summaryrefslogtreecommitdiffstats
path: root/block/bfq-cgroup.c
blob: 420eda2589c0ec99ea4647233fdd85a32b6b63e8 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * cgroups support for the BFQ I/O scheduler.
 */
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/cgroup.h>
#include <linux/ktime.h>
#include <linux/rbtree.h>
#include <linux/ioprio.h>
#include <linux/sbitmap.h>
#include <linux/delay.h>

#include "elevator.h"
#include "bfq-iosched.h"

#ifdef CONFIG_BFQ_CGROUP_DEBUG
static int bfq_stat_init(struct bfq_stat *stat, gfp_t gfp)
{
	int ret;

	ret = percpu_counter_init(&stat->cpu_cnt, 0, gfp);
	if (ret)
		return ret;

	atomic64_set(&stat->aux_cnt, 0);
	return 0;
}

static void bfq_stat_exit(struct bfq_stat *stat)
{
	percpu_counter_destroy(&stat->cpu_cnt);
}

/**
 * bfq_stat_add - add a value to a bfq_stat
 * @stat: target bfq_stat
 * @val: value to add
 *
 * Add @val to @stat.  The caller must ensure that IRQ on the same CPU
 * don't re-enter this function for the same counter.
 */
static inline void bfq_stat_add(struct bfq_stat *stat, uint64_t val)
{
	percpu_counter_add_batch(&stat->cpu_cnt, val, BLKG_STAT_CPU_BATCH);
}

/**
 * bfq_stat_read - read the current value of a bfq_stat
 * @stat: bfq_stat to read
 */
static inline uint64_t bfq_stat_read(struct bfq_stat *stat)
{
	return percpu_counter_sum_positive(&stat->cpu_cnt);
}

/**
 * bfq_stat_reset - reset a bfq_stat
 * @stat: bfq_stat to reset
 */
static inline void bfq_stat_reset(struct bfq_stat *stat)
{
	percpu_counter_set(&stat->cpu_cnt, 0);
	atomic64_set(&stat->aux_cnt, 0);
}

/**
 * bfq_stat_add_aux - add a bfq_stat into another's aux count
 * @to: the destination bfq_stat
 * @from: the source
 *
 * Add @from's count including the aux one to @to's aux count.
 */
static inline void bfq_stat_add_aux(struct bfq_stat *to,
				     struct bfq_stat *from)
{
	atomic64_add(bfq_stat_read(from) + atomic64_read(&from->aux_cnt),
		     &to->aux_cnt);
}

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

/* bfqg stats flags */
enum bfqg_stats_flags {
	BFQG_stats_waiting = 0,
	BFQG_stats_idling,
	BFQG_stats_empty,
};

#define BFQG_FLAG_FNS(name)						\
static void bfqg_stats_mark_##name(struct bfqg_stats *stats)	\
{									\
	stats->flags |= (1 << BFQG_stats_##name);			\
}									\
static void bfqg_stats_clear_##name(struct bfqg_stats *stats)	\
{									\
	stats->flags &= ~(1 << BFQG_stats_##name);			\
}									\
static int bfqg_stats_##name(struct bfqg_stats *stats)		\
{									\
	return (stats->flags & (1 << BFQG_stats_##name)) != 0;		\
}									\

BFQG_FLAG_FNS(waiting)
BFQG_FLAG_FNS(idling)
BFQG_FLAG_FNS(empty)
#undef BFQG_FLAG_FNS

/* This should be called with the scheduler lock held. */
static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
{
	u64 now;

	if (!bfqg_stats_waiting(stats))
		return;

	now = ktime_get_ns();
	if (now > stats->start_group_wait_time)
		bfq_stat_add(&stats->group_wait_time,
			      now - stats->start_group_wait_time);
	bfqg_stats_clear_waiting(stats);
}

/* This should be called with the scheduler lock held. */
static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
						 struct bfq_group *curr_bfqg)
{
	struct bfqg_stats *stats = &bfqg->stats;

	if (bfqg_stats_waiting(stats))
		return;
	if (bfqg == curr_bfqg)
		return;
	stats->start_group_wait_time = ktime_get_ns();
	bfqg_stats_mark_waiting(stats);
}

/* This should be called with the scheduler lock held. */
static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
{
	u64 now;

	if (!bfqg_stats_empty(stats))
		return;

	now = ktime_get_ns();
	if (now > stats->start_empty_time)
		bfq_stat_add(&stats->empty_time,
			      now - stats->start_empty_time);
	bfqg_stats_clear_empty(stats);
}

void bfqg_stats_update_dequeue(struct bfq_group *bfqg)
{
	bfq_stat_add(&bfqg->stats.dequeue, 1);
}

void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg)
{
	struct bfqg_stats *stats = &bfqg->stats;

	if (blkg_rwstat_total(&stats->queued))
		return;

	/*
	 * group is already marked empty. This can happen if bfqq got new
	 * request in parent group and moved to this group while being added
	 * to service tree. Just ignore the event and move on.
	 */
	if (bfqg_stats_empty(stats))
		return;

	stats->start_empty_time = ktime_get_ns();
	bfqg_stats_mark_empty(stats);
}

void bfqg_stats_update_idle_time(struct bfq_group *bfqg)
{
	struct bfqg_stats *stats = &bfqg->stats;

	if (bfqg_stats_idling(stats)) {
		u64 now = ktime_get_ns();

		if (now > stats->start_idle_time)
			bfq_stat_add(&stats->idle_time,
				      now - stats->start_idle_time);
		bfqg_stats_clear_idling(stats);
	}
}

void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg)
{
	struct bfqg_stats *stats = &bfqg->stats;

	stats->start_idle_time = ktime_get_ns();
	bfqg_stats_mark_idling(stats);
}

void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg)
{
	struct bfqg_stats *stats = &bfqg->stats;

