summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_bmap_util.c
blob: 97f952caea74bd8311a3269ca7520e87b01fcb18 (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
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
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
/*
 * Copyright (c) 2000-2006 Silicon Graphics, Inc.
 * Copyright (c) 2012 Red Hat, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_format.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_da_btree.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_extfree_item.h"
#include "xfs_alloc.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.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"

/* 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 be called at transaction's end by xfs_bmapi, xfs_bunmapi
 * caller.  Frees all the extents that need freeing, which must be done
 * last due to locking considerations.  We never free any extents in
 * the first transaction.
 *
 * Return 1 if the given transaction was committed and a new one
 * started, and 0 otherwise in the committed parameter.
 */
int						/* error */
xfs_bmap_finish(
	xfs_trans_t		**tp,		/* transaction pointer addr */
	xfs_bmap_free_t		*flist,		/* i/o: list extents to free */
	int			*committed)	/* xact committed or not */
{
	xfs_efd_log_item_t	*efd;		/* extent free data */
	xfs_efi_log_item_t	*efi;		/* extent free intention */
	int			error;		/* error return value */
	xfs_bmap_free_item_t	*free;		/* free extent item */
	struct xfs_trans_res	tres;		/* new log reservation */
	xfs_mount_t		*mp;		/* filesystem mount structure */
	xfs_bmap_free_item_t	*next;		/* next item on free list */
	xfs_trans_t		*ntp;		/* new transaction pointer */

	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
	if (flist->xbf_count == 0) {
		*committed = 0;
		return 0;
	}
	ntp = *tp;
	efi = xfs_trans_get_efi(ntp, flist->xbf_count);
	for (free = flist->xbf_first; free; free = free->xbfi_next)
		xfs_trans_log_efi_extent(ntp, efi, free->xbfi_startblock,
			free->xbfi_blockcount);

	tres.tr_logres = ntp->t_log_res;
	tres.tr_logcount = ntp->t_log_count;
	tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
	ntp = xfs_trans_dup(*tp);
	error = xfs_trans_commit(*tp, 0);
	*tp = ntp;
	*committed = 1;
	/*
	 * We have a new transaction, so we should return committed=1,
	 * even though we're returning an error.
	 */
	if (error)
		return error;

	/*
	 * transaction commit worked ok so we can drop the extra ticket
	 * reference that we gained in xfs_trans_dup()
	 */
	xfs_log_ticket_put(ntp->t_ticket);

	error = xfs_trans_reserve(ntp, &tres, 0, 0);
	if (error)
		return error;
	efd = xfs_trans_get_efd(ntp, efi, flist->xbf_count);
	for (free = flist->xbf_first; free != NULL; free = next) {
		next = free->xbfi_next;
		if ((error = xfs_free_extent(ntp, free->xbfi_startblock,
				free->xbfi_blockcount))) {
			/*
			 * The bmap free list will be cleaned up at a
			 * higher level.  The EFI will be canceled when
			 * this transaction is aborted.
			 * Need to force shutdown here to make sure it
			 * happens, since this transaction may not be
			 * dirty yet.
			 */
			mp = ntp->t_mountp;
			if (!XFS_FORCED_SHUTDOWN(mp))
				xfs_force_shutdown(mp,
						   (error == EFSCORRUPTED) ?
						   SHUTDOWN_CORRUPT_INCORE :
						   SHUTDOWN_META_IO_ERROR);
			return error;
		}
		xfs_trans_log_efd_extent(ntp, efd, free->xbfi_startblock,
			free->xbfi_blockcount);
		xfs_bmap_del_free(flist, NULL, free);
	}
	return 0;
}

int
xfs_bmap_rtalloc(
	struct xfs_bmalloca	*ap)	/* bmap alloc argument struct */
{
	xfs_alloctype_t	atype = 0;	/* type for allocation routines */
	int		error;		/* error return value */
	xfs_mount_t	*mp;		/* mount point structure */
	xfs_extlen_t	prod = 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.
	 */
	if (do_mod(ap->offset, align) || 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 other modifications to the RT bitmap inode.
	 */
	xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL);
	xfs_trans_ijoin(ap->tp, mp->m_rbmip, 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.
	 */
	atype = ap->blkno == 0 ?  XFS_ALLOCTYPE_ANY_AG : XFS_ALLOCTYPE_NEAR_BNO;
	do_div(ap->blkno, mp->m_sb.sb_rextsize);
	rtb = ap->blkno;
	ap->length = ralen;
	if ((error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, ap->length,
				&ralen, atype, ap->wasdel, prod, &rtb)))
		return error;
	if (rtb == NULLFSBLOCK && prod > 1 &&
	    (error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1,
					   ap->length, &ralen, atype,
					   ap->wasdel, 1, &rtb)))
		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);
	} else {
		ap->length = 0;
	}
	return 0;
}

/*
 * Stack switching interfaces for allocation
 */
static void
xfs_bmapi_allocate_worker(
	struct work_struct	*work)
{
	struct xfs_bmalloca	*args = container_of(work,
						struct xfs_bmalloca, work);
	unsigned long		pflags;

	/* we are in a transaction context here */
	current_set_flags_nested(&pflags, PF_FSTRANS);

	args->result = __xfs_bmapi_allocate(args);
	complete(args->done);

	current_restore_flags_nested(&pflags, PF_FSTRANS);
}

/*
 * Some allocation requests often come in with little stack to work on. Push
 * them off to a worker thread so there is lots of stack to use. Otherwise just
 * call directly to avoid the context switch overhead here.
 */
int
xfs_bmapi_allocate(
	struct xfs_bmalloca	*args)
{
	DECLARE_COMPLETION_ONSTACK(done);

	if (!args->stack_switch)
		return __xfs_bmapi_allocate(args);


	args->done = &done;
	INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker);
	queue_work(xfs_alloc_wq, &args->work);
	wait_for_completion(&done);
	return args->result;
}

