EXPORT_SYMBOL_GPL(blkg_print_stat_ios);

static u64 blkg_prfill_rwstat_field_recursive(struct seq_file *sf,
					      struct blkg_policy_data *pd,
					      int off)
{
	struct blkg_rwstat rwstat = blkg_rwstat_recursive_sum(pd->blkg,
							      NULL, off);
	return __blkg_prfill_rwstat(sf, pd, &rwstat);
}

/**
 * blkg_print_stat_bytes_recursive - recursive version of blkg_print_stat_bytes
 * @sf: seq_file to print to
 * @v: unused
 */
int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  blkg_prfill_rwstat_field_recursive,
			  (void *)seq_cft(sf)->private,
			  offsetof(struct blkcg_gq, stat_bytes), true);
	return 0;
}
EXPORT_SYMBOL_GPL(blkg_print_stat_bytes_recursive);

/**
 * blkg_print_stat_ios_recursive - recursive version of blkg_print_stat_ios
 * @sf: seq_file to print to
 * @v: unused
 */
int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  blkg_prfill_rwstat_field_recursive,
			  (void *)seq_cft(sf)->private,
			  offsetof(struct blkcg_gq, stat_ios), true);
	return 0;
}
EXPORT_SYMBOL_GPL(blkg_print_stat_ios_recursive);

/**
 * blkg_stat_recursive_sum - collect hierarchical blkg_stat
 * @blkg: blkg of interest
 * @pol: blkcg_policy which contains the blkg_stat
 * @off: offset to the blkg_stat in blkg_policy_data or @blkg
 *
 * Collect the blkg_stat specified by @blkg, @pol and @off and all its
 * online descendants and their aux counts.  The caller must be holding the
 * queue lock for online tests.
 *
 * If @pol is NULL, blkg_stat is at @off bytes into @blkg; otherwise, it is
 * at @off bytes into @blkg's blkg_policy_data of the policy.
 */
u64 blkg_stat_recursive_sum(struct blkcg_gq *blkg,
			    struct blkcg_policy *pol, int off)
{
	struct blkcg_gq *pos_blkg;
	struct cgroup_subsys_state *pos_css;
	u64 sum = 0;

	lockdep_assert_held(&blkg->q->queue_lock);

	rcu_read_lock();
	blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
		struct blkg_stat *stat;

		if (!pos_blkg->online)
			continue;

		if (pol)
			stat = (void *)blkg_to_pd(pos_blkg, pol) + off;
		else
			stat = (void *)blkg + off;

		sum += blkg_stat_read(stat) + atomic64_read(&stat->aux_cnt);
	}
	rcu_read_unlock();

	return sum;
}
EXPORT_SYMBOL_GPL(blkg_stat_recursive_sum);

/**
 * blkg_rwstat_recursive_sum - collect hierarchical blkg_rwstat
 * @blkg: blkg of interest
 * @pol: blkcg_policy which contains the blkg_rwstat
 * @off: offset to the blkg_rwstat in blkg_policy_data or @blkg
 *
 * Collect the blkg_rwstat specified by @blkg, @pol and @off and all its
 * online descendants and their aux counts.  The caller must be holding the
 * queue lock for online tests.
 *
 * If @pol is NULL, blkg_rwstat is at @off bytes into @blkg; otherwise, it
 * is at @off bytes into @blkg's blkg_policy_data of the policy.
 */
struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkcg_gq *blkg,
					     struct blkcg_policy *pol, int off)
{
	struct blkcg_gq *pos_blkg;
	struct cgroup_subsys_state *pos_css;
	struct blkg_rwstat sum = { };
	int i;

	lockdep_assert_held(&blkg->q->queue_lock);

	rcu_read_lock();
	blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
		struct blkg_rwstat *rwstat;

		if (!pos_blkg->online)
			continue;

		if (pol)
			rwstat = (void *)blkg_to_pd(pos_blkg, pol) + off;
		else
			rwstat = (void *)pos_blkg + off;

		for (i = 0; i < BLKG_RWSTAT_NR; i++)
			atomic64_add(atomic64_read(&rwstat->aux_cnt[i]) +
				percpu_counter_sum_positive(&rwstat->cpu_cnt[i]),
				&sum.aux_cnt[i]);
	}
	rcu_read_unlock();

	return sum;
}
EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum);

