summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_vnodeops.c
blob: 221e2e3cec8c4cb807859fe67c916c5594d6c5ad (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
/*
 * 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_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_mount.h"
#include "xfs_da_btree.h"
#include "xfs_dir2_format.h"
#include "xfs_dir2.h"
#include "xfs_bmap_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
#include "xfs_itable.h"
#include "xfs_ialloc.h"
#include "xfs_alloc.h"
#include "xfs_bmap.h"
#include "xfs_acl.h"
#include "xfs_attr.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_utils.h"
#include "xfs_rtalloc.h"
#include "xfs_trans_space.h"
#include "xfs_log_priv.h"
#include "xfs_filestream.h"
#include "xfs_vnodeops.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_symlink.h"


/*
 * 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, 0,
					  XFS_ITRUNCATE_LOG_RES(mp),
					  0, XFS_TRANS_PERM_LOG_RES,
					  XFS_ITRUNCATE_LOG_COUNT);
		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;
}

int
xfs_release(
	xfs_inode_t	*ip)
{
	xfs_mount_t	*mp = ip->i_mount;
	int		error;

	if (!S_ISREG(ip->i_d.di_mode) || (ip->i_d.di_mode == 0))
		return 0;

	/* If this is a read-only mount, don't do this (would generate I/O) */
	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return 0;

	if (!XFS_FORCED_SHUTDOWN(mp)) {
		int truncated;

		/*
		 * If we are using filestreams, and we have an unlinked
		 * file that we are processing the last close on, then nothing
		 * will be able to reopen and write to this file. Purge this
		 * inode from the filestreams cache so that it doesn't delay
		 * teardown of the inode.
		 */
		if ((ip->i_d.di_nlink == 0) && xfs_inode_is_filestream(ip))
			xfs_filestream_deassociate(ip);

		/*
		 * If we previously truncated this file and removed old data
		 * in the process, we want to initiate "early" writeout on
		 * the last close.  This is an attempt to combat the notorious
		 * NULL files problem which is particularly noticeable from a
		 * truncate down, buffered (re-)write (delalloc), followed by
		 * a crash.  What we are effectively doing here is
		 * significantly reducing the time window where we'd otherwise
		 * be exposed to that problem.
		 */
		truncated = xfs_iflags_test_and_clear(ip, XFS_ITRUNCATED);
		if (truncated) {
			xfs_iflags_clear(ip, XFS_IDIRTY_RELEASE);
			if (VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0) {
				error = -filemap_flush(VFS_I(ip)->i_mapping);
				if (error)
					return error;
			}
		}
	}

	if (ip->i_d.di_nlink == 0)
		return 0;

	if (xfs_can_free_eofblocks(ip, false)) {

		/*
		 * If we can't get the iolock just skip truncating the blocks
		 * past EOF because we could deadlock with the mmap_sem
		 * otherwise.  We'll get another chance to drop them once the
		 * last reference to the inode is dropped, so we'll never leak
		 * blocks permanently.
		 *
		 * Further, check if the inode is being opened, written and
		 * closed frequently and we have delayed allocation blocks
		 * outstanding (e.g. streaming writes from the NFS server),
		 * truncating the blocks past EOF will cause fragmentation to
		 * occur.
		 *
		 * In this case don't do the truncation, either, but we have to
		 * be careful how we detect this case. Blocks beyond EOF show
		 * up as i_delayed_blks even when the inode is clean, so we
		 * need to truncate them away first before checking for a dirty
		 * release. Hence on the first dirty close we will still remove
		 * the speculative allocation, but after that we will leave it
		 * in place.
		 */
		if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE))
			return 0;

		error = xfs_free_eofblocks(mp, ip, true);
		if (error && error != EAGAIN)
			return error;

		/* delalloc blocks after truncation means it really is dirty */
		if (ip->i_delayed_blks)
			xfs_iflags_set(ip, XFS_IDIRTY_RELEASE);
	}
	return 0;
}

/*
 * xfs_inactive
 *
 * This is called when the vnode reference count for the vnode
 * goes to zero.  If the file has been unlinked, then it must
 * now be truncated.  Also, we clear all of the read-ahead state
 * kept for the inode here since the file is now closed.
 */
int
xfs_inactive(
	xfs_inode_t	*ip)
{
	xfs_bmap_free_t	free_list;
	xfs_fsblock_t	first_block;
	int		committed;
	xfs_trans_t	*tp;
	xfs_mount_t	*mp;
	int		error;
	int		truncate = 0;

