summaryrefslogtreecommitdiffstats
path: root/fs/xfs/libxfs/xfs_refcount.c
blob: 2076627243b02d177cc9165c198b7d54816b9c33 (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
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
// 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_btree.h"
#include "xfs_bmap.h"
#include "xfs_refcount_btree.h"
#include "xfs_alloc.h"
#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_trans.h"
#include "xfs_bit.h"
#include "xfs_refcount.h"
#include "xfs_rmap.h"

/* Allowable refcount adjustment amounts. */
enum xfs_refc_adjust_op {
	XFS_REFCOUNT_ADJUST_INCREASE	= 1,
	XFS_REFCOUNT_ADJUST_DECREASE	= -1,
	XFS_REFCOUNT_ADJUST_COW_ALLOC	= 0,
	XFS_REFCOUNT_ADJUST_COW_FREE	= -1,
};

STATIC int __xfs_refcount_cow_alloc(struct xfs_btree_cur *rcur,
		xfs_agblock_t agbno, xfs_extlen_t aglen);
STATIC int __xfs_refcount_cow_free(struct xfs_btree_cur *rcur,
		xfs_agblock_t agbno, xfs_extlen_t aglen);

/*
 * Look up the first record less than or equal to [bno, len] in the btree
 * given by cur.
 */
int
xfs_refcount_lookup_le(
	struct xfs_btree_cur	*cur,
	xfs_agblock_t		bno,
	int			*stat)
{
	trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.agno, bno,
			XFS_LOOKUP_LE);
	cur->bc_rec.rc.rc_startblock = bno;
	cur->bc_rec.rc.rc_blockcount = 0;
	return xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat);
}

/*
 * Look up the first record greater than or equal to [bno, len] in the btree
 * given by cur.
 */
int
xfs_refcount_lookup_ge(
	struct xfs_btree_cur	*cur,
	xfs_agblock_t		bno,
	int			*stat)
{
	trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.agno, bno,
			XFS_LOOKUP_GE);
	cur->bc_rec.rc.rc_startblock = bno;
	cur->bc_rec.rc.rc_blockcount = 0;
	return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat);
}

/*
 * Look up the first record equal to [bno, len] in the btree
 * given by cur.
 */
int
xfs_refcount_lookup_eq(
	struct xfs_btree_cur	*cur,
	xfs_agblock_t		bno,
	int			*stat)
{
	trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.agno, bno,
			XFS_LOOKUP_LE);
	cur->bc_rec.rc.rc_startblock = bno;
	cur->bc_rec.rc.rc_blockcount = 0;
	return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat);
}

/* Convert on-disk record to in-core format. */
void
xfs_refcount_btrec_to_irec(
	union xfs_btree_rec		*rec,
	struct xfs_refcount_irec	*irec)
{
	irec->rc_startblock = be32_to_cpu(rec->refc.rc_startblock);
	irec->rc_blockcount = be32_to_cpu(rec->refc.rc_blockcount);
	irec->rc_refcount = be32_to_cpu(rec->refc.rc_refcount);
}

/*
 * Get the data from the pointed-to record.
 */
int
xfs_refcount_get_rec(
	struct xfs_btree_cur		*cur,
	struct xfs_refcount_irec	*irec,
	int				*stat)
{
	struct xfs_mount		*mp = cur->bc_mp;
	xfs_agnumber_t			agno = cur->bc_ag.agno;
	union xfs_btree_rec		*rec;
	int				error;
	xfs_agblock_t			realstart;

	error = xfs_btree_get_rec(cur, &rec, stat);
	if (error || !*stat)
		return error;

	xfs_refcount_btrec_to_irec(rec, irec);

	agno = cur->bc_ag.agno;
	if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN)
		goto out_bad_rec;

	/* handle special COW-staging state */
	realstart = irec->rc_startblock;
	if (realstart & XFS_REFC_COW_START) {
		if (irec->rc_refcount != 1)
			goto out_bad_rec;
		realstart &= ~XFS_REFC_COW_START;
	} else if (irec->rc_refcount < 2) {
		goto out_bad_rec;
	}

	/* check for valid extent range, including overflow */
	if (!xfs_verify_agbno(mp, agno, realstart))
		goto out_bad_rec;
	if (realstart > realstart + irec->rc_blockcount)
		goto out_bad_rec;
	if (!xfs_verify_agbno(mp, agno, realstart + irec->rc_blockcount - 1))
		goto out_bad_rec;

	if (irec->rc_refcount == 0 || irec->rc_refcount > MAXREFCOUNT)
		goto out_bad_rec;

	trace_xfs_refcount_get(cur->bc_mp, cur->bc_ag.agno, irec);
	return 0;

out_bad_rec:
	xfs_warn(mp,
		"Refcount BTree record corruption in AG %d detected!", agno);
	xfs_warn(mp,
		"Start block 0x%x, block count 0x%x, references 0x%x",
		irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount);
	return -EFSCORRUPTED;
}

/*
 * Update the record referred to by cur to the value given
 * by [bno, len, refcount].
 * This either works (return 0) or gets an EFSCORRUPTED error.
 */
STATIC int
xfs_refcount_update(
	struct xfs_btree_cur		*cur,
	struct xfs_refcount_irec	*irec)
{
	union xfs_btree_rec	rec;
	int			error;

	trace_xfs_refcount_update(cur->bc_mp, cur->bc_ag.agno, irec);
	rec.refc.rc_startblock = cpu_to_be32(irec->rc_startblock);
	rec.refc.rc_blockcount = cpu_to_be32(irec->rc_blockcount);
	rec.refc.rc_refcount = cpu_to_be32(irec->rc_refcount);
	error = xfs_btree_update(cur, &rec);
	if (error)
		trace_xfs_refcount_update_error(cur->bc_mp,
				cur->bc_ag.agno, error, _RET_IP_);
	return error;
}

/*
 * Insert the record referred to by cur to the value given
 * by [bno, len, refcount].
 * This either works (return 0) or gets an EFSCORRUPTED error.
 */
int
xfs_refcount_insert(
	struct xfs_btree_cur		*cur,
	struct xfs_refcount_irec	*irec,
	int				*i)
{
	int				error;

	trace_xfs_refcount_insert(cur->bc_mp, cur->bc_ag.agno, irec);
	cur->bc_rec.rc.rc_startblock = irec->rc_startblock;
	cur->bc_rec.rc.rc_blockcount = irec->rc_blockcount;
	cur->bc_rec.rc.rc_refcount = irec->rc_refcount;
	error = xfs_btree_insert(cur, i);
	if (error)
		goto out_error;
	if (XFS_IS_CORRUPT(cur->bc_mp, *i != 1)) {
		error = -EFSCORRUPTED;
		goto out_error;
	}

out_error:
	if (error)
		trace_xfs_refcount_insert_error(cur->bc_mp,
				cur->bc_ag.agno, error, _RET_IP_);
	return error;
}