/* Performs queue bypass and policy enabled checks then looks up blkg. */
static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg,
					  const struct blkcg_policy *pol,
					  struct request_queue *q)
{
	WARN_ON_ONCE(!rcu_read_lock_held());
	lockdep_assert_held(&q->queue_lock);

	if (!blkcg_policy_enabled(q, pol))
		return ERR_PTR(-EOPNOTSUPP);
	return __blkg_lookup(blkcg, q, true /* update_hint */);
}

/**
 * blkg_conf_prep - parse and prepare for per-blkg config update
 * @blkcg: target block cgroup
 * @pol: target policy
 * @input: input string
 * @ctx: blkg_conf_ctx to be filled
 *
 * Parse per-blkg config update from @input and initialize @ctx with the
 * result.  @ctx->blkg points to the blkg to be updated and @ctx->body the
 * part of @input following MAJ:MIN.  This function returns with RCU read
 * lock and queue lock held and must be paired with blkg_conf_finish().
 */
int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
		   char *input, struct blkg_conf_ctx *ctx)
	__acquires(rcu) __acquires(&disk->queue->queue_lock)
{
	struct gendisk *disk;
	struct request_queue *q;
	struct blkcg_gq *blkg;
	unsigned int major, minor;
	int key_len, part, ret;
	char *body;

	if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2)
		return -EINVAL;

	body = input + key_len;
	if (!isspace(*body))
		return -EINVAL;
	body = skip_spaces(body);

	disk = get_gendisk(MKDEV(major, minor), &part);
	if (!disk)
		return -ENODEV;
	if (part) {
		ret = -ENODEV;
		goto fail;
	}

	q = disk->queue;

	rcu_read_lock();
	spin_lock_irq(&q->queue_lock);

	blkg = blkg_lookup_check(blkcg, pol, q);
	if (IS_ERR(blkg)) {
		ret = PTR_ERR(blkg);
		goto fail_unlock;
	}

	if (blkg)
		goto success;

	/*
	 * Create blkgs walking down from blkcg_root to @blkcg, so that all
	 * non-root blkgs have access to their parents.
	 */
	while (true) {
		struct blkcg *pos = blkcg;
		struct blkcg *parent;
		struct blkcg_gq *new_blkg;

		parent = blkcg_parent(blkcg);
		while (parent && !__blkg_lookup(parent, q, false)) {
			pos = parent;
			parent = blkcg_parent(parent);
		}

		/* Drop locks to do new blkg allocation with GFP_KERNEL. */
		spin_unlock_irq(&q->queue_lock);
		rcu_read_unlock();

		new_blkg = blkg_alloc(pos, q, GFP_KERNEL);
		if (unlikely(!new_blkg)) {
			ret = -ENOMEM;
			goto fail;
		}

		rcu_read_lock();
		spin_lock_irq(&q->queue_lock);

		blkg = blkg_lookup_check(pos, pol, q);
		if (IS_ERR(blkg)) {
			ret = PTR_ERR(blkg);
			goto fail_unlock;
		}

		if (blkg) {
			blkg_free(new_blkg);
		} else {
			blkg = blkg_create(pos, q, new_blkg);
			if (IS_ERR(blkg)) {
				ret = PTR_ERR(blkg);
				goto fail_unlock;
			}
		}

		if (pos == blkcg)
			goto success;
	}
success:
	ctx->disk = disk;
	ctx->blkg = blkg;
	ctx->body = body;
	return 0;

fail_unlock:
	spin_unlock_irq(&q->queue_lock);
	rcu_read_unlock();
fail:
	put_disk_and_module(disk);
	/*
	 * If queue was bypassing, we should retry.  Do so after a
	 * short msleep().  It isn't strictly necessary but queue
	 * can be bypassing for some time and it's always nice to
	 * avoid busy looping.
	 */
	if (ret == -EBUSY) {
		msleep(10);
		ret = restart_syscall();
	}
	return ret;
}

/**
 * blkg_conf_finish - finish up per-blkg config update
 * @ctx: blkg_conf_ctx intiailized by blkg_conf_prep()
 *
 * Finish up after per-blkg config update.  This function must be paired
 * with blkg_conf_prep().
 */
void blkg_conf_finish(struct blkg_conf_ctx *ctx)
	__releases(&ctx->disk->queue->queue_lock) __releases(rcu)
{
	spin_unlock_irq(&ctx->disk->queue->queue_lock);
	rcu_read_unlock();
	put_disk_and_module(ctx->disk);
}

static int blkcg_print_stat(struct seq_file *sf, void *v)
{
	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
	struct blkcg_gq *blkg;

	rcu_read_lock();