	/*
	 * If the inode is already free, then there can be nothing
	 * to clean up here.
	 */
	if (ip->i_d.di_mode == 0 || is_bad_inode(VFS_I(ip))) {
		ASSERT(ip->i_df.if_real_bytes == 0);
		ASSERT(ip->i_df.if_broot_bytes == 0);
		return VN_INACTIVE_CACHE;
	}

	mp = ip->i_mount;

	error = 0;

	/* If this is a read-only mount, don't do this (would generate I/O) */
	if (mp->m_flags & XFS_MOUNT_RDONLY)
		goto out;

	if (ip->i_d.di_nlink != 0) {
		/*
		 * force is true because we are evicting an inode from the
		 * cache. Post-eof blocks must be freed, lest we end up with
		 * broken free space accounting.
		 */
		if (xfs_can_free_eofblocks(ip, true)) {
			error = xfs_free_eofblocks(mp, ip, false);
			if (error)
				return VN_INACTIVE_CACHE;
		}
		goto out;
	}

	if (S_ISREG(ip->i_d.di_mode) &&
	    (ip->i_d.di_size != 0 || XFS_ISIZE(ip) != 0 ||
	     ip->i_d.di_nextents > 0 || ip->i_delayed_blks > 0))
		truncate = 1;

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

	tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
	error = xfs_trans_reserve(tp, 0,
			(truncate || S_ISLNK(ip->i_d.di_mode)) ?
				XFS_ITRUNCATE_LOG_RES(mp) :
				XFS_IFREE_LOG_RES(mp),
			0,
			XFS_TRANS_PERM_LOG_RES,
			XFS_ITRUNCATE_LOG_COUNT);
	if (error) {
		ASSERT(XFS_FORCED_SHUTDOWN(mp));
		xfs_trans_cancel(tp, 0);
		return VN_INACTIVE_CACHE;
	}

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

	if (S_ISLNK(ip->i_d.di_mode)) {
		error = xfs_inactive_symlink(ip, &tp);
		if (error)
			goto out_cancel;
	} else if (truncate) {
		ip->i_d.di_size = 0;
		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

		error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0);
		if (error)
			goto out_cancel;

		ASSERT(ip->i_d.di_nextents == 0);
	}

	/*
	 * If there are attributes associated with the file then blow them away
	 * now.  The code calls a routine that recursively deconstructs the
	 * attribute fork.  We need to just commit the current transaction
	 * because we can't use it for xfs_attr_inactive().
	 */
	if (ip->i_d.di_anextents > 0) {
		ASSERT(ip->i_d.di_forkoff != 0);

		error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
		if (error)
			goto out_unlock;

		xfs_iunlock(ip, XFS_ILOCK_EXCL);

		error = xfs_attr_inactive(ip);
		if (error)
			goto out;

		tp = xfs_trans_alloc(mp, XFS_TRANS_INACTIVE);
		error = xfs_trans_reserve(tp, 0,
					  XFS_IFREE_LOG_RES(mp),
					  0, XFS_TRANS_PERM_LOG_RES,
					  XFS_INACTIVE_LOG_COUNT);
		if (error) {
			xfs_trans_cancel(tp, 0);
			goto out;
		}

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

	if (ip->i_afp)
		xfs_idestroy_fork(ip, XFS_ATTR_FORK);

	ASSERT(ip->i_d.di_anextents == 0);

	/*
	 * Free the inode.
	 */
	xfs_bmap_init(&free_list, &first_block);
	error = xfs_ifree(tp, ip, &free_list);
	if (error) {
		/*
		 * If we fail to free the inode, shut down.  The cancel
		 * might do that, we need to make sure.  Otherwise the
		 * inode might be lost for a long time or forever.
		 */
		if (!XFS_FORCED_SHUTDOWN(mp)) {
			xfs_notice(mp, "%s: xfs_ifree returned error %d",
				__func__, error);
			xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
		}
		xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
	} else {
		/*
		 * Credit the quota account(s). The inode is gone.
		 */
		xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_ICOUNT, -1);

