summaryrefslogtreecommitdiff
path: root/fs/iomap/buffered-io.c
blob: 6f4c97a6d7e9dcdaa5aa9a06159d33d91c0aa9f6 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2010 Red Hat, Inc.
 * Copyright (C) 2016-2019 Christoph Hellwig.
 */
#include <linux/module.h>
#include <linux/compiler.h>
#include <linux/fs.h>
#include <linux/iomap.h>
#include <linux/pagemap.h>
#include <linux/uio.h>
#include <linux/buffer_head.h>
#include <linux/dax.h>
#include <linux/writeback.h>
#include <linux/list_sort.h>
#include <linux/swap.h>
#include <linux/bio.h>
#include <linux/sched/signal.h>
#include <linux/migrate.h>
#include "trace.h"

#include "../internal.h"

#define IOEND_BATCH_SIZE	4096

/*
 * Structure allocated for each folio when block size < folio size
 * to track sub-folio uptodate status and I/O completions.
 */
struct iomap_page {
	atomic_t		read_bytes_pending;
	atomic_t		write_bytes_pending;
	spinlock_t		uptodate_lock;
	unsigned long		uptodate[];
};

static inline struct iomap_page *to_iomap_page(struct folio *folio)
{
	if (folio_test_private(folio))
		return folio_get_private(folio);
	return NULL;
}

static struct bio_set iomap_ioend_bioset;

static struct iomap_page *
iomap_page_create(struct inode *inode, struct folio *folio, unsigned int flags)
{
	struct iomap_page *iop = to_iomap_page(folio);
	unsigned int nr_blocks = i_blocks_per_folio(inode, folio);
	gfp_t gfp;

	if (iop || nr_blocks <= 1)
		return iop;

	if (flags & IOMAP_NOWAIT)
		gfp = GFP_NOWAIT;
	else
		gfp = GFP_NOFS | __GFP_NOFAIL;

	iop = kzalloc(struct_size(iop, uptodate, BITS_TO_LONGS(nr_blocks)),
		      gfp);
	if (iop) {
		spin_lock_init(&iop->uptodate_lock);
		if (folio_test_uptodate(folio))
			bitmap_fill(iop->uptodate, nr_blocks);
		folio_attach_private(folio, iop);
	}
	return iop;
}

static void iomap_page_release(struct folio *folio)
{
	struct iomap_page *iop = folio_detach_private(folio);
	struct inode *inode = folio->mapping->host;
	unsigned int nr_blocks = i_blocks_per_folio(inode, folio);

	if (!iop)
		return;
	WARN_ON_ONCE(atomic_read(&iop->read_bytes_pending));
	WARN_ON_ONCE(atomic_read(&iop->write_bytes_pending));
	WARN_ON_ONCE(bitmap_full(iop->uptodate, nr_blocks) !=
			folio_test_uptodate(folio));
	kfree(iop);
}

/*
 * Calculate the range inside the folio that we actually need to read.
 */
static void iomap_adjust_read_range(struct inode *inode, struct folio *folio,
		loff_t *pos, loff_t length, size_t *offp, size_t *lenp)
{
	struct iomap_page *iop = to_iomap_page(folio);
	loff_t orig_pos = *pos;
	loff_t isize = i_size_read(inode);
	unsigned block_bits = inode->i_blkbits;
	unsigned block_size = (1 << block_bits);
	size_t poff = offset_in_folio(folio, *pos);
	size_t plen = min_t(loff_t, folio_size(folio) - poff, length);
	unsigned first = poff >> block_bits;
	unsigned last = (poff + plen - 1) >> block_bits;

	/*
	 * If the block size is smaller than the page size, we need to check the
	 * per-block uptodate status and adjust the offset and length if needed
	 * to avoid reading in already uptodate ranges.
	 */
	if (iop) {
		unsigned int i;

		/* move forward for each leading block marked uptodate */
		for (i = first; i <= last; i++) {
			if (!test_bit(i, iop->uptodate))
				break;
			*pos += block_size;
			poff += block_size;
			plen -= block_size;
			first++;
		}

		/* truncate len if we find any trailing uptodate block(s) */
		for ( ; i <= last; i++) {
			if (test_bit(i, iop->uptodate)) {
				plen -= (last - i + 1) * block_size;
				last = i - 1;
				break;
			}
		}
	}

	/*
	 * If the extent spans the block that contains the i_size, we need to
	 * handle both halves separately so that we properly zero data in the
	 * page cache for blocks that are entirely outside of i_size.
	 */
	if (orig_pos <= isize && orig_pos + length > isize) {
		unsigned end = offset_in_folio(folio, isize - 1) >> block_bits;

		if (first <= end && last > end)
			plen -= (last - end) * block_size;
	}

	*offp = poff;
	*lenp = plen;
}

static void iomap_iop_set_range_uptodate(struct folio *folio,
		struct iomap_page *iop, size_t off, size_t len)
{
	struct inode *inode = folio->mapping->host;
	unsigned first = off >> inode->i_blkbits;
	unsigned last = (off + len - 1) >> inode->i_blkbits;
	unsigned long flags;

	spin_lock_irqsave(&iop->uptodate_lock, flags);
	bitmap_set(iop->uptodate, first, last - first + 1);
	if (bitmap_full(iop->uptodate, i_blocks_per_folio(inode, folio)))
		folio_mark_uptodate(folio);
	spin_unlock_irqrestore(&iop->uptodate_lock, flags);
}

static void iomap_set_range_uptodate(struct folio *folio,
		struct iomap_page *iop, size_t off, size_t len)
{
	if (iop)
		iomap_iop_set_range_uptodate(folio, iop, off, len);
	else
		folio_mark_uptodate(folio);
}

static void iomap_finish_folio_read(struct folio *folio, size_t offset,
		size_t len, int error)
{
	struct iomap_page *iop = to_iomap_page(folio);

	if (unlikely(error)) {
		folio_clear_uptodate(folio);
		folio_set_error(folio);
	} else {
		iomap_set_range_uptodate(folio, iop, offset, len);
	}

	if (!iop || atomic_sub_and_test(len, &iop->read_bytes_pending))
		folio_unlock(folio);
}

static void iomap_read_end_io(struct bio *bio)
{
	int error = blk_status_to_errno(bio->bi_status);
	struct folio_iter fi;

	bio_for_each_folio_all(fi, bio)
		iomap_finish_folio_read(fi.folio, fi.offset, fi.length, error);
	bio_put(bio);
}

struct iomap_readpage_ctx {
	struct folio		*cur_folio;
	bool			cur_folio_in_bio;
	struct bio		*bio;
	struct readahead_control *rac;
};

