aboutsummaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_iomap.c
blob: 45a77a3a6c07ed60b2a4fe041c6496c5ded3e1a5 (plain) (blame)
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
/*
 * Copyright (c) 2000-2005 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_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir.h"
#include "xfs_dir2.h"
#include "xfs_alloc.h"
#include "xfs_dmapi.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_dir_sf.h"
#include "xfs_dir2_sf.h"
#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_ialloc.h"
#include "xfs_btree.h"
#include "xfs_bmap.h"
#include "xfs_bit.h"
#include "xfs_rtalloc.h"
#include "xfs_error.h"
#include "xfs_itable.h"
#include "xfs_rw.h"
#include "xfs_acl.h"
#include "xfs_cap.h"
#include "xfs_mac.h"
#include "xfs_attr.h"
#include "xfs_buf_item.h"
#include "xfs_trans_space.h"
#include "xfs_utils.h"
#include "xfs_iomap.h"

#if defined(XFS_RW_TRACE)
void
xfs_iomap_enter_trace(
	int		tag,
	xfs_iocore_t	*io,
	xfs_off_t	offset,
	ssize_t		count)
{
	xfs_inode_t	*ip = XFS_IO_INODE(io);

	if (!ip->i_rwtrace)
		return;

	ktrace_enter(ip->i_rwtrace,
		(void *)((unsigned long)tag),
		(void *)ip,
		(void *)((unsigned long)((ip->i_d.di_size >> 32) & 0xffffffff)),
		(void *)((unsigned long)(ip->i_d.di_size & 0xffffffff)),
		(void *)((unsigned long)((offset >> 32) & 0xffffffff)),
		(void *)((unsigned long)(offset & 0xffffffff)),
		(void *)((unsigned long)count),
		(void *)((unsigned long)((io->io_new_size >> 32) & 0xffffffff)),
		(void *)((unsigned long)(io->io_new_size & 0xffffffff)),
		(void *)NULL,
		(void *)NULL,
		(void *)NULL,
		(void *)NULL,
		(void *)NULL,
		(void *)NULL,
		(void *)NULL);
}

void
xfs_iomap_map_trace(
	int		tag,
	xfs_iocore_t	*io,
	xfs_off_t	offset,
	ssize_t		count,
	xfs_iomap_t	*iomapp,
	xfs_bmbt_irec_t	*imapp,
	int		flags)
{
	xfs_inode_t	*ip = XFS_IO_INODE(io);

	if (!ip->i_rwtrace)
		return;

	ktrace_enter(ip->i_rwtrace,
		(void *)((unsigned long)tag),
		(void *)ip,
		(void *)((unsigned long)((ip->i_d.di_size >> 32) & 0xffffffff)),
		(void *)((unsigned long)(ip->i_d.di_size & 0xffffffff)),
		(void *)((unsigned long)((offset >> 32) & 0xffffffff)),
		(void *)((unsigned long)(offset & 0xffffffff)),
		(void *)((unsigned long)count),
		(void *)((unsigned long)flags),
		(void *)((unsigned long)((iomapp->iomap_offset >> 32) & 0xffffffff)),
		(void *)((unsigned long)(iomapp->iomap_offset & 0xffffffff)),
		(void *)((unsigned long)(iomapp->iomap_delta)),
		(void *)((unsigned long)(iomapp->iomap_bsize)),
		(void *)((unsigned long)(iomapp->iomap_bn)),
		(void *)(__psint_t)(imapp->br_startoff),
		(void *)((unsigned long)(imapp->br_blockcount)),
		(void *)(__psint_t)(imapp->br_startblock));
}
#else
#define xfs_iomap_enter_trace(tag, io, offset, count)
#define xfs_iomap_map_trace(tag, io, offset, count, iomapp, imapp, flags)
#endif

#define XFS_WRITEIO_ALIGN(mp,off)	(((off) >> mp->m_writeio_log) \
						<< mp->m_writeio_log)
#define XFS_STRAT_WRITE_IMAPS	2
#define XFS_WRITE_IMAPS		XFS_BMAP_MAX_NMAP

