summaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_reflink.c
blob: a7757a128a78fcf8d8f3bd1f190c3524c733cf8f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
// SPDX-License-Identifier: GPL-2.0+
/*
 * Copyright (C) 2016 Oracle.  All Rights Reserved.
 * Author: Darrick J. Wong <darrick.wong@oracle.com>
 */
#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_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_error.h"
#include "xfs_dir2.h"
#include "xfs_dir2_priv.h"
#include "xfs_ioctl.h"
#include "xfs_trace.h"
#include "xfs_log.h"
#include "xfs_icache.h"
#include "xfs_pnfs.h"
#include "xfs_btree.h"
#include "xfs_refcount_btree.h"
#include "xfs_refcount.h"
#include "xfs_bmap_btree.h"
#include "xfs_trans_space.h"
#include "xfs_bit.h"
#include "xfs_alloc.h"
#include "xfs_quota_defs.h"
#include "xfs_quota.h"
#include "xfs_reflink.h"
#include "xfs_iomap.h"
#include "xfs_rmap_btree.h"
#include "xfs_sb.h"
#include "xfs_ag_resv.h"

/*
 * Copy on Write of Shared Blocks
 *
 * XFS must preserve "the usual" file semantics even when two files share
 * the same physical blocks.  This means that a write to one file must not
 * alter the blocks in a different file; the way that we'll do that is
 * through the use of a copy-on-write mechanism.  At a high level, that
 * means that when we want to write to a shared block, we allocate a new
 * block, write the data to the new block, and if that succeeds we map the
 * new block into the file.
 *
 * XFS provides a "delayed allocation" mechanism that defers the allocation
 * of disk blocks to dirty-but-not-yet-mapped file blocks as long as
 * possible.  This reduces fragmentation by enabling the filesystem to ask
 * for bigger chunks less often, which is exactly what we want for CoW.
 *
 * The delalloc mechanism begins when the kernel wants to make a block
 * writable (write_begin or page_mkwrite).  If the offset is not mapped, we
 * create a delalloc mapping, which is a regular in-core extent, but without
 * a real startblock.  (For delalloc mappings, the startblock encodes both
 * a flag that this is a delalloc mapping, and a worst-case estimate of how
 * many blocks might be required to put the mapping into the BMBT.)  delalloc
 * mappings are a reservation against the free space in the filesystem;
 * adjacent mappings can also be combined into fewer larger mappings.
 *
 * As an optimization, the CoW extent size hint (cowextsz) creates
 * outsized aligned delalloc reservations in the hope of landing out of
 * order nearby CoW writes in a single extent on disk, thereby reducing
 * fragmentation and improving future performance.
 *
 * D: --RRRRRRSSSRRRRRRRR--- (data fork)
 * C: ------DDDDDDD--------- (CoW fork)
 *
 * When dirty pages are being written out (typically in writepage), the
 * delalloc reservations are converted into unwritten mappings by
 * allocating blocks and replacing the delalloc mapping with real ones.
 * A delalloc mapping can be replaced by several unwritten ones if the
 * free space is fragmented.
 *
 * D: --RRRRRRSSSRRRRRRRR---
 * C: ------UUUUUUU---------
 *
 * We want to adapt the delalloc mechanism for copy-on-write, since the
 * write paths are similar.  The first two steps (creating the reservation
 * and allocating the blocks) are exactly the same as delalloc except that
 * the mappings must be stored in a separate CoW fork because we do not want
 * to disturb the mapping in the data fork until we're sure that the write
 * succeeded.  IO completion in this case is the process of removing the old
 * mapping from the data fork and moving the new mapping from the CoW fork to
 * the data fork.  This will be discussed shortly.
 *
 * For now, unaligned directio writes will be bounced back to the page cache.
 * Block-aligned directio writes will use the same mechanism as buffered
 * writes.
 *
 * Just prior to submitting the actual disk write requests, we convert
 * the extents representing the range of the file actually being written
 * (as opposed to extra pieces created for the cowextsize hint) to real
 * extents.  This will become important in the next step:
 *
 * D: --RRRRRRSSSRRRRRRRR---
 * C: ------UUrrUUU---------
 *
 * CoW remapping must be done after the data block write completes,
 * because we don't want to destroy the old data fork map until we're sure
 * the new block has been written.  Since the new mappings are kept in a
 * separate fork, we can simply iterate these mappings to find the ones
 * that cover the file blocks that we just CoW'd.  For each extent, simply
 * unmap the corresponding range in the data fork, map the new range into
 * the data fork, and remove the extent from the CoW fork.  Because of
 * the presence of the cowextsize hint, however, we must be careful
 * only to remap the blocks that we've actually written out --  we must
 * never remap delalloc reservations nor CoW staging blocks that have
 * yet to be written.  This corresponds exactly to the real extents in
 * the CoW fork:
 *
 * D: --RRRRRRrrSRRRRRRRR---
 * C: ------UU--UUU---------
 *
 * Since the remapping operation can be applied to an arbitrary file
 * range, we record the need for the remap step as a flag in the ioend
 * instead of declaring a new IO type.  This is required for direct io
 * because we only have ioend for the whole dio, and we have to be able to
 * remember the presence of unwritten blocks and CoW blocks with a single
 * ioend structure.  Better yet, the more ground we can cover with one
 * ioend, the better.
 */

/*
 * Given an AG extent, find the lowest-numbered run of shared blocks
 * within that range and return the range in fbno/flen.  If
 * find_end_of_shared is true, return the longest contiguous extent of
 * shared blocks.  If there are no shared extents, fbno and flen will
 * be set to NULLAGBLOCK and 0, respectively.
 */
int
xfs_reflink_find_shared(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	xfs_agnumber_t		agno,
	xfs_agblock_t		agbno,
	xfs_extlen_t		aglen,
	xfs_agblock_t		*fbno,
	xfs_extlen_t		*flen,
	bool			find_end_of_shared)
{
	struct xfs_buf		*agbp;
	struct xfs_btree_cur	*cur;
	int			error;

	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
	if (error)
		return error;
	if (!agbp)
		return -ENOMEM;

	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno);

	error = xfs_refcount_find_shared(cur, agbno, aglen, fbno, flen,
			find_end_of_shared);

	xfs_btree_del_cursor(cur, error);

	xfs_trans_brelse(tp, agbp);
	return error;
}

/*
 * Trim the mapping to the next block where there's a change in the
 * shared/unshared status.  More specifically, this means that we
 * find the lowest-numbered extent of shared blocks that coincides with
 * the given block mapping.  If the shared extent overlaps the start of
 * the mapping, trim the mapping to the end of the shared extent.  If
 * the shared region intersects the mapping, trim the mapping to the
 * start of the shared extent.  If there are no shared regions that
 * overlap, just return the original extent.
 */
int
xfs_reflink_trim_around_shared(
	struct xfs_inode	*ip,
	struct xfs_bmbt_irec	*irec,
	bool			*shared,
	bool			*trimmed)
{
	xfs_agnumber_t		agno;
	xfs_agblock_t		agbno;
	xfs_extlen_t		aglen;
	xfs_agblock_t		fbno;
	xfs_extlen_t		flen;
	int			error = 0;