	bfq_stat_add(&stats->avg_queue_size_sum,
		      blkg_rwstat_total(&stats->queued));
	bfq_stat_add(&stats->avg_queue_size_samples, 1);
	bfqg_stats_update_group_wait_time(stats);
}

void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
			      unsigned int op)
{
	blkg_rwstat_add(&bfqg->stats.queued, op, 1);
	bfqg_stats_end_empty_time(&bfqg->stats);
	if (!(bfqq == ((struct bfq_data *)bfqg->bfqd)->in_service_queue))
		bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq));
}

void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op)
{
	blkg_rwstat_add(&bfqg->stats.queued, op, -1);
}

void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op)
{
	blkg_rwstat_add(&bfqg->stats.merged, op, 1);
}

void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
				  u64 io_start_time_ns, unsigned int op)
{
	struct bfqg_stats *stats = &bfqg->stats;
	u64 now = ktime_get_ns();

	if (now > io_start_time_ns)
		blkg_rwstat_add(&stats->service_time, op,
				now - io_start_time_ns);
	if (io_start_time_ns > start_time_ns)
		blkg_rwstat_add(&stats->wait_time, op,
				io_start_time_ns - start_time_ns);
}

#else /* CONFIG_BFQ_CGROUP_DEBUG */

void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
			      unsigned int op) { }
void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) { }
void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) { }
void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns,
				  u64 io_start_time_ns, unsigned int op) { }
void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { }
void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { }
void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { }
void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { }
void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) { }

#endif /* CONFIG_BFQ_CGROUP_DEBUG */

#ifdef CONFIG_BFQ_GROUP_IOSCHED

/*
 * blk-cgroup policy-related handlers
 * The following functions help in converting between blk-cgroup
 * internal structures and BFQ-specific structures.
 */

static struct bfq_group *pd_to_bfqg(struct blkg_policy_data *pd)
{
	return pd ? container_of(pd, struct bfq_group, pd) : NULL;
}

struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg)
{
	return pd_to_blkg(&bfqg->pd);
}

static struct bfq_group *blkg_to_bfqg(struct blkcg_gq *blkg)
{
	return pd_to_bfqg(blkg_to_pd(blkg, &blkcg_policy_bfq));
}

/*
 * bfq_group handlers
 * The following functions help in navigating the bfq_group hierarchy
 * by allowing to find the parent of a bfq_group or the bfq_group
 * associated to a bfq_queue.
 */

static struct bfq_group *bfqg_parent(struct bfq_group *bfqg)
{
	struct blkcg_gq *pblkg = bfqg_to_blkg(bfqg)->parent;

	return pblkg ? blkg_to_bfqg(pblkg) : NULL;
}

struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
{
	struct bfq_entity *group_entity = bfqq->entity.parent;

	return group_entity ? container_of(group_entity, struct bfq_group,
					   entity) :
			      bfqq->bfqd->root_group;
}

/*
 * The following two functions handle get and put of a bfq_group by
 * wrapping the related blk-cgroup hooks.
 */

static void bfqg_get(struct bfq_group *bfqg)
{
	bfqg->ref++;
}

static void bfqg_put(struct bfq_group *bfqg)
{
	bfqg->ref--;

	if (bfqg->ref == 0)
		kfree(bfqg);
}

static void bfqg_and_blkg_get(struct bfq_group *bfqg)
{
	/* see comments in bfq_bic_update_cgroup for why refcounting bfqg */
	bfqg_get(bfqg);

	blkg_get(bfqg_to_blkg(bfqg));
}

void bfqg_and_blkg_put(struct bfq_group *bfqg)
{
	blkg_put(bfqg_to_blkg(bfqg));

	bfqg_put(bfqg);
}

void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq)
{
	struct bfq_group *bfqg = blkg_to_bfqg(rq->bio->bi_blkg);

	if (!bfqg)
		return;

	blkg_rwstat_add(&bfqg->stats.bytes, rq->cmd_flags, blk_rq_bytes(rq));
	blkg_rwstat_add(&bfqg->stats.ios, rq->cmd_flags, 1);
}

/* @stats = 0 */
static void bfqg_stats_reset(struct bfqg_stats *stats)
{
#ifdef CONFIG_BFQ_CGROUP_DEBUG
	/* queued stats shouldn't be cleared */
	blkg_rwstat_reset(&stats->merged);
	blkg_rwstat_reset(&stats->service_time);
	blkg_rwstat_reset(&stats->wait_time);
	bfq_stat_reset(&stats->time);
	bfq_stat_reset(&stats->avg_queue_size_sum);
	bfq_stat_reset(&stats->avg_queue_size_samples);
	bfq_stat_reset(&stats->dequeue);
	bfq_stat_reset(&stats->group_wait_time);
	bfq_stat_reset(&stats->idle_time);
	bfq_stat_reset(&stats->empty_time);
#endif
}

/* @to += @from */
static void bfqg_stats_add_aux(struct bfqg_stats *to, struct bfqg_stats *from)
{
	if (!to || !from)
		return;

#ifdef CONFIG_BFQ_CGROUP_DEBUG
	/* queued stats shouldn't be cleared */
	blkg_rwstat_add_aux(&to->merged, &from->merged);
	blkg_rwstat_add_aux(&to->service_time, &from->service_time);
	blkg_rwstat_add_aux(&to->wait_time, &from->wait_time);
	bfq_stat_add_aux(&from->time, &from->time);
	bfq_stat_add_aux(&to->avg_queue_size_sum, &from->avg_queue_size_sum);
	bfq_stat_add_aux(&to->avg_queue_size_samples,
			  &from->avg_queue_size_samples);
	bfq_stat_add_aux(&to->dequeue, &from->dequeue);
	bfq_stat_add_aux(&to->group_wait_time, &from->group_wait_time);
	bfq_stat_add_aux(&to->idle_time, &from->idle_time);
	bfq_stat_add_aux(&to->empty_time, &from->empty_time);
#endif
}