/*
 * Remove the record referred to by cur, then set the pointer to the spot
 * where the record could be re-inserted, in case we want to increment or
 * decrement the cursor.
 * This either works (return 0) or gets an EFSCORRUPTED error.
 */
STATIC int
xfs_refcount_delete(
	struct xfs_btree_cur	*cur,
	int			*i)
{
	struct xfs_refcount_irec	irec;
	int			found_rec;
	int			error;

	error = xfs_refcount_get_rec(cur, &irec, &found_rec);
	if (error)
		goto out_error;
	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
		error = -EFSCORRUPTED;
		goto out_error;
	}
	trace_xfs_refcount_delete(cur->bc_mp, cur->bc_ag.agno, &irec);
	error = xfs_btree_delete(cur, i);
	if (XFS_IS_CORRUPT(cur->bc_mp, *i != 1)) {
		error = -EFSCORRUPTED;
		goto out_error;
	}
	if (error)
		goto out_error;
	error = xfs_refcount_lookup_ge(cur, irec.rc_startblock, &found_rec);
out_error:
	if (error)
		trace_xfs_refcount_delete_error(cur->bc_mp,
				cur->bc_ag.agno, error, _RET_IP_);
	return error;
}

/*
 * Adjusting the Reference Count
 *
 * As stated elsewhere, the reference count btree (refcbt) stores
 * >1 reference counts for extents of physical blocks.  In this
 * operation, we're either raising or lowering the reference count of
 * some subrange stored in the tree:
 *
 *      <------ adjustment range ------>
 * ----+   +---+-----+ +--+--------+---------
 *  2  |   | 3 |  4  | |17|   55   |   10
 * ----+   +---+-----+ +--+--------+---------
 * X axis is physical blocks number;
 * reference counts are the numbers inside the rectangles
 *
 * The first thing we need to do is to ensure that there are no
 * refcount extents crossing either boundary of the range to be
 * adjusted.  For any extent that does cross a boundary, split it into
 * two extents so that we can increment the refcount of one of the
 * pieces later:
 *
 *      <------ adjustment range ------>
 * ----+   +---+-----+ +--+--------+----+----
 *  2  |   | 3 |  2  | |17|   55   | 10 | 10
 * ----+   +---+-----+ +--+--------+----+----
 *
 * For this next step, let's assume that all the physical blocks in
 * the adjustment range are mapped to a file and are therefore in use
 * at least once.  Therefore, we can infer that any gap in the
 * refcount tree within the adjustment range represents a physical
 * extent with refcount == 1:
 *
 *      <------ adjustment range ------>
 * ----+---+---+-----+-+--+--------+----+----
 *  2  |"1"| 3 |  2  |1|17|   55   | 10 | 10
 * ----+---+---+-----+-+--+--------+----+----
 *      ^
 *
 * For each extent that falls within the interval range, figure out
 * which extent is to the left or the right of that extent.  Now we
 * have a left, current, and right extent.  If the new reference count
 * of the center extent enables us to merge left, center, and right
 * into one record covering all three, do so.  If the center extent is
 * at the left end of the range, abuts the left extent, and its new
 * reference count matches the left extent's record, then merge them.
 * If the center extent is at the right end of the range, abuts the
 * right extent, and the reference counts match, merge those.  In the
 * example, we can left merge (assuming an increment operation):
 *
 *      <------ adjustment range ------>
 * --------+---+-----+-+--+--------+----+----
 *    2    | 3 |  2  |1|17|   55   | 10 | 10
 * --------+---+-----+-+--+--------+----+----
 *          ^
 *
 * For all other extents within the range, adjust the reference count
 * or delete it if the refcount falls below 2.  If we were
 * incrementing, the end result looks like this:
 *
 *      <------ adjustment range ------>
 * --------+---+-----+-+--+--------+----+----
 *    2    | 4 |  3  |2|18|   56   | 11 | 10
 * --------+---+-----+-+--+--------+----+----
 *
 * The result of a decrement operation looks as such:
 *
 *      <------ adjustment range ------>
 * ----+   +---+       +--+--------+----+----
 *  2  |   | 2 |       |16|   54   |  9 | 10
 * ----+   +---+       +--+--------+----+----
 *      DDDD    111111DD
 *
 * The blocks marked "D" are freed; the blocks marked "1" are only
 * referenced once and therefore the record is removed from the
 * refcount btree.
 */

/* Next block after this extent. */
static inline xfs_agblock_t
xfs_refc_next(
	struct xfs_refcount_irec	*rc)
{
	return rc->rc_startblock + rc->rc_blockcount;
}

/*
 * Split a refcount extent that crosses agbno.
 */
STATIC int
xfs_refcount_split_extent(
	struct xfs_btree_cur		*cur,
	xfs_agblock_t			agbno,
	bool				*shape_changed)
{
	struct xfs_refcount_irec	rcext, tmp;
	int				found_rec;
	int				error;

	*shape_changed = false;
	error = xfs_refcount_lookup_le(cur, agbno, &found_rec);
	if (error)
		goto out_error;
	if (!found_rec)
		return 0;

	error = xfs_refcount_get_rec(cur, &rcext, &found_rec);
	if (error)
		goto out_error;
	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
		error = -EFSCORRUPTED;
		goto out_error;
	}
	if (rcext.rc_startblock == agbno || xfs_refc_next(&rcext) <= agbno)
		return 0;

	*shape_changed = true;
	trace_xfs_refcount_split_extent(cur->bc_mp, cur->bc_ag.agno,
			&rcext, agbno);

	/* Establish the right extent. */
	tmp = rcext;
	tmp.rc_startblock = agbno;
	tmp.rc_blockcount -= (agbno - rcext.rc_startblock);
	error = xfs_refcount_update(cur, &tmp);
	if (error)
		goto out_error;

	/* Insert the left extent. */
	tmp = rcext;
	tmp.rc_blockcount = agbno - rcext.rc_startblock;
	error = xfs_refcount_insert(cur, &tmp, &found_rec);
	if (error)
		goto out_error;
	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
		error = -EFSCORRUPTED;
		goto out_error;
	}
	return error;

out_error:
	trace_xfs_refcount_split_extent_error(cur->bc_mp,
			cur->bc_ag.agno, error, _RET_IP_);
	return error;
}

/*
 * Merge the left, center, and right extents.
 */
STATIC int
xfs_refcount_merge_center_extents(
	struct xfs_btree_cur		*cur,
	struct xfs_refcount_irec	*left,
	struct xfs_refcount_irec	*center,
	struct xfs_refcount_irec	*right,
	unsigned long long		extlen,
	xfs_extlen_t			*aglen)
{
	int				error;
	int				found_rec;

	trace_xfs_refcount_merge_center_extents(cur->bc_mp,
			cur->bc_ag.agno, left, center, right);

	/*
	 * Make sure the center and right extents are not in the btree.
	 * If the center extent was synthesized, the first delete call
	 * removes the right extent and we skip the second deletion.
	 * If center and right were in the btree, then the first delete
	 * call removes the center and the second one removes the right
	 * extent.
	 */
	error = xfs_refcount_lookup_ge(cur, center->rc_startblock,
			&found_rec);
	if (error)
		goto out_error;
	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
		error = -EFSCORRUPTED;
		goto out_error;
	}

	error = xfs_refcount_delete(cur, &found_rec);
	if (error)
		goto out_error;
	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
		error = -EFSCORRUPTED;
		goto out_error;
	}

	if (center->rc_refcount > 1) {
		error = xfs_refcount_delete(cur, &found_rec);
		if (error)
			goto out_error;
		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
			error = -EFSCORRUPTED;
			goto out_error;
		}
	}