	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
		const char *dname;
		char *buf;
		struct blkg_rwstat rwstat;
		u64 rbytes, wbytes, rios, wios, dbytes, dios;
		size_t size = seq_get_buf(sf, &buf), off = 0;
		int i;
		bool has_stats = false;

		dname = blkg_dev_name(blkg);
		if (!dname)
			continue;

		/*
		 * Hooray string manipulation, count is the size written NOT
		 * INCLUDING THE \0, so size is now count+1 less than what we
		 * had before, but we want to start writing the next bit from
		 * the \0 so we only add count to buf.
		 */
		off += scnprintf(buf+off, size-off, "%s ", dname);

		spin_lock_irq(&blkg->q->queue_lock);

		rwstat = blkg_rwstat_recursive_sum(blkg, NULL,
					offsetof(struct blkcg_gq, stat_bytes));
		rbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_READ]);
		wbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]);
		dbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_DISCARD]);

		rwstat = blkg_rwstat_recursive_sum(blkg, NULL,
					offsetof(struct blkcg_gq, stat_ios));
		rios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_READ]);
		wios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]);
		dios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_DISCARD]);

		spin_unlock_irq(&blkg->q->queue_lock);

		if (rbytes || wbytes || rios || wios) {
			has_stats = true;
			off += scnprintf(buf+off, size-off,
					 "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu",
					 rbytes, wbytes, rios, wios,
					 dbytes, dios);
		}

		if (!blkcg_debug_stats)
			goto next;

		if (atomic_read(&blkg->use_delay)) {
			has_stats = true;
			off += scnprintf(buf+off, size-off,
					 " use_delay=%d delay_nsec=%llu",
					 atomic_read(&blkg->use_delay),
					(unsigned long long)atomic64_read(&blkg->delay_nsec));
		}

		for (i = 0; i < BLKCG_MAX_POLS; i++) {
			struct blkcg_policy *pol = blkcg_policy[i];
			size_t written;

			if (!blkg->pd[i] || !pol->pd_stat_fn)
				continue;

			written = pol->pd_stat_fn(blkg->pd[i], buf+off, size-off);
			if (written)
				has_stats = true;
			off += written;
		}
next:
		if (has_stats) {
			off += scnprintf(buf+off, size-off, "\n");
			seq_commit(sf, off);
		}
	}

	rcu_read_unlock();
	return 0;
}

static struct cftype blkcg_files[] = {
	{
		.name = "stat",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = blkcg_print_stat,
	},
	{ }	/* terminate */
};

static struct cftype blkcg_legacy_files[] = {
	{
		.name = "reset_stats",
		.write_u64 = blkcg_reset_stats,
	},
	{ }	/* terminate */
};

/*
 * blkcg destruction is a three-stage process.
 *
 * 1. Destruction starts.  The blkcg_css_offline() callback is invoked
 *    which offlines writeback.  Here we tie the next stage of blkg destruction
 *    to the completion of writeback associated with the blkcg.  This lets us
 *    avoid punting potentially large amounts of outstanding writeback to root
 *    while maintaining any ongoing policies.  The next stage is triggered when
 *    the nr_cgwbs count goes to zero.
 *
 * 2. When the nr_cgwbs count goes to zero, blkcg_destroy_blkgs() is called
 *    and handles the destruction of blkgs.  Here the css reference held by
 *    the blkg is put back eventually allowing blkcg_css_free() to be called.
 *    This work may occur in cgwb_release_workfn() on the cgwb_release
 *    workqueue.  Any submitted ios that fail to get the blkg ref will be
 *    punted to the root_blkg.
 *
 * 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called.
 *    This finally frees the blkcg.
 */

/**
 * blkcg_css_offline - cgroup css_offline callback
 * @css: css of interest
 *
 * This function is called when @css is about to go away.  Here the cgwbs are
 * offlined first and only once writeback associated with the blkcg has
 * finished do we start step 2 (see above).
 */
static void blkcg_css_offline(struct cgroup_subsys_state *css)
{
	struct blkcg *blkcg = css_to_blkcg(css);

	/* this prevents anyone from attaching or migrating to this blkcg */
	wb_blkcg_offline(blkcg);

	/* put the base cgwb reference allowing step 2 to be triggered */
	blkcg_cgwb_put(blkcg);
}