/*
 * Transfer @bfqg's stats to its parent's aux counts so that the ancestors'
 * recursive stats can still account for the amount used by this bfqg after
 * it's gone.
 */
static void bfqg_stats_xfer_dead(struct bfq_group *bfqg)
{
	struct bfq_group *parent;

	if (!bfqg) /* root_group */
		return;

	parent = bfqg_parent(bfqg);

	lockdep_assert_held(&bfqg_to_blkg(bfqg)->q->queue_lock);

	if (unlikely(!parent))
		return;

	bfqg_stats_add_aux(&parent->stats, &bfqg->stats);
	bfqg_stats_reset(&bfqg->stats);
}

void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg)
{
	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);

	entity->weight = entity->new_weight;
	entity->orig_weight = entity->new_weight;
	if (bfqq) {
		bfqq->ioprio = bfqq->new_ioprio;
		bfqq->ioprio_class = bfqq->new_ioprio_class;
		/*
		 * Make sure that bfqg and its associated blkg do not
		 * disappear before entity.
		 */
		bfqg_and_blkg_get(bfqg);
	}
	entity->parent = bfqg->my_entity; /* NULL for root group */
	entity->sched_data = &bfqg->sched_data;
}

static void bfqg_stats_exit(struct bfqg_stats *stats)
{
	blkg_rwstat_exit(&stats->bytes);
	blkg_rwstat_exit(&stats->ios);
#ifdef CONFIG_BFQ_CGROUP_DEBUG
	blkg_rwstat_exit(&stats->merged);
	blkg_rwstat_exit(&stats->service_time);
	blkg_rwstat_exit(&stats->wait_time);
	blkg_rwstat_exit(&stats->queued);
	bfq_stat_exit(&stats->time);
	bfq_stat_exit(&stats->avg_queue_size_sum);
	bfq_stat_exit(&stats->avg_queue_size_samples);
	bfq_stat_exit(&stats->dequeue);
	bfq_stat_exit(&stats->group_wait_time);
	bfq_stat_exit(&stats->idle_time);
	bfq_stat_exit(&stats->empty_time);
#endif
}

static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
{
	if (blkg_rwstat_init(&stats->bytes, gfp) ||
	    blkg_rwstat_init(&stats->ios, gfp))
		goto error;

#ifdef CONFIG_BFQ_CGROUP_DEBUG
	if (blkg_rwstat_init(&stats->merged, gfp) ||
	    blkg_rwstat_init(&stats->service_time, gfp) ||
	    blkg_rwstat_init(&stats->wait_time, gfp) ||
	    blkg_rwstat_init(&stats->queued, gfp) ||
	    bfq_stat_init(&stats->time, gfp) ||
	    bfq_stat_init(&stats->avg_queue_size_sum, gfp) ||
	    bfq_stat_init(&stats->avg_queue_size_samples, gfp) ||
	    bfq_stat_init(&stats->dequeue, gfp) ||
	    bfq_stat_init(&stats->group_wait_time, gfp) ||
	    bfq_stat_init(&stats->idle_time, gfp) ||
	    bfq_stat_init(&stats->empty_time, gfp))
		goto error;
#endif

	return 0;

error:
	bfqg_stats_exit(stats);
	return -ENOMEM;
}

static struct bfq_group_data *cpd_to_bfqgd(struct blkcg_policy_data *cpd)
{
	return cpd ? container_of(cpd, struct bfq_group_data, pd) : NULL;
}

static struct bfq_group_data *blkcg_to_bfqgd(struct blkcg *blkcg)
{
	return cpd_to_bfqgd(blkcg_to_cpd(blkcg, &blkcg_policy_bfq));
}

static struct blkcg_policy_data *bfq_cpd_alloc(gfp_t gfp)
{
	struct bfq_group_data *bgd;

	bgd = kzalloc(sizeof(*bgd), gfp);
	if (!bgd)
		return NULL;
	return &bgd->pd;
}

static void bfq_cpd_init(struct blkcg_policy_data *cpd)
{
	struct bfq_group_data *d = cpd_to_bfqgd(cpd);

	d->weight = cgroup_subsys_on_dfl(io_cgrp_subsys) ?
		CGROUP_WEIGHT_DFL : BFQ_WEIGHT_LEGACY_DFL;
}

static void bfq_cpd_free(struct blkcg_policy_data *cpd)
{
	kfree(cpd_to_bfqgd(cpd));
}

static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, struct request_queue *q,
					     struct blkcg *blkcg)
{
	struct bfq_group *bfqg;

	bfqg = kzalloc_node(sizeof(*bfqg), gfp, q->node);
	if (!bfqg)
		return NULL;

	if (bfqg_stats_init(&bfqg->stats, gfp)) {
		kfree(bfqg);
		return NULL;
	}

	/* see comments in bfq_bic_update_cgroup for why refcounting */
	bfqg_get(bfqg);
	return &bfqg->pd;
}

static void bfq_pd_init(struct blkg_policy_data *pd)
{
	struct blkcg_gq *blkg = pd_to_blkg(pd);
	struct bfq_group *bfqg = blkg_to_bfqg(blkg);
	struct bfq_data *bfqd = blkg->q->elevator->elevator_data;
	struct bfq_entity *entity = &bfqg->entity;
	struct bfq_group_data *d = blkcg_to_bfqgd(blkg->blkcg);

	entity->orig_weight = entity->weight = entity->new_weight = d->weight;
	entity->my_sched_data = &bfqg->sched_data;
	entity->last_bfqq_created = NULL;

	bfqg->my_entity = entity; /*
				   * the root_group's will be set to NULL
				   * in bfq_init_queue()
				   */
	bfqg->bfqd = bfqd;
	bfqg->active_entities = 0;
	bfqg->rq_pos_tree = RB_ROOT;
}