	/* Enlarge the left extent. */
	error = xfs_refcount_lookup_le(cur, left->rc_startblock,
			&found_rec);
	if (error)
		goto out_error;
	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
		error = -EFSCORRUPTED;
		goto out_error;
	}

	left->rc_blockcount = extlen;
	error = xfs_refcount_update(cur, left);
	if (error)
		goto out_error;

	*aglen = 0;
	return error;

out_error:
	trace_xfs_refcount_merge_center_extents_error(cur->bc_mp,
			cur->bc_ag.agno, error, _RET_IP_);
	return error;
}

/*
 * Merge with the left extent.
 */
STATIC int
xfs_refcount_merge_left_extent(
	struct xfs_btree_cur		*cur,
	struct xfs_refcount_irec	*left,
	struct xfs_refcount_irec	*cleft,
	xfs_agblock_t			*agbno,
	xfs_extlen_t			*aglen)
{
	int				error;
	int				found_rec;

	trace_xfs_refcount_merge_left_extent(cur->bc_mp,
			cur->bc_ag.agno, left, cleft);

	/* If the extent at agbno (cleft) wasn't synthesized, remove it. */
	if (cleft->rc_refcount > 1) {
		error = xfs_refcount_lookup_le(cur, cleft->rc_startblock,
				&found_rec);
		if (error)
			goto out_error;
		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
			error = -EFSCORRUPTED;
			goto out_error;
		}

		error = xfs_refcount_delete(cur, &found_rec);
		if (error)
			goto out_error;
		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
			error = -EFSCORRUPTED;
			goto out_error;
		}
	}

	/* Enlarge the left extent. */
	error = xfs_refcount_lookup_le(cur, left->rc_startblock,
			&found_rec);
	if (error)
		goto out_error;
	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
		error = -EFSCORRUPTED;
		goto out_error;
	}

	left->rc_blockcount += cleft->rc_blockcount;
	error = xfs_refcount_update(cur, left);
	if (error)
		goto out_error;

	*agbno += cleft->rc_blockcount;
	*aglen -= cleft->rc_blockcount;
	return error;

out_error:
	trace_xfs_refcount_merge_left_extent_error(cur->bc_mp,
			cur->bc_ag.agno, error, _RET_IP_);
	return error;
}

/*
 * Merge with the right extent.
 */
STATIC int
xfs_refcount_merge_right_extent(
	struct xfs_btree_cur		*cur,
	struct xfs_refcount_irec	*right,
	struct xfs_refcount_irec	*cright,
	xfs_extlen_t			*aglen)
{
	int				error;
	int				found_rec;

	trace_xfs_refcount_merge_right_extent(cur->bc_mp,
			cur->bc_ag.agno, cright, right);

	/*
	 * If the extent ending at agbno+aglen (cright) wasn't synthesized,
	 * remove it.
	 */
	if (cright->rc_refcount > 1) {
		error = xfs_refcount_lookup_le(cur, cright->rc_startblock,
			&found_rec);
		if (error)
			goto out_error;
		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
			error = -EFSCORRUPTED;
			goto out_error;
		}

		error = xfs_refcount_delete(cur, &found_rec);
		if (error)
			goto out_error;
		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
			error = -EFSCORRUPTED;
			goto out_error;
		}
	}

	/* Enlarge the right extent. */
	error = xfs_refcount_lookup_le(cur, right->rc_startblock,
			&found_rec);
	if (error)
		goto out_error;
	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
		error = -EFSCORRUPTED;
		goto out_error;
	}

	right->rc_startblock -= cright->rc_blockcount;
	right->rc_blockcount += cright->rc_blockcount;
	error = xfs_refcount_update(cur, right);
	if (error)
		goto out_error;

	*aglen -= cright->rc_blockcount;
	return error;

out_error:
	trace_xfs_refcount_merge_right_extent_error(cur->bc_mp,
			cur->bc_ag.agno, error, _RET_IP_);
	return error;
}

#define XFS_FIND_RCEXT_SHARED	1
#define XFS_FIND_RCEXT_COW	2
/*
 * Find the left extent and the one after it (cleft).  This function assumes
 * that we've already split any extent crossing agbno.
 */
STATIC int
xfs_refcount_find_left_extents(
	struct xfs_btree_cur		*cur,
	struct xfs_refcount_irec	*left,
	struct xfs_refcount_irec	*cleft,
	xfs_agblock_t			agbno,
	xfs_extlen_t			aglen,
	int				flags)
{
	struct xfs_refcount_irec	tmp;
	int				error;
	int				found_rec;

	left->rc_startblock = cleft->rc_startblock = NULLAGBLOCK;
	error = xfs_refcount_lookup_le(cur, agbno - 1, &found_rec);
	if (error)
		goto out_error;
	if (!found_rec)
		return 0;

	error = xfs_refcount_get_rec(cur, &tmp, &found_rec);
	if (error)
		goto out_error;
	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
		error = -EFSCORRUPTED;
		goto out_error;
	}

	if (xfs_refc_next(&tmp) != agbno)
		return 0;
	if ((flags & XFS_FIND_RCEXT_SHARED) && tmp.rc_refcount < 2)
		return 0;
	if ((flags & XFS_FIND_RCEXT_COW) && tmp.rc_refcount > 1)
		return 0;
	/* We have a left extent; retrieve (or invent) the next right one */
	*left = tmp;

	error = xfs_btree_increment(cur, 0, &found_rec);
	if (error)
		goto out_error;
	if (found_rec) {
		error = xfs_refcount_get_rec(cur, &tmp, &found_rec);
		if (error)
			goto out_error;
		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
			error = -EFSCORRUPTED;
			goto out_error;
		}

		/* if tmp starts at the end of our range, just use that */
		if (tmp.rc_startblock == agbno)
			*cleft = tmp;
		else {
			/*
			 * There's a gap in the refcntbt at the start of the
			 * range we're interested in (refcount == 1) so
			 * synthesize the implied extent and pass it back.
			 * We assume here that the agbno/aglen range was
			 * passed in from a data fork extent mapping and
			 * therefore is allocated to exactly one owner.
			 */
			cleft->rc_startblock = agbno;
			cleft->rc_blockcount = min(aglen,
					tmp.rc_startblock - agbno);
			cleft->rc_refcount = 1;
		}
	} else {
		/*
		 * No extents, so pretend that there's one covering the whole
		 * range.
		 */
		cleft->rc_startblock = agbno;
		cleft->rc_blockcount = aglen;
		cleft->rc_refcount = 1;
	}
	trace_xfs_refcount_find_left_extent(cur->bc_mp, cur->bc_ag.agno,
			left, cleft, agbno);
	return error;

out_error:
	trace_xfs_refcount_find_left_extent_error(cur->bc_mp,
			cur->bc_ag.agno, error, _RET_IP_);
	return error;
}

