summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_iomap.c
blob: 555603ef4234eec0c557f60ddba1564e95bc4298 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2006 Silicon Graphics, Inc.
 * Copyright (c) 2016-2018 Christoph Hellwig.
 * All Rights Reserved.
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_bmap_btree.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_trans.h"
#include "xfs_trans_space.h"
#include "xfs_inode_item.h"
#include "xfs_iomap.h"
#include "xfs_trace.h"
#include "xfs_quota.h"
#include "xfs_dquot_item.h"
#include "xfs_dquot.h"
#include "xfs_reflink.h"
#include "xfs_health.h"
#include "xfs_rtbitmap.h"

#define XFS_ALLOC_ALIGN(mp, off) \
	(((off) >> mp->m_allocsize_log) << mp->m_allocsize_log)

static int
xfs_alert_fsblock_zero(
	xfs_inode_t	*ip,
	xfs_bmbt_irec_t	*imap)
{
	xfs_alert_tag(ip->i_mount, XFS_PTAG_FSBLOCK_ZERO,
			"Access to block zero in inode %llu "
			"start_block: %llx start_off: %llx "
			"blkcnt: %llx extent-state: %x",
		(unsigned long long)ip->i_ino,
		(unsigned long long)imap->br_startblock,
		(unsigned long long)imap->br_startoff,
		(unsigned long long)imap->br_blockcount,
		imap->br_state);
	xfs_bmap_mark_sick(ip, XFS_DATA_FORK);
	return -EFSCORRUPTED;
}

u64
xfs_iomap_inode_sequence(
	struct xfs_inode	*ip,
	u16			iomap_flags)
{
	u64			cookie = 0;

	if (iomap_flags & IOMAP_F_XATTR)
		return READ_ONCE(ip->i_af.if_seq);
	if ((iomap_flags & IOMAP_F_SHARED) && ip->i_cowfp)
		cookie = (u64)READ_ONCE(ip->i_cowfp->if_seq) << 32;
	return cookie | READ_ONCE(ip->i_df.if_seq);
}

/*
 * Check that the iomap passed to us is still valid for the given offset and
 * length.
 */
static bool
xfs_iomap_valid(
	struct inode		*inode,
	const struct iomap	*iomap)
{
	struct xfs_inode	*ip = XFS_I(inode);

	if (iomap->validity_cookie !=
			xfs_iomap_inode_sequence(ip, iomap->flags)) {
		trace_xfs_iomap_invalid(ip, iomap);
		return false;
	}

	XFS_ERRORTAG_DELAY(ip->i_mount, XFS_ERRTAG_WRITE_DELAY_MS);
	return true;
}

static const struct iomap_folio_ops xfs_iomap_folio_ops = {
	.iomap_valid		= xfs_iomap_valid,
};

int
xfs_bmbt_to_iomap(
	struct xfs_inode	*ip,
	struct iomap		*iomap,
	struct xfs_bmbt_irec	*imap,
	unsigned int		mapping_flags,
	u16			iomap_flags,
	u64			sequence_cookie)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_buftarg	*target = xfs_inode_buftarg(ip);

	if (unlikely(!xfs_valid_startblock(ip, imap->br_startblock))) {
		xfs_bmap_mark_sick(ip, XFS_DATA_FORK);
		return xfs_alert_fsblock_zero(ip, imap);
	}

	if (imap->br_startblock == HOLESTARTBLOCK) {
		iomap->addr = IOMAP_NULL_ADDR;
		iomap->type = IOMAP_HOLE;
	} else if (imap->br_startblock == DELAYSTARTBLOCK ||
		   isnullstartblock(imap->br_startblock)) {
		iomap->addr = IOMAP_NULL_ADDR;
		iomap->type = IOMAP_DELALLOC;
	} else {
		iomap->addr = BBTOB(xfs_fsb_to_db(ip, imap->br_startblock));
		if (mapping_flags & IOMAP_DAX)
			iomap->addr += target->bt_dax_part_off;

		if (imap->br_state == XFS_EXT_UNWRITTEN)
			iomap->type = IOMAP_UNWRITTEN;
		else
			iomap->type = IOMAP_MAPPED;

	}
	iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff);
	iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
	if (mapping_flags & IOMAP_DAX)
		iomap->dax_dev = target->bt_daxdev;
	else
		iomap->bdev = target->bt_bdev;
	iomap->flags = iomap_flags;

	if (xfs_ipincount(ip) &&
	    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
		iomap->flags |= IOMAP_F_DIRTY;

	iomap->validity_cookie = sequence_cookie;
	iomap->folio_ops = &xfs_iomap_folio_ops;
	return 0;
}

static void
xfs_hole_to_iomap(
	struct xfs_inode	*ip,
	struct iomap		*iomap,
	xfs_fileoff_t		offset_fsb,
	xfs_fileoff_t		end_fsb)
{
	struct xfs_buftarg	*target = xfs_inode_buftarg(ip);

	iomap->addr = IOMAP_NULL_ADDR;
	iomap->type = IOMAP_HOLE;
	iomap->offset = XFS_FSB_TO_B(ip->i_mount, offset_fsb);
	iomap->length = XFS_FSB_TO_B(ip->i_mount, end_fsb - offset_fsb);
	iomap->bdev = target->bt_bdev;
	iomap->dax_dev = target->bt_daxdev;
}

static inline xfs_fileoff_t
xfs_iomap_end_fsb(
	struct xfs_mount	*mp,
	loff_t			offset,
	loff_t			count)
{
	ASSERT(offset <= mp->m_super->s_maxbytes);
	return min(XFS_B_TO_FSB(mp, offset + count),
		   XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes));
}

static xfs_extlen_t
xfs_eof_alignment(
	struct xfs_inode	*ip)
{
	struct xfs_mount	*mp = ip->i_mount;
	xfs_extlen_t		align = 0;