static void bfq_pd_free(struct blkg_policy_data *pd)
{
	struct bfq_group *bfqg = pd_to_bfqg(pd);

	bfqg_stats_exit(&bfqg->stats);
	bfqg_put(bfqg);
}

static void bfq_pd_reset_stats(struct blkg_policy_data *pd)
{
	struct bfq_group *bfqg = pd_to_bfqg(pd);

	bfqg_stats_reset(&bfqg->stats);
}

static void bfq_group_set_parent(struct bfq_group *bfqg,
					struct bfq_group *parent)
{
	struct bfq_entity *entity;

	entity = &bfqg->entity;
	entity->parent = parent->my_entity;
	entity->sched_data = &parent->sched_data;
}

static struct bfq_group *bfq_lookup_bfqg(struct bfq_data *bfqd,
					 struct blkcg *blkcg)
{
	struct blkcg_gq *blkg;

	blkg = blkg_lookup(blkcg, bfqd->queue);
	if (likely(blkg))
		return blkg_to_bfqg(blkg);
	return NULL;
}

struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
				     struct blkcg *blkcg)
{
	struct bfq_group *bfqg, *parent;
	struct bfq_entity *entity;

	bfqg = bfq_lookup_bfqg(bfqd, blkcg);

	if (unlikely(!bfqg))
		return NULL;

	/*
	 * Update chain of bfq_groups as we might be handling a leaf group
	 * which, along with some of its relatives, has not been hooked yet
	 * to the private hierarchy of BFQ.
	 */
	entity = &bfqg->entity;
	for_each_entity(entity) {
		struct bfq_group *curr_bfqg = container_of(entity,
						struct bfq_group, entity);
		if (curr_bfqg != bfqd->root_group) {
			parent = bfqg_parent(curr_bfqg);
			if (!parent)
				parent = bfqd->root_group;
			bfq_group_set_parent(curr_bfqg, parent);
		}
	}

	return bfqg;
}

/**
 * bfq_bfqq_move - migrate @bfqq to @bfqg.
 * @bfqd: queue descriptor.
 * @bfqq: the queue to move.
 * @bfqg: the group to move to.
 *
 * Move @bfqq to @bfqg, deactivating it from its old group and reactivating
 * it on the new one.  Avoid putting the entity on the old group idle tree.
 *
 * Must be called under the scheduler lock, to make sure that the blkg
 * owning @bfqg does not disappear (see comments in
 * bfq_bic_update_cgroup on guaranteeing the consistency of blkg
 * objects).
 */
void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
		   struct bfq_group *bfqg)
{
	struct bfq_entity *entity = &bfqq->entity;
	struct bfq_group *old_parent = bfqq_group(bfqq);

	/*
	 * No point to move bfqq to the same group, which can happen when
	 * root group is offlined
	 */
	if (old_parent == bfqg)
		return;

	/*
	 * oom_bfqq is not allowed to move, oom_bfqq will hold ref to root_group
	 * until elevator exit.
	 */
	if (bfqq == &bfqd->oom_bfqq)
		return;
	/*
	 * Get extra reference to prevent bfqq from being freed in
	 * next possible expire or deactivate.
	 */
	bfqq->ref++;

	/* If bfqq is empty, then bfq_bfqq_expire also invokes
	 * bfq_del_bfqq_busy, thereby removing bfqq and its entity
	 * from data structures related to current group. Otherwise we
	 * need to remove bfqq explicitly with bfq_deactivate_bfqq, as
	 * we do below.
	 */
	if (bfqq == bfqd->in_service_queue)
		bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
				false, BFQQE_PREEMPTED);

	if (bfq_bfqq_busy(bfqq))
		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
	else if (entity->on_st_or_in_serv)
		bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
	bfqg_and_blkg_put(old_parent);

	if (entity->parent &&
	    entity->parent->last_bfqq_created == bfqq)
		entity->parent->last_bfqq_created = NULL;
	else if (bfqd->last_bfqq_created == bfqq)
		bfqd->last_bfqq_created = NULL;

	entity->parent = bfqg->my_entity;
	entity->sched_data = &bfqg->sched_data;
	/* pin down bfqg and its associated blkg  */
	bfqg_and_blkg_get(bfqg);

	if (bfq_bfqq_busy(bfqq)) {
		if (unlikely(!bfqd->nonrot_with_queueing))
			bfq_pos_tree_add_move(bfqd, bfqq);
		bfq_activate_bfqq(bfqd, bfqq);
	}

	if (!bfqd->in_service_queue && !bfqd->rq_in_driver)
		bfq_schedule_dispatch(bfqd);
	/* release extra ref taken above, bfqq may happen to be freed now */
	bfq_put_queue(bfqq);
}

/**
 * __bfq_bic_change_cgroup - move @bic to @cgroup.
 * @bfqd: the queue descriptor.
 * @bic: the bic to move.
 * @blkcg: the blk-cgroup to move to.
 *
 * Move bic to blkcg, assuming that bfqd->lock is held; which makes
 * sure that the reference to cgroup is valid across the call (see
 * comments in bfq_bic_update_cgroup on this issue)
 *
 * NOTE: an alternative approach might have been to store the current
 * cgroup in bfqq and getting a reference to it, reducing the lookup
 * time here, at the price of slightly more complex code.
 */
static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
						struct bfq_io_cq *bic,
						struct blkcg *blkcg)
{
	struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0);
	struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1);
	struct bfq_group *bfqg;
	struct bfq_entity *entity;

	bfqg = bfq_find_set_group(bfqd, blkcg);

	if (unlikely(!bfqg))
		bfqg = bfqd->root_group;

	if (async_bfqq) {
		entity = &async_bfqq->entity;

		if (entity->sched_data != &bfqg->sched_data) {
			bic_set_bfqq(bic, NULL, 0);
			bfq_release_process_ref(bfqd, async_bfqq);
		}
	}

	if (sync_bfqq) {
		entity = &sync_bfqq->entity;
		if (entity->sched_data != &bfqg->sched_data)
			bfq_bfqq_move(bfqd, sync_bfqq, bfqg);
	}

	return bfqg;
}

void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio)
{
	struct bfq_data *bfqd = bic_to_bfqd(bic);
	struct bfq_group *bfqg = NULL;
	uint64_t serial_nr;

	rcu_read_lock();
	serial_nr = __bio_blkcg(bio)->css.serial_nr;

