summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_iomap.c
blob: 0d147428971e0c21c88aa90e2628001cf582971c (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
/*
 * Copyright (c) 2000-2006 Silicon Graphics, Inc.
 * Copyright (c) 2016 Christoph Hellwig.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include <linux/iomap.h>
#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_defer.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_error.h"
#include "xfs_trans.h"
#include "xfs_trans_space.h"
#include "xfs_iomap.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_quota.h"
#include "xfs_dquot_item.h"
#include "xfs_dquot.h"
#include "xfs_reflink.h"


#define XFS_WRITEIO_ALIGN(mp,off)	(((off) >> mp->m_writeio_log) \
						<< mp->m_writeio_log)

void
xfs_bmbt_to_iomap(
	struct xfs_inode	*ip,
	struct iomap		*iomap,
	struct xfs_bmbt_irec	*imap)
{
	struct xfs_mount	*mp = ip->i_mount;

	if (imap->br_startblock == HOLESTARTBLOCK) {
		iomap->blkno = IOMAP_NULL_BLOCK;
		iomap->type = IOMAP_HOLE;
	} else if (imap->br_startblock == DELAYSTARTBLOCK) {
		iomap->blkno = IOMAP_NULL_BLOCK;
		iomap->type = IOMAP_DELALLOC;
	} else {
		iomap->blkno = xfs_fsb_to_db(ip, imap->br_startblock);
		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);
	iomap->bdev = xfs_find_bdev_for_inode(VFS_I(ip));
}

xfs_extlen_t
xfs_eof_alignment(
	struct xfs_inode	*ip,
	xfs_extlen_t		extsize)
{
	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 && (mp->m_flags & XFS_MOUNT_SWALLOC))
			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;
	}

	/*
	 * Always round up the allocation request to an extent boundary
	 * (when file on a real-time subvolume or has di_extsize hint).
	 */
	if (extsize) {
		if (align)
			align = roundup_64(align, extsize);
		else
			align = extsize;
	}

	return align;
}

STATIC int
xfs_iomap_eof_align_last_fsb(
	struct xfs_inode	*ip,
	xfs_extlen_t		extsize,
	xfs_fileoff_t		*last_fsb)
{
	xfs_extlen_t		align = xfs_eof_alignment(ip, extsize);

	if (align) {
		xfs_fileoff_t	new_last_fsb = roundup_64(*last_fsb, align);
		int		eof, error;

		error = xfs_bmap_eof(ip, new_last_fsb, XFS_DATA_FORK, &eof);
		if (error)
			return error;
		if (eof)
			*last_fsb = new_last_fsb;
	}
	return 0;
}

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);
	return -EFSCORRUPTED;
}

int
xfs_iomap_write_direct(
	xfs_inode_t	*ip,
	xfs_off_t	offset,
	size_t		count,
	xfs_bmbt_irec_t *imap,
	int		nmaps)
{
	xfs_mount_t	*mp = ip->i_mount;
	xfs_fileoff_t	offset_fsb;
	xfs_fileoff_t	last_fsb;
	xfs_filblks_t	count_fsb, resaligned;
	xfs_fsblock_t	firstfsb;
	xfs_extlen_t	extsz, temp;
	int		nimaps;
	int		quota_flag;
	int		rt;
	xfs_trans_t	*tp;
	struct xfs_defer_ops dfops;
	uint		qblocks, resblks, resrtextents;
	int		error;
	int		lockmode;
	int		bmapi_flags = XFS_BMAPI_PREALLOC;
	uint		tflags = 0;

	rt = XFS_IS_REALTIME_INODE(ip);
	extsz = xfs_get_extsz_hint(ip);
	lockmode = XFS_ILOCK_SHARED;	/* locked by caller */