/*
 * 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.
 */
STATIC void
xfs_bmap_count_leaves(
	xfs_ifork_t		*ifp,
	xfs_extnum_t		idx,
	int			numrecs,
	int			*count)
{
	int		b;

	for (b = 0; b < numrecs; b++) {
		xfs_bmbt_rec_host_t *frp = xfs_iext_get_ext(ifp, idx + b);
		*count += xfs_bmbt_get_blockcount(frp);
	}
}

/*
 * 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,
	int			*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                                     /* error */
xfs_bmap_count_tree(
	xfs_mount_t     *mp,            /* file system mount point */
	xfs_trans_t     *tp,            /* transaction pointer */
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	xfs_fsblock_t   blockno,	/* file system block number */
	int             levelin,	/* level in btree */
	int		*count)		/* Count of blocks */
{
	int			error;
	xfs_buf_t		*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);
		if (unlikely((error =
		     xfs_bmap_count_tree(mp, tp, ifp, bno, level, count)) < 0)) {
			xfs_trans_brelse(tp, bp);
			XFS_ERROR_REPORT("xfs_bmap_count_tree(1)",
					 XFS_ERRLEVEL_LOW, mp);
			return XFS_ERROR(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);
			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.
 */
int						/* error */
xfs_bmap_count_blocks(
	xfs_trans_t		*tp,		/* transaction pointer */
	xfs_inode_t		*ip,		/* incore inode */
	int			whichfork,	/* data or attr fork */
	int			*count)		/* out: count of blocks */
{
	struct xfs_btree_block	*block;	/* current btree block */
	xfs_fsblock_t		bno;	/* block # of "block" */
	xfs_ifork_t		*ifp;	/* fork structure */
	int			level;	/* btree level, for checking */
	xfs_mount_t		*mp;	/* file system mount structure */
	__be64			*pp;	/* pointer to block address */

	bno = NULLFSBLOCK;
	mp = ip->i_mount;
	ifp = XFS_IFORK_PTR(ip, whichfork);
	if ( XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ) {
		xfs_bmap_count_leaves(ifp, 0,
			ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t),
			count);
		return 0;
	}

	/*
	 * 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 != NULLDFSBNO);
	ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
	ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);

	if (unlikely(xfs_bmap_count_tree(mp, tp, ifp, bno, level, count) < 0)) {
		XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)", XFS_ERRLEVEL_LOW,
				 mp);
		return XFS_ERROR(EFSCORRUPTED);
	}

	return 0;
}

/*
 * returns 1 for success, 0 if we failed to map the extent.
 */
STATIC int
xfs_getbmapx_fix_eof_hole(
	xfs_inode_t		*ip,		/* xfs incore inode pointer */
	struct getbmapx		*out,		/* output structure */
	int			prealloced,	/* this is a file with
						 * preallocated data space */
	__int64_t		end,		/* last block requested */
	xfs_fsblock_t		startblock)
{
	__int64_t		fixlen;
	xfs_mount_t		*mp;		/* file system mount point */
	xfs_ifork_t		*ifp;		/* inode fork pointer */
	xfs_extnum_t		lastx;		/* last extent pointer */
	xfs_fileoff_t		fileblock;

	if (startblock == HOLESTARTBLOCK) {
		mp = ip->i_mount;
		out->bmv_block = -1;
		fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, XFS_ISIZE(ip)));
		fixlen -= out->bmv_offset;
		if (prealloced && out->bmv_offset + out->bmv_length == end) {
			/* Came to hole at EOF. Trim it. */
			if (fixlen <= 0)
				return 0;
			out->bmv_length = fixlen;
		}
	} else {
		if (startblock == DELAYSTARTBLOCK)
			out->bmv_block = -2;
		else
			out->bmv_block = xfs_fsb_to_db(ip, startblock);
		fileblock = XFS_BB_TO_FSB(ip->i_mount, out->bmv_offset);
		ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
		if (xfs_iext_bno_to_ext(ifp, fileblock, &lastx) &&
		   (lastx == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))-1))
			out->bmv_oflags |= BMV_OF_LAST;
	}

	return 1;
}

/*
 * 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(
	xfs_inode_t		*ip,
	struct getbmapx		*bmv,		/* user bmap structure */
	xfs_bmap_format_t	formatter,	/* format to user */
	void			*arg)		/* formatter arg */
{
	__int64_t		bmvend;		/* last block requested */
	int			error = 0;	/* return value */
	__int64_t		fixlen;		/* length for -1 case */
	int			i;		/* extent number */
	int			lock;		/* lock state */
	xfs_bmbt_irec_t		*map;		/* buffer for user's data */
	xfs_mount_t		*mp;		/* file system mount point */
	int			nex;		/* # of user extents can do */
	int			nexleft;	/* # of user extents left */
	int			subnex;		/* # of bmapi's can do */
	int			nmap;		/* number of map entries */
	struct getbmapx		*out;		/* output structure */
	int			whichfork;	/* data or attr fork */
	int			prealloced;	/* this is a file with
						 * preallocated data space */
	int			iflags;		/* interface flags */
	int			bmapi_flags;	/* flags for xfs_bmapi */
	int			cur_ext = 0;

	mp = ip->i_mount;
	iflags = bmv->bmv_iflags;
	whichfork = iflags & BMV_IF_ATTRFORK ? XFS_ATTR_FORK : XFS_DATA_FORK;