STATIC int
xfs_imap_to_bmap(
	xfs_iocore_t	*io,
	xfs_off_t	offset,
	xfs_bmbt_irec_t *imap,
	xfs_iomap_t	*iomapp,
	int		imaps,			/* Number of imap entries */
	int		iomaps,			/* Number of iomap entries */
	int		flags)
{
	xfs_mount_t	*mp;
	xfs_fsize_t	nisize;
	int		pbm;
	xfs_fsblock_t	start_block;

	mp = io->io_mount;
	nisize = XFS_SIZE(mp, io);
	if (io->io_new_size > nisize)
		nisize = io->io_new_size;

	for (pbm = 0; imaps && pbm < iomaps; imaps--, iomapp++, imap++, pbm++) {
		iomapp->iomap_offset = XFS_FSB_TO_B(mp, imap->br_startoff);
		iomapp->iomap_delta = offset - iomapp->iomap_offset;
		iomapp->iomap_bsize = XFS_FSB_TO_B(mp, imap->br_blockcount);
		iomapp->iomap_flags = flags;

		if (io->io_flags & XFS_IOCORE_RT) {
			iomapp->iomap_flags |= IOMAP_REALTIME;
			iomapp->iomap_target = mp->m_rtdev_targp;
		} else {
			iomapp->iomap_target = mp->m_ddev_targp;
		}
		start_block = imap->br_startblock;
		if (start_block == HOLESTARTBLOCK) {
			iomapp->iomap_bn = IOMAP_DADDR_NULL;
			iomapp->iomap_flags |= IOMAP_HOLE;
		} else if (start_block == DELAYSTARTBLOCK) {
			iomapp->iomap_bn = IOMAP_DADDR_NULL;
			iomapp->iomap_flags |= IOMAP_DELAY;
		} else {
			iomapp->iomap_bn = XFS_FSB_TO_DB_IO(io, start_block);
			if (ISUNWRITTEN(imap))
				iomapp->iomap_flags |= IOMAP_UNWRITTEN;
		}

		if ((iomapp->iomap_offset + iomapp->iomap_bsize) >= nisize) {
			iomapp->iomap_flags |= IOMAP_EOF;
		}

		offset += iomapp->iomap_bsize - iomapp->iomap_delta;
	}
	return pbm;	/* Return the number filled */
}

int
xfs_iomap(
	xfs_iocore_t	*io,
	xfs_off_t	offset,
	ssize_t		count,
	int		flags,
	xfs_iomap_t	*iomapp,
	int		*niomaps)
{
	xfs_mount_t	*mp = io->io_mount;
	xfs_fileoff_t	offset_fsb, end_fsb;
	int		error = 0;
	int		lockmode = 0;
	xfs_bmbt_irec_t	imap;
	int		nimaps = 1;
	int		bmapi_flags = 0;
	int		iomap_flags = 0;

	if (XFS_FORCED_SHUTDOWN(mp))
		return XFS_ERROR(EIO);

	switch (flags &
		(BMAPI_READ | BMAPI_WRITE | BMAPI_ALLOCATE |
		 BMAPI_UNWRITTEN | BMAPI_DEVICE)) {
	case BMAPI_READ:
		xfs_iomap_enter_trace(XFS_IOMAP_READ_ENTER, io, offset, count);
		lockmode = XFS_LCK_MAP_SHARED(mp, io);
		bmapi_flags = XFS_BMAPI_ENTIRE;
		break;
	case BMAPI_WRITE:
		xfs_iomap_enter_trace(XFS_IOMAP_WRITE_ENTER, io, offset, count);
		lockmode = XFS_ILOCK_EXCL|XFS_EXTSIZE_WR;
		if (flags & BMAPI_IGNSTATE)
			bmapi_flags |= XFS_BMAPI_IGSTATE|XFS_BMAPI_ENTIRE;
		XFS_ILOCK(mp, io, lockmode);
		break;
	case BMAPI_ALLOCATE:
		xfs_iomap_enter_trace(XFS_IOMAP_ALLOC_ENTER, io, offset, count);
		lockmode = XFS_ILOCK_SHARED|XFS_EXTSIZE_RD;
		bmapi_flags = XFS_BMAPI_ENTIRE;
		/* Attempt non-blocking lock */
		if (flags & BMAPI_TRYLOCK) {
			if (!XFS_ILOCK_NOWAIT(mp, io, lockmode))
				return XFS_ERROR(EAGAIN);
		} else {
			XFS_ILOCK(mp, io, lockmode);
		}
		break;
	case BMAPI_UNWRITTEN:
		goto phase2;
	case BMAPI_DEVICE:
		lockmode = XFS_LCK_MAP_SHARED(mp, io);
		iomapp->iomap_target = io->io_flags & XFS_IOCORE_RT ?
			mp->m_rtdev_targp : mp->m_ddev_targp;
		error = 0;
		*niomaps = 1;
		goto out;
	default:
		BUG();
	}