	/*
	 * Check whether blkcg has changed.  The condition may trigger
	 * spuriously on a newly created cic but there's no harm.
	 */
	if (unlikely(!bfqd) || likely(bic->blkcg_serial_nr == serial_nr))
		goto out;

	bfqg = __bfq_bic_change_cgroup(bfqd, bic, __bio_blkcg(bio));
	/*
	 * Update blkg_path for bfq_log_* functions. We cache this
	 * path, and update it here, for the following
	 * reasons. Operations on blkg objects in blk-cgroup are
	 * protected with the request_queue lock, and not with the
	 * lock that protects the instances of this scheduler
	 * (bfqd->lock). This exposes BFQ to the following sort of
	 * race.
	 *
	 * The blkg_lookup performed in bfq_get_queue, protected
	 * through rcu, may happen to return the address of a copy of
	 * the original blkg. If this is the case, then the
	 * bfqg_and_blkg_get performed in bfq_get_queue, to pin down
	 * the blkg, is useless: it does not prevent blk-cgroup code
	 * from destroying both the original blkg and all objects
	 * directly or indirectly referred by the copy of the
	 * blkg.
	 *
	 * On the bright side, destroy operations on a blkg invoke, as
	 * a first step, hooks of the scheduler associated with the
	 * blkg. And these hooks are executed with bfqd->lock held for
	 * BFQ. As a consequence, for any blkg associated with the
	 * request queue this instance of the scheduler is attached
	 * to, we are guaranteed that such a blkg is not destroyed, and
	 * that all the pointers it contains are consistent, while we
	 * are holding bfqd->lock. A blkg_lookup performed with
	 * bfqd->lock held then returns a fully consistent blkg, which
	 * remains consistent until this lock is held.
	 *
	 * Thanks to the last fact, and to the fact that: (1) bfqg has
	 * been obtained through a blkg_lookup in the above
	 * assignment, and (2) bfqd->lock is being held, here we can
	 * safely use the policy data for the involved blkg (i.e., the
	 * field bfqg->pd) to get to the blkg associated with bfqg,
	 * and then we can safely use any field of blkg. After we
	 * release bfqd->lock, even just getting blkg through this
	 * bfqg may cause dangling references to be traversed, as
	 * bfqg->pd may not exist any more.
	 *
	 * In view of the above facts, here we cache, in the bfqg, any
	 * blkg data we may need for this bic, and for its associated
	 * bfq_queue. As of now, we need to cache only the path of the
	 * blkg, which is used in the bfq_log_* functions.
	 *
	 * Finally, note that bfqg itself needs to be protected from
	 * destruction on the blkg_free of the original blkg (which
	 * invokes bfq_pd_free). We use an additional private
	 * refcounter for bfqg, to let it disappear only after no
	 * bfq_queue refers to it any longer.
	 */
	blkg_path(bfqg_to_blkg(bfqg), bfqg->blkg_path, sizeof(bfqg->blkg_path));
	bic->blkcg_serial_nr = serial_nr;
out:
	rcu_read_unlock();
}

/**
 * bfq_flush_idle_tree - deactivate any entity on the idle tree of @st.
 * @st: the service tree being flushed.
 */
static void bfq_flush_idle_tree(struct bfq_service_tree *st)
{
	struct bfq_entity *entity = st->first_idle;

	for (; entity ; entity = st->first_idle)
		__bfq_deactivate_entity(entity, false);
}

/**
 * bfq_reparent_leaf_entity - move leaf entity to the root_group.
 * @bfqd: the device data structure with the root group.
 * @entity: the entity to move, if entity is a leaf; or the parent entity
 *	    of an active leaf entity to move, if entity is not a leaf.
 */
static void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
				     struct bfq_entity *entity,
				     int ioprio_class)
{
	struct bfq_queue *bfqq;
	struct bfq_entity *child_entity = entity;

	while (child_entity->my_sched_data) { /* leaf not reached yet */
		struct bfq_sched_data *child_sd = child_entity->my_sched_data;
		struct bfq_service_tree *child_st = child_sd->service_tree +
			ioprio_class;
		struct rb_root *child_active = &child_st->active;

		child_entity = bfq_entity_of(rb_first(child_active));

		if (!child_entity)
			child_entity = child_sd->in_service_entity;
	}

	bfqq = bfq_entity_to_bfqq(child_entity);
	bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);
}

/**
 * bfq_reparent_active_queues - move to the root group all active queues.
 * @bfqd: the device data structure with the root group.
 * @bfqg: the group to move from.
 * @st: the service tree to start the search from.
 */
static void bfq_reparent_active_queues(struct bfq_data *bfqd,
				       struct bfq_group *bfqg,
				       struct bfq_service_tree *st,
				       int ioprio_class)
{
	struct rb_root *active = &st->active;
	struct bfq_entity *entity;

	while ((entity = bfq_entity_of(rb_first(active))))
		bfq_reparent_leaf_entity(bfqd, entity, ioprio_class);

	if (bfqg->sched_data.in_service_entity)
		bfq_reparent_leaf_entity(bfqd,
					 bfqg->sched_data.in_service_entity,
					 ioprio_class);
}