	if (whichfork == XFS_ATTR_FORK) {
		if (XFS_IFORK_Q(ip)) {
			if (ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS &&
			    ip->i_d.di_aformat != XFS_DINODE_FMT_BTREE &&
			    ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)
				return XFS_ERROR(EINVAL);
		} else if (unlikely(
			   ip->i_d.di_aformat != 0 &&
			   ip->i_d.di_aformat != XFS_DINODE_FMT_EXTENTS)) {
			XFS_ERROR_REPORT("xfs_getbmap", XFS_ERRLEVEL_LOW,
					 ip->i_mount);
			return XFS_ERROR(EFSCORRUPTED);
		}

		prealloced = 0;
		fixlen = 1LL << 32;
	} else {
		if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
		    ip->i_d.di_format != XFS_DINODE_FMT_BTREE &&
		    ip->i_d.di_format != XFS_DINODE_FMT_LOCAL)
			return XFS_ERROR(EINVAL);

		if (xfs_get_extsz_hint(ip) ||
		    ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC|XFS_DIFLAG_APPEND)){
			prealloced = 1;
			fixlen = mp->m_super->s_maxbytes;
		} else {
			prealloced = 0;
			fixlen = XFS_ISIZE(ip);
		}
	}

	if (bmv->bmv_length == -1) {
		fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, fixlen));
		bmv->bmv_length =
			max_t(__int64_t, fixlen - bmv->bmv_offset, 0);
	} else if (bmv->bmv_length == 0) {
		bmv->bmv_entries = 0;
		return 0;
	} else if (bmv->bmv_length < 0) {
		return XFS_ERROR(EINVAL);
	}

	nex = bmv->bmv_count - 1;
	if (nex <= 0)
		return XFS_ERROR(EINVAL);
	bmvend = bmv->bmv_offset + bmv->bmv_length;


	if (bmv->bmv_count > ULONG_MAX / sizeof(struct getbmapx))
		return XFS_ERROR(ENOMEM);
	out = kmem_zalloc_large(bmv->bmv_count * sizeof(struct getbmapx), 0);
	if (!out)
		return XFS_ERROR(ENOMEM);

	xfs_ilock(ip, XFS_IOLOCK_SHARED);
	if (whichfork == XFS_DATA_FORK && !(iflags & BMV_IF_DELALLOC)) {
		if (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.
		 */
	}

	lock = xfs_ilock_map_shared(ip);

	/*
	 * Don't let nex be bigger than the number of extents
	 * we can have assuming alternating holes and real extents.
	 */
	if (nex > XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1)
		nex = XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1;

	bmapi_flags = xfs_bmapi_aflag(whichfork);
	if (!(iflags & BMV_IF_PREALLOC))
		bmapi_flags |= XFS_BMAPI_IGSTATE;

	/*
	 * Allocate enough space to handle "subnex" maps at a time.
	 */
	error = ENOMEM;
	subnex = 16;
	map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL | KM_NOFS);
	if (!map)
		goto out_unlock_ilock;

	bmv->bmv_entries = 0;

	if (XFS_IFORK_NEXTENTS(ip, whichfork) == 0 &&
	    (whichfork == XFS_ATTR_FORK || !(iflags & BMV_IF_DELALLOC))) {
		error = 0;
		goto out_free_map;
	}

	nexleft = nex;

	do {
		nmap = (nexleft > subnex) ? subnex : nexleft;
		error = xfs_bmapi_read(ip, XFS_BB_TO_FSBT(mp, bmv->bmv_offset),
				       XFS_BB_TO_FSB(mp, bmv->bmv_length),
				       map, &nmap, bmapi_flags);
		if (error)
			goto out_free_map;
		ASSERT(nmap <= subnex);

		for (i = 0; i < nmap && nexleft && bmv->bmv_length; i++) {
			out[cur_ext].bmv_oflags = 0;
			if (map[i].br_state == XFS_EXT_UNWRITTEN)
				out[cur_ext].bmv_oflags |= BMV_OF_PREALLOC;
			else if (map[i].br_startblock == DELAYSTARTBLOCK)
				out[cur_ext].bmv_oflags |= BMV_OF_DELALLOC;
			out[cur_ext].bmv_offset =
				XFS_FSB_TO_BB(mp, map[i].br_startoff);
			out[cur_ext].bmv_length =
				XFS_FSB_TO_BB(mp, map[i].br_blockcount);
			out[cur_ext].bmv_unused1 = 0;
			out[cur_ext].bmv_unused2 = 0;

			/*
			 * delayed allocation 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 (map[i].br_startblock == DELAYSTARTBLOCK &&
			    map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
				ASSERT((iflags & BMV_IF_DELALLOC) != 0);

                        if (map[i].br_startblock == HOLESTARTBLOCK &&
			    whichfork == XFS_ATTR_FORK) {
				/* came to the end of attribute fork */
				out[cur_ext].bmv_oflags |= BMV_OF_LAST;
				goto out_free_map;
			}

			if (!xfs_getbmapx_fix_eof_hole(ip, &out[cur_ext],
					prealloced, bmvend,
					map[i].br_startblock))
				goto out_free_map;

			bmv->bmv_offset =
				out[cur_ext].bmv_offset +
				out[cur_ext].bmv_length;
			bmv->bmv_length =
				max_t(__int64_t, 0, bmvend - bmv->bmv_offset);