	if (!XFS_IS_REALTIME_INODE(ip)) {
		/*
		 * Round up the allocation request to a stripe unit
		 * (m_dalign) boundary if the file size is >= stripe unit
		 * size, and we are allocating past the allocation eof.
		 *
		 * If mounted with the "-o swalloc" option the alignment is
		 * increased from the strip unit size to the stripe width.
		 */
		if (mp->m_swidth && xfs_has_swalloc(mp))
			align = mp->m_swidth;
		else if (mp->m_dalign)
			align = mp->m_dalign;

		if (align && XFS_ISIZE(ip) < XFS_FSB_TO_B(mp, align))
			align = 0;
	}

	return align;
}

/*
 * Check if last_fsb is outside the last extent, and if so grow it to the next
 * stripe unit boundary.
 */
xfs_fileoff_t
xfs_iomap_eof_align_last_fsb(
	struct xfs_inode	*ip,
	xfs_fileoff_t		end_fsb)
{
	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
	xfs_extlen_t		extsz = xfs_get_extsz_hint(ip);
	xfs_extlen_t		align = xfs_eof_alignment(ip);
	struct xfs_bmbt_irec	irec;
	struct xfs_iext_cursor	icur;

	ASSERT(!xfs_need_iread_extents(ifp));

	/*
	 * Always round up the allocation request to the extent hint boundary.
	 */
	if (extsz) {
		if (align)
			align = roundup_64(align, extsz);
		else
			align = extsz;
	}

	if (align) {
		xfs_fileoff_t	aligned_end_fsb = roundup_64(end_fsb, align);

		xfs_iext_last(ifp, &icur);
		if (!xfs_iext_get_extent(ifp, &icur, &irec) ||
		    aligned_end_fsb >= irec.br_startoff + irec.br_blockcount)
			return aligned_end_fsb;
	}

	return end_fsb;
}

int
xfs_iomap_write_direct(
	struct xfs_inode	*ip,
	xfs_fileoff_t		offset_fsb,
	xfs_fileoff_t		count_fsb,
	unsigned int		flags,
	struct xfs_bmbt_irec	*imap,
	u64			*seq)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp;
	xfs_filblks_t		resaligned;
	int			nimaps;
	unsigned int		dblocks, rblocks;
	bool			force = false;
	int			error;
	int			bmapi_flags = XFS_BMAPI_PREALLOC;
	int			nr_exts = XFS_IEXT_ADD_NOSPLIT_CNT;

	ASSERT(count_fsb > 0);

	resaligned = xfs_aligned_fsb_count(offset_fsb, count_fsb,
					   xfs_get_extsz_hint(ip));
	if (unlikely(XFS_IS_REALTIME_INODE(ip))) {
		dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
		rblocks = resaligned;
	} else {
		dblocks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned);
		rblocks = 0;
	}

	error = xfs_qm_dqattach(ip);
	if (error)
		return error;

	/*
	 * For DAX, we do not allocate unwritten extents, but instead we zero
	 * the block before we commit the transaction.  Ideally we'd like to do
	 * this outside the transaction context, but if we commit and then crash
	 * we may not have zeroed the blocks and this will be exposed on
	 * recovery of the allocation. Hence we must zero before commit.
	 *
	 * Further, if we are mapping unwritten extents here, we need to zero
	 * and convert them to written so that we don't need an unwritten extent
	 * callback for DAX. This also means that we need to be able to dip into
	 * the reserve block pool for bmbt block allocation if there is no space
	 * left but we need to do unwritten extent conversion.
	 */
	if (flags & IOMAP_DAX) {
		bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
		if (imap->br_state == XFS_EXT_UNWRITTEN) {
			force = true;
			nr_exts = XFS_IEXT_WRITE_UNWRITTEN_CNT;
			dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1;
		}
	}

	error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, dblocks,
			rblocks, force, &tp);
	if (error)
		return error;

	error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, nr_exts);
	if (error == -EFBIG)
		error = xfs_iext_count_upgrade(tp, ip, nr_exts);
	if (error)
		goto out_trans_cancel;

	/*
	 * From this point onwards we overwrite the imap pointer that the
	 * caller gave to us.
	 */
	nimaps = 1;
	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb, bmapi_flags, 0,
				imap, &nimaps);
	if (error)
		goto out_trans_cancel;

	/*
	 * Complete the transaction
	 */
	error = xfs_trans_commit(tp);
	if (error)
		goto out_unlock;

	/*
	 * Copy any maps to caller's array and return any error.
	 */
	if (nimaps == 0) {
		error = -ENOSPC;
		goto out_unlock;
	}

	if (unlikely(!xfs_valid_startblock(ip, imap->br_startblock))) {
		xfs_bmap_mark_sick(ip, XFS_DATA_FORK);
		error = xfs_alert_fsblock_zero(ip, imap);
	}

out_unlock:
	*seq = xfs_iomap_inode_sequence(ip, 0);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	return error;

out_trans_cancel:
	xfs_trans_cancel(tp);
	goto out_unlock;
}

STATIC bool
xfs_quota_need_throttle(
	struct xfs_inode	*ip,
	xfs_dqtype_t		type,
	xfs_fsblock_t		alloc_blocks)
{
	struct xfs_dquot	*dq = xfs_inode_dquot(ip, type);

	if (!dq || !xfs_this_quota_on(ip->i_mount, type))
		return false;

	/* no hi watermark, no throttle */
	if (!dq->q_prealloc_hi_wmark)
		return false;

	/* under the lo watermark, no throttle */
	if (dq->q_blk.reserved + alloc_blocks < dq->q_prealloc_lo_wmark)
		return false;

	return true;
}

STATIC void
xfs_quota_calc_throttle(
	struct xfs_inode	*ip,
	xfs_dqtype_t		type,
	xfs_fsblock_t		*qblocks,
	int			*qshift,
	int64_t			*qfreesp)
{
	struct xfs_dquot	*dq = xfs_inode_dquot(ip, type);
	int64_t			freesp;
	int			shift = 0;