		/*
		 * Just ignore errors at this point.  There is nothing we can
		 * do except to try to keep going. Make sure it's not a silent
		 * error.
		 */
		error = xfs_bmap_finish(&tp,  &free_list, &committed);
		if (error)
			xfs_notice(mp, "%s: xfs_bmap_finish returned error %d",
				__func__, error);
		error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
		if (error)
			xfs_notice(mp, "%s: xfs_trans_commit returned error %d",
				__func__, error);
	}

	/*
	 * Release the dquots held by inode, if any.
	 */
	xfs_qm_dqdetach(ip);
out_unlock:
	xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
	return VN_INACTIVE_CACHE;
out_cancel:
	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
	goto out_unlock;
}

/*
 * Lookups up an inode from "name". If ci_name is not NULL, then a CI match
 * is allowed, otherwise it has to be an exact match. If a CI match is found,
 * ci_name->name will point to a the actual name (caller must free) or
 * will be set to NULL if an exact match is found.
 */
int
xfs_lookup(
	xfs_inode_t		*dp,
	struct xfs_name		*name,
	xfs_inode_t		**ipp,
	struct xfs_name		*ci_name)
{
	xfs_ino_t		inum;
	int			error;
	uint			lock_mode;

	trace_xfs_lookup(dp, name);

	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
		return XFS_ERROR(EIO);

	lock_mode = xfs_ilock_map_shared(dp);
	error = xfs_dir_lookup(NULL, dp, name, &inum, ci_name);
	xfs_iunlock_map_shared(dp, lock_mode);

	if (error)
		goto out;

	error = xfs_iget(dp->i_mount, NULL, inum, 0, 0, ipp);
	if (error)
		goto out_free_name;

	return 0;

out_free_name:
	if (ci_name)
		kmem_free(ci_name->name);
out:
	*ipp = NULL;
	return error;
}

int
xfs_create(
	xfs_inode_t		*dp,
	struct xfs_name		*name,
	umode_t			mode,
	xfs_dev_t		rdev,
	xfs_inode_t		**ipp)
{
	int			is_dir = S_ISDIR(mode);
	struct xfs_mount	*mp = dp->i_mount;
	struct xfs_inode	*ip = NULL;
	struct xfs_trans	*tp = NULL;
	int			error;
	xfs_bmap_free_t		free_list;
	xfs_fsblock_t		first_block;
	bool                    unlock_dp_on_error = false;
	uint			cancel_flags;
	int			committed;
	prid_t			prid;
	struct xfs_dquot	*udqp = NULL;
	struct xfs_dquot	*gdqp = NULL;
	struct xfs_dquot	*pdqp = NULL;
	uint			resblks;
	uint			log_res;
	uint			log_count;

	trace_xfs_create(dp, name);

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

	if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
		prid = xfs_get_projid(dp);
	else
		prid = XFS_PROJID_DEFAULT;

	/*
	 * Make sure that we have allocated dquot(s) on disk.
	 */
	error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
					XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
					&udqp, &gdqp, &pdqp);
	if (error)
		return error;

	if (is_dir) {
		rdev = 0;
		resblks = XFS_MKDIR_SPACE_RES(mp, name->len);
		log_res = XFS_MKDIR_LOG_RES(mp);
		log_count = XFS_MKDIR_LOG_COUNT;
		tp = xfs_trans_alloc(mp, XFS_TRANS_MKDIR);
	} else {
		resblks = XFS_CREATE_SPACE_RES(mp, name->len);
		log_res = XFS_CREATE_LOG_RES(mp);
		log_count = XFS_CREATE_LOG_COUNT;
		tp = xfs_trans_alloc(mp, XFS_TRANS_CREATE);
	}

	cancel_flags = XFS_TRANS_RELEASE_LOG_RES;

	/*
	 * Initially assume that the file does not exist and
	 * reserve the resources for that case.  If that is not
	 * the case we'll drop the one we have and get a more
	 * appropriate transaction later.
	 */
	error = xfs_trans_reserve(tp, resblks, log_res, 0,
			XFS_TRANS_PERM_LOG_RES, log_count);
	if (error == ENOSPC) {
		/* flush outstanding delalloc blocks and retry */
		xfs_flush_inodes(mp);
		error = xfs_trans_reserve(tp, resblks, log_res, 0,
				XFS_TRANS_PERM_LOG_RES, log_count);
	}
	if (error == ENOSPC) {
		/* No space at all so try a "no-allocation" reservation */
		resblks = 0;
		error = xfs_trans_reserve(tp, 0, log_res, 0,
				XFS_TRANS_PERM_LOG_RES, log_count);
	}
	if (error) {
		cancel_flags = 0;
		goto out_trans_cancel;
	}

	xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
	unlock_dp_on_error = true;

	xfs_bmap_init(&free_list, &first_block);

