summaryrefslogtreecommitdiff
path: root/fs/io-wq.c
blob: 824623bcf1a53f78e67370a947e063c4245c8c13 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Basic worker thread pool for io_uring
 *
 * Copyright (C) 2019 Jens Axboe
 *
 */
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/sched/signal.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/rculist_nulls.h>
#include <linux/cpu.h>
#include <linux/task_work.h>
#include <linux/audit.h>
#include <uapi/linux/io_uring.h>

#include "io-wq.h"

#define WORKER_IDLE_TIMEOUT	(5 * HZ)

enum {
	IO_WORKER_F_UP		= 1,	/* up and active */
	IO_WORKER_F_RUNNING	= 2,	/* account as running */
	IO_WORKER_F_FREE	= 4,	/* worker on free list */
	IO_WORKER_F_BOUND	= 8,	/* is doing bounded work */
};

enum {
	IO_WQ_BIT_EXIT		= 0,	/* wq exiting */
};

enum {
	IO_ACCT_STALLED_BIT	= 0,	/* stalled on hash */
};

/*
 * One for each thread in a wqe pool
 */
struct io_worker {
	refcount_t ref;
	unsigned flags;
	struct hlist_nulls_node nulls_node;
	struct list_head all_list;
	struct task_struct *task;
	struct io_wqe *wqe;

	struct io_wq_work *cur_work;
	struct io_wq_work *next_work;
	raw_spinlock_t lock;

	struct completion ref_done;

	unsigned long create_state;
	struct callback_head create_work;
	int create_index;

	union {
		struct rcu_head rcu;
		struct work_struct work;
	};
};

#if BITS_PER_LONG == 64
#define IO_WQ_HASH_ORDER	6
#else
#define IO_WQ_HASH_ORDER	5
#endif

#define IO_WQ_NR_HASH_BUCKETS	(1u << IO_WQ_HASH_ORDER)

struct io_wqe_acct {
	unsigned nr_workers;
	unsigned max_workers;
	int index;
	atomic_t nr_running;
	raw_spinlock_t lock;
	struct io_wq_work_list work_list;
	unsigned long flags;
};

enum {
	IO_WQ_ACCT_BOUND,
	IO_WQ_ACCT_UNBOUND,
	IO_WQ_ACCT_NR,
};

/*
 * Per-node worker thread pool
 */
struct io_wqe {
	raw_spinlock_t lock;
	struct io_wqe_acct acct[IO_WQ_ACCT_NR];

	int node;

	struct hlist_nulls_head free_list;
	struct list_head all_list;

	struct wait_queue_entry wait;

	struct io_wq *wq;
	struct io_wq_work *hash_tail[IO_WQ_NR_HASH_BUCKETS];

	cpumask_var_t cpu_mask;
};

/*
 * Per io_wq state
  */
struct io_wq {
	unsigned long state;

	free_work_fn *free_work;
	io_wq_work_fn *do_work;

	struct io_wq_hash *hash;

	atomic_t worker_refs;
	struct completion worker_done;

	struct hlist_node cpuhp_node;

	struct task_struct *task;

	struct io_wqe *wqes[];
};

static enum cpuhp_state io_wq_online;

struct io_cb_cancel_data {
	work_cancel_fn *fn;
	void *data;
	int nr_running;
	int nr_pending;
	bool cancel_all;
};

static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index);
static void io_wqe_dec_running(struct io_worker *worker);
static bool io_acct_cancel_pending_work(struct io_wqe *wqe,
					struct io_wqe_acct *acct,
					struct io_cb_cancel_data *match);
static void create_worker_cb(struct callback_head *cb);
static void io_wq_cancel_tw_create(struct io_wq *wq);

static bool io_worker_get(struct io_worker *worker)
{
	return refcount_inc_not_zero(&worker->ref);
}

static void io_worker_release(struct io_worker *worker)
{
	if (refcount_dec_and_test(&worker->ref))
		complete(&worker->ref_done);
}

static inline struct io_wqe_acct *io_get_acct(struct io_wqe *wqe, bool bound)
{
	return &wqe->acct[bound ? IO_WQ_ACCT_BOUND : IO_WQ_ACCT_UNBOUND];
}

static inline struct io_wqe_acct *io_work_get_acct(struct io_wqe *wqe,
						   struct io_wq_work *work)
{
	return io_get_acct(wqe, !(work->flags & IO_WQ_WORK_UNBOUND));
}

static inline struct io_wqe_acct *io_wqe_get_acct(struct io_worker *worker)
{
	return io_get_acct(worker->wqe, worker->flags & IO_WORKER_F_BOUND);
}

static void io_worker_ref_put(struct io_wq *wq)
{
	if (atomic_dec_and_test(&wq->worker_refs))
		complete(&wq->worker_done);
}

static void io_worker_cancel_cb(struct io_worker *worker)
{
	struct io_wqe_acct *acct = io_wqe_get_acct(worker);
	struct io_wqe *wqe = worker->wqe;
	struct io_wq *wq = wqe->wq;

	atomic_dec(&acct->nr_running);
	raw_spin_lock(&worker->wqe->lock);
	acct->nr_workers--;
	raw_spin_unlock(&worker->wqe->lock);
	io_worker_ref_put(wq);
	clear_bit_unlock(0, &worker->create_state);
	io_worker_release(worker);
}

static bool io_task_worker_match(struct callback_head *cb, void *data)
{
	struct io_worker *worker;