	/* no dq, or over hi wmark, squash the prealloc completely */
	if (!dq || dq->q_blk.reserved >= dq->q_prealloc_hi_wmark) {
		*qblocks = 0;
		*qfreesp = 0;
		return;
	}

	freesp = dq->q_prealloc_hi_wmark - dq->q_blk.reserved;
	if (freesp < dq->q_low_space[XFS_QLOWSP_5_PCNT]) {
		shift = 2;
		if (freesp < dq->q_low_space[XFS_QLOWSP_3_PCNT])
			shift += 2;
		if (freesp < dq->q_low_space[XFS_QLOWSP_1_PCNT])
			shift += 2;
	}

	if (freesp < *qfreesp)
		*qfreesp = freesp;

	/* only overwrite the throttle values if we are more aggressive */
	if ((freesp >> shift) < (*qblocks >> *qshift)) {
		*qblocks = freesp;
		*qshift = shift;
	}
}

static int64_t
xfs_iomap_freesp(
	struct percpu_counter	*counter,
	uint64_t		low_space[XFS_LOWSP_MAX],
	int			*shift)
{
	int64_t			freesp;

	freesp = percpu_counter_read_positive(counter);
	if (freesp < low_space[XFS_LOWSP_5_PCNT]) {
		*shift = 2;
		if (freesp < low_space[XFS_LOWSP_4_PCNT])
			(*shift)++;
		if (freesp < low_space[XFS_LOWSP_3_PCNT])
			(*shift)++;
		if (freesp < low_space[XFS_LOWSP_2_PCNT])
			(*shift)++;
		if (freesp < low_space[XFS_LOWSP_1_PCNT])
			(*shift)++;
	}
	return freesp;
}

/*
 * If we don't have a user specified preallocation size, dynamically increase
 * the preallocation size as the size of the file grows.  Cap the maximum size
 * at a single extent or less if the filesystem is near full. The closer the
 * filesystem is to being full, the smaller the maximum preallocation.
 */
STATIC xfs_fsblock_t
xfs_iomap_prealloc_size(
	struct xfs_inode	*ip,
	int			whichfork,
	loff_t			offset,
	loff_t			count,
	struct xfs_iext_cursor	*icur)
{
	struct xfs_iext_cursor	ncur = *icur;
	struct xfs_bmbt_irec	prev, got;
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
	int64_t			freesp;
	xfs_fsblock_t		qblocks;
	xfs_fsblock_t		alloc_blocks = 0;
	xfs_extlen_t		plen;
	int			shift = 0;
	int			qshift = 0;

	/*
	 * As an exception we don't do any preallocation at all if the file is
	 * smaller than the minimum preallocation and we are using the default
	 * dynamic preallocation scheme, as it is likely this is the only write
	 * to the file that is going to be done.
	 */
	if (XFS_ISIZE(ip) < XFS_FSB_TO_B(mp, mp->m_allocsize_blocks))
		return 0;

	/*
	 * Use the minimum preallocation size for small files or if we are
	 * writing right after a hole.
	 */
	if (XFS_ISIZE(ip) < XFS_FSB_TO_B(mp, mp->m_dalign) ||
	    !xfs_iext_prev_extent(ifp, &ncur, &prev) ||
	    prev.br_startoff + prev.br_blockcount < offset_fsb)
		return mp->m_allocsize_blocks;

	/*
	 * Take the size of the preceding data extents as the basis for the
	 * preallocation size. Note that we don't care if the previous extents
	 * are written or not.
	 */
	plen = prev.br_blockcount;
	while (xfs_iext_prev_extent(ifp, &ncur, &got)) {
		if (plen > XFS_MAX_BMBT_EXTLEN / 2 ||
		    isnullstartblock(got.br_startblock) ||
		    got.br_startoff + got.br_blockcount != prev.br_startoff ||
		    got.br_startblock + got.br_blockcount != prev.br_startblock)
			break;
		plen += got.br_blockcount;
		prev = got;
	}

	/*
	 * If the size of the extents is greater than half the maximum extent
	 * length, then use the current offset as the basis.  This ensures that
	 * for large files the preallocation size always extends to
	 * XFS_BMBT_MAX_EXTLEN rather than falling short due to things like stripe
	 * unit/width alignment of real extents.
	 */
	alloc_blocks = plen * 2;
	if (alloc_blocks > XFS_MAX_BMBT_EXTLEN)
		alloc_blocks = XFS_B_TO_FSB(mp, offset);
	qblocks = alloc_blocks;

	/*
	 * XFS_BMBT_MAX_EXTLEN is not a power of two value but we round the prealloc
	 * down to the nearest power of two value after throttling. To prevent
	 * the round down from unconditionally reducing the maximum supported
	 * prealloc size, we round up first, apply appropriate throttling, round
	 * down and cap the value to XFS_BMBT_MAX_EXTLEN.
	 */
	alloc_blocks = XFS_FILEOFF_MIN(roundup_pow_of_two(XFS_MAX_BMBT_EXTLEN),
				       alloc_blocks);

	if (unlikely(XFS_IS_REALTIME_INODE(ip)))
		freesp = xfs_rtx_to_rtb(mp,
			xfs_iomap_freesp(&mp->m_frextents,
					mp->m_low_rtexts, &shift));
	else
		freesp = xfs_iomap_freesp(&mp->m_fdblocks, mp->m_low_space,
				&shift);

	/*
	 * Check each quota to cap the prealloc size, provide a shift value to
	 * throttle with and adjust amount of available space.
	 */
	if (xfs_quota_need_throttle(ip, XFS_DQTYPE_USER, alloc_blocks))
		xfs_quota_calc_throttle(ip, XFS_DQTYPE_USER, &qblocks, &qshift,
					&freesp);
	if (xfs_quota_need_throttle(ip, XFS_DQTYPE_GROUP, alloc_blocks))
		xfs_quota_calc_throttle(ip, XFS_DQTYPE_GROUP, &qblocks, &qshift,
					&freesp);
	if (xfs_quota_need_throttle(ip, XFS_DQTYPE_PROJ, alloc_blocks))
		xfs_quota_calc_throttle(ip, XFS_DQTYPE_PROJ, &qblocks, &qshift,
					&freesp);