/*
 * Find the right extent and the one before it (cright).  This function
 * assumes that we've already split any extents crossing agbno + aglen.
 */
STATIC int
xfs_refcount_find_right_extents(
	struct xfs_btree_cur		*cur,
	struct xfs_refcount_irec	*right,
	struct xfs_refcount_irec	*cright,
	xfs_agblock_t			agbno,
	xfs_extlen_t			aglen,
	int				flags)
{
	struct xfs_refcount_irec	tmp;
	int				error;
	int				found_rec;

	right->rc_startblock = cright->rc_startblock = NULLAGBLOCK;
	error = xfs_refcount_lookup_ge(cur, agbno + aglen, &found_rec);
	if (error)
		goto out_error;
	if (!found_rec)
		return 0;

	error = xfs_refcount_get_rec(cur, &tmp, &found_rec);
	if (error)
		goto out_error;
	if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
		error = -EFSCORRUPTED;
		goto out_error;
	}

	if (tmp.rc_startblock != agbno + aglen)
		return 0;
	if ((flags & XFS_FIND_RCEXT_SHARED) && tmp.rc_refcount < 2)
		return 0;
	if ((flags & XFS_FIND_RCEXT_COW) && tmp.rc_refcount > 1)
		return 0;
	/* We have a right extent; retrieve (or invent) the next left one */
	*right = tmp;

	error = xfs_btree_decrement(cur, 0, &found_rec);
	if (error)
		goto out_error;
	if (found_rec) {
		error = xfs_refcount_get_rec(cur, &tmp, &found_rec);
		if (error)
			goto out_error;
		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
			error = -EFSCORRUPTED;
			goto out_error;
		}

		/* if tmp ends at the end of our range, just use that */
		if (xfs_refc_next(&tmp) == agbno + aglen)
			*cright = tmp;
		else {
			/*
			 * There's a gap in the refcntbt at the end of the
			 * range we're interested in (refcount == 1) so
			 * create the implied extent and pass it back.
			 * We assume here that the agbno/aglen range was
			 * passed in from a data fork extent mapping and
			 * therefore is allocated to exactly one owner.
			 */
			cright->rc_startblock = max(agbno, xfs_refc_next(&tmp));
			cright->rc_blockcount = right->rc_startblock -
					cright->rc_startblock;
			cright->rc_refcount = 1;
		}
	} else {
		/*
		 * No extents, so pretend that there's one covering the whole
		 * range.
		 */
		cright->rc_startblock = agbno;
		cright->rc_blockcount = aglen;
		cright->rc_refcount = 1;
	}
	trace_xfs_refcount_find_right_extent(cur->bc_mp, cur->bc_ag.agno,
			cright, right, agbno + aglen);
	return error;

out_error:
	trace_xfs_refcount_find_right_extent_error(cur->bc_mp,
			cur->bc_ag.agno, error, _RET_IP_);
	return error;
}

/* Is this extent valid? */
static inline bool
xfs_refc_valid(
	struct xfs_refcount_irec	*rc)
{
	return rc->rc_startblock != NULLAGBLOCK;
}

/*
 * Try to merge with any extents on the boundaries of the adjustment range.
 */
STATIC int
xfs_refcount_merge_extents(
	struct xfs_btree_cur	*cur,
	xfs_agblock_t		*agbno,
	xfs_extlen_t		*aglen,
	enum xfs_refc_adjust_op adjust,
	int			flags,
	bool			*shape_changed)
{
	struct xfs_refcount_irec	left = {0}, cleft = {0};
	struct xfs_refcount_irec	cright = {0}, right = {0};
	int				error;
	unsigned long long		ulen;
	bool				cequal;

	*shape_changed = false;
	/*
	 * Find the extent just below agbno [left], just above agbno [cleft],
	 * just below (agbno + aglen) [cright], and just above (agbno + aglen)
	 * [right].
	 */
	error = xfs_refcount_find_left_extents(cur, &left, &cleft, *agbno,
			*aglen, flags);
	if (error)
		return error;
	error = xfs_refcount_find_right_extents(cur, &right, &cright, *agbno,
			*aglen, flags);
	if (error)
		return error;

	/* No left or right extent to merge; exit. */
	if (!xfs_refc_valid(&left) && !xfs_refc_valid(&right))
		return 0;

	cequal = (cleft.rc_startblock == cright.rc_startblock) &&
		 (cleft.rc_blockcount == cright.rc_blockcount);

	/* Try to merge left, cleft, and right.  cleft must == cright. */
	ulen = (unsigned long long)left.rc_blockcount + cleft.rc_blockcount +
			right.rc_blockcount;
	if (xfs_refc_valid(&left) && xfs_refc_valid(&right) &&
	    xfs_refc_valid(&cleft) && xfs_refc_valid(&cright) && cequal &&
	    left.rc_refcount == cleft.rc_refcount + adjust &&
	    right.rc_refcount == cleft.rc_refcount + adjust &&
	    ulen < MAXREFCEXTLEN) {
		*shape_changed = true;
		return xfs_refcount_merge_center_extents(cur, &left, &cleft,
				&right, ulen, aglen);
	}

	/* Try to merge left and cleft. */
	ulen = (unsigned long long)left.rc_blockcount + cleft.rc_blockcount;
	if (xfs_refc_valid(&left) && xfs_refc_valid(&cleft) &&
	    left.rc_refcount == cleft.rc_refcount + adjust &&
	    ulen < MAXREFCEXTLEN) {
		*shape_changed = true;
		error = xfs_refcount_merge_left_extent(cur, &left, &cleft,
				agbno, aglen);
		if (error)
			return error;

		/*
		 * If we just merged left + cleft and cleft == cright,
		 * we no longer have a cright to merge with right.  We're done.
		 */
		if (cequal)
			return 0;
	}

	/* Try to merge cright and right. */
	ulen = (unsigned long long)right.rc_blockcount + cright.rc_blockcount;
	if (xfs_refc_valid(&right) && xfs_refc_valid(&cright) &&
	    right.rc_refcount == cright.rc_refcount + adjust &&
	    ulen < MAXREFCEXTLEN) {
		*shape_changed = true;
		return xfs_refcount_merge_right_extent(cur, &right, &cright,
				aglen);
	}

	return error;
}

/*
 * XXX: This is a pretty hand-wavy estimate.  The penalty for guessing
 * true incorrectly is a shutdown FS; the penalty for guessing false
 * incorrectly is more transaction rolls than might be necessary.
 * Be conservative here.
 */
static bool
xfs_refcount_still_have_space(
	struct xfs_btree_cur		*cur)
{
	unsigned long			overhead;

	overhead = cur->bc_ag.refc.shape_changes *
			xfs_allocfree_log_count(cur->bc_mp, 1);
	overhead *= cur->bc_mp->m_sb.sb_blocksize;

	/*
	 * Only allow 2 refcount extent updates per transaction if the
	 * refcount continue update "error" has been injected.
	 */
	if (cur->bc_ag.refc.nr_ops > 2 &&
	    XFS_TEST_ERROR(false, cur->bc_mp,
			XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE))
		return false;

	if (cur->bc_ag.refc.nr_ops == 0)
		return true;
	else if (overhead > cur->bc_tp->t_log_res)
		return false;
	return  cur->bc_tp->t_log_res - overhead >
		cur->bc_ag.refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD;
}