			/*
			 * In case we don't want to return the hole,
			 * don't increase cur_ext so that we can reuse
			 * it in the next loop.
			 */
			if ((iflags & BMV_IF_NO_HOLES) &&
			    map[i].br_startblock == HOLESTARTBLOCK) {
				memset(&out[cur_ext], 0, sizeof(out[cur_ext]));
				continue;
			}

			nexleft--;
			bmv->bmv_entries++;
			cur_ext++;
		}
	} while (nmap && nexleft && bmv->bmv_length);

 out_free_map:
	kmem_free(map);
 out_unlock_ilock:
	xfs_iunlock_map_shared(ip, lock);
 out_unlock_iolock:
	xfs_iunlock(ip, XFS_IOLOCK_SHARED);

	for (i = 0; i < cur_ext; i++) {
		int full = 0;	/* user array is full */

		/* format results & advance arg */
		error = formatter(&arg, &out[i], &full);
		if (error || full)
			break;
	}

	kmem_free(out);
	return error;
}

/*
 * dead simple method of punching delalyed allocation blocks from a range in
 * the inode. Walks a block at a time so will be slow, but is only executed in
 * rare error cases so the overhead is not critical. 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)
{
	xfs_fileoff_t		remaining = length;
	int			error = 0;

	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));

	do {
		int		done;
		xfs_bmbt_irec_t	imap;
		int		nimaps = 1;
		xfs_fsblock_t	firstblock;
		xfs_bmap_free_t flist;

		/*
		 * Map the range first and check that it is a delalloc extent
		 * before trying to unmap the range. Otherwise we will be
		 * trying to remove a real extent (which requires a
		 * transaction) or a hole, which is probably a bad idea...
		 */
		error = xfs_bmapi_read(ip, start_fsb, 1, &imap, &nimaps,
				       XFS_BMAPI_ENTIRE);

		if (error) {
			/* something screwed, just bail */
			if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
				xfs_alert(ip->i_mount,
			"Failed delalloc mapping lookup ino %lld fsb %lld.",
						ip->i_ino, start_fsb);
			}
			break;
		}
		if (!nimaps) {
			/* nothing there */
			goto next_block;
		}
		if (imap.br_startblock != DELAYSTARTBLOCK) {
			/* been converted, ignore */
			goto next_block;
		}
		WARN_ON(imap.br_blockcount == 0);

		/*
		 * Note: while we initialise the firstblock/flist pair, they
		 * should never be used because blocks should never be
		 * allocated or freed for a delalloc extent and hence we need
		 * don't cancel or finish them after the xfs_bunmapi() call.
		 */
		xfs_bmap_init(&flist, &firstblock);
		error = xfs_bunmapi(NULL, ip, start_fsb, 1, 0, 1, &firstblock,
					&flist, &done);
		if (error)
			break;

		ASSERT(!flist.xbf_count && !flist.xbf_first);
next_block:
		start_fsb++;
		remaining--;
	} while(remaining > 0);

	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(ip->i_d.di_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 &&
	    VN_CACHED(VFS_I(ip)) == 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 by xfs_inactive to free any blocks beyond eof
 * when the link count isn't zero and by xfs_dm_punch_hole() when
 * punching a hole to EOF.
 */
int
xfs_free_eofblocks(
	xfs_mount_t	*mp,
	xfs_inode_t	*ip,
	bool		need_iolock)
{
	xfs_trans_t	*tp;
	int		error;
	xfs_fileoff_t	end_fsb;
	xfs_fileoff_t	last_fsb;
	xfs_filblks_t	map_len;
	int		nimaps;
	xfs_bmbt_irec_t	imap;

	/*
	 * 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 (!error && (nimaps != 0) &&
	    (imap.br_startblock != HOLESTARTBLOCK ||
	     ip->i_delayed_blks)) {
		/*
		 * Attach the dquots to the inode up front.
		 */
		error = xfs_qm_dqattach(ip, 0);
		if (error)
			return error;

		/*
		 * There are blocks after the end of file.
		 * Free them up now by truncating the file to
		 * its current size.
		 */
		tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);

		if (need_iolock) {
			if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
				xfs_trans_cancel(tp, 0);
				return EAGAIN;
			}
		}

		error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
		if (error) {
			ASSERT(XFS_FORCED_SHUTDOWN(mp));
			xfs_trans_cancel(tp, 0);
			if (need_iolock)
				xfs_iunlock(ip, XFS_IOLOCK_EXCL);
			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(&tp, ip, XFS_DATA_FORK,
					      XFS_ISIZE(ip));
		if (error) {
			/*
			 * If we get an error at this point we simply don't
			 * bother truncating the file.
			 */
			xfs_trans_cancel(tp,
					 (XFS_TRANS_RELEASE_LOG_RES |
					  XFS_TRANS_ABORT));
		} else {
			error = xfs_trans_commit(tp,
						XFS_TRANS_RELEASE_LOG_RES);
			if (!error)
				xfs_inode_clear_eofblocks_tag(ip);
		}

		xfs_iunlock(ip, XFS_ILOCK_EXCL);
		if (need_iolock)
			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
	}
	return error;
}

/*
 * xfs_alloc_file_space()
 *      This routine allocates disk space for the given file.
 *
 *	If alloc_type == 0, this request is for an ALLOCSP type
 *	request which will change the file size.  In this case, no
 *	DMAPI event will be generated by the call.  A TRUNCATE event
 *	will be generated later by xfs_setattr.
 *
 *	If alloc_type != 0, this request is for a RESVSP type
 *	request, and a DMAPI DM_EVENT_WRITE will be generated if the
 *	lower block boundary byte address is less than the file's
 *	length.
 *
 * RETURNS:
 *       0 on success
 *      errno on error
 *
 */
STATIC int
xfs_alloc_file_space(
	xfs_inode_t		*ip,
	xfs_off_t		offset,
	xfs_off_t		len,
	int			alloc_type,
	int			attr_flags)
{
	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;
	xfs_fsblock_t		firstfsb;
	int			nimaps;
	int			quota_flag;
	int			rt;
	xfs_trans_t		*tp;
	xfs_bmbt_irec_t		imaps[1], *imapp;
	xfs_bmap_free_t		free_list;
	uint			qblocks, resblks, resrtextents;
	int			committed;
	int			error;

	trace_xfs_alloc_file_space(ip);