/**
 * iomap_read_inline_data - copy inline data into the page cache
 * @iter: iteration structure
 * @folio: folio to copy to
 *
 * Copy the inline data in @iter into @folio and zero out the rest of the folio.
 * Only a single IOMAP_INLINE extent is allowed at the end of each file.
 * Returns zero for success to complete the read, or the usual negative errno.
 */
static int iomap_read_inline_data(const struct iomap_iter *iter,
		struct folio *folio)
{
	struct iomap_page *iop;
	const struct iomap *iomap = iomap_iter_srcmap(iter);
	size_t size = i_size_read(iter->inode) - iomap->offset;
	size_t poff = offset_in_page(iomap->offset);
	size_t offset = offset_in_folio(folio, iomap->offset);
	void *addr;

	if (folio_test_uptodate(folio))
		return 0;

	if (WARN_ON_ONCE(size > PAGE_SIZE - poff))
		return -EIO;
	if (WARN_ON_ONCE(size > PAGE_SIZE -
			 offset_in_page(iomap->inline_data)))
		return -EIO;
	if (WARN_ON_ONCE(size > iomap->length))
		return -EIO;
	if (offset > 0)
		iop = iomap_page_create(iter->inode, folio, iter->flags);
	else
		iop = to_iomap_page(folio);

	addr = kmap_local_folio(folio, offset);
	memcpy(addr, iomap->inline_data, size);
	memset(addr + size, 0, PAGE_SIZE - poff - size);
	kunmap_local(addr);
	iomap_set_range_uptodate(folio, iop, offset, PAGE_SIZE - poff);
	return 0;
}

static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter,
		loff_t pos)
{
	const struct iomap *srcmap = iomap_iter_srcmap(iter);

	return srcmap->type != IOMAP_MAPPED ||
		(srcmap->flags & IOMAP_F_NEW) ||
		pos >= i_size_read(iter->inode);
}

static loff_t iomap_readpage_iter(const struct iomap_iter *iter,
		struct iomap_readpage_ctx *ctx, loff_t offset)
{
	const struct iomap *iomap = &iter->iomap;
	loff_t pos = iter->pos + offset;
	loff_t length = iomap_length(iter) - offset;
	struct folio *folio = ctx->cur_folio;
	struct iomap_page *iop;
	loff_t orig_pos = pos;
	size_t poff, plen;
	sector_t sector;

	if (iomap->type == IOMAP_INLINE)
		return iomap_read_inline_data(iter, folio);

	/* zero post-eof blocks as the page may be mapped */
	iop = iomap_page_create(iter->inode, folio, iter->flags);
	iomap_adjust_read_range(iter->inode, folio, &pos, length, &poff, &plen);
	if (plen == 0)
		goto done;

	if (iomap_block_needs_zeroing(iter, pos)) {
		folio_zero_range(folio, poff, plen);
		iomap_set_range_uptodate(folio, iop, poff, plen);
		goto done;
	}

	ctx->cur_folio_in_bio = true;
	if (iop)
		atomic_add(plen, &iop->read_bytes_pending);

	sector = iomap_sector(iomap, pos);
	if (!ctx->bio ||
	    bio_end_sector(ctx->bio) != sector ||
	    !bio_add_folio(ctx->bio, folio, plen, poff)) {
		gfp_t gfp = mapping_gfp_constraint(folio->mapping, GFP_KERNEL);
		gfp_t orig_gfp = gfp;
		unsigned int nr_vecs = DIV_ROUND_UP(length, PAGE_SIZE);

		if (ctx->bio)
			submit_bio(ctx->bio);

		if (ctx->rac) /* same as readahead_gfp_mask */
			gfp |= __GFP_NORETRY | __GFP_NOWARN;
		ctx->bio = bio_alloc(iomap->bdev, bio_max_segs(nr_vecs),
				     REQ_OP_READ, gfp);
		/*
		 * If the bio_alloc fails, try it again for a single page to
		 * avoid having to deal with partial page reads.  This emulates
		 * what do_mpage_read_folio does.
		 */
		if (!ctx->bio) {
			ctx->bio = bio_alloc(iomap->bdev, 1, REQ_OP_READ,
					     orig_gfp);
		}
		if (ctx->rac)
			ctx->bio->bi_opf |= REQ_RAHEAD;
		ctx->bio->bi_iter.bi_sector = sector;
		ctx->bio->bi_end_io = iomap_read_end_io;
		bio_add_folio(ctx->bio, folio, plen, poff);
	}

done:
	/*
	 * Move the caller beyond our range so that it keeps making progress.
	 * For that, we have to include any leading non-uptodate ranges, but
	 * we can skip trailing ones as they will be handled in the next
	 * iteration.
	 */
	return pos - orig_pos + plen;
}

int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops)
{
	struct iomap_iter iter = {
		.inode		= folio->mapping->host,
		.pos		= folio_pos(folio),
		.len		= folio_size(folio),
	};
	struct iomap_readpage_ctx ctx = {
		.cur_folio	= folio,
	};
	int ret;

	trace_iomap_readpage(iter.inode, 1);

	while ((ret = iomap_iter(&iter, ops)) > 0)
		iter.processed = iomap_readpage_iter(&iter, &ctx, 0);

	if (ret < 0)
		folio_set_error(folio);

	if (ctx.bio) {
		submit_bio(ctx.bio);
		WARN_ON_ONCE(!ctx.cur_folio_in_bio);
	} else {
		WARN_ON_ONCE(ctx.cur_folio_in_bio);
		folio_unlock(folio);
	}

	/*
	 * Just like mpage_readahead and block_read_full_folio, we always
	 * return 0 and just set the folio error flag on errors.  This
	 * should be cleaned up throughout the stack eventually.
	 */
	return 0;
}
EXPORT_SYMBOL_GPL(iomap_read_folio);

static loff_t iomap_readahead_iter(const struct iomap_iter *iter,
		struct iomap_readpage_ctx *ctx)
{
	loff_t length = iomap_length(iter);
	loff_t done, ret;

	for (done = 0; done < length; done += ret) {
		if (ctx->cur_folio &&
		    offset_in_folio(ctx->cur_folio, iter->pos + done) == 0) {
			if (!ctx->cur_folio_in_bio)
				folio_unlock(ctx->cur_folio);
			ctx->cur_folio = NULL;
		}
		if (!ctx->cur_folio) {
			ctx->cur_folio = readahead_folio(ctx->rac);
			ctx->cur_folio_in_bio = false;
		}
		ret = iomap_readpage_iter(iter, ctx, done);
		if (ret <= 0)
			return ret;
	}

	return done;
}

/**
 * iomap_readahead - Attempt to read pages from a file.
 * @rac: Describes the pages to be read.
 * @ops: The operations vector for the filesystem.
 *
 * This function is for filesystems to call to implement their readahead
 * address_space operation.
 *
 * Context: The @ops callbacks may submit I/O (eg to read the addresses of
 * blocks from disc), and may wait for it.  The caller may be trying to
 * access a different page, and so sleeping excessively should be avoided.
 * It may allocate memory, but should avoid costly allocations.  This
 * function is called with memalloc_nofs set, so allocations will not cause
 * the filesystem to be reentered.
 */
void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops)
{
	struct iomap_iter iter = {
		.inode	= rac->mapping->host,
		.pos	= readahead_pos(rac),
		.len	= readahead_length(rac),
	};
	struct iomap_readpage_ctx ctx = {
		.rac	= rac,
	};

	trace_iomap_readahead(rac->mapping->host, readahead_count(rac));

	while (iomap_iter(&iter, ops) > 0)
		iter.processed = iomap_readahead_iter(&iter, &ctx);

	if (ctx.bio)
		submit_bio(ctx.bio);
	if (ctx.cur_folio) {
		if (!ctx.cur_folio_in_bio)
			folio_unlock(ctx.cur_folio);
	}
}
EXPORT_SYMBOL_GPL(iomap_readahead);

/*
 * iomap_is_partially_uptodate checks whether blocks within a folio are
 * uptodate or not.
 *
 * Returns true if all blocks which correspond to the specified part
 * of the folio are uptodate.
 */
bool iomap_is_partially_uptodate(struct folio *folio, size_t from, size_t count)
{
	struct iomap_page *iop = to_iomap_page(folio);
	struct inode *inode = folio->mapping->host;
	unsigned first, last, i;

	if (!iop)
		return false;

	/* Caller's range may extend past the end of this folio */
	count = min(folio_size(folio) - from, count);

	/* First and last blocks in range within folio */
	first = from >> inode->i_blkbits;
	last = (from + count - 1) >> inode->i_blkbits;

	for (i = first; i <= last; i++)
		if (!test_bit(i, iop->uptodate))
			return false;
	return true;
}
EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate);