/*
 * Adjust the refcounts of middle extents.  At this point we should have
 * split extents that crossed the adjustment range; merged with adjacent
 * extents; and updated agbno/aglen to reflect the merges.  Therefore,
 * all we have to do is update the extents inside [agbno, agbno + aglen].
 */
STATIC int
xfs_refcount_adjust_extents(
	struct xfs_btree_cur	*cur,
	xfs_agblock_t		*agbno,
	xfs_extlen_t		*aglen,
	enum xfs_refc_adjust_op	adj,
	struct xfs_owner_info	*oinfo)
{
	struct xfs_refcount_irec	ext, tmp;
	int				error;
	int				found_rec, found_tmp;
	xfs_fsblock_t			fsbno;

	/* Merging did all the work already. */
	if (*aglen == 0)
		return 0;

	error = xfs_refcount_lookup_ge(cur, *agbno, &found_rec);
	if (error)
		goto out_error;

	while (*aglen > 0 && xfs_refcount_still_have_space(cur)) {
		error = xfs_refcount_get_rec(cur, &ext, &found_rec);
		if (error)
			goto out_error;
		if (!found_rec) {
			ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks;
			ext.rc_blockcount = 0;
			ext.rc_refcount = 0;
		}

		/*
		 * Deal with a hole in the refcount tree; if a file maps to
		 * these blocks and there's no refcountbt record, pretend that
		 * there is one with refcount == 1.
		 */
		if (ext.rc_startblock != *agbno) {
			tmp.rc_startblock = *agbno;
			tmp.rc_blockcount = min(*aglen,
					ext.rc_startblock - *agbno);
			tmp.rc_refcount = 1 + adj;
			trace_xfs_refcount_modify_extent(cur->bc_mp,
					cur->bc_ag.agno, &tmp);

			/*
			 * Either cover the hole (increment) or
			 * delete the range (decrement).
			 */
			if (tmp.rc_refcount) {
				error = xfs_refcount_insert(cur, &tmp,
						&found_tmp);
				if (error)
					goto out_error;
				if (XFS_IS_CORRUPT(cur->bc_mp,
						   found_tmp != 1)) {
					error = -EFSCORRUPTED;
					goto out_error;
				}
				cur->bc_ag.refc.nr_ops++;
			} else {
				fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
						cur->bc_ag.agno,
						tmp.rc_startblock);
				xfs_bmap_add_free(cur->bc_tp, fsbno,
						  tmp.rc_blockcount, oinfo);
			}

			(*agbno) += tmp.rc_blockcount;
			(*aglen) -= tmp.rc_blockcount;

			error = xfs_refcount_lookup_ge(cur, *agbno,
					&found_rec);
			if (error)
				goto out_error;
		}

		/* Stop if there's nothing left to modify */
		if (*aglen == 0 || !xfs_refcount_still_have_space(cur))
			break;

		/*
		 * Adjust the reference count and either update the tree
		 * (incr) or free the blocks (decr).
		 */
		if (ext.rc_refcount == MAXREFCOUNT)
			goto skip;
		ext.rc_refcount += adj;
		trace_xfs_refcount_modify_extent(cur->bc_mp,
				cur->bc_ag.agno, &ext);
		if (ext.rc_refcount > 1) {
			error = xfs_refcount_update(cur, &ext);
			if (error)
				goto out_error;
			cur->bc_ag.refc.nr_ops++;
		} else if (ext.rc_refcount == 1) {
			error = xfs_refcount_delete(cur, &found_rec);
			if (error)
				goto out_error;
			if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
				error = -EFSCORRUPTED;
				goto out_error;
			}
			cur->bc_ag.refc.nr_ops++;
			goto advloop;
		} else {
			fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
					cur->bc_ag.agno,
					ext.rc_startblock);
			xfs_bmap_add_free(cur->bc_tp, fsbno, ext.rc_blockcount,
					  oinfo);
		}

skip:
		error = xfs_btree_increment(cur, 0, &found_rec);
		if (error)
			goto out_error;

advloop:
		(*agbno) += ext.rc_blockcount;
		(*aglen) -= ext.rc_blockcount;
	}

	return error;
out_error:
	trace_xfs_refcount_modify_extent_error(cur->bc_mp,
			cur->bc_ag.agno, error, _RET_IP_);
	return error;
}

/* Adjust the reference count of a range of AG blocks. */
STATIC int
xfs_refcount_adjust(
	struct xfs_btree_cur	*cur,
	xfs_agblock_t		agbno,
	xfs_extlen_t		aglen,
	xfs_agblock_t		*new_agbno,
	xfs_extlen_t		*new_aglen,
	enum xfs_refc_adjust_op	adj,
	struct xfs_owner_info	*oinfo)
{
	bool			shape_changed;
	int			shape_changes = 0;
	int			error;

	*new_agbno = agbno;
	*new_aglen = aglen;
	if (adj == XFS_REFCOUNT_ADJUST_INCREASE)
		trace_xfs_refcount_increase(cur->bc_mp, cur->bc_ag.agno,
				agbno, aglen);
	else
		trace_xfs_refcount_decrease(cur->bc_mp, cur->bc_ag.agno,
				agbno, aglen);

	/*
	 * Ensure that no rcextents cross the boundary of the adjustment range.
	 */
	error = xfs_refcount_split_extent(cur, agbno, &shape_changed);
	if (error)
		goto out_error;
	if (shape_changed)
		shape_changes++;

	error = xfs_refcount_split_extent(cur, agbno + aglen, &shape_changed);
	if (error)
		goto out_error;
	if (shape_changed)
		shape_changes++;

	/*
	 * Try to merge with the left or right extents of the range.
	 */
	error = xfs_refcount_merge_extents(cur, new_agbno, new_aglen, adj,
			XFS_FIND_RCEXT_SHARED, &shape_changed);
	if (error)
		goto out_error;
	if (shape_changed)
		shape_changes++;
	if (shape_changes)
		cur->bc_ag.refc.shape_changes++;

	/* Now that we've taken care of the ends, adjust the middle extents */
	error = xfs_refcount_adjust_extents(cur, new_agbno, new_aglen,
			adj, oinfo);
	if (error)
		goto out_error;

	return 0;

out_error:
	trace_xfs_refcount_adjust_error(cur->bc_mp, cur->bc_ag.agno,
			error, _RET_IP_);
	return error;
}

/* Clean up after calling xfs_refcount_finish_one. */
void
xfs_refcount_finish_one_cleanup(
	struct xfs_trans	*tp,
	struct xfs_btree_cur	*rcur,
	int			error)
{
	struct xfs_buf		*agbp;

	if (rcur == NULL)
		return;
	agbp = rcur->bc_ag.agbp;
	xfs_btree_del_cursor(rcur, error);
	if (error)
		xfs_trans_brelse(tp, agbp);
}