	ASSERT(offset <= mp->m_maxioffset);
	if ((xfs_fsize_t)offset + count > mp->m_maxioffset)
		count = mp->m_maxioffset - offset;
	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
	offset_fsb = XFS_B_TO_FSBT(mp, offset);

	error = XFS_BMAPI(mp, NULL, io, offset_fsb,
			(xfs_filblks_t)(end_fsb - offset_fsb),
			bmapi_flags,  NULL, 0, &imap,
			&nimaps, NULL);

	if (error)
		goto out;

phase2:
	switch (flags & (BMAPI_WRITE|BMAPI_ALLOCATE|BMAPI_UNWRITTEN)) {
	case BMAPI_WRITE:
		/* If we found an extent, return it */
		if (nimaps &&
		    (imap.br_startblock != HOLESTARTBLOCK) && 
		    (imap.br_startblock != DELAYSTARTBLOCK)) {
			xfs_iomap_map_trace(XFS_IOMAP_WRITE_MAP, io,
					offset, count, iomapp, &imap, flags);
			break;
		}

		if (flags & (BMAPI_DIRECT|BMAPI_MMAP)) {
			error = XFS_IOMAP_WRITE_DIRECT(mp, io, offset,
					count, flags, &imap, &nimaps, nimaps);
		} else {
			error = XFS_IOMAP_WRITE_DELAY(mp, io, offset, count,
					flags, &imap, &nimaps);
		}
		if (!error) {
			xfs_iomap_map_trace(XFS_IOMAP_ALLOC_MAP, io,
					offset, count, iomapp, &imap, flags);
		}
		iomap_flags = IOMAP_NEW;
		break;
	case BMAPI_ALLOCATE:
		/* If we found an extent, return it */
		XFS_IUNLOCK(mp, io, lockmode);
		lockmode = 0;

		if (nimaps && !ISNULLSTARTBLOCK(imap.br_startblock)) {
			xfs_iomap_map_trace(XFS_IOMAP_WRITE_MAP, io,
					offset, count, iomapp, &imap, flags);
			break;
		}

		error = XFS_IOMAP_WRITE_ALLOCATE(mp, io, offset, count,
						 &imap, &nimaps);
		break;
	case BMAPI_UNWRITTEN:
		lockmode = 0;
		error = XFS_IOMAP_WRITE_UNWRITTEN(mp, io, offset, count);
		nimaps = 0;
		break;
	}

	if (nimaps) {
		*niomaps = xfs_imap_to_bmap(io, offset, &imap,
					    iomapp, nimaps, *niomaps, iomap_flags);
	} else if (niomaps) {
		*niomaps = 0;
	}

out:
	if (lockmode)
		XFS_IUNLOCK(mp, io, lockmode);
	return XFS_ERROR(error);
}

STATIC int
xfs_flush_space(
	xfs_inode_t	*ip,
	int		*fsynced,
	int		*ioflags)
{
	switch (*fsynced) {
	case 0:
		if (ip->i_delayed_blks) {
			xfs_iunlock(ip, XFS_ILOCK_EXCL);
			xfs_flush_inode(ip);
			xfs_ilock(ip, XFS_ILOCK_EXCL);
			*fsynced = 1;
		} else {
			*ioflags |= BMAPI_SYNC;
			*fsynced = 2;
		}
		return 0;
	case 1:
		*fsynced = 2;
		*ioflags |= BMAPI_SYNC;
		return 0;
	case 2:
		xfs_iunlock(ip, XFS_ILOCK_EXCL);
		xfs_flush_device(ip);
		xfs_ilock(ip, XFS_ILOCK_EXCL);
		*fsynced = 3;
		return 0;
	}
	return 1;
}