	if (cb->func != create_worker_cb)
		return false;
	worker = container_of(cb, struct io_worker, create_work);
	return worker == data;
}

static void io_worker_exit(struct io_worker *worker)
{
	struct io_wqe *wqe = worker->wqe;
	struct io_wq *wq = wqe->wq;

	while (1) {
		struct callback_head *cb = task_work_cancel_match(wq->task,
						io_task_worker_match, worker);

		if (!cb)
			break;
		io_worker_cancel_cb(worker);
	}

	io_worker_release(worker);
	wait_for_completion(&worker->ref_done);

	raw_spin_lock(&wqe->lock);
	if (worker->flags & IO_WORKER_F_FREE)
		hlist_nulls_del_rcu(&worker->nulls_node);
	list_del_rcu(&worker->all_list);
	raw_spin_unlock(&wqe->lock);
	io_wqe_dec_running(worker);
	worker->flags = 0;
	preempt_disable();
	current->flags &= ~PF_IO_WORKER;
	preempt_enable();

	kfree_rcu(worker, rcu);
	io_worker_ref_put(wqe->wq);
	do_exit(0);
}

static inline bool io_acct_run_queue(struct io_wqe_acct *acct)
{
	bool ret = false;

	raw_spin_lock(&acct->lock);
	if (!wq_list_empty(&acct->work_list) &&
	    !test_bit(IO_ACCT_STALLED_BIT, &acct->flags))
		ret = true;
	raw_spin_unlock(&acct->lock);

	return ret;
}

/*
 * Check head of free list for an available worker. If one isn't available,
 * caller must create one.
 */
static bool io_wqe_activate_free_worker(struct io_wqe *wqe,
					struct io_wqe_acct *acct)
	__must_hold(RCU)
{
	struct hlist_nulls_node *n;
	struct io_worker *worker;

	/*
	 * Iterate free_list and see if we can find an idle worker to
	 * activate. If a given worker is on the free_list but in the process
	 * of exiting, keep trying.
	 */
	hlist_nulls_for_each_entry_rcu(worker, n, &wqe->free_list, nulls_node) {
		if (!io_worker_get(worker))
			continue;
		if (io_wqe_get_acct(worker) != acct) {
			io_worker_release(worker);
			continue;
		}
		if (wake_up_process(worker->task)) {
			io_worker_release(worker);
			return true;
		}
		io_worker_release(worker);
	}

	return false;
}

/*
 * We need a worker. If we find a free one, we're good. If not, and we're
 * below the max number of workers, create one.
 */
static bool io_wqe_create_worker(struct io_wqe *wqe, struct io_wqe_acct *acct)
{
	/*
	 * Most likely an attempt to queue unbounded work on an io_wq that
	 * wasn't setup with any unbounded workers.
	 */
	if (unlikely(!acct->max_workers))
		pr_warn_once("io-wq is not configured for unbound workers");

	raw_spin_lock(&wqe->lock);
	if (acct->nr_workers >= acct->max_workers) {
		raw_spin_unlock(&wqe->lock);
		return true;
	}
	acct->nr_workers++;
	raw_spin_unlock(&wqe->lock);
	atomic_inc(&acct->nr_running);
	atomic_inc(&wqe->wq->worker_refs);
	return create_io_worker(wqe->wq, wqe, acct->index);
}

static void io_wqe_inc_running(struct io_worker *worker)
{
	struct io_wqe_acct *acct = io_wqe_get_acct(worker);

	atomic_inc(&acct->nr_running);
}

static void create_worker_cb(struct callback_head *cb)
{
	struct io_worker *worker;
	struct io_wq *wq;
	struct io_wqe *wqe;
	struct io_wqe_acct *acct;
	bool do_create = false;

	worker = container_of(cb, struct io_worker, create_work);
	wqe = worker->wqe;
	wq = wqe->wq;
	acct = &wqe->acct[worker->create_index];
	raw_spin_lock(&wqe->lock);
	if (acct->nr_workers < acct->max_workers) {
		acct->nr_workers++;
		do_create = true;
	}
	raw_spin_unlock(&wqe->lock);
	if (do_create) {
		create_io_worker(wq, wqe, worker->create_index);
	} else {
		atomic_dec(&acct->nr_running);
		io_worker_ref_put(wq);
	}
	clear_bit_unlock(0, &worker->create_state);
	io_worker_release(worker);
}

static bool io_queue_worker_create(struct io_worker *worker,
				   struct io_wqe_acct *acct,
				   task_work_func_t func)
{
	struct io_wqe *wqe = worker->wqe;
	struct io_wq *wq = wqe->wq;