/*
 * Process one of the deferred refcount operations.  We pass back the
 * btree cursor to maintain our lock on the btree between calls.
 * This saves time and eliminates a buffer deadlock between the
 * superblock and the AGF because we'll always grab them in the same
 * order.
 */
int
xfs_refcount_finish_one(
	struct xfs_trans		*tp,
	enum xfs_refcount_intent_type	type,
	xfs_fsblock_t			startblock,
	xfs_extlen_t			blockcount,
	xfs_fsblock_t			*new_fsb,
	xfs_extlen_t			*new_len,
	struct xfs_btree_cur		**pcur)
{
	struct xfs_mount		*mp = tp->t_mountp;
	struct xfs_btree_cur		*rcur;
	struct xfs_buf			*agbp = NULL;
	int				error = 0;
	xfs_agnumber_t			agno;
	xfs_agblock_t			bno;
	xfs_agblock_t			new_agbno;
	unsigned long			nr_ops = 0;
	int				shape_changes = 0;

	agno = XFS_FSB_TO_AGNO(mp, startblock);
	ASSERT(agno != NULLAGNUMBER);
	bno = XFS_FSB_TO_AGBNO(mp, startblock);

	trace_xfs_refcount_deferred(mp, XFS_FSB_TO_AGNO(mp, startblock),
			type, XFS_FSB_TO_AGBNO(mp, startblock),
			blockcount);

	if (XFS_TEST_ERROR(false, mp,
			XFS_ERRTAG_REFCOUNT_FINISH_ONE))
		return -EIO;

	/*
	 * If we haven't gotten a cursor or the cursor AG doesn't match
	 * the startblock, get one now.
	 */
	rcur = *pcur;
	if (rcur != NULL && rcur->bc_ag.agno != agno) {
		nr_ops = rcur->bc_ag.refc.nr_ops;
		shape_changes = rcur->bc_ag.refc.shape_changes;
		xfs_refcount_finish_one_cleanup(tp, rcur, 0);
		rcur = NULL;
		*pcur = NULL;
	}
	if (rcur == NULL) {
		error = xfs_alloc_read_agf(tp->t_mountp, tp, agno,
				XFS_ALLOC_FLAG_FREEING, &agbp);
		if (error)
			return error;

		rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno);
		if (!rcur) {
			error = -ENOMEM;
			goto out_cur;
		}
		rcur->bc_ag.refc.nr_ops = nr_ops;
		rcur->bc_ag.refc.shape_changes = shape_changes;
	}
	*pcur = rcur;

	switch (type) {
	case XFS_REFCOUNT_INCREASE:
		error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
			new_len, XFS_REFCOUNT_ADJUST_INCREASE, NULL);
		*new_fsb = XFS_AGB_TO_FSB(mp, agno, new_agbno);
		break;
	case XFS_REFCOUNT_DECREASE:
		error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
			new_len, XFS_REFCOUNT_ADJUST_DECREASE, NULL);
		*new_fsb = XFS_AGB_TO_FSB(mp, agno, new_agbno);
		break;
	case XFS_REFCOUNT_ALLOC_COW:
		*new_fsb = startblock + blockcount;
		*new_len = 0;
		error = __xfs_refcount_cow_alloc(rcur, bno, blockcount);
		break;
	case XFS_REFCOUNT_FREE_COW:
		*new_fsb = startblock + blockcount;
		*new_len = 0;
		error = __xfs_refcount_cow_free(rcur, bno, blockcount);
		break;
	default:
		ASSERT(0);
		error = -EFSCORRUPTED;
	}
	if (!error && *new_len > 0)
		trace_xfs_refcount_finish_one_leftover(mp, agno, type,
				bno, blockcount, new_agbno, *new_len);
	return error;

out_cur:
	xfs_trans_brelse(tp, agbp);

	return error;
}

/*
 * Record a refcount intent for later processing.
 */
static void
__xfs_refcount_add(
	struct xfs_trans		*tp,
	enum xfs_refcount_intent_type	type,
	xfs_fsblock_t			startblock,
	xfs_extlen_t			blockcount)
{
	struct xfs_refcount_intent	*ri;

	trace_xfs_refcount_defer(tp->t_mountp,
			XFS_FSB_TO_AGNO(tp->t_mountp, startblock),
			type, XFS_FSB_TO_AGBNO(tp->t_mountp, startblock),
			blockcount);

	ri = kmem_alloc(sizeof(struct xfs_refcount_intent),
			KM_NOFS);
	INIT_LIST_HEAD(&ri->ri_list);
	ri->ri_type = type;
	ri->ri_startblock = startblock;
	ri->ri_blockcount = blockcount;

	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_REFCOUNT, &ri->ri_list);
}

/*
 * Increase the reference count of the blocks backing a file's extent.
 */
void
xfs_refcount_increase_extent(
	struct xfs_trans		*tp,
	struct xfs_bmbt_irec		*PREV)
{
	if (!xfs_sb_version_hasreflink(&tp->t_mountp->m_sb))
		return;

	__xfs_refcount_add(tp, XFS_REFCOUNT_INCREASE, PREV->br_startblock,
			PREV->br_blockcount);
}

/*
 * Decrease the reference count of the blocks backing a file's extent.
 */
void
xfs_refcount_decrease_extent(
	struct xfs_trans		*tp,
	struct xfs_bmbt_irec		*PREV)
{
	if (!xfs_sb_version_hasreflink(&tp->t_mountp->m_sb))
		return;

	__xfs_refcount_add(tp, XFS_REFCOUNT_DECREASE, PREV->br_startblock,
			PREV->br_blockcount);
}

/*
 * 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 set, return the longest contiguous extent of
 * shared blocks; if not, just return the first extent we find.  If no
 * shared blocks are found, fbno and flen will be set to NULLAGBLOCK
 * and 0, respectively.
 */
int
xfs_refcount_find_shared(
	struct xfs_btree_cur		*cur,
	xfs_agblock_t			agbno,
	xfs_extlen_t			aglen,
	xfs_agblock_t			*fbno,
	xfs_extlen_t			*flen,
	bool				find_end_of_shared)
{
	struct xfs_refcount_irec	tmp;
	int				i;
	int				have;
	int				error;

	trace_xfs_refcount_find_shared(cur->bc_mp, cur->bc_ag.agno,
			agbno, aglen);

	/* By default, skip the whole range */
	*fbno = NULLAGBLOCK;
	*flen = 0;

	/* Try to find a refcount extent that crosses the start */
	error = xfs_refcount_lookup_le(cur, agbno, &have);
	if (error)
		goto out_error;
	if (!have) {
		/* No left extent, look at the next one */
		error = xfs_btree_increment(cur, 0, &have);
		if (error)
			goto out_error;
		if (!have)
			goto done;
	}
	error = xfs_refcount_get_rec(cur, &tmp, &i);
	if (error)
		goto out_error;
	if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
		error = -EFSCORRUPTED;
		goto out_error;
	}

	/* If the extent ends before the start, look at the next one */
	if (tmp.rc_startblock + tmp.rc_blockcount <= agbno) {
		error = xfs_btree_increment(cur, 0, &have);
		if (error)
			goto out_error;
		if (!have)
			goto done;
		error = xfs_refcount_get_rec(cur, &tmp, &i);
		if (error)
			goto out_error;
		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto out_error;
		}
	}

	/* If the extent starts after the range we want, bail out */
	if (tmp.rc_startblock >= agbno + aglen)
		goto done;

	/* We found the start of a shared extent! */
	if (tmp.rc_startblock < agbno) {
		tmp.rc_blockcount -= (agbno - tmp.rc_startblock);
		tmp.rc_startblock = agbno;
	}