	/* Holes, unwritten, and delalloc extents cannot be shared */
	if (!xfs_is_reflink_inode(ip) || !xfs_bmap_is_real_extent(irec)) {
		*shared = false;
		return 0;
	}

	trace_xfs_reflink_trim_around_shared(ip, irec);

	agno = XFS_FSB_TO_AGNO(ip->i_mount, irec->br_startblock);
	agbno = XFS_FSB_TO_AGBNO(ip->i_mount, irec->br_startblock);
	aglen = irec->br_blockcount;

	error = xfs_reflink_find_shared(ip->i_mount, NULL, agno, agbno,
			aglen, &fbno, &flen, true);
	if (error)
		return error;

	*shared = *trimmed = false;
	if (fbno == NULLAGBLOCK) {
		/* No shared blocks at all. */
		return 0;
	} else if (fbno == agbno) {
		/*
		 * The start of this extent is shared.  Truncate the
		 * mapping at the end of the shared region so that a
		 * subsequent iteration starts at the start of the
		 * unshared region.
		 */
		irec->br_blockcount = flen;
		*shared = true;
		if (flen != aglen)
			*trimmed = true;
		return 0;
	} else {
		/*
		 * There's a shared extent midway through this extent.
		 * Truncate the mapping at the start of the shared
		 * extent so that a subsequent iteration starts at the
		 * start of the shared region.
		 */
		irec->br_blockcount = fbno - agbno;
		*trimmed = true;
		return 0;
	}
}

/*
 * Trim the passed in imap to the next shared/unshared extent boundary, and
 * if imap->br_startoff points to a shared extent reserve space for it in the
 * COW fork.  In this case *shared is set to true, else to false.
 *
 * Note that imap will always contain the block numbers for the existing blocks
 * in the data fork, as the upper layers need them for read-modify-write
 * operations.
 */
int
xfs_reflink_reserve_cow(
	struct xfs_inode	*ip,
	struct xfs_bmbt_irec	*imap,
	bool			*shared)
{
	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
	struct xfs_bmbt_irec	got;
	int			error = 0;
	bool			eof = false, trimmed;
	struct xfs_iext_cursor	icur;

	/*
	 * Search the COW fork extent list first.  This serves two purposes:
	 * first this implement the speculative preallocation using cowextisze,
	 * so that we also unshared block adjacent to shared blocks instead
	 * of just the shared blocks themselves.  Second the lookup in the
	 * extent list is generally faster than going out to the shared extent
	 * tree.
	 */

	if (!xfs_iext_lookup_extent(ip, ifp, imap->br_startoff, &icur, &got))
		eof = true;
	if (!eof && got.br_startoff <= imap->br_startoff) {
		trace_xfs_reflink_cow_found(ip, imap);
		xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);

		*shared = true;
		return 0;
	}

	/* Trim the mapping to the nearest shared extent boundary. */
	error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
	if (error)
		return error;

	/* Not shared?  Just report the (potentially capped) extent. */
	if (!*shared)
		return 0;

	/*
	 * Fork all the shared blocks from our write offset until the end of
	 * the extent.
	 */
	error = xfs_qm_dqattach_locked(ip, false);
	if (error)
		return error;

	error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, imap->br_startoff,
			imap->br_blockcount, 0, &got, &icur, eof);
	if (error == -ENOSPC || error == -EDQUOT)
		trace_xfs_reflink_cow_enospc(ip, imap);
	if (error)
		return error;

	trace_xfs_reflink_cow_alloc(ip, &got);
	return 0;
}

/* Convert part of an unwritten CoW extent to a real one. */
STATIC int
xfs_reflink_convert_cow_extent(
	struct xfs_inode		*ip,
	struct xfs_bmbt_irec		*imap,
	xfs_fileoff_t			offset_fsb,
	xfs_filblks_t			count_fsb)
{
	int				nimaps = 1;

	if (imap->br_state == XFS_EXT_NORM)
		return 0;

	xfs_trim_extent(imap, offset_fsb, count_fsb);
	trace_xfs_reflink_convert_cow(ip, imap);
	if (imap->br_blockcount == 0)
		return 0;
	return xfs_bmapi_write(NULL, ip, imap->br_startoff, imap->br_blockcount,
			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT, 0, imap,
			&nimaps);
}

/* Convert all of the unwritten CoW extents in a file's range to real ones. */
int
xfs_reflink_convert_cow(
	struct xfs_inode	*ip,
	xfs_off_t		offset,
	xfs_off_t		count)
{
	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 + count);
	xfs_filblks_t		count_fsb = end_fsb - offset_fsb;
	struct xfs_bmbt_irec	imap;
	int			nimaps = 1, error = 0;

	ASSERT(count != 0);

	xfs_ilock(ip, XFS_ILOCK_EXCL);
	error = xfs_bmapi_write(NULL, ip, offset_fsb, count_fsb,
			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT |
			XFS_BMAPI_CONVERT_ONLY, 0, &imap, &nimaps);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	return error;
}

/*
 * Find the extent that maps the given range in the COW fork. Even if the extent
 * is not shared we might have a preallocation for it in the COW fork. If so we
 * use it that rather than trigger a new allocation.
 */
static int
xfs_find_trim_cow_extent(
	struct xfs_inode	*ip,
	struct xfs_bmbt_irec	*imap,
	bool			*shared,
	bool			*found)
{
	xfs_fileoff_t		offset_fsb = imap->br_startoff;
	xfs_filblks_t		count_fsb = imap->br_blockcount;
	struct xfs_iext_cursor	icur;
	struct xfs_bmbt_irec	got;
	bool			trimmed;

	*found = false;

	/*
	 * If we don't find an overlapping extent, trim the range we need to
	 * allocate to fit the hole we found.
	 */
	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got) ||
	    got.br_startoff > offset_fsb)
		return xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);

	*shared = true;
	if (isnullstartblock(got.br_startblock)) {
		xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
		return 0;
	}

	/* real extent found - no need to allocate */
	xfs_trim_extent(&got, offset_fsb, count_fsb);
	*imap = got;
	*found = true;
	return 0;
}