	/*
	 * Reserve disk quota and the inode.
	 */
	error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp,
						pdqp, resblks, 1, 0);
	if (error)
		goto out_trans_cancel;

	error = xfs_dir_canenter(tp, dp, name, resblks);
	if (error)
		goto out_trans_cancel;

	/*
	 * A newly created regular or special file just has one directory
	 * entry pointing to them, but a directory also the "." entry
	 * pointing to itself.
	 */
	error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev,
			       prid, resblks > 0, &ip, &committed);
	if (error) {
		if (error == ENOSPC)
			goto out_trans_cancel;
		goto out_trans_abort;
	}

	/*
	 * Now we join the directory inode to the transaction.  We do not do it
	 * earlier because xfs_dir_ialloc might commit the previous transaction
	 * (and release all the locks).  An error from here on will result in
	 * the transaction cancel unlocking dp so don't do it explicitly in the
	 * error path.
	 */
	xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
	unlock_dp_on_error = false;

	error = xfs_dir_createname(tp, dp, name, ip->i_ino,
					&first_block, &free_list, resblks ?
					resblks - XFS_IALLOC_SPACE_RES(mp) : 0);
	if (error) {
		ASSERT(error != ENOSPC);
		goto out_trans_abort;
	}
	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);

	if (is_dir) {
		error = xfs_dir_init(tp, ip, dp);
		if (error)
			goto out_bmap_cancel;

		error = xfs_bumplink(tp, dp);
		if (error)
			goto out_bmap_cancel;
	}

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

	/*
	 * Attach the dquot(s) to the inodes and modify them incore.
	 * These ids of the inode couldn't have changed since the new
	 * inode has been locked ever since it was created.
	 */
	xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);

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

	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
	if (error)
		goto out_release_inode;

	xfs_qm_dqrele(udqp);
	xfs_qm_dqrele(gdqp);
	xfs_qm_dqrele(pdqp);

	*ipp = ip;
	return 0;

 out_bmap_cancel:
	xfs_bmap_cancel(&free_list);
 out_trans_abort:
	cancel_flags |= XFS_TRANS_ABORT;
 out_trans_cancel:
	xfs_trans_cancel(tp, cancel_flags);
 out_release_inode:
	/*
	 * Wait until after the current transaction is aborted to
	 * release the inode.  This prevents recursive transactions
	 * and deadlocks from xfs_inactive.
	 */
	if (ip)
		IRELE(ip);

	xfs_qm_dqrele(udqp);
	xfs_qm_dqrele(gdqp);
	xfs_qm_dqrele(pdqp);

	if (unlock_dp_on_error)
		xfs_iunlock(dp, XFS_ILOCK_EXCL);
	return error;
}

#ifdef DEBUG
int xfs_locked_n;
int xfs_small_retries;
int xfs_middle_retries;
int xfs_lots_retries;
int xfs_lock_delays;
#endif

/*
 * Bump the subclass so xfs_lock_inodes() acquires each lock with
 * a different value
 */
static inline int
xfs_lock_inumorder(int lock_mode, int subclass)
{
	if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL))
		lock_mode |= (subclass + XFS_LOCK_INUMORDER) << XFS_IOLOCK_SHIFT;
	if (lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL))
		lock_mode |= (subclass + XFS_LOCK_INUMORDER) << XFS_ILOCK_SHIFT;

	return lock_mode;
}

/*
 * The following routine will lock n inodes in exclusive mode.
 * We assume the caller calls us with the inodes in i_ino order.
 *
 * We need to detect deadlock where an inode that we lock
 * is in the AIL and we start waiting for another inode that is locked
 * by a thread in a long running transaction (such as truncate). This can
 * result in deadlock since the long running trans might need to wait
 * for the inode we just locked in order to push the tail and free space
 * in the log.
 */
void
xfs_lock_inodes(
	xfs_inode_t	**ips,
	int		inodes,
	uint		lock_mode)
{
	int		attempts = 0, i, j, try_lock;
	xfs_log_item_t	*lp;