/**
 * bfq_pd_offline - deactivate the entity associated with @pd,
 *		    and reparent its children entities.
 * @pd: descriptor of the policy going offline.
 *
 * blkio already grabs the queue_lock for us, so no need to use
 * RCU-based magic
 */
static void bfq_pd_offline(struct blkg_policy_data *pd)
{
	struct bfq_service_tree *st;
	struct bfq_group *bfqg = pd_to_bfqg(pd);
	struct bfq_data *bfqd = bfqg->bfqd;
	struct bfq_entity *entity = bfqg->my_entity;
	unsigned long flags;
	int i;

	spin_lock_irqsave(&bfqd->lock, flags);

	if (!entity) /* root group */
		goto put_async_queues;

	/*
	 * Empty all service_trees belonging to this group before
	 * deactivating the group itself.
	 */
	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) {
		st = bfqg->sched_data.service_tree + i;

		/*
		 * It may happen that some queues are still active
		 * (busy) upon group destruction (if the corresponding
		 * processes have been forced to terminate). We move
		 * all the leaf entities corresponding to these queues
		 * to the root_group.
		 * Also, it may happen that the group has an entity
		 * in service, which is disconnected from the active
		 * tree: it must be moved, too.
		 * There is no need to put the sync queues, as the
		 * scheduler has taken no reference.
		 */
		bfq_reparent_active_queues(bfqd, bfqg, st, i);

		/*
		 * The idle tree may still contain bfq_queues
		 * belonging to exited task because they never
		 * migrated to a different cgroup from the one being
		 * destroyed now. In addition, even
		 * bfq_reparent_active_queues() may happen to add some
		 * entities to the idle tree. It happens if, in some
		 * of the calls to bfq_bfqq_move() performed by
		 * bfq_reparent_active_queues(), the queue to move is
		 * empty and gets expired.
		 */
		bfq_flush_idle_tree(st);
	}

	__bfq_deactivate_entity(entity, false);

put_async_queues:
	bfq_put_async_queues(bfqd, bfqg);

	spin_unlock_irqrestore(&bfqd->lock, flags);
	/*
	 * @blkg is going offline and will be ignored by
	 * blkg_[rw]stat_recursive_sum().  Transfer stats to the parent so
	 * that they don't get lost.  If IOs complete after this point, the
	 * stats for them will be lost.  Oh well...
	 */
	bfqg_stats_xfer_dead(bfqg);
}

void bfq_end_wr_async(struct bfq_data *bfqd)
{
	struct blkcg_gq *blkg;

	list_for_each_entry(blkg, &bfqd->queue->blkg_list, q_node) {
		struct bfq_group *bfqg = blkg_to_bfqg(blkg);

		bfq_end_wr_async_queues(bfqd, bfqg);
	}
	bfq_end_wr_async_queues(bfqd, bfqd->root_group);
}

static int bfq_io_show_weight_legacy(struct seq_file *sf, void *v)
{
	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
	struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
	unsigned int val = 0;

	if (bfqgd)
		val = bfqgd->weight;

	seq_printf(sf, "%u\n", val);

	return 0;
}

static u64 bfqg_prfill_weight_device(struct seq_file *sf,
				     struct blkg_policy_data *pd, int off)
{
	struct bfq_group *bfqg = pd_to_bfqg(pd);

	if (!bfqg->entity.dev_weight)
		return 0;
	return __blkg_prfill_u64(sf, pd, bfqg->entity.dev_weight);
}

static int bfq_io_show_weight(struct seq_file *sf, void *v)
{
	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
	struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);

	seq_printf(sf, "default %u\n", bfqgd->weight);
	blkcg_print_blkgs(sf, blkcg, bfqg_prfill_weight_device,
			  &blkcg_policy_bfq, 0, false);
	return 0;
}

static void bfq_group_set_weight(struct bfq_group *bfqg, u64 weight, u64 dev_weight)
{
	weight = dev_weight ?: weight;

	bfqg->entity.dev_weight = dev_weight;
	/*
	 * Setting the prio_changed flag of the entity
	 * to 1 with new_weight == weight would re-set
	 * the value of the weight to its ioprio mapping.
	 * Set the flag only if necessary.
	 */
	if ((unsigned short)weight != bfqg->entity.new_weight) {
		bfqg->entity.new_weight = (unsigned short)weight;
		/*
		 * Make sure that the above new value has been
		 * stored in bfqg->entity.new_weight before
		 * setting the prio_changed flag. In fact,
		 * this flag may be read asynchronously (in
		 * critical sections protected by a different
		 * lock than that held here), and finding this
		 * flag set may cause the execution of the code
		 * for updating parameters whose value may
		 * depend also on bfqg->entity.new_weight (in
		 * __bfq_entity_update_weight_prio).
		 * This barrier makes sure that the new value
		 * of bfqg->entity.new_weight is correctly
		 * seen in that code.
		 */
		smp_wmb();
		bfqg->entity.prio_changed = 1;
	}
}

static int bfq_io_set_weight_legacy(struct cgroup_subsys_state *css,
				    struct cftype *cftype,
				    u64 val)
{
	struct blkcg *blkcg = css_to_blkcg(css);
	struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
	struct blkcg_gq *blkg;
	int ret = -ERANGE;

	if (val < BFQ_MIN_WEIGHT || val > BFQ_MAX_WEIGHT)
		return ret;

	ret = 0;
	spin_lock_irq(&blkcg->lock);
	bfqgd->weight = (unsigned short)val;
	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
		struct bfq_group *bfqg = blkg_to_bfqg(blkg);

		if (bfqg)
			bfq_group_set_weight(bfqg, val, 0);
	}
	spin_unlock_irq(&blkcg->lock);

	return ret;
}

static ssize_t bfq_io_set_device_weight(struct kernfs_open_file *of,
					char *buf, size_t nbytes,
					loff_t off)
{
	int ret;
	struct blkg_conf_ctx ctx;
	struct blkcg *blkcg = css_to_blkcg(of_css(of));
	struct bfq_group *bfqg;
	u64 v;