/**
 * iomap_get_folio - get a folio reference for writing
 * @iter: iteration structure
 * @pos: start offset of write
 *
 * Returns a locked reference to the folio at @pos, or an error pointer if the
 * folio could not be obtained.
 */
struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos)
{
	unsigned fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE | FGP_NOFS;
	struct folio *folio;

	if (iter->flags & IOMAP_NOWAIT)
		fgp |= FGP_NOWAIT;

	folio = __filemap_get_folio(iter->inode->i_mapping, pos >> PAGE_SHIFT,
			fgp, mapping_gfp_mask(iter->inode->i_mapping));
	if (folio)
		return folio;

	if (iter->flags & IOMAP_NOWAIT)
		return ERR_PTR(-EAGAIN);
	return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL_GPL(iomap_get_folio);

bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags)
{
	trace_iomap_release_folio(folio->mapping->host, folio_pos(folio),
			folio_size(folio));

	/*
	 * mm accommodates an old ext3 case where clean folios might
	 * not have had the dirty bit cleared.  Thus, it can send actual
	 * dirty folios to ->release_folio() via shrink_active_list();
	 * skip those here.
	 */
	if (folio_test_dirty(folio) || folio_test_writeback(folio))
		return false;
	iomap_page_release(folio);
	return true;
}
EXPORT_SYMBOL_GPL(iomap_release_folio);

void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len)
{
	trace_iomap_invalidate_folio(folio->mapping->host,
					folio_pos(folio) + offset, len);

	/*
	 * If we're invalidating the entire folio, clear the dirty state
	 * from it and release it to avoid unnecessary buildup of the LRU.
	 */
	if (offset == 0 && len == folio_size(folio)) {
		WARN_ON_ONCE(folio_test_writeback(folio));
		folio_cancel_dirty(folio);
		iomap_page_release(folio);
	} else if (folio_test_large(folio)) {
		/* Must release the iop so the page can be split */
		WARN_ON_ONCE(!folio_test_uptodate(folio) &&
			     folio_test_dirty(folio));
		iomap_page_release(folio);
	}
}
EXPORT_SYMBOL_GPL(iomap_invalidate_folio);

static void
iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
{
	loff_t i_size = i_size_read(inode);

	/*
	 * Only truncate newly allocated pages beyoned EOF, even if the
	 * write started inside the existing inode size.
	 */
	if (pos + len > i_size)
		truncate_pagecache_range(inode, max(pos, i_size),
					 pos + len - 1);
}

static int iomap_read_folio_sync(loff_t block_start, struct folio *folio,
		size_t poff, size_t plen, const struct iomap *iomap)
{
	struct bio_vec bvec;
	struct bio bio;

	bio_init(&bio, iomap->bdev, &bvec, 1, REQ_OP_READ);
	bio.bi_iter.bi_sector = iomap_sector(iomap, block_start);
	bio_add_folio(&bio, folio, plen, poff);
	return submit_bio_wait(&bio);
}

static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
		size_t len, struct folio *folio)
{
	const struct iomap *srcmap = iomap_iter_srcmap(iter);
	struct iomap_page *iop;
	loff_t block_size = i_blocksize(iter->inode);
	loff_t block_start = round_down(pos, block_size);
	loff_t block_end = round_up(pos + len, block_size);
	unsigned int nr_blocks = i_blocks_per_folio(iter->inode, folio);
	size_t from = offset_in_folio(folio, pos), to = from + len;
	size_t poff, plen;

	if (folio_test_uptodate(folio))
		return 0;
	folio_clear_error(folio);

	iop = iomap_page_create(iter->inode, folio, iter->flags);
	if ((iter->flags & IOMAP_NOWAIT) && !iop && nr_blocks > 1)
		return -EAGAIN;

	do {
		iomap_adjust_read_range(iter->inode, folio, &block_start,
				block_end - block_start, &poff, &plen);
		if (plen == 0)
			break;

		if (!(iter->flags & IOMAP_UNSHARE) &&
		    (from <= poff || from >= poff + plen) &&
		    (to <= poff || to >= poff + plen))
			continue;

		if (iomap_block_needs_zeroing(iter, block_start)) {
			if (WARN_ON_ONCE(iter->flags & IOMAP_UNSHARE))
				return -EIO;
			folio_zero_segments(folio, poff, from, to, poff + plen);
		} else {
			int status;

			if (iter->flags & IOMAP_NOWAIT)
				return -EAGAIN;

			status = iomap_read_folio_sync(block_start, folio,
					poff, plen, srcmap);
			if (status)
				return status;
		}
		iomap_set_range_uptodate(folio, iop, poff, plen);
	} while ((block_start += plen) < block_end);

	return 0;
}

static struct folio *__iomap_get_folio(struct iomap_iter *iter, loff_t pos,
		size_t len)
{
	const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops;

	if (folio_ops && folio_ops->get_folio)
		return folio_ops->get_folio(iter, pos, len);
	else
		return iomap_get_folio(iter, pos);
}

static void __iomap_put_folio(struct iomap_iter *iter, loff_t pos, size_t ret,
		struct folio *folio)
{
	const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops;

	if (folio_ops && folio_ops->put_folio) {
		folio_ops->put_folio(iter->inode, pos, ret, folio);
	} else {
		folio_unlock(folio);
		folio_put(folio);
	}
}

static int iomap_write_begin_inline(const struct iomap_iter *iter,
		struct folio *folio)
{
	/* needs more work for the tailpacking case; disable for now */
	if (WARN_ON_ONCE(iomap_iter_srcmap(iter)->offset != 0))
		return -EIO;
	return iomap_read_inline_data(iter, folio);
}

static int iomap_write_begin(struct iomap_iter *iter, loff_t pos,
		size_t len, struct folio **foliop)
{
	const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops;
	const struct iomap *srcmap = iomap_iter_srcmap(iter);
	struct folio *folio;
	int status = 0;

	BUG_ON(pos + len > iter->iomap.offset + iter->iomap.length);
	if (srcmap != &iter->iomap)
		BUG_ON(pos + len > srcmap->offset + srcmap->length);

	if (fatal_signal_pending(current))
		return -EINTR;

	if (!mapping_large_folio_support(iter->inode->i_mapping))
		len = min_t(size_t, len, PAGE_SIZE - offset_in_page(pos));

	folio = __iomap_get_folio(iter, pos, len);
	if (IS_ERR(folio))
		return PTR_ERR(folio);

	/*
	 * Now we have a locked folio, before we do anything with it we need to
	 * check that the iomap we have cached is not stale. The inode extent
	 * mapping can change due to concurrent IO in flight (e.g.
	 * IOMAP_UNWRITTEN state can change and memory reclaim could have
	 * reclaimed a previously partially written page at this index after IO
	 * completion before this write reaches this file offset) and hence we
	 * could do the wrong thing here (zero a page range incorrectly or fail
	 * to zero) and corrupt data.
	 */
	if (folio_ops && folio_ops->iomap_valid) {
		bool iomap_valid = folio_ops->iomap_valid(iter->inode,
							 &iter->iomap);
		if (!iomap_valid) {
			iter->iomap.flags |= IOMAP_F_STALE;
			status = 0;
			goto out_unlock;
		}
	}

	if (pos + len > folio_pos(folio) + folio_size(folio))
		len = folio_pos(folio) + folio_size(folio) - pos;

	if (srcmap->type == IOMAP_INLINE)
		status = iomap_write_begin_inline(iter, folio);
	else if (srcmap->flags & IOMAP_F_BUFFER_HEAD)
		status = __block_write_begin_int(folio, pos, len, NULL, srcmap);
	else
		status = __iomap_write_begin(iter, pos, len, folio);

	if (unlikely(status))
		goto out_unlock;