	ASSERT(ips && (inodes >= 2)); /* we need at least two */

	try_lock = 0;
	i = 0;

again:
	for (; i < inodes; i++) {
		ASSERT(ips[i]);

		if (i && (ips[i] == ips[i-1]))	/* Already locked */
			continue;

		/*
		 * If try_lock is not set yet, make sure all locked inodes
		 * are not in the AIL.
		 * If any are, set try_lock to be used later.
		 */

		if (!try_lock) {
			for (j = (i - 1); j >= 0 && !try_lock; j--) {
				lp = (xfs_log_item_t *)ips[j]->i_itemp;
				if (lp && (lp->li_flags & XFS_LI_IN_AIL)) {
					try_lock++;
				}
			}
		}

		/*
		 * If any of the previous locks we have locked is in the AIL,
		 * we must TRY to get the second and subsequent locks. If
		 * we can't get any, we must release all we have
		 * and try again.
		 */

		if (try_lock) {
			/* try_lock must be 0 if i is 0. */
			/*
			 * try_lock means we have an inode locked
			 * that is in the AIL.
			 */
			ASSERT(i != 0);
			if (!xfs_ilock_nowait(ips[i], xfs_lock_inumorder(lock_mode, i))) {
				attempts++;

				/*
				 * Unlock all previous guys and try again.
				 * xfs_iunlock will try to push the tail
				 * if the inode is in the AIL.
				 */

				for(j = i - 1; j >= 0; j--) {

					/*
					 * Check to see if we've already
					 * unlocked this one.
					 * Not the first one going back,
					 * and the inode ptr is the same.
					 */
					if ((j != (i - 1)) && ips[j] ==
								ips[j+1])
						continue;

					xfs_iunlock(ips[j], lock_mode);
				}

				if ((attempts % 5) == 0) {
					delay(1); /* Don't just spin the CPU */
#ifdef DEBUG
					xfs_lock_delays++;
#endif
				}
				i = 0;
				try_lock = 0;
				goto again;
			}
		} else {
			xfs_ilock(ips[i], xfs_lock_inumorder(lock_mode, i));
		}
	}

#ifdef DEBUG
	if (attempts) {
		if (attempts < 5) xfs_small_retries++;
		else if (attempts < 100) xfs_middle_retries++;
		else xfs_lots_retries++;
	} else {
		xfs_locked_n++;
	}
#endif
}

/*
 * xfs_lock_two_inodes() can only be used to lock one type of lock
 * at a time - the iolock or the ilock, but not both at once. If
 * we lock both at once, lockdep will report false positives saying
 * we have violated locking orders.
 */
void
xfs_lock_two_inodes(
	xfs_inode_t		*ip0,
	xfs_inode_t		*ip1,
	uint			lock_mode)
{
	xfs_inode_t		*temp;
	int			attempts = 0;
	xfs_log_item_t		*lp;

	if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL))
		ASSERT((lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)) == 0);
	ASSERT(ip0->i_ino != ip1->i_ino);

	if (ip0->i_ino > ip1->i_ino) {
		temp = ip0;
		ip0 = ip1;
		ip1 = temp;
	}

 again:
	xfs_ilock(ip0, xfs_lock_inumorder(lock_mode, 0));

	/*
	 * If the first lock we have locked is in the AIL, we must TRY to get
	 * the second lock. If we can't get it, we must release the first one
	 * and try again.
	 */
	lp = (xfs_log_item_t *)ip0->i_itemp;
	if (lp && (lp->li_flags & XFS_LI_IN_AIL)) {
		if (!xfs_ilock_nowait(ip1, xfs_lock_inumorder(lock_mode, 1))) {
			xfs_iunlock(ip0, lock_mode);
			if ((++attempts % 5) == 0)
				delay(1); /* Don't just spin the CPU */
			goto again;
		}
	} else {
		xfs_ilock(ip1, xfs_lock_inumorder(lock_mode, 1));
	}
}

int
xfs_remove(
	xfs_inode_t             *dp,
	struct xfs_name		*name,
	xfs_inode_t		*ip)
{
	xfs_mount_t		*mp = dp->i_mount;
	xfs_trans_t             *tp = NULL;
	int			is_dir = S_ISDIR(ip->i_d.di_mode);
	int                     error = 0;
	xfs_bmap_free_t         free_list;
	xfs_fsblock_t           first_block;
	int			cancel_flags;
	int			committed;
	int			link_zero;
	uint			resblks;
	uint			log_count;

	trace_xfs_remove(dp, name);

