summaryrefslogtreecommitdiff
path: root/fs/ubifs/journal.c
blob: 74aee92433d75c2fe0880e351519e00a85b1729a (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
2046
2047
// SPDX-License-Identifier: GPL-2.0-only
/*
 * This file is part of UBIFS.
 *
 * Copyright (C) 2006-2008 Nokia Corporation.
 *
 * Authors: Artem Bityutskiy (Битюцкий Артём)
 *          Adrian Hunter
 */

/*
 * This file implements UBIFS journal.
 *
 * The journal consists of 2 parts - the log and bud LEBs. The log has fixed
 * length and position, while a bud logical eraseblock is any LEB in the main
 * area. Buds contain file system data - data nodes, inode nodes, etc. The log
 * contains only references to buds and some other stuff like commit
 * start node. The idea is that when we commit the journal, we do
 * not copy the data, the buds just become indexed. Since after the commit the
 * nodes in bud eraseblocks become leaf nodes of the file system index tree, we
 * use term "bud". Analogy is obvious, bud eraseblocks contain nodes which will
 * become leafs in the future.
 *
 * The journal is multi-headed because we want to write data to the journal as
 * optimally as possible. It is nice to have nodes belonging to the same inode
 * in one LEB, so we may write data owned by different inodes to different
 * journal heads, although at present only one data head is used.
 *
 * For recovery reasons, the base head contains all inode nodes, all directory
 * entry nodes and all truncate nodes. This means that the other heads contain
 * only data nodes.
 *
 * Bud LEBs may be half-indexed. For example, if the bud was not full at the
 * time of commit, the bud is retained to continue to be used in the journal,
 * even though the "front" of the LEB is now indexed. In that case, the log
 * reference contains the offset where the bud starts for the purposes of the
 * journal.
 *
 * The journal size has to be limited, because the larger is the journal, the
 * longer it takes to mount UBIFS (scanning the journal) and the more memory it
 * takes (indexing in the TNC).
 *
 * All the journal write operations like 'ubifs_jnl_update()' here, which write
 * multiple UBIFS nodes to the journal at one go, are atomic with respect to
 * unclean reboots. Should the unclean reboot happen, the recovery code drops
 * all the nodes.
 */

#include "ubifs.h"

/**
 * zero_ino_node_unused - zero out unused fields of an on-flash inode node.
 * @ino: the inode to zero out
 */
static inline void zero_ino_node_unused(struct ubifs_ino_node *ino)
{
	memset(ino->padding1, 0, 4);
	memset(ino->padding2, 0, 26);
}

/**
 * zero_dent_node_unused - zero out unused fields of an on-flash directory
 *                         entry node.
 * @dent: the directory entry to zero out
 */
static inline void zero_dent_node_unused(struct ubifs_dent_node *dent)
{
	dent->padding1 = 0;
}

/**
 * zero_trun_node_unused - zero out unused fields of an on-flash truncation
 *                         node.
 * @trun: the truncation node to zero out
 */
static inline void zero_trun_node_unused(struct ubifs_trun_node *trun)
{
	memset(trun->padding, 0, 12);
}

static void ubifs_add_auth_dirt(struct ubifs_info *c, int lnum)
{
	if (ubifs_authenticated(c))
		ubifs_add_dirt(c, lnum, ubifs_auth_node_sz(c));
}

/**
 * reserve_space - reserve space in the journal.
 * @c: UBIFS file-system description object
 * @jhead: journal head number
 * @len: node length
 *
 * This function reserves space in journal head @head. If the reservation
 * succeeded, the journal head stays locked and later has to be unlocked using
 * 'release_head()'. Returns zero in case of success, %-EAGAIN if commit has to
 * be done, and other negative error codes in case of other failures.
 */
static int reserve_space(struct ubifs_info *c, int jhead, int len)
{
	int err = 0, err1, retries = 0, avail, lnum, offs, squeeze;
	struct ubifs_wbuf *wbuf = &c->jheads[jhead].wbuf;

	/*
	 * Typically, the base head has smaller nodes written to it, so it is
	 * better to try to allocate space at the ends of eraseblocks. This is
	 * what the squeeze parameter does.
	 */
	ubifs_assert(c, !c->ro_media && !c->ro_mount);
	squeeze = (jhead == BASEHD);
again:
	mutex_lock_nested(&wbuf->io_mutex, wbuf->jhead);

	if (c->ro_error) {
		err = -EROFS;
		goto out_unlock;
	}

	avail = c->leb_size - wbuf->offs - wbuf->used;
	if (wbuf->lnum != -1 && avail >= len)
		return 0;

	/*
	 * Write buffer wasn't seek'ed or there is no enough space - look for an
	 * LEB with some empty space.
	 */
	lnum = ubifs_find_free_space(c, len, &offs, squeeze);
	if (lnum >= 0)
		goto out;

	err = lnum;
	if (err != -ENOSPC)
		goto out_unlock;

	/*
	 * No free space, we have to run garbage collector to make
	 * some. But the write-buffer mutex has to be unlocked because
	 * GC also takes it.
	 */
	dbg_jnl("no free space in jhead %s, run GC", dbg_jhead(jhead));
	mutex_unlock(&wbuf->io_mutex);

	lnum = ubifs_garbage_collect(c, 0);
	if (lnum < 0) {
		err = lnum;
		if (err != -ENOSPC)
			return err;

		/*
		 * GC could not make a free LEB. But someone else may
		 * have allocated new bud for this journal head,
		 * because we dropped @wbuf->io_mutex, so try once
		 * again.
		 */
		dbg_jnl("GC couldn't make a free LEB for jhead %s",
			dbg_jhead(jhead));
		if (retries++ < 2) {
			dbg_jnl("retry (%d)", retries);
			goto again;
		}

		dbg_jnl("return -ENOSPC");
		return err;
	}

	mutex_lock_nested(&wbuf->io_mutex, wbuf->jhead);
	dbg_jnl("got LEB %d for jhead %s", lnum, dbg_jhead(jhead));
	avail = c->leb_size - wbuf->offs - wbuf->used;

	if (wbuf->lnum != -1 && avail >= len) {
		/*
		 * Someone else has switched the journal head and we have
		 * enough space now. This happens when more than one process is
		 * trying to write to the same journal head at the same time.
		 */
		dbg_jnl("return LEB %d back, already have LEB %d:%d",
			lnum, wbuf->lnum, wbuf->offs + wbuf->used);
		err = ubifs_return_leb(c, lnum);
		if (err)
			goto out_unlock;
		return 0;
	}

	offs = 0;

out:
	/*
	 * Make sure we synchronize the write-buffer before we add the new bud
	 * to the log. Otherwise we may have a power cut after the log
	 * reference node for the last bud (@lnum) is written but before the
	 * write-buffer data are written to the next-to-last bud
	 * (@wbuf->lnum). And the effect would be that the recovery would see
	 * that there is corruption in the next-to-last bud.
	 */
	err = ubifs_wbuf_sync_nolock(wbuf);
	if (err)
		goto out_return;
	err = ubifs_add_bud_to_log(c, jhead, lnum, offs);
	if (err)
		goto out_return;
	err = ubifs_wbuf_seek_nolock(wbuf, lnum, offs);
	if (err)
		goto out_unlock;

	return 0;

out_unlock:
	mutex_unlock(&wbuf->io_mutex);
	return err;

out_return:
	/* An error occurred and the LEB has to be returned to lprops */
	ubifs_assert(c, err < 0);
	err1 = ubifs_return_leb(c, lnum);
	if (err1 && err == -EAGAIN)
		/*
		 * Return original error code only if it is not %-EAGAIN,
		 * which is not really an error. Otherwise, return the error
		 * code of 'ubifs_return_leb()'.
		 */
		err = err1;
	mutex_unlock(&wbuf->io_mutex);
	return err;
}

static int ubifs_hash_nodes(struct ubifs_info *c, void *node,
			     int len, struct shash_desc *hash)
{
	int auth_node_size = ubifs_auth_node_sz(c);
	int err;

	while (1) {
		const struct ubifs_ch *ch = node;
		int nodelen = le32_to_cpu(ch->len);

		ubifs_assert(c, len >= auth_node_size);

		if (len == auth_node_size)
			break;

		ubifs_assert(c, len > nodelen);
		ubifs_assert(c, ch->magic == cpu_to_le32(UBIFS_NODE_MAGIC));

		err = ubifs_shash_update(c, hash, (void *)node, nodelen);
		if (err)
			return err;

		node += ALIGN(nodelen, 8);
		len -= ALIGN(nodelen, 8);
	}

	return ubifs_prepare_auth_node(c, node, hash);
}

/**
 * write_head - write data to a journal head.
 * @c: UBIFS file-system description object
 * @jhead: journal head
 * @buf: buffer to write
 * @len: length to write
 * @lnum: LEB number written is returned here
 * @offs: offset written is returned here
 * @sync: non-zero if the write-buffer has to by synchronized
 *
 * This function writes data to the reserved space of journal head @jhead.
 * Returns zero in case of success and a negative error code in case of
 * failure.
 */
static int write_head(struct ubifs_info *c, int jhead, void *buf, int len,
		      int *lnum, int *offs, int sync)
{
	int err;
	struct ubifs_wbuf *wbuf = &c->jheads[jhead].wbuf;

	ubifs_assert(c, jhead != GCHD);