	ASSERT(xfs_isilocked(ip, lockmode));

	offset_fsb = XFS_B_TO_FSBT(mp, offset);
	last_fsb = XFS_B_TO_FSB(mp, ((xfs_ufsize_t)(offset + count)));
	if ((offset + count) > XFS_ISIZE(ip)) {
		/*
		 * Assert that the in-core extent list is present since this can
		 * call xfs_iread_extents() and we only have the ilock shared.
		 * This should be safe because the lock was held around a bmapi
		 * call in the caller and we only need it to access the in-core
		 * list.
		 */
		ASSERT(XFS_IFORK_PTR(ip, XFS_DATA_FORK)->if_flags &
								XFS_IFEXTENTS);
		error = xfs_iomap_eof_align_last_fsb(ip, extsz, &last_fsb);
		if (error)
			goto out_unlock;
	} else {
		if (nmaps && (imap->br_startblock == HOLESTARTBLOCK))
			last_fsb = MIN(last_fsb, (xfs_fileoff_t)
					imap->br_blockcount +
					imap->br_startoff);
	}
	count_fsb = last_fsb - offset_fsb;
	ASSERT(count_fsb > 0);

	resaligned = count_fsb;
	if (unlikely(extsz)) {
		if ((temp = do_mod(offset_fsb, extsz)))
			resaligned += temp;
		if ((temp = do_mod(resaligned, extsz)))
			resaligned += extsz - temp;
	}

	if (unlikely(rt)) {
		resrtextents = qblocks = resaligned;
		resrtextents /= mp->m_sb.sb_rextsize;
		resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
		quota_flag = XFS_QMOPT_RES_RTBLKS;
	} else {
		resrtextents = 0;
		resblks = qblocks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned);
		quota_flag = XFS_QMOPT_RES_REGBLKS;
	}

	/*
	 * Drop the shared lock acquired by the caller, attach the dquot if
	 * necessary and move on to transaction setup.
	 */
	xfs_iunlock(ip, lockmode);
	error = xfs_qm_dqattach(ip, 0);
	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 (IS_DAX(VFS_I(ip))) {
		bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
		if (ISUNWRITTEN(imap)) {
			tflags |= XFS_TRANS_RESERVE;
			resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1;
		}
	}
	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, resrtextents,
			tflags, &tp);
	if (error)
		return error;

	lockmode = XFS_ILOCK_EXCL;
	xfs_ilock(ip, lockmode);

	error = xfs_trans_reserve_quota_nblks(tp, ip, qblocks, 0, quota_flag);
	if (error)
		goto out_trans_cancel;

	xfs_trans_ijoin(tp, ip, 0);

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

	/*
	 * Complete the transaction
	 */
	error = xfs_defer_finish(&tp, &dfops, NULL);
	if (error)
		goto out_bmap_cancel;

	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 (!(imap->br_startblock || XFS_IS_REALTIME_INODE(ip)))
		error = xfs_alert_fsblock_zero(ip, imap);

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

out_bmap_cancel:
	xfs_defer_cancel(&dfops);
	xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
out_trans_cancel:
	xfs_trans_cancel(tp);
	goto out_unlock;
}

STATIC bool
xfs_quota_need_throttle(
	struct xfs_inode *ip,
	int 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_res_bcount + alloc_blocks < dq->q_prealloc_lo_wmark)
		return false;

	return true;
}

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

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

	freesp = dq->q_prealloc_hi_wmark - dq->q_res_bcount;
	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;
	}
}

/*
 * If we are doing a write at the end of the file and there are no allocations
 * past this one, then extend the allocation out to the file system's write
 * iosize.
 *
 * 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 full, the smaller the maximum prealocation.
 *
 * 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.
 *
 * We clean up any extra space left over when the file is closed in
 * xfs_inactive().
 */
STATIC xfs_fsblock_t
xfs_iomap_prealloc_size(
	struct xfs_inode	*ip,
	loff_t			offset,
	loff_t			count,
	xfs_extnum_t		idx)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
	struct xfs_bmbt_irec	prev;
	int			shift = 0;
	int64_t			freesp;
	xfs_fsblock_t		qblocks;
	int			qshift = 0;
	xfs_fsblock_t		alloc_blocks = 0;

	if (offset + count <= XFS_ISIZE(ip))
		return 0;

	if (!(mp->m_flags & XFS_MOUNT_DFLT_IOSIZE) &&
	    (XFS_ISIZE(ip) < XFS_FSB_TO_B(mp, mp->m_writeio_blocks)))
		return 0;