	/* raced with exit, just ignore create call */
	if (test_bit(IO_WQ_BIT_EXIT, &wq->state))
		goto fail;
	if (!io_worker_get(worker))
		goto fail;
	/*
	 * create_state manages ownership of create_work/index. We should
	 * only need one entry per worker, as the worker going to sleep
	 * will trigger the condition, and waking will clear it once it
	 * runs the task_work.
	 */
	if (test_bit(0, &worker->create_state) ||
	    test_and_set_bit_lock(0, &worker->create_state))
		goto fail_release;

	atomic_inc(&wq->worker_refs);
	init_task_work(&worker->create_work, func);
	worker->create_index = acct->index;
	if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) {
		/*
		 * EXIT may have been set after checking it above, check after
		 * adding the task_work and remove any creation item if it is
		 * now set. wq exit does that too, but we can have added this
		 * work item after we canceled in io_wq_exit_workers().
		 */
		if (test_bit(IO_WQ_BIT_EXIT, &wq->state))
			io_wq_cancel_tw_create(wq);
		io_worker_ref_put(wq);
		return true;
	}
	io_worker_ref_put(wq);
	clear_bit_unlock(0, &worker->create_state);
fail_release:
	io_worker_release(worker);
fail:
	atomic_dec(&acct->nr_running);
	io_worker_ref_put(wq);
	return false;
}

static void io_wqe_dec_running(struct io_worker *worker)
{
	struct io_wqe_acct *acct = io_wqe_get_acct(worker);
	struct io_wqe *wqe = worker->wqe;

	if (!(worker->flags & IO_WORKER_F_UP))
		return;

	if (!atomic_dec_and_test(&acct->nr_running))
		return;
	if (!io_acct_run_queue(acct))
		return;

	atomic_inc(&acct->nr_running);
	atomic_inc(&wqe->wq->worker_refs);
	io_queue_worker_create(worker, acct, create_worker_cb);
}

/*
 * Worker will start processing some work. Move it to the busy list, if
 * it's currently on the freelist
 */
static void __io_worker_busy(struct io_wqe *wqe, struct io_worker *worker)
{
	if (worker->flags & IO_WORKER_F_FREE) {
		worker->flags &= ~IO_WORKER_F_FREE;
		raw_spin_lock(&wqe->lock);
		hlist_nulls_del_init_rcu(&worker->nulls_node);
		raw_spin_unlock(&wqe->lock);
	}
}

/*
 * No work, worker going to sleep. Move to freelist, and unuse mm if we
 * have one attached. Dropping the mm may potentially sleep, so we drop
 * the lock in that case and return success. Since the caller has to
 * retry the loop in that case (we changed task state), we don't regrab
 * the lock if we return success.
 */
static void __io_worker_idle(struct io_wqe *wqe, struct io_worker *worker)
	__must_hold(wqe->lock)
{
	if (!(worker->flags & IO_WORKER_F_FREE)) {
		worker->flags |= IO_WORKER_F_FREE;
		hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list);
	}
}

static inline unsigned int io_get_work_hash(struct io_wq_work *work)
{
	return work->flags >> IO_WQ_HASH_SHIFT;
}

static bool io_wait_on_hash(struct io_wqe *wqe, unsigned int hash)
{
	struct io_wq *wq = wqe->wq;
	bool ret = false;

	spin_lock_irq(&wq->hash->wait.lock);
	if (list_empty(&wqe->wait.entry)) {
		__add_wait_queue(&wq->hash->wait, &wqe->wait);
		if (!test_bit(hash, &wq->hash->map)) {
			__set_current_state(TASK_RUNNING);
			list_del_init(&wqe->wait.entry);
			ret = true;
		}
	}
	spin_unlock_irq(&wq->hash->wait.lock);
	return ret;
}

static struct io_wq_work *io_get_next_work(struct io_wqe_acct *acct,
					   struct io_worker *worker)
	__must_hold(acct->lock)
{
	struct io_wq_work_node *node, *prev;
	struct io_wq_work *work, *tail;
	unsigned int stall_hash = -1U;
	struct io_wqe *wqe = worker->wqe;

	wq_list_for_each(node, prev, &acct->work_list) {
		unsigned int hash;

		work = container_of(node, struct io_wq_work, list);

		/* not hashed, can run anytime */
		if (!io_wq_is_hashed(work)) {
			wq_list_del(&acct->work_list, node, prev);
			return work;
		}

		hash = io_get_work_hash(work);
		/* all items with this hash lie in [work, tail] */
		tail = wqe->hash_tail[hash];

		/* hashed, can run if not already running */
		if (!test_and_set_bit(hash, &wqe->wq->hash->map)) {
			wqe->hash_tail[hash] = NULL;
			wq_list_cut(&acct->work_list, &tail->list, prev);
			return work;
		}
		if (stall_hash == -1U)
			stall_hash = hash;
		/* fast forward to a next hash, for-each will fix up @prev */
		node = &tail->list;
	}

	if (stall_hash != -1U) {
		bool unstalled;

		/*
		 * Set this before dropping the lock to avoid racing with new
		 * work being added and clearing the stalled bit.
		 */
		set_bit(IO_ACCT_STALLED_BIT, &acct->flags);
		raw_spin_unlock(&acct->lock);
		unstalled = io_wait_on_hash(wqe, stall_hash);
		raw_spin_lock(&acct->lock);
		if (unstalled) {
			clear_bit(IO_ACCT_STALLED_BIT, &acct->flags);
			if (wq_has_sleeper(&wqe->wq->hash->wait))
				wake_up(&wqe->wq->hash->wait);
		}
	}

	return NULL;
}

static bool io_flush_signals(void)
{
	if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL))) {
		__set_current_state(TASK_RUNNING);
		clear_notify_signal();
		if (task_work_pending(current))
			task_work_run();
		return true;
	}
	return false;
}

static void io_assign_current_work(struct io_worker *worker,
				   struct io_wq_work *work)
{
	if (work) {
		io_flush_signals();
		cond_resched();
	}

	raw_spin_lock(&worker->lock);
	worker->cur_work = work;
	worker->next_work = NULL;
	raw_spin_unlock(&worker->lock);
}

static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work);

static void io_worker_handle_work(struct io_worker *worker)
{
	struct io_wqe_acct *acct = io_wqe_get_acct(worker);
	struct io_wqe *wqe = worker->wqe;
	struct io_wq *wq = wqe->wq;
	bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state);

	do {
		struct io_wq_work *work;

