aboutsummaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_bmap_util.c
blob: 5d263dfdb3bcc60ca30708622397e42de9fbaeac (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
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
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2006 Silicon Graphics, Inc.
 * Copyright (c) 2012 Red Hat, Inc.
 * All Rights Reserved.
 */
#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_bit.h"
#include "xfs_mount.h"
#include "xfs_da_format.h"
#include "xfs_defer.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_trans.h"
#include "xfs_extfree_item.h"
#include "xfs_alloc.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_bmap_btree.h"
#include "xfs_rtalloc.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_trans_space.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_log.h"
#include "xfs_rmap_btree.h"
#include "xfs_iomap.h"
#include "xfs_reflink.h"
#include "xfs_refcount.h"

/* Kernel only BMAP related definitions and functions */

/*
 * Convert the given file system block to a disk block.  We have to treat it
 * differently based on whether the file is a real time file or not, because the
 * bmap code does.
 */
xfs_daddr_t
xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
{
	return (XFS_IS_REALTIME_INODE(ip) ? \
		 (xfs_daddr_t)XFS_FSB_TO_BB((ip)->i_mount, (fsb)) : \
		 XFS_FSB_TO_DADDR((ip)->i_mount, (fsb)));
}

/*
 * Routine to zero an extent on disk allocated to the specific inode.
 *
 * The VFS functions take a linearised filesystem block offset, so we have to
 * convert the sparse xfs fsb to the right format first.
 * VFS types are real funky, too.
 */
int
xfs_zero_extent(
	struct xfs_inode *ip,
	xfs_fsblock_t	start_fsb,
	xfs_off_t	count_fsb)
{
	struct xfs_mount *mp = ip->i_mount;
	xfs_daddr_t	sector = xfs_fsb_to_db(ip, start_fsb);
	sector_t	block = XFS_BB_TO_FSBT(mp, sector);

	return blkdev_issue_zeroout(xfs_find_bdev_for_inode(VFS_I(ip)),
		block << (mp->m_super->s_blocksize_bits - 9),
		count_fsb << (mp->m_super->s_blocksize_bits - 9),
		GFP_NOFS, 0);
}

#ifdef CONFIG_XFS_RT
int
xfs_bmap_rtalloc(
	struct xfs_bmalloca	*ap)	/* bmap alloc argument struct */
{
	int		error;		/* error return value */
	xfs_mount_t	*mp;		/* mount point structure */
	xfs_extlen_t	prod = 0;	/* product factor for allocators */
	xfs_extlen_t	mod = 0;	/* product factor for allocators */
	xfs_extlen_t	ralen = 0;	/* realtime allocation length */
	xfs_extlen_t	align;		/* minimum allocation alignment */
	xfs_rtblock_t	rtb;

	mp = ap->ip->i_mount;
	align = xfs_get_extsz_hint(ap->ip);
	prod = align / mp->m_sb.sb_rextsize;
	error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
					align, 1, ap->eof, 0,
					ap->conv, &ap->offset, &ap->length);
	if (error)
		return error;
	ASSERT(ap->length);
	ASSERT(ap->length % mp->m_sb.sb_rextsize == 0);

	/*
	 * If the offset & length are not perfectly aligned
	 * then kill prod, it will just get us in trouble.
	 */
	div_u64_rem(ap->offset, align, &mod);
	if (mod || ap->length % align)
		prod = 1;
	/*
	 * Set ralen to be the actual requested length in rtextents.
	 */
	ralen = ap->length / mp->m_sb.sb_rextsize;
	/*
	 * If the old value was close enough to MAXEXTLEN that
	 * we rounded up to it, cut it back so it's valid again.
	 * Note that if it's a really large request (bigger than
	 * MAXEXTLEN), we don't hear about that number, and can't
	 * adjust the starting point to match it.
	 */
	if (ralen * mp->m_sb.sb_rextsize >= MAXEXTLEN)
		ralen = MAXEXTLEN / mp->m_sb.sb_rextsize;

	/*
	 * Lock out modifications to both the RT bitmap and summary inodes
	 */
	xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL|XFS_ILOCK_RTBITMAP);
	xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL);
	xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL|XFS_ILOCK_RTSUM);
	xfs_trans_ijoin(ap->tp, mp->m_rsumip, XFS_ILOCK_EXCL);

	/*
	 * If it's an allocation to an empty file at offset 0,
	 * pick an extent that will space things out in the rt area.
	 */
	if (ap->eof && ap->offset == 0) {
		xfs_rtblock_t uninitialized_var(rtx); /* realtime extent no */

		error = xfs_rtpick_extent(mp, ap->tp, ralen, &rtx);
		if (error)
			return error;
		ap->blkno = rtx * mp->m_sb.sb_rextsize;
	} else {
		ap->blkno = 0;
	}

	xfs_bmap_adjacent(ap);

	/*
	 * Realtime allocation, done through xfs_rtallocate_extent.
	 */
	do_div(ap->blkno, mp->m_sb.sb_rextsize);
	rtb = ap->blkno;
	ap->length = ralen;
	error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, ap->length,
				&ralen, ap->wasdel, prod, &rtb);
	if (error)
		return error;

	ap->blkno = rtb;
	if (ap->blkno != NULLFSBLOCK) {
		ap->blkno *= mp->m_sb.sb_rextsize;
		ralen *= mp->m_sb.sb_rextsize;
		ap->length = ralen;
		ap->ip->i_d.di_nblocks += ralen;
		xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
		if (ap->wasdel)
			ap->ip->i_delayed_blks -= ralen;
		/*
		 * Adjust the disk quota also. This was reserved
		 * earlier.
		 */
		xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
			ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT :
					XFS_TRANS_DQ_RTBCOUNT, (long) ralen);

		/* Zero the extent if we were asked to do so */
		if (ap->datatype & XFS_ALLOC_USERDATA_ZERO) {
			error = xfs_zero_extent(ap->ip, ap->blkno, ap->length);
			if (error)
				return error;
		}
	} else {
		ap->length = 0;
	}
	return 0;
}
#endif /* CONFIG_XFS_RT */

/*
 * Check if the endoff is outside the last extent. If so the caller will grow
 * the allocation to a stripe unit boundary.  All offsets are considered outside
 * the end of file for an empty fork, so 1 is returned in *eof in that case.
 */
int
xfs_bmap_eof(
	struct xfs_inode	*ip,
	xfs_fileoff_t		endoff,
	int			whichfork,
	int			*eof)
{
	struct xfs_bmbt_irec	rec;
	int			error;

	error = xfs_bmap_last_extent(NULL, ip, whichfork, &rec, eof);
	if (error || *eof)
		return error;

	*eof = endoff >= rec.br_startoff + rec.br_blockcount;
	return 0;
}

/*
 * Extent tree block counting routines.
 */

/*
 * Count leaf blocks given a range of extent records.  Delayed allocation
 * extents are not counted towards the totals.
 */
xfs_extnum_t
xfs_bmap_count_leaves(
	struct xfs_ifork	*ifp,
	xfs_filblks_t		*count)
{
	struct xfs_iext_cursor	icur;
	struct xfs_bmbt_irec	got;
	xfs_extnum_t		numrecs = 0;

	for_each_xfs_iext(ifp, &icur, &got) {
		if (!isnullstartblock(got.br_startblock)) {
			*count += got.br_blockcount;
			numrecs++;
		}
	}

	return numrecs;
}

/*
 * Count leaf blocks given a range of extent records originally
 * in btree format.
 */
STATIC void
xfs_bmap_disk_count_leaves(
	struct xfs_mount	*mp,
	struct xfs_btree_block	*block,
	int			numrecs,
	xfs_filblks_t		*count)
{
	int		b;
	xfs_bmbt_rec_t	*frp;

	for (b = 1; b <= numrecs; b++) {
		frp = XFS_BMBT_REC_ADDR(mp, block, b);
		*count += xfs_bmbt_disk_get_blockcount(frp);
	}
}