	/*
	 * If an explicit allocsize is set, the file is small, or we
	 * are writing behind a hole, then use the minimum prealloc:
	 */
	if ((mp->m_flags & XFS_MOUNT_DFLT_IOSIZE) ||
	    XFS_ISIZE(ip) < XFS_FSB_TO_B(mp, mp->m_dalign) ||
	    !xfs_iext_get_extent(ifp, idx - 1, &prev) ||
	    prev.br_startoff + prev.br_blockcount < offset_fsb)
		return mp->m_writeio_blocks;

	/*
	 * Determine the initial size of the preallocation. We are beyond the
	 * current EOF here, but we need to take into account whether this is
	 * a sparse write or an extending write when determining the
	 * preallocation size.  Hence we need to look up the extent that ends
	 * at the current write offset and use the result to determine the
	 * preallocation size.
	 *
	 * If the extent is a hole, then preallocation is essentially disabled.
	 * Otherwise we take the size of the preceding data extent as the basis
	 * for the preallocation size. If the size of the extent 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 MAXEXTLEN rather than falling short due to things
	 * like stripe unit/width alignment of real extents.
	 */
	if (prev.br_blockcount <= (MAXEXTLEN >> 1))
		alloc_blocks = prev.br_blockcount << 1;
	else
		alloc_blocks = XFS_B_TO_FSB(mp, offset);
	if (!alloc_blocks)
		goto check_writeio;
	qblocks = alloc_blocks;

	/*
	 * MAXEXTLEN 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 MAXEXTLEN.
	 */
	alloc_blocks = XFS_FILEOFF_MIN(roundup_pow_of_two(MAXEXTLEN),
				       alloc_blocks);

	freesp = percpu_counter_read_positive(&mp->m_fdblocks);
	if (freesp < mp->m_low_space[XFS_LOWSP_5_PCNT]) {
		shift = 2;
		if (freesp < mp->m_low_space[XFS_LOWSP_4_PCNT])
			shift++;
		if (freesp < mp->m_low_space[XFS_LOWSP_3_PCNT])
			shift++;
		if (freesp < mp->m_low_space[XFS_LOWSP_2_PCNT])
			shift++;
		if (freesp < mp->m_low_space[XFS_LOWSP_1_PCNT])
			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_DQ_USER, alloc_blocks))
		xfs_quota_calc_throttle(ip, XFS_DQ_USER, &qblocks, &qshift,
					&freesp);
	if (xfs_quota_need_throttle(ip, XFS_DQ_GROUP, alloc_blocks))
		xfs_quota_calc_throttle(ip, XFS_DQ_GROUP, &qblocks, &qshift,
					&freesp);
	if (xfs_quota_need_throttle(ip, XFS_DQ_PROJ, alloc_blocks))
		xfs_quota_calc_throttle(ip, XFS_DQ_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 > MAXEXTLEN)
		alloc_blocks = MAXEXTLEN;

	/*
	 * 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 MAXEXTLEN.
	 */
	while (alloc_blocks && alloc_blocks >= freesp)
		alloc_blocks >>= 4;
check_writeio:
	if (alloc_blocks < mp->m_writeio_blocks)
		alloc_blocks = mp->m_writeio_blocks;
	trace_xfs_iomap_prealloc_size(ip, alloc_blocks, shift,
				      mp->m_writeio_blocks);
	return alloc_blocks;
}

static int
xfs_file_iomap_begin_delay(
	struct inode		*inode,
	loff_t			offset,
	loff_t			count,
	unsigned		flags,
	struct iomap		*iomap)
{
	struct xfs_inode	*ip = XFS_I(inode);
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
	xfs_fileoff_t		maxbytes_fsb =
		XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
	xfs_fileoff_t		end_fsb;
	int			error = 0, eof = 0;
	struct xfs_bmbt_irec	got;
	xfs_extnum_t		idx;
	xfs_fsblock_t		prealloc_blocks = 0;