	*foliop = folio;
	return 0;

out_unlock:
	__iomap_put_folio(iter, pos, 0, folio);
	iomap_write_failed(iter->inode, pos, len);

	return status;
}

static size_t __iomap_write_end(struct inode *inode, loff_t pos, size_t len,
		size_t copied, struct folio *folio)
{
	struct iomap_page *iop = to_iomap_page(folio);
	flush_dcache_folio(folio);

	/*
	 * The blocks that were entirely written will now be uptodate, so we
	 * don't have to worry about a read_folio reading them and overwriting a
	 * partial write.  However, if we've encountered a short write and only
	 * partially written into a block, it will not be marked uptodate, so a
	 * read_folio might come in and destroy our partial write.
	 *
	 * Do the simplest thing and just treat any short write to a
	 * non-uptodate page as a zero-length write, and force the caller to
	 * redo the whole thing.
	 */
	if (unlikely(copied < len && !folio_test_uptodate(folio)))
		return 0;
	iomap_set_range_uptodate(folio, iop, offset_in_folio(folio, pos), len);
	filemap_dirty_folio(inode->i_mapping, folio);
	return copied;
}

static size_t iomap_write_end_inline(const struct iomap_iter *iter,
		struct folio *folio, loff_t pos, size_t copied)
{
	const struct iomap *iomap = &iter->iomap;
	void *addr;

	WARN_ON_ONCE(!folio_test_uptodate(folio));
	BUG_ON(!iomap_inline_data_valid(iomap));

	flush_dcache_folio(folio);
	addr = kmap_local_folio(folio, pos);
	memcpy(iomap_inline_data(iomap, pos), addr, copied);
	kunmap_local(addr);

	mark_inode_dirty(iter->inode);
	return copied;
}

/* Returns the number of bytes copied.  May be 0.  Cannot be an errno. */
static size_t iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len,
		size_t copied, struct folio *folio)
{
	const struct iomap *srcmap = iomap_iter_srcmap(iter);
	loff_t old_size = iter->inode->i_size;
	size_t ret;

	if (srcmap->type == IOMAP_INLINE) {
		ret = iomap_write_end_inline(iter, folio, pos, copied);
	} else if (srcmap->flags & IOMAP_F_BUFFER_HEAD) {
		ret = block_write_end(NULL, iter->inode->i_mapping, pos, len,
				copied, &folio->page, NULL);
	} else {
		ret = __iomap_write_end(iter->inode, pos, len, copied, folio);
	}

	/*
	 * Update the in-memory inode size after copying the data into the page
	 * cache.  It's up to the file system to write the updated size to disk,
	 * preferably after I/O completion so that no stale data is exposed.
	 */
	if (pos + ret > old_size) {
		i_size_write(iter->inode, pos + ret);
		iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
	}
	__iomap_put_folio(iter, pos, ret, folio);

	if (old_size < pos)
		pagecache_isize_extended(iter->inode, old_size, pos);
	if (ret < len)
		iomap_write_failed(iter->inode, pos + ret, len - ret);
	return ret;
}

static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
{
	loff_t length = iomap_length(iter);
	loff_t pos = iter->pos;
	ssize_t written = 0;
	long status = 0;
	struct address_space *mapping = iter->inode->i_mapping;
	unsigned int bdp_flags = (iter->flags & IOMAP_NOWAIT) ? BDP_ASYNC : 0;

	do {
		struct folio *folio;
		struct page *page;
		unsigned long offset;	/* Offset into pagecache page */
		unsigned long bytes;	/* Bytes to write to page */
		size_t copied;		/* Bytes copied from user */

		offset = offset_in_page(pos);
		bytes = min_t(unsigned long, PAGE_SIZE - offset,
						iov_iter_count(i));
again:
		status = balance_dirty_pages_ratelimited_flags(mapping,
							       bdp_flags);
		if (unlikely(status))
			break;

		if (bytes > length)
			bytes = length;

		/*
		 * Bring in the user page that we'll copy from _first_.
		 * Otherwise there's a nasty deadlock on copying from the
		 * same page as we're writing to, without it being marked
		 * up-to-date.
		 *
		 * For async buffered writes the assumption is that the user
		 * page has already been faulted in. This can be optimized by
		 * faulting the user page.
		 */
		if (unlikely(fault_in_iov_iter_readable(i, bytes) == bytes)) {
			status = -EFAULT;
			break;
		}

		status = iomap_write_begin(iter, pos, bytes, &folio);
		if (unlikely(status))
			break;
		if (iter->iomap.flags & IOMAP_F_STALE)
			break;

		page = folio_file_page(folio, pos >> PAGE_SHIFT);
		if (mapping_writably_mapped(mapping))
			flush_dcache_page(page);

		copied = copy_page_from_iter_atomic(page, offset, bytes, i);

		status = iomap_write_end(iter, pos, bytes, copied, folio);

		if (unlikely(copied != status))
			iov_iter_revert(i, copied - status);

		cond_resched();
		if (unlikely(status == 0)) {
			/*
			 * A short copy made iomap_write_end() reject the
			 * thing entirely.  Might be memory poisoning
			 * halfway through, might be a race with munmap,
			 * might be severe memory pressure.
			 */
			if (copied)
				bytes = copied;
			goto again;
		}
		pos += status;
		written += status;
		length -= status;
	} while (iov_iter_count(i) && length);

	if (status == -EAGAIN) {
		iov_iter_revert(i, written);
		return -EAGAIN;
	}
	return written ? written : status;
}

ssize_t
iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i,
		const struct iomap_ops *ops)
{
	struct iomap_iter iter = {
		.inode		= iocb->ki_filp->f_mapping->host,
		.pos		= iocb->ki_pos,
		.len		= iov_iter_count(i),
		.flags		= IOMAP_WRITE,
	};
	int ret;

	if (iocb->ki_flags & IOCB_NOWAIT)
		iter.flags |= IOMAP_NOWAIT;

	while ((ret = iomap_iter(&iter, ops)) > 0)
		iter.processed = iomap_write_iter(&iter, i);
	if (iter.pos == iocb->ki_pos)
		return ret;
	return iter.pos - iocb->ki_pos;
}
EXPORT_SYMBOL_GPL(iomap_file_buffered_write);

/*
 * Scan the data range passed to us for dirty page cache folios. If we find a
 * dirty folio, punch out the preceeding range and update the offset from which
 * the next punch will start from.
 *
 * We can punch out storage reservations under clean pages because they either
 * contain data that has been written back - in which case the delalloc punch
 * over that range is a no-op - or they have been read faults in which case they
 * contain zeroes and we can remove the delalloc backing range and any new
 * writes to those pages will do the normal hole filling operation...
 *
 * This makes the logic simple: we only need to keep the delalloc extents only
 * over the dirty ranges of the page cache.
 *
 * This function uses [start_byte, end_byte) intervals (i.e. open ended) to
 * simplify range iterations.
 */
static int iomap_write_delalloc_scan(struct inode *inode,
		loff_t *punch_start_byte, loff_t start_byte, loff_t end_byte,
		int (*punch)(struct inode *inode, loff_t offset, loff_t length))
{
	while (start_byte < end_byte) {
		struct folio	*folio;

		/* grab locked page */
		folio = filemap_lock_folio(inode->i_mapping,
				start_byte >> PAGE_SHIFT);
		if (!folio) {
			start_byte = ALIGN_DOWN(start_byte, PAGE_SIZE) +
					PAGE_SIZE;
			continue;
		}