		/*
		 * If we got some work, mark us as busy. If we didn't, but
		 * the list isn't empty, it means we stalled on hashed work.
		 * Mark us stalled so we don't keep looking for work when we
		 * can't make progress, any work completion or insertion will
		 * clear the stalled flag.
		 */
		raw_spin_lock(&acct->lock);
		work = io_get_next_work(acct, worker);
		raw_spin_unlock(&acct->lock);
		if (work) {
			__io_worker_busy(wqe, worker);

			/*
			 * Make sure cancelation can find this, even before
			 * it becomes the active work. That avoids a window
			 * where the work has been removed from our general
			 * work list, but isn't yet discoverable as the
			 * current work item for this worker.
			 */
			raw_spin_lock(&worker->lock);
			worker->next_work = work;
			raw_spin_unlock(&worker->lock);
		} else {
			break;
		}
		io_assign_current_work(worker, work);
		__set_current_state(TASK_RUNNING);

		/* handle a whole dependent link */
		do {
			struct io_wq_work *next_hashed, *linked;
			unsigned int hash = io_get_work_hash(work);

			next_hashed = wq_next_work(work);

			if (unlikely(do_kill) && (work->flags & IO_WQ_WORK_UNBOUND))
				work->flags |= IO_WQ_WORK_CANCEL;
			wq->do_work(work);
			io_assign_current_work(worker, NULL);

			linked = wq->free_work(work);
			work = next_hashed;
			if (!work && linked && !io_wq_is_hashed(linked)) {
				work = linked;
				linked = NULL;
			}
			io_assign_current_work(worker, work);
			if (linked)
				io_wqe_enqueue(wqe, linked);

			if (hash != -1U && !next_hashed) {
				/* serialize hash clear with wake_up() */
				spin_lock_irq(&wq->hash->wait.lock);
				clear_bit(hash, &wq->hash->map);
				clear_bit(IO_ACCT_STALLED_BIT, &acct->flags);
				spin_unlock_irq(&wq->hash->wait.lock);
				if (wq_has_sleeper(&wq->hash->wait))
					wake_up(&wq->hash->wait);
			}
		} while (work);
	} while (1);
}

static int io_wqe_worker(void *data)
{
	struct io_worker *worker = data;
	struct io_wqe_acct *acct = io_wqe_get_acct(worker);
	struct io_wqe *wqe = worker->wqe;
	struct io_wq *wq = wqe->wq;
	bool last_timeout = false;
	char buf[TASK_COMM_LEN];

	worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING);

	snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task->pid);
	set_task_comm(current, buf);

	audit_alloc_kernel(current);

	while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
		long ret;

		set_current_state(TASK_INTERRUPTIBLE);
		while (io_acct_run_queue(acct))
			io_worker_handle_work(worker);

		raw_spin_lock(&wqe->lock);
		/* timed out, exit unless we're the last worker */
		if (last_timeout && acct->nr_workers > 1) {
			acct->nr_workers--;
			raw_spin_unlock(&wqe->lock);
			__set_current_state(TASK_RUNNING);
			break;
		}
		last_timeout = false;
		__io_worker_idle(wqe, worker);
		raw_spin_unlock(&wqe->lock);
		if (io_flush_signals())
			continue;
		ret = schedule_timeout(WORKER_IDLE_TIMEOUT);
		if (signal_pending(current)) {
			struct ksignal ksig;

			if (!get_signal(&ksig))
				continue;
			break;
		}
		last_timeout = !ret;
	}

	if (test_bit(IO_WQ_BIT_EXIT, &wq->state))
		io_worker_handle_work(worker);

	audit_free(current);
	io_worker_exit(worker);
	return 0;
}

/*
 * Called when a worker is scheduled in. Mark us as currently running.
 */
void io_wq_worker_running(struct task_struct *tsk)
{
	struct io_worker *worker = tsk->worker_private;

	if (!worker)
		return;
	if (!(worker->flags & IO_WORKER_F_UP))
		return;
	if (worker->flags & IO_WORKER_F_RUNNING)
		return;
	worker->flags |= IO_WORKER_F_RUNNING;
	io_wqe_inc_running(worker);
}

/*
 * Called when worker is going to sleep. If there are no workers currently
 * running and we have work pending, wake up a free one or create a new one.
 */
void io_wq_worker_sleeping(struct task_struct *tsk)
{
	struct io_worker *worker = tsk->worker_private;

	if (!worker)
		return;
	if (!(worker->flags & IO_WORKER_F_UP))
		return;
	if (!(worker->flags & IO_WORKER_F_RUNNING))
		return;

	worker->flags &= ~IO_WORKER_F_RUNNING;
	io_wqe_dec_running(worker);
}

static void io_init_new_worker(struct io_wqe *wqe, struct io_worker *worker,
			       struct task_struct *tsk)
{
	tsk->worker_private = worker;
	worker->task = tsk;
	set_cpus_allowed_ptr(tsk, wqe->cpu_mask);
	tsk->flags |= PF_NO_SETAFFINITY;