	ASSERT(!XFS_IS_REALTIME_INODE(ip));
	ASSERT(!xfs_get_extsz_hint(ip));

	xfs_ilock(ip, XFS_ILOCK_EXCL);

	if (unlikely(XFS_TEST_ERROR(
	    (XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_EXTENTS &&
	     XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_BTREE),
	     mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
		error = -EFSCORRUPTED;
		goto out_unlock;
	}

	XFS_STATS_INC(mp, xs_blk_mapw);

	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
		error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
		if (error)
			goto out_unlock;
	}

	eof = !xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got);
	if (!eof && got.br_startoff <= offset_fsb) {
		if (xfs_is_reflink_inode(ip)) {
			bool		shared;

			end_fsb = min(XFS_B_TO_FSB(mp, offset + count),
					maxbytes_fsb);
			xfs_trim_extent(&got, offset_fsb, end_fsb - offset_fsb);
			error = xfs_reflink_reserve_cow(ip, &got, &shared);
			if (error)
				goto out_unlock;
		}

		trace_xfs_iomap_found(ip, offset, count, 0, &got);
		goto done;
	}

	error = xfs_qm_dqattach_locked(ip, 0);
	if (error)
		goto out_unlock;

	/*
	 * 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 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.
	 */
	count = min_t(loff_t, count, 1024 * PAGE_SIZE);
	end_fsb = min(XFS_B_TO_FSB(mp, offset + count), maxbytes_fsb);

	if (eof) {
		prealloc_blocks = xfs_iomap_prealloc_size(ip, offset, count, idx);
		if (prealloc_blocks) {
			xfs_extlen_t	align;
			xfs_off_t	end_offset;
			xfs_fileoff_t	p_end_fsb;

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

			align = xfs_eof_alignment(ip, 0);
			if (align)
				p_end_fsb = roundup_64(p_end_fsb, align);

			p_end_fsb = min(p_end_fsb, maxbytes_fsb);
			ASSERT(p_end_fsb > offset_fsb);
			prealloc_blocks = p_end_fsb - end_fsb;
		}
	}

retry:
	error = xfs_bmapi_reserve_delalloc(ip, XFS_DATA_FORK, offset_fsb,
			end_fsb - offset_fsb, prealloc_blocks, &got, &idx, 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;
		}
		/*FALLTHRU*/
	default:
		goto out_unlock;
	}

	trace_xfs_iomap_alloc(ip, offset, count, 0, &got);
done:
	if (isnullstartblock(got.br_startblock))
		got.br_startblock = DELAYSTARTBLOCK;

	if (!got.br_startblock) {
		error = xfs_alert_fsblock_zero(ip, &got);
		if (error)
			goto out_unlock;
	}

	xfs_bmbt_to_iomap(ip, iomap, &got);

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

/*
 * Pass in a delayed allocate extent, convert it to real extents;
 * return to the caller the extent we create which maps on top of
 * the originating callers request.
 *
 * Called without a lock on the inode.
 *
 * We no longer bother to look at the incoming map - all we have to
 * guarantee is that whatever we allocate fills the required range.
 */
int
xfs_iomap_write_allocate(
	xfs_inode_t	*ip,
	int		whichfork,
	xfs_off_t	offset,
	xfs_bmbt_irec_t *imap)
{
	xfs_mount_t	*mp = ip->i_mount;
	xfs_fileoff_t	offset_fsb, last_block;
	xfs_fileoff_t	end_fsb, map_start_fsb;
	xfs_fsblock_t	first_block;
	struct xfs_defer_ops	dfops;
	xfs_filblks_t	count_fsb;
	xfs_trans_t	*tp;
	int		nimaps;
	int		error = 0;
	int		flags = 0;
	int		nres;

	if (whichfork == XFS_COW_FORK)
		flags |= XFS_BMAPI_COWFORK;