	*lnum = c->jheads[jhead].wbuf.lnum;
	*offs = c->jheads[jhead].wbuf.offs + c->jheads[jhead].wbuf.used;
	dbg_jnl("jhead %s, LEB %d:%d, len %d",
		dbg_jhead(jhead), *lnum, *offs, len);

	if (ubifs_authenticated(c)) {
		err = ubifs_hash_nodes(c, buf, len, c->jheads[jhead].log_hash);
		if (err)
			return err;
	}

	err = ubifs_wbuf_write_nolock(wbuf, buf, len);
	if (err)
		return err;
	if (sync)
		err = ubifs_wbuf_sync_nolock(wbuf);
	return err;
}

/**
 * __queue_and_wait - queue a task and wait until the task is waked up.
 * @c: UBIFS file-system description object
 *
 * This function adds current task in queue and waits until the task is waked
 * up. This function should be called with @c->reserve_space_wq locked.
 */
static void __queue_and_wait(struct ubifs_info *c)
{
	DEFINE_WAIT(wait);

	__add_wait_queue_entry_tail_exclusive(&c->reserve_space_wq, &wait);
	set_current_state(TASK_UNINTERRUPTIBLE);
	spin_unlock(&c->reserve_space_wq.lock);

	schedule();
	finish_wait(&c->reserve_space_wq, &wait);
}

/**
 * wait_for_reservation - try queuing current task to wait until waked up.
 * @c: UBIFS file-system description object
 *
 * This function queues current task to wait until waked up, if queuing is
 * started(@c->need_wait_space is not %0). Returns %true if current task is
 * added in queue, otherwise %false is returned.
 */
static bool wait_for_reservation(struct ubifs_info *c)
{
	if (likely(atomic_read(&c->need_wait_space) == 0))
		/* Quick path to check whether queuing is started. */
		return false;

	spin_lock(&c->reserve_space_wq.lock);
	if (atomic_read(&c->need_wait_space) == 0) {
		/* Queuing is not started, don't queue current task. */
		spin_unlock(&c->reserve_space_wq.lock);
		return false;
	}

	__queue_and_wait(c);
	return true;
}

/**
 * wake_up_reservation - wake up first task in queue or stop queuing.
 * @c: UBIFS file-system description object
 *
 * This function wakes up the first task in queue if it exists, or stops
 * queuing if no tasks in queue.
 */
static void wake_up_reservation(struct ubifs_info *c)
{
	spin_lock(&c->reserve_space_wq.lock);
	if (waitqueue_active(&c->reserve_space_wq))
		wake_up_locked(&c->reserve_space_wq);
	else
		/*
		 * Compared with wait_for_reservation(), set @c->need_wait_space
		 * under the protection of wait queue lock, which can avoid that
		 * @c->need_wait_space is set to 0 after new task queued.
		 */
		atomic_set(&c->need_wait_space, 0);
	spin_unlock(&c->reserve_space_wq.lock);
}

/**
 * wake_up_reservation - add current task in queue or start queuing.
 * @c: UBIFS file-system description object
 *
 * This function starts queuing if queuing is not started, otherwise adds
 * current task in queue.
 */
static void add_or_start_queue(struct ubifs_info *c)
{
	spin_lock(&c->reserve_space_wq.lock);
	if (atomic_cmpxchg(&c->need_wait_space, 0, 1) == 0) {
		/* Starts queuing, task can go on directly. */
		spin_unlock(&c->reserve_space_wq.lock);
		return;
	}

	/*
	 * There are at least two tasks have retried more than 32 times
	 * at certain point, first task has started queuing, just queue
	 * the left tasks.
	 */
	__queue_and_wait(c);
}

/**
 * make_reservation - reserve journal space.
 * @c: UBIFS file-system description object
 * @jhead: journal head
 * @len: how many bytes to reserve
 *
 * This function makes space reservation in journal head @jhead. The function
 * takes the commit lock and locks the journal head, and the caller has to
 * unlock the head and finish the reservation with 'finish_reservation()'.
 * Returns zero in case of success and a negative error code in case of
 * failure.
 *
 * Note, the journal head may be unlocked as soon as the data is written, while
 * the commit lock has to be released after the data has been added to the
 * TNC.
 */
static int make_reservation(struct ubifs_info *c, int jhead, int len)
{
	int err, cmt_retries = 0, nospc_retries = 0;
	bool blocked = wait_for_reservation(c);

again:
	down_read(&c->commit_sem);
	err = reserve_space(c, jhead, len);
	if (!err) {
		/* c->commit_sem will get released via finish_reservation(). */
		goto out_wake_up;
	}
	up_read(&c->commit_sem);

	if (err == -ENOSPC) {
		/*
		 * GC could not make any progress. We should try to commit
		 * because it could make some dirty space and GC would make
		 * progress, so make the error -EAGAIN so that the below
		 * will commit and re-try.
		 */
		nospc_retries++;
		dbg_jnl("no space, retry");
		err = -EAGAIN;
	}

	if (err != -EAGAIN)
		goto out;

	/*
	 * -EAGAIN means that the journal is full or too large, or the above
	 * code wants to do one commit. Do this and re-try.
	 */
	if (cmt_retries > 128) {
		/*
		 * This should not happen unless:
		 * 1. The journal size limitations are too tough.
		 * 2. The budgeting is incorrect. We always have to be able to
		 *    write to the media, because all operations are budgeted.
		 *    Deletions are not budgeted, though, but we reserve an
		 *    extra LEB for them.
		 */
		ubifs_err(c, "stuck in space allocation, nospc_retries %d",
			  nospc_retries);
		err = -ENOSPC;
		goto out;
	} else if (cmt_retries > 32) {
		/*
		 * It's almost impossible to happen, unless there are many tasks
		 * making reservation concurrently and someone task has retried
		 * gc + commit for many times, generated available space during
		 * this period are grabbed by other tasks.
		 * But if it happens, start queuing up all tasks that will make
		 * space reservation, then there is only one task making space
		 * reservation at any time, and it can always make success under
		 * the premise of correct budgeting.
		 */
		ubifs_warn(c, "too many space allocation cmt_retries (%d) "
			   "nospc_retries (%d), start queuing tasks",
			   cmt_retries, nospc_retries);

		if (!blocked) {
			blocked = true;
			add_or_start_queue(c);
		}
	}

	dbg_jnl("-EAGAIN, commit and retry (retried %d times)",
		cmt_retries);
	cmt_retries += 1;

	err = ubifs_run_commit(c);
	if (err)
		goto out_wake_up;
	goto again;

out:
	ubifs_err(c, "cannot reserve %d bytes in jhead %d, error %d",
		  len, jhead, err);
	if (err == -ENOSPC) {
		/* This are some budgeting problems, print useful information */
		down_write(&c->commit_sem);
		dump_stack();
		ubifs_dump_budg(c, &c->bi);
		ubifs_dump_lprops(c);
		cmt_retries = dbg_check_lprops(c);
		up_write(&c->commit_sem);
	}
out_wake_up:
	if (blocked) {
		/*
		 * Only tasks that have ever started queuing or ever been queued
		 * can wake up other queued tasks, which can make sure that
		 * there is only one task waked up to make space reservation.
		 * For example:
		 *      task A          task B           task C
		 *                 make_reservation  make_reservation
		 * reserve_space // 0
		 * wake_up_reservation
		 *                  atomic_cmpxchg // 0, start queuing
		 *                  reserve_space
		 *                                    wait_for_reservation
		 *                                     __queue_and_wait
		 *                                      add_wait_queue
		 *  if (blocked) // false
		 *  // So that task C won't be waked up to race with task B
		 */
		wake_up_reservation(c);
	}
	return err;
}

/**
 * release_head - release a journal head.
 * @c: UBIFS file-system description object
 * @jhead: journal head
 *
 * This function releases journal head @jhead which was locked by
 * the 'make_reservation()' function. It has to be called after each successful
 * 'make_reservation()' invocation.
 */
static inline void release_head(struct ubifs_info *c, int jhead)
{
	mutex_unlock(&c->jheads[jhead].wbuf.io_mutex);
}

/**
 * finish_reservation - finish a reservation.
 * @c: UBIFS file-system description object
 *
 * This function finishes journal space reservation. It must be called after
 * 'make_reservation()'.
 */
static void finish_reservation(struct ubifs_info *c)
{
	up_read(&c->commit_sem);
}

/**
 * get_dent_type - translate VFS inode mode to UBIFS directory entry type.
 * @mode: inode mode
 */
static int get_dent_type(int mode)
{
	switch (mode & S_IFMT) {
	case S_IFREG:
		return UBIFS_ITYPE_REG;
	case S_IFDIR:
		return UBIFS_ITYPE_DIR;
	case S_IFLNK:
		return UBIFS_ITYPE_LNK;
	case S_IFBLK:
		return UBIFS_ITYPE_BLK;
	case S_IFCHR:
		return UBIFS_ITYPE_CHR;
	case S_IFIFO:
		return UBIFS_ITYPE_FIFO;
	case S_IFSOCK:
		return UBIFS_ITYPE_SOCK;
	default:
		BUG();
	}
	return 0;
}