/*
 * Recursively walks each level of a btree
 * to count total fsblocks in use.
 */
STATIC int
xfs_bmap_count_tree(
	struct xfs_mount	*mp,
	struct xfs_trans	*tp,
	struct xfs_ifork	*ifp,
	xfs_fsblock_t		blockno,
	int			levelin,
	xfs_extnum_t		*nextents,
	xfs_filblks_t		*count)
{
	int			error;
	struct xfs_buf		*bp, *nbp;
	int			level = levelin;
	__be64			*pp;
	xfs_fsblock_t           bno = blockno;
	xfs_fsblock_t		nextbno;
	struct xfs_btree_block	*block, *nextblock;
	int			numrecs;

	error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp, XFS_BMAP_BTREE_REF,
						&xfs_bmbt_buf_ops);
	if (error)
		return error;
	*count += 1;
	block = XFS_BUF_TO_BLOCK(bp);

	if (--level) {
		/* Not at node above leaves, count this level of nodes */
		nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
		while (nextbno != NULLFSBLOCK) {
			error = xfs_btree_read_bufl(mp, tp, nextbno, 0, &nbp,
						XFS_BMAP_BTREE_REF,
						&xfs_bmbt_buf_ops);
			if (error)
				return error;
			*count += 1;
			nextblock = XFS_BUF_TO_BLOCK(nbp);
			nextbno = be64_to_cpu(nextblock->bb_u.l.bb_rightsib);
			xfs_trans_brelse(tp, nbp);
		}

		/* Dive to the next level */
		pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
		bno = be64_to_cpu(*pp);
		error = xfs_bmap_count_tree(mp, tp, ifp, bno, level, nextents,
				count);
		if (error) {
			xfs_trans_brelse(tp, bp);
			XFS_ERROR_REPORT("xfs_bmap_count_tree(1)",
					 XFS_ERRLEVEL_LOW, mp);
			return -EFSCORRUPTED;
		}
		xfs_trans_brelse(tp, bp);
	} else {
		/* count all level 1 nodes and their leaves */
		for (;;) {
			nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
			numrecs = be16_to_cpu(block->bb_numrecs);
			(*nextents) += numrecs;
			xfs_bmap_disk_count_leaves(mp, block, numrecs, count);
			xfs_trans_brelse(tp, bp);
			if (nextbno == NULLFSBLOCK)
				break;
			bno = nextbno;
			error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp,
						XFS_BMAP_BTREE_REF,
						&xfs_bmbt_buf_ops);
			if (error)
				return error;
			*count += 1;
			block = XFS_BUF_TO_BLOCK(bp);
		}
	}
	return 0;
}

/*
 * Count fsblocks of the given fork.  Delayed allocation extents are
 * not counted towards the totals.
 */
int
xfs_bmap_count_blocks(
	struct xfs_trans	*tp,
	struct xfs_inode	*ip,
	int			whichfork,
	xfs_extnum_t		*nextents,
	xfs_filblks_t		*count)
{
	struct xfs_mount	*mp;	/* file system mount structure */
	__be64			*pp;	/* pointer to block address */
	struct xfs_btree_block	*block;	/* current btree block */
	struct xfs_ifork	*ifp;	/* fork structure */
	xfs_fsblock_t		bno;	/* block # of "block" */
	int			level;	/* btree level, for checking */
	int			error;

	bno = NULLFSBLOCK;
	mp = ip->i_mount;
	*nextents = 0;
	*count = 0;
	ifp = XFS_IFORK_PTR(ip, whichfork);
	if (!ifp)
		return 0;

	switch (XFS_IFORK_FORMAT(ip, whichfork)) {
	case XFS_DINODE_FMT_EXTENTS:
		*nextents = xfs_bmap_count_leaves(ifp, count);
		return 0;
	case XFS_DINODE_FMT_BTREE:
		if (!(ifp->if_flags & XFS_IFEXTENTS)) {
			error = xfs_iread_extents(tp, ip, whichfork);
			if (error)
				return error;
		}

		/*
		 * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
		 */
		block = ifp->if_broot;
		level = be16_to_cpu(block->bb_level);
		ASSERT(level > 0);
		pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
		bno = be64_to_cpu(*pp);
		ASSERT(bno != NULLFSBLOCK);
		ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
		ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);

		error = xfs_bmap_count_tree(mp, tp, ifp, bno, level,
				nextents, count);
		if (error) {
			XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)",
					XFS_ERRLEVEL_LOW, mp);
			return -EFSCORRUPTED;
		}
		return 0;
	}

	return 0;
}

static int
xfs_getbmap_report_one(
	struct xfs_inode	*ip,
	struct getbmapx		*bmv,
	struct kgetbmap		*out,
	int64_t			bmv_end,
	struct xfs_bmbt_irec	*got)
{
	struct kgetbmap		*p = out + bmv->bmv_entries;
	bool			shared = false;
	int			error;

	error = xfs_reflink_trim_around_shared(ip, got, &shared);
	if (error)
		return error;

	if (isnullstartblock(got->br_startblock) ||
	    got->br_startblock == DELAYSTARTBLOCK) {
		/*
		 * Delalloc extents that start beyond EOF can occur due to
		 * speculative EOF allocation when the delalloc extent is larger
		 * than the largest freespace extent at conversion time.  These
		 * extents cannot be converted by data writeback, so can exist
		 * here even if we are not supposed to be finding delalloc
		 * extents.
		 */
		if (got->br_startoff < XFS_B_TO_FSB(ip->i_mount, XFS_ISIZE(ip)))
			ASSERT((bmv->bmv_iflags & BMV_IF_DELALLOC) != 0);

		p->bmv_oflags |= BMV_OF_DELALLOC;
		p->bmv_block = -2;
	} else {
		p->bmv_block = xfs_fsb_to_db(ip, got->br_startblock);
	}

	if (got->br_state == XFS_EXT_UNWRITTEN &&
	    (bmv->bmv_iflags & BMV_IF_PREALLOC))
		p->bmv_oflags |= BMV_OF_PREALLOC;

	if (shared)
		p->bmv_oflags |= BMV_OF_SHARED;

	p->bmv_offset = XFS_FSB_TO_BB(ip->i_mount, got->br_startoff);
	p->bmv_length = XFS_FSB_TO_BB(ip->i_mount, got->br_blockcount);

	bmv->bmv_offset = p->bmv_offset + p->bmv_length;
	bmv->bmv_length = max(0LL, bmv_end - bmv->bmv_offset);
	bmv->bmv_entries++;
	return 0;
}

static void
xfs_getbmap_report_hole(
	struct xfs_inode	*ip,
	struct getbmapx		*bmv,
	struct kgetbmap		*out,
	int64_t			bmv_end,
	xfs_fileoff_t		bno,
	xfs_fileoff_t		end)
{
	struct kgetbmap		*p = out + bmv->bmv_entries;

	if (bmv->bmv_iflags & BMV_IF_NO_HOLES)
		return;

	p->bmv_block = -1;
	p->bmv_offset = XFS_FSB_TO_BB(ip->i_mount, bno);
	p->bmv_length = XFS_FSB_TO_BB(ip->i_mount, end - bno);

	bmv->bmv_offset = p->bmv_offset + p->bmv_length;
	bmv->bmv_length = max(0LL, bmv_end - bmv->bmv_offset);
	bmv->bmv_entries++;
}

static inline bool
xfs_getbmap_full(
	struct getbmapx		*bmv)
{
	return bmv->bmv_length == 0 || bmv->bmv_entries >= bmv->bmv_count - 1;
}

static bool
xfs_getbmap_next_rec(
	struct xfs_bmbt_irec	*rec,
	xfs_fileoff_t		total_end)
{
	xfs_fileoff_t		end = rec->br_startoff + rec->br_blockcount;

	if (end == total_end)
		return false;

	rec->br_startoff += rec->br_blockcount;
	if (!isnullstartblock(rec->br_startblock) &&
	    rec->br_startblock != DELAYSTARTBLOCK)
		rec->br_startblock += rec->br_blockcount;
	rec->br_blockcount = total_end - end;
	return true;
}