	/*
	 * Make sure that the dquots are there.
	 */
	error = xfs_qm_dqattach(ip, 0);
	if (error)
		return error;

	offset_fsb = XFS_B_TO_FSBT(mp, offset);
	count_fsb = imap->br_blockcount;
	map_start_fsb = imap->br_startoff;

	XFS_STATS_ADD(mp, xs_xstrat_bytes, XFS_FSB_TO_B(mp, count_fsb));

	while (count_fsb != 0) {
		/*
		 * Set up a transaction with which to allocate the
		 * backing store for the file.  Do allocations in a
		 * loop until we get some space in the range we are
		 * interested in.  The other space that might be allocated
		 * is in the delayed allocation extent on which we sit
		 * but before our buffer starts.
		 */
		nimaps = 0;
		while (nimaps == 0) {
			nres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
			/*
			 * We have already reserved space for the extent and any
			 * indirect blocks when creating the delalloc extent,
			 * there is no need to reserve space in this transaction
			 * again.
			 */
			error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0,
					0, XFS_TRANS_RESERVE, &tp);
			if (error)
				return error;

			xfs_ilock(ip, XFS_ILOCK_EXCL);
			xfs_trans_ijoin(tp, ip, 0);

			xfs_defer_init(&dfops, &first_block);

			/*
			 * it is possible that the extents have changed since
			 * we did the read call as we dropped the ilock for a
			 * while. We have to be careful about truncates or hole
			 * punchs here - we are not allowed to allocate
			 * non-delalloc blocks here.
			 *
			 * The only protection against truncation is the pages
			 * for the range we are being asked to convert are
			 * locked and hence a truncate will block on them
			 * first.
			 *
			 * As a result, if we go beyond the range we really
			 * need and hit an delalloc extent boundary followed by
			 * a hole while we have excess blocks in the map, we
			 * will fill the hole incorrectly and overrun the
			 * transaction reservation.
			 *
			 * Using a single map prevents this as we are forced to
			 * check each map we look for overlap with the desired
			 * range and abort as soon as we find it. Also, given
			 * that we only return a single map, having one beyond
			 * what we can return is probably a bit silly.
			 *
			 * We also need to check that we don't go beyond EOF;
			 * this is a truncate optimisation as a truncate sets
			 * the new file size before block on the pages we
			 * currently have locked under writeback. Because they
			 * are about to be tossed, we don't need to write them
			 * back....
			 */
			nimaps = 1;
			end_fsb = XFS_B_TO_FSB(mp, XFS_ISIZE(ip));
			error = xfs_bmap_last_offset(ip, &last_block,
							XFS_DATA_FORK);
			if (error)
				goto trans_cancel;

			last_block = XFS_FILEOFF_MAX(last_block, end_fsb);
			if ((map_start_fsb + count_fsb) > last_block) {
				count_fsb = last_block - map_start_fsb;
				if (count_fsb == 0) {
					error = -EAGAIN;
					goto trans_cancel;
				}
			}

			/*
			 * From this point onwards we overwrite the imap
			 * pointer that the caller gave to us.
			 */
			error = xfs_bmapi_write(tp, ip, map_start_fsb,
						count_fsb, flags, &first_block,
						nres, imap, &nimaps,
						&dfops);
			if (error)
				goto trans_cancel;

			error = xfs_defer_finish(&tp, &dfops, NULL);
			if (error)
				goto trans_cancel;

			error = xfs_trans_commit(tp);
			if (error)
				goto error0;

			xfs_iunlock(ip, XFS_ILOCK_EXCL);
		}

		/*
		 * See if we were able to allocate an extent that
		 * covers at least part of the callers request
		 */
		if (!(imap->br_startblock || XFS_IS_REALTIME_INODE(ip)))
			return xfs_alert_fsblock_zero(ip, imap);

		if ((offset_fsb >= imap->br_startoff) &&
		    (offset_fsb < (imap->br_startoff +
				   imap->br_blockcount))) {
			XFS_STATS_INC(mp, xs_xstrat_quick);
			return 0;
		}