int
xfs_iomap_write_direct(
	xfs_inode_t	*ip,
	xfs_off_t	offset,
	size_t		count,
	int		flags,
	xfs_bmbt_irec_t *ret_imap,
	int		*nmaps,
	int		found)
{
	xfs_mount_t	*mp = ip->i_mount;
	xfs_iocore_t	*io = &ip->i_iocore;
	xfs_fileoff_t	offset_fsb;
	xfs_fileoff_t	last_fsb;
	xfs_filblks_t	count_fsb;
	xfs_fsblock_t	firstfsb;
	int		nimaps;
	int		error;
	int		bmapi_flag;
	int		quota_flag;
	int		rt;
	xfs_trans_t	*tp;
	xfs_bmbt_irec_t imap;
	xfs_bmap_free_t free_list;
	xfs_filblks_t	qblocks, resblks;
	int		committed;
	int		resrtextents;

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

	offset_fsb = XFS_B_TO_FSBT(mp, offset);
	last_fsb = XFS_B_TO_FSB(mp, ((xfs_ufsize_t)(offset + count)));
	count_fsb = last_fsb - offset_fsb;
	if (found && (ret_imap->br_startblock == HOLESTARTBLOCK)) {
		xfs_fileoff_t	map_last_fsb;

		map_last_fsb = ret_imap->br_blockcount + ret_imap->br_startoff;
		if (map_last_fsb < last_fsb) {
			last_fsb = map_last_fsb;
			count_fsb = last_fsb - offset_fsb;
		}
		ASSERT(count_fsb > 0);
	}

	/*
	 * Determine if reserving space on the data or realtime partition.
	 */
	if ((rt = XFS_IS_REALTIME_INODE(ip))) {
		xfs_extlen_t	extsz;

		if (!(extsz = ip->i_d.di_extsize))
			extsz = mp->m_sb.sb_rextsize;
		resrtextents = qblocks = (count_fsb + extsz - 1);
		do_div(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, count_fsb);
		quota_flag = XFS_QMOPT_RES_REGBLKS;
	}

	/*
	 * Allocate and setup the transaction
	 */
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	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);
	xfs_ilock(ip, XFS_ILOCK_EXCL);
	if (error)
		goto error_out;

	if (XFS_TRANS_RESERVE_QUOTA_NBLKS(mp, tp, ip, qblocks, 0, quota_flag)) {
		error = (EDQUOT);
		goto error1;
	}

	bmapi_flag = XFS_BMAPI_WRITE;
	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
	xfs_trans_ihold(tp, ip);

	if (!(flags & BMAPI_MMAP) && (offset < ip->i_d.di_size || rt))
		bmapi_flag |= XFS_BMAPI_PREALLOC;

	/*
	 * Issue the bmapi() call to allocate the blocks
	 */
	XFS_BMAP_INIT(&free_list, &firstfsb);
	nimaps = 1;
	error = xfs_bmapi(tp, ip, offset_fsb, count_fsb,
		bmapi_flag, &firstfsb, 0, &imap, &nimaps, &free_list);
	if (error)
		goto error0;

	/*
	 * Complete the transaction
	 */
	error = xfs_bmap_finish(&tp, &free_list, firstfsb, &committed);
	if (error)
		goto error0;
	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
	if (error)
		goto error_out;

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

	*ret_imap = imap;
	*nmaps = 1;
	if ( !(io->io_flags & XFS_IOCORE_RT)  && !ret_imap->br_startblock) {
                cmn_err(CE_PANIC,"Access to block zero:  fs <%s> inode: %lld "
                        "start_block : %llx start_off : %llx blkcnt : %llx "
                        "extent-state : %x \n",
                        (ip->i_mount)->m_fsname,
                        (long long)ip->i_ino,
                        ret_imap->br_startblock, ret_imap->br_startoff,
                        ret_imap->br_blockcount,ret_imap->br_state);
        }
	return 0;

