aboutsummaryrefslogtreecommitdiff
path: root/block/bio.c
blob: 51c99f2c5c90873eed4f7d480f3a5c91282b2888 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2001 Jens Axboe <axboe@kernel.dk>
 */
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/uio.h>
#include <linux/iocontext.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/mempool.h>
#include <linux/workqueue.h>
#include <linux/cgroup.h>
#include <linux/highmem.h>
#include <linux/sched/sysctl.h>
#include <linux/blk-crypto.h>
#include <linux/xarray.h>

#include <trace/events/block.h>
#include "blk.h"
#include "blk-rq-qos.h"
#include "blk-cgroup.h"

struct bio_alloc_cache {
	struct bio		*free_list;
	unsigned int		nr;
};

static struct biovec_slab {
	int nr_vecs;
	char *name;
	struct kmem_cache *slab;
} bvec_slabs[] __read_mostly = {
	{ .nr_vecs = 16, .name = "biovec-16" },
	{ .nr_vecs = 64, .name = "biovec-64" },
	{ .nr_vecs = 128, .name = "biovec-128" },
	{ .nr_vecs = BIO_MAX_VECS, .name = "biovec-max" },
};

static struct biovec_slab *biovec_slab(unsigned short nr_vecs)
{
	switch (nr_vecs) {
	/* smaller bios use inline vecs */
	case 5 ... 16:
		return &bvec_slabs[0];
	case 17 ... 64:
		return &bvec_slabs[1];
	case 65 ... 128:
		return &bvec_slabs[2];
	case 129 ... BIO_MAX_VECS:
		return &bvec_slabs[3];
	default:
		BUG();
		return NULL;
	}
}

/*
 * fs_bio_set is the bio_set containing bio and iovec memory pools used by
 * IO code that does not need private memory pools.
 */
struct bio_set fs_bio_set;
EXPORT_SYMBOL(fs_bio_set);

/*
 * Our slab pool management
 */
struct bio_slab {
	struct kmem_cache *slab;
	unsigned int slab_ref;
	unsigned int slab_size;
	char name[8];
};
static DEFINE_MUTEX(bio_slab_lock);
static DEFINE_XARRAY(bio_slabs);

static struct bio_slab *create_bio_slab(unsigned int size)
{
	struct bio_slab *bslab = kzalloc(sizeof(*bslab), GFP_KERNEL);

	if (!bslab)
		return NULL;

	snprintf(bslab->name, sizeof(bslab->name), "bio-%d", size);
	bslab->slab = kmem_cache_create(bslab->name, size,
			ARCH_KMALLOC_MINALIGN,
			SLAB_HWCACHE_ALIGN | SLAB_TYPESAFE_BY_RCU, NULL);
	if (!bslab->slab)
		goto fail_alloc_slab;

	bslab->slab_ref = 1;
	bslab->slab_size = size;

	if (!xa_err(xa_store(&bio_slabs, size, bslab, GFP_KERNEL)))
		return bslab;

	kmem_cache_destroy(bslab->slab);

fail_alloc_slab:
	kfree(bslab);
	return NULL;
}

static inline unsigned int bs_bio_slab_size(struct bio_set *bs)
{
	return bs->front_pad + sizeof(struct bio) + bs->back_pad;
}

static struct kmem_cache *bio_find_or_create_slab(struct bio_set *bs)
{
	unsigned int size = bs_bio_slab_size(bs);
	struct bio_slab *bslab;

	mutex_lock(&bio_slab_lock);
	bslab = xa_load(&bio_slabs, size);
	if (bslab)
		bslab->slab_ref++;
	else
		bslab = create_bio_slab(size);
	mutex_unlock(&bio_slab_lock);

	if (bslab)
		return bslab->slab;
	return NULL;
}

static void bio_put_slab(struct bio_set *bs)
{
	struct bio_slab *bslab = NULL;
	unsigned int slab_size = bs_bio_slab_size(bs);

	mutex_lock(&bio_slab_lock);

	bslab = xa_load(&bio_slabs, slab_size);
	if (WARN(!bslab, KERN_ERR "bio: unable to find slab!\n"))
		goto out;

	WARN_ON_ONCE(bslab->slab != bs->bio_slab);

	WARN_ON(!bslab->slab_ref);

	if (--bslab->slab_ref)
		goto out;

	xa_erase(&bio_slabs, slab_size);

	kmem_cache_destroy(bslab->slab);
	kfree(bslab);

out:
	mutex_unlock(&bio_slab_lock);
}

void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned short nr_vecs)
{
	BUG_ON(nr_vecs > BIO_MAX_VECS);

	if (nr_vecs == BIO_MAX_VECS)
		mempool_free(bv, pool);
	else if (nr_vecs > BIO_INLINE_VECS)
		kmem_cache_free(biovec_slab(nr_vecs)->slab, bv);
}

/*
 * Make the first allocation restricted and don't dump info on allocation
 * failures, since we'll fall back to the mempool in case of failure.
 */
static inline gfp_t bvec_alloc_gfp(gfp_t gfp)
{
	return (gfp & ~(__GFP_DIRECT_RECLAIM | __GFP_IO)) |
		__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
}

struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs,
		gfp_t gfp_mask)
{
	struct biovec_slab *bvs = biovec_slab(*nr_vecs);

	if (WARN_ON_ONCE(!bvs))
		return NULL;

	/*
	 * Upgrade the nr_vecs request to take full advantage of the allocation.
	 * We also rely on this in the bvec_free path.
	 */
	*nr_vecs = bvs->nr_vecs;

	/*
	 * Try a slab allocation first for all smaller allocations.  If that
	 * fails and __GFP_DIRECT_RECLAIM is set retry with the mempool.
	 * The mempool is sized to handle up to BIO_MAX_VECS entries.
	 */
	if (*nr_vecs < BIO_MAX_VECS) {
		struct bio_vec *bvl;

		bvl = kmem_cache_alloc(bvs->slab, bvec_alloc_gfp(gfp_mask));
		if (likely(bvl) || !(gfp_mask & __GFP_DIRECT_RECLAIM))
			return bvl;
		*nr_vecs = BIO_MAX_VECS;
	}

	return mempool_alloc(pool, gfp_mask);
}

void bio_uninit(struct bio *bio)
{
#ifdef CONFIG_BLK_CGROUP
	if (bio->bi_blkg) {
		blkg_put(bio->bi_blkg);
		bio->bi_blkg = NULL;
	}
#endif
	if (bio_integrity(bio))
		bio_integrity_free(bio);

	bio_crypt_free_ctx(bio);
}
EXPORT_SYMBOL(bio_uninit);

static void bio_free(struct bio *bio)
{
	struct bio_set *bs = bio->bi_pool;
	void *p = bio;

	WARN_ON_ONCE(!bs);

	bio_uninit(bio);
	bvec_free(&bs->bvec_pool, bio->bi_io_vec, bio->bi_max_vecs);
	mempool_free(p - bs->front_pad, &bs->bio_pool);
}