		/* if dirty, punch up to offset */
		if (folio_test_dirty(folio)) {
			if (start_byte > *punch_start_byte) {
				int	error;

				error = punch(inode, *punch_start_byte,
						start_byte - *punch_start_byte);
				if (error) {
					folio_unlock(folio);
					folio_put(folio);
					return error;
				}
			}

			/*
			 * Make sure the next punch start is correctly bound to
			 * the end of this data range, not the end of the folio.
			 */
			*punch_start_byte = min_t(loff_t, end_byte,
					folio_next_index(folio) << PAGE_SHIFT);
		}

		/* move offset to start of next folio in range */
		start_byte = folio_next_index(folio) << PAGE_SHIFT;
		folio_unlock(folio);
		folio_put(folio);
	}
	return 0;
}

/*
 * Punch out all the delalloc blocks in the range given except for those that
 * have dirty data still pending in the page cache - those are going to be
 * written and so must still retain the delalloc backing for writeback.
 *
 * As we are scanning the page cache for data, we don't need to reimplement the
 * wheel - mapping_seek_hole_data() does exactly what we need to identify the
 * start and end of data ranges correctly even for sub-folio block sizes. This
 * byte range based iteration is especially convenient because it means we
 * don't have to care about variable size folios, nor where the start or end of
 * the data range lies within a folio, if they lie within the same folio or even
 * if there are multiple discontiguous data ranges within the folio.
 *
 * It should be noted that mapping_seek_hole_data() is not aware of EOF, and so
 * can return data ranges that exist in the cache beyond EOF. e.g. a page fault
 * spanning EOF will initialise the post-EOF data to zeroes and mark it up to
 * date. A write page fault can then mark it dirty. If we then fail a write()
 * beyond EOF into that up to date cached range, we allocate a delalloc block
 * beyond EOF and then have to punch it out. Because the range is up to date,
 * mapping_seek_hole_data() will return it, and we will skip the punch because
 * the folio is dirty. THis is incorrect - we always need to punch out delalloc
 * beyond EOF in this case as writeback will never write back and covert that
 * delalloc block beyond EOF. Hence we limit the cached data scan range to EOF,
 * resulting in always punching out the range from the EOF to the end of the
 * range the iomap spans.
 *
 * Intervals are of the form [start_byte, end_byte) (i.e. open ended) because it
 * matches the intervals returned by mapping_seek_hole_data(). i.e. SEEK_DATA
 * returns the start of a data range (start_byte), and SEEK_HOLE(start_byte)
 * returns the end of the data range (data_end). Using closed intervals would
 * require sprinkling this code with magic "+ 1" and "- 1" arithmetic and expose
 * the code to subtle off-by-one bugs....
 */
static int iomap_write_delalloc_release(struct inode *inode,
		loff_t start_byte, loff_t end_byte,
		int (*punch)(struct inode *inode, loff_t pos, loff_t length))
{
	loff_t punch_start_byte = start_byte;
	loff_t scan_end_byte = min(i_size_read(inode), end_byte);
	int error = 0;

	/*
	 * Lock the mapping to avoid races with page faults re-instantiating
	 * folios and dirtying them via ->page_mkwrite whilst we walk the
	 * cache and perform delalloc extent removal. Failing to do this can
	 * leave dirty pages with no space reservation in the cache.
	 */
	filemap_invalidate_lock(inode->i_mapping);
	while (start_byte < scan_end_byte) {
		loff_t		data_end;

		start_byte = mapping_seek_hole_data(inode->i_mapping,
				start_byte, scan_end_byte, SEEK_DATA);
		/*
		 * If there is no more data to scan, all that is left is to
		 * punch out the remaining range.
		 */
		if (start_byte == -ENXIO || start_byte == scan_end_byte)
			break;
		if (start_byte < 0) {
			error = start_byte;
			goto out_unlock;
		}
		WARN_ON_ONCE(start_byte < punch_start_byte);
		WARN_ON_ONCE(start_byte > scan_end_byte);

		/*
		 * We find the end of this contiguous cached data range by
		 * seeking from start_byte to the beginning of the next hole.
		 */
		data_end = mapping_seek_hole_data(inode->i_mapping, start_byte,
				scan_end_byte, SEEK_HOLE);
		if (data_end < 0) {
			error = data_end;
			goto out_unlock;
		}
		WARN_ON_ONCE(data_end <= start_byte);
		WARN_ON_ONCE(data_end > scan_end_byte);

		error = iomap_write_delalloc_scan(inode, &punch_start_byte,
				start_byte, data_end, punch);
		if (error)
			goto out_unlock;

		/* The next data search starts at the end of this one. */
		start_byte = data_end;
	}

	if (punch_start_byte < end_byte)
		error = punch(inode, punch_start_byte,
				end_byte - punch_start_byte);
out_unlock:
	filemap_invalidate_unlock(inode->i_mapping);
	return error;
}

/*
 * When a short write occurs, the filesystem may need to remove reserved space
 * that was allocated in ->iomap_begin from it's ->iomap_end method. For
 * filesystems that use delayed allocation, we need to punch out delalloc
 * extents from the range that are not dirty in the page cache. As the write can
 * race with page faults, there can be dirty pages over the delalloc extent
 * outside the range of a short write but still within the delalloc extent
 * allocated for this iomap.
 *
 * This function uses [start_byte, end_byte) intervals (i.e. open ended) to
 * simplify range iterations.
 *
 * The punch() callback *must* only punch delalloc extents in the range passed
 * to it. It must skip over all other types of extents in the range and leave
 * them completely unchanged. It must do this punch atomically with respect to
 * other extent modifications.
 *
 * The punch() callback may be called with a folio locked to prevent writeback
 * extent allocation racing at the edge of the range we are currently punching.
 * The locked folio may or may not cover the range being punched, so it is not
 * safe for the punch() callback to lock folios itself.
 *
 * Lock order is:
 *
 * inode->i_rwsem (shared or exclusive)
 *   inode->i_mapping->invalidate_lock (exclusive)
 *     folio_lock()
 *       ->punch
 *         internal filesystem allocation lock
 */
int iomap_file_buffered_write_punch_delalloc(struct inode *inode,
		struct iomap *iomap, loff_t pos, loff_t length,
		ssize_t written,
		int (*punch)(struct inode *inode, loff_t pos, loff_t length))
{
	loff_t			start_byte;
	loff_t			end_byte;
	int			blocksize = i_blocksize(inode);

	if (iomap->type != IOMAP_DELALLOC)
		return 0;

	/* If we didn't reserve the blocks, we're not allowed to punch them. */
	if (!(iomap->flags & IOMAP_F_NEW))
		return 0;

	/*
	 * start_byte refers to the first unused block after a short write. If
	 * nothing was written, round offset down to point at the first block in
	 * the range.
	 */
	if (unlikely(!written))
		start_byte = round_down(pos, blocksize);
	else
		start_byte = round_up(pos + written, blocksize);
	end_byte = round_up(pos + length, blocksize);

	/* Nothing to do if we've written the entire delalloc extent */
	if (start_byte >= end_byte)
		return 0;

	return iomap_write_delalloc_release(inode, start_byte, end_byte,
					punch);
}
EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc);

static loff_t iomap_unshare_iter(struct iomap_iter *iter)
{
	struct iomap *iomap = &iter->iomap;
	const struct iomap *srcmap = iomap_iter_srcmap(iter);
	loff_t pos = iter->pos;
	loff_t length = iomap_length(iter);
	long status = 0;
	loff_t written = 0;

