aboutsummaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_iomap.c
blob: 5a30dd899d2b32c38dbc1fc552e323d233f33e50 (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
/*
 * Copyright (c) 2000-2006 Silicon Graphics, Inc.
 * 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 "xfs.h"
#include "xfs_fs.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_alloc.h"
#include "xfs_quota.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
#include "xfs_btree.h"
#include "xfs_bmap.h"
#include "xfs_rtalloc.h"
#include "xfs_error.h"
#include "xfs_itable.h"
#include "xfs_attr.h"
#include "xfs_buf_item.h"
#include "xfs_trans_space.h"
#include "xfs_utils.h"
#include "xfs_iomap.h"
#include "xfs_trace.h"
#include "xfs_icache.h"


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

STATIC int
xfs_iomap_eof_align_last_fsb(
	xfs_mount_t	*mp,
	xfs_inode_t	*ip,
	xfs_extlen_t	extsize,
	xfs_fileoff_t	*last_fsb)
{
	xfs_fileoff_t	new_last_fsb = 0;
	xfs_extlen_t	align = 0;
	int		eof, error;

	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))
			new_last_fsb = roundup_64(*last_fsb, align);
	}

	/*
	 * 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 (new_last_fsb)
			align = roundup_64(new_last_fsb, extsize);
		else
			align = extsize;
		new_last_fsb = roundup_64(*last_fsb, align);
	}

	if (new_last_fsb) {
		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\n",
		(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		bmapi_flag;
	int		quota_flag;
	int		rt;
	xfs_trans_t	*tp;
	xfs_bmap_free_t free_list;
	uint		qblocks, resblks, resrtextents;
	int		committed;
	int		error;

	error = xfs_qm_dqattach(ip, 0);
	if (error)
		return XFS_ERROR(error);

	rt = XFS_IS_REALTIME_INODE(ip);
	extsz = xfs_get_extsz_hint(ip);

	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)) {
		error = xfs_iomap_eof_align_last_fsb(mp, ip, extsz, &last_fsb);
		if (error)
			return XFS_ERROR(error);
	} 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;
	}

	/*
	 * Allocate and setup the transaction
	 */
	tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
	error = xfs_trans_reserve(tp, resblks,
			XFS_WRITE_LOG_RES(mp), resrtextents,
			XFS_TRANS_PERM_LOG_RES,
			XFS_WRITE_LOG_COUNT);
	/*
	 * Check for running out of space, note: need lock to return
	 */
	if (error) {
		xfs_trans_cancel(tp, 0);
		return XFS_ERROR(error);
	}

	xfs_ilock(ip, XFS_ILOCK_EXCL);

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

	xfs_trans_ijoin(tp, ip, 0);

	bmapi_flag = 0;
	if (offset < XFS_ISIZE(ip) || extsz)
		bmapi_flag |= XFS_BMAPI_PREALLOC;

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

	/*
	 * Complete the transaction
	 */
	error = xfs_bmap_finish(&tp, &free_list, &committed);
	if (error)
		goto out_bmap_cancel;
	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
	if (error)
		goto out_unlock;

	/*
	 * Copy any maps to caller's array and return any error.
	 */
	if (nimaps == 0) {
		error = XFS_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, XFS_ILOCK_EXCL);
	return error;

out_bmap_cancel:
	xfs_bmap_cancel(&free_list);
	xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
out_trans_cancel:
	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
	goto out_unlock;
}

/*
 * If the caller is doing a write at the end of the file, then extend the
 * allocation out to the file system's write iosize.  We clean up any extra
 * space left over when the file is closed in xfs_inactive().
 *
 * If we find we already have delalloc preallocation beyond EOF, don't do more
 * preallocation as it it not needed.
 */
STATIC int
xfs_iomap_eof_want_preallocate(
	xfs_mount_t	*mp,
	xfs_inode_t	*ip,
	xfs_off_t	offset,
	size_t		count,
	xfs_bmbt_irec_t *imap,
	int		nimaps,
	int		*prealloc)
{
	xfs_fileoff_t   start_fsb;
	xfs_filblks_t   count_fsb;
	xfs_fsblock_t	firstblock;
	int		n, error, imaps;
	int		found_delalloc = 0;