/*
 * Users of this function have their own bio allocation. Subsequently,
 * they must remember to pair any call to bio_init() with bio_uninit()
 * when IO has completed, or when the bio is released.
 */
void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table,
	      unsigned short max_vecs, unsigned int opf)
{
	bio->bi_next = NULL;
	bio->bi_bdev = bdev;
	bio->bi_opf = opf;
	bio->bi_flags = 0;
	bio->bi_ioprio = 0;
	bio->bi_status = 0;
	bio->bi_iter.bi_sector = 0;
	bio->bi_iter.bi_size = 0;
	bio->bi_iter.bi_idx = 0;
	bio->bi_iter.bi_bvec_done = 0;
	bio->bi_end_io = NULL;
	bio->bi_private = NULL;
#ifdef CONFIG_BLK_CGROUP
	bio->bi_blkg = NULL;
	bio->bi_issue.value = 0;
	if (bdev)
		bio_associate_blkg(bio);
#ifdef CONFIG_BLK_CGROUP_IOCOST
	bio->bi_iocost_cost = 0;
#endif
#endif
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
	bio->bi_crypt_context = NULL;
#endif
#ifdef CONFIG_BLK_DEV_INTEGRITY
	bio->bi_integrity = NULL;
#endif
	bio->bi_vcnt = 0;

	atomic_set(&bio->__bi_remaining, 1);
	atomic_set(&bio->__bi_cnt, 1);
	bio->bi_cookie = BLK_QC_T_NONE;

	bio->bi_max_vecs = max_vecs;
	bio->bi_io_vec = table;
	bio->bi_pool = NULL;
}
EXPORT_SYMBOL(bio_init);

/**
 * bio_reset - reinitialize a bio
 * @bio:	bio to reset
 * @bdev:	block device to use the bio for
 * @opf:	operation and flags for bio
 *
 * Description:
 *   After calling bio_reset(), @bio will be in the same state as a freshly
 *   allocated bio returned bio bio_alloc_bioset() - the only fields that are
 *   preserved are the ones that are initialized by bio_alloc_bioset(). See
 *   comment in struct bio.
 */
void bio_reset(struct bio *bio, struct block_device *bdev, unsigned int opf)
{
	bio_uninit(bio);
	memset(bio, 0, BIO_RESET_BYTES);
	atomic_set(&bio->__bi_remaining, 1);
	bio->bi_bdev = bdev;
	if (bio->bi_bdev)
		bio_associate_blkg(bio);
	bio->bi_opf = opf;
}
EXPORT_SYMBOL(bio_reset);

static struct bio *__bio_chain_endio(struct bio *bio)
{
	struct bio *parent = bio->bi_private;

	if (bio->bi_status && !parent->bi_status)
		parent->bi_status = bio->bi_status;
	bio_put(bio);
	return parent;
}

static void bio_chain_endio(struct bio *bio)
{
	bio_endio(__bio_chain_endio(bio));
}

/**
 * bio_chain - chain bio completions
 * @bio: the target bio
 * @parent: the parent bio of @bio
 *
 * The caller won't have a bi_end_io called when @bio completes - instead,
 * @parent's bi_end_io won't be called until both @parent and @bio have
 * completed; the chained bio will also be freed when it completes.
 *
 * The caller must not set bi_private or bi_end_io in @bio.
 */
void bio_chain(struct bio *bio, struct bio *parent)
{
	BUG_ON(bio->bi_private || bio->bi_end_io);

	bio->bi_private = parent;
	bio->bi_end_io	= bio_chain_endio;
	bio_inc_remaining(parent);
}
EXPORT_SYMBOL(bio_chain);

struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
		unsigned int nr_pages, unsigned int opf, gfp_t gfp)
{
	struct bio *new = bio_alloc(bdev, nr_pages, opf, gfp);

	if (bio) {
		bio_chain(bio, new);
		submit_bio(bio);
	}

	return new;
}
EXPORT_SYMBOL_GPL(blk_next_bio);

static void bio_alloc_rescue(struct work_struct *work)
{
	struct bio_set *bs = container_of(work, struct bio_set, rescue_work);
	struct bio *bio;

	while (1) {
		spin_lock(&bs->rescue_lock);
		bio = bio_list_pop(&bs->rescue_list);
		spin_unlock(&bs->rescue_lock);

		if (!bio)
			break;

		submit_bio_noacct(bio);
	}
}

static void punt_bios_to_rescuer(struct bio_set *bs)
{
	struct bio_list punt, nopunt;
	struct bio *bio;

	if (WARN_ON_ONCE(!bs->rescue_workqueue))
		return;
	/*
	 * In order to guarantee forward progress we must punt only bios that
	 * were allocated from this bio_set; otherwise, if there was a bio on
	 * there for a stacking driver higher up in the stack, processing it
	 * could require allocating bios from this bio_set, and doing that from
	 * our own rescuer would be bad.
	 *
	 * Since bio lists are singly linked, pop them all instead of trying to
	 * remove from the middle of the list:
	 */

	bio_list_init(&punt);
	bio_list_init(&nopunt);

	while ((bio = bio_list_pop(&current->bio_list[0])))
		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
	current->bio_list[0] = nopunt;

	bio_list_init(&nopunt);
	while ((bio = bio_list_pop(&current->bio_list[1])))
		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);
	current->bio_list[1] = nopunt;

	spin_lock(&bs->rescue_lock);
	bio_list_merge(&bs->rescue_list, &punt);
	spin_unlock(&bs->rescue_lock);

	queue_work(bs->rescue_workqueue, &bs->rescue_work);
}

static struct bio *bio_alloc_percpu_cache(struct block_device *bdev,
		unsigned short nr_vecs, unsigned int opf, gfp_t gfp,
		struct bio_set *bs)
{
	struct bio_alloc_cache *cache;
	struct bio *bio;

	cache = per_cpu_ptr(bs->cache, get_cpu());
	if (!cache->free_list) {
		put_cpu();
		return NULL;
	}
	bio = cache->free_list;
	cache->free_list = bio->bi_next;
	cache->nr--;
	put_cpu();

	bio_init(bio, bdev, nr_vecs ? bio->bi_inline_vecs : NULL, nr_vecs, opf);
	bio->bi_pool = bs;
	return bio;
}

/**
 * bio_alloc_bioset - allocate a bio for I/O
 * @bdev:	block device to allocate the bio for (can be %NULL)
 * @nr_vecs:	number of bvecs to pre-allocate
 * @opf:	operation and flags for bio
 * @gfp_mask:   the GFP_* mask given to the slab allocator
 * @bs:		the bio_set to allocate from.
 *
 * Allocate a bio from the mempools in @bs.
 *
 * If %__GFP_DIRECT_RECLAIM is set then bio_alloc will always be able to
 * allocate a bio.  This is due to the mempool guarantees.  To make this work,
 * callers must never allocate more than 1 bio at a time from the general pool.
 * Callers that need to allocate more than 1 bio must always submit the
 * previously allocated bio for IO before attempting to allocate a new one.
 * Failure to do so can cause deadlocks under memory pressure.
 *
 * Note that when running under submit_bio_noacct() (i.e. any block driver),
 * bios are not submitted until after you return - see the code in
 * submit_bio_noacct() that converts recursion into iteration, to prevent
 * stack overflows.
 *
 * This would normally mean allocating multiple bios under submit_bio_noacct()
 * would be susceptible to deadlocks, but we have
 * deadlock avoidance code that resubmits any blocked bios from a rescuer
 * thread.
 *
 * However, we do not guarantee forward progress for allocations from other
 * mempools. Doing multiple allocations from the same mempool under
 * submit_bio_noacct() should be avoided - instead, use bio_set's front_pad
 * for per bio allocations.
 *
 * If REQ_ALLOC_CACHE is set, the final put of the bio MUST be done from process
 * context, not hard/soft IRQ.
 *
 * Returns: Pointer to new bio on success, NULL on failure.
 */
struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs,
			     unsigned int opf, gfp_t gfp_mask,
			     struct bio_set *bs)
{
	gfp_t saved_gfp = gfp_mask;
	struct bio *bio;
	void *p;