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

	error = xfs_qm_dqattach(dp, 0);
	if (error)
		goto std_return;

	error = xfs_qm_dqattach(ip, 0);
	if (error)
		goto std_return;

	if (is_dir) {
		tp = xfs_trans_alloc(mp, XFS_TRANS_RMDIR);
		log_count = XFS_DEFAULT_LOG_COUNT;
	} else {
		tp = xfs_trans_alloc(mp, XFS_TRANS_REMOVE);
		log_count = XFS_REMOVE_LOG_COUNT;
	}
	cancel_flags = XFS_TRANS_RELEASE_LOG_RES;

	/*
	 * We try to get the real space reservation first,
	 * allowing for directory btree deletion(s) implying
	 * possible bmap insert(s).  If we can't get the space
	 * reservation then we use 0 instead, and avoid the bmap
	 * btree insert(s) in the directory code by, if the bmap
	 * insert tries to happen, instead trimming the LAST
	 * block from the directory.
	 */
	resblks = XFS_REMOVE_SPACE_RES(mp);
	error = xfs_trans_reserve(tp, resblks, XFS_REMOVE_LOG_RES(mp), 0,
				  XFS_TRANS_PERM_LOG_RES, log_count);
	if (error == ENOSPC) {
		resblks = 0;
		error = xfs_trans_reserve(tp, 0, XFS_REMOVE_LOG_RES(mp), 0,
					  XFS_TRANS_PERM_LOG_RES, log_count);
	}
	if (error) {
		ASSERT(error != ENOSPC);
		cancel_flags = 0;
		goto out_trans_cancel;
	}

	xfs_lock_two_inodes(dp, ip, XFS_ILOCK_EXCL);

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

	/*
	 * If we're removing a directory perform some additional validation.
	 */
	if (is_dir) {
		ASSERT(ip->i_d.di_nlink >= 2);
		if (ip->i_d.di_nlink != 2) {
			error = XFS_ERROR(ENOTEMPTY);
			goto out_trans_cancel;
		}
		if (!xfs_dir_isempty(ip)) {
			error = XFS_ERROR(ENOTEMPTY);
			goto out_trans_cancel;
		}
	}

	xfs_bmap_init(&free_list, &first_block);
	error = xfs_dir_removename(tp, dp, name, ip->i_ino,
					&first_block, &free_list, resblks);
	if (error) {
		ASSERT(error != ENOENT);
		goto out_bmap_cancel;
	}
	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);

	if (is_dir) {
		/*
		 * Drop the link from ip's "..".
		 */
		error = xfs_droplink(tp, dp);
		if (error)
			goto out_bmap_cancel;

		/*
		 * Drop the "." link from ip to self.
		 */
		error = xfs_droplink(tp, ip);
		if (error)
			goto out_bmap_cancel;
	} else {
		/*
		 * When removing a non-directory we need to log the parent
		 * inode here.  For a directory this is done implicitly
		 * by the xfs_droplink call for the ".." entry.
		 */
		xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
	}

	/*
	 * Drop the link from dp to ip.
	 */
	error = xfs_droplink(tp, ip);
	if (error)
		goto out_bmap_cancel;

	/*
	 * Determine if this is the last link while
	 * we are in the transaction.
	 */
	link_zero = (ip->i_d.di_nlink == 0);

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

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

	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
	if (error)
		goto std_return;

	/*
	 * If we are using filestreams, kill the stream association.
	 * If the file is still open it may get a new one but that
	 * will get killed on last close in xfs_close() so we don't
	 * have to worry about that.
	 */
	if (!is_dir && link_zero && xfs_inode_is_filestream(ip))
		xfs_filestream_deassociate(ip);

	return 0;

 out_bmap_cancel:
	xfs_bmap_cancel(&free_list);
	cancel_flags |= XFS_TRANS_ABORT;
 out_trans_cancel:
	xfs_trans_cancel(tp, cancel_flags);
 std_return:
	return error;
}

int
xfs_link(
	xfs_inode_t		*tdp,
	xfs_inode_t		*sip,
	struct xfs_name		*target_name)
{
	xfs_mount_t		*mp = tdp->i_mount;
	xfs_trans_t		*tp;
	int			error;
	xfs_bmap_free_t         free_list;
	xfs_fsblock_t           first_block;
	int			cancel_flags;
	int			committed;
	int			resblks;

	trace_xfs_link(tdp, target_name);