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

	/*
	 * If there are any real blocks past eof, then don't
	 * do any speculative allocation.
	 */
	start_fsb = XFS_B_TO_FSBT(mp, ((xfs_ufsize_t)(offset + count - 1)));
	count_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
	while (count_fsb > 0) {
		imaps = nimaps;
		firstblock = NULLFSBLOCK;
		error = xfs_bmapi_read(ip, start_fsb, count_fsb, imap, &imaps,
				       0);
		if (error)
			return error;
		for (n = 0; n < imaps; n++) {
			if ((imap[n].br_startblock != HOLESTARTBLOCK) &&
			    (imap[n].br_startblock != DELAYSTARTBLOCK))
				return 0;
			start_fsb += imap[n].br_blockcount;
			count_fsb -= imap[n].br_blockcount;

			if (imap[n].br_startblock == DELAYSTARTBLOCK)
				found_delalloc = 1;
		}
	}
	if (!found_delalloc)
		*prealloc = 1;
	return 0;
}

/*
 * 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 preceeding 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.
 */
STATIC xfs_fsblock_t
xfs_iomap_eof_prealloc_initial_size(
	struct xfs_mount	*mp,
	struct xfs_inode	*ip,
	xfs_off_t		offset,
	xfs_bmbt_irec_t		*imap,
	int			nimaps)
{
	xfs_fileoff_t   start_fsb;
	int		imaps = 1;
	int		error;

	ASSERT(nimaps >= imaps);

	/* if we are using a specific prealloc size, return now */
	if (mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)
		return 0;

	/*
	 * As we write multiple pages, the offset will always align to the
	 * start of a page and hence point to a hole at EOF. i.e. if the size is
	 * 4096 bytes, we only have one block at FSB 0, but XFS_B_TO_FSB(4096)
	 * will return FSB 1. Hence if there are blocks in the file, we want to
	 * point to the block prior to the EOF block and not the hole that maps
	 * directly at @offset.
	 */
	start_fsb = XFS_B_TO_FSB(mp, offset);
	if (start_fsb)
		start_fsb--;
	error = xfs_bmapi_read(ip, start_fsb, 1, imap, &imaps, XFS_BMAPI_ENTIRE);
	if (error)
		return 0;

	ASSERT(imaps == 1);
	if (imap[0].br_startblock == HOLESTARTBLOCK)
		return 0;
	if (imap[0].br_blockcount <= (MAXEXTLEN >> 1))
		return imap[0].br_blockcount;
	return XFS_B_TO_FSB(mp, offset);
}

/*
 * 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.
 */
STATIC xfs_fsblock_t
xfs_iomap_prealloc_size(
	struct xfs_mount	*mp,
	struct xfs_inode	*ip,
	xfs_off_t		offset,
	struct xfs_bmbt_irec	*imap,
	int			nimaps)
{
	xfs_fsblock_t		alloc_blocks = 0;

	alloc_blocks = xfs_iomap_eof_prealloc_initial_size(mp, ip, offset,
							   imap, nimaps);
	if (alloc_blocks > 0) {
		int shift = 0;
		int64_t freesp;

		alloc_blocks = XFS_FILEOFF_MIN(MAXEXTLEN,
					rounddown_pow_of_two(alloc_blocks));

		xfs_icsb_sync_counters(mp, XFS_ICSB_LAZY_COUNT);
		freesp = mp->m_sb.sb_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++;
		}
		if (shift)
			alloc_blocks >>= shift;

		/*
		 * 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;
	}

	if (alloc_blocks < mp->m_writeio_blocks)
		alloc_blocks = mp->m_writeio_blocks;

	return alloc_blocks;
}

int
xfs_iomap_write_delay(
	xfs_inode_t	*ip,
	xfs_off_t	offset,
	size_t		count,
	xfs_bmbt_irec_t *ret_imap)
{
	xfs_mount_t	*mp = ip->i_mount;
	xfs_fileoff_t	offset_fsb;
	xfs_fileoff_t	last_fsb;
	xfs_off_t	aligned_offset;
	xfs_fileoff_t	ioalign;
	xfs_extlen_t	extsz;
	int		nimaps;
	xfs_bmbt_irec_t imap[XFS_WRITE_IMAPS];
	int		prealloc;
	int		error;

	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));

	/*
	 * Make sure that the dquots are there. This doesn't hold
	 * the ilock across a disk read.
	 */
	error = xfs_qm_dqattach_locked(ip, 0);
	if (error)
		return XFS_ERROR(error);

	extsz = xfs_get_extsz_hint(ip);
	offset_fsb = XFS_B_TO_FSBT(mp, offset);

	error = xfs_iomap_eof_want_preallocate(mp, ip, offset, count,
				imap, XFS_WRITE_IMAPS, &prealloc);
	if (error)
		return error;

retry:
	if (prealloc) {
		xfs_fsblock_t	alloc_blocks;

		alloc_blocks = xfs_iomap_prealloc_size(mp, ip, offset, imap,
						       XFS_WRITE_IMAPS);

		aligned_offset = XFS_WRITEIO_ALIGN(mp, (offset + count - 1));
		ioalign = XFS_B_TO_FSBT(mp, aligned_offset);
		last_fsb = ioalign + alloc_blocks;
	} else {
		last_fsb = XFS_B_TO_FSB(mp, ((xfs_ufsize_t)(offset + count)));
	}

	if (prealloc || extsz) {
		error = xfs_iomap_eof_align_last_fsb(mp, ip, extsz, &last_fsb);
		if (error)
			return error;
	}