/* Allocate all CoW reservations covering a range of blocks in a file. */
int
xfs_reflink_allocate_cow(
	struct xfs_inode	*ip,
	struct xfs_bmbt_irec	*imap,
	bool			*shared,
	uint			*lockmode)
{
	struct xfs_mount	*mp = ip->i_mount;
	xfs_fileoff_t		offset_fsb = imap->br_startoff;
	xfs_filblks_t		count_fsb = imap->br_blockcount;
	struct xfs_trans	*tp;
	int			nimaps, error = 0;
	bool			found;
	xfs_filblks_t		resaligned;
	xfs_extlen_t		resblks = 0;

	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
	ASSERT(xfs_is_reflink_inode(ip));

	error = xfs_find_trim_cow_extent(ip, imap, shared, &found);
	if (error || !*shared)
		return error;
	if (found)
		goto convert;

	resaligned = xfs_aligned_fsb_count(imap->br_startoff,
		imap->br_blockcount, xfs_get_cowextsz_hint(ip));
	resblks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned);

	xfs_iunlock(ip, *lockmode);
	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
	*lockmode = XFS_ILOCK_EXCL;
	xfs_ilock(ip, *lockmode);

	if (error)
		return error;

	error = xfs_qm_dqattach_locked(ip, false);
	if (error)
		goto out_trans_cancel;

	/*
	 * Check for an overlapping extent again now that we dropped the ilock.
	 */
	error = xfs_find_trim_cow_extent(ip, imap, shared, &found);
	if (error || !*shared)
		goto out_trans_cancel;
	if (found) {
		xfs_trans_cancel(tp);
		goto convert;
	}

	error = xfs_trans_reserve_quota_nblks(tp, ip, resblks, 0,
			XFS_QMOPT_RES_REGBLKS);
	if (error)
		goto out_trans_cancel;

	xfs_trans_ijoin(tp, ip, 0);

	/* Allocate the entire reservation as unwritten blocks. */
	nimaps = 1;
	error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount,
			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC,
			resblks, imap, &nimaps);
	if (error)
		goto out_unreserve;

	xfs_inode_set_cowblocks_tag(ip);
	error = xfs_trans_commit(tp);
	if (error)
		return error;

	/*
	 * Allocation succeeded but the requested range was not even partially
	 * satisfied?  Bail out!
	 */
	if (nimaps == 0)
		return -ENOSPC;
convert:
	return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb);

out_unreserve:
	xfs_trans_unreserve_quota_nblks(tp, ip, (long)resblks, 0,
			XFS_QMOPT_RES_REGBLKS);
out_trans_cancel:
	xfs_trans_cancel(tp);
	return error;
}

/*
 * Cancel CoW reservations for some block range of an inode.
 *
 * If cancel_real is true this function cancels all COW fork extents for the
 * inode; if cancel_real is false, real extents are not cleared.
 *
 * Caller must have already joined the inode to the current transaction. The
 * inode will be joined to the transaction returned to the caller.
 */
int
xfs_reflink_cancel_cow_blocks(
	struct xfs_inode		*ip,
	struct xfs_trans		**tpp,
	xfs_fileoff_t			offset_fsb,
	xfs_fileoff_t			end_fsb,
	bool				cancel_real)
{
	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
	struct xfs_bmbt_irec		got, del;
	struct xfs_iext_cursor		icur;
	int				error = 0;

	if (!xfs_inode_has_cow_data(ip))
		return 0;
	if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
		return 0;

	/* Walk backwards until we're out of the I/O range... */
	while (got.br_startoff + got.br_blockcount > offset_fsb) {
		del = got;
		xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);

		/* Extent delete may have bumped ext forward */
		if (!del.br_blockcount) {
			xfs_iext_prev(ifp, &icur);
			goto next_extent;
		}

		trace_xfs_reflink_cancel_cow(ip, &del);

		if (isnullstartblock(del.br_startblock)) {
			error = xfs_bmap_del_extent_delay(ip, XFS_COW_FORK,
					&icur, &got, &del);
			if (error)
				break;
		} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
			ASSERT((*tpp)->t_firstblock == NULLFSBLOCK);

			/* Free the CoW orphan record. */
			error = xfs_refcount_free_cow_extent(*tpp,
					del.br_startblock, del.br_blockcount);
			if (error)
				break;

			xfs_bmap_add_free(*tpp, del.br_startblock,
					  del.br_blockcount, NULL);

			/* Roll the transaction */
			error = xfs_defer_finish(tpp);
			if (error)
				break;

			/* Remove the mapping from the CoW fork. */
			xfs_bmap_del_extent_cow(ip, &icur, &got, &del);

			/* Remove the quota reservation */
			error = xfs_trans_reserve_quota_nblks(NULL, ip,
					-(long)del.br_blockcount, 0,
					XFS_QMOPT_RES_REGBLKS);
			if (error)
				break;
		} else {
			/* Didn't do anything, push cursor back. */
			xfs_iext_prev(ifp, &icur);
		}
next_extent:
		if (!xfs_iext_get_extent(ifp, &icur, &got))
			break;
	}

	/* clear tag if cow fork is emptied */
	if (!ifp->if_bytes)
		xfs_inode_clear_cowblocks_tag(ip);
	return error;
}

/*
 * Cancel CoW reservations for some byte range of an inode.
 *
 * If cancel_real is true this function cancels all COW fork extents for the
 * inode; if cancel_real is false, real extents are not cleared.
 */
int
xfs_reflink_cancel_cow_range(
	struct xfs_inode	*ip,
	xfs_off_t		offset,
	xfs_off_t		count,
	bool			cancel_real)
{
	struct xfs_trans	*tp;
	xfs_fileoff_t		offset_fsb;
	xfs_fileoff_t		end_fsb;
	int			error;

	trace_xfs_reflink_cancel_cow_range(ip, offset, count);
	ASSERT(xfs_is_reflink_inode(ip));

	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
	if (count == NULLFILEOFF)
		end_fsb = NULLFILEOFF;
	else
		end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);

	/* Start a rolling transaction to remove the mappings */
	error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_write,
			0, 0, XFS_TRANS_NOFS, &tp);
	if (error)
		goto out;

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

	/* Scrape out the old CoW reservations */
	error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb,
			cancel_real);
	if (error)
		goto out_cancel;

	error = xfs_trans_commit(tp);

	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	return error;

out_cancel:
	xfs_trans_cancel(tp);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
	trace_xfs_reflink_cancel_cow_range_error(ip, error, _RET_IP_);
	return error;
}