/**
 * pack_inode - pack an inode node.
 * @c: UBIFS file-system description object
 * @ino: buffer in which to pack inode node
 * @inode: inode to pack
 * @last: indicates the last node of the group
 */
static void pack_inode(struct ubifs_info *c, struct ubifs_ino_node *ino,
		       const struct inode *inode, int last)
{
	int data_len = 0, last_reference = !inode->i_nlink;
	struct ubifs_inode *ui = ubifs_inode(inode);

	ino->ch.node_type = UBIFS_INO_NODE;
	ino_key_init_flash(c, &ino->key, inode->i_ino);
	ino->creat_sqnum = cpu_to_le64(ui->creat_sqnum);
	ino->atime_sec  = cpu_to_le64(inode_get_atime_sec(inode));
	ino->atime_nsec = cpu_to_le32(inode_get_atime_nsec(inode));
	ino->ctime_sec  = cpu_to_le64(inode_get_ctime_sec(inode));
	ino->ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode));
	ino->mtime_sec  = cpu_to_le64(inode_get_mtime_sec(inode));
	ino->mtime_nsec = cpu_to_le32(inode_get_mtime_nsec(inode));
	ino->uid   = cpu_to_le32(i_uid_read(inode));
	ino->gid   = cpu_to_le32(i_gid_read(inode));
	ino->mode  = cpu_to_le32(inode->i_mode);
	ino->flags = cpu_to_le32(ui->flags);
	ino->size  = cpu_to_le64(ui->ui_size);
	ino->nlink = cpu_to_le32(inode->i_nlink);
	ino->compr_type  = cpu_to_le16(ui->compr_type);
	ino->data_len    = cpu_to_le32(ui->data_len);
	ino->xattr_cnt   = cpu_to_le32(ui->xattr_cnt);
	ino->xattr_size  = cpu_to_le32(ui->xattr_size);
	ino->xattr_names = cpu_to_le32(ui->xattr_names);
	zero_ino_node_unused(ino);

	/*
	 * Drop the attached data if this is a deletion inode, the data is not
	 * needed anymore.
	 */
	if (!last_reference) {
		memcpy(ino->data, ui->data, ui->data_len);
		data_len = ui->data_len;
	}

	ubifs_prep_grp_node(c, ino, UBIFS_INO_NODE_SZ + data_len, last);
}

/**
 * mark_inode_clean - mark UBIFS inode as clean.
 * @c: UBIFS file-system description object
 * @ui: UBIFS inode to mark as clean
 *
 * This helper function marks UBIFS inode @ui as clean by cleaning the
 * @ui->dirty flag and releasing its budget. Note, VFS may still treat the
 * inode as dirty and try to write it back, but 'ubifs_write_inode()' would
 * just do nothing.
 */
static void mark_inode_clean(struct ubifs_info *c, struct ubifs_inode *ui)
{
	if (ui->dirty)
		ubifs_release_dirty_inode_budget(c, ui);
	ui->dirty = 0;
}

static void set_dent_cookie(struct ubifs_info *c, struct ubifs_dent_node *dent)
{
	if (c->double_hash)
		dent->cookie = (__force __le32) get_random_u32();
	else
		dent->cookie = 0;
}

/**
 * ubifs_jnl_update - update inode.
 * @c: UBIFS file-system description object
 * @dir: parent inode or host inode in case of extended attributes
 * @nm: directory entry name
 * @inode: inode to update
 * @deletion: indicates a directory entry deletion i.e unlink or rmdir
 * @xent: non-zero if the directory entry is an extended attribute entry
 *
 * This function updates an inode by writing a directory entry (or extended
 * attribute entry), the inode itself, and the parent directory inode (or the
 * host inode) to the journal.
 *
 * The function writes the host inode @dir last, which is important in case of
 * extended attributes. Indeed, then we guarantee that if the host inode gets
 * synchronized (with 'fsync()'), and the write-buffer it sits in gets flushed,
 * the extended attribute inode gets flushed too. And this is exactly what the
 * user expects - synchronizing the host inode synchronizes its extended
 * attributes. Similarly, this guarantees that if @dir is synchronized, its
 * directory entry corresponding to @nm gets synchronized too.
 *
 * If the inode (@inode) or the parent directory (@dir) are synchronous, this
 * function synchronizes the write-buffer.
 *
 * This function marks the @dir and @inode inodes as clean and returns zero on
 * success. In case of failure, a negative error code is returned.
 */
int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
		     const struct fscrypt_name *nm, const struct inode *inode,
		     int deletion, int xent)
{
	int err, dlen, ilen, len, lnum, ino_offs, dent_offs, orphan_added = 0;
	int aligned_dlen, aligned_ilen, sync = IS_DIRSYNC(dir);
	int last_reference = !!(deletion && inode->i_nlink == 0);
	struct ubifs_inode *ui = ubifs_inode(inode);
	struct ubifs_inode *host_ui = ubifs_inode(dir);
	struct ubifs_dent_node *dent;
	struct ubifs_ino_node *ino;
	union ubifs_key dent_key, ino_key;
	u8 hash_dent[UBIFS_HASH_ARR_SZ];
	u8 hash_ino[UBIFS_HASH_ARR_SZ];
	u8 hash_ino_host[UBIFS_HASH_ARR_SZ];

	ubifs_assert(c, mutex_is_locked(&host_ui->ui_mutex));

	dlen = UBIFS_DENT_NODE_SZ + fname_len(nm) + 1;
	ilen = UBIFS_INO_NODE_SZ;

	/*
	 * If the last reference to the inode is being deleted, then there is
	 * no need to attach and write inode data, it is being deleted anyway.
	 * And if the inode is being deleted, no need to synchronize
	 * write-buffer even if the inode is synchronous.
	 */
	if (!last_reference) {
		ilen += ui->data_len;
		sync |= IS_SYNC(inode);
	}

	aligned_dlen = ALIGN(dlen, 8);
	aligned_ilen = ALIGN(ilen, 8);

	len = aligned_dlen + aligned_ilen + UBIFS_INO_NODE_SZ;
	/* Make sure to also account for extended attributes */
	if (ubifs_authenticated(c))
		len += ALIGN(host_ui->data_len, 8) + ubifs_auth_node_sz(c);
	else
		len += host_ui->data_len;

	dent = kzalloc(len, GFP_NOFS);
	if (!dent)
		return -ENOMEM;

	/* Make reservation before allocating sequence numbers */
	err = make_reservation(c, BASEHD, len);
	if (err)
		goto out_free;

	if (!xent) {
		dent->ch.node_type = UBIFS_DENT_NODE;
		if (fname_name(nm) == NULL)
			dent_key_init_hash(c, &dent_key, dir->i_ino, nm->hash);
		else
			dent_key_init(c, &dent_key, dir->i_ino, nm);
	} else {
		dent->ch.node_type = UBIFS_XENT_NODE;
		xent_key_init(c, &dent_key, dir->i_ino, nm);
	}

	key_write(c, &dent_key, dent->key);
	dent->inum = deletion ? 0 : cpu_to_le64(inode->i_ino);
	dent->type = get_dent_type(inode->i_mode);
	dent->nlen = cpu_to_le16(fname_len(nm));
	memcpy(dent->name, fname_name(nm), fname_len(nm));
	dent->name[fname_len(nm)] = '\0';
	set_dent_cookie(c, dent);

	zero_dent_node_unused(dent);
	ubifs_prep_grp_node(c, dent, dlen, 0);
	err = ubifs_node_calc_hash(c, dent, hash_dent);
	if (err)
		goto out_release;

	ino = (void *)dent + aligned_dlen;
	pack_inode(c, ino, inode, 0);
	err = ubifs_node_calc_hash(c, ino, hash_ino);
	if (err)
		goto out_release;

	ino = (void *)ino + aligned_ilen;
	pack_inode(c, ino, dir, 1);
	err = ubifs_node_calc_hash(c, ino, hash_ino_host);
	if (err)
		goto out_release;

	if (last_reference) {
		err = ubifs_add_orphan(c, inode->i_ino);
		if (err) {
			release_head(c, BASEHD);
			goto out_finish;
		}
		ui->del_cmtno = c->cmt_no;
		orphan_added = 1;
	}

	err = write_head(c, BASEHD, dent, len, &lnum, &dent_offs, sync);
	if (err)
		goto out_release;
	if (!sync) {
		struct ubifs_wbuf *wbuf = &c->jheads[BASEHD].wbuf;

		ubifs_wbuf_add_ino_nolock(wbuf, inode->i_ino);
		ubifs_wbuf_add_ino_nolock(wbuf, dir->i_ino);
	}
	release_head(c, BASEHD);
	kfree(dent);
	ubifs_add_auth_dirt(c, lnum);

	if (deletion) {
		if (fname_name(nm) == NULL)
			err = ubifs_tnc_remove_dh(c, &dent_key, nm->minor_hash);
		else
			err = ubifs_tnc_remove_nm(c, &dent_key, nm);
		if (err)
			goto out_ro;
		err = ubifs_add_dirt(c, lnum, dlen);
	} else
		err = ubifs_tnc_add_nm(c, &dent_key, lnum, dent_offs, dlen,
				       hash_dent, nm);
	if (err)
		goto out_ro;