/*
 * Get inode's extents as described in bmv, and format for output.
 * Calls formatter to fill the user's buffer until all extents
 * are mapped, until the passed-in bmv->bmv_count slots have
 * been filled, or until the formatter short-circuits the loop,
 * if it is tracking filled-in extents on its own.
 */
int						/* error code */
xfs_getbmap(
	struct xfs_inode	*ip,
	struct getbmapx		*bmv,		/* user bmap structure */
	struct kgetbmap		*out)
{
	struct xfs_mount	*mp = ip->i_mount;
	int			iflags = bmv->bmv_iflags;
	int			whichfork, lock, error = 0;
	int64_t			bmv_end, max_len;
	xfs_fileoff_t		bno, first_bno;
	struct xfs_ifork	*ifp;
	struct xfs_bmbt_irec	got, rec;
	xfs_filblks_t		len;
	struct xfs_iext_cursor	icur;

	if (bmv->bmv_iflags & ~BMV_IF_VALID)
		return -EINVAL;
#ifndef DEBUG
	/* Only allow CoW fork queries if we're debugging. */
	if (iflags & BMV_IF_COWFORK)
		return -EINVAL;
#endif
	if ((iflags & BMV_IF_ATTRFORK) && (iflags & BMV_IF_COWFORK))
		return -EINVAL;

	if (bmv->bmv_length < -1)
		return -EINVAL;
	bmv->bmv_entries = 0;
	if (bmv->bmv_length == 0)
		return 0;

	if (iflags & BMV_IF_ATTRFORK)
		whichfork = XFS_ATTR_FORK;
	else if (iflags & BMV_IF_COWFORK)
		whichfork = XFS_COW_FORK;
	else
		whichfork = XFS_DATA_FORK;
	ifp = XFS_IFORK_PTR(ip, whichfork);

	xfs_ilock(ip, XFS_IOLOCK_SHARED);
	switch (whichfork) {
	case XFS_ATTR_FORK:
		if (!XFS_IFORK_Q(ip))
			goto out_unlock_iolock;

		max_len = 1LL << 32;
		lock = xfs_ilock_attr_map_shared(ip);
		break;
	case XFS_COW_FORK:
		/* No CoW fork? Just return */
		if (!ifp)
			goto out_unlock_iolock;

		if (xfs_get_cowextsz_hint(ip))
			max_len = mp->m_super->s_maxbytes;
		else
			max_len = XFS_ISIZE(ip);

		lock = XFS_ILOCK_SHARED;
		xfs_ilock(ip, lock);
		break;
	case XFS_DATA_FORK:
		if (!(iflags & BMV_IF_DELALLOC) &&
		    (ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_d.di_size)) {
			error = filemap_write_and_wait(VFS_I(ip)->i_mapping);
			if (error)
				goto out_unlock_iolock;

			/*
			 * Even after flushing the inode, there can still be
			 * delalloc blocks on the inode beyond EOF due to
			 * speculative preallocation.  These are not removed
			 * until the release function is called or the inode
			 * is inactivated.  Hence we cannot assert here that
			 * ip->i_delayed_blks == 0.
			 */
		}

		if (xfs_get_extsz_hint(ip) ||
		    (ip->i_d.di_flags &
		     (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)))
			max_len = mp->m_super->s_maxbytes;
		else
			max_len = XFS_ISIZE(ip);

		lock = xfs_ilock_data_map_shared(ip);
		break;
	}

	switch (XFS_IFORK_FORMAT(ip, whichfork)) {
	case XFS_DINODE_FMT_EXTENTS:
	case XFS_DINODE_FMT_BTREE:
		break;
	case XFS_DINODE_FMT_LOCAL:
		/* Local format inode forks report no extents. */
		goto out_unlock_ilock;
	default:
		error = -EINVAL;
		goto out_unlock_ilock;
	}

	if (bmv->bmv_length == -1) {
		max_len = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, max_len));
		bmv->bmv_length = max(0LL, max_len - bmv->bmv_offset);
	}

	bmv_end = bmv->bmv_offset + bmv->bmv_length;

	first_bno = bno = XFS_BB_TO_FSBT(mp, bmv->bmv_offset);
	len = XFS_BB_TO_FSB(mp, bmv->bmv_length);

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

	if (!xfs_iext_lookup_extent(ip, ifp, bno, &icur, &got)) {
		/*
		 * Report a whole-file hole if the delalloc flag is set to
		 * stay compatible with the old implementation.
		 */
		if (iflags & BMV_IF_DELALLOC)
			xfs_getbmap_report_hole(ip, bmv, out, bmv_end, bno,
					XFS_B_TO_FSB(mp, XFS_ISIZE(ip)));
		goto out_unlock_ilock;
	}

	while (!xfs_getbmap_full(bmv)) {
		xfs_trim_extent(&got, first_bno, len);

		/*
		 * Report an entry for a hole if this extent doesn't directly
		 * follow the previous one.
		 */
		if (got.br_startoff > bno) {
			xfs_getbmap_report_hole(ip, bmv, out, bmv_end, bno,
					got.br_startoff);
			if (xfs_getbmap_full(bmv))
				break;
		}

		/*
		 * In order to report shared extents accurately, we report each
		 * distinct shared / unshared part of a single bmbt record with
		 * an individual getbmapx record.
		 */
		bno = got.br_startoff + got.br_blockcount;
		rec = got;
		do {
			error = xfs_getbmap_report_one(ip, bmv, out, bmv_end,
					&rec);
			if (error || xfs_getbmap_full(bmv))
				goto out_unlock_ilock;
		} while (xfs_getbmap_next_rec(&rec, bno));

		if (!xfs_iext_next_extent(ifp, &icur, &got)) {
			xfs_fileoff_t	end = XFS_B_TO_FSB(mp, XFS_ISIZE(ip));

			out[bmv->bmv_entries - 1].bmv_oflags |= BMV_OF_LAST;

			if (whichfork != XFS_ATTR_FORK && bno < end &&
			    !xfs_getbmap_full(bmv)) {
				xfs_getbmap_report_hole(ip, bmv, out, bmv_end,
						bno, end);
			}
			break;
		}

		if (bno >= first_bno + len)
			break;
	}

out_unlock_ilock:
	xfs_iunlock(ip, lock);
out_unlock_iolock:
	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
	return error;
}

/*
 * Dead simple method of punching delalyed allocation blocks from a range in
 * the inode.  This will always punch out both the start and end blocks, even
 * if the ranges only partially overlap them, so it is up to the caller to
 * ensure that partial blocks are not passed in.
 */
int
xfs_bmap_punch_delalloc_range(
	struct xfs_inode	*ip,
	xfs_fileoff_t		start_fsb,
	xfs_fileoff_t		length)
{
	struct xfs_ifork	*ifp = &ip->i_df;
	xfs_fileoff_t		end_fsb = start_fsb + length;
	struct xfs_bmbt_irec	got, del;
	struct xfs_iext_cursor	icur;
	int			error = 0;