error0:	/* Cancel bmap, unlock inode, unreserve quota blocks, cancel trans */
	xfs_bmap_cancel(&free_list);
	XFS_TRANS_UNRESERVE_QUOTA_NBLKS(mp, tp, ip, qblocks, 0, quota_flag);

error1:	/* Just cancel transaction */
	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
	*nmaps = 0;	/* nothing set-up here */

error_out:
	return XFS_ERROR(error);
}

int
xfs_iomap_write_delay(
	xfs_inode_t	*ip,
	xfs_off_t	offset,
	size_t		count,
	int		ioflag,
	xfs_bmbt_irec_t *ret_imap,
	int		*nmaps)
{
	xfs_mount_t	*mp = ip->i_mount;
	xfs_iocore_t	*io = &ip->i_iocore;
	xfs_fileoff_t	offset_fsb;
	xfs_fileoff_t	last_fsb;
	xfs_fsize_t	isize;
	xfs_fsblock_t	firstblock;
	int		nimaps;
	int		error;
	xfs_bmbt_irec_t imap[XFS_WRITE_IMAPS];
	int		aeof;
	int		fsynced = 0;

	ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE) != 0);

	/*
	 * Make sure that the dquots are there. This doesn't hold
	 * the ilock across a disk read.
	 */

	error = XFS_QM_DQATTACH(mp, ip, XFS_QMOPT_ILOCKED);
	if (error)
		return XFS_ERROR(error);

retry:
	isize = ip->i_d.di_size;
	if (io->io_new_size > isize) {
		isize = io->io_new_size;
	}

	aeof = 0;
	offset_fsb = XFS_B_TO_FSBT(mp, offset);
	last_fsb = XFS_B_TO_FSB(mp, ((xfs_ufsize_t)(offset + count)));
	/*
	 * If the caller is doing a write at the end of the file,
	 * then extend the allocation (and the buffer used for the write)
	 * out to the file system's write iosize.  We clean up any extra
	 * space left over when the file is closed in xfs_inactive().
	 *
	 * For sync writes, we are flushing delayed allocate space to
	 * try to make additional space available for allocation near
	 * the filesystem full boundary - preallocation hurts in that
	 * situation, of course.
	 */
	if (!(ioflag & BMAPI_SYNC) && ((offset + count) > ip->i_d.di_size)) {
		xfs_off_t	aligned_offset;
		xfs_filblks_t   count_fsb;
		unsigned int	iosize;
		xfs_fileoff_t	ioalign;
		int		n;
		xfs_fileoff_t   start_fsb;

		/*
		 * 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, (xfs_ufsize_t)XFS_MAXIOFFSET(mp));
		while (count_fsb > 0) {
			nimaps = XFS_WRITE_IMAPS;
			error = XFS_BMAPI(mp, NULL, io, start_fsb, count_fsb,
					0, &firstblock, 0, imap, &nimaps, NULL);
			if (error) {
				return error;
			}
			for (n = 0; n < nimaps; n++) {
				if ( !(io->io_flags & XFS_IOCORE_RT)  && 
					!imap[n].br_startblock) {
					cmn_err(CE_PANIC,"Access to block "
						"zero:  fs <%s> inode: %lld "
						"start_block : %llx start_off "
						": %llx blkcnt : %llx "
						"extent-state : %x \n",
						(ip->i_mount)->m_fsname,
						(long long)ip->i_ino,
						imap[n].br_startblock,
						imap[n].br_startoff,
						imap[n].br_blockcount,
						imap[n].br_state);
        			}
				if ((imap[n].br_startblock != HOLESTARTBLOCK) &&
				    (imap[n].br_startblock != DELAYSTARTBLOCK)) {
					goto write_map;
				}
				start_fsb += imap[n].br_blockcount;
				count_fsb -= imap[n].br_blockcount;
			}
		}
		iosize = mp->m_writeio_blocks;
		aligned_offset = XFS_WRITEIO_ALIGN(mp, (offset + count - 1));
		ioalign = XFS_B_TO_FSBT(mp, aligned_offset);
		last_fsb = ioalign + iosize;
		aeof = 1;
	}
write_map:
	nimaps = XFS_WRITE_IMAPS;
	firstblock = NULLFSBLOCK;