	/* should not use nobvec bioset for nr_vecs > 0 */
	if (WARN_ON_ONCE(!mempool_initialized(&bs->bvec_pool) && nr_vecs > 0))
		return NULL;

	if (opf & REQ_ALLOC_CACHE) {
		if (bs->cache && nr_vecs <= BIO_INLINE_VECS) {
			bio = bio_alloc_percpu_cache(bdev, nr_vecs, opf,
						     gfp_mask, bs);
			if (bio)
				return bio;
			/*
			 * No cached bio available, bio returned below marked with
			 * REQ_ALLOC_CACHE to particpate in per-cpu alloc cache.
			 */
		} else {
			opf &= ~REQ_ALLOC_CACHE;
		}
	}

	/*
	 * submit_bio_noacct() converts recursion to iteration; this means if
	 * we're running beneath it, any bios we allocate and submit will not be
	 * submitted (and thus freed) until after we return.
	 *
	 * This exposes us to a potential deadlock if we allocate multiple bios
	 * from the same bio_set() while running underneath submit_bio_noacct().
	 * If we were to allocate multiple bios (say a stacking block driver
	 * that was splitting bios), we would deadlock if we exhausted the
	 * mempool's reserve.
	 *
	 * We solve this, and guarantee forward progress, with a rescuer
	 * workqueue per bio_set. If we go to allocate and there are bios on
	 * current->bio_list, we first try the allocation without
	 * __GFP_DIRECT_RECLAIM; if that fails, we punt those bios we would be
	 * blocking to the rescuer workqueue before we retry with the original
	 * gfp_flags.
	 */
	if (current->bio_list &&
	    (!bio_list_empty(&current->bio_list[0]) ||
	     !bio_list_empty(&current->bio_list[1])) &&
	    bs->rescue_workqueue)
		gfp_mask &= ~__GFP_DIRECT_RECLAIM;

	p = mempool_alloc(&bs->bio_pool, gfp_mask);
	if (!p && gfp_mask != saved_gfp) {
		punt_bios_to_rescuer(bs);
		gfp_mask = saved_gfp;
		p = mempool_alloc(&bs->bio_pool, gfp_mask);
	}
	if (unlikely(!p))
		return NULL;

	bio = p + bs->front_pad;
	if (nr_vecs > BIO_INLINE_VECS) {
		struct bio_vec *bvl = NULL;

		bvl = bvec_alloc(&bs->bvec_pool, &nr_vecs, gfp_mask);
		if (!bvl && gfp_mask != saved_gfp) {
			punt_bios_to_rescuer(bs);
			gfp_mask = saved_gfp;
			bvl = bvec_alloc(&bs->bvec_pool, &nr_vecs, gfp_mask);
		}
		if (unlikely(!bvl))
			goto err_free;

		bio_init(bio, bdev, bvl, nr_vecs, opf);
	} else if (nr_vecs) {
		bio_init(bio, bdev, bio->bi_inline_vecs, BIO_INLINE_VECS, opf);
	} else {
		bio_init(bio, bdev, NULL, 0, opf);
	}

	bio->bi_pool = bs;
	return bio;

err_free:
	mempool_free(p, &bs->bio_pool);
	return NULL;
}
EXPORT_SYMBOL(bio_alloc_bioset);

/**
 * bio_kmalloc - kmalloc a bio
 * @nr_vecs:	number of bio_vecs to allocate
 * @gfp_mask:   the GFP_* mask given to the slab allocator
 *
 * Use kmalloc to allocate a bio (including bvecs).  The bio must be initialized
 * using bio_init() before use.  To free a bio returned from this function use
 * kfree() after calling bio_uninit().  A bio returned from this function can
 * be reused by calling bio_uninit() before calling bio_init() again.
 *
 * Note that unlike bio_alloc() or bio_alloc_bioset() allocations from this
 * function are not backed by a mempool can can fail.  Do not use this function
 * for allocations in the file system I/O path.
 *
 * Returns: Pointer to new bio on success, NULL on failure.
 */
struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask)
{
	struct bio *bio;

	if (nr_vecs > UIO_MAXIOV)
		return NULL;
	return kmalloc(struct_size(bio, bi_inline_vecs, nr_vecs), gfp_mask);
}
EXPORT_SYMBOL(bio_kmalloc);

void zero_fill_bio(struct bio *bio)
{
	struct bio_vec bv;
	struct bvec_iter iter;

	bio_for_each_segment(bv, bio, iter)
		memzero_bvec(&bv);
}
EXPORT_SYMBOL(zero_fill_bio);

/**
 * bio_truncate - truncate the bio to small size of @new_size
 * @bio:	the bio to be truncated
 * @new_size:	new size for truncating the bio
 *
 * Description:
 *   Truncate the bio to new size of @new_size. If bio_op(bio) is
 *   REQ_OP_READ, zero the truncated part. This function should only
 *   be used for handling corner cases, such as bio eod.
 */
static void bio_truncate(struct bio *bio, unsigned new_size)
{
	struct bio_vec bv;
	struct bvec_iter iter;
	unsigned int done = 0;
	bool truncated = false;

	if (new_size >= bio->bi_iter.bi_size)
		return;

	if (bio_op(bio) != REQ_OP_READ)
		goto exit;

	bio_for_each_segment(bv, bio, iter) {
		if (done + bv.bv_len > new_size) {
			unsigned offset;

			if (!truncated)
				offset = new_size - done;
			else
				offset = 0;
			zero_user(bv.bv_page, bv.bv_offset + offset,
				  bv.bv_len - offset);
			truncated = true;
		}
		done += bv.bv_len;
	}

 exit:
	/*
	 * Don't touch bvec table here and make it really immutable, since
	 * fs bio user has to retrieve all pages via bio_for_each_segment_all
	 * in its .end_bio() callback.
	 *
	 * It is enough to truncate bio by updating .bi_size since we can make
	 * correct bvec with the updated .bi_size for drivers.
	 */
	bio->bi_iter.bi_size = new_size;
}

/**
 * guard_bio_eod - truncate a BIO to fit the block device
 * @bio:	bio to truncate
 *
 * This allows us to do IO even on the odd last sectors of a device, even if the
 * block size is some multiple of the physical sector size.
 *
 * We'll just truncate the bio to the size of the device, and clear the end of
 * the buffer head manually.  Truly out-of-range accesses will turn into actual
 * I/O errors, this only handles the "we need to be able to do I/O at the final
 * sector" case.
 */
void guard_bio_eod(struct bio *bio)
{
	sector_t maxsector = bdev_nr_sectors(bio->bi_bdev);

	if (!maxsector)
		return;