	/*
	 * Make sure preallocation does not create extents beyond the range we
	 * actually support in this filesystem.
	 */
	if (last_fsb > XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes))
		last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);

	ASSERT(last_fsb > offset_fsb);

	nimaps = XFS_WRITE_IMAPS;
	error = xfs_bmapi_delay(ip, offset_fsb, last_fsb - offset_fsb,
				imap, &nimaps, XFS_BMAPI_ENTIRE);
	switch (error) {
	case 0:
	case ENOSPC:
	case EDQUOT:
		break;
	default:
		return XFS_ERROR(error);
	}

	/*
	 * If bmapi returned us nothing, we got either ENOSPC or EDQUOT. Retry
	 * without EOF preallocation.
	 */
	if (nimaps == 0) {
		trace_xfs_delalloc_enospc(ip, offset, count);
		if (prealloc) {
			prealloc = 0;
			error = 0;
			goto retry;
		}
		return XFS_ERROR(error ? error : ENOSPC);
	}

	if (!(imap[0].br_startblock || XFS_IS_REALTIME_INODE(ip)))
		return xfs_alert_fsblock_zero(ip, &imap[0]);

	/*
	 * Tag the inode as speculatively preallocated so we can reclaim this
	 * space on demand, if necessary.
	 */
	if (prealloc)
		xfs_inode_set_eofblocks_tag(ip);

	*ret_imap = imap[0];
	return 0;
}

/*
 * 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,
	xfs_off_t	offset,
	size_t		count,
	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;
	xfs_bmap_free_t	free_list;
	xfs_filblks_t	count_fsb;
	xfs_trans_t	*tp;
	int		nimaps, committed;
	int		error = 0;
	int		nres;

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

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

	XFS_STATS_ADD(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) {
			tp = xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE);
			tp->t_flags |= XFS_TRANS_RESERVE;
			nres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
			error = xfs_trans_reserve(tp, nres,
					XFS_WRITE_LOG_RES(mp),
					0, XFS_TRANS_PERM_LOG_RES,
					XFS_WRITE_LOG_COUNT);
			if (error) {
				xfs_trans_cancel(tp, 0);
				return XFS_ERROR(error);
			}
			xfs_ilock(ip, XFS_ILOCK_EXCL);
			xfs_trans_ijoin(tp, ip, 0);

			xfs_bmap_init(&free_list, &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(NULL, 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,
						XFS_BMAPI_STACK_SWITCH,
						&first_block, 1,
						imap, &nimaps, &free_list);
			if (error)
				goto trans_cancel;

			error = xfs_bmap_finish(&tp, &free_list, &committed);
			if (error)
				goto trans_cancel;

			error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
			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(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_bmap_cancel(&free_list);
	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
error0:
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	return XFS_ERROR(error);
}

int
xfs_iomap_write_unwritten(
	xfs_inode_t	*ip,
	xfs_off_t	offset,
	size_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;
	xfs_bmap_free_t free_list;
	xfs_fsize_t	i_size;
	uint		resblks;
	int		committed;
	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 open code the transaction allocation here
		 * to pass KM_NOFS--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.
		 */
		sb_start_intwrite(mp->m_super);
		tp = _xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE, KM_NOFS);
		tp->t_flags |= XFS_TRANS_RESERVE | XFS_TRANS_FREEZE_PROT;
		error = xfs_trans_reserve(tp, resblks,
				XFS_WRITE_LOG_RES(mp), 0,
				XFS_TRANS_PERM_LOG_RES,
				XFS_WRITE_LOG_COUNT);
		if (error) {
			xfs_trans_cancel(tp, 0);
			return XFS_ERROR(error);
		}

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

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

		error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
		xfs_iunlock(ip, XFS_ILOCK_EXCL);
		if (error)
			return XFS_ERROR(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_bmap_cancel(&free_list);
	xfs_trans_cancel(tp, (XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT));
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	return XFS_ERROR(error);
}