	raw_spin_lock(&wqe->lock);
	hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list);
	list_add_tail_rcu(&worker->all_list, &wqe->all_list);
	worker->flags |= IO_WORKER_F_FREE;
	raw_spin_unlock(&wqe->lock);
	wake_up_new_task(tsk);
}

static bool io_wq_work_match_all(struct io_wq_work *work, void *data)
{
	return true;
}

static inline bool io_should_retry_thread(long err)
{
	/*
	 * Prevent perpetual task_work retry, if the task (or its group) is
	 * exiting.
	 */
	if (fatal_signal_pending(current))
		return false;

	switch (err) {
	case -EAGAIN:
	case -ERESTARTSYS:
	case -ERESTARTNOINTR:
	case -ERESTARTNOHAND:
		return true;
	default:
		return false;
	}
}

static void create_worker_cont(struct callback_head *cb)
{
	struct io_worker *worker;
	struct task_struct *tsk;
	struct io_wqe *wqe;

	worker = container_of(cb, struct io_worker, create_work);
	clear_bit_unlock(0, &worker->create_state);
	wqe = worker->wqe;
	tsk = create_io_thread(io_wqe_worker, worker, wqe->node);
	if (!IS_ERR(tsk)) {
		io_init_new_worker(wqe, worker, tsk);
		io_worker_release(worker);
		return;
	} else if (!io_should_retry_thread(PTR_ERR(tsk))) {
		struct io_wqe_acct *acct = io_wqe_get_acct(worker);

		atomic_dec(&acct->nr_running);
		raw_spin_lock(&wqe->lock);
		acct->nr_workers--;
		if (!acct->nr_workers) {
			struct io_cb_cancel_data match = {
				.fn		= io_wq_work_match_all,
				.cancel_all	= true,
			};

			raw_spin_unlock(&wqe->lock);
			while (io_acct_cancel_pending_work(wqe, acct, &match))
				;
		} else {
			raw_spin_unlock(&wqe->lock);
		}
		io_worker_ref_put(wqe->wq);
		kfree(worker);
		return;
	}

	/* re-create attempts grab a new worker ref, drop the existing one */
	io_worker_release(worker);
	schedule_work(&worker->work);
}

static void io_workqueue_create(struct work_struct *work)
{
	struct io_worker *worker = container_of(work, struct io_worker, work);
	struct io_wqe_acct *acct = io_wqe_get_acct(worker);

	if (!io_queue_worker_create(worker, acct, create_worker_cont))
		kfree(worker);
}

static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
{
	struct io_wqe_acct *acct = &wqe->acct[index];
	struct io_worker *worker;
	struct task_struct *tsk;

	__set_current_state(TASK_RUNNING);

	worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, wqe->node);
	if (!worker) {
fail:
		atomic_dec(&acct->nr_running);
		raw_spin_lock(&wqe->lock);
		acct->nr_workers--;
		raw_spin_unlock(&wqe->lock);
		io_worker_ref_put(wq);
		return false;
	}

	refcount_set(&worker->ref, 1);
	worker->wqe = wqe;
	raw_spin_lock_init(&worker->lock);
	init_completion(&worker->ref_done);

	if (index == IO_WQ_ACCT_BOUND)
		worker->flags |= IO_WORKER_F_BOUND;

	tsk = create_io_thread(io_wqe_worker, worker, wqe->node);
	if (!IS_ERR(tsk)) {
		io_init_new_worker(wqe, worker, tsk);
	} else if (!io_should_retry_thread(PTR_ERR(tsk))) {
		kfree(worker);
		goto fail;
	} else {
		INIT_WORK(&worker->work, io_workqueue_create);
		schedule_work(&worker->work);
	}

	return true;
}

/*
 * Iterate the passed in list and call the specific function for each
 * worker that isn't exiting
 */
static bool io_wq_for_each_worker(struct io_wqe *wqe,
				  bool (*func)(struct io_worker *, void *),
				  void *data)
{
	struct io_worker *worker;
	bool ret = false;

	list_for_each_entry_rcu(worker, &wqe->all_list, all_list) {
		if (io_worker_get(worker)) {
			/* no task if node is/was offline */
			if (worker->task)
				ret = func(worker, data);
			io_worker_release(worker);
			if (ret)
				break;
		}
	}

	return ret;
}

static bool io_wq_worker_wake(struct io_worker *worker, void *data)
{
	__set_notify_signal(worker->task);
	wake_up_process(worker->task);
	return false;
}

static void io_run_cancel(struct io_wq_work *work, struct io_wqe *wqe)
{
	struct io_wq *wq = wqe->wq;

	do {
		work->flags |= IO_WQ_WORK_CANCEL;
		wq->do_work(work);
		work = wq->free_work(work);
	} while (work);
}

static void io_wqe_insert_work(struct io_wqe *wqe, struct io_wq_work *work)
{
	struct io_wqe_acct *acct = io_work_get_acct(wqe, work);
	unsigned int hash;
	struct io_wq_work *tail;

	if (!io_wq_is_hashed(work)) {
append:
		wq_list_add_tail(&work->list, &acct->work_list);
		return;
	}

	hash = io_get_work_hash(work);
	tail = wqe->hash_tail[hash];
	wqe->hash_tail[hash] = work;
	if (!tail)
		goto append;

	wq_list_add_after(&work->list, &tail->list, &acct->work_list);
}

static bool io_wq_work_match_item(struct io_wq_work *work, void *data)
{
	return work == data;
}

static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
{
	struct io_wqe_acct *acct = io_work_get_acct(wqe, work);
	struct io_cb_cancel_data match;
	unsigned work_flags = work->flags;
	bool do_create;