	/*
	 * If the *whole* IO is past the end of the device,
	 * let it through, and the IO layer will turn it into
	 * an EIO.
	 */
	if (unlikely(bio->bi_iter.bi_sector >= maxsector))
		return;

	maxsector -= bio->bi_iter.bi_sector;
	if (likely((bio->bi_iter.bi_size >> 9) <= maxsector))
		return;

	bio_truncate(bio, maxsector << 9);
}

#define ALLOC_CACHE_MAX		512
#define ALLOC_CACHE_SLACK	 64

static void bio_alloc_cache_prune(struct bio_alloc_cache *cache,
				  unsigned int nr)
{
	unsigned int i = 0;
	struct bio *bio;

	while ((bio = cache->free_list) != NULL) {
		cache->free_list = bio->bi_next;
		cache->nr--;
		bio_free(bio);
		if (++i == nr)
			break;
	}
}

static int bio_cpu_dead(unsigned int cpu, struct hlist_node *node)
{
	struct bio_set *bs;

	bs = hlist_entry_safe(node, struct bio_set, cpuhp_dead);
	if (bs->cache) {
		struct bio_alloc_cache *cache = per_cpu_ptr(bs->cache, cpu);

		bio_alloc_cache_prune(cache, -1U);
	}
	return 0;
}

static void bio_alloc_cache_destroy(struct bio_set *bs)
{
	int cpu;

	if (!bs->cache)
		return;

	cpuhp_state_remove_instance_nocalls(CPUHP_BIO_DEAD, &bs->cpuhp_dead);
	for_each_possible_cpu(cpu) {
		struct bio_alloc_cache *cache;

		cache = per_cpu_ptr(bs->cache, cpu);
		bio_alloc_cache_prune(cache, -1U);
	}
	free_percpu(bs->cache);
	bs->cache = NULL;
}

/**
 * bio_put - release a reference to a bio
 * @bio:   bio to release reference to
 *
 * Description:
 *   Put a reference to a &struct bio, either one you have gotten with
 *   bio_alloc, bio_get or bio_clone_*. The last put of a bio will free it.
 **/
void bio_put(struct bio *bio)
{
	if (unlikely(bio_flagged(bio, BIO_REFFED))) {
		BUG_ON(!atomic_read(&bio->__bi_cnt));
		if (!atomic_dec_and_test(&bio->__bi_cnt))
			return;
	}

	if (bio->bi_opf & REQ_ALLOC_CACHE) {
		struct bio_alloc_cache *cache;

		bio_uninit(bio);
		cache = per_cpu_ptr(bio->bi_pool->cache, get_cpu());
		bio->bi_next = cache->free_list;
		cache->free_list = bio;
		if (++cache->nr > ALLOC_CACHE_MAX + ALLOC_CACHE_SLACK)
			bio_alloc_cache_prune(cache, ALLOC_CACHE_SLACK);
		put_cpu();
	} else {
		bio_free(bio);
	}
}
EXPORT_SYMBOL(bio_put);

static int __bio_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp)
{
	bio_set_flag(bio, BIO_CLONED);
	if (bio_flagged(bio_src, BIO_THROTTLED))
		bio_set_flag(bio, BIO_THROTTLED);
	bio->bi_ioprio = bio_src->bi_ioprio;
	bio->bi_iter = bio_src->bi_iter;

	if (bio->bi_bdev) {
		if (bio->bi_bdev == bio_src->bi_bdev &&
		    bio_flagged(bio_src, BIO_REMAPPED))
			bio_set_flag(bio, BIO_REMAPPED);
		bio_clone_blkg_association(bio, bio_src);
	}

	if (bio_crypt_clone(bio, bio_src, gfp) < 0)
		return -ENOMEM;
	if (bio_integrity(bio_src) &&
	    bio_integrity_clone(bio, bio_src, gfp) < 0)
		return -ENOMEM;
	return 0;
}

/**
 * bio_alloc_clone - clone a bio that shares the original bio's biovec
 * @bdev: block_device to clone onto
 * @bio_src: bio to clone from
 * @gfp: allocation priority
 * @bs: bio_set to allocate from
 *
 * Allocate a new bio that is a clone of @bio_src. The caller owns the returned
 * bio, but not the actual data it points to.
 *
 * The caller must ensure that the return bio is not freed before @bio_src.
 */
struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src,
		gfp_t gfp, struct bio_set *bs)
{
	struct bio *bio;

	bio = bio_alloc_bioset(bdev, 0, bio_src->bi_opf, gfp, bs);
	if (!bio)
		return NULL;

	if (__bio_clone(bio, bio_src, gfp) < 0) {
		bio_put(bio);
		return NULL;
	}
	bio->bi_io_vec = bio_src->bi_io_vec;

	return bio;
}
EXPORT_SYMBOL(bio_alloc_clone);

/**
 * bio_init_clone - clone a bio that shares the original bio's biovec
 * @bdev: block_device to clone onto
 * @bio: bio to clone into
 * @bio_src: bio to clone from
 * @gfp: allocation priority
 *
 * Initialize a new bio in caller provided memory that is a clone of @bio_src.
 * The caller owns the returned bio, but not the actual data it points to.
 *
 * The caller must ensure that @bio_src is not freed before @bio.
 */
int bio_init_clone(struct block_device *bdev, struct bio *bio,
		struct bio *bio_src, gfp_t gfp)
{
	int ret;

	bio_init(bio, bdev, bio_src->bi_io_vec, 0, bio_src->bi_opf);
	ret = __bio_clone(bio, bio_src, gfp);
	if (ret)
		bio_uninit(bio);
	return ret;
}
EXPORT_SYMBOL(bio_init_clone);

/**
 * bio_full - check if the bio is full
 * @bio:	bio to check
 * @len:	length of one segment to be added
 *
 * Return true if @bio is full and one segment with @len bytes can't be
 * added to the bio, otherwise return false
 */
static inline bool bio_full(struct bio *bio, unsigned len)
{
	if (bio->bi_vcnt >= bio->bi_max_vecs)
		return true;
	if (bio->bi_iter.bi_size > UINT_MAX - len)
		return true;
	return false;
}

static inline bool page_is_mergeable(const struct bio_vec *bv,
		struct page *page, unsigned int len, unsigned int off,
		bool *same_page)
{
	size_t bv_end = bv->bv_offset + bv->bv_len;
	phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + bv_end - 1;
	phys_addr_t page_addr = page_to_phys(page);

	if (vec_end_addr + 1 != page_addr + off)
		return false;
	if (xen_domain() && !xen_biovec_phys_mergeable(bv, page))
		return false;

	*same_page = ((vec_end_addr & PAGE_MASK) == page_addr);
	if (*same_page)
		return true;
	return (bv->bv_page + bv_end / PAGE_SIZE) == (page + off / PAGE_SIZE);
}