	ASSERT(ifp->if_flags & XFS_IFEXTENTS);

	xfs_ilock(ip, XFS_ILOCK_EXCL);
	if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
		goto out_unlock;

	while (got.br_startoff + got.br_blockcount > start_fsb) {
		del = got;
		xfs_trim_extent(&del, start_fsb, length);

		/*
		 * A delete can push the cursor forward. Step back to the
		 * previous extent on non-delalloc or extents outside the
		 * target range.
		 */
		if (!del.br_blockcount ||
		    !isnullstartblock(del.br_startblock)) {
			if (!xfs_iext_prev_extent(ifp, &icur, &got))
				break;
			continue;
		}

		error = xfs_bmap_del_extent_delay(ip, XFS_DATA_FORK, &icur,
						  &got, &del);
		if (error || !xfs_iext_get_extent(ifp, &icur, &got))
			break;
	}

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

/*
 * Test whether it is appropriate to check an inode for and free post EOF
 * blocks. The 'force' parameter determines whether we should also consider
 * regular files that are marked preallocated or append-only.
 */
bool
xfs_can_free_eofblocks(struct xfs_inode *ip, bool force)
{
	/* prealloc/delalloc exists only on regular files */
	if (!S_ISREG(VFS_I(ip)->i_mode))
		return false;

	/*
	 * Zero sized files with no cached pages and delalloc blocks will not
	 * have speculative prealloc/delalloc blocks to remove.
	 */
	if (VFS_I(ip)->i_size == 0 &&
	    VFS_I(ip)->i_mapping->nrpages == 0 &&
	    ip->i_delayed_blks == 0)
		return false;

	/* If we haven't read in the extent list, then don't do it now. */
	if (!(ip->i_df.if_flags & XFS_IFEXTENTS))
		return false;

	/*
	 * Do not free real preallocated or append-only files unless the file
	 * has delalloc blocks and we are forced to remove them.
	 */
	if (ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND))
		if (!force || ip->i_delayed_blks == 0)
			return false;

	return true;
}

/*
 * This is called to free any blocks beyond eof. The caller must hold
 * IOLOCK_EXCL unless we are in the inode reclaim path and have the only
 * reference to the inode.
 */
int
xfs_free_eofblocks(
	struct xfs_inode	*ip)
{
	struct xfs_trans	*tp;
	int			error;
	xfs_fileoff_t		end_fsb;
	xfs_fileoff_t		last_fsb;
	xfs_filblks_t		map_len;
	int			nimaps;
	struct xfs_bmbt_irec	imap;
	struct xfs_mount	*mp = ip->i_mount;

	/*
	 * Figure out if there are any blocks beyond the end
	 * of the file.  If not, then there is nothing to do.
	 */
	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
	last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
	if (last_fsb <= end_fsb)
		return 0;
	map_len = last_fsb - end_fsb;

	nimaps = 1;
	xfs_ilock(ip, XFS_ILOCK_SHARED);
	error = xfs_bmapi_read(ip, end_fsb, map_len, &imap, &nimaps, 0);
	xfs_iunlock(ip, XFS_ILOCK_SHARED);

	/*
	 * If there are blocks after the end of file, truncate the file to its
	 * current size to free them up.
	 */
	if (!error && (nimaps != 0) &&
	    (imap.br_startblock != HOLESTARTBLOCK ||
	     ip->i_delayed_blks)) {
		/*
		 * Attach the dquots to the inode up front.
		 */
		error = xfs_qm_dqattach(ip);
		if (error)
			return error;

		/* wait on dio to ensure i_size has settled */
		inode_dio_wait(VFS_I(ip));

		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0,
				&tp);
		if (error) {
			ASSERT(XFS_FORCED_SHUTDOWN(mp));
			return error;
		}

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

		/*
		 * Do not update the on-disk file size.  If we update the
		 * on-disk file size and then the system crashes before the
		 * contents of the file are flushed to disk then the files
		 * may be full of holes (ie NULL files bug).
		 */
		error = xfs_itruncate_extents_flags(&tp, ip, XFS_DATA_FORK,
					XFS_ISIZE(ip), XFS_BMAPI_NODISCARD);
		if (error) {
			/*
			 * If we get an error at this point we simply don't
			 * bother truncating the file.
			 */
			xfs_trans_cancel(tp);
		} else {
			error = xfs_trans_commit(tp);
			if (!error)
				xfs_inode_clear_eofblocks_tag(ip);
		}

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

int
xfs_alloc_file_space(
	struct xfs_inode	*ip,
	xfs_off_t		offset,
	xfs_off_t		len,
	int			alloc_type)
{
	xfs_mount_t		*mp = ip->i_mount;
	xfs_off_t		count;
	xfs_filblks_t		allocated_fsb;
	xfs_filblks_t		allocatesize_fsb;
	xfs_extlen_t		extsz, temp;
	xfs_fileoff_t		startoffset_fsb;
	int			nimaps;
	int			quota_flag;
	int			rt;
	xfs_trans_t		*tp;
	xfs_bmbt_irec_t		imaps[1], *imapp;
	uint			qblocks, resblks, resrtextents;
	int			error;

	trace_xfs_alloc_file_space(ip);

	if (XFS_FORCED_SHUTDOWN(mp))
		return -EIO;

	error = xfs_qm_dqattach(ip);
	if (error)
		return error;

	if (len <= 0)
		return -EINVAL;

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

	count = len;
	imapp = &imaps[0];
	nimaps = 1;
	startoffset_fsb	= XFS_B_TO_FSBT(mp, offset);
	allocatesize_fsb = XFS_B_TO_FSB(mp, count);

	/*
	 * Allocate file space until done or until there is an error
	 */
	while (allocatesize_fsb && !error) {
		xfs_fileoff_t	s, e;

		/*
		 * Determine space reservations for data/realtime.
		 */
		if (unlikely(extsz)) {
			s = startoffset_fsb;
			do_div(s, extsz);
			s *= extsz;
			e = startoffset_fsb + allocatesize_fsb;
			div_u64_rem(startoffset_fsb, extsz, &temp);
			if (temp)
				e += temp;
			div_u64_rem(e, extsz, &temp);
			if (temp)
				e += extsz - temp;
		} else {
			s = 0;
			e = allocatesize_fsb;
		}

		/*
		 * The transaction reservation is limited to a 32-bit block
		 * count, hence we need to limit the number of blocks we are
		 * trying to reserve to avoid an overflow. We can't allocate
		 * more than @nimaps extents, and an extent is limited on disk
		 * to MAXEXTLEN (21 bits), so use that to enforce the limit.
		 */
		resblks = min_t(xfs_fileoff_t, (e - s), (MAXEXTLEN * nimaps));
		if (unlikely(rt)) {
			resrtextents = qblocks = resblks;
			resrtextents /= mp->m_sb.sb_rextsize;
			resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
			quota_flag = XFS_QMOPT_RES_RTBLKS;
		} else {
			resrtextents = 0;
			resblks = qblocks = XFS_DIOSTRAT_SPACE_RES(mp, resblks);
			quota_flag = XFS_QMOPT_RES_REGBLKS;
		}

		/*
		 * Allocate and setup the transaction.
		 */
		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks,
				resrtextents, 0, &tp);

		/*
		 * Check for running out of space
		 */
		if (error) {
			/*
			 * Free the transaction structure.
			 */
			ASSERT(error == -ENOSPC || XFS_FORCED_SHUTDOWN(mp));
			break;
		}
		xfs_ilock(ip, XFS_ILOCK_EXCL);
		error = xfs_trans_reserve_quota_nblks(tp, ip, qblocks,
						      0, quota_flag);
		if (error)
			goto error1;

		xfs_trans_ijoin(tp, ip, 0);