	/*
	 * Note, we do not remove the inode from TNC even if the last reference
	 * to it has just been deleted, because the inode may still be opened.
	 * Instead, the inode has been added to orphan lists and the orphan
	 * subsystem will take further care about it.
	 */
	ino_key_init(c, &ino_key, inode->i_ino);
	ino_offs = dent_offs + aligned_dlen;
	err = ubifs_tnc_add(c, &ino_key, lnum, ino_offs, ilen, hash_ino);
	if (err)
		goto out_ro;

	ino_key_init(c, &ino_key, dir->i_ino);
	ino_offs += aligned_ilen;
	err = ubifs_tnc_add(c, &ino_key, lnum, ino_offs,
			    UBIFS_INO_NODE_SZ + host_ui->data_len, hash_ino_host);
	if (err)
		goto out_ro;

	finish_reservation(c);
	spin_lock(&ui->ui_lock);
	ui->synced_i_size = ui->ui_size;
	spin_unlock(&ui->ui_lock);
	if (xent) {
		spin_lock(&host_ui->ui_lock);
		host_ui->synced_i_size = host_ui->ui_size;
		spin_unlock(&host_ui->ui_lock);
	}
	mark_inode_clean(c, ui);
	mark_inode_clean(c, host_ui);
	return 0;

out_finish:
	finish_reservation(c);
out_free:
	kfree(dent);
	return err;

out_release:
	release_head(c, BASEHD);
	kfree(dent);
out_ro:
	ubifs_ro_mode(c, err);
	if (orphan_added)
		ubifs_delete_orphan(c, inode->i_ino);
	finish_reservation(c);
	return err;
}

/**
 * ubifs_jnl_write_data - write a data node to the journal.
 * @c: UBIFS file-system description object
 * @inode: inode the data node belongs to
 * @key: node key
 * @buf: buffer to write
 * @len: data length (must not exceed %UBIFS_BLOCK_SIZE)
 *
 * This function writes a data node to the journal. Returns %0 if the data node
 * was successfully written, and a negative error code in case of failure.
 */
int ubifs_jnl_write_data(struct ubifs_info *c, const struct inode *inode,
			 const union ubifs_key *key, const void *buf, int len)
{
	struct ubifs_data_node *data;
	int err, lnum, offs, compr_type, out_len, compr_len, auth_len;
	int dlen = COMPRESSED_DATA_NODE_BUF_SZ, allocated = 1;
	int write_len;
	struct ubifs_inode *ui = ubifs_inode(inode);
	bool encrypted = IS_ENCRYPTED(inode);
	u8 hash[UBIFS_HASH_ARR_SZ];

	dbg_jnlk(key, "ino %lu, blk %u, len %d, key ",
		(unsigned long)key_inum(c, key), key_block(c, key), len);
	ubifs_assert(c, len <= UBIFS_BLOCK_SIZE);

	if (encrypted)
		dlen += UBIFS_CIPHER_BLOCK_SIZE;

	auth_len = ubifs_auth_node_sz(c);

	data = kmalloc(dlen + auth_len, GFP_NOFS | __GFP_NOWARN);
	if (!data) {
		/*
		 * Fall-back to the write reserve buffer. Note, we might be
		 * currently on the memory reclaim path, when the kernel is
		 * trying to free some memory by writing out dirty pages. The
		 * write reserve buffer helps us to guarantee that we are
		 * always able to write the data.
		 */
		allocated = 0;
		mutex_lock(&c->write_reserve_mutex);
		data = c->write_reserve_buf;
	}

	data->ch.node_type = UBIFS_DATA_NODE;
	key_write(c, key, &data->key);
	data->size = cpu_to_le32(len);

	if (!(ui->flags & UBIFS_COMPR_FL))
		/* Compression is disabled for this inode */
		compr_type = UBIFS_COMPR_NONE;
	else
		compr_type = ui->compr_type;

	out_len = compr_len = dlen - UBIFS_DATA_NODE_SZ;
	ubifs_compress(c, buf, len, &data->data, &compr_len, &compr_type);
	ubifs_assert(c, compr_len <= UBIFS_BLOCK_SIZE);

	if (encrypted) {
		err = ubifs_encrypt(inode, data, compr_len, &out_len, key_block(c, key));
		if (err)
			goto out_free;

	} else {
		data->compr_size = 0;
		out_len = compr_len;
	}

	dlen = UBIFS_DATA_NODE_SZ + out_len;
	if (ubifs_authenticated(c))
		write_len = ALIGN(dlen, 8) + auth_len;
	else
		write_len = dlen;

	data->compr_type = cpu_to_le16(compr_type);

	/* Make reservation before allocating sequence numbers */
	err = make_reservation(c, DATAHD, write_len);
	if (err)
		goto out_free;

	ubifs_prepare_node(c, data, dlen, 0);
	err = write_head(c, DATAHD, data, write_len, &lnum, &offs, 0);
	if (err)
		goto out_release;

	err = ubifs_node_calc_hash(c, data, hash);
	if (err)
		goto out_release;

	ubifs_wbuf_add_ino_nolock(&c->jheads[DATAHD].wbuf, key_inum(c, key));
	release_head(c, DATAHD);

	ubifs_add_auth_dirt(c, lnum);

	err = ubifs_tnc_add(c, key, lnum, offs, dlen, hash);
	if (err)
		goto out_ro;

	finish_reservation(c);
	if (!allocated)
		mutex_unlock(&c->write_reserve_mutex);
	else
		kfree(data);
	return 0;

out_release:
	release_head(c, DATAHD);
out_ro:
	ubifs_ro_mode(c, err);
	finish_reservation(c);
out_free:
	if (!allocated)
		mutex_unlock(&c->write_reserve_mutex);
	else
		kfree(data);
	return err;
}

/**
 * ubifs_jnl_write_inode - flush inode to the journal.
 * @c: UBIFS file-system description object
 * @inode: inode to flush
 *
 * This function writes inode @inode to the journal. If the inode is
 * synchronous, it also synchronizes the write-buffer. Returns zero in case of
 * success and a negative error code in case of failure.
 */
int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode)
{
	int err, lnum, offs;
	struct ubifs_ino_node *ino, *ino_start;
	struct ubifs_inode *ui = ubifs_inode(inode);
	int sync = 0, write_len = 0, ilen = UBIFS_INO_NODE_SZ;
	int last_reference = !inode->i_nlink;
	int kill_xattrs = ui->xattr_cnt && last_reference;
	u8 hash[UBIFS_HASH_ARR_SZ];

	dbg_jnl("ino %lu, nlink %u", inode->i_ino, inode->i_nlink);

	/*
	 * If the inode is being deleted, do not write the attached data. No
	 * need to synchronize the write-buffer either.
	 */
	if (!last_reference) {
		ilen += ui->data_len;
		sync = IS_SYNC(inode);
	} else if (kill_xattrs) {
		write_len += UBIFS_INO_NODE_SZ * ui->xattr_cnt;
	}

	if (ubifs_authenticated(c))
		write_len += ALIGN(ilen, 8) + ubifs_auth_node_sz(c);
	else
		write_len += ilen;

	ino_start = ino = kmalloc(write_len, GFP_NOFS);
	if (!ino)
		return -ENOMEM;

	/* Make reservation before allocating sequence numbers */
	err = make_reservation(c, BASEHD, write_len);
	if (err)
		goto out_free;

	if (kill_xattrs) {
		union ubifs_key key;
		struct fscrypt_name nm = {0};
		struct inode *xino;
		struct ubifs_dent_node *xent, *pxent = NULL;

		if (ui->xattr_cnt > ubifs_xattr_max_cnt(c)) {
			err = -EPERM;
			ubifs_err(c, "Cannot delete inode, it has too much xattrs!");
			goto out_release;
		}

		lowest_xent_key(c, &key, inode->i_ino);
		while (1) {
			xent = ubifs_tnc_next_ent(c, &key, &nm);
			if (IS_ERR(xent)) {
				err = PTR_ERR(xent);
				if (err == -ENOENT)
					break;

				kfree(pxent);
				goto out_release;
			}

			fname_name(&nm) = xent->name;
			fname_len(&nm) = le16_to_cpu(xent->nlen);

			xino = ubifs_iget(c->vfs_sb, le64_to_cpu(xent->inum));
			if (IS_ERR(xino)) {
				err = PTR_ERR(xino);
				ubifs_err(c, "dead directory entry '%s', error %d",
					  xent->name, err);
				ubifs_ro_mode(c, err);
				kfree(pxent);
				kfree(xent);
				goto out_release;
			}
			ubifs_assert(c, ubifs_inode(xino)->xattr);

			clear_nlink(xino);
			pack_inode(c, ino, xino, 0);
			ino = (void *)ino + UBIFS_INO_NODE_SZ;
			iput(xino);

			kfree(pxent);
			pxent = xent;
			key_read(c, &xent->key, &key);
		}
		kfree(pxent);
	}

	pack_inode(c, ino, inode, 1);
	err = ubifs_node_calc_hash(c, ino, hash);
	if (err)
		goto out_release;

	err = write_head(c, BASEHD, ino_start, write_len, &lnum, &offs, sync);
	if (err)
		goto out_release;
	if (!sync)
		ubifs_wbuf_add_ino_nolock(&c->jheads[BASEHD].wbuf,
					  inode->i_ino);
	release_head(c, BASEHD);

	if (last_reference) {
		err = ubifs_tnc_remove_ino(c, inode->i_ino);
		if (err)
			goto out_ro;
		ubifs_delete_orphan(c, inode->i_ino);
		err = ubifs_add_dirt(c, lnum, write_len);
	} else {
		union ubifs_key key;

		ubifs_add_auth_dirt(c, lnum);

		ino_key_init(c, &key, inode->i_ino);
		err = ubifs_tnc_add(c, &key, lnum, offs, ilen, hash);
	}
	if (err)
		goto out_ro;

	finish_reservation(c);
	spin_lock(&ui->ui_lock);
	ui->synced_i_size = ui->ui_size;
	spin_unlock(&ui->ui_lock);
	kfree(ino_start);
	return 0;

out_release:
	release_head(c, BASEHD);
out_ro:
	ubifs_ro_mode(c, err);
	finish_reservation(c);
out_free:
	kfree(ino_start);
	return err;
}