	*fbno = tmp.rc_startblock;
	*flen = min(tmp.rc_blockcount, agbno + aglen - *fbno);
	if (!find_end_of_shared)
		goto done;

	/* Otherwise, find the end of this shared extent */
	while (*fbno + *flen < agbno + aglen) {
		error = xfs_btree_increment(cur, 0, &have);
		if (error)
			goto out_error;
		if (!have)
			break;
		error = xfs_refcount_get_rec(cur, &tmp, &i);
		if (error)
			goto out_error;
		if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto out_error;
		}
		if (tmp.rc_startblock >= agbno + aglen ||
		    tmp.rc_startblock != *fbno + *flen)
			break;
		*flen = min(*flen + tmp.rc_blockcount, agbno + aglen - *fbno);
	}

done:
	trace_xfs_refcount_find_shared_result(cur->bc_mp,
			cur->bc_ag.agno, *fbno, *flen);

out_error:
	if (error)
		trace_xfs_refcount_find_shared_error(cur->bc_mp,
				cur->bc_ag.agno, error, _RET_IP_);
	return error;
}

/*
 * Recovering CoW Blocks After a Crash
 *
 * Due to the way that the copy on write mechanism works, there's a window of
 * opportunity in which we can lose track of allocated blocks during a crash.
 * Because CoW uses delayed allocation in the in-core CoW fork, writeback
 * causes blocks to be allocated and stored in the CoW fork.  The blocks are
 * no longer in the free space btree but are not otherwise recorded anywhere
 * until the write completes and the blocks are mapped into the file.  A crash
 * in between allocation and remapping results in the replacement blocks being
 * lost.  This situation is exacerbated by the CoW extent size hint because
 * allocations can hang around for long time.
 *
 * However, there is a place where we can record these allocations before they
 * become mappings -- the reference count btree.  The btree does not record
 * extents with refcount == 1, so we can record allocations with a refcount of
 * 1.  Blocks being used for CoW writeout cannot be shared, so there should be
 * no conflict with shared block records.  These mappings should be created
 * when we allocate blocks to the CoW fork and deleted when they're removed
 * from the CoW fork.
 *
 * Minor nit: records for in-progress CoW allocations and records for shared
 * extents must never be merged, to preserve the property that (except for CoW
 * allocations) there are no refcount btree entries with refcount == 1.  The
 * only time this could potentially happen is when unsharing a block that's
 * adjacent to CoW allocations, so we must be careful to avoid this.
 *
 * At mount time we recover lost CoW allocations by searching the refcount
 * btree for these refcount == 1 mappings.  These represent CoW allocations
 * that were in progress at the time the filesystem went down, so we can free
 * them to get the space back.
 *
 * This mechanism is superior to creating EFIs for unmapped CoW extents for
 * several reasons -- first, EFIs pin the tail of the log and would have to be
 * periodically relogged to avoid filling up the log.  Second, CoW completions
 * will have to file an EFD and create new EFIs for whatever remains in the
 * CoW fork; this partially takes care of (1) but extent-size reservations
 * will have to periodically relog even if there's no writeout in progress.
 * This can happen if the CoW extent size hint is set, which you really want.
 * Third, EFIs cannot currently be automatically relogged into newer
 * transactions to advance the log tail.  Fourth, stuffing the log full of
 * EFIs places an upper bound on the number of CoW allocations that can be
 * held filesystem-wide at any given time.  Recording them in the refcount
 * btree doesn't require us to maintain any state in memory and doesn't pin
 * the log.
 */
/*
 * Adjust the refcounts of CoW allocations.  These allocations are "magic"
 * in that they're not referenced anywhere else in the filesystem, so we
 * stash them in the refcount btree with a refcount of 1 until either file
 * remapping (or CoW cancellation) happens.
 */
STATIC int
xfs_refcount_adjust_cow_extents(
	struct xfs_btree_cur	*cur,
	xfs_agblock_t		agbno,
	xfs_extlen_t		aglen,
	enum xfs_refc_adjust_op	adj)
{
	struct xfs_refcount_irec	ext, tmp;
	int				error;
	int				found_rec, found_tmp;

	if (aglen == 0)
		return 0;

	/* Find any overlapping refcount records */
	error = xfs_refcount_lookup_ge(cur, agbno, &found_rec);
	if (error)
		goto out_error;
	error = xfs_refcount_get_rec(cur, &ext, &found_rec);
	if (error)
		goto out_error;
	if (!found_rec) {
		ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks +
				XFS_REFC_COW_START;
		ext.rc_blockcount = 0;
		ext.rc_refcount = 0;
	}

	switch (adj) {
	case XFS_REFCOUNT_ADJUST_COW_ALLOC:
		/* Adding a CoW reservation, there should be nothing here. */
		if (XFS_IS_CORRUPT(cur->bc_mp,
				   agbno + aglen > ext.rc_startblock)) {
			error = -EFSCORRUPTED;
			goto out_error;
		}

		tmp.rc_startblock = agbno;
		tmp.rc_blockcount = aglen;
		tmp.rc_refcount = 1;
		trace_xfs_refcount_modify_extent(cur->bc_mp,
				cur->bc_ag.agno, &tmp);

		error = xfs_refcount_insert(cur, &tmp,
				&found_tmp);
		if (error)
			goto out_error;
		if (XFS_IS_CORRUPT(cur->bc_mp, found_tmp != 1)) {
			error = -EFSCORRUPTED;
			goto out_error;
		}
		break;
	case XFS_REFCOUNT_ADJUST_COW_FREE:
		/* Removing a CoW reservation, there should be one extent. */
		if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_startblock != agbno)) {
			error = -EFSCORRUPTED;
			goto out_error;
		}
		if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount != aglen)) {
			error = -EFSCORRUPTED;
			goto out_error;
		}
		if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_refcount != 1)) {
			error = -EFSCORRUPTED;
			goto out_error;
		}

		ext.rc_refcount = 0;
		trace_xfs_refcount_modify_extent(cur->bc_mp,
				cur->bc_ag.agno, &ext);
		error = xfs_refcount_delete(cur, &found_rec);
		if (error)
			goto out_error;
		if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
			error = -EFSCORRUPTED;
			goto out_error;
		}
		break;
	default:
		ASSERT(0);
	}

	return error;
out_error:
	trace_xfs_refcount_modify_extent_error(cur->bc_mp,
			cur->bc_ag.agno, error, _RET_IP_);
	return error;
}

/*
 * Add or remove refcount btree entries for CoW reservations.
 */
STATIC int
xfs_refcount_adjust_cow(
	struct xfs_btree_cur	*cur,
	xfs_agblock_t		agbno,
	xfs_extlen_t		aglen,
	enum xfs_refc_adjust_op	adj)
{
	bool			shape_changed;
	int			error;

	agbno += XFS_REFC_COW_START;

	/*
	 * Ensure that no rcextents cross the boundary of the adjustment range.
	 */
	error = xfs_refcount_split_extent(cur, agbno, &shape_changed);
	if (error)
		goto out_error;

	error = xfs_refcount_split_extent(cur, agbno + aglen, &shape_changed);
	if (error)
		goto out_error;