		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
					allocatesize_fsb, alloc_type, resblks,
					imapp, &nimaps);
		if (error)
			goto error0;

		/*
		 * Complete the transaction
		 */
		error = xfs_trans_commit(tp);
		xfs_iunlock(ip, XFS_ILOCK_EXCL);
		if (error)
			break;

		allocated_fsb = imapp->br_blockcount;

		if (nimaps == 0) {
			error = -ENOSPC;
			break;
		}

		startoffset_fsb += allocated_fsb;
		allocatesize_fsb -= allocated_fsb;
	}

	return error;

error0:	/* unlock inode, unreserve quota blocks, cancel trans */
	xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);

error1:	/* Just cancel transaction */
	xfs_trans_cancel(tp);
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	return error;
}

static int
xfs_unmap_extent(
	struct xfs_inode	*ip,
	xfs_fileoff_t		startoffset_fsb,
	xfs_filblks_t		len_fsb,
	int			*done)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp;
	uint			resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
	int			error;

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
	if (error) {
		ASSERT(error == -ENOSPC || XFS_FORCED_SHUTDOWN(mp));
		return error;
	}

	xfs_ilock(ip, XFS_ILOCK_EXCL);
	error = xfs_trans_reserve_quota(tp, mp, ip->i_udquot, ip->i_gdquot,
			ip->i_pdquot, resblks, 0, XFS_QMOPT_RES_REGBLKS);
	if (error)
		goto out_trans_cancel;

	xfs_trans_ijoin(tp, ip, 0);

	error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, done);
	if (error)
		goto out_trans_cancel;

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

out_trans_cancel:
	xfs_trans_cancel(tp);
	goto out_unlock;
}

static int
xfs_flush_unmap_range(
	struct xfs_inode	*ip,
	xfs_off_t		offset,
	xfs_off_t		len)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct inode		*inode = VFS_I(ip);
	xfs_off_t		rounding, start, end;
	int			error;

	/* wait for the completion of any pending DIOs */
	inode_dio_wait(inode);

	rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_SIZE);
	start = round_down(offset, rounding);
	end = round_up(offset + len, rounding) - 1;

	error = filemap_write_and_wait_range(inode->i_mapping, start, end);
	if (error)
		return error;
	truncate_pagecache_range(inode, start, end);
	return 0;
}

int
xfs_free_file_space(
	struct xfs_inode	*ip,
	xfs_off_t		offset,
	xfs_off_t		len)
{
	struct xfs_mount	*mp = ip->i_mount;
	xfs_fileoff_t		startoffset_fsb;
	xfs_fileoff_t		endoffset_fsb;
	int			done = 0, error;

	trace_xfs_free_file_space(ip);

	error = xfs_qm_dqattach(ip);
	if (error)
		return error;

	if (len <= 0)	/* if nothing being freed */
		return 0;

	error = xfs_flush_unmap_range(ip, offset, len);
	if (error)
		return error;

	startoffset_fsb = XFS_B_TO_FSB(mp, offset);
	endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);

	/*
	 * Need to zero the stuff we're not freeing, on disk.
	 */
	if (endoffset_fsb > startoffset_fsb) {
		while (!done) {
			error = xfs_unmap_extent(ip, startoffset_fsb,
					endoffset_fsb - startoffset_fsb, &done);
			if (error)
				return error;
		}
	}

	/*
	 * Now that we've unmap all full blocks we'll have to zero out any
	 * partial block at the beginning and/or end.  iomap_zero_range is smart
	 * enough to skip any holes, including those we just created, but we
	 * must take care not to zero beyond EOF and enlarge i_size.
	 */
	if (offset >= XFS_ISIZE(ip))
		return 0;
	if (offset + len > XFS_ISIZE(ip))
		len = XFS_ISIZE(ip) - offset;
	error = iomap_zero_range(VFS_I(ip), offset, len, NULL, &xfs_iomap_ops);
	if (error)
		return error;

	/*
	 * If we zeroed right up to EOF and EOF straddles a page boundary we
	 * must make sure that the post-EOF area is also zeroed because the
	 * page could be mmap'd and iomap_zero_range doesn't do that for us.
	 * Writeback of the eof page will do this, albeit clumsily.
	 */
	if (offset + len >= XFS_ISIZE(ip) && ((offset + len) & PAGE_MASK)) {
		error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
				(offset + len) & ~PAGE_MASK, LLONG_MAX);
	}

	return error;
}

/*
 * Preallocate and zero a range of a file. This mechanism has the allocation
 * semantics of fallocate and in addition converts data in the range to zeroes.
 */
int
xfs_zero_file_space(
	struct xfs_inode	*ip,
	xfs_off_t		offset,
	xfs_off_t		len)
{
	struct xfs_mount	*mp = ip->i_mount;
	uint			blksize;
	int			error;

	trace_xfs_zero_file_space(ip);

	blksize = 1 << mp->m_sb.sb_blocklog;

	/*
	 * Punch a hole and prealloc the range. We use hole punch rather than
	 * unwritten extent conversion for two reasons:
	 *
	 * 1.) Hole punch handles partial block zeroing for us.
	 *
	 * 2.) If prealloc returns ENOSPC, the file range is still zero-valued
	 * by virtue of the hole punch.
	 */
	error = xfs_free_file_space(ip, offset, len);
	if (error)
		goto out;

	error = xfs_alloc_file_space(ip, round_down(offset, blksize),
				     round_up(offset + len, blksize) -
				     round_down(offset, blksize),
				     XFS_BMAPI_PREALLOC);
out:
	return error;

}

static int
xfs_prepare_shift(
	struct xfs_inode	*ip,
	loff_t			offset)
{
	int			error;

	/*
	 * Trim eofblocks to avoid shifting uninitialized post-eof preallocation
	 * into the accessible region of the file.
	 */
	if (xfs_can_free_eofblocks(ip, true)) {
		error = xfs_free_eofblocks(ip);
		if (error)
			return error;
	}

	/*
	 * Writeback and invalidate cache for the remainder of the file as we're
	 * about to shift down every extent from offset to EOF.
	 */
	error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, offset, -1);
	if (error)
		return error;
	error = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping,
					offset >> PAGE_SHIFT, -1);
	if (error)
		return error;

	/*
	 * Clean out anything hanging around in the cow fork now that
	 * we've flushed all the dirty data out to disk to avoid having
	 * CoW extents at the wrong offsets.
	 */
	if (xfs_inode_has_cow_data(ip)) {
		error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF,
				true);
		if (error)
			return error;
	}

	return 0;
}

/*
 * xfs_collapse_file_space()
 *	This routine frees disk space and shift extent for the given file.
 *	The first thing we do is to free data blocks in the specified range
 *	by calling xfs_free_file_space(). It would also sync dirty data
 *	and invalidate page cache over the region on which collapse range
 *	is working. And Shift extent records to the left to cover a hole.
 * RETURNS:
 *	0 on success
 *	errno on error
 *
 */
int
xfs_collapse_file_space(
	struct xfs_inode	*ip,
	xfs_off_t		offset,
	xfs_off_t		len)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp;
	int			error;
	xfs_fileoff_t		next_fsb = XFS_B_TO_FSB(mp, offset + len);
	xfs_fileoff_t		shift_fsb = XFS_B_TO_FSB(mp, len);
	uint			resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
	bool			done = false;