	/*
	 * The final prealloc size is set to the minimum of free space available
	 * in each of the quotas and the overall filesystem.
	 *
	 * The shift throttle value is set to the maximum value as determined by
	 * the global low free space values and per-quota low free space values.
	 */
	alloc_blocks = min(alloc_blocks, qblocks);
	shift = max(shift, qshift);

	if (shift)
		alloc_blocks >>= shift;
	/*
	 * rounddown_pow_of_two() returns an undefined result if we pass in
	 * alloc_blocks = 0.
	 */
	if (alloc_blocks)
		alloc_blocks = rounddown_pow_of_two(alloc_blocks);
	if (alloc_blocks > XFS_MAX_BMBT_EXTLEN)
		alloc_blocks = XFS_MAX_BMBT_EXTLEN;

	/*
	 * If we are still trying to allocate more space than is
	 * available, squash the prealloc hard. This can happen if we
	 * have a large file on a small filesystem and the above
	 * lowspace thresholds are smaller than XFS_BMBT_MAX_EXTLEN.
	 */
	while (alloc_blocks && alloc_blocks >= freesp)
		alloc_blocks >>= 4;
	if (alloc_blocks < mp->m_allocsize_blocks)
		alloc_blocks = mp->m_allocsize_blocks;
	trace_xfs_iomap_prealloc_size(ip, alloc_blocks, shift,
				      mp->m_allocsize_blocks);
	return alloc_blocks;
}

int
xfs_iomap_write_unwritten(
	xfs_inode_t	*ip,
	xfs_off_t	offset,
	xfs_off_t	count,
	bool		update_isize)
{
	xfs_mount_t	*mp = ip->i_mount;
	xfs_fileoff_t	offset_fsb;
	xfs_filblks_t	count_fsb;
	xfs_filblks_t	numblks_fsb;
	int		nimaps;
	xfs_trans_t	*tp;
	xfs_bmbt_irec_t imap;
	struct inode	*inode = VFS_I(ip);
	xfs_fsize_t	i_size;
	uint		resblks;
	int		error;

	trace_xfs_unwritten_convert(ip, offset, count);

	offset_fsb = XFS_B_TO_FSBT(mp, offset);
	count_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
	count_fsb = (xfs_filblks_t)(count_fsb - offset_fsb);

	/*
	 * Reserve enough blocks in this transaction for two complete extent
	 * btree splits.  We may be converting the middle part of an unwritten
	 * extent and in this case we will insert two new extents in the btree
	 * each of which could cause a full split.
	 *
	 * This reservation amount will be used in the first call to
	 * xfs_bmbt_split() to select an AG with enough space to satisfy the
	 * rest of the operation.
	 */
	resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1;

	/* Attach dquots so that bmbt splits are accounted correctly. */
	error = xfs_qm_dqattach(ip);
	if (error)
		return error;

	do {
		/*
		 * Set up a transaction to convert the range of extents
		 * from unwritten to real. Do allocations in a loop until
		 * we have covered the range passed in.
		 *
		 * Note that we can't risk to recursing back into the filesystem
		 * here as we might be asked to write out the same inode that we
		 * complete here and might deadlock on the iolock.
		 */
		error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, resblks,
				0, true, &tp);
		if (error)
			return error;

		error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK,
				XFS_IEXT_WRITE_UNWRITTEN_CNT);
		if (error == -EFBIG)
			error = xfs_iext_count_upgrade(tp, ip,
					XFS_IEXT_WRITE_UNWRITTEN_CNT);
		if (error)
			goto error_on_bmapi_transaction;

		/*
		 * Modify the unwritten extent state of the buffer.
		 */
		nimaps = 1;
		error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
					XFS_BMAPI_CONVERT, resblks, &imap,
					&nimaps);
		if (error)
			goto error_on_bmapi_transaction;

		/*
		 * Log the updated inode size as we go.  We have to be careful
		 * to only log it up to the actual write offset if it is
		 * halfway into a block.
		 */
		i_size = XFS_FSB_TO_B(mp, offset_fsb + count_fsb);
		if (i_size > offset + count)
			i_size = offset + count;
		if (update_isize && i_size > i_size_read(inode))
			i_size_write(inode, i_size);
		i_size = xfs_new_eof(ip, i_size);
		if (i_size) {
			ip->i_disk_size = i_size;
			xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
		}

		error = xfs_trans_commit(tp);
		xfs_iunlock(ip, XFS_ILOCK_EXCL);
		if (error)
			return error;

		if (unlikely(!xfs_valid_startblock(ip, imap.br_startblock))) {
			xfs_bmap_mark_sick(ip, XFS_DATA_FORK);
			return xfs_alert_fsblock_zero(ip, &imap);
		}

		if ((numblks_fsb = imap.br_blockcount) == 0) {
			/*
			 * The numblks_fsb value should always get
			 * smaller, otherwise the loop is stuck.
			 */
			ASSERT(imap.br_blockcount);
			break;
		}
		offset_fsb += numblks_fsb;
		count_fsb -= numblks_fsb;
	} while (count_fsb > 0);

	return 0;

error_on_bmapi_transaction:
	xfs_trans_cancel(tp);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	return error;
}

static inline bool
imap_needs_alloc(
	struct inode		*inode,
	unsigned		flags,
	struct xfs_bmbt_irec	*imap,
	int			nimaps)
{
	/* don't allocate blocks when just zeroing */
	if (flags & IOMAP_ZERO)
		return false;
	if (!nimaps ||
	    imap->br_startblock == HOLESTARTBLOCK ||
	    imap->br_startblock == DELAYSTARTBLOCK)
		return true;
	/* we convert unwritten extents before copying the data for DAX */
	if ((flags & IOMAP_DAX) && imap->br_state == XFS_EXT_UNWRITTEN)
		return true;
	return false;
}

static inline bool
imap_needs_cow(
	struct xfs_inode	*ip,
	unsigned int		flags,
	struct xfs_bmbt_irec	*imap,
	int			nimaps)
{
	if (!xfs_is_cow_inode(ip))
		return false;