	/*
	 * Try to merge with the left or right extents of the range.
	 */
	error = xfs_refcount_merge_extents(cur, &agbno, &aglen, adj,
			XFS_FIND_RCEXT_COW, &shape_changed);
	if (error)
		goto out_error;

	/* Now that we've taken care of the ends, adjust the middle extents */
	error = xfs_refcount_adjust_cow_extents(cur, agbno, aglen, adj);
	if (error)
		goto out_error;

	return 0;

out_error:
	trace_xfs_refcount_adjust_cow_error(cur->bc_mp, cur->bc_ag.agno,
			error, _RET_IP_);
	return error;
}

/*
 * Record a CoW allocation in the refcount btree.
 */
STATIC int
__xfs_refcount_cow_alloc(
	struct xfs_btree_cur	*rcur,
	xfs_agblock_t		agbno,
	xfs_extlen_t		aglen)
{
	trace_xfs_refcount_cow_increase(rcur->bc_mp, rcur->bc_ag.agno,
			agbno, aglen);

	/* Add refcount btree reservation */
	return xfs_refcount_adjust_cow(rcur, agbno, aglen,
			XFS_REFCOUNT_ADJUST_COW_ALLOC);
}

/*
 * Remove a CoW allocation from the refcount btree.
 */
STATIC int
__xfs_refcount_cow_free(
	struct xfs_btree_cur	*rcur,
	xfs_agblock_t		agbno,
	xfs_extlen_t		aglen)
{
	trace_xfs_refcount_cow_decrease(rcur->bc_mp, rcur->bc_ag.agno,
			agbno, aglen);

	/* Remove refcount btree reservation */
	return xfs_refcount_adjust_cow(rcur, agbno, aglen,
			XFS_REFCOUNT_ADJUST_COW_FREE);
}

/* Record a CoW staging extent in the refcount btree. */
void
xfs_refcount_alloc_cow_extent(
	struct xfs_trans		*tp,
	xfs_fsblock_t			fsb,
	xfs_extlen_t			len)
{
	struct xfs_mount		*mp = tp->t_mountp;

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

	__xfs_refcount_add(tp, XFS_REFCOUNT_ALLOC_COW, fsb, len);

	/* Add rmap entry */
	xfs_rmap_alloc_extent(tp, XFS_FSB_TO_AGNO(mp, fsb),
			XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW);
}

/* Forget a CoW staging event in the refcount btree. */
void
xfs_refcount_free_cow_extent(
	struct xfs_trans		*tp,
	xfs_fsblock_t			fsb,
	xfs_extlen_t			len)
{
	struct xfs_mount		*mp = tp->t_mountp;

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

	/* Remove rmap entry */
	xfs_rmap_free_extent(tp, XFS_FSB_TO_AGNO(mp, fsb),
			XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW);
	__xfs_refcount_add(tp, XFS_REFCOUNT_FREE_COW, fsb, len);
}

struct xfs_refcount_recovery {
	struct list_head		rr_list;
	struct xfs_refcount_irec	rr_rrec;
};

/* Stuff an extent on the recovery list. */
STATIC int
xfs_refcount_recover_extent(
	struct xfs_btree_cur		*cur,
	union xfs_btree_rec		*rec,
	void				*priv)
{
	struct list_head		*debris = priv;
	struct xfs_refcount_recovery	*rr;

	if (XFS_IS_CORRUPT(cur->bc_mp,
			   be32_to_cpu(rec->refc.rc_refcount) != 1))
		return -EFSCORRUPTED;

	rr = kmem_alloc(sizeof(struct xfs_refcount_recovery), 0);
	xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec);
	list_add_tail(&rr->rr_list, debris);

	return 0;
}

/* Find and remove leftover CoW reservations. */
int
xfs_refcount_recover_cow_leftovers(
	struct xfs_mount		*mp,
	xfs_agnumber_t			agno)
{
	struct xfs_trans		*tp;
	struct xfs_btree_cur		*cur;
	struct xfs_buf			*agbp;
	struct xfs_refcount_recovery	*rr, *n;
	struct list_head		debris;
	union xfs_btree_irec		low;
	union xfs_btree_irec		high;
	xfs_fsblock_t			fsb;
	xfs_agblock_t			agbno;
	int				error;

	if (mp->m_sb.sb_agblocks >= XFS_REFC_COW_START)
		return -EOPNOTSUPP;

	INIT_LIST_HEAD(&debris);

	/*
	 * In this first part, we use an empty transaction to gather up
	 * all the leftover CoW extents so that we can subsequently
	 * delete them.  The empty transaction is used to avoid
	 * a buffer lock deadlock if there happens to be a loop in the
	 * refcountbt because we're allowed to re-grab a buffer that is
	 * already attached to our transaction.  When we're done
	 * recording the CoW debris we cancel the (empty) transaction
	 * and everything goes away cleanly.
	 */
	error = xfs_trans_alloc_empty(mp, &tp);
	if (error)
		return error;

	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
	if (error)
		goto out_trans;
	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno);

	/* Find all the leftover CoW staging extents. */
	memset(&low, 0, sizeof(low));
	memset(&high, 0, sizeof(high));
	low.rc.rc_startblock = XFS_REFC_COW_START;
	high.rc.rc_startblock = -1U;
	error = xfs_btree_query_range(cur, &low, &high,
			xfs_refcount_recover_extent, &debris);
	xfs_btree_del_cursor(cur, error);
	xfs_trans_brelse(tp, agbp);
	xfs_trans_cancel(tp);
	if (error)
		goto out_free;

	/* Now iterate the list to free the leftovers */
	list_for_each_entry_safe(rr, n, &debris, rr_list) {
		/* Set up transaction. */
		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, 0, &tp);
		if (error)
			goto out_free;

		trace_xfs_refcount_recover_extent(mp, agno, &rr->rr_rrec);

		/* Free the orphan record */
		agbno = rr->rr_rrec.rc_startblock - XFS_REFC_COW_START;
		fsb = XFS_AGB_TO_FSB(mp, agno, agbno);
		xfs_refcount_free_cow_extent(tp, fsb,
				rr->rr_rrec.rc_blockcount);

		/* Free the block. */
		xfs_bmap_add_free(tp, fsb, rr->rr_rrec.rc_blockcount, NULL);

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

		list_del(&rr->rr_list);
		kmem_free(rr);
	}

	return error;
out_trans:
	xfs_trans_cancel(tp);
out_free:
	/* Free the leftover list */
	list_for_each_entry_safe(rr, n, &debris, rr_list) {
		list_del(&rr->rr_list);
		kmem_free(rr);
	}
	return error;
}

/* Is there a record covering a given extent? */
int
xfs_refcount_has_record(
	struct xfs_btree_cur	*cur,
	xfs_agblock_t		bno,
	xfs_extlen_t		len,
	bool			*exists)
{
	union xfs_btree_irec	low;
	union xfs_btree_irec	high;

	memset(&low, 0, sizeof(low));
	low.rc.rc_startblock = bno;
	memset(&high, 0xFF, sizeof(high));
	high.rc.rc_startblock = bno + len - 1;

	return xfs_btree_has_record(cur, &low, &high, exists);
}