	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
	ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL));

	trace_xfs_collapse_file_space(ip);

	error = xfs_free_file_space(ip, offset, len);
	if (error)
		return error;

	error = xfs_prepare_shift(ip, offset);
	if (error)
		return error;

	while (!error && !done) {
		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0,
					&tp);
		if (error)
			break;

		xfs_ilock(ip, XFS_ILOCK_EXCL);
		error = xfs_trans_reserve_quota(tp, mp, ip->i_udquot,
				ip->i_gdquot, ip->i_pdquot, resblks, 0,
				XFS_QMOPT_RES_REGBLKS);
		if (error)
			goto out_trans_cancel;
		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);

		error = xfs_bmap_collapse_extents(tp, ip, &next_fsb, shift_fsb,
				&done);
		if (error)
			goto out_trans_cancel;

		error = xfs_trans_commit(tp);
	}

	return error;

out_trans_cancel:
	xfs_trans_cancel(tp);
	return error;
}

/*
 * xfs_insert_file_space()
 *	This routine create hole space by shifting extents for the given file.
 *	The first thing we do is to sync dirty data and invalidate page cache
 *	over the region on which insert range is working. And split an extent
 *	to two extents at given offset by calling xfs_bmap_split_extent.
 *	And shift all extent records which are laying between [offset,
 *	last allocated extent] to the right to reserve hole range.
 * RETURNS:
 *	0 on success
 *	errno on error
 */
int
xfs_insert_file_space(
	struct xfs_inode	*ip,
	loff_t			offset,
	loff_t			len)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp;
	int			error;
	xfs_fileoff_t		stop_fsb = XFS_B_TO_FSB(mp, offset);
	xfs_fileoff_t		next_fsb = NULLFSBLOCK;
	xfs_fileoff_t		shift_fsb = XFS_B_TO_FSB(mp, len);
	bool			done = false;

	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
	ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL));

	trace_xfs_insert_file_space(ip);

	error = xfs_bmap_can_insert_extents(ip, stop_fsb, shift_fsb);
	if (error)
		return error;

	error = xfs_prepare_shift(ip, offset);
	if (error)
		return error;

	/*
	 * The extent shifting code works on extent granularity. So, if stop_fsb
	 * is not the starting block of extent, we need to split the extent at
	 * stop_fsb.
	 */
	error = xfs_bmap_split_extent(ip, stop_fsb);
	if (error)
		return error;

	while (!error && !done) {
		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, 0,
					&tp);
		if (error)
			break;

		xfs_ilock(ip, XFS_ILOCK_EXCL);
		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
		error = xfs_bmap_insert_extents(tp, ip, &next_fsb, shift_fsb,
				&done, stop_fsb);
		if (error)
			goto out_trans_cancel;

		error = xfs_trans_commit(tp);
	}

	return error;

out_trans_cancel:
	xfs_trans_cancel(tp);
	return error;
}

/*
 * We need to check that the format of the data fork in the temporary inode is
 * valid for the target inode before doing the swap. This is not a problem with
 * attr1 because of the fixed fork offset, but attr2 has a dynamically sized
 * data fork depending on the space the attribute fork is taking so we can get
 * invalid formats on the target inode.
 *
 * E.g. target has space for 7 extents in extent format, temp inode only has
 * space for 6.  If we defragment down to 7 extents, then the tmp format is a
 * btree, but when swapped it needs to be in extent format. Hence we can't just
 * blindly swap data forks on attr2 filesystems.
 *
 * Note that we check the swap in both directions so that we don't end up with
 * a corrupt temporary inode, either.
 *
 * Note that fixing the way xfs_fsr sets up the attribute fork in the source
 * inode will prevent this situation from occurring, so all we do here is
 * reject and log the attempt. basically we are putting the responsibility on
 * userspace to get this right.
 */
static int
xfs_swap_extents_check_format(
	struct xfs_inode	*ip,	/* target inode */
	struct xfs_inode	*tip)	/* tmp inode */
{

	/* Should never get a local format */
	if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL ||
	    tip->i_d.di_format == XFS_DINODE_FMT_LOCAL)
		return -EINVAL;

	/*
	 * if the target inode has less extents that then temporary inode then
	 * why did userspace call us?
	 */
	if (ip->i_d.di_nextents < tip->i_d.di_nextents)
		return -EINVAL;

	/*
	 * If we have to use the (expensive) rmap swap method, we can
	 * handle any number of extents and any format.
	 */
	if (xfs_sb_version_hasrmapbt(&ip->i_mount->m_sb))
		return 0;

	/*
	 * if the target inode is in extent form and the temp inode is in btree
	 * form then we will end up with the target inode in the wrong format
	 * as we already know there are less extents in the temp inode.
	 */
	if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
	    tip->i_d.di_format == XFS_DINODE_FMT_BTREE)
		return -EINVAL;

	/* Check temp in extent form to max in target */
	if (tip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
	    XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) >
			XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
		return -EINVAL;

	/* Check target in extent form to max in temp */
	if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
	    XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) >
			XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
		return -EINVAL;

	/*
	 * If we are in a btree format, check that the temp root block will fit
	 * in the target and that it has enough extents to be in btree format
	 * in the target.
	 *
	 * Note that we have to be careful to allow btree->extent conversions
	 * (a common defrag case) which will occur when the temp inode is in
	 * extent format...
	 */
	if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
		if (XFS_IFORK_Q(ip) &&
		    XFS_BMAP_BMDR_SPACE(tip->i_df.if_broot) > XFS_IFORK_BOFF(ip))
			return -EINVAL;
		if (XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) <=
		    XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
			return -EINVAL;
	}

	/* Reciprocal target->temp btree format checks */
	if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
		if (XFS_IFORK_Q(tip) &&
		    XFS_BMAP_BMDR_SPACE(ip->i_df.if_broot) > XFS_IFORK_BOFF(tip))
			return -EINVAL;
		if (XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) <=
		    XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
			return -EINVAL;
	}

	return 0;
}

static int
xfs_swap_extent_flush(
	struct xfs_inode	*ip)
{
	int	error;

	error = filemap_write_and_wait(VFS_I(ip)->i_mapping);
	if (error)
		return error;
	truncate_pagecache_range(VFS_I(ip), 0, -1);

	/* Verify O_DIRECT for ftmp */
	if (VFS_I(ip)->i_mapping->nrpages)
		return -EINVAL;
	return 0;
}

/*
 * Move extents from one file to another, when rmap is enabled.
 */
STATIC int
xfs_swap_extent_rmap(
	struct xfs_trans		**tpp,
	struct xfs_inode		*ip,
	struct xfs_inode		*tip)
{
	struct xfs_trans		*tp = *tpp;
	struct xfs_bmbt_irec		irec;
	struct xfs_bmbt_irec		uirec;
	struct xfs_bmbt_irec		tirec;
	xfs_fileoff_t			offset_fsb;
	xfs_fileoff_t			end_fsb;
	xfs_filblks_t			count_fsb;
	int				error;
	xfs_filblks_t			ilen;
	xfs_filblks_t			rlen;
	int				nimaps;
	uint64_t			tip_flags2;

	/*
	 * If the source file has shared blocks, we must flag the donor
	 * file as having shared blocks so that we get the shared-block
	 * rmap functions when we go to fix up the rmaps.  The flags
	 * will be switch for reals later.
	 */
	tip_flags2 = tip->i_d.di_flags2;
	if (ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK)
		tip->i_d.di_flags2 |= XFS_DIFLAG2_REFLINK;

	offset_fsb = 0;
	end_fsb = XFS_B_TO_FSB(ip->i_mount, i_size_read(VFS_I(ip)));
	count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);

	while (count_fsb) {
		/* Read extent from the donor file */
		nimaps = 1;
		error = xfs_bmapi_read(tip, offset_fsb, count_fsb, &tirec,
				&nimaps, 0);
		if (error)
			goto out;
		ASSERT(nimaps == 1);
		ASSERT(tirec.br_startblock != DELAYSTARTBLOCK);

		trace_xfs_swap_extent_rmap_remap(tip, &tirec);
		ilen = tirec.br_blockcount;