	/* when zeroing we don't have to COW holes or unwritten extents */
	if (flags & IOMAP_ZERO) {
		if (!nimaps ||
		    imap->br_startblock == HOLESTARTBLOCK ||
		    imap->br_state == XFS_EXT_UNWRITTEN)
			return false;
	}

	return true;
}

static int
xfs_ilock_for_iomap(
	struct xfs_inode	*ip,
	unsigned		flags,
	unsigned		*lockmode)
{
	unsigned int		mode = *lockmode;
	bool			is_write = flags & (IOMAP_WRITE | IOMAP_ZERO);

	/*
	 * COW writes may allocate delalloc space or convert unwritten COW
	 * extents, so we need to make sure to take the lock exclusively here.
	 */
	if (xfs_is_cow_inode(ip) && is_write)
		mode = XFS_ILOCK_EXCL;

	/*
	 * Extents not yet cached requires exclusive access, don't block.  This
	 * is an opencoded xfs_ilock_data_map_shared() call but with
	 * non-blocking behaviour.
	 */
	if (xfs_need_iread_extents(&ip->i_df)) {
		if (flags & IOMAP_NOWAIT)
			return -EAGAIN;
		mode = XFS_ILOCK_EXCL;
	}

relock:
	if (flags & IOMAP_NOWAIT) {
		if (!xfs_ilock_nowait(ip, mode))
			return -EAGAIN;
	} else {
		xfs_ilock(ip, mode);
	}

	/*
	 * The reflink iflag could have changed since the earlier unlocked
	 * check, so if we got ILOCK_SHARED for a write and but we're now a
	 * reflink inode we have to switch to ILOCK_EXCL and relock.
	 */
	if (mode == XFS_ILOCK_SHARED && is_write && xfs_is_cow_inode(ip)) {
		xfs_iunlock(ip, mode);
		mode = XFS_ILOCK_EXCL;
		goto relock;
	}

	*lockmode = mode;
	return 0;
}

/*
 * Check that the imap we are going to return to the caller spans the entire
 * range that the caller requested for the IO.
 */
static bool
imap_spans_range(
	struct xfs_bmbt_irec	*imap,
	xfs_fileoff_t		offset_fsb,
	xfs_fileoff_t		end_fsb)
{
	if (imap->br_startoff > offset_fsb)
		return false;
	if (imap->br_startoff + imap->br_blockcount < end_fsb)
		return false;
	return true;
}

static int
xfs_direct_write_iomap_begin(
	struct inode		*inode,
	loff_t			offset,
	loff_t			length,
	unsigned		flags,
	struct iomap		*iomap,
	struct iomap		*srcmap)
{
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_bmbt_irec	imap, cmap;
	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
	xfs_fileoff_t		end_fsb = xfs_iomap_end_fsb(mp, offset, length);
	int			nimaps = 1, error = 0;
	bool			shared = false;
	u16			iomap_flags = 0;
	unsigned int		lockmode = XFS_ILOCK_SHARED;
	u64			seq;

	ASSERT(flags & (IOMAP_WRITE | IOMAP_ZERO));

	if (xfs_is_shutdown(mp))
		return -EIO;

	/*
	 * Writes that span EOF might trigger an IO size update on completion,
	 * so consider them to be dirty for the purposes of O_DSYNC even if
	 * there is no other metadata changes pending or have been made here.
	 */
	if (offset + length > i_size_read(inode))
		iomap_flags |= IOMAP_F_DIRTY;

	error = xfs_ilock_for_iomap(ip, flags, &lockmode);
	if (error)
		return error;

	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
			       &nimaps, 0);
	if (error)
		goto out_unlock;

	if (imap_needs_cow(ip, flags, &imap, nimaps)) {
		error = -EAGAIN;
		if (flags & IOMAP_NOWAIT)
			goto out_unlock;

		/* may drop and re-acquire the ilock */
		error = xfs_reflink_allocate_cow(ip, &imap, &cmap, &shared,
				&lockmode,
				(flags & IOMAP_DIRECT) || IS_DAX(inode));
		if (error)
			goto out_unlock;
		if (shared)
			goto out_found_cow;
		end_fsb = imap.br_startoff + imap.br_blockcount;
		length = XFS_FSB_TO_B(mp, end_fsb) - offset;
	}

	if (imap_needs_alloc(inode, flags, &imap, nimaps))
		goto allocate_blocks;

	/*
	 * NOWAIT and OVERWRITE I/O needs to span the entire requested I/O with
	 * a single map so that we avoid partial IO failures due to the rest of
	 * the I/O range not covered by this map triggering an EAGAIN condition
	 * when it is subsequently mapped and aborting the I/O.
	 */
	if (flags & (IOMAP_NOWAIT | IOMAP_OVERWRITE_ONLY)) {
		error = -EAGAIN;
		if (!imap_spans_range(&imap, offset_fsb, end_fsb))
			goto out_unlock;
	}

	/*
	 * For overwrite only I/O, we cannot convert unwritten extents without
	 * requiring sub-block zeroing.  This can only be done under an
	 * exclusive IOLOCK, hence return -EAGAIN if this is not a written
	 * extent to tell the caller to try again.
	 */
	if (flags & IOMAP_OVERWRITE_ONLY) {
		error = -EAGAIN;
		if (imap.br_state != XFS_EXT_NORM &&
	            ((offset | length) & mp->m_blockmask))
			goto out_unlock;
	}

	seq = xfs_iomap_inode_sequence(ip, iomap_flags);
	xfs_iunlock(ip, lockmode);
	trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap);
	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, iomap_flags, seq);

allocate_blocks:
	error = -EAGAIN;
	if (flags & (IOMAP_NOWAIT | IOMAP_OVERWRITE_ONLY))
		goto out_unlock;