/*
 * Remap parts of a file's data fork after a successful CoW.
 */
int
xfs_reflink_end_cow(
	struct xfs_inode		*ip,
	xfs_off_t			offset,
	xfs_off_t			count)
{
	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
	struct xfs_bmbt_irec		got, del;
	struct xfs_trans		*tp;
	xfs_fileoff_t			offset_fsb;
	xfs_fileoff_t			end_fsb;
	int				error;
	unsigned int			resblks;
	xfs_filblks_t			rlen;
	struct xfs_iext_cursor		icur;

	trace_xfs_reflink_end_cow(ip, offset, count);

	/* No COW extents?  That's easy! */
	if (ifp->if_bytes == 0)
		return 0;

	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
	end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);

	/*
	 * Start a rolling transaction to switch the mappings.  We're
	 * unlikely ever to have to remap 16T worth of single-block
	 * extents, so just cap the worst case extent count to 2^32-1.
	 * Stick a warning in just in case, and avoid 64-bit division.
	 */
	BUILD_BUG_ON(MAX_RW_COUNT > UINT_MAX);
	if (end_fsb - offset_fsb > UINT_MAX) {
		error = -EFSCORRUPTED;
		xfs_force_shutdown(ip->i_mount, SHUTDOWN_CORRUPT_INCORE);
		ASSERT(0);
		goto out;
	}
	resblks = XFS_NEXTENTADD_SPACE_RES(ip->i_mount,
			(unsigned int)(end_fsb - offset_fsb),
			XFS_DATA_FORK);
	error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_write,
			resblks, 0, XFS_TRANS_RESERVE | XFS_TRANS_NOFS, &tp);
	if (error)
		goto out;

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

	/*
	 * In case of racing, overlapping AIO writes no COW extents might be
	 * left by the time I/O completes for the loser of the race.  In that
	 * case we are done.
	 */
	if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
		goto out_cancel;

	/* Walk backwards until we're out of the I/O range... */
	while (got.br_startoff + got.br_blockcount > offset_fsb) {
		del = got;
		xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);

		/* Extent delete may have bumped ext forward */
		if (!del.br_blockcount)
			goto prev_extent;

		/*
		 * Only remap real extent that contain data.  With AIO
		 * speculatively preallocations can leak into the range we
		 * are called upon, and we need to skip them.
		 */
		if (!xfs_bmap_is_real_extent(&got))
			goto prev_extent;

		/* Unmap the old blocks in the data fork. */
		ASSERT(tp->t_firstblock == NULLFSBLOCK);
		rlen = del.br_blockcount;
		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1);
		if (error)
			goto out_cancel;

		/* Trim the extent to whatever got unmapped. */
		if (rlen) {
			xfs_trim_extent(&del, del.br_startoff + rlen,
				del.br_blockcount - rlen);
		}
		trace_xfs_reflink_cow_remap(ip, &del);

		/* Free the CoW orphan record. */
		error = xfs_refcount_free_cow_extent(tp, del.br_startblock,
				del.br_blockcount);
		if (error)
			goto out_cancel;

		/* Map the new blocks into the data fork. */
		error = xfs_bmap_map_extent(tp, ip, &del);
		if (error)
			goto out_cancel;

		/* Charge this new data fork mapping to the on-disk quota. */
		xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_DELBCOUNT,
				(long)del.br_blockcount);

		/* Remove the mapping from the CoW fork. */
		xfs_bmap_del_extent_cow(ip, &icur, &got, &del);

		error = xfs_defer_finish(&tp);
		if (error)
			goto out_cancel;
		if (!xfs_iext_get_extent(ifp, &icur, &got))
			break;
		continue;
prev_extent:
		if (!xfs_iext_prev_extent(ifp, &icur, &got))
			break;
	}

	error = xfs_trans_commit(tp);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	if (error)
		goto out;
	return 0;

out_cancel:
	xfs_trans_cancel(tp);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
	trace_xfs_reflink_end_cow_error(ip, error, _RET_IP_);
	return error;
}

/*
 * Free leftover CoW reservations that didn't get cleaned out.
 */
int
xfs_reflink_recover_cow(
	struct xfs_mount	*mp)
{
	xfs_agnumber_t		agno;
	int			error = 0;

	if (!xfs_sb_version_hasreflink(&mp->m_sb))
		return 0;

	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
		error = xfs_refcount_recover_cow_leftovers(mp, agno);
		if (error)
			break;
	}

	return error;
}

/*
 * Reflinking (Block) Ranges of Two Files Together
 *
 * First, ensure that the reflink flag is set on both inodes.  The flag is an
 * optimization to avoid unnecessary refcount btree lookups in the write path.
 *
 * Now we can iteratively remap the range of extents (and holes) in src to the
 * corresponding ranges in dest.  Let drange and srange denote the ranges of
 * logical blocks in dest and src touched by the reflink operation.
 *
 * While the length of drange is greater than zero,
 *    - Read src's bmbt at the start of srange ("imap")
 *    - If imap doesn't exist, make imap appear to start at the end of srange
 *      with zero length.
 *    - If imap starts before srange, advance imap to start at srange.
 *    - If imap goes beyond srange, truncate imap to end at the end of srange.
 *    - Punch (imap start - srange start + imap len) blocks from dest at
 *      offset (drange start).
 *    - If imap points to a real range of pblks,
 *         > Increase the refcount of the imap's pblks
 *         > Map imap's pblks into dest at the offset
 *           (drange start + imap start - srange start)
 *    - Advance drange and srange by (imap start - srange start + imap len)
 *
 * Finally, if the reflink made dest longer, update both the in-core and
 * on-disk file sizes.
 *
 * ASCII Art Demonstration:
 *
 * Let's say we want to reflink this source file:
 *
 * ----SSSSSSS-SSSSS----SSSSSS (src file)
 *   <-------------------->
 *
 * into this destination file:
 *
 * --DDDDDDDDDDDDDDDDDDD--DDD (dest file)
 *        <-------------------->
 * '-' means a hole, and 'S' and 'D' are written blocks in the src and dest.
 * Observe that the range has different logical offsets in either file.
 *
 * Consider that the first extent in the source file doesn't line up with our
 * reflink range.  Unmapping  and remapping are separate operations, so we can
 * unmap more blocks from the destination file than we remap.
 *
 * ----SSSSSSS-SSSSS----SSSSSS
 *   <------->
 * --DDDDD---------DDDDD--DDD
 *        <------->
 *
 * Now remap the source extent into the destination file:
 *
 * ----SSSSSSS-SSSSS----SSSSSS
 *   <------->
 * --DDDDD--SSSSSSSDDDDD--DDD
 *        <------->
 *
 * Do likewise with the second hole and extent in our range.  Holes in the
 * unmap range don't affect our operation.
 *
 * ----SSSSSSS-SSSSS----SSSSSS
 *            <---->
 * --DDDDD--SSSSSSS-SSSSS-DDD
 *                 <---->
 *
 * Finally, unmap and remap part of the third extent.  This will increase the
 * size of the destination file.
 *
 * ----SSSSSSS-SSSSS----SSSSSS
 *                  <----->
 * --DDDDD--SSSSSSS-SSSSS----SSS
 *                       <----->
 *
 * Once we update the destination file's i_size, we're done.
 */