		/* Unmap the old blocks in the source file. */
		while (tirec.br_blockcount) {
			ASSERT(tp->t_firstblock == NULLFSBLOCK);
			trace_xfs_swap_extent_rmap_remap_piece(tip, &tirec);

			/* Read extent from the source file */
			nimaps = 1;
			error = xfs_bmapi_read(ip, tirec.br_startoff,
					tirec.br_blockcount, &irec,
					&nimaps, 0);
			if (error)
				goto out;
			ASSERT(nimaps == 1);
			ASSERT(tirec.br_startoff == irec.br_startoff);
			trace_xfs_swap_extent_rmap_remap_piece(ip, &irec);

			/* Trim the extent. */
			uirec = tirec;
			uirec.br_blockcount = rlen = min_t(xfs_filblks_t,
					tirec.br_blockcount,
					irec.br_blockcount);
			trace_xfs_swap_extent_rmap_remap_piece(tip, &uirec);

			/* Remove the mapping from the donor file. */
			error = xfs_bmap_unmap_extent(tp, tip, &uirec);
			if (error)
				goto out;

			/* Remove the mapping from the source file. */
			error = xfs_bmap_unmap_extent(tp, ip, &irec);
			if (error)
				goto out;

			/* Map the donor file's blocks into the source file. */
			error = xfs_bmap_map_extent(tp, ip, &uirec);
			if (error)
				goto out;

			/* Map the source file's blocks into the donor file. */
			error = xfs_bmap_map_extent(tp, tip, &irec);
			if (error)
				goto out;

			error = xfs_defer_finish(tpp);
			tp = *tpp;
			if (error)
				goto out;

			tirec.br_startoff += rlen;
			if (tirec.br_startblock != HOLESTARTBLOCK &&
			    tirec.br_startblock != DELAYSTARTBLOCK)
				tirec.br_startblock += rlen;
			tirec.br_blockcount -= rlen;
		}

		/* Roll on... */
		count_fsb -= ilen;
		offset_fsb += ilen;
	}

	tip->i_d.di_flags2 = tip_flags2;
	return 0;

out:
	trace_xfs_swap_extent_rmap_error(ip, error, _RET_IP_);
	tip->i_d.di_flags2 = tip_flags2;
	return error;
}

/* Swap the extents of two files by swapping data forks. */
STATIC int
xfs_swap_extent_forks(
	struct xfs_trans	*tp,
	struct xfs_inode	*ip,
	struct xfs_inode	*tip,
	int			*src_log_flags,
	int			*target_log_flags)
{
	xfs_filblks_t		aforkblks = 0;
	xfs_filblks_t		taforkblks = 0;
	xfs_extnum_t		junk;
	uint64_t		tmp;
	int			error;

	/*
	 * Count the number of extended attribute blocks
	 */
	if ( ((XFS_IFORK_Q(ip) != 0) && (ip->i_d.di_anextents > 0)) &&
	     (ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
		error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &junk,
				&aforkblks);
		if (error)
			return error;
	}
	if ( ((XFS_IFORK_Q(tip) != 0) && (tip->i_d.di_anextents > 0)) &&
	     (tip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
		error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK, &junk,
				&taforkblks);
		if (error)
			return error;
	}

	/*
	 * Btree format (v3) inodes have the inode number stamped in the bmbt
	 * block headers. We can't start changing the bmbt blocks until the
	 * inode owner change is logged so recovery does the right thing in the
	 * event of a crash. Set the owner change log flags now and leave the
	 * bmbt scan as the last step.
	 */
	if (ip->i_d.di_version == 3 &&
	    ip->i_d.di_format == XFS_DINODE_FMT_BTREE)
		(*target_log_flags) |= XFS_ILOG_DOWNER;
	if (tip->i_d.di_version == 3 &&
	    tip->i_d.di_format == XFS_DINODE_FMT_BTREE)
		(*src_log_flags) |= XFS_ILOG_DOWNER;

	/*
	 * Swap the data forks of the inodes
	 */
	swap(ip->i_df, tip->i_df);

	/*
	 * Fix the on-disk inode values
	 */
	tmp = (uint64_t)ip->i_d.di_nblocks;
	ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
	tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;

	swap(ip->i_d.di_nextents, tip->i_d.di_nextents);
	swap(ip->i_d.di_format, tip->i_d.di_format);

	/*
	 * The extents in the source inode could still contain speculative
	 * preallocation beyond EOF (e.g. the file is open but not modified
	 * while defrag is in progress). In that case, we need to copy over the
	 * number of delalloc blocks the data fork in the source inode is
	 * tracking beyond EOF so that when the fork is truncated away when the
	 * temporary inode is unlinked we don't underrun the i_delayed_blks
	 * counter on that inode.
	 */
	ASSERT(tip->i_delayed_blks == 0);
	tip->i_delayed_blks = ip->i_delayed_blks;
	ip->i_delayed_blks = 0;

	switch (ip->i_d.di_format) {
	case XFS_DINODE_FMT_EXTENTS:
		(*src_log_flags) |= XFS_ILOG_DEXT;
		break;
	case XFS_DINODE_FMT_BTREE:
		ASSERT(ip->i_d.di_version < 3 ||
		       (*src_log_flags & XFS_ILOG_DOWNER));
		(*src_log_flags) |= XFS_ILOG_DBROOT;
		break;
	}

	switch (tip->i_d.di_format) {
	case XFS_DINODE_FMT_EXTENTS:
		(*target_log_flags) |= XFS_ILOG_DEXT;
		break;
	case XFS_DINODE_FMT_BTREE:
		(*target_log_flags) |= XFS_ILOG_DBROOT;
		ASSERT(tip->i_d.di_version < 3 ||
		       (*target_log_flags & XFS_ILOG_DOWNER));
		break;
	}

	return 0;
}

/*
 * Fix up the owners of the bmbt blocks to refer to the current inode. The
 * change owner scan attempts to order all modified buffers in the current
 * transaction. In the event of ordered buffer failure, the offending buffer is
 * physically logged as a fallback and the scan returns -EAGAIN. We must roll
 * the transaction in this case to replenish the fallback log reservation and
 * restart the scan. This process repeats until the scan completes.
 */
static int
xfs_swap_change_owner(
	struct xfs_trans	**tpp,
	struct xfs_inode	*ip,
	struct xfs_inode	*tmpip)
{
	int			error;
	struct xfs_trans	*tp = *tpp;

	do {
		error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK, ip->i_ino,
					      NULL);
		/* success or fatal error */
		if (error != -EAGAIN)
			break;

		error = xfs_trans_roll(tpp);
		if (error)
			break;
		tp = *tpp;

		/*
		 * Redirty both inodes so they can relog and keep the log tail
		 * moving forward.
		 */
		xfs_trans_ijoin(tp, ip, 0);
		xfs_trans_ijoin(tp, tmpip, 0);
		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
		xfs_trans_log_inode(tp, tmpip, XFS_ILOG_CORE);
	} while (true);

	return error;
}

int
xfs_swap_extents(
	struct xfs_inode	*ip,	/* target inode */
	struct xfs_inode	*tip,	/* tmp inode */
	struct xfs_swapext	*sxp)
{
	struct xfs_mount	*mp = ip->i_mount;
	struct xfs_trans	*tp;
	struct xfs_bstat	*sbp = &sxp->sx_stat;
	int			src_log_flags, target_log_flags;
	int			error = 0;
	int			lock_flags;
	uint64_t		f;
	int			resblks = 0;