	ASSERT(!S_ISDIR(sip->i_d.di_mode));

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

	error = xfs_qm_dqattach(sip, 0);
	if (error)
		goto std_return;

	error = xfs_qm_dqattach(tdp, 0);
	if (error)
		goto std_return;

	tp = xfs_trans_alloc(mp, XFS_TRANS_LINK);
	cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
	resblks = XFS_LINK_SPACE_RES(mp, target_name->len);
	error = xfs_trans_reserve(tp, resblks, XFS_LINK_LOG_RES(mp), 0,
			XFS_TRANS_PERM_LOG_RES, XFS_LINK_LOG_COUNT);
	if (error == ENOSPC) {
		resblks = 0;
		error = xfs_trans_reserve(tp, 0, XFS_LINK_LOG_RES(mp), 0,
				XFS_TRANS_PERM_LOG_RES, XFS_LINK_LOG_COUNT);
	}
	if (error) {
		cancel_flags = 0;
		goto error_return;
	}

	xfs_lock_two_inodes(sip, tdp, XFS_ILOCK_EXCL);

	xfs_trans_ijoin(tp, sip, XFS_ILOCK_EXCL);
	xfs_trans_ijoin(tp, tdp, XFS_ILOCK_EXCL);

	/*
	 * If we are using project inheritance, we only allow hard link
	 * creation in our tree when the project IDs are the same; else
	 * the tree quota mechanism could be circumvented.
	 */
	if (unlikely((tdp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
		     (xfs_get_projid(tdp) != xfs_get_projid(sip)))) {
		error = XFS_ERROR(EXDEV);
		goto error_return;
	}

	error = xfs_dir_canenter(tp, tdp, target_name, resblks);
	if (error)
		goto error_return;

	xfs_bmap_init(&free_list, &first_block);

	error = xfs_dir_createname(tp, tdp, target_name, sip->i_ino,
					&first_block, &free_list, resblks);
	if (error)
		goto abort_return;
	xfs_trans_ichgtime(tp, tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
	xfs_trans_log_inode(tp, tdp, XFS_ILOG_CORE);

	error = xfs_bumplink(tp, sip);
	if (error)
		goto abort_return;

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

	error = xfs_bmap_finish (&tp, &free_list, &committed);
	if (error) {
		xfs_bmap_cancel(&free_list);
		goto abort_return;
	}

	return xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);

 abort_return:
	cancel_flags |= XFS_TRANS_ABORT;
 error_return:
	xfs_trans_cancel(tp, cancel_flags);
 std_return:
	return error;
}

int
xfs_set_dmattrs(
	xfs_inode_t     *ip,
	u_int		evmask,
	u_int16_t	state)
{
	xfs_mount_t	*mp = ip->i_mount;
	xfs_trans_t	*tp;
	int		error;

	if (!capable(CAP_SYS_ADMIN))
		return XFS_ERROR(EPERM);

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

	tp = xfs_trans_alloc(mp, XFS_TRANS_SET_DMATTRS);
	error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES (mp), 0, 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);

	ip->i_d.di_dmevmask = evmask;
	ip->i_d.di_dmstate  = state;

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
	error = xfs_trans_commit(tp, 0);

	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, resblks,
					  XFS_WRITE_LOG_RES(mp), resrtextents,
					  XFS_TRANS_PERM_LOG_RES,
					  XFS_WRITE_LOG_COUNT);
		/*
		 * 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,
					  resblks,
					  XFS_WRITE_LOG_RES(mp),
					  0,
					  XFS_TRANS_PERM_LOG_RES,
					  XFS_WRITE_LOG_COUNT);

		/*
		 * 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);

	if ((error = xfs_trans_reserve(tp, 0, XFS_WRITEID_LOG_RES(mp),
				      0, 0, 0))) {
		/* ASSERT(0); */
		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);
}