/*
 * Ensure the reflink bit is set in both inodes.
 */
STATIC int
xfs_reflink_set_inode_flag(
	struct xfs_inode	*src,
	struct xfs_inode	*dest)
{
	struct xfs_mount	*mp = src->i_mount;
	int			error;
	struct xfs_trans	*tp;

	if (xfs_is_reflink_inode(src) && xfs_is_reflink_inode(dest))
		return 0;

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
	if (error)
		goto out_error;

	/* Lock both files against IO */
	if (src->i_ino == dest->i_ino)
		xfs_ilock(src, XFS_ILOCK_EXCL);
	else
		xfs_lock_two_inodes(src, XFS_ILOCK_EXCL, dest, XFS_ILOCK_EXCL);

	if (!xfs_is_reflink_inode(src)) {
		trace_xfs_reflink_set_inode_flag(src);
		xfs_trans_ijoin(tp, src, XFS_ILOCK_EXCL);
		src->i_d.di_flags2 |= XFS_DIFLAG2_REFLINK;
		xfs_trans_log_inode(tp, src, XFS_ILOG_CORE);
		xfs_ifork_init_cow(src);
	} else
		xfs_iunlock(src, XFS_ILOCK_EXCL);

	if (src->i_ino == dest->i_ino)
		goto commit_flags;

	if (!xfs_is_reflink_inode(dest)) {
		trace_xfs_reflink_set_inode_flag(dest);
		xfs_trans_ijoin(tp, dest, XFS_ILOCK_EXCL);
		dest->i_d.di_flags2 |= XFS_DIFLAG2_REFLINK;
		xfs_trans_log_inode(tp, dest, XFS_ILOG_CORE);
		xfs_ifork_init_cow(dest);
	} else
		xfs_iunlock(dest, XFS_ILOCK_EXCL);

commit_flags:
	error = xfs_trans_commit(tp);
	if (error)
		goto out_error;
	return error;

out_error:
	trace_xfs_reflink_set_inode_flag_error(dest, error, _RET_IP_);
	return error;
}

/*
 * Update destination inode size & cowextsize hint, if necessary.
 */
STATIC int
xfs_reflink_update_dest(
	struct xfs_inode	*dest,
	xfs_off_t		newlen,
	xfs_extlen_t		cowextsize,
	bool			is_dedupe)
{
	struct xfs_mount	*mp = dest->i_mount;
	struct xfs_trans	*tp;
	int			error;

	if (is_dedupe && newlen <= i_size_read(VFS_I(dest)) && cowextsize == 0)
		return 0;

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
	if (error)
		goto out_error;

	xfs_ilock(dest, XFS_ILOCK_EXCL);
	xfs_trans_ijoin(tp, dest, XFS_ILOCK_EXCL);

	if (newlen > i_size_read(VFS_I(dest))) {
		trace_xfs_reflink_update_inode_size(dest, newlen);
		i_size_write(VFS_I(dest), newlen);
		dest->i_d.di_size = newlen;
	}

	if (cowextsize) {
		dest->i_d.di_cowextsize = cowextsize;
		dest->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
	}

	if (!is_dedupe) {
		xfs_trans_ichgtime(tp, dest,
				   XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
	}
	xfs_trans_log_inode(tp, dest, XFS_ILOG_CORE);

	error = xfs_trans_commit(tp);
	if (error)
		goto out_error;
	return error;

out_error:
	trace_xfs_reflink_update_inode_size_error(dest, error, _RET_IP_);
	return error;
}

/*
 * Do we have enough reserve in this AG to handle a reflink?  The refcount
 * btree already reserved all the space it needs, but the rmap btree can grow
 * infinitely, so we won't allow more reflinks when the AG is down to the
 * btree reserves.
 */
static int
xfs_reflink_ag_has_free_space(
	struct xfs_mount	*mp,
	xfs_agnumber_t		agno)
{
	struct xfs_perag	*pag;
	int			error = 0;

	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
		return 0;

	pag = xfs_perag_get(mp, agno);
	if (xfs_ag_resv_critical(pag, XFS_AG_RESV_RMAPBT) ||
	    xfs_ag_resv_critical(pag, XFS_AG_RESV_METADATA))
		error = -ENOSPC;
	xfs_perag_put(pag);
	return error;
}

/*
 * Unmap a range of blocks from a file, then map other blocks into the hole.
 * The range to unmap is (destoff : destoff + srcioff + irec->br_blockcount).
 * The extent irec is mapped into dest at irec->br_startoff.
 */
STATIC int
xfs_reflink_remap_extent(
	struct xfs_inode	*ip,
	struct xfs_bmbt_irec	*irec,
	xfs_fileoff_t		destoff,
	xfs_off_t		new_isize)
{
	struct xfs_mount	*mp = ip->i_mount;
	bool			real_extent = xfs_bmap_is_real_extent(irec);
	struct xfs_trans	*tp;
	unsigned int		resblks;
	struct xfs_bmbt_irec	uirec;
	xfs_filblks_t		rlen;
	xfs_filblks_t		unmap_len;
	xfs_off_t		newlen;
	int			error;

	unmap_len = irec->br_startoff + irec->br_blockcount - destoff;
	trace_xfs_reflink_punch_range(ip, destoff, unmap_len);

	/* No reflinking if we're low on space */
	if (real_extent) {
		error = xfs_reflink_ag_has_free_space(mp,
				XFS_FSB_TO_AGNO(mp, irec->br_startblock));
		if (error)
			goto out;
	}

	/* Start a rolling transaction to switch the mappings */
	resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
	if (error)
		goto out;

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

	/* If we're not just clearing space, then do we have enough quota? */
	if (real_extent) {
		error = xfs_trans_reserve_quota_nblks(tp, ip,
				irec->br_blockcount, 0, XFS_QMOPT_RES_REGBLKS);
		if (error)
			goto out_cancel;
	}

	trace_xfs_reflink_remap(ip, irec->br_startoff,
				irec->br_blockcount, irec->br_startblock);

	/* Unmap the old blocks in the data fork. */
	rlen = unmap_len;
	while (rlen) {
		ASSERT(tp->t_firstblock == NULLFSBLOCK);
		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1);
		if (error)
			goto out_cancel;