/**
 * ubifs_jnl_delete_inode - delete an inode.
 * @c: UBIFS file-system description object
 * @inode: inode to delete
 *
 * This function deletes inode @inode which includes removing it from orphans,
 * deleting it from TNC and, in some cases, writing a deletion inode to the
 * journal.
 *
 * When regular file inodes are unlinked or a directory inode is removed, the
 * 'ubifs_jnl_update()' function writes a corresponding deletion inode and
 * direntry to the media, and adds the inode to orphans. After this, when the
 * last reference to this inode has been dropped, this function is called. In
 * general, it has to write one more deletion inode to the media, because if
 * a commit happened between 'ubifs_jnl_update()' and
 * 'ubifs_jnl_delete_inode()', the deletion inode is not in the journal
 * anymore, and in fact it might not be on the flash anymore, because it might
 * have been garbage-collected already. And for optimization reasons UBIFS does
 * not read the orphan area if it has been unmounted cleanly, so it would have
 * no indication in the journal that there is a deleted inode which has to be
 * removed from TNC.
 *
 * However, if there was no commit between 'ubifs_jnl_update()' and
 * 'ubifs_jnl_delete_inode()', then there is no need to write the deletion
 * inode to the media for the second time. And this is quite a typical case.
 *
 * This function returns zero in case of success and a negative error code in
 * case of failure.
 */
int ubifs_jnl_delete_inode(struct ubifs_info *c, const struct inode *inode)
{
	int err;
	struct ubifs_inode *ui = ubifs_inode(inode);

	ubifs_assert(c, inode->i_nlink == 0);

	if (ui->xattr_cnt || ui->del_cmtno != c->cmt_no)
		/* A commit happened for sure or inode hosts xattrs */
		return ubifs_jnl_write_inode(c, inode);

	down_read(&c->commit_sem);
	/*
	 * Check commit number again, because the first test has been done
	 * without @c->commit_sem, so a commit might have happened.
	 */
	if (ui->del_cmtno != c->cmt_no) {
		up_read(&c->commit_sem);
		return ubifs_jnl_write_inode(c, inode);
	}

	err = ubifs_tnc_remove_ino(c, inode->i_ino);
	if (err)
		ubifs_ro_mode(c, err);
	else
		ubifs_delete_orphan(c, inode->i_ino);
	up_read(&c->commit_sem);
	return err;
}

/**
 * ubifs_jnl_xrename - cross rename two directory entries.
 * @c: UBIFS file-system description object
 * @fst_dir: parent inode of 1st directory entry to exchange
 * @fst_inode: 1st inode to exchange
 * @fst_nm: name of 1st inode to exchange
 * @snd_dir: parent inode of 2nd directory entry to exchange
 * @snd_inode: 2nd inode to exchange
 * @snd_nm: name of 2nd inode to exchange
 * @sync: non-zero if the write-buffer has to be synchronized
 *
 * This function implements the cross rename operation which may involve
 * writing 2 inodes and 2 directory entries. It marks the written inodes as clean
 * and returns zero on success. In case of failure, a negative error code is
 * returned.
 */
int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir,
		      const struct inode *fst_inode,
		      const struct fscrypt_name *fst_nm,
		      const struct inode *snd_dir,
		      const struct inode *snd_inode,
		      const struct fscrypt_name *snd_nm, int sync)
{
	union ubifs_key key;
	struct ubifs_dent_node *dent1, *dent2;
	int err, dlen1, dlen2, lnum, offs, len, plen = UBIFS_INO_NODE_SZ;
	int aligned_dlen1, aligned_dlen2;
	int twoparents = (fst_dir != snd_dir);
	void *p;
	u8 hash_dent1[UBIFS_HASH_ARR_SZ];
	u8 hash_dent2[UBIFS_HASH_ARR_SZ];
	u8 hash_p1[UBIFS_HASH_ARR_SZ];
	u8 hash_p2[UBIFS_HASH_ARR_SZ];

	ubifs_assert(c, ubifs_inode(fst_dir)->data_len == 0);
	ubifs_assert(c, ubifs_inode(snd_dir)->data_len == 0);
	ubifs_assert(c, mutex_is_locked(&ubifs_inode(fst_dir)->ui_mutex));
	ubifs_assert(c, mutex_is_locked(&ubifs_inode(snd_dir)->ui_mutex));

	dlen1 = UBIFS_DENT_NODE_SZ + fname_len(snd_nm) + 1;
	dlen2 = UBIFS_DENT_NODE_SZ + fname_len(fst_nm) + 1;
	aligned_dlen1 = ALIGN(dlen1, 8);
	aligned_dlen2 = ALIGN(dlen2, 8);

	len = aligned_dlen1 + aligned_dlen2 + ALIGN(plen, 8);
	if (twoparents)
		len += plen;

	len += ubifs_auth_node_sz(c);

	dent1 = kzalloc(len, GFP_NOFS);
	if (!dent1)
		return -ENOMEM;

	/* Make reservation before allocating sequence numbers */
	err = make_reservation(c, BASEHD, len);
	if (err)
		goto out_free;

	/* Make new dent for 1st entry */
	dent1->ch.node_type = UBIFS_DENT_NODE;
	dent_key_init_flash(c, &dent1->key, snd_dir->i_ino, snd_nm);
	dent1->inum = cpu_to_le64(fst_inode->i_ino);
	dent1->type = get_dent_type(fst_inode->i_mode);
	dent1->nlen = cpu_to_le16(fname_len(snd_nm));
	memcpy(dent1->name, fname_name(snd_nm), fname_len(snd_nm));
	dent1->name[fname_len(snd_nm)] = '\0';
	set_dent_cookie(c, dent1);
	zero_dent_node_unused(dent1);
	ubifs_prep_grp_node(c, dent1, dlen1, 0);
	err = ubifs_node_calc_hash(c, dent1, hash_dent1);
	if (err)
		goto out_release;

	/* Make new dent for 2nd entry */
	dent2 = (void *)dent1 + aligned_dlen1;
	dent2->ch.node_type = UBIFS_DENT_NODE;
	dent_key_init_flash(c, &dent2->key, fst_dir->i_ino, fst_nm);
	dent2->inum = cpu_to_le64(snd_inode->i_ino);
	dent2->type = get_dent_type(snd_inode->i_mode);
	dent2->nlen = cpu_to_le16(fname_len(fst_nm));
	memcpy(dent2->name, fname_name(fst_nm), fname_len(fst_nm));
	dent2->name[fname_len(fst_nm)] = '\0';
	set_dent_cookie(c, dent2);
	zero_dent_node_unused(dent2);
	ubifs_prep_grp_node(c, dent2, dlen2, 0);
	err = ubifs_node_calc_hash(c, dent2, hash_dent2);
	if (err)
		goto out_release;

	p = (void *)dent2 + aligned_dlen2;
	if (!twoparents) {
		pack_inode(c, p, fst_dir, 1);
		err = ubifs_node_calc_hash(c, p, hash_p1);
		if (err)
			goto out_release;
	} else {
		pack_inode(c, p, fst_dir, 0);
		err = ubifs_node_calc_hash(c, p, hash_p1);
		if (err)
			goto out_release;
		p += ALIGN(plen, 8);
		pack_inode(c, p, snd_dir, 1);
		err = ubifs_node_calc_hash(c, p, hash_p2);
		if (err)
			goto out_release;
	}

	err = write_head(c, BASEHD, dent1, len, &lnum, &offs, sync);
	if (err)
		goto out_release;
	if (!sync) {
		struct ubifs_wbuf *wbuf = &c->jheads[BASEHD].wbuf;

		ubifs_wbuf_add_ino_nolock(wbuf, fst_dir->i_ino);
		ubifs_wbuf_add_ino_nolock(wbuf, snd_dir->i_ino);
	}
	release_head(c, BASEHD);

	ubifs_add_auth_dirt(c, lnum);

	dent_key_init(c, &key, snd_dir->i_ino, snd_nm);
	err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen1, hash_dent1, snd_nm);
	if (err)
		goto out_ro;

	offs += aligned_dlen1;
	dent_key_init(c, &key, fst_dir->i_ino, fst_nm);
	err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen2, hash_dent2, fst_nm);
	if (err)
		goto out_ro;

	offs += aligned_dlen2;

	ino_key_init(c, &key, fst_dir->i_ino);
	err = ubifs_tnc_add(c, &key, lnum, offs, plen, hash_p1);
	if (err)
		goto out_ro;

	if (twoparents) {
		offs += ALIGN(plen, 8);
		ino_key_init(c, &key, snd_dir->i_ino);
		err = ubifs_tnc_add(c, &key, lnum, offs, plen, hash_p2);
		if (err)
			goto out_ro;
	}

	finish_reservation(c);

	mark_inode_clean(c, ubifs_inode(fst_dir));
	if (twoparents)
		mark_inode_clean(c, ubifs_inode(snd_dir));
	kfree(dent1);
	return 0;

out_release:
	release_head(c, BASEHD);
out_ro:
	ubifs_ro_mode(c, err);
	finish_reservation(c);
out_free:
	kfree(dent1);
	return err;
}