	/* don't bother with blocks that are not shared to start with */
	if (!(iomap->flags & IOMAP_F_SHARED))
		return length;
	/* don't bother with holes or unwritten extents */
	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
		return length;

	do {
		unsigned long offset = offset_in_page(pos);
		unsigned long bytes = min_t(loff_t, PAGE_SIZE - offset, length);
		struct folio *folio;

		status = iomap_write_begin(iter, pos, bytes, &folio);
		if (unlikely(status))
			return status;
		if (iter->iomap.flags & IOMAP_F_STALE)
			break;

		status = iomap_write_end(iter, pos, bytes, bytes, folio);
		if (WARN_ON_ONCE(status == 0))
			return -EIO;

		cond_resched();

		pos += status;
		written += status;
		length -= status;

		balance_dirty_pages_ratelimited(iter->inode->i_mapping);
	} while (length);

	return written;
}

int
iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
		const struct iomap_ops *ops)
{
	struct iomap_iter iter = {
		.inode		= inode,
		.pos		= pos,
		.len		= len,
		.flags		= IOMAP_WRITE | IOMAP_UNSHARE,
	};
	int ret;

	while ((ret = iomap_iter(&iter, ops)) > 0)
		iter.processed = iomap_unshare_iter(&iter);
	return ret;
}
EXPORT_SYMBOL_GPL(iomap_file_unshare);

static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
{
	const struct iomap *srcmap = iomap_iter_srcmap(iter);
	loff_t pos = iter->pos;
	loff_t length = iomap_length(iter);
	loff_t written = 0;

	/* already zeroed?  we're done. */
	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
		return length;

	do {
		struct folio *folio;
		int status;
		size_t offset;
		size_t bytes = min_t(u64, SIZE_MAX, length);

		status = iomap_write_begin(iter, pos, bytes, &folio);
		if (status)
			return status;
		if (iter->iomap.flags & IOMAP_F_STALE)
			break;

		offset = offset_in_folio(folio, pos);
		if (bytes > folio_size(folio) - offset)
			bytes = folio_size(folio) - offset;

		folio_zero_range(folio, offset, bytes);
		folio_mark_accessed(folio);

		bytes = iomap_write_end(iter, pos, bytes, bytes, folio);
		if (WARN_ON_ONCE(bytes == 0))
			return -EIO;

		pos += bytes;
		length -= bytes;
		written += bytes;
	} while (length > 0);

	if (did_zero)
		*did_zero = true;
	return written;
}

int
iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
		const struct iomap_ops *ops)
{
	struct iomap_iter iter = {
		.inode		= inode,
		.pos		= pos,
		.len		= len,
		.flags		= IOMAP_ZERO,
	};
	int ret;

	while ((ret = iomap_iter(&iter, ops)) > 0)
		iter.processed = iomap_zero_iter(&iter, did_zero);
	return ret;
}
EXPORT_SYMBOL_GPL(iomap_zero_range);

int
iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
		const struct iomap_ops *ops)
{
	unsigned int blocksize = i_blocksize(inode);
	unsigned int off = pos & (blocksize - 1);

	/* Block boundary? Nothing to do */
	if (!off)
		return 0;
	return iomap_zero_range(inode, pos, blocksize - off, did_zero, ops);
}
EXPORT_SYMBOL_GPL(iomap_truncate_page);

static loff_t iomap_folio_mkwrite_iter(struct iomap_iter *iter,
		struct folio *folio)
{
	loff_t length = iomap_length(iter);
	int ret;

	if (iter->iomap.flags & IOMAP_F_BUFFER_HEAD) {
		ret = __block_write_begin_int(folio, iter->pos, length, NULL,
					      &iter->iomap);
		if (ret)
			return ret;
		block_commit_write(&folio->page, 0, length);
	} else {
		WARN_ON_ONCE(!folio_test_uptodate(folio));
		folio_mark_dirty(folio);
	}

	return length;
}

vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
{
	struct iomap_iter iter = {
		.inode		= file_inode(vmf->vma->vm_file),
		.flags		= IOMAP_WRITE | IOMAP_FAULT,
	};
	struct folio *folio = page_folio(vmf->page);
	ssize_t ret;

	folio_lock(folio);
	ret = folio_mkwrite_check_truncate(folio, iter.inode);
	if (ret < 0)
		goto out_unlock;
	iter.pos = folio_pos(folio);
	iter.len = ret;
	while ((ret = iomap_iter(&iter, ops)) > 0)
		iter.processed = iomap_folio_mkwrite_iter(&iter, folio);

	if (ret < 0)
		goto out_unlock;
	folio_wait_stable(folio);
	return VM_FAULT_LOCKED;
out_unlock:
	folio_unlock(folio);
	return block_page_mkwrite_return(ret);
}
EXPORT_SYMBOL_GPL(iomap_page_mkwrite);

static void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
		size_t len, int error)
{
	struct iomap_page *iop = to_iomap_page(folio);

	if (error) {
		folio_set_error(folio);
		mapping_set_error(inode->i_mapping, error);
	}

	WARN_ON_ONCE(i_blocks_per_folio(inode, folio) > 1 && !iop);
	WARN_ON_ONCE(iop && atomic_read(&iop->write_bytes_pending) <= 0);

	if (!iop || atomic_sub_and_test(len, &iop->write_bytes_pending))
		folio_end_writeback(folio);
}

/*
 * We're now finished for good with this ioend structure.  Update the page
 * state, release holds on bios, and finally free up memory.  Do not use the
 * ioend after this.
 */
static u32
iomap_finish_ioend(struct iomap_ioend *ioend, int error)
{
	struct inode *inode = ioend->io_inode;
	struct bio *bio = &ioend->io_inline_bio;
	struct bio *last = ioend->io_bio, *next;
	u64 start = bio->bi_iter.bi_sector;
	loff_t offset = ioend->io_offset;
	bool quiet = bio_flagged(bio, BIO_QUIET);
	u32 folio_count = 0;

	for (bio = &ioend->io_inline_bio; bio; bio = next) {
		struct folio_iter fi;

		/*
		 * For the last bio, bi_private points to the ioend, so we
		 * need to explicitly end the iteration here.
		 */
		if (bio == last)
			next = NULL;
		else
			next = bio->bi_private;

		/* walk all folios in bio, ending page IO on them */
		bio_for_each_folio_all(fi, bio) {
			iomap_finish_folio_write(inode, fi.folio, fi.length,
					error);
			folio_count++;
		}
		bio_put(bio);
	}
	/* The ioend has been freed by bio_put() */

	if (unlikely(error && !quiet)) {
		printk_ratelimited(KERN_ERR
"%s: writeback error on inode %lu, offset %lld, sector %llu",
			inode->i_sb->s_id, inode->i_ino, offset, start);
	}
	return folio_count;
}

/*
 * Ioend completion routine for merged bios. This can only be called from task
 * contexts as merged ioends can be of unbound length. Hence we have to break up
 * the writeback completions into manageable chunks to avoid long scheduler
 * holdoffs. We aim to keep scheduler holdoffs down below 10ms so that we get
 * good batch processing throughput without creating adverse scheduler latency
 * conditions.
 */
void
iomap_finish_ioends(struct iomap_ioend *ioend, int error)
{
	struct list_head tmp;
	u32 completions;

	might_sleep();

	list_replace_init(&ioend->io_list, &tmp);
	completions = iomap_finish_ioend(ioend, error);

	while (!list_empty(&tmp)) {
		if (completions > IOEND_BATCH_SIZE * 8) {
			cond_resched();
			completions = 0;
		}
		ioend = list_first_entry(&tmp, struct iomap_ioend, io_list);
		list_del_init(&ioend->io_list);
		completions += iomap_finish_ioend(ioend, error);
	}
}
EXPORT_SYMBOL_GPL(iomap_finish_ioends);