	/*
	 * We cap the maximum length we map to a sane size  to keep the chunks
	 * of work done where somewhat symmetric with the work writeback does.
	 * This is a completely arbitrary number pulled out of thin air as a
	 * best guess for initial testing.
	 *
	 * Note that the values needs to be less than 32-bits wide until the
	 * lower level functions are updated.
	 */
	length = min_t(loff_t, length, 1024 * PAGE_SIZE);
	end_fsb = xfs_iomap_end_fsb(mp, offset, length);

	if (offset + length > XFS_ISIZE(ip))
		end_fsb = xfs_iomap_eof_align_last_fsb(ip, end_fsb);
	else if (nimaps && imap.br_startblock == HOLESTARTBLOCK)
		end_fsb = min(end_fsb, imap.br_startoff + imap.br_blockcount);
	xfs_iunlock(ip, lockmode);

	error = xfs_iomap_write_direct(ip, offset_fsb, end_fsb - offset_fsb,
			flags, &imap, &seq);
	if (error)
		return error;

	trace_xfs_iomap_alloc(ip, offset, length, XFS_DATA_FORK, &imap);
	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags,
				 iomap_flags | IOMAP_F_NEW, seq);

out_found_cow:
	length = XFS_FSB_TO_B(mp, cmap.br_startoff + cmap.br_blockcount);
	trace_xfs_iomap_found(ip, offset, length - offset, XFS_COW_FORK, &cmap);
	if (imap.br_startblock != HOLESTARTBLOCK) {
		seq = xfs_iomap_inode_sequence(ip, 0);
		error = xfs_bmbt_to_iomap(ip, srcmap, &imap, flags, 0, seq);
		if (error)
			goto out_unlock;
	}
	seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED);
	xfs_iunlock(ip, lockmode);
	return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED, seq);

out_unlock:
	if (lockmode)
		xfs_iunlock(ip, lockmode);
	return error;
}

const struct iomap_ops xfs_direct_write_iomap_ops = {
	.iomap_begin		= xfs_direct_write_iomap_begin,
};

static int
xfs_dax_write_iomap_end(
	struct inode		*inode,
	loff_t			pos,
	loff_t			length,
	ssize_t			written,
	unsigned		flags,
	struct iomap		*iomap)
{
	struct xfs_inode	*ip = XFS_I(inode);

	if (!xfs_is_cow_inode(ip))
		return 0;

	if (!written) {
		xfs_reflink_cancel_cow_range(ip, pos, length, true);
		return 0;
	}

	return xfs_reflink_end_cow(ip, pos, written);
}

const struct iomap_ops xfs_dax_write_iomap_ops = {
	.iomap_begin	= xfs_direct_write_iomap_begin,
	.iomap_end	= xfs_dax_write_iomap_end,
};

static int
xfs_buffered_write_iomap_begin(
	struct inode		*inode,
	loff_t			offset,
	loff_t			count,
	unsigned		flags,
	struct iomap		*iomap,
	struct iomap		*srcmap)
{
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
	xfs_fileoff_t		end_fsb = xfs_iomap_end_fsb(mp, offset, count);
	struct xfs_bmbt_irec	imap, cmap;
	struct xfs_iext_cursor	icur, ccur;
	xfs_fsblock_t		prealloc_blocks = 0;
	bool			eof = false, cow_eof = false, shared = false;
	int			allocfork = XFS_DATA_FORK;
	int			error = 0;
	unsigned int		lockmode = XFS_ILOCK_EXCL;
	u64			seq;

	if (xfs_is_shutdown(mp))
		return -EIO;

	/* we can't use delayed allocations when using extent size hints */
	if (xfs_get_extsz_hint(ip))
		return xfs_direct_write_iomap_begin(inode, offset, count,
				flags, iomap, srcmap);

	error = xfs_qm_dqattach(ip);
	if (error)
		return error;

	error = xfs_ilock_for_iomap(ip, flags, &lockmode);
	if (error)
		return error;

	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(&ip->i_df)) ||
	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
		xfs_bmap_mark_sick(ip, XFS_DATA_FORK);
		error = -EFSCORRUPTED;
		goto out_unlock;
	}

	XFS_STATS_INC(mp, xs_blk_mapw);

	error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
	if (error)
		goto out_unlock;

	/*
	 * Search the data fork first to look up our source mapping.  We
	 * always need the data fork map, as we have to return it to the
	 * iomap code so that the higher level write code can read data in to
	 * perform read-modify-write cycles for unaligned writes.
	 */
	eof = !xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap);
	if (eof)
		imap.br_startoff = end_fsb; /* fake hole until the end */

	/* We never need to allocate blocks for zeroing or unsharing a hole. */
	if ((flags & (IOMAP_UNSHARE | IOMAP_ZERO)) &&
	    imap.br_startoff > offset_fsb) {
		xfs_hole_to_iomap(ip, iomap, offset_fsb, imap.br_startoff);
		goto out_unlock;
	}

	/*
	 * Search the COW fork extent list even if we did not find a data fork
	 * extent.  This serves two purposes: first this implements the
	 * speculative preallocation using cowextsize, so that we also unshare
	 * block adjacent to shared blocks instead of just the shared blocks
	 * themselves.  Second the lookup in the extent list is generally faster
	 * than going out to the shared extent tree.
	 */
	if (xfs_is_cow_inode(ip)) {
		if (!ip->i_cowfp) {
			ASSERT(!xfs_is_reflink_inode(ip));
			xfs_ifork_init_cow(ip);
		}
		cow_eof = !xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb,
				&ccur, &cmap);
		if (!cow_eof && cmap.br_startoff <= offset_fsb) {
			trace_xfs_reflink_cow_found(ip, &cmap);
			goto found_cow;
		}
	}

	if (imap.br_startoff <= offset_fsb) {
		/*
		 * For reflink files we may need a delalloc reservation when
		 * overwriting shared extents.   This includes zeroing of
		 * existing extents that contain data.
		 */
		if (!xfs_is_cow_inode(ip) ||
		    ((flags & IOMAP_ZERO) && imap.br_state != XFS_EXT_NORM)) {
			trace_xfs_iomap_found(ip, offset, count, XFS_DATA_FORK,
					&imap);
			goto found_imap;
		}

		xfs_trim_extent(&imap, offset_fsb, end_fsb - offset_fsb);

		/* Trim the mapping to the nearest shared extent boundary. */
		error = xfs_bmap_trim_cow(ip, &imap, &shared);
		if (error)
			goto out_unlock;