/**
 * ubifs_jnl_rename - rename a directory entry.
 * @c: UBIFS file-system description object
 * @old_dir: parent inode of directory entry to rename
 * @old_inode: directory entry's inode to rename
 * @old_nm: name of the old directory entry to rename
 * @new_dir: parent inode of directory entry to rename
 * @new_inode: new directory entry's inode (or directory entry's inode to
 *		replace)
 * @new_nm: new name of the new directory entry
 * @whiteout: whiteout inode
 * @sync: non-zero if the write-buffer has to be synchronized
 *
 * This function implements the re-name operation which may involve writing up
 * to 4 inodes(new inode, whiteout inode, old and new parent directory inodes)
 * and 2 directory entries. It marks the written inodes as clean and returns
 * zero on success. In case of failure, a negative error code is returned.
 */
int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
		     const struct inode *old_inode,
		     const struct fscrypt_name *old_nm,
		     const struct inode *new_dir,
		     const struct inode *new_inode,
		     const struct fscrypt_name *new_nm,
		     const struct inode *whiteout, int sync)
{
	void *p;
	union ubifs_key key;
	struct ubifs_dent_node *dent, *dent2;
	int err, dlen1, dlen2, ilen, wlen, lnum, offs, len, orphan_added = 0;
	int aligned_dlen1, aligned_dlen2, plen = UBIFS_INO_NODE_SZ;
	int last_reference = !!(new_inode && new_inode->i_nlink == 0);
	int move = (old_dir != new_dir);
	struct ubifs_inode *new_ui, *whiteout_ui;
	u8 hash_old_dir[UBIFS_HASH_ARR_SZ];
	u8 hash_new_dir[UBIFS_HASH_ARR_SZ];
	u8 hash_new_inode[UBIFS_HASH_ARR_SZ];
	u8 hash_whiteout_inode[UBIFS_HASH_ARR_SZ];
	u8 hash_dent1[UBIFS_HASH_ARR_SZ];
	u8 hash_dent2[UBIFS_HASH_ARR_SZ];

	ubifs_assert(c, ubifs_inode(old_dir)->data_len == 0);
	ubifs_assert(c, ubifs_inode(new_dir)->data_len == 0);
	ubifs_assert(c, mutex_is_locked(&ubifs_inode(old_dir)->ui_mutex));
	ubifs_assert(c, mutex_is_locked(&ubifs_inode(new_dir)->ui_mutex));

	dlen1 = UBIFS_DENT_NODE_SZ + fname_len(new_nm) + 1;
	dlen2 = UBIFS_DENT_NODE_SZ + fname_len(old_nm) + 1;
	if (new_inode) {
		new_ui = ubifs_inode(new_inode);
		ubifs_assert(c, mutex_is_locked(&new_ui->ui_mutex));
		ilen = UBIFS_INO_NODE_SZ;
		if (!last_reference)
			ilen += new_ui->data_len;
	} else
		ilen = 0;

	if (whiteout) {
		whiteout_ui = ubifs_inode(whiteout);
		ubifs_assert(c, mutex_is_locked(&whiteout_ui->ui_mutex));
		ubifs_assert(c, whiteout->i_nlink == 1);
		ubifs_assert(c, !whiteout_ui->dirty);
		wlen = UBIFS_INO_NODE_SZ;
		wlen += whiteout_ui->data_len;
	} else
		wlen = 0;

	aligned_dlen1 = ALIGN(dlen1, 8);
	aligned_dlen2 = ALIGN(dlen2, 8);
	len = aligned_dlen1 + aligned_dlen2 + ALIGN(ilen, 8) +
	      ALIGN(wlen, 8) + ALIGN(plen, 8);
	if (move)
		len += plen;

	len += ubifs_auth_node_sz(c);

	dent = kzalloc(len, GFP_NOFS);
	if (!dent)
		return -ENOMEM;

	/* Make reservation before allocating sequence numbers */
	err = make_reservation(c, BASEHD, len);
	if (err)
		goto out_free;

	/* Make new dent */
	dent->ch.node_type = UBIFS_DENT_NODE;
	dent_key_init_flash(c, &dent->key, new_dir->i_ino, new_nm);
	dent->inum = cpu_to_le64(old_inode->i_ino);
	dent->type = get_dent_type(old_inode->i_mode);
	dent->nlen = cpu_to_le16(fname_len(new_nm));
	memcpy(dent->name, fname_name(new_nm), fname_len(new_nm));
	dent->name[fname_len(new_nm)] = '\0';
	set_dent_cookie(c, dent);
	zero_dent_node_unused(dent);
	ubifs_prep_grp_node(c, dent, dlen1, 0);
	err = ubifs_node_calc_hash(c, dent, hash_dent1);
	if (err)
		goto out_release;

	dent2 = (void *)dent + aligned_dlen1;
	dent2->ch.node_type = UBIFS_DENT_NODE;
	dent_key_init_flash(c, &dent2->key, old_dir->i_ino, old_nm);

	if (whiteout) {
		dent2->inum = cpu_to_le64(whiteout->i_ino);
		dent2->type = get_dent_type(whiteout->i_mode);
	} else {
		/* Make deletion dent */
		dent2->inum = 0;
		dent2->type = DT_UNKNOWN;
	}
	dent2->nlen = cpu_to_le16(fname_len(old_nm));
	memcpy(dent2->name, fname_name(old_nm), fname_len(old_nm));
	dent2->name[fname_len(old_nm)] = '\0';
	set_dent_cookie(c, dent2);
	zero_dent_node_unused(dent2);
	ubifs_prep_grp_node(c, dent2, dlen2, 0);
	err = ubifs_node_calc_hash(c, dent2, hash_dent2);
	if (err)
		goto out_release;

	p = (void *)dent2 + aligned_dlen2;
	if (new_inode) {
		pack_inode(c, p, new_inode, 0);
		err = ubifs_node_calc_hash(c, p, hash_new_inode);
		if (err)
			goto out_release;

		p += ALIGN(ilen, 8);
	}

	if (whiteout) {
		pack_inode(c, p, whiteout, 0);
		err = ubifs_node_calc_hash(c, p, hash_whiteout_inode);
		if (err)
			goto out_release;

		p += ALIGN(wlen, 8);
	}

	if (!move) {
		pack_inode(c, p, old_dir, 1);
		err = ubifs_node_calc_hash(c, p, hash_old_dir);
		if (err)
			goto out_release;
	} else {
		pack_inode(c, p, old_dir, 0);
		err = ubifs_node_calc_hash(c, p, hash_old_dir);
		if (err)
			goto out_release;

		p += ALIGN(plen, 8);
		pack_inode(c, p, new_dir, 1);
		err = ubifs_node_calc_hash(c, p, hash_new_dir);
		if (err)
			goto out_release;
	}

	if (last_reference) {
		err = ubifs_add_orphan(c, new_inode->i_ino);
		if (err) {
			release_head(c, BASEHD);
			goto out_finish;
		}
		new_ui->del_cmtno = c->cmt_no;
		orphan_added = 1;
	}

	err = write_head(c, BASEHD, dent, len, &lnum, &offs, sync);
	if (err)
		goto out_release;
	if (!sync) {
		struct ubifs_wbuf *wbuf = &c->jheads[BASEHD].wbuf;

		ubifs_wbuf_add_ino_nolock(wbuf, new_dir->i_ino);
		ubifs_wbuf_add_ino_nolock(wbuf, old_dir->i_ino);
		if (new_inode)
			ubifs_wbuf_add_ino_nolock(&c->jheads[BASEHD].wbuf,
						  new_inode->i_ino);
		if (whiteout)
			ubifs_wbuf_add_ino_nolock(&c->jheads[BASEHD].wbuf,
						  whiteout->i_ino);
	}
	release_head(c, BASEHD);

	ubifs_add_auth_dirt(c, lnum);

	dent_key_init(c, &key, new_dir->i_ino, new_nm);
	err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen1, hash_dent1, new_nm);
	if (err)
		goto out_ro;

	offs += aligned_dlen1;
	if (whiteout) {
		dent_key_init(c, &key, old_dir->i_ino, old_nm);
		err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen2, hash_dent2, old_nm);
		if (err)
			goto out_ro;
	} else {
		err = ubifs_add_dirt(c, lnum, dlen2);
		if (err)
			goto out_ro;

		dent_key_init(c, &key, old_dir->i_ino, old_nm);
		err = ubifs_tnc_remove_nm(c, &key, old_nm);
		if (err)
			goto out_ro;
	}