		/*
		 * Trim the extent to whatever got unmapped.
		 * Remember, bunmapi works backwards.
		 */
		uirec.br_startblock = irec->br_startblock + rlen;
		uirec.br_startoff = irec->br_startoff + rlen;
		uirec.br_blockcount = unmap_len - rlen;
		unmap_len = rlen;

		/* If this isn't a real mapping, we're done. */
		if (!real_extent || uirec.br_blockcount == 0)
			goto next_extent;

		trace_xfs_reflink_remap(ip, uirec.br_startoff,
				uirec.br_blockcount, uirec.br_startblock);

		/* Update the refcount tree */
		error = xfs_refcount_increase_extent(tp, &uirec);
		if (error)
			goto out_cancel;

		/* Map the new blocks into the data fork. */
		error = xfs_bmap_map_extent(tp, ip, &uirec);
		if (error)
			goto out_cancel;

		/* Update quota accounting. */
		xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT,
				uirec.br_blockcount);

		/* Update dest isize if needed. */
		newlen = XFS_FSB_TO_B(mp,
				uirec.br_startoff + uirec.br_blockcount);
		newlen = min_t(xfs_off_t, newlen, new_isize);
		if (newlen > i_size_read(VFS_I(ip))) {
			trace_xfs_reflink_update_inode_size(ip, newlen);
			i_size_write(VFS_I(ip), newlen);
			ip->i_d.di_size = newlen;
			xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
		}

next_extent:
		/* Process all the deferred stuff. */
		error = xfs_defer_finish(&tp);
		if (error)
			goto out_cancel;
	}

	error = xfs_trans_commit(tp);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	if (error)
		goto out;
	return 0;

out_cancel:
	xfs_trans_cancel(tp);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
	trace_xfs_reflink_remap_extent_error(ip, error, _RET_IP_);
	return error;
}

/*
 * Iteratively remap one file's extents (and holes) to another's.
 */
STATIC int
xfs_reflink_remap_blocks(
	struct xfs_inode	*src,
	xfs_fileoff_t		srcoff,
	struct xfs_inode	*dest,
	xfs_fileoff_t		destoff,
	xfs_filblks_t		len,
	xfs_off_t		new_isize)
{
	struct xfs_bmbt_irec	imap;
	int			nimaps;
	int			error = 0;
	xfs_filblks_t		range_len;

	/* drange = (destoff, destoff + len); srange = (srcoff, srcoff + len) */
	while (len) {
		uint		lock_mode;

		trace_xfs_reflink_remap_blocks_loop(src, srcoff, len,
				dest, destoff);

		/* Read extent from the source file */
		nimaps = 1;
		lock_mode = xfs_ilock_data_map_shared(src);
		error = xfs_bmapi_read(src, srcoff, len, &imap, &nimaps, 0);
		xfs_iunlock(src, lock_mode);
		if (error)
			goto err;
		ASSERT(nimaps == 1);

		trace_xfs_reflink_remap_imap(src, srcoff, len, XFS_IO_OVERWRITE,
				&imap);

		/* Translate imap into the destination file. */
		range_len = imap.br_startoff + imap.br_blockcount - srcoff;
		imap.br_startoff += destoff - srcoff;

		/* Clear dest from destoff to the end of imap and map it in. */
		error = xfs_reflink_remap_extent(dest, &imap, destoff,
				new_isize);
		if (error)
			goto err;

		if (fatal_signal_pending(current)) {
			error = -EINTR;
			goto err;
		}

		/* Advance drange/srange */
		srcoff += range_len;
		destoff += range_len;
		len -= range_len;
	}

	return 0;

err:
	trace_xfs_reflink_remap_blocks_error(dest, error, _RET_IP_);
	return error;
}

/*
 * Grab the exclusive iolock for a data copy from src to dest, making
 * sure to abide vfs locking order (lowest pointer value goes first) and
 * breaking the pnfs layout leases on dest before proceeding.  The loop
 * is needed because we cannot call the blocking break_layout() with the
 * src iolock held, and therefore have to back out both locks.
 */
static int
xfs_iolock_two_inodes_and_break_layout(
	struct inode		*src,
	struct inode		*dest)
{
	int			error;

retry:
	if (src < dest) {
		inode_lock_shared(src);
		inode_lock_nested(dest, I_MUTEX_NONDIR2);
	} else {
		/* src >= dest */
		inode_lock(dest);
	}

	error = break_layout(dest, false);
	if (error == -EWOULDBLOCK) {
		inode_unlock(dest);
		if (src < dest)
			inode_unlock_shared(src);
		error = break_layout(dest, true);
		if (error)
			return error;
		goto retry;
	}
	if (error) {
		inode_unlock(dest);
		if (src < dest)
			inode_unlock_shared(src);
		return error;
	}
	if (src > dest)
		inode_lock_shared_nested(src, I_MUTEX_NONDIR2);
	return 0;
}

/* Unlock both inodes after they've been prepped for a range clone. */
STATIC void
xfs_reflink_remap_unlock(
	struct file		*file_in,
	struct file		*file_out)
{
	struct inode		*inode_in = file_inode(file_in);
	struct xfs_inode	*src = XFS_I(inode_in);
	struct inode		*inode_out = file_inode(file_out);
	struct xfs_inode	*dest = XFS_I(inode_out);
	bool			same_inode = (inode_in == inode_out);

	xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
	if (!same_inode)
		xfs_iunlock(src, XFS_MMAPLOCK_SHARED);
	inode_unlock(inode_out);
	if (!same_inode)
		inode_unlock_shared(inode_in);
}

/*
 * If we're reflinking to a point past the destination file's EOF, we must
 * zero any speculative post-EOF preallocations that sit between the old EOF
 * and the destination file offset.
 */
static int
xfs_reflink_zero_posteof(
	struct xfs_inode	*ip,
	loff_t			pos)
{
	loff_t			isize = i_size_read(VFS_I(ip));

	if (pos <= isize)
		return 0;

	trace_xfs_zero_eof(ip, isize, pos - isize);
	return iomap_zero_range(VFS_I(ip), isize, pos - isize, NULL,
			&xfs_iomap_ops);
}