	/*
	 * If mounted with the "-o swalloc" option, roundup the allocation
	 * request to a stripe width boundary if the file size is >=
	 * stripe width and we are allocating past the allocation eof.
	 */
	if (!(io->io_flags & XFS_IOCORE_RT) && mp->m_swidth 
	    && (mp->m_flags & XFS_MOUNT_SWALLOC)
	    && (isize >= XFS_FSB_TO_B(mp, mp->m_swidth)) && aeof) {
		int eof;
		xfs_fileoff_t new_last_fsb;

		new_last_fsb = roundup_64(last_fsb, mp->m_swidth);
		error = xfs_bmap_eof(ip, new_last_fsb, XFS_DATA_FORK, &eof);
		if (error) {
			return error;
		}
		if (eof) {
			last_fsb = new_last_fsb;
		}
	/*
	 * Roundup 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.
	 */
	} else if (!(io->io_flags & XFS_IOCORE_RT) && mp->m_dalign &&
		   (isize >= XFS_FSB_TO_B(mp, mp->m_dalign)) && aeof) {
		int eof;
		xfs_fileoff_t new_last_fsb;
		new_last_fsb = roundup_64(last_fsb, mp->m_dalign);
		error = xfs_bmap_eof(ip, new_last_fsb, XFS_DATA_FORK, &eof);
		if (error) {
			return error;
		}
		if (eof) {
			last_fsb = new_last_fsb;
		}
	/*
	 * Round up the allocation request to a real-time extent boundary
	 * if the file is on the real-time subvolume.
	 */
	} else if (io->io_flags & XFS_IOCORE_RT && aeof) {
		int eof;
		xfs_fileoff_t new_last_fsb;

		new_last_fsb = roundup_64(last_fsb, mp->m_sb.sb_rextsize);
		error = XFS_BMAP_EOF(mp, io, new_last_fsb, XFS_DATA_FORK, &eof);
		if (error) {
			return error;
		}
		if (eof)
			last_fsb = new_last_fsb;
	}
	error = xfs_bmapi(NULL, ip, offset_fsb,
			  (xfs_filblks_t)(last_fsb - offset_fsb),
			  XFS_BMAPI_DELAY | XFS_BMAPI_WRITE |
			  XFS_BMAPI_ENTIRE, &firstblock, 1, imap,
			  &nimaps, NULL);
	/*
	 * This can be EDQUOT, if nimaps == 0
	 */
	if (error && (error != ENOSPC)) {
		return XFS_ERROR(error);
	}
	/*
	 * If bmapi returned us nothing, and if we didn't get back EDQUOT,
	 * then we must have run out of space.
	 */
	if (nimaps == 0) {
		xfs_iomap_enter_trace(XFS_IOMAP_WRITE_NOSPACE,
					io, offset, count);
		if (xfs_flush_space(ip, &fsynced, &ioflag))
			return XFS_ERROR(ENOSPC);

		error = 0;
		goto retry;
	}

	*ret_imap = imap[0];
	*nmaps = 1;
	if ( !(io->io_flags & XFS_IOCORE_RT)  && !ret_imap->br_startblock) {
		cmn_err(CE_PANIC,"Access to block zero:  fs <%s> inode: %lld "
                        "start_block : %llx start_off : %llx blkcnt : %llx "
                        "extent-state : %x \n",
                        (ip->i_mount)->m_fsname,
                        (long long)ip->i_ino,
                        ret_imap->br_startblock, ret_imap->br_startoff,
                        ret_imap->br_blockcount,ret_imap->br_state);
	}
	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.
 */
int
xfs_iomap_write_allocate(
	xfs_inode_t	*ip,
	xfs_off_t	offset,
	size_t		count,
	xfs_bmbt_irec_t *map,
	int		*retmap)
{
	xfs_mount_t	*mp = ip->i_mount;
	xfs_iocore_t    *io = &ip->i_iocore;
	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_bmbt_irec_t	imap[XFS_STRAT_WRITE_IMAPS];
	xfs_trans_t	*tp;
	int		i, nimaps, committed;
	int		error = 0;
	int		nres;

	*retmap = 0;