/*
 * We can merge two adjacent ioends if they have the same set of work to do.
 */
static bool
iomap_ioend_can_merge(struct iomap_ioend *ioend, struct iomap_ioend *next)
{
	if (ioend->io_bio->bi_status != next->io_bio->bi_status)
		return false;
	if ((ioend->io_flags & IOMAP_F_SHARED) ^
	    (next->io_flags & IOMAP_F_SHARED))
		return false;
	if ((ioend->io_type == IOMAP_UNWRITTEN) ^
	    (next->io_type == IOMAP_UNWRITTEN))
		return false;
	if (ioend->io_offset + ioend->io_size != next->io_offset)
		return false;
	/*
	 * Do not merge physically discontiguous ioends. The filesystem
	 * completion functions will have to iterate the physical
	 * discontiguities even if we merge the ioends at a logical level, so
	 * we don't gain anything by merging physical discontiguities here.
	 *
	 * We cannot use bio->bi_iter.bi_sector here as it is modified during
	 * submission so does not point to the start sector of the bio at
	 * completion.
	 */
	if (ioend->io_sector + (ioend->io_size >> 9) != next->io_sector)
		return false;
	return true;
}

void
iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends)
{
	struct iomap_ioend *next;

	INIT_LIST_HEAD(&ioend->io_list);

	while ((next = list_first_entry_or_null(more_ioends, struct iomap_ioend,
			io_list))) {
		if (!iomap_ioend_can_merge(ioend, next))
			break;
		list_move_tail(&next->io_list, &ioend->io_list);
		ioend->io_size += next->io_size;
	}
}
EXPORT_SYMBOL_GPL(iomap_ioend_try_merge);

static int
iomap_ioend_compare(void *priv, const struct list_head *a,
		const struct list_head *b)
{
	struct iomap_ioend *ia = container_of(a, struct iomap_ioend, io_list);
	struct iomap_ioend *ib = container_of(b, struct iomap_ioend, io_list);

	if (ia->io_offset < ib->io_offset)
		return -1;
	if (ia->io_offset > ib->io_offset)
		return 1;
	return 0;
}

void
iomap_sort_ioends(struct list_head *ioend_list)
{
	list_sort(NULL, ioend_list, iomap_ioend_compare);
}
EXPORT_SYMBOL_GPL(iomap_sort_ioends);

static void iomap_writepage_end_bio(struct bio *bio)
{
	struct iomap_ioend *ioend = bio->bi_private;

	iomap_finish_ioend(ioend, blk_status_to_errno(bio->bi_status));
}

/*
 * Submit the final bio for an ioend.
 *
 * If @error is non-zero, it means that we have a situation where some part of
 * the submission process has failed after we've marked pages for writeback
 * and unlocked them.  In this situation, we need to fail the bio instead of
 * submitting it.  This typically only happens on a filesystem shutdown.
 */
static int
iomap_submit_ioend(struct iomap_writepage_ctx *wpc, struct iomap_ioend *ioend,
		int error)
{
	ioend->io_bio->bi_private = ioend;
	ioend->io_bio->bi_end_io = iomap_writepage_end_bio;

	if (wpc->ops->prepare_ioend)
		error = wpc->ops->prepare_ioend(ioend, error);
	if (error) {
		/*
		 * If we're failing the IO now, just mark the ioend with an
		 * error and finish it.  This will run IO completion immediately
		 * as there is only one reference to the ioend at this point in
		 * time.
		 */
		ioend->io_bio->bi_status = errno_to_blk_status(error);
		bio_endio(ioend->io_bio);
		return error;
	}

	submit_bio(ioend->io_bio);
	return 0;
}

static struct iomap_ioend *
iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc,
		loff_t offset, sector_t sector, struct writeback_control *wbc)
{
	struct iomap_ioend *ioend;
	struct bio *bio;

	bio = bio_alloc_bioset(wpc->iomap.bdev, BIO_MAX_VECS,
			       REQ_OP_WRITE | wbc_to_write_flags(wbc),
			       GFP_NOFS, &iomap_ioend_bioset);
	bio->bi_iter.bi_sector = sector;
	wbc_init_bio(wbc, bio);

	ioend = container_of(bio, struct iomap_ioend, io_inline_bio);
	INIT_LIST_HEAD(&ioend->io_list);
	ioend->io_type = wpc->iomap.type;
	ioend->io_flags = wpc->iomap.flags;
	ioend->io_inode = inode;
	ioend->io_size = 0;
	ioend->io_folios = 0;
	ioend->io_offset = offset;
	ioend->io_bio = bio;
	ioend->io_sector = sector;
	return ioend;
}

/*
 * Allocate a new bio, and chain the old bio to the new one.
 *
 * Note that we have to perform the chaining in this unintuitive order
 * so that the bi_private linkage is set up in the right direction for the
 * traversal in iomap_finish_ioend().
 */
static struct bio *
iomap_chain_bio(struct bio *prev)
{
	struct bio *new;

	new = bio_alloc(prev->bi_bdev, BIO_MAX_VECS, prev->bi_opf, GFP_NOFS);
	bio_clone_blkg_association(new, prev);
	new->bi_iter.bi_sector = bio_end_sector(prev);

	bio_chain(prev, new);
	bio_get(prev);		/* for iomap_finish_ioend */
	submit_bio(prev);
	return new;
}

static bool
iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t offset,
		sector_t sector)
{
	if ((wpc->iomap.flags & IOMAP_F_SHARED) !=
	    (wpc->ioend->io_flags & IOMAP_F_SHARED))
		return false;
	if (wpc->iomap.type != wpc->ioend->io_type)
		return false;
	if (offset != wpc->ioend->io_offset + wpc->ioend->io_size)
		return false;
	if (sector != bio_end_sector(wpc->ioend->io_bio))
		return false;
	/*
	 * Limit ioend bio chain lengths to minimise IO completion latency. This
	 * also prevents long tight loops ending page writeback on all the
	 * folios in the ioend.
	 */
	if (wpc->ioend->io_folios >= IOEND_BATCH_SIZE)
		return false;
	return true;
}

/*
 * Test to see if we have an existing ioend structure that we could append to
 * first; otherwise finish off the current ioend and start another.
 */
static void
iomap_add_to_ioend(struct inode *inode, loff_t pos, struct folio *folio,
		struct iomap_page *iop, struct iomap_writepage_ctx *wpc,
		struct writeback_control *wbc, struct list_head *iolist)
{
	sector_t sector = iomap_sector(&wpc->iomap, pos);
	unsigned len = i_blocksize(inode);
	size_t poff = offset_in_folio(folio, pos);

	if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, pos, sector)) {
		if (wpc->ioend)
			list_add(&wpc->ioend->io_list, iolist);
		wpc->ioend = iomap_alloc_ioend(inode, wpc, pos, sector, wbc);
	}

	if (!bio_add_folio(wpc->ioend->io_bio, folio, len, poff)) {
		wpc->ioend->io_bio = iomap_chain_bio(wpc->ioend->io_bio);
		bio_add_folio(wpc->ioend->io_bio, folio, len, poff);
	}

	if (iop)
		atomic_add(len, &iop->write_bytes_pending);
	wpc->ioend->io_size += len;
	wbc_account_cgroup_owner(wbc, &folio->page, len);
}