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

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

	if (len <= 0)
		return XFS_ERROR(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;
			if ((temp = do_mod(startoffset_fsb, extsz)))
				e += temp;
			if ((temp = do_mod(e, extsz)))
				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.
		 */
		tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
		error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
					  resblks, resrtextents);
		/*
		 * Check for running out of space
		 */
		if (error) {
			/*
			 * Free the transaction structure.
			 */
			ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
			xfs_trans_cancel(tp, 0);
			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);

		xfs_bmap_init(&free_list, &firstfsb);
		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
					allocatesize_fsb, alloc_type, &firstfsb,
					0, imapp, &nimaps, &free_list);
		if (error) {
			goto error0;
		}

		/*
		 * Complete the transaction
		 */
		error = xfs_bmap_finish(&tp, &free_list, &committed);
		if (error) {
			goto error0;
		}

		error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
		xfs_iunlock(ip, XFS_ILOCK_EXCL);
		if (error) {
			break;
		}

		allocated_fsb = imapp->br_blockcount;

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

		startoffset_fsb += allocated_fsb;
		allocatesize_fsb -= allocated_fsb;
	}

	return error;

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

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

/*
 * Zero file bytes between startoff and endoff inclusive.
 * The iolock is held exclusive and no blocks are buffered.
 *
 * This function is used by xfs_free_file_space() to zero
 * partial blocks when the range to free is not block aligned.
 * When unreserving space with boundaries that are not block
 * aligned we round up the start and round down the end
 * boundaries and then use this function to zero the parts of
 * the blocks that got dropped during the rounding.
 */
STATIC int
xfs_zero_remaining_bytes(
	xfs_inode_t		*ip,
	xfs_off_t		startoff,
	xfs_off_t		endoff)
{
	xfs_bmbt_irec_t		imap;
	xfs_fileoff_t		offset_fsb;
	xfs_off_t		lastoffset;
	xfs_off_t		offset;
	xfs_buf_t		*bp;
	xfs_mount_t		*mp = ip->i_mount;
	int			nimap;
	int			error = 0;

	/*
	 * Avoid doing I/O beyond eof - it's not necessary
	 * since nothing can read beyond eof.  The space will
	 * be zeroed when the file is extended anyway.
	 */
	if (startoff >= XFS_ISIZE(ip))
		return 0;

	if (endoff > XFS_ISIZE(ip))
		endoff = XFS_ISIZE(ip);

	bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ?
					mp->m_rtdev_targp : mp->m_ddev_targp,
				  BTOBB(mp->m_sb.sb_blocksize), 0);
	if (!bp)
		return XFS_ERROR(ENOMEM);

	xfs_buf_unlock(bp);

	for (offset = startoff; offset <= endoff; offset = lastoffset + 1) {
		offset_fsb = XFS_B_TO_FSBT(mp, offset);
		nimap = 1;
		error = xfs_bmapi_read(ip, offset_fsb, 1, &imap, &nimap, 0);
		if (error || nimap < 1)
			break;
		ASSERT(imap.br_blockcount >= 1);
		ASSERT(imap.br_startoff == offset_fsb);
		lastoffset = XFS_FSB_TO_B(mp, imap.br_startoff + 1) - 1;
		if (lastoffset > endoff)
			lastoffset = endoff;
		if (imap.br_startblock == HOLESTARTBLOCK)
			continue;
		ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
		if (imap.br_state == XFS_EXT_UNWRITTEN)
			continue;
		XFS_BUF_UNDONE(bp);
		XFS_BUF_UNWRITE(bp);
		XFS_BUF_READ(bp);
		XFS_BUF_SET_ADDR(bp, xfs_fsb_to_db(ip, imap.br_startblock));
		xfsbdstrat(mp, bp);
		error = xfs_buf_iowait(bp);
		if (error) {
			xfs_buf_ioerror_alert(bp,
					"xfs_zero_remaining_bytes(read)");
			break;
		}
		memset(bp->b_addr +
			(offset - XFS_FSB_TO_B(mp, imap.br_startoff)),
		      0, lastoffset - offset + 1);
		XFS_BUF_UNDONE(bp);
		XFS_BUF_UNREAD(bp);
		XFS_BUF_WRITE(bp);
		xfsbdstrat(mp, bp);
		error = xfs_buf_iowait(bp);
		if (error) {
			xfs_buf_ioerror_alert(bp,
					"xfs_zero_remaining_bytes(write)");
			break;
		}
	}
	xfs_buf_free(bp);
	return error;
}

/*
 * xfs_free_file_space()
 *      This routine frees disk space for the given file.
 *
 *	This routine is only called by xfs_change_file_space
 *	for an UNRESVSP type call.
 *
 * RETURNS:
 *       0 on success
 *      errno on error
 *
 */
STATIC int
xfs_free_file_space(
	xfs_inode_t		*ip,
	xfs_off_t		offset,
	xfs_off_t		len,
	int			attr_flags)
{
	int			committed;
	int			done;
	xfs_fileoff_t		endoffset_fsb;
	int			error;
	xfs_fsblock_t		firstfsb;
	xfs_bmap_free_t		free_list;
	xfs_bmbt_irec_t		imap;
	xfs_off_t		ioffset;
	xfs_extlen_t		mod=0;
	xfs_mount_t		*mp;
	int			nimap;
	uint			resblks;
	xfs_off_t		rounding;
	int			rt;
	xfs_fileoff_t		startoffset_fsb;
	xfs_trans_t		*tp;
	int			need_iolock = 1;

	mp = ip->i_mount;

	trace_xfs_free_file_space(ip);