	ret = blkg_conf_prep(blkcg, &blkcg_policy_bfq, buf, &ctx);
	if (ret)
		return ret;

	if (sscanf(ctx.body, "%llu", &v) == 1) {
		/* require "default" on dfl */
		ret = -ERANGE;
		if (!v)
			goto out;
	} else if (!strcmp(strim(ctx.body), "default")) {
		v = 0;
	} else {
		ret = -EINVAL;
		goto out;
	}

	bfqg = blkg_to_bfqg(ctx.blkg);

	ret = -ERANGE;
	if (!v || (v >= BFQ_MIN_WEIGHT && v <= BFQ_MAX_WEIGHT)) {
		bfq_group_set_weight(bfqg, bfqg->entity.weight, v);
		ret = 0;
	}
out:
	blkg_conf_finish(&ctx);
	return ret ?: nbytes;
}

static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
				 char *buf, size_t nbytes,
				 loff_t off)
{
	char *endp;
	int ret;
	u64 v;

	buf = strim(buf);

	/* "WEIGHT" or "default WEIGHT" sets the default weight */
	v = simple_strtoull(buf, &endp, 0);
	if (*endp == '\0' || sscanf(buf, "default %llu", &v) == 1) {
		ret = bfq_io_set_weight_legacy(of_css(of), NULL, v);
		return ret ?: nbytes;
	}

	return bfq_io_set_device_weight(of, buf, nbytes, off);
}

static int bfqg_print_rwstat(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat,
			  &blkcg_policy_bfq, seq_cft(sf)->private, true);
	return 0;
}

static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf,
					struct blkg_policy_data *pd, int off)
{
	struct blkg_rwstat_sample sum;

	blkg_rwstat_recursive_sum(pd_to_blkg(pd), &blkcg_policy_bfq, off, &sum);
	return __blkg_prfill_rwstat(sf, pd, &sum);
}

static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq,
			  seq_cft(sf)->private, true);
	return 0;
}

#ifdef CONFIG_BFQ_CGROUP_DEBUG
static int bfqg_print_stat(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
			  &blkcg_policy_bfq, seq_cft(sf)->private, false);
	return 0;
}

static u64 bfqg_prfill_stat_recursive(struct seq_file *sf,
				      struct blkg_policy_data *pd, int off)
{
	struct blkcg_gq *blkg = pd_to_blkg(pd);
	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 bfq_stat *stat;

		if (!pos_blkg->online)
			continue;

		stat = (void *)blkg_to_pd(pos_blkg, &blkcg_policy_bfq) + off;
		sum += bfq_stat_read(stat) + atomic64_read(&stat->aux_cnt);
	}
	rcu_read_unlock();

	return __blkg_prfill_u64(sf, pd, sum);
}

static int bfqg_print_stat_recursive(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  bfqg_prfill_stat_recursive, &blkcg_policy_bfq,
			  seq_cft(sf)->private, false);
	return 0;
}

static u64 bfqg_prfill_sectors(struct seq_file *sf, struct blkg_policy_data *pd,
			       int off)
{
	struct bfq_group *bfqg = blkg_to_bfqg(pd->blkg);
	u64 sum = blkg_rwstat_total(&bfqg->stats.bytes);

	return __blkg_prfill_u64(sf, pd, sum >> 9);
}

static int bfqg_print_stat_sectors(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  bfqg_prfill_sectors, &blkcg_policy_bfq, 0, false);
	return 0;
}

static u64 bfqg_prfill_sectors_recursive(struct seq_file *sf,
					 struct blkg_policy_data *pd, int off)
{
	struct blkg_rwstat_sample tmp;

	blkg_rwstat_recursive_sum(pd->blkg, &blkcg_policy_bfq,
			offsetof(struct bfq_group, stats.bytes), &tmp);

	return __blkg_prfill_u64(sf, pd,
		(tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]) >> 9);
}

static int bfqg_print_stat_sectors_recursive(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  bfqg_prfill_sectors_recursive, &blkcg_policy_bfq, 0,
			  false);
	return 0;
}

static u64 bfqg_prfill_avg_queue_size(struct seq_file *sf,
				      struct blkg_policy_data *pd, int off)
{
	struct bfq_group *bfqg = pd_to_bfqg(pd);
	u64 samples = bfq_stat_read(&bfqg->stats.avg_queue_size_samples);
	u64 v = 0;

	if (samples) {
		v = bfq_stat_read(&bfqg->stats.avg_queue_size_sum);
		v = div64_u64(v, samples);
	}
	__blkg_prfill_u64(sf, pd, v);
	return 0;
}

/* print avg_queue_size */
static int bfqg_print_avg_queue_size(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  bfqg_prfill_avg_queue_size, &blkcg_policy_bfq,
			  0, false);
	return 0;
}
#endif /* CONFIG_BFQ_CGROUP_DEBUG */

struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
{
	int ret;

	ret = blkcg_activate_policy(bfqd->queue, &blkcg_policy_bfq);
	if (ret)
		return NULL;

	return blkg_to_bfqg(bfqd->queue->root_blkg);
}

struct blkcg_policy blkcg_policy_bfq = {
	.dfl_cftypes		= bfq_blkg_files,
	.legacy_cftypes		= bfq_blkcg_legacy_files,

	.cpd_alloc_fn		= bfq_cpd_alloc,
	.cpd_init_fn		= bfq_cpd_init,
	.cpd_bind_fn	        = bfq_cpd_init,
	.cpd_free_fn		= bfq_cpd_free,