/*
 * We implement an immediate ioend submission policy here to avoid needing to
 * chain multiple ioends and hence nest mempool allocations which can violate
 * the forward progress guarantees we need to provide. The current ioend we're
 * adding blocks to is cached in the writepage context, and if the new block
 * doesn't append to the cached ioend, it will create a new ioend and cache that
 * instead.
 *
 * If a new ioend is created and cached, the old ioend is returned and queued
 * locally for submission once the entire page is processed or an error has been
 * detected.  While ioends are submitted immediately after they are completed,
 * batching optimisations are provided by higher level block plugging.
 *
 * At the end of a writeback pass, there will be a cached ioend remaining on the
 * writepage context that the caller will need to submit.
 */
static int
iomap_writepage_map(struct iomap_writepage_ctx *wpc,
		struct writeback_control *wbc, struct inode *inode,
		struct folio *folio, u64 end_pos)
{
	struct iomap_page *iop = iomap_page_create(inode, folio, 0);
	struct iomap_ioend *ioend, *next;
	unsigned len = i_blocksize(inode);
	unsigned nblocks = i_blocks_per_folio(inode, folio);
	u64 pos = folio_pos(folio);
	int error = 0, count = 0, i;
	LIST_HEAD(submit_list);

	WARN_ON_ONCE(iop && atomic_read(&iop->write_bytes_pending) != 0);

	/*
	 * Walk through the folio to find areas to write back. If we
	 * run off the end of the current map or find the current map
	 * invalid, grab a new one.
	 */
	for (i = 0; i < nblocks && pos < end_pos; i++, pos += len) {
		if (iop && !test_bit(i, iop->uptodate))
			continue;

		error = wpc->ops->map_blocks(wpc, inode, pos);
		if (error)
			break;
		trace_iomap_writepage_map(inode, &wpc->iomap);
		if (WARN_ON_ONCE(wpc->iomap.type == IOMAP_INLINE))
			continue;
		if (wpc->iomap.type == IOMAP_HOLE)
			continue;
		iomap_add_to_ioend(inode, pos, folio, iop, wpc, wbc,
				 &submit_list);
		count++;
	}
	if (count)
		wpc->ioend->io_folios++;

	WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list));
	WARN_ON_ONCE(!folio_test_locked(folio));
	WARN_ON_ONCE(folio_test_writeback(folio));
	WARN_ON_ONCE(folio_test_dirty(folio));

	/*
	 * We cannot cancel the ioend directly here on error.  We may have
	 * already set other pages under writeback and hence we have to run I/O
	 * completion to mark the error state of the pages under writeback
	 * appropriately.
	 */
	if (unlikely(error)) {
		/*
		 * Let the filesystem know what portion of the current page
		 * failed to map. If the page hasn't been added to ioend, it
		 * won't be affected by I/O completion and we must unlock it
		 * now.
		 */
		if (wpc->ops->discard_folio)
			wpc->ops->discard_folio(folio, pos);
		if (!count) {
			folio_unlock(folio);
			goto done;
		}
	}

	folio_start_writeback(folio);
	folio_unlock(folio);

	/*
	 * Preserve the original error if there was one; catch
	 * submission errors here and propagate into subsequent ioend
	 * submissions.
	 */
	list_for_each_entry_safe(ioend, next, &submit_list, io_list) {
		int error2;

		list_del_init(&ioend->io_list);
		error2 = iomap_submit_ioend(wpc, ioend, error);
		if (error2 && !error)
			error = error2;
	}

	/*
	 * We can end up here with no error and nothing to write only if we race
	 * with a partial page truncate on a sub-page block sized filesystem.
	 */
	if (!count)
		folio_end_writeback(folio);
done:
	mapping_set_error(inode->i_mapping, error);
	return error;
}

/*
 * Write out a dirty page.
 *
 * For delalloc space on the page, we need to allocate space and flush it.
 * For unwritten space on the page, we need to start the conversion to
 * regular allocated space.
 */
static int iomap_do_writepage(struct folio *folio,
		struct writeback_control *wbc, void *data)
{
	struct iomap_writepage_ctx *wpc = data;
	struct inode *inode = folio->mapping->host;
	u64 end_pos, isize;

	trace_iomap_writepage(inode, folio_pos(folio), folio_size(folio));

	/*
	 * Refuse to write the folio out if we're called from reclaim context.
	 *
	 * This avoids stack overflows when called from deeply used stacks in
	 * random callers for direct reclaim or memcg reclaim.  We explicitly
	 * allow reclaim from kswapd as the stack usage there is relatively low.
	 *
	 * This should never happen except in the case of a VM regression so
	 * warn about it.
	 */
	if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) ==
			PF_MEMALLOC))
		goto redirty;

	/*
	 * Is this folio beyond the end of the file?
	 *
	 * The folio index is less than the end_index, adjust the end_pos
	 * to the highest offset that this folio should represent.
	 * -----------------------------------------------------
	 * |			file mapping	       | <EOF> |
	 * -----------------------------------------------------
	 * | Page ... | Page N-2 | Page N-1 |  Page N  |       |
	 * ^--------------------------------^----------|--------
	 * |     desired writeback range    |      see else    |
	 * ---------------------------------^------------------|
	 */
	isize = i_size_read(inode);
	end_pos = folio_pos(folio) + folio_size(folio);
	if (end_pos > isize) {
		/*
		 * Check whether the page to write out is beyond or straddles
		 * i_size or not.
		 * -------------------------------------------------------
		 * |		file mapping		        | <EOF>  |
		 * -------------------------------------------------------
		 * | Page ... | Page N-2 | Page N-1 |  Page N   | Beyond |
		 * ^--------------------------------^-----------|---------
		 * |				    |      Straddles     |
		 * ---------------------------------^-----------|--------|
		 */
		size_t poff = offset_in_folio(folio, isize);
		pgoff_t end_index = isize >> PAGE_SHIFT;

		/*
		 * Skip the page if it's fully outside i_size, e.g.
		 * due to a truncate operation that's in progress.  We've
		 * cleaned this page and truncate will finish things off for
		 * us.
		 *
		 * Note that the end_index is unsigned long.  If the given
		 * offset is greater than 16TB on a 32-bit system then if we
		 * checked if the page is fully outside i_size with
		 * "if (page->index >= end_index + 1)", "end_index + 1" would
		 * overflow and evaluate to 0.  Hence this page would be
		 * redirtied and written out repeatedly, which would result in
		 * an infinite loop; the user program performing this operation
		 * would hang.  Instead, we can detect this situation by
		 * checking if the page is totally beyond i_size or if its
		 * offset is just equal to the EOF.
		 */
		if (folio->index > end_index ||
		    (folio->index == end_index && poff == 0))
			goto unlock;

		/*
		 * The page straddles i_size.  It must be zeroed out on each
		 * and every writepage invocation because it may be mmapped.
		 * "A file is mapped in multiples of the page size.  For a file
		 * that is not a multiple of the page size, the remaining
		 * memory is zeroed when mapped, and writes to that region are
		 * not written out to the file."
		 */
		folio_zero_segment(folio, poff, folio_size(folio));
		end_pos = isize;
	}

	return iomap_writepage_map(wpc, wbc, inode, folio, end_pos);

redirty:
	folio_redirty_for_writepage(wbc, folio);
unlock:
	folio_unlock(folio);
	return 0;
}

int
iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
		struct iomap_writepage_ctx *wpc,
		const struct iomap_writeback_ops *ops)
{
	int			ret;

	wpc->ops = ops;
	ret = write_cache_pages(mapping, wbc, iomap_do_writepage, wpc);
	if (!wpc->ioend)
		return ret;
	return iomap_submit_ioend(wpc, wpc->ioend, ret);
}
EXPORT_SYMBOL_GPL(iomap_writepages);

static int __init iomap_init(void)
{
	return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
			   offsetof(struct iomap_ioend, io_inline_bio),
			   BIOSET_NEED_BVECS);
}
fs_initcall(iomap_init);