aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ntfs/attrib.c
blob: f14fde2b03d68f03e38b1aa62580227a5243cc91 (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
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
/**
 * attrib.c - NTFS attribute operations.  Part of the Linux-NTFS project.
 *
 * Copyright (c) 2001-2007 Anton Altaparmakov
 * Copyright (c) 2002 Richard Russon
 *
 * This program/include file 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; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program/include file is distributed in the hope that it will 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 (in the main directory of the Linux-NTFS
 * distribution in the file COPYING); if not, write to the Free Software
 * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */

#include <linux/buffer_head.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/writeback.h>

#include "attrib.h"
#include "debug.h"
#include "layout.h"
#include "lcnalloc.h"
#include "malloc.h"
#include "mft.h"
#include "ntfs.h"
#include "types.h"

/**
 * ntfs_map_runlist_nolock - map (a part of) a runlist of an ntfs inode
 * @ni:		ntfs inode for which to map (part of) a runlist
 * @vcn:	map runlist part containing this vcn
 * @ctx:	active attribute search context if present or NULL if not
 *
 * Map the part of a runlist containing the @vcn of the ntfs inode @ni.
 *
 * If @ctx is specified, it is an active search context of @ni and its base mft
 * record.  This is needed when ntfs_map_runlist_nolock() encounters unmapped
 * runlist fragments and allows their mapping.  If you do not have the mft
 * record mapped, you can specify @ctx as NULL and ntfs_map_runlist_nolock()
 * will perform the necessary mapping and unmapping.
 *
 * Note, ntfs_map_runlist_nolock() saves the state of @ctx on entry and
 * restores it before returning.  Thus, @ctx will be left pointing to the same
 * attribute on return as on entry.  However, the actual pointers in @ctx may
 * point to different memory locations on return, so you must remember to reset
 * any cached pointers from the @ctx, i.e. after the call to
 * ntfs_map_runlist_nolock(), you will probably want to do:
 *	m = ctx->mrec;
 *	a = ctx->attr;
 * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that
 * you cache ctx->mrec in a variable @m of type MFT_RECORD *.
 *
 * Return 0 on success and -errno on error.  There is one special error code
 * which is not an error as such.  This is -ENOENT.  It means that @vcn is out
 * of bounds of the runlist.
 *
 * Note the runlist can be NULL after this function returns if @vcn is zero and
 * the attribute has zero allocated size, i.e. there simply is no runlist.
 *
 * WARNING: If @ctx is supplied, regardless of whether success or failure is
 *	    returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx
 *	    is no longer valid, i.e. you need to either call
 *	    ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
 *	    In that case PTR_ERR(@ctx->mrec) will give you the error code for
 *	    why the mapping of the old inode failed.
 *
 * Locking: - The runlist described by @ni must be locked for writing on entry
 *	      and is locked on return.  Note the runlist will be modified.
 *	    - If @ctx is NULL, the base mft record of @ni must not be mapped on
 *	      entry and it will be left unmapped on return.
 *	    - If @ctx is not NULL, the base mft record must be mapped on entry
 *	      and it will be left mapped on return.
 */
int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn, ntfs_attr_search_ctx *ctx)
{
	VCN end_vcn;
	unsigned long flags;
	ntfs_inode *base_ni;
	MFT_RECORD *m;
	ATTR_RECORD *a;
	runlist_element *rl;
	struct page *put_this_page = NULL;
	int err = 0;
	bool ctx_is_temporary, ctx_needs_reset;
	ntfs_attr_search_ctx old_ctx = { NULL, };

	ntfs_debug("Mapping runlist part containing vcn 0x%llx.",
			(unsigned long long)vcn);
	if (!NInoAttr(ni))
		base_ni = ni;
	else
		base_ni = ni->ext.base_ntfs_ino;
	if (!ctx) {
		ctx_is_temporary = ctx_needs_reset = true;
		m = map_mft_record(base_ni);
		if (IS_ERR(m))
			return PTR_ERR(m);
		ctx = ntfs_attr_get_search_ctx(base_ni, m);
		if (unlikely(!ctx)) {
			err = -ENOMEM;
			goto err_out;
		}
	} else {
		VCN allocated_size_vcn;