		/* Not shared?  Just report the (potentially capped) extent. */
		if (!shared) {
			trace_xfs_iomap_found(ip, offset, count, XFS_DATA_FORK,
					&imap);
			goto found_imap;
		}

		/*
		 * Fork all the shared blocks from our write offset until the
		 * end of the extent.
		 */
		allocfork = XFS_COW_FORK;
		end_fsb = imap.br_startoff + imap.br_blockcount;
	} else {
		/*
		 * We cap the maximum length we map here to MAX_WRITEBACK_PAGES
		 * pages to keep the chunks of work done where somewhat
		 * symmetric with the work writeback does.  This is a completely
		 * arbitrary number pulled out of thin air.
		 *
		 * Note that the values needs to be less than 32-bits wide until
		 * the lower level functions are updated.
		 */
		count = min_t(loff_t, count, 1024 * PAGE_SIZE);
		end_fsb = xfs_iomap_end_fsb(mp, offset, count);

		if (xfs_is_always_cow_inode(ip))
			allocfork = XFS_COW_FORK;
	}

	if (eof && offset + count > XFS_ISIZE(ip)) {
		/*
		 * Determine the initial size of the preallocation.
		 * We clean up any extra preallocation when the file is closed.
		 */
		if (xfs_has_allocsize(mp))
			prealloc_blocks = mp->m_allocsize_blocks;
		else if (allocfork == XFS_DATA_FORK)
			prealloc_blocks = xfs_iomap_prealloc_size(ip, allocfork,
						offset, count, &icur);
		else
			prealloc_blocks = xfs_iomap_prealloc_size(ip, allocfork,
						offset, count, &ccur);
		if (prealloc_blocks) {
			xfs_extlen_t	align;
			xfs_off_t	end_offset;
			xfs_fileoff_t	p_end_fsb;

			end_offset = XFS_ALLOC_ALIGN(mp, offset + count - 1);
			p_end_fsb = XFS_B_TO_FSBT(mp, end_offset) +
					prealloc_blocks;

			align = xfs_eof_alignment(ip);
			if (align)
				p_end_fsb = roundup_64(p_end_fsb, align);

			p_end_fsb = min(p_end_fsb,
				XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes));
			ASSERT(p_end_fsb > offset_fsb);
			prealloc_blocks = p_end_fsb - end_fsb;
		}
	}

retry:
	error = xfs_bmapi_reserve_delalloc(ip, allocfork, offset_fsb,
			end_fsb - offset_fsb, prealloc_blocks,
			allocfork == XFS_DATA_FORK ? &imap : &cmap,
			allocfork == XFS_DATA_FORK ? &icur : &ccur,
			allocfork == XFS_DATA_FORK ? eof : cow_eof);
	switch (error) {
	case 0:
		break;
	case -ENOSPC:
	case -EDQUOT:
		/* retry without any preallocation */
		trace_xfs_delalloc_enospc(ip, offset, count);
		if (prealloc_blocks) {
			prealloc_blocks = 0;
			goto retry;
		}
		fallthrough;
	default:
		goto out_unlock;
	}

	if (allocfork == XFS_COW_FORK) {
		trace_xfs_iomap_alloc(ip, offset, count, allocfork, &cmap);
		goto found_cow;
	}

	/*
	 * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
	 * them out if the write happens to fail.
	 */
	seq = xfs_iomap_inode_sequence(ip, IOMAP_F_NEW);
	xfs_iunlock(ip, lockmode);
	trace_xfs_iomap_alloc(ip, offset, count, allocfork, &imap);
	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, IOMAP_F_NEW, seq);

found_imap:
	seq = xfs_iomap_inode_sequence(ip, 0);
	xfs_iunlock(ip, lockmode);
	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0, seq);

found_cow:
	seq = xfs_iomap_inode_sequence(ip, 0);
	if (imap.br_startoff <= offset_fsb) {
		error = xfs_bmbt_to_iomap(ip, srcmap, &imap, flags, 0, seq);
		if (error)
			goto out_unlock;
		seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED);
		xfs_iunlock(ip, lockmode);
		return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags,
					 IOMAP_F_SHARED, seq);
	}

	xfs_trim_extent(&cmap, offset_fsb, imap.br_startoff - offset_fsb);
	xfs_iunlock(ip, lockmode);
	return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, 0, seq);

out_unlock:
	xfs_iunlock(ip, lockmode);
	return error;
}

static int
xfs_buffered_write_delalloc_punch(
	struct inode		*inode,
	loff_t			offset,
	loff_t			length)
{
	return xfs_bmap_punch_delalloc_range(XFS_I(inode), offset,
			offset + length);
}

static int
xfs_buffered_write_iomap_end(
	struct inode		*inode,
	loff_t			offset,
	loff_t			length,
	ssize_t			written,
	unsigned		flags,
	struct iomap		*iomap)
{

	struct xfs_mount	*mp = XFS_M(inode->i_sb);
	int			error;

	error = iomap_file_buffered_write_punch_delalloc(inode, iomap, offset,
			length, written, &xfs_buffered_write_delalloc_punch);
	if (error && !xfs_is_shutdown(mp)) {
		xfs_alert(mp, "%s: unable to clean up ino 0x%llx",
			__func__, XFS_I(inode)->i_ino);
		return error;
	}
	return 0;
}

const struct iomap_ops xfs_buffered_write_iomap_ops = {
	.iomap_begin		= xfs_buffered_write_iomap_begin,
	.iomap_end		= xfs_buffered_write_iomap_end,
};

/*
 * iomap_page_mkwrite() will never fail in a way that requires delalloc extents
 * that it allocated to be revoked. Hence we do not need an .iomap_end method
 * for this operation.
 */
const struct iomap_ops xfs_page_mkwrite_iomap_ops = {
	.iomap_begin		= xfs_buffered_write_iomap_begin,
};

static int
xfs_read_iomap_begin(
	struct inode		*inode,
	loff_t			offset,
	loff_t			length,
	unsigned		flags,
	struct iomap		*iomap,
	struct iomap		*srcmap)
{
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_bmbt_irec	imap;
	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
	xfs_fileoff_t		end_fsb = xfs_iomap_end_fsb(mp, offset, length);
	int			nimaps = 1, error = 0;
	bool			shared = false;
	unsigned int		lockmode = XFS_ILOCK_SHARED;
	u64			seq;