	/*
	 * If io-wq is exiting for this task, or if the request has explicitly
	 * been marked as one that should not get executed, cancel it here.
	 */
	if (test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state) ||
	    (work->flags & IO_WQ_WORK_CANCEL)) {
		io_run_cancel(work, wqe);
		return;
	}

	raw_spin_lock(&acct->lock);
	io_wqe_insert_work(wqe, work);
	clear_bit(IO_ACCT_STALLED_BIT, &acct->flags);
	raw_spin_unlock(&acct->lock);

	raw_spin_lock(&wqe->lock);
	rcu_read_lock();
	do_create = !io_wqe_activate_free_worker(wqe, acct);
	rcu_read_unlock();

	raw_spin_unlock(&wqe->lock);

	if (do_create && ((work_flags & IO_WQ_WORK_CONCURRENT) ||
	    !atomic_read(&acct->nr_running))) {
		bool did_create;

		did_create = io_wqe_create_worker(wqe, acct);
		if (likely(did_create))
			return;

		raw_spin_lock(&wqe->lock);
		if (acct->nr_workers) {
			raw_spin_unlock(&wqe->lock);
			return;
		}
		raw_spin_unlock(&wqe->lock);

		/* fatal condition, failed to create the first worker */
		match.fn		= io_wq_work_match_item,
		match.data		= work,
		match.cancel_all	= false,

		io_acct_cancel_pending_work(wqe, acct, &match);
	}
}

void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work)
{
	struct io_wqe *wqe = wq->wqes[numa_node_id()];

	io_wqe_enqueue(wqe, work);
}

/*
 * Work items that hash to the same value will not be done in parallel.
 * Used to limit concurrent writes, generally hashed by inode.
 */
void io_wq_hash_work(struct io_wq_work *work, void *val)
{
	unsigned int bit;

	bit = hash_ptr(val, IO_WQ_HASH_ORDER);
	work->flags |= (IO_WQ_WORK_HASHED | (bit << IO_WQ_HASH_SHIFT));
}

static bool __io_wq_worker_cancel(struct io_worker *worker,
				  struct io_cb_cancel_data *match,
				  struct io_wq_work *work)
{
	if (work && match->fn(work, match->data)) {
		work->flags |= IO_WQ_WORK_CANCEL;
		__set_notify_signal(worker->task);
		return true;
	}

	return false;
}

static bool io_wq_worker_cancel(struct io_worker *worker, void *data)
{
	struct io_cb_cancel_data *match = data;

	/*
	 * Hold the lock to avoid ->cur_work going out of scope, caller
	 * may dereference the passed in work.
	 */
	raw_spin_lock(&worker->lock);
	if (__io_wq_worker_cancel(worker, match, worker->cur_work) ||
	    __io_wq_worker_cancel(worker, match, worker->next_work))
		match->nr_running++;
	raw_spin_unlock(&worker->lock);

	return match->nr_running && !match->cancel_all;
}

static inline void io_wqe_remove_pending(struct io_wqe *wqe,
					 struct io_wq_work *work,
					 struct io_wq_work_node *prev)
{
	struct io_wqe_acct *acct = io_work_get_acct(wqe, work);
	unsigned int hash = io_get_work_hash(work);
	struct io_wq_work *prev_work = NULL;

	if (io_wq_is_hashed(work) && work == wqe->hash_tail[hash]) {
		if (prev)
			prev_work = container_of(prev, struct io_wq_work, list);
		if (prev_work && io_get_work_hash(prev_work) == hash)
			wqe->hash_tail[hash] = prev_work;
		else
			wqe->hash_tail[hash] = NULL;
	}
	wq_list_del(&acct->work_list, &work->list, prev);
}

static bool io_acct_cancel_pending_work(struct io_wqe *wqe,
					struct io_wqe_acct *acct,
					struct io_cb_cancel_data *match)
{
	struct io_wq_work_node *node, *prev;
	struct io_wq_work *work;

	raw_spin_lock(&acct->lock);
	wq_list_for_each(node, prev, &acct->work_list) {
		work = container_of(node, struct io_wq_work, list);
		if (!match->fn(work, match->data))
			continue;
		io_wqe_remove_pending(wqe, work, prev);
		raw_spin_unlock(&acct->lock);
		io_run_cancel(work, wqe);
		match->nr_pending++;
		/* not safe to continue after unlock */
		return true;
	}
	raw_spin_unlock(&acct->lock);

	return false;
}

static void io_wqe_cancel_pending_work(struct io_wqe *wqe,
				       struct io_cb_cancel_data *match)
{
	int i;
retry:
	for (i = 0; i < IO_WQ_ACCT_NR; i++) {
		struct io_wqe_acct *acct = io_get_acct(wqe, i == 0);

		if (io_acct_cancel_pending_work(wqe, acct, match)) {
			if (match->cancel_all)
				goto retry;
			break;
		}
	}
}

static void io_wqe_cancel_running_work(struct io_wqe *wqe,
				       struct io_cb_cancel_data *match)
{
	rcu_read_lock();
	io_wq_for_each_worker(wqe, io_wq_worker_cancel, match);
	rcu_read_unlock();
}

enum io_wq_cancel io_wq_cancel_cb(struct io_wq *wq, work_cancel_fn *cancel,
				  void *data, bool cancel_all)
{
	struct io_cb_cancel_data match = {
		.fn		= cancel,
		.data		= data,
		.cancel_all	= cancel_all,
	};
	int node;