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

	offset_fsb = XFS_B_TO_FSBT(mp, offset);
	count_fsb = map->br_blockcount;
	map_start_fsb = map->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);
			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 == ENOSPC) {
				error = xfs_trans_reserve(tp, 0,
						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, XFS_ILOCK_EXCL);
			xfs_trans_ihold(tp, ip);

			XFS_BMAP_INIT(&free_list, &first_block);

			nimaps = XFS_STRAT_WRITE_IMAPS;
			/*
			 * Ensure we don't go beyond eof - it is possible
			 * the extents changed since we did the read call,
			 * we dropped the ilock in the interim.
			 */

			end_fsb = XFS_B_TO_FSB(mp, ip->i_d.di_size);
			xfs_bmap_last_offset(NULL, ip, &last_block,
				XFS_DATA_FORK);
			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;
				}
			}

			/* Go get the actual blocks */
			error = xfs_bmapi(tp, ip, map_start_fsb, count_fsb,
					XFS_BMAPI_WRITE, &first_block, 1,
					imap, &nimaps, &free_list);
			if (error)
				goto trans_cancel;

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

			error = xfs_trans_commit(tp,
					XFS_TRANS_RELEASE_LOG_RES, NULL);
			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
		 */

		for (i = 0; i < nimaps; i++) {
			if ( !(io->io_flags & XFS_IOCORE_RT)  && 
				!imap[i].br_startblock) {
				cmn_err(CE_PANIC,"Access to block zero:  "
					"fs <%s> inode: %lld "
					"start_block : %llx start_off : %llx " 
					"blkcnt : %llx extent-state : %x \n",
					(ip->i_mount)->m_fsname,
					(long long)ip->i_ino,
					imap[i].br_startblock,
					imap[i].br_startoff,
				        imap[i].br_blockcount,imap[i].br_state);
                        }
			if ((offset_fsb >= imap[i].br_startoff) &&
			    (offset_fsb < (imap[i].br_startoff +
					   imap[i].br_blockcount))) {
				*map = imap[i];
				*retmap = 1;
				XFS_STATS_INC(xs_xstrat_quick);
				return 0;
			}
			count_fsb -= imap[i].br_blockcount;
		}

		/* So far we have not mapped the requested part of the
		 * file, just surrounding data, try again.
		 */
		nimaps--;
		map_start_fsb = imap[nimaps].br_startoff +
				imap[nimaps].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_iocore_t    *io = &ip->i_iocore;
	xfs_trans_t	*tp;
	xfs_fileoff_t	offset_fsb;
	xfs_filblks_t	count_fsb;
	xfs_filblks_t	numblks_fsb;
	xfs_bmbt_irec_t	imap;
	int		committed;
	int		error;
	int		nres;
	int		nimaps;
	xfs_fsblock_t	firstfsb;
	xfs_bmap_free_t	free_list;

	xfs_iomap_enter_trace(XFS_IOMAP_UNWRITTEN,
				&ip->i_iocore, 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);

	do {
		nres = XFS_DIOSTRAT_SPACE_RES(mp, 0);

		/*
		 * 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.
		 */

		tp = xfs_trans_alloc(mp, XFS_TRANS_STRAT_WRITE);
		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);
			goto error0;
		}

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

		/*
		 * Modify the unwritten extent state of the buffer.
		 */
		XFS_BMAP_INIT(&free_list, &firstfsb);
		nimaps = 1;
		error = xfs_bmapi(tp, ip, offset_fsb, count_fsb,
				  XFS_BMAPI_WRITE, &firstfsb,
				  1, &imap, &nimaps, &free_list);
		if (error)
			goto error_on_bmapi_transaction;

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

		error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES, NULL);
		xfs_iunlock(ip, XFS_ILOCK_EXCL);
		if (error)
			goto error0;
		
		if ( !(io->io_flags & XFS_IOCORE_RT)  && !imap.br_startblock) {
			cmn_err(CE_PANIC,"Access to block zero:  fs <%s> "
				"inode: %lld start_block : %llx start_off : "
				"%llx blkcnt : %llx extent-state : %x \n",
				(ip->i_mount)->m_fsname,
				(long long)ip->i_ino,
				imap.br_startblock,imap.br_startoff,
				imap.br_blockcount,imap.br_state);
        	}

		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);
error0:
	return XFS_ERROR(error);
}