/*
 * Prepare two files for range cloning.  Upon a successful return both inodes
 * will have the iolock and mmaplock held, the page cache of the out file will
 * be truncated, and any leases on the out file will have been broken.  This
 * function borrows heavily from xfs_file_aio_write_checks.
 *
 * The VFS allows partial EOF blocks to "match" for dedupe even though it hasn't
 * checked that the bytes beyond EOF physically match. Hence we cannot use the
 * EOF block in the source dedupe range because it's not a complete block match,
 * hence can introduce a corruption into the file that has it's block replaced.
 *
 * In similar fashion, the VFS file cloning also allows partial EOF blocks to be
 * "block aligned" for the purposes of cloning entire files.  However, if the
 * source file range includes the EOF block and it lands within the existing EOF
 * of the destination file, then we can expose stale data from beyond the source
 * file EOF in the destination file.
 *
 * XFS doesn't support partial block sharing, so in both cases we have check
 * these cases ourselves. For dedupe, we can simply round the length to dedupe
 * down to the previous whole block and ignore the partial EOF block. While this
 * means we can't dedupe the last block of a file, this is an acceptible
 * tradeoff for simplicity on implementation.
 *
 * For cloning, we want to share the partial EOF block if it is also the new EOF
 * block of the destination file. If the partial EOF block lies inside the
 * existing destination EOF, then we have to abort the clone to avoid exposing
 * stale data in the destination file. Hence we reject these clone attempts with
 * -EINVAL in this case.
 */
STATIC int
xfs_reflink_remap_prep(
	struct file		*file_in,
	loff_t			pos_in,
	struct file		*file_out,
	loff_t			pos_out,
	u64			*len,
	bool			is_dedupe)
{
	struct inode		*inode_in = file_inode(file_in);
	struct xfs_inode	*src = XFS_I(inode_in);
	struct inode		*inode_out = file_inode(file_out);
	struct xfs_inode	*dest = XFS_I(inode_out);
	bool			same_inode = (inode_in == inode_out);
	u64			blkmask = i_blocksize(inode_in) - 1;
	ssize_t			ret;

	/* Lock both files against IO */
	ret = xfs_iolock_two_inodes_and_break_layout(inode_in, inode_out);
	if (ret)
		return ret;
	if (same_inode)
		xfs_ilock(src, XFS_MMAPLOCK_EXCL);
	else
		xfs_lock_two_inodes(src, XFS_MMAPLOCK_SHARED, dest,
				XFS_MMAPLOCK_EXCL);

	/* Check file eligibility and prepare for block sharing. */
	ret = -EINVAL;
	/* Don't reflink realtime inodes */
	if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
		goto out_unlock;

	/* Don't share DAX file data for now. */
	if (IS_DAX(inode_in) || IS_DAX(inode_out))
		goto out_unlock;

	ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
			len, is_dedupe);
	if (ret <= 0)
		goto out_unlock;

	/*
	 * If the dedupe data matches, chop off the partial EOF block
	 * from the source file so we don't try to dedupe the partial
	 * EOF block.
	 */
	if (is_dedupe) {
		*len &= ~blkmask;
	} else if (*len & blkmask) {
		/*
		 * The user is attempting to share a partial EOF block,
		 * if it's inside the destination EOF then reject it.
		 */
		if (pos_out + *len < i_size_read(inode_out)) {
			ret = -EINVAL;
			goto out_unlock;
		}
	}

	/* Attach dquots to dest inode before changing block map */
	ret = xfs_qm_dqattach(dest);
	if (ret)
		goto out_unlock;

	/*
	 * Zero existing post-eof speculative preallocations in the destination
	 * file.
	 */
	ret = xfs_reflink_zero_posteof(dest, pos_out);
	if (ret)
		goto out_unlock;

	/* Set flags and remap blocks. */
	ret = xfs_reflink_set_inode_flag(src, dest);
	if (ret)
		goto out_unlock;

	/* Zap any page cache for the destination file's range. */
	truncate_inode_pages_range(&inode_out->i_data, pos_out,
				   PAGE_ALIGN(pos_out + *len) - 1);

	/* If we're altering the file contents... */
	if (!is_dedupe) {
		/*
		 * ...update the timestamps (which will grab the ilock again
		 * from xfs_fs_dirty_inode, so we have to call it before we
		 * take the ilock).
		 */
		if (!(file_out->f_mode & FMODE_NOCMTIME)) {
			ret = file_update_time(file_out);
			if (ret)
				goto out_unlock;
		}

		/*
		 * ...clear the security bits if the process is not being run
		 * by root.  This keeps people from modifying setuid and setgid
		 * binaries.
		 */
		ret = file_remove_privs(file_out);
		if (ret)
			goto out_unlock;
	}

	return 1;
out_unlock:
	xfs_reflink_remap_unlock(file_in, file_out);
	return ret;
}

/*
 * Link a range of blocks from one file to another.
 */
int
xfs_reflink_remap_range(
	struct file		*file_in,
	loff_t			pos_in,
	struct file		*file_out,
	loff_t			pos_out,
	u64			len,
	bool			is_dedupe)
{
	struct inode		*inode_in = file_inode(file_in);
	struct xfs_inode	*src = XFS_I(inode_in);
	struct inode		*inode_out = file_inode(file_out);
	struct xfs_inode	*dest = XFS_I(inode_out);
	struct xfs_mount	*mp = src->i_mount;
	xfs_fileoff_t		sfsbno, dfsbno;
	xfs_filblks_t		fsblen;
	xfs_extlen_t		cowextsize;
	ssize_t			ret;

	if (!xfs_sb_version_hasreflink(&mp->m_sb))
		return -EOPNOTSUPP;

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	/* Prepare and then clone file data. */
	ret = xfs_reflink_remap_prep(file_in, pos_in, file_out, pos_out,
			&len, is_dedupe);
	if (ret <= 0)
		return ret;

	trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);

	dfsbno = XFS_B_TO_FSBT(mp, pos_out);
	sfsbno = XFS_B_TO_FSBT(mp, pos_in);
	fsblen = XFS_B_TO_FSB(mp, len);
	ret = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
			pos_out + len);
	if (ret)
		goto out_unlock;

	/*
	 * Carry the cowextsize hint from src to dest if we're sharing the
	 * entire source file to the entire destination file, the source file
	 * has a cowextsize hint, and the destination file does not.
	 */
	cowextsize = 0;
	if (pos_in == 0 && len == i_size_read(inode_in) &&
	    (src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) &&
	    pos_out == 0 && len >= i_size_read(inode_out) &&
	    !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
		cowextsize = src->i_d.di_cowextsize;

	ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize,
			is_dedupe);

out_unlock:
	xfs_reflink_remap_unlock(file_in, file_out);
	if (ret)
		trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_);
	return ret;
}