	/*
	 * Lock the inodes against other IO, page faults and truncate to
	 * begin with.  Then we can ensure the inodes are flushed and have no
	 * page cache safely. Once we have done this we can take the ilocks and
	 * do the rest of the checks.
	 */
	lock_two_nondirectories(VFS_I(ip), VFS_I(tip));
	lock_flags = XFS_MMAPLOCK_EXCL;
	xfs_lock_two_inodes(ip, XFS_MMAPLOCK_EXCL, tip, XFS_MMAPLOCK_EXCL);

	/* Verify that both files have the same format */
	if ((VFS_I(ip)->i_mode & S_IFMT) != (VFS_I(tip)->i_mode & S_IFMT)) {
		error = -EINVAL;
		goto out_unlock;
	}

	/* Verify both files are either real-time or non-realtime */
	if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) {
		error = -EINVAL;
		goto out_unlock;
	}

	error = xfs_swap_extent_flush(ip);
	if (error)
		goto out_unlock;
	error = xfs_swap_extent_flush(tip);
	if (error)
		goto out_unlock;

	if (xfs_inode_has_cow_data(tip)) {
		error = xfs_reflink_cancel_cow_range(tip, 0, NULLFILEOFF, true);
		if (error)
			return error;
	}

	/*
	 * Extent "swapping" with rmap requires a permanent reservation and
	 * a block reservation because it's really just a remap operation
	 * performed with log redo items!
	 */
	if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
		int		w	= XFS_DATA_FORK;
		uint32_t	ipnext	= XFS_IFORK_NEXTENTS(ip, w);
		uint32_t	tipnext	= XFS_IFORK_NEXTENTS(tip, w);

		/*
		 * Conceptually this shouldn't affect the shape of either bmbt,
		 * but since we atomically move extents one by one, we reserve
		 * enough space to rebuild both trees.
		 */
		resblks = XFS_SWAP_RMAP_SPACE_RES(mp, ipnext, w);
		resblks +=  XFS_SWAP_RMAP_SPACE_RES(mp, tipnext, w);

		/*
		 * Handle the corner case where either inode might straddle the
		 * btree format boundary. If so, the inode could bounce between
		 * btree <-> extent format on unmap -> remap cycles, freeing and
		 * allocating a bmapbt block each time.
		 */
		if (ipnext == (XFS_IFORK_MAXEXT(ip, w) + 1))
			resblks += XFS_IFORK_MAXEXT(ip, w);
		if (tipnext == (XFS_IFORK_MAXEXT(tip, w) + 1))
			resblks += XFS_IFORK_MAXEXT(tip, w);
	}
	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
	if (error)
		goto out_unlock;

	/*
	 * Lock and join the inodes to the tansaction so that transaction commit
	 * or cancel will unlock the inodes from this point onwards.
	 */
	xfs_lock_two_inodes(ip, XFS_ILOCK_EXCL, tip, XFS_ILOCK_EXCL);
	lock_flags |= XFS_ILOCK_EXCL;
	xfs_trans_ijoin(tp, ip, 0);
	xfs_trans_ijoin(tp, tip, 0);


	/* Verify all data are being swapped */
	if (sxp->sx_offset != 0 ||
	    sxp->sx_length != ip->i_d.di_size ||
	    sxp->sx_length != tip->i_d.di_size) {
		error = -EFAULT;
		goto out_trans_cancel;
	}

	trace_xfs_swap_extent_before(ip, 0);
	trace_xfs_swap_extent_before(tip, 1);

	/* check inode formats now that data is flushed */
	error = xfs_swap_extents_check_format(ip, tip);
	if (error) {
		xfs_notice(mp,
		    "%s: inode 0x%llx format is incompatible for exchanging.",
				__func__, ip->i_ino);
		goto out_trans_cancel;
	}

	/*
	 * Compare the current change & modify times with that
	 * passed in.  If they differ, we abort this swap.
	 * This is the mechanism used to ensure the calling
	 * process that the file was not changed out from
	 * under it.
	 */
	if ((sbp->bs_ctime.tv_sec != VFS_I(ip)->i_ctime.tv_sec) ||
	    (sbp->bs_ctime.tv_nsec != VFS_I(ip)->i_ctime.tv_nsec) ||
	    (sbp->bs_mtime.tv_sec != VFS_I(ip)->i_mtime.tv_sec) ||
	    (sbp->bs_mtime.tv_nsec != VFS_I(ip)->i_mtime.tv_nsec)) {
		error = -EBUSY;
		goto out_trans_cancel;
	}

	/*
	 * Note the trickiness in setting the log flags - we set the owner log
	 * flag on the opposite inode (i.e. the inode we are setting the new
	 * owner to be) because once we swap the forks and log that, log
	 * recovery is going to see the fork as owned by the swapped inode,
	 * not the pre-swapped inodes.
	 */
	src_log_flags = XFS_ILOG_CORE;
	target_log_flags = XFS_ILOG_CORE;

	if (xfs_sb_version_hasrmapbt(&mp->m_sb))
		error = xfs_swap_extent_rmap(&tp, ip, tip);
	else
		error = xfs_swap_extent_forks(tp, ip, tip, &src_log_flags,
				&target_log_flags);
	if (error)
		goto out_trans_cancel;

	/* Do we have to swap reflink flags? */
	if ((ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK) ^
	    (tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK)) {
		f = ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK;
		ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
		ip->i_d.di_flags2 |= tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK;
		tip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
		tip->i_d.di_flags2 |= f & XFS_DIFLAG2_REFLINK;
	}

	/* Swap the cow forks. */
	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
		ASSERT(ip->i_cformat == XFS_DINODE_FMT_EXTENTS);
		ASSERT(tip->i_cformat == XFS_DINODE_FMT_EXTENTS);

		swap(ip->i_cnextents, tip->i_cnextents);
		swap(ip->i_cowfp, tip->i_cowfp);

		if (ip->i_cowfp && ip->i_cowfp->if_bytes)
			xfs_inode_set_cowblocks_tag(ip);
		else
			xfs_inode_clear_cowblocks_tag(ip);
		if (tip->i_cowfp && tip->i_cowfp->if_bytes)
			xfs_inode_set_cowblocks_tag(tip);
		else
			xfs_inode_clear_cowblocks_tag(tip);
	}

	xfs_trans_log_inode(tp, ip,  src_log_flags);
	xfs_trans_log_inode(tp, tip, target_log_flags);

	/*
	 * The extent forks have been swapped, but crc=1,rmapbt=0 filesystems
	 * have inode number owner values in the bmbt blocks that still refer to
	 * the old inode. Scan each bmbt to fix up the owner values with the
	 * inode number of the current inode.
	 */
	if (src_log_flags & XFS_ILOG_DOWNER) {
		error = xfs_swap_change_owner(&tp, ip, tip);
		if (error)
			goto out_trans_cancel;
	}
	if (target_log_flags & XFS_ILOG_DOWNER) {
		error = xfs_swap_change_owner(&tp, tip, ip);
		if (error)
			goto out_trans_cancel;
	}

	/*
	 * If this is a synchronous mount, make sure that the
	 * transaction goes to disk before returning to the user.
	 */
	if (mp->m_flags & XFS_MOUNT_WSYNC)
		xfs_trans_set_sync(tp);

	error = xfs_trans_commit(tp);

	trace_xfs_swap_extent_after(ip, 0);
	trace_xfs_swap_extent_after(tip, 1);

out_unlock:
	xfs_iunlock(ip, lock_flags);
	xfs_iunlock(tip, lock_flags);
	unlock_two_nondirectories(VFS_I(ip), VFS_I(tip));
	return error;

out_trans_cancel:
	xfs_trans_cancel(tp);
	goto out_unlock;
}