/**
 * blkcg_destroy_blkgs - responsible for shooting down blkgs
 * @blkcg: blkcg of interest
 *
 * blkgs should be removed while holding both q and blkcg locks.  As blkcg lock
 * is nested inside q lock, this function performs reverse double lock dancing.
 * Destroying the blkgs releases the reference held on the blkcg's css allowing
 * blkcg_css_free to eventually be called.
 *
 * This is the blkcg counterpart of ioc_release_fn().
 */
void blkcg_destroy_blkgs(struct blkcg *blkcg)
{
	spin_lock_irq(&blkcg->lock);

	while (!hlist_empty(&blkcg->blkg_list)) {
		struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first,
						struct blkcg_gq, blkcg_node);
		struct request_queue *q = blkg->q;

		if (spin_trylock(&q->queue_lock)) {
			blkg_destroy(blkg);
			spin_unlock(&q->queue_lock);
		} else {
			spin_unlock_irq(&blkcg->lock);
			cpu_relax();
			spin_lock_irq(&blkcg->lock);
		}
	}

	spin_unlock_irq(&blkcg->lock);
}

static void blkcg_css_free(struct cgroup_subsys_state *css)
{
	struct blkcg *blkcg = css_to_blkcg(css);
	int i;

	mutex_lock(&blkcg_pol_mutex);

	list_del(&blkcg->all_blkcgs_node);

	for (i = 0; i < BLKCG_MAX_POLS; i++)
		if (blkcg->cpd[i])
			blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]);

	mutex_unlock(&blkcg_pol_mutex);

	kfree(blkcg);
}

static struct cgroup_subsys_state *
blkcg_css_alloc(struct cgroup_subsys_state *parent_css)
{
	struct blkcg *blkcg;
	struct cgroup_subsys_state *ret;
	int i;

	mutex_lock(&blkcg_pol_mutex);

	if (!parent_css) {
		blkcg = &blkcg_root;
	} else {
		blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
		if (!blkcg) {
			ret = ERR_PTR(-ENOMEM);
			goto unlock;
		}
	}

	for (i = 0; i < BLKCG_MAX_POLS ; i++) {
		struct blkcg_policy *pol = blkcg_policy[i];
		struct blkcg_policy_data *cpd;

		/*
		 * If the policy hasn't been attached yet, wait for it
		 * to be attached before doing anything else. Otherwise,
		 * check if the policy requires any specific per-cgroup
		 * data: if it does, allocate and initialize it.
		 */
		if (!pol || !pol->cpd_alloc_fn)
			continue;

		cpd = pol->cpd_alloc_fn(GFP_KERNEL);
		if (!cpd) {
			ret = ERR_PTR(-ENOMEM);
			goto free_pd_blkcg;
		}
		blkcg->cpd[i] = cpd;
		cpd->blkcg = blkcg;
		cpd->plid = i;
		if (pol->cpd_init_fn)
			pol->cpd_init_fn(cpd);
	}

	spin_lock_init(&blkcg->lock);
	INIT_RADIX_TREE(&blkcg->blkg_tree, GFP_NOWAIT | __GFP_NOWARN);
	INIT_HLIST_HEAD(&blkcg->blkg_list);
#ifdef CONFIG_CGROUP_WRITEBACK
	INIT_LIST_HEAD(&blkcg->cgwb_list);
	refcount_set(&blkcg->cgwb_refcnt, 1);
#endif
	list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs);

	mutex_unlock(&blkcg_pol_mutex);
	return &blkcg->css;

free_pd_blkcg:
	for (i--; i >= 0; i--)
		if (blkcg->cpd[i])
			blkcg_policy[i]->cpd_free_fn(blkcg->cpd[i]);

	if (blkcg != &blkcg_root)
		kfree(blkcg);
unlock:
	mutex_unlock(&blkcg_pol_mutex);
	return ret;
}

/**
 * blkcg_init_queue - initialize blkcg part of request queue
 * @q: request_queue to initialize
 *
 * Called from blk_alloc_queue_node(). Responsible for initializing blkcg
 * part of new request_queue @q.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int blkcg_init_queue(struct request_queue *q)
{
	struct blkcg_gq *new_blkg, *blkg;
	bool preloaded;
	int ret;

	new_blkg = blkg_alloc(&blkcg_root, q, GFP_KERNEL);
	if (!new_blkg)
		return -ENOMEM;

	preloaded = !radix_tree_preload(GFP_KERNEL);

	/* Make sure the root blkg exists. */
	rcu_read_lock();
	spin_lock_irq(&q->queue_lock);
	blkg = blkg_create(&blkcg_root, q, new_blkg);
	if (IS_ERR(blkg))
		goto err_unlock;
	q->root_blkg = blkg;
	spin_unlock_irq(&q->queue_lock);
	rcu_read_unlock();

	if (preloaded)
		radix_tree_preload_end();

	ret = blk_iolatency_init(q);
	if (ret)
		goto err_destroy_all;

	ret = blk_throtl_init(q);
	if (ret)
		goto err_destroy_all;
	return 0;

err_destroy_all:
	blkg_destroy_all(q);
	return ret;
err_unlock:
	spin_unlock_irq(&q->queue_lock);
	rcu_read_unlock();
	if (preloaded)
		radix_tree_preload_end();
	return PTR_ERR(blkg);
}