/*
 * The user wants to preemptively CoW all shared blocks in this file,
 * which enables us to turn off the reflink flag.  Iterate all
 * extents which are not prealloc/delalloc to see which ranges are
 * mentioned in the refcount tree, then read those blocks into the
 * pagecache, dirty them, fsync them back out, and then we can update
 * the inode flag.  What happens if we run out of memory? :)
 */
STATIC int
xfs_reflink_dirty_extents(
	struct xfs_inode	*ip,
	xfs_fileoff_t		fbno,
	xfs_filblks_t		end,
	xfs_off_t		isize)
{
	struct xfs_mount	*mp = ip->i_mount;
	xfs_agnumber_t		agno;
	xfs_agblock_t		agbno;
	xfs_extlen_t		aglen;
	xfs_agblock_t		rbno;
	xfs_extlen_t		rlen;
	xfs_off_t		fpos;
	xfs_off_t		flen;
	struct xfs_bmbt_irec	map[2];
	int			nmaps;
	int			error = 0;

	while (end - fbno > 0) {
		nmaps = 1;
		/*
		 * Look for extents in the file.  Skip holes, delalloc, or
		 * unwritten extents; they can't be reflinked.
		 */
		error = xfs_bmapi_read(ip, fbno, end - fbno, map, &nmaps, 0);
		if (error)
			goto out;
		if (nmaps == 0)
			break;
		if (!xfs_bmap_is_real_extent(&map[0]))
			goto next;

		map[1] = map[0];
		while (map[1].br_blockcount) {
			agno = XFS_FSB_TO_AGNO(mp, map[1].br_startblock);
			agbno = XFS_FSB_TO_AGBNO(mp, map[1].br_startblock);
			aglen = map[1].br_blockcount;

			error = xfs_reflink_find_shared(mp, NULL, agno, agbno,
					aglen, &rbno, &rlen, true);
			if (error)
				goto out;
			if (rbno == NULLAGBLOCK)
				break;

			/* Dirty the pages */
			xfs_iunlock(ip, XFS_ILOCK_EXCL);
			fpos = XFS_FSB_TO_B(mp, map[1].br_startoff +
					(rbno - agbno));
			flen = XFS_FSB_TO_B(mp, rlen);
			if (fpos + flen > isize)
				flen = isize - fpos;
			error = iomap_file_dirty(VFS_I(ip), fpos, flen,
					&xfs_iomap_ops);
			xfs_ilock(ip, XFS_ILOCK_EXCL);
			if (error)
				goto out;

			map[1].br_blockcount -= (rbno - agbno + rlen);
			map[1].br_startoff += (rbno - agbno + rlen);
			map[1].br_startblock += (rbno - agbno + rlen);
		}

next:
		fbno = map[0].br_startoff + map[0].br_blockcount;
	}
out:
	return error;
}

/* Does this inode need the reflink flag? */
int
xfs_reflink_inode_has_shared_extents(
	struct xfs_trans		*tp,
	struct xfs_inode		*ip,
	bool				*has_shared)
{
	struct xfs_bmbt_irec		got;
	struct xfs_mount		*mp = ip->i_mount;
	struct xfs_ifork		*ifp;
	xfs_agnumber_t			agno;
	xfs_agblock_t			agbno;
	xfs_extlen_t			aglen;
	xfs_agblock_t			rbno;
	xfs_extlen_t			rlen;
	struct xfs_iext_cursor		icur;
	bool				found;
	int				error;

	ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
		error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
		if (error)
			return error;
	}

	*has_shared = false;
	found = xfs_iext_lookup_extent(ip, ifp, 0, &icur, &got);
	while (found) {
		if (isnullstartblock(got.br_startblock) ||
		    got.br_state != XFS_EXT_NORM)
			goto next;
		agno = XFS_FSB_TO_AGNO(mp, got.br_startblock);
		agbno = XFS_FSB_TO_AGBNO(mp, got.br_startblock);
		aglen = got.br_blockcount;

		error = xfs_reflink_find_shared(mp, tp, agno, agbno, aglen,
				&rbno, &rlen, false);
		if (error)
			return error;
		/* Is there still a shared block here? */
		if (rbno != NULLAGBLOCK) {
			*has_shared = true;
			return 0;
		}
next:
		found = xfs_iext_next_extent(ifp, &icur, &got);
	}

	return 0;
}

/*
 * Clear the inode reflink flag if there are no shared extents.
 *
 * The caller is responsible for joining the inode to the transaction passed in.
 * The inode will be joined to the transaction that is returned to the caller.
 */
int
xfs_reflink_clear_inode_flag(
	struct xfs_inode	*ip,
	struct xfs_trans	**tpp)
{
	bool			needs_flag;
	int			error = 0;

	ASSERT(xfs_is_reflink_inode(ip));

	error = xfs_reflink_inode_has_shared_extents(*tpp, ip, &needs_flag);
	if (error || needs_flag)
		return error;

	/*
	 * We didn't find any shared blocks so turn off the reflink flag.
	 * First, get rid of any leftover CoW mappings.
	 */
	error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF, true);
	if (error)
		return error;

	/* Clear the inode flag. */
	trace_xfs_reflink_unset_inode_flag(ip);
	ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
	xfs_inode_clear_cowblocks_tag(ip);
	xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE);

	return error;
}

/*
 * Clear the inode reflink flag if there are no shared extents and the size
 * hasn't changed.
 */
STATIC int
xfs_reflink_try_clear_inode_flag(
	struct xfs_inode	*ip)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp;
	int			error = 0;

	/* Start a rolling transaction to remove the mappings */
	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, 0, &tp);
	if (error)
		return error;

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

	error = xfs_reflink_clear_inode_flag(ip, &tp);
	if (error)
		goto cancel;

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

	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	return 0;
cancel:
	xfs_trans_cancel(tp);
out:
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	return error;
}

/*
 * Pre-COW all shared blocks within a given byte range of a file and turn off
 * the reflink flag if we unshare all of the file's blocks.
 */
int
xfs_reflink_unshare(
	struct xfs_inode	*ip,
	xfs_off_t		offset,
	xfs_off_t		len)
{
	struct xfs_mount	*mp = ip->i_mount;
	xfs_fileoff_t		fbno;
	xfs_filblks_t		end;
	xfs_off_t		isize;
	int			error;

	if (!xfs_is_reflink_inode(ip))
		return 0;

	trace_xfs_reflink_unshare(ip, offset, len);

	inode_dio_wait(VFS_I(ip));

	/* Try to CoW the selected ranges */
	xfs_ilock(ip, XFS_ILOCK_EXCL);
	fbno = XFS_B_TO_FSBT(mp, offset);
	isize = i_size_read(VFS_I(ip));
	end = XFS_B_TO_FSB(mp, offset + len);
	error = xfs_reflink_dirty_extents(ip, fbno, end, isize);
	if (error)
		goto out_unlock;
	xfs_iunlock(ip, XFS_ILOCK_EXCL);

	/* Wait for the IO to finish */
	error = filemap_write_and_wait(VFS_I(ip)->i_mapping);
	if (error)
		goto out;

	/* Turn off the reflink flag if possible. */
	error = xfs_reflink_try_clear_inode_flag(ip);
	if (error)
		goto out;

	return 0;

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