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

	error = 0;
	if (len <= 0)	/* if nothing being freed */
		return error;
	rt = XFS_IS_REALTIME_INODE(ip);
	startoffset_fsb	= XFS_B_TO_FSB(mp, offset);
	endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);

	if (attr_flags & XFS_ATTR_NOLOCK)
		need_iolock = 0;
	if (need_iolock) {
		xfs_ilock(ip, XFS_IOLOCK_EXCL);
		/* wait for the completion of any pending DIOs */
		inode_dio_wait(VFS_I(ip));
	}

	rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
	ioffset = offset & ~(rounding - 1);
	error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
					      ioffset, -1);
	if (error)
		goto out_unlock_iolock;
	truncate_pagecache_range(VFS_I(ip), ioffset, -1);

	/*
	 * Need to zero the stuff we're not freeing, on disk.
	 * If it's a realtime file & can't use unwritten extents then we
	 * actually need to zero the extent edges.  Otherwise xfs_bunmapi
	 * will take care of it for us.
	 */
	if (rt && !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
		nimap = 1;
		error = xfs_bmapi_read(ip, startoffset_fsb, 1,
					&imap, &nimap, 0);
		if (error)
			goto out_unlock_iolock;
		ASSERT(nimap == 0 || nimap == 1);
		if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
			xfs_daddr_t	block;

			ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
			block = imap.br_startblock;
			mod = do_div(block, mp->m_sb.sb_rextsize);
			if (mod)
				startoffset_fsb += mp->m_sb.sb_rextsize - mod;
		}
		nimap = 1;
		error = xfs_bmapi_read(ip, endoffset_fsb - 1, 1,
					&imap, &nimap, 0);
		if (error)
			goto out_unlock_iolock;
		ASSERT(nimap == 0 || nimap == 1);
		if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
			ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
			mod++;
			if (mod && (mod != mp->m_sb.sb_rextsize))
				endoffset_fsb -= mod;
		}
	}
	if ((done = (endoffset_fsb <= startoffset_fsb)))
		/*
		 * One contiguous piece to clear
		 */
		error = xfs_zero_remaining_bytes(ip, offset, offset + len - 1);
	else {
		/*
		 * Some full blocks, possibly two pieces to clear
		 */
		if (offset < XFS_FSB_TO_B(mp, startoffset_fsb))
			error = xfs_zero_remaining_bytes(ip, offset,
				XFS_FSB_TO_B(mp, startoffset_fsb) - 1);
		if (!error &&
		    XFS_FSB_TO_B(mp, endoffset_fsb) < offset + len)
			error = xfs_zero_remaining_bytes(ip,
				XFS_FSB_TO_B(mp, endoffset_fsb),
				offset + len - 1);
	}

	/*
	 * free file space until done or until there is an error
	 */
	resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
	while (!error && !done) {

		/*
		 * allocate and setup the transaction. Allow this
		 * transaction to dip into the reserve blocks to ensure
		 * the freeing of the space succeeds at ENOSPC.
		 */
		tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
		tp->t_flags |= XFS_TRANS_RESERVE;
		error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write, resblks, 0);

		/*
		 * check for running out of space
		 */
		if (error) {
			/*
			 * Free the transaction structure.
			 */
			ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
			xfs_trans_cancel(tp, 0);
			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 error1;

		xfs_trans_ijoin(tp, ip, 0);

		/*
		 * issue the bunmapi() call to free the blocks
		 */
		xfs_bmap_init(&free_list, &firstfsb);
		error = xfs_bunmapi(tp, ip, startoffset_fsb,
				  endoffset_fsb - startoffset_fsb,
				  0, 2, &firstfsb, &free_list, &done);
		if (error) {
			goto error0;
		}

		/*
		 * complete the transaction
		 */
		error = xfs_bmap_finish(&tp, &free_list, &committed);
		if (error) {
			goto error0;
		}

		error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
		xfs_iunlock(ip, XFS_ILOCK_EXCL);
	}

 out_unlock_iolock:
	if (need_iolock)
		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
	return error;

 error0:
	xfs_bmap_cancel(&free_list);
 error1:
	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
	xfs_iunlock(ip, need_iolock ? (XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL) :
		    XFS_ILOCK_EXCL);
	return error;
}


STATIC int
xfs_zero_file_space(
	struct xfs_inode	*ip,
	xfs_off_t		offset,
	xfs_off_t		len,
	int			attr_flags)
{
	struct xfs_mount	*mp = ip->i_mount;
	uint			granularity;
	xfs_off_t		start_boundary;
	xfs_off_t		end_boundary;
	int			error;

	granularity = max_t(uint, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);

	/*
	 * Round the range of extents we are going to convert inwards.  If the
	 * offset is aligned, then it doesn't get changed so we zero from the
	 * start of the block offset points to.
	 */
	start_boundary = round_up(offset, granularity);
	end_boundary = round_down(offset + len, granularity);

	ASSERT(start_boundary >= offset);
	ASSERT(end_boundary <= offset + len);

	if (!(attr_flags & XFS_ATTR_NOLOCK))
		xfs_ilock(ip, XFS_IOLOCK_EXCL);

	if (start_boundary < end_boundary - 1) {
		/* punch out the page cache over the conversion range */
		truncate_pagecache_range(VFS_I(ip), start_boundary,
					 end_boundary - 1);
		/* convert the blocks */
		error = xfs_alloc_file_space(ip, start_boundary,
					end_boundary - start_boundary - 1,
					XFS_BMAPI_PREALLOC | XFS_BMAPI_CONVERT,
					attr_flags);
		if (error)
			goto out_unlock;

		/* We've handled the interior of the range, now for the edges */
		if (start_boundary != offset)
			error = xfs_iozero(ip, offset, start_boundary - offset);
		if (error)
			goto out_unlock;

		if (end_boundary != offset + len)
			error = xfs_iozero(ip, end_boundary,
					   offset + len - end_boundary);