/**
 * blkcg_drain_queue - drain blkcg part of request_queue
 * @q: request_queue to drain
 *
 * Called from blk_drain_queue().  Responsible for draining blkcg part.
 */
void blkcg_drain_queue(struct request_queue *q)
{
	lockdep_assert_held(&q->queue_lock);

	/*
	 * @q could be exiting and already have destroyed all blkgs as
	 * indicated by NULL root_blkg.  If so, don't confuse policies.
	 */
	if (!q->root_blkg)
		return;

	blk_throtl_drain(q);
}

/**
 * blkcg_exit_queue - exit and release blkcg part of request_queue
 * @q: request_queue being released
 *
 * Called from blk_exit_queue().  Responsible for exiting blkcg part.
 */
void blkcg_exit_queue(struct request_queue *q)
{
	blkg_destroy_all(q);
	blk_throtl_exit(q);
}

/*
 * We cannot support shared io contexts, as we have no mean to support
 * two tasks with the same ioc in two different groups without major rework
 * of the main cic data structures.  For now we allow a task to change
 * its cgroup only if it's the only owner of its ioc.
 */
static int blkcg_can_attach(struct cgroup_taskset *tset)
{
	struct task_struct *task;
	struct cgroup_subsys_state *dst_css;
	struct io_context *ioc;
	int ret = 0;

	/* task_lock() is needed to avoid races with exit_io_context() */
	cgroup_taskset_for_each(task, dst_css, tset) {
		task_lock(task);
		ioc = task->io_context;
		if (ioc && atomic_read(&ioc->nr_tasks) > 1)
			ret = -EINVAL;
		task_unlock(task);
		if (ret)
			break;
	}
	return ret;
}

static void blkcg_bind(struct cgroup_subsys_state *root_css)
{
	int i;

	mutex_lock(&blkcg_pol_mutex);

	for (i = 0; i < BLKCG_MAX_POLS; i++) {
		struct blkcg_policy *pol = blkcg_policy[i];
		struct blkcg *blkcg;

		if (!pol || !pol->cpd_bind_fn)
			continue;

		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node)
			if (blkcg->cpd[pol->plid])
				pol->cpd_bind_fn(blkcg->cpd[pol->plid]);
	}
	mutex_unlock(&blkcg_pol_mutex);
}

static void blkcg_exit(struct task_struct *tsk)
{
	if (tsk->throttle_queue)
		blk_put_queue(tsk->throttle_queue);
	tsk->throttle_queue = NULL;
}

struct cgroup_subsys io_cgrp_subsys = {
	.css_alloc = blkcg_css_alloc,
	.css_offline = blkcg_css_offline,
	.css_free = blkcg_css_free,
	.can_attach = blkcg_can_attach,
	.bind = blkcg_bind,
	.dfl_cftypes = blkcg_files,
	.legacy_cftypes = blkcg_legacy_files,
	.legacy_name = "blkio",
	.exit = blkcg_exit,
#ifdef CONFIG_MEMCG
	/*
	 * This ensures that, if available, memcg is automatically enabled
	 * together on the default hierarchy so that the owner cgroup can
	 * be retrieved from writeback pages.
	 */
	.depends_on = 1 << memory_cgrp_id,
#endif
};
EXPORT_SYMBOL_GPL(io_cgrp_subsys);

/**
 * blkcg_activate_policy - activate a blkcg policy on a request_queue
 * @q: request_queue of interest
 * @pol: blkcg policy to activate
 *
 * Activate @pol on @q.  Requires %GFP_KERNEL context.  @q goes through
 * bypass mode to populate its blkgs with policy_data for @pol.
 *
 * Activation happens with @q bypassed, so nobody would be accessing blkgs
 * from IO path.  Update of each blkg is protected by both queue and blkcg
 * locks so that holding either lock and testing blkcg_policy_enabled() is
 * always enough for dereferencing policy data.
 *
 * The caller is responsible for synchronizing [de]activations and policy
 * [un]registerations.  Returns 0 on success, -errno on failure.
 */
int blkcg_activate_policy(struct request_queue *q,
			  const struct blkcg_policy *pol)
{
	struct blkg_policy_data *pd_prealloc = NULL;
	struct blkcg_gq *blkg;
	int ret;