/**
 * __bio_try_merge_page - try appending data to an existing bvec.
 * @bio: destination bio
 * @page: start page to add
 * @len: length of the data to add
 * @off: offset of the data relative to @page
 * @same_page: return if the segment has been merged inside the same page
 *
 * Try to add the data at @page + @off to the last bvec of @bio.  This is a
 * useful optimisation for file systems with a block size smaller than the
 * page size.
 *
 * Warn if (@len, @off) crosses pages in case that @same_page is true.
 *
 * Return %true on success or %false on failure.
 */
static bool __bio_try_merge_page(struct bio *bio, struct page *page,
		unsigned int len, unsigned int off, bool *same_page)
{
	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
		return false;

	if (bio->bi_vcnt > 0) {
		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];

		if (page_is_mergeable(bv, page, len, off, same_page)) {
			if (bio->bi_iter.bi_size > UINT_MAX - len) {
				*same_page = false;
				return false;
			}
			bv->bv_len += len;
			bio->bi_iter.bi_size += len;
			return true;
		}
	}
	return false;
}

/*
 * Try to merge a page into a segment, while obeying the hardware segment
 * size limit.  This is not for normal read/write bios, but for passthrough
 * or Zone Append operations that we can't split.
 */
static bool bio_try_merge_hw_seg(struct request_queue *q, struct bio *bio,
				 struct page *page, unsigned len,
				 unsigned offset, bool *same_page)
{
	struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
	unsigned long mask = queue_segment_boundary(q);
	phys_addr_t addr1 = page_to_phys(bv->bv_page) + bv->bv_offset;
	phys_addr_t addr2 = page_to_phys(page) + offset + len - 1;

	if ((addr1 | mask) != (addr2 | mask))
		return false;
	if (bv->bv_len + len > queue_max_segment_size(q))
		return false;
	return __bio_try_merge_page(bio, page, len, offset, same_page);
}

/**
 * bio_add_hw_page - attempt to add a page to a bio with hw constraints
 * @q: the target queue
 * @bio: destination bio
 * @page: page to add
 * @len: vec entry length
 * @offset: vec entry offset
 * @max_sectors: maximum number of sectors that can be added
 * @same_page: return if the segment has been merged inside the same page
 *
 * Add a page to a bio while respecting the hardware max_sectors, max_segment
 * and gap limitations.
 */
int bio_add_hw_page(struct request_queue *q, struct bio *bio,
		struct page *page, unsigned int len, unsigned int offset,
		unsigned int max_sectors, bool *same_page)
{
	struct bio_vec *bvec;

	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
		return 0;

	if (((bio->bi_iter.bi_size + len) >> 9) > max_sectors)
		return 0;

	if (bio->bi_vcnt > 0) {
		if (bio_try_merge_hw_seg(q, bio, page, len, offset, same_page))
			return len;

		/*
		 * If the queue doesn't support SG gaps and adding this segment
		 * would create a gap, disallow it.
		 */
		bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
		if (bvec_gap_to_prev(q, bvec, offset))
			return 0;
	}

	if (bio_full(bio, len))
		return 0;

	if (bio->bi_vcnt >= queue_max_segments(q))
		return 0;

	bvec = &bio->bi_io_vec[bio->bi_vcnt];
	bvec->bv_page = page;
	bvec->bv_len = len;
	bvec->bv_offset = offset;
	bio->bi_vcnt++;
	bio->bi_iter.bi_size += len;
	return len;
}

/**
 * bio_add_pc_page	- attempt to add page to passthrough bio
 * @q: the target queue
 * @bio: destination bio
 * @page: page to add
 * @len: vec entry length
 * @offset: vec entry offset
 *
 * Attempt to add a page to the bio_vec maplist. This can fail for a
 * number of reasons, such as the bio being full or target block device
 * limitations. The target block device must allow bio's up to PAGE_SIZE,
 * so it is always possible to add a single page to an empty bio.
 *
 * This should only be used by passthrough bios.
 */
int bio_add_pc_page(struct request_queue *q, struct bio *bio,
		struct page *page, unsigned int len, unsigned int offset)
{
	bool same_page = false;
	return bio_add_hw_page(q, bio, page, len, offset,
			queue_max_hw_sectors(q), &same_page);
}
EXPORT_SYMBOL(bio_add_pc_page);

/**
 * bio_add_zone_append_page - attempt to add page to zone-append bio
 * @bio: destination bio
 * @page: page to add
 * @len: vec entry length
 * @offset: vec entry offset
 *
 * Attempt to add a page to the bio_vec maplist of a bio that will be submitted
 * for a zone-append request. This can fail for a number of reasons, such as the
 * bio being full or the target block device is not a zoned block device or
 * other limitations of the target block device. The target block device must
 * allow bio's up to PAGE_SIZE, so it is always possible to add a single page
 * to an empty bio.
 *
 * Returns: number of bytes added to the bio, or 0 in case of a failure.
 */
int bio_add_zone_append_page(struct bio *bio, struct page *page,
			     unsigned int len, unsigned int offset)
{
	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
	bool same_page = false;

	if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_ZONE_APPEND))
		return 0;

	if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
		return 0;

	return bio_add_hw_page(q, bio, page, len, offset,
			       queue_max_zone_append_sectors(q), &same_page);
}
EXPORT_SYMBOL_GPL(bio_add_zone_append_page);

/**
 * __bio_add_page - add page(s) to a bio in a new segment
 * @bio: destination bio
 * @page: start page to add
 * @len: length of the data to add, may cross pages
 * @off: offset of the data relative to @page, may cross pages
 *
 * Add the data at @page + @off to @bio as a new bvec.  The caller must ensure
 * that @bio has space for another bvec.
 */
void __bio_add_page(struct bio *bio, struct page *page,
		unsigned int len, unsigned int off)
{
	struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt];

	WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
	WARN_ON_ONCE(bio_full(bio, len));

	bv->bv_page = page;
	bv->bv_offset = off;
	bv->bv_len = len;

	bio->bi_iter.bi_size += len;
	bio->bi_vcnt++;

	if (!bio_flagged(bio, BIO_WORKINGSET) && unlikely(PageWorkingset(page)))
		bio_set_flag(bio, BIO_WORKINGSET);
}
EXPORT_SYMBOL_GPL(__bio_add_page);

/**
 *	bio_add_page	-	attempt to add page(s) to bio
 *	@bio: destination bio
 *	@page: start page to add
 *	@len: vec entry length, may cross pages
 *	@offset: vec entry offset relative to @page, may cross pages
 *
 *	Attempt to add page(s) to the bio_vec maplist. This will only fail
 *	if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio.
 */
int bio_add_page(struct bio *bio, struct page *page,
		 unsigned int len, unsigned int offset)
{
	bool same_page = false;

	if (!__bio_try_merge_page(bio, page, len, offset, &same_page)) {
		if (bio_full(bio, len))
			return 0;
		__bio_add_page(bio, page, len, offset);
	}
	return len;
}
EXPORT_SYMBOL(bio_add_page);