	offs += aligned_dlen2;
	if (new_inode) {
		ino_key_init(c, &key, new_inode->i_ino);
		err = ubifs_tnc_add(c, &key, lnum, offs, ilen, hash_new_inode);
		if (err)
			goto out_ro;
		offs += ALIGN(ilen, 8);
	}

	if (whiteout) {
		ino_key_init(c, &key, whiteout->i_ino);
		err = ubifs_tnc_add(c, &key, lnum, offs, wlen,
				    hash_whiteout_inode);
		if (err)
			goto out_ro;
		offs += ALIGN(wlen, 8);
	}

	ino_key_init(c, &key, old_dir->i_ino);
	err = ubifs_tnc_add(c, &key, lnum, offs, plen, hash_old_dir);
	if (err)
		goto out_ro;

	if (move) {
		offs += ALIGN(plen, 8);
		ino_key_init(c, &key, new_dir->i_ino);
		err = ubifs_tnc_add(c, &key, lnum, offs, plen, hash_new_dir);
		if (err)
			goto out_ro;
	}

	finish_reservation(c);
	if (new_inode) {
		mark_inode_clean(c, new_ui);
		spin_lock(&new_ui->ui_lock);
		new_ui->synced_i_size = new_ui->ui_size;
		spin_unlock(&new_ui->ui_lock);
	}
	/*
	 * No need to mark whiteout inode clean.
	 * Whiteout doesn't have non-zero size, no need to update
	 * synced_i_size for whiteout_ui.
	 */
	mark_inode_clean(c, ubifs_inode(old_dir));
	if (move)
		mark_inode_clean(c, ubifs_inode(new_dir));
	kfree(dent);
	return 0;

out_release:
	release_head(c, BASEHD);
out_ro:
	ubifs_ro_mode(c, err);
	if (orphan_added)
		ubifs_delete_orphan(c, new_inode->i_ino);
out_finish:
	finish_reservation(c);
out_free:
	kfree(dent);
	return err;
}

/**
 * truncate_data_node - re-compress/encrypt a truncated data node.
 * @c: UBIFS file-system description object
 * @inode: inode which refers to the data node
 * @block: data block number
 * @dn: data node to re-compress
 * @new_len: new length
 * @dn_size: size of the data node @dn in memory
 *
 * This function is used when an inode is truncated and the last data node of
 * the inode has to be re-compressed/encrypted and re-written.
 */
static int truncate_data_node(const struct ubifs_info *c, const struct inode *inode,
			      unsigned int block, struct ubifs_data_node *dn,
			      int *new_len, int dn_size)
{
	void *buf;
	int err, dlen, compr_type, out_len, data_size;

	out_len = le32_to_cpu(dn->size);
	buf = kmalloc_array(out_len, WORST_COMPR_FACTOR, GFP_NOFS);
	if (!buf)
		return -ENOMEM;

	dlen = le32_to_cpu(dn->ch.len) - UBIFS_DATA_NODE_SZ;
	data_size = dn_size - UBIFS_DATA_NODE_SZ;
	compr_type = le16_to_cpu(dn->compr_type);

	if (IS_ENCRYPTED(inode)) {
		err = ubifs_decrypt(inode, dn, &dlen, block);
		if (err)
			goto out;
	}

	if (compr_type == UBIFS_COMPR_NONE) {
		out_len = *new_len;
	} else {
		err = ubifs_decompress(c, &dn->data, dlen, buf, &out_len, compr_type);
		if (err)
			goto out;

		ubifs_compress(c, buf, *new_len, &dn->data, &out_len, &compr_type);
	}

	if (IS_ENCRYPTED(inode)) {
		err = ubifs_encrypt(inode, dn, out_len, &data_size, block);
		if (err)
			goto out;

		out_len = data_size;
	} else {
		dn->compr_size = 0;
	}

	ubifs_assert(c, out_len <= UBIFS_BLOCK_SIZE);
	dn->compr_type = cpu_to_le16(compr_type);
	dn->size = cpu_to_le32(*new_len);
	*new_len = UBIFS_DATA_NODE_SZ + out_len;
	err = 0;
out:
	kfree(buf);
	return err;
}

/**
 * ubifs_jnl_truncate - update the journal for a truncation.
 * @c: UBIFS file-system description object
 * @inode: inode to truncate
 * @old_size: old size
 * @new_size: new size
 *
 * When the size of a file decreases due to truncation, a truncation node is
 * written, the journal tree is updated, and the last data block is re-written
 * if it has been affected. The inode is also updated in order to synchronize
 * the new inode size.
 *
 * This function marks the inode as clean and returns zero on success. In case
 * of failure, a negative error code is returned.
 */
int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode,
		       loff_t old_size, loff_t new_size)
{
	union ubifs_key key, to_key;
	struct ubifs_ino_node *ino;
	struct ubifs_trun_node *trun;
	struct ubifs_data_node *dn;
	int err, dlen, len, lnum, offs, bit, sz, sync = IS_SYNC(inode);
	int dn_size;
	struct ubifs_inode *ui = ubifs_inode(inode);
	ino_t inum = inode->i_ino;
	unsigned int blk;
	u8 hash_ino[UBIFS_HASH_ARR_SZ];
	u8 hash_dn[UBIFS_HASH_ARR_SZ];

	dbg_jnl("ino %lu, size %lld -> %lld",
		(unsigned long)inum, old_size, new_size);
	ubifs_assert(c, !ui->data_len);
	ubifs_assert(c, S_ISREG(inode->i_mode));
	ubifs_assert(c, mutex_is_locked(&ui->ui_mutex));

	dn_size = COMPRESSED_DATA_NODE_BUF_SZ;

	if (IS_ENCRYPTED(inode))
		dn_size += UBIFS_CIPHER_BLOCK_SIZE;

	sz =  UBIFS_TRUN_NODE_SZ + UBIFS_INO_NODE_SZ +
		dn_size + ubifs_auth_node_sz(c);

	ino = kmalloc(sz, GFP_NOFS);
	if (!ino)
		return -ENOMEM;

	trun = (void *)ino + UBIFS_INO_NODE_SZ;
	trun->ch.node_type = UBIFS_TRUN_NODE;
	trun->inum = cpu_to_le32(inum);
	trun->old_size = cpu_to_le64(old_size);
	trun->new_size = cpu_to_le64(new_size);
	zero_trun_node_unused(trun);

	dlen = new_size & (UBIFS_BLOCK_SIZE - 1);
	if (dlen) {
		/* Get last data block so it can be truncated */
		dn = (void *)trun + UBIFS_TRUN_NODE_SZ;
		blk = new_size >> UBIFS_BLOCK_SHIFT;
		data_key_init(c, &key, inum, blk);
		dbg_jnlk(&key, "last block key ");
		err = ubifs_tnc_lookup(c, &key, dn);
		if (err == -ENOENT)
			dlen = 0; /* Not found (so it is a hole) */
		else if (err)
			goto out_free;
		else {
			int dn_len = le32_to_cpu(dn->size);

			if (dn_len <= 0 || dn_len > UBIFS_BLOCK_SIZE) {
				ubifs_err(c, "bad data node (block %u, inode %lu)",
					  blk, inode->i_ino);
				ubifs_dump_node(c, dn, dn_size);
				err = -EUCLEAN;
				goto out_free;
			}

			if (dn_len <= dlen)
				dlen = 0; /* Nothing to do */
			else {
				err = truncate_data_node(c, inode, blk, dn,
						&dlen, dn_size);
				if (err)
					goto out_free;
			}
		}
	}

	/* Must make reservation before allocating sequence numbers */
	len = UBIFS_TRUN_NODE_SZ + UBIFS_INO_NODE_SZ;

	if (ubifs_authenticated(c))
		len += ALIGN(dlen, 8) + ubifs_auth_node_sz(c);
	else
		len += dlen;

	err = make_reservation(c, BASEHD, len);
	if (err)
		goto out_free;

	pack_inode(c, ino, inode, 0);
	err = ubifs_node_calc_hash(c, ino, hash_ino);
	if (err)
		goto out_release;

	ubifs_prep_grp_node(c, trun, UBIFS_TRUN_NODE_SZ, dlen ? 0 : 1);
	if (dlen) {
		ubifs_prep_grp_node(c, dn, dlen, 1);
		err = ubifs_node_calc_hash(c, dn, hash_dn);
		if (err)
			goto out_release;
	}

	err = write_head(c, BASEHD, ino, len, &lnum, &offs, sync);
	if (err)
		goto out_release;
	if (!sync)
		ubifs_wbuf_add_ino_nolock(&c->jheads[BASEHD].wbuf, inum);
	release_head(c, BASEHD);

	ubifs_add_auth_dirt(c, lnum);

	if (dlen) {
		sz = offs + UBIFS_INO_NODE_SZ + UBIFS_TRUN_NODE_SZ;
		err = ubifs_tnc_add(c, &key, lnum, sz, dlen, hash_dn);
		if (err)
			goto out_ro;
	}

	ino_key_init(c, &key, inum);
	err = ubifs_tnc_add(c, &key, lnum, offs, UBIFS_INO_NODE_SZ, hash_ino);
	if (err)
		goto out_ro;

	err = ubifs_add_dirt(c, lnum, UBIFS_TRUN_NODE_SZ);
	if (err)
		goto out_ro;

	bit = new_size & (UBIFS_BLOCK_SIZE - 1);
	blk = (new_size >> UBIFS_BLOCK_SHIFT) + (bit ? 1 : 0);
	data_key_init(c, &key, inum, blk);

	bit = old_size & (UBIFS_BLOCK_SIZE - 1);
	blk = (old_size >> UBIFS_BLOCK_SHIFT) - (bit ? 0 : 1);
	data_key_init(c, &to_key, inum, blk);

	err = ubifs_tnc_remove_range(c, &key, &to_key);
	if (err)
		goto out_ro;

	finish_reservation(c);
	spin_lock(&ui->ui_lock);
	ui->synced_i_size = ui->ui_size;
	spin_unlock(&ui->ui_lock);
	mark_inode_clean(c, ui);
	kfree(ino);
	return 0;

out_release:
	release_head(c, BASEHD);
out_ro:
	ubifs_ro_mode(c, err);
	finish_reservation(c);
out_free:
	kfree(ino);
	return err;
}