	if (blkcg_policy_enabled(q, pol))
		return 0;

	if (queue_is_mq(q))
		blk_mq_freeze_queue(q);
pd_prealloc:
	if (!pd_prealloc) {
		pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q->node);
		if (!pd_prealloc) {
			ret = -ENOMEM;
			goto out_bypass_end;
		}
	}

	spin_lock_irq(&q->queue_lock);

	list_for_each_entry(blkg, &q->blkg_list, q_node) {
		struct blkg_policy_data *pd;

		if (blkg->pd[pol->plid])
			continue;

		pd = pol->pd_alloc_fn(GFP_NOWAIT | __GFP_NOWARN, q->node);
		if (!pd)
			swap(pd, pd_prealloc);
		if (!pd) {
			spin_unlock_irq(&q->queue_lock);
			goto pd_prealloc;
		}

		blkg->pd[pol->plid] = pd;
		pd->blkg = blkg;
		pd->plid = pol->plid;
		if (pol->pd_init_fn)
			pol->pd_init_fn(pd);
	}

	__set_bit(pol->plid, q->blkcg_pols);
	ret = 0;

	spin_unlock_irq(&q->queue_lock);
out_bypass_end:
	if (queue_is_mq(q))
		blk_mq_unfreeze_queue(q);
	if (pd_prealloc)
		pol->pd_free_fn(pd_prealloc);
	return ret;
}
EXPORT_SYMBOL_GPL(blkcg_activate_policy);

/**
 * blkcg_deactivate_policy - deactivate a blkcg policy on a request_queue
 * @q: request_queue of interest
 * @pol: blkcg policy to deactivate
 *
 * Deactivate @pol on @q.  Follows the same synchronization rules as
 * blkcg_activate_policy().
 */
void blkcg_deactivate_policy(struct request_queue *q,
			     const struct blkcg_policy *pol)
{
	struct blkcg_gq *blkg;

	if (!blkcg_policy_enabled(q, pol))
		return;

	if (queue_is_mq(q))
		blk_mq_freeze_queue(q);

	spin_lock_irq(&q->queue_lock);

	__clear_bit(pol->plid, q->blkcg_pols);

	list_for_each_entry(blkg, &q->blkg_list, q_node) {
		if (blkg->pd[pol->plid]) {
			if (pol->pd_offline_fn)
				pol->pd_offline_fn(blkg->pd[pol->plid]);
			pol->pd_free_fn(blkg->pd[pol->plid]);
			blkg->pd[pol->plid] = NULL;
		}
	}

	spin_unlock_irq(&q->queue_lock);

	if (queue_is_mq(q))
		blk_mq_unfreeze_queue(q);
}
EXPORT_SYMBOL_GPL(blkcg_deactivate_policy);

/**
 * blkcg_policy_register - register a blkcg policy
 * @pol: blkcg policy to register
 *
 * Register @pol with blkcg core.  Might sleep and @pol may be modified on
 * successful registration.  Returns 0 on success and -errno on failure.
 */
int blkcg_policy_register(struct blkcg_policy *pol)
{
	struct blkcg *blkcg;
	int i, ret;

	mutex_lock(&blkcg_pol_register_mutex);
	mutex_lock(&blkcg_pol_mutex);

	/* find an empty slot */
	ret = -ENOSPC;
	for (i = 0; i < BLKCG_MAX_POLS; i++)
		if (!blkcg_policy[i])
			break;
	if (i >= BLKCG_MAX_POLS) {
		pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n");
		goto err_unlock;
	}

	/* Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs */
	if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) ||
		(!pol->pd_alloc_fn ^ !pol->pd_free_fn))
		goto err_unlock;

	/* register @pol */
	pol->plid = i;
	blkcg_policy[pol->plid] = pol;

	/* allocate and install cpd's */
	if (pol->cpd_alloc_fn) {
		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
			struct blkcg_policy_data *cpd;

			cpd = pol->cpd_alloc_fn(GFP_KERNEL);
			if (!cpd)
				goto err_free_cpds;

			blkcg->cpd[pol->plid] = cpd;
			cpd->blkcg = blkcg;
			cpd->plid = pol->plid;
			pol->cpd_init_fn(cpd);
		}
	}

	mutex_unlock(&blkcg_pol_mutex);