	.pd_alloc_fn		= bfq_pd_alloc,
	.pd_init_fn		= bfq_pd_init,
	.pd_offline_fn		= bfq_pd_offline,
	.pd_free_fn		= bfq_pd_free,
	.pd_reset_stats_fn	= bfq_pd_reset_stats,
};

struct cftype bfq_blkcg_legacy_files[] = {
	{
		.name = "bfq.weight",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = bfq_io_show_weight_legacy,
		.write_u64 = bfq_io_set_weight_legacy,
	},
	{
		.name = "bfq.weight_device",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = bfq_io_show_weight,
		.write = bfq_io_set_weight,
	},

	/* statistics, covers only the tasks in the bfqg */
	{
		.name = "bfq.io_service_bytes",
		.private = offsetof(struct bfq_group, stats.bytes),
		.seq_show = bfqg_print_rwstat,
	},
	{
		.name = "bfq.io_serviced",
		.private = offsetof(struct bfq_group, stats.ios),
		.seq_show = bfqg_print_rwstat,
	},
#ifdef CONFIG_BFQ_CGROUP_DEBUG
	{
		.name = "bfq.time",
		.private = offsetof(struct bfq_group, stats.time),
		.seq_show = bfqg_print_stat,
	},
	{
		.name = "bfq.sectors",
		.seq_show = bfqg_print_stat_sectors,
	},
	{
		.name = "bfq.io_service_time",
		.private = offsetof(struct bfq_group, stats.service_time),
		.seq_show = bfqg_print_rwstat,
	},
	{
		.name = "bfq.io_wait_time",
		.private = offsetof(struct bfq_group, stats.wait_time),
		.seq_show = bfqg_print_rwstat,
	},
	{
		.name = "bfq.io_merged",
		.private = offsetof(struct bfq_group, stats.merged),
		.seq_show = bfqg_print_rwstat,
	},
	{
		.name = "bfq.io_queued",
		.private = offsetof(struct bfq_group, stats.queued),
		.seq_show = bfqg_print_rwstat,
	},
#endif /* CONFIG_BFQ_CGROUP_DEBUG */

	/* the same statistics which cover the bfqg and its descendants */
	{
		.name = "bfq.io_service_bytes_recursive",
		.private = offsetof(struct bfq_group, stats.bytes),
		.seq_show = bfqg_print_rwstat_recursive,
	},
	{
		.name = "bfq.io_serviced_recursive",
		.private = offsetof(struct bfq_group, stats.ios),
		.seq_show = bfqg_print_rwstat_recursive,
	},
#ifdef CONFIG_BFQ_CGROUP_DEBUG
	{
		.name = "bfq.time_recursive",
		.private = offsetof(struct bfq_group, stats.time),
		.seq_show = bfqg_print_stat_recursive,
	},
	{
		.name = "bfq.sectors_recursive",
		.seq_show = bfqg_print_stat_sectors_recursive,
	},
	{
		.name = "bfq.io_service_time_recursive",
		.private = offsetof(struct bfq_group, stats.service_time),
		.seq_show = bfqg_print_rwstat_recursive,
	},
	{
		.name = "bfq.io_wait_time_recursive",
		.private = offsetof(struct bfq_group, stats.wait_time),
		.seq_show = bfqg_print_rwstat_recursive,
	},
	{
		.name = "bfq.io_merged_recursive",
		.private = offsetof(struct bfq_group, stats.merged),
		.seq_show = bfqg_print_rwstat_recursive,
	},
	{
		.name = "bfq.io_queued_recursive",
		.private = offsetof(struct bfq_group, stats.queued),
		.seq_show = bfqg_print_rwstat_recursive,
	},
	{
		.name = "bfq.avg_queue_size",
		.seq_show = bfqg_print_avg_queue_size,
	},
	{
		.name = "bfq.group_wait_time",
		.private = offsetof(struct bfq_group, stats.group_wait_time),
		.seq_show = bfqg_print_stat,
	},
	{
		.name = "bfq.idle_time",
		.private = offsetof(struct bfq_group, stats.idle_time),
		.seq_show = bfqg_print_stat,
	},
	{
		.name = "bfq.empty_time",
		.private = offsetof(struct bfq_group, stats.empty_time),
		.seq_show = bfqg_print_stat,
	},
	{
		.name = "bfq.dequeue",
		.private = offsetof(struct bfq_group, stats.dequeue),
		.seq_show = bfqg_print_stat,
	},
#endif	/* CONFIG_BFQ_CGROUP_DEBUG */
	{ }	/* terminate */
};

struct cftype bfq_blkg_files[] = {
	{
		.name = "bfq.weight",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = bfq_io_show_weight,
		.write = bfq_io_set_weight,
	},
	{} /* terminate */
};

#else	/* CONFIG_BFQ_GROUP_IOSCHED */

void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
		   struct bfq_group *bfqg) {}

void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg)
{
	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);

	entity->weight = entity->new_weight;
	entity->orig_weight = entity->new_weight;
	if (bfqq) {
		bfqq->ioprio = bfqq->new_ioprio;
		bfqq->ioprio_class = bfqq->new_ioprio_class;
	}
	entity->sched_data = &bfqg->sched_data;
}

void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) {}

void bfq_end_wr_async(struct bfq_data *bfqd)
{
	bfq_end_wr_async_queues(bfqd, bfqd->root_group);
}

struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, struct blkcg *blkcg)
{
	return bfqd->root_group;
}

struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
{
	return bfqq->bfqd->root_group;
}

void bfqg_and_blkg_get(struct bfq_group *bfqg) {}

void bfqg_and_blkg_put(struct bfq_group *bfqg) {}

struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
{
	struct bfq_group *bfqg;
	int i;

	bfqg = kmalloc_node(sizeof(*bfqg), GFP_KERNEL | __GFP_ZERO, node);
	if (!bfqg)
		return NULL;

	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
		bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;

	return bfqg;
}
#endif	/* CONFIG_BFQ_GROUP_IOSCHED */