	/*
	 * First check pending list, if we're lucky we can just remove it
	 * from there. CANCEL_OK means that the work is returned as-new,
	 * no completion will be posted for it.
	 *
	 * Then check if a free (going busy) or busy worker has the work
	 * currently running. If we find it there, we'll return CANCEL_RUNNING
	 * as an indication that we attempt to signal cancellation. The
	 * completion will run normally in this case.
	 *
	 * Do both of these while holding the wqe->lock, to ensure that
	 * we'll find a work item regardless of state.
	 */
	for_each_node(node) {
		struct io_wqe *wqe = wq->wqes[node];

		io_wqe_cancel_pending_work(wqe, &match);
		if (match.nr_pending && !match.cancel_all)
			return IO_WQ_CANCEL_OK;

		raw_spin_lock(&wqe->lock);
		io_wqe_cancel_running_work(wqe, &match);
		raw_spin_unlock(&wqe->lock);
		if (match.nr_running && !match.cancel_all)
			return IO_WQ_CANCEL_RUNNING;
	}

	if (match.nr_running)
		return IO_WQ_CANCEL_RUNNING;
	if (match.nr_pending)
		return IO_WQ_CANCEL_OK;
	return IO_WQ_CANCEL_NOTFOUND;
}

static int io_wqe_hash_wake(struct wait_queue_entry *wait, unsigned mode,
			    int sync, void *key)
{
	struct io_wqe *wqe = container_of(wait, struct io_wqe, wait);
	int i;

	list_del_init(&wait->entry);

	rcu_read_lock();
	for (i = 0; i < IO_WQ_ACCT_NR; i++) {
		struct io_wqe_acct *acct = &wqe->acct[i];

		if (test_and_clear_bit(IO_ACCT_STALLED_BIT, &acct->flags))
			io_wqe_activate_free_worker(wqe, acct);
	}
	rcu_read_unlock();
	return 1;
}

struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
{
	int ret, node, i;
	struct io_wq *wq;

	if (WARN_ON_ONCE(!data->free_work || !data->do_work))
		return ERR_PTR(-EINVAL);
	if (WARN_ON_ONCE(!bounded))
		return ERR_PTR(-EINVAL);

	wq = kzalloc(struct_size(wq, wqes, nr_node_ids), GFP_KERNEL);
	if (!wq)
		return ERR_PTR(-ENOMEM);
	ret = cpuhp_state_add_instance_nocalls(io_wq_online, &wq->cpuhp_node);
	if (ret)
		goto err_wq;

	refcount_inc(&data->hash->refs);
	wq->hash = data->hash;
	wq->free_work = data->free_work;
	wq->do_work = data->do_work;

	ret = -ENOMEM;
	for_each_node(node) {
		struct io_wqe *wqe;
		int alloc_node = node;

		if (!node_online(alloc_node))
			alloc_node = NUMA_NO_NODE;
		wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, alloc_node);
		if (!wqe)
			goto err;
		if (!alloc_cpumask_var(&wqe->cpu_mask, GFP_KERNEL))
			goto err;
		cpumask_copy(wqe->cpu_mask, cpumask_of_node(node));
		wq->wqes[node] = wqe;
		wqe->node = alloc_node;
		wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded;
		wqe->acct[IO_WQ_ACCT_UNBOUND].max_workers =
					task_rlimit(current, RLIMIT_NPROC);
		INIT_LIST_HEAD(&wqe->wait.entry);
		wqe->wait.func = io_wqe_hash_wake;
		for (i = 0; i < IO_WQ_ACCT_NR; i++) {
			struct io_wqe_acct *acct = &wqe->acct[i];

			acct->index = i;
			atomic_set(&acct->nr_running, 0);
			INIT_WQ_LIST(&acct->work_list);
			raw_spin_lock_init(&acct->lock);
		}
		wqe->wq = wq;
		raw_spin_lock_init(&wqe->lock);
		INIT_HLIST_NULLS_HEAD(&wqe->free_list, 0);
		INIT_LIST_HEAD(&wqe->all_list);
	}

	wq->task = get_task_struct(data->task);
	atomic_set(&wq->worker_refs, 1);
	init_completion(&wq->worker_done);
	return wq;
err:
	io_wq_put_hash(data->hash);
	cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node);
	for_each_node(node) {
		if (!wq->wqes[node])
			continue;
		free_cpumask_var(wq->wqes[node]->cpu_mask);
		kfree(wq->wqes[node]);
	}
err_wq:
	kfree(wq);
	return ERR_PTR(ret);
}

static bool io_task_work_match(struct callback_head *cb, void *data)
{
	struct io_worker *worker;

	if (cb->func != create_worker_cb && cb->func != create_worker_cont)
		return false;
	worker = container_of(cb, struct io_worker, create_work);
	return worker->wqe->wq == data;
}

void io_wq_exit_start(struct io_wq *wq)
{
	set_bit(IO_WQ_BIT_EXIT, &wq->state);
}

static void io_wq_cancel_tw_create(struct io_wq *wq)
{
	struct callback_head *cb;