	/* everything is in place, add intf files for the new policy */
	if (pol->dfl_cftypes)
		WARN_ON(cgroup_add_dfl_cftypes(&io_cgrp_subsys,
					       pol->dfl_cftypes));
	if (pol->legacy_cftypes)
		WARN_ON(cgroup_add_legacy_cftypes(&io_cgrp_subsys,
						  pol->legacy_cftypes));
	mutex_unlock(&blkcg_pol_register_mutex);
	return 0;

err_free_cpds:
	if (pol->cpd_free_fn) {
		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
			if (blkcg->cpd[pol->plid]) {
				pol->cpd_free_fn(blkcg->cpd[pol->plid]);
				blkcg->cpd[pol->plid] = NULL;
			}
		}
	}
	blkcg_policy[pol->plid] = NULL;
err_unlock:
	mutex_unlock(&blkcg_pol_mutex);
	mutex_unlock(&blkcg_pol_register_mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(blkcg_policy_register);

/**
 * blkcg_policy_unregister - unregister a blkcg policy
 * @pol: blkcg policy to unregister
 *
 * Undo blkcg_policy_register(@pol).  Might sleep.
 */
void blkcg_policy_unregister(struct blkcg_policy *pol)
{
	struct blkcg *blkcg;

	mutex_lock(&blkcg_pol_register_mutex);

	if (WARN_ON(blkcg_policy[pol->plid] != pol))
		goto out_unlock;

	/* kill the intf files first */
	if (pol->dfl_cftypes)
		cgroup_rm_cftypes(pol->dfl_cftypes);
	if (pol->legacy_cftypes)
		cgroup_rm_cftypes(pol->legacy_cftypes);

	/* remove cpds and unregister */
	mutex_lock(&blkcg_pol_mutex);

	if (pol->cpd_free_fn) {
		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
			if (blkcg->cpd[pol->plid]) {
				pol->cpd_free_fn(blkcg->cpd[pol->plid]);
				blkcg->cpd[pol->plid] = NULL;
			}
		}
	}
	blkcg_policy[pol->plid] = NULL;

	mutex_unlock(&blkcg_pol_mutex);
out_unlock:
	mutex_unlock(&blkcg_pol_register_mutex);
}
EXPORT_SYMBOL_GPL(blkcg_policy_unregister);

/*
 * Scale the accumulated delay based on how long it has been since we updated
 * the delay.  We only call this when we are adding delay, in case it's been a
 * while since we added delay, and when we are checking to see if we need to
 * delay a task, to account for any delays that may have occurred.
 */
static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now)
{
	u64 old = atomic64_read(&blkg->delay_start);

	/*
	 * We only want to scale down every second.  The idea here is that we
	 * want to delay people for min(delay_nsec, NSEC_PER_SEC) in a certain
	 * time window.  We only want to throttle tasks for recent delay that
	 * has occurred, in 1 second time windows since that's the maximum
	 * things can be throttled.  We save the current delay window in
	 * blkg->last_delay so we know what amount is still left to be charged
	 * to the blkg from this point onward.  blkg->last_use keeps track of
	 * the use_delay counter.  The idea is if we're unthrottling the blkg we
	 * are ok with whatever is happening now, and we can take away more of
	 * the accumulated delay as we've already throttled enough that
	 * everybody is happy with their IO latencies.
	 */
	if (time_before64(old + NSEC_PER_SEC, now) &&
	    atomic64_cmpxchg(&blkg->delay_start, old, now) == old) {
		u64 cur = atomic64_read(&blkg->delay_nsec);
		u64 sub = min_t(u64, blkg->last_delay, now - old);
		int cur_use = atomic_read(&blkg->use_delay);

		/*
		 * We've been unthrottled, subtract a larger chunk of our
		 * accumulated delay.
		 */
		if (cur_use < blkg->last_use)
			sub = max_t(u64, sub, blkg->last_delay >> 1);

		/*
		 * This shouldn't happen, but handle it anyway.  Our delay_nsec
		 * should only ever be growing except here where we subtract out
		 * min(last_delay, 1 second), but lord knows bugs happen and I'd
		 * rather not end up with negative numbers.
		 */
		if (unlikely(cur < sub)) {
			atomic64_set(&blkg->delay_nsec, 0);
			blkg->last_delay = 0;
		} else {
			atomic64_sub(sub, &blkg->delay_nsec);
			blkg->last_delay = cur - sub;
		}
		blkg->last_use = cur_use;
	}
}