/**
 * bio_add_folio - Attempt to add part of a folio to a bio.
 * @bio: BIO to add to.
 * @folio: Folio to add.
 * @len: How many bytes from the folio to add.
 * @off: First byte in this folio to add.
 *
 * Filesystems that use folios can call this function instead of calling
 * bio_add_page() for each page in the folio.  If @off is bigger than
 * PAGE_SIZE, this function can create a bio_vec that starts in a page
 * after the bv_page.  BIOs do not support folios that are 4GiB or larger.
 *
 * Return: Whether the addition was successful.
 */
bool bio_add_folio(struct bio *bio, struct folio *folio, size_t len,
		   size_t off)
{
	if (len > UINT_MAX || off > UINT_MAX)
		return false;
	return bio_add_page(bio, &folio->page, len, off) > 0;
}

void __bio_release_pages(struct bio *bio, bool mark_dirty)
{
	struct bvec_iter_all iter_all;
	struct bio_vec *bvec;

	bio_for_each_segment_all(bvec, bio, iter_all) {
		if (mark_dirty && !PageCompound(bvec->bv_page))
			set_page_dirty_lock(bvec->bv_page);
		put_page(bvec->bv_page);
	}
}
EXPORT_SYMBOL_GPL(__bio_release_pages);

void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
{
	size_t size = iov_iter_count(iter);

	WARN_ON_ONCE(bio->bi_max_vecs);

	if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
		size_t max_sectors = queue_max_zone_append_sectors(q);

		size = min(size, max_sectors << SECTOR_SHIFT);
	}

	bio->bi_vcnt = iter->nr_segs;
	bio->bi_io_vec = (struct bio_vec *)iter->bvec;
	bio->bi_iter.bi_bvec_done = iter->iov_offset;
	bio->bi_iter.bi_size = size;
	bio_set_flag(bio, BIO_NO_PAGE_REF);
	bio_set_flag(bio, BIO_CLONED);
}

static void bio_put_pages(struct page **pages, size_t size, size_t off)
{
	size_t i, nr = DIV_ROUND_UP(size + (off & ~PAGE_MASK), PAGE_SIZE);

	for (i = 0; i < nr; i++)
		put_page(pages[i]);
}

#define PAGE_PTRS_PER_BVEC     (sizeof(struct bio_vec) / sizeof(struct page *))

/**
 * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
 * @bio: bio to add pages to
 * @iter: iov iterator describing the region to be mapped
 *
 * Pins pages from *iter and appends them to @bio's bvec array. The
 * pages will have to be released using put_page() when done.
 * For multi-segment *iter, this function only adds pages from the
 * next non-empty segment of the iov iterator.
 */
static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
{
	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
	unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
	struct page **pages = (struct page **)bv;
	bool same_page = false;
	ssize_t size, left;
	unsigned len, i;
	size_t offset;

	/*
	 * Move page array up in the allocated memory for the bio vecs as far as
	 * possible so that we can start filling biovecs from the beginning
	 * without overwriting the temporary page array.
	*/
	BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
	pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);

	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
	if (unlikely(size <= 0))
		return size ? size : -EFAULT;

	for (left = size, i = 0; left > 0; left -= len, i++) {
		struct page *page = pages[i];

		len = min_t(size_t, PAGE_SIZE - offset, left);

		if (__bio_try_merge_page(bio, page, len, offset, &same_page)) {
			if (same_page)
				put_page(page);
		} else {
			if (WARN_ON_ONCE(bio_full(bio, len))) {
				bio_put_pages(pages + i, left, offset);
				return -EINVAL;
			}
			__bio_add_page(bio, page, len, offset);
		}
		offset = 0;
	}

	iov_iter_advance(iter, size);
	return 0;
}

static int __bio_iov_append_get_pages(struct bio *bio, struct iov_iter *iter)
{
	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
	unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
	unsigned int max_append_sectors = queue_max_zone_append_sectors(q);
	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
	struct page **pages = (struct page **)bv;
	ssize_t size, left;
	unsigned len, i;
	size_t offset;
	int ret = 0;

	if (WARN_ON_ONCE(!max_append_sectors))
		return 0;

	/*
	 * Move page array up in the allocated memory for the bio vecs as far as
	 * possible so that we can start filling biovecs from the beginning
	 * without overwriting the temporary page array.
	 */
	BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
	pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);

	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
	if (unlikely(size <= 0))
		return size ? size : -EFAULT;

	for (left = size, i = 0; left > 0; left -= len, i++) {
		struct page *page = pages[i];
		bool same_page = false;

		len = min_t(size_t, PAGE_SIZE - offset, left);
		if (bio_add_hw_page(q, bio, page, len, offset,
				max_append_sectors, &same_page) != len) {
			bio_put_pages(pages + i, left, offset);
			ret = -EINVAL;
			break;
		}
		if (same_page)
			put_page(page);
		offset = 0;
	}

	iov_iter_advance(iter, size - left);
	return ret;
}

/**
 * bio_iov_iter_get_pages - add user or kernel pages to a bio
 * @bio: bio to add pages to
 * @iter: iov iterator describing the region to be added
 *
 * This takes either an iterator pointing to user memory, or one pointing to
 * kernel pages (BVEC iterator). If we're adding user pages, we pin them and
 * map them into the kernel. On IO completion, the caller should put those
 * pages. For bvec based iterators bio_iov_iter_get_pages() uses the provided
 * bvecs rather than copying them. Hence anyone issuing kiocb based IO needs
 * to ensure the bvecs and pages stay referenced until the submitted I/O is
 * completed by a call to ->ki_complete() or returns with an error other than
 * -EIOCBQUEUED. The caller needs to check if the bio is flagged BIO_NO_PAGE_REF
 * on IO completion. If it isn't, then pages should be released.
 *
 * The function tries, but does not guarantee, to pin as many pages as
 * fit into the bio, or are requested in @iter, whatever is smaller. If
 * MM encounters an error pinning the requested pages, it stops. Error
 * is returned only if 0 pages could be pinned.
 *
 * It's intended for direct IO, so doesn't do PSI tracking, the caller is
 * responsible for setting BIO_WORKINGSET if necessary.
 */
int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
{
	int ret = 0;

	if (iov_iter_is_bvec(iter)) {
		bio_iov_bvec_set(bio, iter);
		iov_iter_advance(iter, bio->bi_iter.bi_size);
		return 0;
	}

	do {
		if (bio_op(bio) == REQ_OP_ZONE_APPEND)
			ret = __bio_iov_append_get_pages(bio, iter);
		else
			ret = __bio_iov_iter_get_pages(bio, iter);
	} while (!ret && iov_iter_count(iter) && !bio_full(bio, 0));

	/* don't account direct I/O as memory stall */
	bio_clear_flag(bio, BIO_WORKINGSET);
	return bio->bi_vcnt ? 0 : ret;
}
EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);

static void submit_bio_wait_endio(struct bio *bio)
{
	complete(bio->bi_private);
}

/**
 * submit_bio_wait - submit a bio, and wait until it completes
 * @bio: The &struct bio which describes the I/O
 *
 * Simple wrapper around submit_bio(). Returns 0 on success, or the error from
 * bio_endio() on failure.
 *
 * WARNING: Unlike to how submit_bio() is usually used, this function does not
 * result in bio reference to be consumed. The caller must drop the reference
 * on his own.
 */
int submit_bio_wait(struct bio *bio)
{
	DECLARE_COMPLETION_ONSTACK_MAP(done,
			bio->bi_bdev->bd_disk->lockdep_map);
	unsigned long hang_check;

	bio->bi_private = &done;
	bio->bi_end_io = submit_bio_wait_endio;
	bio->bi_opf |= REQ_SYNC;
	submit_bio(bio);