	} else {
		/*
		 * It's either a sub-granularity range or the range spanned lies
		 * partially across two adjacent blocks.
		 */
		error = xfs_iozero(ip, offset, len);
	}

out_unlock:
	if (!(attr_flags & XFS_ATTR_NOLOCK))
		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
	return error;

}

/*
 * xfs_change_file_space()
 *      This routine allocates or frees disk space for the given file.
 *      The user specified parameters are checked for alignment and size
 *      limitations.
 *
 * RETURNS:
 *       0 on success
 *      errno on error
 *
 */
int
xfs_change_file_space(
	xfs_inode_t	*ip,
	int		cmd,
	xfs_flock64_t	*bf,
	xfs_off_t	offset,
	int		attr_flags)
{
	xfs_mount_t	*mp = ip->i_mount;
	int		clrprealloc;
	int		error;
	xfs_fsize_t	fsize;
	int		setprealloc;
	xfs_off_t	startoffset;
	xfs_trans_t	*tp;
	struct iattr	iattr;

	if (!S_ISREG(ip->i_d.di_mode))
		return XFS_ERROR(EINVAL);

	switch (bf->l_whence) {
	case 0: /*SEEK_SET*/
		break;
	case 1: /*SEEK_CUR*/
		bf->l_start += offset;
		break;
	case 2: /*SEEK_END*/
		bf->l_start += XFS_ISIZE(ip);
		break;
	default:
		return XFS_ERROR(EINVAL);
	}

	/*
	 * length of <= 0 for resv/unresv/zero is invalid.  length for
	 * alloc/free is ignored completely and we have no idea what userspace
	 * might have set it to, so set it to zero to allow range
	 * checks to pass.
	 */
	switch (cmd) {
	case XFS_IOC_ZERO_RANGE:
	case XFS_IOC_RESVSP:
	case XFS_IOC_RESVSP64:
	case XFS_IOC_UNRESVSP:
	case XFS_IOC_UNRESVSP64:
		if (bf->l_len <= 0)
			return XFS_ERROR(EINVAL);
		break;
	default:
		bf->l_len = 0;
		break;
	}

	if (bf->l_start < 0 ||
	    bf->l_start > mp->m_super->s_maxbytes ||
	    bf->l_start + bf->l_len < 0 ||
	    bf->l_start + bf->l_len >= mp->m_super->s_maxbytes)
		return XFS_ERROR(EINVAL);

	bf->l_whence = 0;

	startoffset = bf->l_start;
	fsize = XFS_ISIZE(ip);

	setprealloc = clrprealloc = 0;
	switch (cmd) {
	case XFS_IOC_ZERO_RANGE:
		error = xfs_zero_file_space(ip, startoffset, bf->l_len,
						attr_flags);
		if (error)
			return error;
		setprealloc = 1;
		break;

	case XFS_IOC_RESVSP:
	case XFS_IOC_RESVSP64:
		error = xfs_alloc_file_space(ip, startoffset, bf->l_len,
						XFS_BMAPI_PREALLOC, attr_flags);
		if (error)
			return error;
		setprealloc = 1;
		break;

	case XFS_IOC_UNRESVSP:
	case XFS_IOC_UNRESVSP64:
		if ((error = xfs_free_file_space(ip, startoffset, bf->l_len,
								attr_flags)))
			return error;
		break;

	case XFS_IOC_ALLOCSP:
	case XFS_IOC_ALLOCSP64:
	case XFS_IOC_FREESP:
	case XFS_IOC_FREESP64:
		/*
		 * These operations actually do IO when extending the file, but
		 * the allocation is done seperately to the zeroing that is
		 * done. This set of operations need to be serialised against
		 * other IO operations, such as truncate and buffered IO. We
		 * need to take the IOLOCK here to serialise the allocation and
		 * zeroing IO to prevent other IOLOCK holders (e.g. getbmap,
		 * truncate, direct IO) from racing against the transient
		 * allocated but not written state we can have here.
		 */
		xfs_ilock(ip, XFS_IOLOCK_EXCL);
		if (startoffset > fsize) {
			error = xfs_alloc_file_space(ip, fsize,
					startoffset - fsize, 0,
					attr_flags | XFS_ATTR_NOLOCK);
			if (error) {
				xfs_iunlock(ip, XFS_IOLOCK_EXCL);
				break;
			}
		}

		iattr.ia_valid = ATTR_SIZE;
		iattr.ia_size = startoffset;

		error = xfs_setattr_size(ip, &iattr,
					 attr_flags | XFS_ATTR_NOLOCK);
		xfs_iunlock(ip, XFS_IOLOCK_EXCL);

		if (error)
			return error;

		clrprealloc = 1;
		break;

	default:
		ASSERT(0);
		return XFS_ERROR(EINVAL);
	}

	/*
	 * update the inode timestamp, mode, and prealloc flag bits
	 */
	tp = xfs_trans_alloc(mp, XFS_TRANS_WRITEID);
	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_writeid, 0, 0);
	if (error) {
		xfs_trans_cancel(tp, 0);
		return error;
	}

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

	if ((attr_flags & XFS_ATTR_DMI) == 0) {
		ip->i_d.di_mode &= ~S_ISUID;

		/*
		 * Note that we don't have to worry about mandatory
		 * file locking being disabled here because we only
		 * clear the S_ISGID bit if the Group execute bit is
		 * on, but if it was on then mandatory locking wouldn't
		 * have been enabled.
		 */
		if (ip->i_d.di_mode & S_IXGRP)
			ip->i_d.di_mode &= ~S_ISGID;

		xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
	}
	if (setprealloc)
		ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
	else if (clrprealloc)
		ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC;

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
	if (attr_flags & XFS_ATTR_SYNC)
		xfs_trans_set_sync(tp);
	return xfs_trans_commit(tp, 0);
}