/*
 * This is called when we want to actually walk up the hierarchy and check to
 * see if we need to throttle, and then actually throttle if there is some
 * accumulated delay.  This should only be called upon return to user space so
 * we're not holding some lock that would induce a priority inversion.
 */
static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
{
	u64 now = ktime_to_ns(ktime_get());
	u64 exp;
	u64 delay_nsec = 0;
	int tok;

	while (blkg->parent) {
		if (atomic_read(&blkg->use_delay)) {
			blkcg_scale_delay(blkg, now);
			delay_nsec = max_t(u64, delay_nsec,
					   atomic64_read(&blkg->delay_nsec));
		}
		blkg = blkg->parent;
	}

	if (!delay_nsec)
		return;

	/*
	 * Let's not sleep for all eternity if we've amassed a huge delay.
	 * Swapping or metadata IO can accumulate 10's of seconds worth of
	 * delay, and we want userspace to be able to do _something_ so cap the
	 * delays at 1 second.  If there's 10's of seconds worth of delay then
	 * the tasks will be delayed for 1 second for every syscall.
	 */
	delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC);

	/*
	 * TODO: the use_memdelay flag is going to be for the upcoming psi stuff
	 * that hasn't landed upstream yet.  Once that stuff is in place we need
	 * to do a psi_memstall_enter/leave if memdelay is set.
	 */

	exp = ktime_add_ns(now, delay_nsec);
	tok = io_schedule_prepare();
	do {
		__set_current_state(TASK_KILLABLE);
		if (!schedule_hrtimeout(&exp, HRTIMER_MODE_ABS))
			break;
	} while (!fatal_signal_pending(current));
	io_schedule_finish(tok);
}

/**
 * blkcg_maybe_throttle_current - throttle the current task if it has been marked
 *
 * This is only called if we've been marked with set_notify_resume().  Obviously
 * we can be set_notify_resume() for reasons other than blkcg throttling, so we
 * check to see if current->throttle_queue is set and if not this doesn't do
 * anything.  This should only ever be called by the resume code, it's not meant
 * to be called by people willy-nilly as it will actually do the work to
 * throttle the task if it is setup for throttling.
 */
void blkcg_maybe_throttle_current(void)
{
	struct request_queue *q = current->throttle_queue;
	struct cgroup_subsys_state *css;
	struct blkcg *blkcg;
	struct blkcg_gq *blkg;
	bool use_memdelay = current->use_memdelay;

	if (!q)
		return;

	current->throttle_queue = NULL;
	current->use_memdelay = false;

	rcu_read_lock();
	css = kthread_blkcg();
	if (css)
		blkcg = css_to_blkcg(css);
	else
		blkcg = css_to_blkcg(task_css(current, io_cgrp_id));

	if (!blkcg)
		goto out;
	blkg = blkg_lookup(blkcg, q);
	if (!blkg)
		goto out;
	if (!blkg_tryget(blkg))
		goto out;
	rcu_read_unlock();

	blkcg_maybe_throttle_blkg(blkg, use_memdelay);
	blkg_put(blkg);
	blk_put_queue(q);
	return;
out:
	rcu_read_unlock();
	blk_put_queue(q);
}

/**
 * blkcg_schedule_throttle - this task needs to check for throttling
 * @q: the request queue IO was submitted on
 * @use_memdelay: do we charge this to memory delay for PSI
 *
 * This is called by the IO controller when we know there's delay accumulated
 * for the blkg for this task.  We do not pass the blkg because there are places
 * we call this that may not have that information, the swapping code for
 * instance will only have a request_queue at that point.  This set's the
 * notify_resume for the task to check and see if it requires throttling before
 * returning to user space.
 *
 * We will only schedule once per syscall.  You can call this over and over
 * again and it will only do the check once upon return to user space, and only
 * throttle once.  If the task needs to be throttled again it'll need to be
 * re-set at the next time we see the task.
 */
void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay)
{
	if (unlikely(current->flags & PF_KTHREAD))
		return;

	if (!blk_get_queue(q))
		return;

	if (current->throttle_queue)
		blk_put_queue(current->throttle_queue);
	current->throttle_queue = q;
	if (use_memdelay)
		current->use_memdelay = use_memdelay;
	set_notify_resume(current);
}

/**
 * blkcg_add_delay - add delay to this blkg
 * @blkg: blkg of interest
 * @now: the current time in nanoseconds
 * @delta: how many nanoseconds of delay to add
 *
 * Charge @delta to the blkg's current delay accumulation.  This is used to
 * throttle tasks if an IO controller thinks we need more throttling.
 */
void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta)
{
	blkcg_scale_delay(blkg, now);
	atomic64_add(delta, &blkg->delay_nsec);
}

module_param(blkcg_debug_stats, bool, 0644);
MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not");