	/* Prevent hang_check timer from firing at us during very long I/O */
	hang_check = sysctl_hung_task_timeout_secs;
	if (hang_check)
		while (!wait_for_completion_io_timeout(&done,
					hang_check * (HZ/2)))
			;
	else
		wait_for_completion_io(&done);

	return blk_status_to_errno(bio->bi_status);
}
EXPORT_SYMBOL(submit_bio_wait);

void __bio_advance(struct bio *bio, unsigned bytes)
{
	if (bio_integrity(bio))
		bio_integrity_advance(bio, bytes);

	bio_crypt_advance(bio, bytes);
	bio_advance_iter(bio, &bio->bi_iter, bytes);
}
EXPORT_SYMBOL(__bio_advance);

void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
			struct bio *src, struct bvec_iter *src_iter)
{
	while (src_iter->bi_size && dst_iter->bi_size) {
		struct bio_vec src_bv = bio_iter_iovec(src, *src_iter);
		struct bio_vec dst_bv = bio_iter_iovec(dst, *dst_iter);
		unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len);
		void *src_buf = bvec_kmap_local(&src_bv);
		void *dst_buf = bvec_kmap_local(&dst_bv);

		memcpy(dst_buf, src_buf, bytes);

		kunmap_local(dst_buf);
		kunmap_local(src_buf);

		bio_advance_iter_single(src, src_iter, bytes);
		bio_advance_iter_single(dst, dst_iter, bytes);
	}
}
EXPORT_SYMBOL(bio_copy_data_iter);

/**
 * bio_copy_data - copy contents of data buffers from one bio to another
 * @src: source bio
 * @dst: destination bio
 *
 * Stops when it reaches the end of either @src or @dst - that is, copies
 * min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of bios).
 */
void bio_copy_data(struct bio *dst, struct bio *src)
{
	struct bvec_iter src_iter = src->bi_iter;
	struct bvec_iter dst_iter = dst->bi_iter;

	bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
}
EXPORT_SYMBOL(bio_copy_data);

void bio_free_pages(struct bio *bio)
{
	struct bio_vec *bvec;
	struct bvec_iter_all iter_all;

	bio_for_each_segment_all(bvec, bio, iter_all)
		__free_page(bvec->bv_page);
}
EXPORT_SYMBOL(bio_free_pages);

/*
 * bio_set_pages_dirty() and bio_check_pages_dirty() are support functions
 * for performing direct-IO in BIOs.
 *
 * The problem is that we cannot run set_page_dirty() from interrupt context
 * because the required locks are not interrupt-safe.  So what we can do is to
 * mark the pages dirty _before_ performing IO.  And in interrupt context,
 * check that the pages are still dirty.   If so, fine.  If not, redirty them
 * in process context.
 *
 * We special-case compound pages here: normally this means reads into hugetlb
 * pages.  The logic in here doesn't really work right for compound pages
 * because the VM does not uniformly chase down the head page in all cases.
 * But dirtiness of compound pages is pretty meaningless anyway: the VM doesn't
 * handle them at all.  So we skip compound pages here at an early stage.
 *
 * Note that this code is very hard to test under normal circumstances because
 * direct-io pins the pages with get_user_pages().  This makes
 * is_page_cache_freeable return false, and the VM will not clean the pages.
 * But other code (eg, flusher threads) could clean the pages if they are mapped
 * pagecache.
 *
 * Simply disabling the call to bio_set_pages_dirty() is a good way to test the
 * deferred bio dirtying paths.
 */

/*
 * bio_set_pages_dirty() will mark all the bio's pages as dirty.
 */
void bio_set_pages_dirty(struct bio *bio)
{
	struct bio_vec *bvec;
	struct bvec_iter_all iter_all;

	bio_for_each_segment_all(bvec, bio, iter_all) {
		if (!PageCompound(bvec->bv_page))
			set_page_dirty_lock(bvec->bv_page);
	}
}

/*
 * bio_check_pages_dirty() will check that all the BIO's pages are still dirty.
 * If they are, then fine.  If, however, some pages are clean then they must
 * have been written out during the direct-IO read.  So we take another ref on
 * the BIO and re-dirty the pages in process context.
 *
 * It is expected that bio_check_pages_dirty() will wholly own the BIO from
 * here on.  It will run one put_page() against each page and will run one
 * bio_put() against the BIO.
 */

static void bio_dirty_fn(struct work_struct *work);

static DECLARE_WORK(bio_dirty_work, bio_dirty_fn);
static DEFINE_SPINLOCK(bio_dirty_lock);
static struct bio *bio_dirty_list;

/*
 * This runs in process context
 */
static void bio_dirty_fn(struct work_struct *work)
{
	struct bio *bio, *next;

	spin_lock_irq(&bio_dirty_lock);
	next = bio_dirty_list;
	bio_dirty_list = NULL;
	spin_unlock_irq(&bio_dirty_lock);

	while ((bio = next) != NULL) {
		next = bio->bi_private;

		bio_release_pages(bio, true);
		bio_put(bio);
	}
}

void bio_check_pages_dirty(struct bio *bio)
{
	struct bio_vec *bvec;
	unsigned long flags;
	struct bvec_iter_all iter_all;

	bio_for_each_segment_all(bvec, bio, iter_all) {
		if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page))
			goto defer;
	}

	bio_release_pages(bio, false);
	bio_put(bio);
	return;
defer:
	spin_lock_irqsave(&bio_dirty_lock, flags);
	bio->bi_private = bio_dirty_list;
	bio_dirty_list = bio;
	spin_unlock_irqrestore(&bio_dirty_lock, flags);
	schedule_work(&bio_dirty_work);
}

static inline bool bio_remaining_done(struct bio *bio)
{
	/*
	 * If we're not chaining, then ->__bi_remaining is always 1 and
	 * we always end io on the first invocation.
	 */
	if (!bio_flagged(bio, BIO_CHAIN))
		return true;

	BUG_ON(atomic_read(&bio->__bi_remaining) <= 0);

	if (atomic_dec_and_test(&bio->__bi_remaining)) {
		bio_clear_flag(bio, BIO_CHAIN);
		return true;
	}

	return false;
}

/**
 * bio_endio - end I/O on a bio
 * @bio:	bio
 *
 * Description:
 *   bio_endio() will end I/O on the whole bio. bio_endio() is the preferred
 *   way to end I/O on a bio. No one should call bi_end_io() directly on a
 *   bio unless they own it and thus know that it has an end_io function.
 *
 *   bio_endio() can be called several times on a bio that has been chained
 *   using bio_chain().  The ->bi_end_io() function will only be called the
 *   last time.
 **/
void bio_endio(struct bio *bio)
{
again:
	if (!bio_remaining_done(bio))
		return;
	if (!bio_integrity_endio(bio))
		return;

	rq_qos_done_bio(bio);

	if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
		trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio);
		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
	}