/*
 * 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(
	xfs_inode_t	*ip,	/* target inode */
	xfs_inode_t	*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 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_BOFF(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_BOFF(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;
}

int
xfs_swap_extents(
	xfs_inode_t	*ip,	/* target inode */
	xfs_inode_t	*tip,	/* tmp inode */
	xfs_swapext_t	*sxp)
{
	xfs_mount_t	*mp = ip->i_mount;
	xfs_trans_t	*tp;
	xfs_bstat_t	*sbp = &sxp->sx_stat;
	xfs_ifork_t	*tempifp, *ifp, *tifp;
	int		src_log_flags, target_log_flags;
	int		error = 0;
	int		aforkblks = 0;
	int		taforkblks = 0;
	__uint64_t	tmp;

	tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
	if (!tempifp) {
		error = XFS_ERROR(ENOMEM);
		goto out;
	}

	/*
	 * we have to do two separate lock calls here to keep lockdep
	 * happy. If we try to get all the locks in one call, lock will
	 * report false positives when we drop the ILOCK and regain them
	 * below.
	 */
	xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
	xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);

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

	error = -filemap_write_and_wait(VFS_I(tip)->i_mapping);
	if (error)
		goto out_unlock;
	truncate_pagecache_range(VFS_I(tip), 0, -1);

	/* Verify O_DIRECT for ftmp */
	if (VN_CACHED(VFS_I(tip)) != 0) {
		error = XFS_ERROR(EINVAL);
		goto out_unlock;
	}

	/* 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 = XFS_ERROR(EFAULT);
		goto out_unlock;
	}

	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_unlock;
	}

	/*
	 * 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 = XFS_ERROR(EBUSY);
		goto out_unlock;
	}

	/* We need to fail if the file is memory mapped.  Once we have tossed
	 * all existing pages, the page fault will have no option
	 * but to go to the filesystem for pages. By making the page fault call
	 * vop_read (or write in the case of autogrow) they block on the iolock
	 * until we have switched the extents.
	 */
	if (VN_MAPPED(VFS_I(ip))) {
		error = XFS_ERROR(EBUSY);
		goto out_unlock;
	}

	xfs_iunlock(ip, XFS_ILOCK_EXCL);
	xfs_iunlock(tip, XFS_ILOCK_EXCL);

	/*
	 * There is a race condition here since we gave up the
	 * ilock.  However, the data fork will not change since
	 * we have the iolock (locked for truncation too) so we
	 * are safe.  We don't really care if non-io related
	 * fields change.
	 */
	truncate_pagecache_range(VFS_I(ip), 0, -1);

	tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
	if (error) {
		xfs_iunlock(ip,  XFS_IOLOCK_EXCL);
		xfs_iunlock(tip, XFS_IOLOCK_EXCL);
		xfs_trans_cancel(tp, 0);
		goto out;
	}
	xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);

	/*
	 * 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, &aforkblks);
		if (error)
			goto out_trans_cancel;
	}
	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,
			&taforkblks);
		if (error)
			goto out_trans_cancel;
	}

	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
	xfs_trans_ijoin(tp, tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);

	/*
	 * Before we've swapped the forks, lets set the owners of the forks
	 * appropriately. We have to do this as we are demand paging the btree
	 * buffers, and so the validation done on read will expect the owner
	 * field to be correctly set. Once we change the owners, we can swap the
	 * inode forks.
	 *
	 * 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 (ip->i_d.di_version == 3 &&
	    ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
		target_log_flags |= XFS_ILOG_DOWNER;
		error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK,
					      tip->i_ino, NULL);
		if (error)
			goto out_trans_cancel;
	}

	if (tip->i_d.di_version == 3 &&
	    tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
		src_log_flags |= XFS_ILOG_DOWNER;
		error = xfs_bmbt_change_owner(tp, tip, XFS_DATA_FORK,
					      ip->i_ino, NULL);
		if (error)
			goto out_trans_cancel;
	}

	/*
	 * Swap the data forks of the inodes
	 */
	ifp = &ip->i_df;
	tifp = &tip->i_df;
	*tempifp = *ifp;	/* struct copy */
	*ifp = *tifp;		/* struct copy */
	*tifp = *tempifp;	/* struct copy */

	/*
	 * 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;

	tmp = (__uint64_t) ip->i_d.di_nextents;
	ip->i_d.di_nextents = tip->i_d.di_nextents;
	tip->i_d.di_nextents = tmp;

	tmp = (__uint64_t) ip->i_d.di_format;
	ip->i_d.di_format = tip->i_d.di_format;
	tip->i_d.di_format = tmp;

	/*
	 * 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:
		/* If the extents fit in the inode, fix the
		 * pointer.  Otherwise it's already NULL or
		 * pointing to the extent.
		 */
		if (ip->i_d.di_nextents <= XFS_INLINE_EXTS) {
			ifp->if_u1.if_extents =
				ifp->if_u2.if_inline_ext;
		}
		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:
		/* If the extents fit in the inode, fix the
		 * pointer.  Otherwise it's already NULL or
		 * pointing to the extent.
		 */
		if (tip->i_d.di_nextents <= XFS_INLINE_EXTS) {
			tifp->if_u1.if_extents =
				tifp->if_u2.if_inline_ext;
		}
		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;
	}

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

	/*
	 * 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, 0);

	trace_xfs_swap_extent_after(ip, 0);
	trace_xfs_swap_extent_after(tip, 1);
out:
	kmem_free(tempifp);
	return error;

out_unlock:
	xfs_iunlock(ip,  XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
	xfs_iunlock(tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
	goto out;

out_trans_cancel:
	xfs_trans_cancel(tp, 0);
	goto out_unlock;
}