	ASSERT(!(flags & (IOMAP_WRITE | IOMAP_ZERO)));

	if (xfs_is_shutdown(mp))
		return -EIO;

	error = xfs_ilock_for_iomap(ip, flags, &lockmode);
	if (error)
		return error;
	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
			       &nimaps, 0);
	if (!error && ((flags & IOMAP_REPORT) || IS_DAX(inode)))
		error = xfs_reflink_trim_around_shared(ip, &imap, &shared);
	seq = xfs_iomap_inode_sequence(ip, shared ? IOMAP_F_SHARED : 0);
	xfs_iunlock(ip, lockmode);

	if (error)
		return error;
	trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap);
	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags,
				 shared ? IOMAP_F_SHARED : 0, seq);
}

const struct iomap_ops xfs_read_iomap_ops = {
	.iomap_begin		= xfs_read_iomap_begin,
};

static int
xfs_seek_iomap_begin(
	struct inode		*inode,
	loff_t			offset,
	loff_t			length,
	unsigned		flags,
	struct iomap		*iomap,
	struct iomap		*srcmap)
{
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + length);
	xfs_fileoff_t		cow_fsb = NULLFILEOFF, data_fsb = NULLFILEOFF;
	struct xfs_iext_cursor	icur;
	struct xfs_bmbt_irec	imap, cmap;
	int			error = 0;
	unsigned		lockmode;
	u64			seq;

	if (xfs_is_shutdown(mp))
		return -EIO;

	lockmode = xfs_ilock_data_map_shared(ip);
	error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
	if (error)
		goto out_unlock;

	if (xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap)) {
		/*
		 * If we found a data extent we are done.
		 */
		if (imap.br_startoff <= offset_fsb)
			goto done;
		data_fsb = imap.br_startoff;
	} else {
		/*
		 * Fake a hole until the end of the file.
		 */
		data_fsb = xfs_iomap_end_fsb(mp, offset, length);
	}

	/*
	 * If a COW fork extent covers the hole, report it - capped to the next
	 * data fork extent:
	 */
	if (xfs_inode_has_cow_data(ip) &&
	    xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap))
		cow_fsb = cmap.br_startoff;
	if (cow_fsb != NULLFILEOFF && cow_fsb <= offset_fsb) {
		if (data_fsb < cow_fsb + cmap.br_blockcount)
			end_fsb = min(end_fsb, data_fsb);
		xfs_trim_extent(&cmap, offset_fsb, end_fsb - offset_fsb);
		seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED);
		error = xfs_bmbt_to_iomap(ip, iomap, &cmap, flags,
				IOMAP_F_SHARED, seq);
		/*
		 * This is a COW extent, so we must probe the page cache
		 * because there could be dirty page cache being backed
		 * by this extent.
		 */
		iomap->type = IOMAP_UNWRITTEN;
		goto out_unlock;
	}

	/*
	 * Else report a hole, capped to the next found data or COW extent.
	 */
	if (cow_fsb != NULLFILEOFF && cow_fsb < data_fsb)
		imap.br_blockcount = cow_fsb - offset_fsb;
	else
		imap.br_blockcount = data_fsb - offset_fsb;
	imap.br_startoff = offset_fsb;
	imap.br_startblock = HOLESTARTBLOCK;
	imap.br_state = XFS_EXT_NORM;
done:
	seq = xfs_iomap_inode_sequence(ip, 0);
	xfs_trim_extent(&imap, offset_fsb, end_fsb - offset_fsb);
	error = xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0, seq);
out_unlock:
	xfs_iunlock(ip, lockmode);
	return error;
}

const struct iomap_ops xfs_seek_iomap_ops = {
	.iomap_begin		= xfs_seek_iomap_begin,
};

static int
xfs_xattr_iomap_begin(
	struct inode		*inode,
	loff_t			offset,
	loff_t			length,
	unsigned		flags,
	struct iomap		*iomap,
	struct iomap		*srcmap)
{
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + length);
	struct xfs_bmbt_irec	imap;
	int			nimaps = 1, error = 0;
	unsigned		lockmode;
	int			seq;

	if (xfs_is_shutdown(mp))
		return -EIO;

	lockmode = xfs_ilock_attr_map_shared(ip);

	/* if there are no attribute fork or extents, return ENOENT */
	if (!xfs_inode_has_attr_fork(ip) || !ip->i_af.if_nextents) {
		error = -ENOENT;
		goto out_unlock;
	}

	ASSERT(ip->i_af.if_format != XFS_DINODE_FMT_LOCAL);
	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
			       &nimaps, XFS_BMAPI_ATTRFORK);
out_unlock:

	seq = xfs_iomap_inode_sequence(ip, IOMAP_F_XATTR);
	xfs_iunlock(ip, lockmode);

	if (error)
		return error;
	ASSERT(nimaps);
	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, IOMAP_F_XATTR, seq);
}

const struct iomap_ops xfs_xattr_iomap_ops = {
	.iomap_begin		= xfs_xattr_iomap_begin,
};

int
xfs_zero_range(
	struct xfs_inode	*ip,
	loff_t			pos,
	loff_t			len,
	bool			*did_zero)
{
	struct inode		*inode = VFS_I(ip);

	if (IS_DAX(inode))
		return dax_zero_range(inode, pos, len, did_zero,
				      &xfs_dax_write_iomap_ops);
	return iomap_zero_range(inode, pos, len, did_zero,
				&xfs_buffered_write_iomap_ops);
}

int
xfs_truncate_page(
	struct xfs_inode	*ip,
	loff_t			pos,
	bool			*did_zero)
{
	struct inode		*inode = VFS_I(ip);

	if (IS_DAX(inode))
		return dax_truncate_page(inode, pos, did_zero,
					&xfs_dax_write_iomap_ops);
	return iomap_truncate_page(inode, pos, did_zero,
				   &xfs_buffered_write_iomap_ops);
}