	/*
	 * Need to have a real endio function for chained bios, otherwise
	 * various corner cases will break (like stacking block devices that
	 * save/restore bi_end_io) - however, we want to avoid unbounded
	 * recursion and blowing the stack. Tail call optimization would
	 * handle this, but compiling with frame pointers also disables
	 * gcc's sibling call optimization.
	 */
	if (bio->bi_end_io == bio_chain_endio) {
		bio = __bio_chain_endio(bio);
		goto again;
	}

	blk_throtl_bio_endio(bio);
	/* release cgroup info */
	bio_uninit(bio);
	if (bio->bi_end_io)
		bio->bi_end_io(bio);
}
EXPORT_SYMBOL(bio_endio);

/**
 * bio_split - split a bio
 * @bio:	bio to split
 * @sectors:	number of sectors to split from the front of @bio
 * @gfp:	gfp mask
 * @bs:		bio set to allocate from
 *
 * Allocates and returns a new bio which represents @sectors from the start of
 * @bio, and updates @bio to represent the remaining sectors.
 *
 * Unless this is a discard request the newly allocated bio will point
 * to @bio's bi_io_vec. It is the caller's responsibility to ensure that
 * neither @bio nor @bs are freed before the split bio.
 */
struct bio *bio_split(struct bio *bio, int sectors,
		      gfp_t gfp, struct bio_set *bs)
{
	struct bio *split;

	BUG_ON(sectors <= 0);
	BUG_ON(sectors >= bio_sectors(bio));

	/* Zone append commands cannot be split */
	if (WARN_ON_ONCE(bio_op(bio) == REQ_OP_ZONE_APPEND))
		return NULL;

	split = bio_alloc_clone(bio->bi_bdev, bio, gfp, bs);
	if (!split)
		return NULL;

	split->bi_iter.bi_size = sectors << 9;

	if (bio_integrity(split))
		bio_integrity_trim(split);

	bio_advance(bio, split->bi_iter.bi_size);

	if (bio_flagged(bio, BIO_TRACE_COMPLETION))
		bio_set_flag(split, BIO_TRACE_COMPLETION);

	return split;
}
EXPORT_SYMBOL(bio_split);

/**
 * bio_trim - trim a bio
 * @bio:	bio to trim
 * @offset:	number of sectors to trim from the front of @bio
 * @size:	size we want to trim @bio to, in sectors
 *
 * This function is typically used for bios that are cloned and submitted
 * to the underlying device in parts.
 */
void bio_trim(struct bio *bio, sector_t offset, sector_t size)
{
	if (WARN_ON_ONCE(offset > BIO_MAX_SECTORS || size > BIO_MAX_SECTORS ||
			 offset + size > bio_sectors(bio)))
		return;

	size <<= 9;
	if (offset == 0 && size == bio->bi_iter.bi_size)
		return;

	bio_advance(bio, offset << 9);
	bio->bi_iter.bi_size = size;

	if (bio_integrity(bio))
		bio_integrity_trim(bio);
}
EXPORT_SYMBOL_GPL(bio_trim);

/*
 * create memory pools for biovec's in a bio_set.
 * use the global biovec slabs created for general use.
 */
int biovec_init_pool(mempool_t *pool, int pool_entries)
{
	struct biovec_slab *bp = bvec_slabs + ARRAY_SIZE(bvec_slabs) - 1;

	return mempool_init_slab_pool(pool, pool_entries, bp->slab);
}

/*
 * bioset_exit - exit a bioset initialized with bioset_init()
 *
 * May be called on a zeroed but uninitialized bioset (i.e. allocated with
 * kzalloc()).
 */
void bioset_exit(struct bio_set *bs)
{
	bio_alloc_cache_destroy(bs);
	if (bs->rescue_workqueue)
		destroy_workqueue(bs->rescue_workqueue);
	bs->rescue_workqueue = NULL;

	mempool_exit(&bs->bio_pool);
	mempool_exit(&bs->bvec_pool);

	bioset_integrity_free(bs);
	if (bs->bio_slab)
		bio_put_slab(bs);
	bs->bio_slab = NULL;
}
EXPORT_SYMBOL(bioset_exit);

/**
 * bioset_init - Initialize a bio_set
 * @bs:		pool to initialize
 * @pool_size:	Number of bio and bio_vecs to cache in the mempool
 * @front_pad:	Number of bytes to allocate in front of the returned bio
 * @flags:	Flags to modify behavior, currently %BIOSET_NEED_BVECS
 *              and %BIOSET_NEED_RESCUER
 *
 * Description:
 *    Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
 *    to ask for a number of bytes to be allocated in front of the bio.
 *    Front pad allocation is useful for embedding the bio inside
 *    another structure, to avoid allocating extra data to go with the bio.
 *    Note that the bio must be embedded at the END of that structure always,
 *    or things will break badly.
 *    If %BIOSET_NEED_BVECS is set in @flags, a separate pool will be allocated
 *    for allocating iovecs.  This pool is not needed e.g. for bio_init_clone().
 *    If %BIOSET_NEED_RESCUER is set, a workqueue is created which can be used
 *    to dispatch queued requests when the mempool runs out of space.
 *
 */
int bioset_init(struct bio_set *bs,
		unsigned int pool_size,
		unsigned int front_pad,
		int flags)
{
	bs->front_pad = front_pad;
	if (flags & BIOSET_NEED_BVECS)
		bs->back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec);
	else
		bs->back_pad = 0;

	spin_lock_init(&bs->rescue_lock);
	bio_list_init(&bs->rescue_list);
	INIT_WORK(&bs->rescue_work, bio_alloc_rescue);

	bs->bio_slab = bio_find_or_create_slab(bs);
	if (!bs->bio_slab)
		return -ENOMEM;

	if (mempool_init_slab_pool(&bs->bio_pool, pool_size, bs->bio_slab))
		goto bad;

	if ((flags & BIOSET_NEED_BVECS) &&
	    biovec_init_pool(&bs->bvec_pool, pool_size))
		goto bad;

	if (flags & BIOSET_NEED_RESCUER) {
		bs->rescue_workqueue = alloc_workqueue("bioset",
							WQ_MEM_RECLAIM, 0);
		if (!bs->rescue_workqueue)
			goto bad;
	}
	if (flags & BIOSET_PERCPU_CACHE) {
		bs->cache = alloc_percpu(struct bio_alloc_cache);
		if (!bs->cache)
			goto bad;
		cpuhp_state_add_instance_nocalls(CPUHP_BIO_DEAD, &bs->cpuhp_dead);
	}

	return 0;
bad:
	bioset_exit(bs);
	return -ENOMEM;
}
EXPORT_SYMBOL(bioset_init);

static int __init init_bio(void)
{
	int i;

	bio_integrity_init();

	for (i = 0; i < ARRAY_SIZE(bvec_slabs); i++) {
		struct biovec_slab *bvs = bvec_slabs + i;

		bvs->slab = kmem_cache_create(bvs->name,
				bvs->nr_vecs * sizeof(struct bio_vec), 0,
				SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
	}

	cpuhp_setup_state_multi(CPUHP_BIO_DEAD, "block/bio:dead", NULL,
					bio_cpu_dead);

	if (bioset_init(&fs_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS))
		panic("bio: can't allocate bios\n");

	if (bioset_integrity_create(&fs_bio_set, BIO_POOL_SIZE))
		panic("bio: can't create integrity pool\n");

	return 0;
}
subsys_initcall(init_bio);