		/*
		 * So far we have not mapped the requested part of the
		 * file, just surrounding data, try again.
		 */
		count_fsb -= imap->br_blockcount;
		map_start_fsb = imap->br_startoff + imap->br_blockcount;
	}

trans_cancel:
	xfs_defer_cancel(&dfops);
	xfs_trans_cancel(tp);
error0:
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	return error;
}

int
xfs_iomap_write_unwritten(
	xfs_inode_t	*ip,
	xfs_off_t	offset,
	xfs_off_t	count)
{
	xfs_mount_t	*mp = ip->i_mount;
	xfs_fileoff_t	offset_fsb;
	xfs_filblks_t	count_fsb;
	xfs_filblks_t	numblks_fsb;
	xfs_fsblock_t	firstfsb;
	int		nimaps;
	xfs_trans_t	*tp;
	xfs_bmbt_irec_t imap;
	struct xfs_defer_ops dfops;
	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;

	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(mp, &M_RES(mp)->tr_write, resblks, 0,
				XFS_TRANS_RESERVE | XFS_TRANS_NOFS, &tp);
		if (error)
			return error;

		xfs_ilock(ip, XFS_ILOCK_EXCL);
		xfs_trans_ijoin(tp, ip, 0);

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

		i_size = xfs_new_eof(ip, i_size);
		if (i_size) {
			ip->i_d.di_size = i_size;
			xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
		}

		error = xfs_defer_finish(&tp, &dfops, NULL);
		if (error)
			goto error_on_bmapi_transaction;

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

		if (!(imap.br_startblock || XFS_IS_REALTIME_INODE(ip)))
			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_defer_cancel(&dfops);
	xfs_trans_cancel(tp);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	return error;
}

static inline bool imap_needs_alloc(struct inode *inode,
		struct xfs_bmbt_irec *imap, int nimaps)
{
	return !nimaps ||
		imap->br_startblock == HOLESTARTBLOCK ||
		imap->br_startblock == DELAYSTARTBLOCK ||
		(IS_DAX(inode) && ISUNWRITTEN(imap));
}

static inline bool need_excl_ilock(struct xfs_inode *ip, unsigned flags)
{
	/*
	 * COW writes will allocate delalloc space, so we need to make sure
	 * to take the lock exclusively here.
	 */
	if (xfs_is_reflink_inode(ip) && (flags & (IOMAP_WRITE | IOMAP_ZERO)))
		return true;
	if ((flags & IOMAP_DIRECT) && (flags & IOMAP_WRITE))
		return true;
	return false;
}

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

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	if (((flags & (IOMAP_WRITE | IOMAP_DIRECT)) == IOMAP_WRITE) &&
			!IS_DAX(inode) && !xfs_get_extsz_hint(ip)) {
		/* Reserve delalloc blocks for regular writeback. */
		return xfs_file_iomap_begin_delay(inode, offset, length, flags,
				iomap);
	}

	if (need_excl_ilock(ip, flags)) {
		lockmode = XFS_ILOCK_EXCL;
		xfs_ilock(ip, XFS_ILOCK_EXCL);
	} else {
		lockmode = xfs_ilock_data_map_shared(ip);
	}

	ASSERT(offset <= mp->m_super->s_maxbytes);
	if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes)
		length = mp->m_super->s_maxbytes - offset;
	offset_fsb = XFS_B_TO_FSBT(mp, offset);
	end_fsb = XFS_B_TO_FSB(mp, offset + length);

	if (xfs_is_reflink_inode(ip) &&
	    (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT)) {
		shared = xfs_reflink_find_cow_mapping(ip, offset, &imap);
		if (shared) {
			xfs_iunlock(ip, lockmode);
			goto alloc_done;
		}
		ASSERT(!isnullstartblock(imap.br_startblock));
	}

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

	if ((flags & IOMAP_REPORT) ||
	    (xfs_is_reflink_inode(ip) &&
	     (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT))) {
		/* Trim the mapping to the nearest shared extent boundary. */
		error = xfs_reflink_trim_around_shared(ip, &imap, &shared,
				&trimmed);
		if (error)
			goto out_unlock;