/**
 * ubifs_jnl_delete_xattr - delete an extended attribute.
 * @c: UBIFS file-system description object
 * @host: host inode
 * @inode: extended attribute inode
 * @nm: extended attribute entry name
 *
 * This function delete an extended attribute which is very similar to
 * un-linking regular files - it writes a deletion xentry, a deletion inode and
 * updates the target inode. Returns zero in case of success and a negative
 * error code in case of failure.
 */
int ubifs_jnl_delete_xattr(struct ubifs_info *c, const struct inode *host,
			   const struct inode *inode,
			   const struct fscrypt_name *nm)
{
	int err, xlen, hlen, len, lnum, xent_offs, aligned_xlen, write_len;
	struct ubifs_dent_node *xent;
	struct ubifs_ino_node *ino;
	union ubifs_key xent_key, key1, key2;
	int sync = IS_DIRSYNC(host);
	struct ubifs_inode *host_ui = ubifs_inode(host);
	u8 hash[UBIFS_HASH_ARR_SZ];

	ubifs_assert(c, inode->i_nlink == 0);
	ubifs_assert(c, mutex_is_locked(&host_ui->ui_mutex));

	/*
	 * Since we are deleting the inode, we do not bother to attach any data
	 * to it and assume its length is %UBIFS_INO_NODE_SZ.
	 */
	xlen = UBIFS_DENT_NODE_SZ + fname_len(nm) + 1;
	aligned_xlen = ALIGN(xlen, 8);
	hlen = host_ui->data_len + UBIFS_INO_NODE_SZ;
	len = aligned_xlen + UBIFS_INO_NODE_SZ + ALIGN(hlen, 8);

	write_len = len + ubifs_auth_node_sz(c);

	xent = kzalloc(write_len, GFP_NOFS);
	if (!xent)
		return -ENOMEM;

	/* Make reservation before allocating sequence numbers */
	err = make_reservation(c, BASEHD, write_len);
	if (err) {
		kfree(xent);
		return err;
	}

	xent->ch.node_type = UBIFS_XENT_NODE;
	xent_key_init(c, &xent_key, host->i_ino, nm);
	key_write(c, &xent_key, xent->key);
	xent->inum = 0;
	xent->type = get_dent_type(inode->i_mode);
	xent->nlen = cpu_to_le16(fname_len(nm));
	memcpy(xent->name, fname_name(nm), fname_len(nm));
	xent->name[fname_len(nm)] = '\0';
	zero_dent_node_unused(xent);
	ubifs_prep_grp_node(c, xent, xlen, 0);

	ino = (void *)xent + aligned_xlen;
	pack_inode(c, ino, inode, 0);
	ino = (void *)ino + UBIFS_INO_NODE_SZ;
	pack_inode(c, ino, host, 1);
	err = ubifs_node_calc_hash(c, ino, hash);
	if (err)
		goto out_release;

	err = write_head(c, BASEHD, xent, write_len, &lnum, &xent_offs, sync);
	if (!sync && !err)
		ubifs_wbuf_add_ino_nolock(&c->jheads[BASEHD].wbuf, host->i_ino);
	release_head(c, BASEHD);

	ubifs_add_auth_dirt(c, lnum);
	kfree(xent);
	if (err)
		goto out_ro;

	/* Remove the extended attribute entry from TNC */
	err = ubifs_tnc_remove_nm(c, &xent_key, nm);
	if (err)
		goto out_ro;
	err = ubifs_add_dirt(c, lnum, xlen);
	if (err)
		goto out_ro;

	/*
	 * Remove all nodes belonging to the extended attribute inode from TNC.
	 * Well, there actually must be only one node - the inode itself.
	 */
	lowest_ino_key(c, &key1, inode->i_ino);
	highest_ino_key(c, &key2, inode->i_ino);
	err = ubifs_tnc_remove_range(c, &key1, &key2);
	if (err)
		goto out_ro;
	err = ubifs_add_dirt(c, lnum, UBIFS_INO_NODE_SZ);
	if (err)
		goto out_ro;

	/* And update TNC with the new host inode position */
	ino_key_init(c, &key1, host->i_ino);
	err = ubifs_tnc_add(c, &key1, lnum, xent_offs + len - hlen, hlen, hash);
	if (err)
		goto out_ro;

	finish_reservation(c);
	spin_lock(&host_ui->ui_lock);
	host_ui->synced_i_size = host_ui->ui_size;
	spin_unlock(&host_ui->ui_lock);
	mark_inode_clean(c, host_ui);
	return 0;

out_release:
	kfree(xent);
	release_head(c, BASEHD);
out_ro:
	ubifs_ro_mode(c, err);
	finish_reservation(c);
	return err;
}

/**
 * ubifs_jnl_change_xattr - change an extended attribute.
 * @c: UBIFS file-system description object
 * @inode: extended attribute inode
 * @host: host inode
 *
 * This function writes the updated version of an extended attribute inode and
 * the host inode to the journal (to the base head). The host inode is written
 * after the extended attribute inode in order to guarantee that the extended
 * attribute will be flushed when the inode is synchronized by 'fsync()' and
 * consequently, the write-buffer is synchronized. This function returns zero
 * in case of success and a negative error code in case of failure.
 */
int ubifs_jnl_change_xattr(struct ubifs_info *c, const struct inode *inode,
			   const struct inode *host)
{
	int err, len1, len2, aligned_len, aligned_len1, lnum, offs;
	struct ubifs_inode *host_ui = ubifs_inode(host);
	struct ubifs_ino_node *ino;
	union ubifs_key key;
	int sync = IS_DIRSYNC(host);
	u8 hash_host[UBIFS_HASH_ARR_SZ];
	u8 hash[UBIFS_HASH_ARR_SZ];

	dbg_jnl("ino %lu, ino %lu", host->i_ino, inode->i_ino);
	ubifs_assert(c, inode->i_nlink > 0);
	ubifs_assert(c, mutex_is_locked(&host_ui->ui_mutex));

	len1 = UBIFS_INO_NODE_SZ + host_ui->data_len;
	len2 = UBIFS_INO_NODE_SZ + ubifs_inode(inode)->data_len;
	aligned_len1 = ALIGN(len1, 8);
	aligned_len = aligned_len1 + ALIGN(len2, 8);

	aligned_len += ubifs_auth_node_sz(c);

	ino = kzalloc(aligned_len, GFP_NOFS);
	if (!ino)
		return -ENOMEM;

	/* Make reservation before allocating sequence numbers */
	err = make_reservation(c, BASEHD, aligned_len);
	if (err)
		goto out_free;

	pack_inode(c, ino, host, 0);
	err = ubifs_node_calc_hash(c, ino, hash_host);
	if (err)
		goto out_release;
	pack_inode(c, (void *)ino + aligned_len1, inode, 1);
	err = ubifs_node_calc_hash(c, (void *)ino + aligned_len1, hash);
	if (err)
		goto out_release;

	err = write_head(c, BASEHD, ino, aligned_len, &lnum, &offs, 0);
	if (!sync && !err) {
		struct ubifs_wbuf *wbuf = &c->jheads[BASEHD].wbuf;

		ubifs_wbuf_add_ino_nolock(wbuf, host->i_ino);
		ubifs_wbuf_add_ino_nolock(wbuf, inode->i_ino);
	}
	release_head(c, BASEHD);
	if (err)
		goto out_ro;

	ubifs_add_auth_dirt(c, lnum);

	ino_key_init(c, &key, host->i_ino);
	err = ubifs_tnc_add(c, &key, lnum, offs, len1, hash_host);
	if (err)
		goto out_ro;

	ino_key_init(c, &key, inode->i_ino);
	err = ubifs_tnc_add(c, &key, lnum, offs + aligned_len1, len2, hash);
	if (err)
		goto out_ro;

	finish_reservation(c);
	spin_lock(&host_ui->ui_lock);
	host_ui->synced_i_size = host_ui->ui_size;
	spin_unlock(&host_ui->ui_lock);
	mark_inode_clean(c, host_ui);
	kfree(ino);
	return 0;

out_release:
	release_head(c, BASEHD);
out_ro:
	ubifs_ro_mode(c, err);
	finish_reservation(c);
out_free:
	kfree(ino);
	return err;
}