	while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) {
		struct io_worker *worker;

		worker = container_of(cb, struct io_worker, create_work);
		io_worker_cancel_cb(worker);
	}
}

static void io_wq_exit_workers(struct io_wq *wq)
{
	int node;

	if (!wq->task)
		return;

	io_wq_cancel_tw_create(wq);

	rcu_read_lock();
	for_each_node(node) {
		struct io_wqe *wqe = wq->wqes[node];

		io_wq_for_each_worker(wqe, io_wq_worker_wake, NULL);
	}
	rcu_read_unlock();
	io_worker_ref_put(wq);
	wait_for_completion(&wq->worker_done);

	for_each_node(node) {
		spin_lock_irq(&wq->hash->wait.lock);
		list_del_init(&wq->wqes[node]->wait.entry);
		spin_unlock_irq(&wq->hash->wait.lock);
	}
	put_task_struct(wq->task);
	wq->task = NULL;
}

static void io_wq_destroy(struct io_wq *wq)
{
	int node;

	cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node);

	for_each_node(node) {
		struct io_wqe *wqe = wq->wqes[node];
		struct io_cb_cancel_data match = {
			.fn		= io_wq_work_match_all,
			.cancel_all	= true,
		};
		io_wqe_cancel_pending_work(wqe, &match);
		free_cpumask_var(wqe->cpu_mask);
		kfree(wqe);
	}
	io_wq_put_hash(wq->hash);
	kfree(wq);
}

void io_wq_put_and_exit(struct io_wq *wq)
{
	WARN_ON_ONCE(!test_bit(IO_WQ_BIT_EXIT, &wq->state));

	io_wq_exit_workers(wq);
	io_wq_destroy(wq);
}

struct online_data {
	unsigned int cpu;
	bool online;
};

static bool io_wq_worker_affinity(struct io_worker *worker, void *data)
{
	struct online_data *od = data;

	if (od->online)
		cpumask_set_cpu(od->cpu, worker->wqe->cpu_mask);
	else
		cpumask_clear_cpu(od->cpu, worker->wqe->cpu_mask);
	return false;
}

static int __io_wq_cpu_online(struct io_wq *wq, unsigned int cpu, bool online)
{
	struct online_data od = {
		.cpu = cpu,
		.online = online
	};
	int i;

	rcu_read_lock();
	for_each_node(i)
		io_wq_for_each_worker(wq->wqes[i], io_wq_worker_affinity, &od);
	rcu_read_unlock();
	return 0;
}

static int io_wq_cpu_online(unsigned int cpu, struct hlist_node *node)
{
	struct io_wq *wq = hlist_entry_safe(node, struct io_wq, cpuhp_node);

	return __io_wq_cpu_online(wq, cpu, true);
}

static int io_wq_cpu_offline(unsigned int cpu, struct hlist_node *node)
{
	struct io_wq *wq = hlist_entry_safe(node, struct io_wq, cpuhp_node);

	return __io_wq_cpu_online(wq, cpu, false);
}

int io_wq_cpu_affinity(struct io_wq *wq, cpumask_var_t mask)
{
	int i;

	rcu_read_lock();
	for_each_node(i) {
		struct io_wqe *wqe = wq->wqes[i];

		if (mask)
			cpumask_copy(wqe->cpu_mask, mask);
		else
			cpumask_copy(wqe->cpu_mask, cpumask_of_node(i));
	}
	rcu_read_unlock();
	return 0;
}

/*
 * Set max number of unbounded workers, returns old value. If new_count is 0,
 * then just return the old value.
 */
int io_wq_max_workers(struct io_wq *wq, int *new_count)
{
	int prev[IO_WQ_ACCT_NR];
	bool first_node = true;
	int i, node;

	BUILD_BUG_ON((int) IO_WQ_ACCT_BOUND   != (int) IO_WQ_BOUND);
	BUILD_BUG_ON((int) IO_WQ_ACCT_UNBOUND != (int) IO_WQ_UNBOUND);
	BUILD_BUG_ON((int) IO_WQ_ACCT_NR      != 2);

	for (i = 0; i < IO_WQ_ACCT_NR; i++) {
		if (new_count[i] > task_rlimit(current, RLIMIT_NPROC))
			new_count[i] = task_rlimit(current, RLIMIT_NPROC);
	}

	for (i = 0; i < IO_WQ_ACCT_NR; i++)
		prev[i] = 0;

	rcu_read_lock();
	for_each_node(node) {
		struct io_wqe *wqe = wq->wqes[node];
		struct io_wqe_acct *acct;

		raw_spin_lock(&wqe->lock);
		for (i = 0; i < IO_WQ_ACCT_NR; i++) {
			acct = &wqe->acct[i];
			if (first_node)
				prev[i] = max_t(int, acct->max_workers, prev[i]);
			if (new_count[i])
				acct->max_workers = new_count[i];
		}
		raw_spin_unlock(&wqe->lock);
		first_node = false;
	}
	rcu_read_unlock();

	for (i = 0; i < IO_WQ_ACCT_NR; i++)
		new_count[i] = prev[i];

	return 0;
}

static __init int io_wq_init(void)
{
	int ret;

	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "io-wq/online",
					io_wq_cpu_online, io_wq_cpu_offline);
	if (ret < 0)
		return ret;
	io_wq_online = ret;
	return 0;
}
subsys_initcall(io_wq_init);