		/*
		 * We're here because we're trying to do a directio write to a
		 * region that isn't aligned to a filesystem block.  If the
		 * extent is shared, fall back to buffered mode to handle the
		 * RMW.
		 */
		if (!(flags & IOMAP_REPORT) && shared) {
			trace_xfs_reflink_bounce_dio_write(ip, &imap);
			error = -EREMCHG;
			goto out_unlock;
		}
	}

	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
		error = xfs_reflink_reserve_cow(ip, &imap, &shared);
		if (error)
			goto out_unlock;

		end_fsb = imap.br_startoff + imap.br_blockcount;
		length = XFS_FSB_TO_B(mp, end_fsb) - offset;
	}

	if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) {
		/*
		 * 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 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);
		/*
		 * xfs_iomap_write_direct() expects the shared lock. It
		 * is unlocked on return.
		 */
		if (lockmode == XFS_ILOCK_EXCL)
			xfs_ilock_demote(ip, lockmode);
		error = xfs_iomap_write_direct(ip, offset, length, &imap,
				nimaps);
		if (error)
			return error;

alloc_done:
		iomap->flags = IOMAP_F_NEW;
		trace_xfs_iomap_alloc(ip, offset, length, 0, &imap);
	} else {
		ASSERT(nimaps);

		xfs_iunlock(ip, lockmode);
		trace_xfs_iomap_found(ip, offset, length, 0, &imap);
	}

	xfs_bmbt_to_iomap(ip, iomap, &imap);
	if (shared)
		iomap->flags |= IOMAP_F_SHARED;
	return 0;
out_unlock:
	xfs_iunlock(ip, lockmode);
	return error;
}

static int
xfs_file_iomap_end_delalloc(
	struct xfs_inode	*ip,
	loff_t			offset,
	loff_t			length,
	ssize_t			written)
{
	struct xfs_mount	*mp = ip->i_mount;
	xfs_fileoff_t		start_fsb;
	xfs_fileoff_t		end_fsb;
	int			error = 0;

	start_fsb = XFS_B_TO_FSB(mp, offset + written);
	end_fsb = XFS_B_TO_FSB(mp, offset + length);

	/*
	 * Trim back delalloc blocks if we didn't manage to write the whole
	 * range reserved.
	 *
	 * We don't need to care about racing delalloc as we hold i_mutex
	 * across the reserve/allocate/unreserve calls. If there are delalloc
	 * blocks in the range, they are ours.
	 */
	if (start_fsb < end_fsb) {
		xfs_ilock(ip, XFS_ILOCK_EXCL);
		error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
					       end_fsb - start_fsb);
		xfs_iunlock(ip, XFS_ILOCK_EXCL);

		if (error && !XFS_FORCED_SHUTDOWN(mp)) {
			xfs_alert(mp, "%s: unable to clean up ino %lld",
				__func__, ip->i_ino);
			return error;
		}
	}

	return 0;
}

static int
xfs_file_iomap_end(
	struct inode		*inode,
	loff_t			offset,
	loff_t			length,
	ssize_t			written,
	unsigned		flags,
	struct iomap		*iomap)
{
	if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC)
		return xfs_file_iomap_end_delalloc(XFS_I(inode), offset,
				length, written);
	return 0;
}

struct iomap_ops xfs_iomap_ops = {
	.iomap_begin		= xfs_file_iomap_begin,
	.iomap_end		= xfs_file_iomap_end,
};

static int
xfs_xattr_iomap_begin(
	struct inode		*inode,
	loff_t			offset,
	loff_t			length,
	unsigned		flags,
	struct iomap		*iomap)
{
	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;

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	lockmode = xfs_ilock_data_map_shared(ip);

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

	ASSERT(ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL);
	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
			       &nimaps, XFS_BMAPI_ENTIRE | XFS_BMAPI_ATTRFORK);
out_unlock:
	xfs_iunlock(ip, lockmode);

	if (!error) {
		ASSERT(nimaps);
		xfs_bmbt_to_iomap(ip, iomap, &imap);
	}

	return error;
}

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