		BUG_ON(IS_ERR(ctx->mrec));
		a = ctx->attr;
		BUG_ON(!a->non_resident);
		ctx_is_temporary = false;
		end_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
		read_lock_irqsave(&ni->size_lock, flags);
		allocated_size_vcn = ni->allocated_size >>
				ni->vol->cluster_size_bits;
		read_unlock_irqrestore(&ni->size_lock, flags);
		if (!a->data.non_resident.lowest_vcn && end_vcn <= 0)
			end_vcn = allocated_size_vcn - 1;
		/*
		 * If we already have the attribute extent containing @vcn in
		 * @ctx, no need to look it up again.  We slightly cheat in
		 * that if vcn exceeds the allocated size, we will refuse to
		 * map the runlist below, so there is definitely no need to get
		 * the right attribute extent.
		 */
		if (vcn >= allocated_size_vcn || (a->type == ni->type &&
				a->name_length == ni->name_len &&
				!memcmp((u8*)a + le16_to_cpu(a->name_offset),
				ni->name, ni->name_len) &&
				sle64_to_cpu(a->data.non_resident.lowest_vcn)
				<= vcn && end_vcn >= vcn))
			ctx_needs_reset = false;
		else {
			/* Save the old search context. */
			old_ctx = *ctx;
			/*
			 * If the currently mapped (extent) inode is not the
			 * base inode we will unmap it when we reinitialize the
			 * search context which means we need to get a
			 * reference to the page containing the mapped mft
			 * record so we do not accidentally drop changes to the
			 * mft record when it has not been marked dirty yet.
			 */
			if (old_ctx.base_ntfs_ino && old_ctx.ntfs_ino !=
					old_ctx.base_ntfs_ino) {
				put_this_page = old_ctx.ntfs_ino->page;
				page_cache_get(put_this_page);
			}
			/*
			 * Reinitialize the search context so we can lookup the
			 * needed attribute extent.
			 */
			ntfs_attr_reinit_search_ctx(ctx);
			ctx_needs_reset = true;
		}
	}
	if (ctx_needs_reset) {
		err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
				CASE_SENSITIVE, vcn, NULL, 0, ctx);
		if (unlikely(err)) {
			if (err == -ENOENT)
				err = -EIO;
			goto err_out;
		}
		BUG_ON(!ctx->attr->non_resident);
	}
	a = ctx->attr;
	/*
	 * Only decompress the mapping pairs if @vcn is inside it.  Otherwise
	 * we get into problems when we try to map an out of bounds vcn because
	 * we then try to map the already mapped runlist fragment and
	 * ntfs_mapping_pairs_decompress() fails.
	 */
	end_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn) + 1;
	if (unlikely(vcn && vcn >= end_vcn)) {
		err = -ENOENT;
		goto err_out;
	}
	rl = ntfs_mapping_pairs_decompress(ni->vol, a, ni->runlist.rl);
	if (IS_ERR(rl))
		err = PTR_ERR(rl);
	else
		ni->runlist.rl = rl;
err_out:
	if (ctx_is_temporary) {
		if (likely(ctx))
			ntfs_attr_put_search_ctx(ctx);
		unmap_mft_record(base_ni);
	} else if (ctx_needs_reset) {
		/*
		 * If there is no attribute list, restoring the search context
		 * is accomplished simply by copying the saved context back over
		 * the caller supplied context.  If there is an attribute list,
		 * things are more complicated as we need to deal with mapping
		 * of mft records and resulting potential changes in pointers.
		 */
		if (NInoAttrList(base_ni)) {
			/*
			 * If the currently mapped (extent) inode is not the
			 * one we had before, we need to unmap it and map the
			 * old one.
			 */
			if (ctx->ntfs_ino != old_ctx.ntfs_ino) {
				/*
				 * If the currently mapped inode is not the
				 * base inode, unmap it.
				 */
				if (ctx->base_ntfs_ino && ctx->ntfs_ino !=
						ctx->base_ntfs_ino) {
					unmap_extent_mft_record(ctx->ntfs_ino);
					ctx->mrec = ctx->base_mrec;
					BUG_ON(!ctx->mrec);
				}
				/*
				 * If the old mapped inode is not the base
				 * inode, map it.
				 */
				if (old_ctx.base_ntfs_ino &&
						old_ctx.ntfs_ino !=
						old_ctx.base_ntfs_ino) {
retry_map:
					ctx->mrec = map_mft_record(
							old_ctx.ntfs_ino);
					/*
					 * Something bad has happened.  If out
					 * of memory retry till it succeeds.
					 * Any other errors are fatal and we
					 * return the error code in ctx->mrec.
					 * Let the caller deal with it...  We
					 * just need to fudge things so the
					 * caller can reinit and/or put the
					 * search context safely.
					 */
					if (IS_ERR(ctx->mrec)) {
						if (PTR_ERR(ctx->mrec) ==
								-ENOMEM) {
							schedule();
							goto retry_map;
						} else
							old_ctx.ntfs_ino =
								old_ctx.
								base_ntfs_ino;
					}
				}
			}
			/* Update the changed pointers in the saved context. */
			if (ctx->mrec != old_ctx.mrec) {
				if (!IS_ERR(ctx->mrec))
					old_ctx.attr = (ATTR_RECORD*)(
							(u8*)ctx->mrec +
							((u8*)old_ctx.attr -
							(u8*)old_ctx.mrec));
				old_ctx.mrec = ctx->mrec;
			}
		}
		/* Restore the search context to the saved one. */
		*ctx = old_ctx;
		/*
		 * We drop the reference on the page we took earlier.  In the
		 * case that IS_ERR(ctx->mrec) is true this means we might lose
		 * some changes to the mft record that had been made between
		 * the last time it was marked dirty/written out and now.  This
		 * at this stage is not a problem as the mapping error is fatal
		 * enough that the mft record cannot be written out anyway and
		 * the caller is very likely to shutdown the whole inode
		 * immediately and mark the volume dirty for chkdsk to pick up
		 * the pieces anyway.
		 */
		if (put_this_page)
			page_cache_release(put_this_page);
	}
	return err;
}

/**
 * ntfs_map_runlist - map (a part of) a runlist of an ntfs inode
 * @ni:		ntfs inode for which to map (part of) a runlist
 * @vcn:	map runlist part containing this vcn
 *
 * Map the part of a runlist containing the @vcn of the ntfs inode @ni.
 *
 * Return 0 on success and -errno on error.  There is one special error code
 * which is not an error as such.  This is -ENOENT.  It means that @vcn is out
 * of bounds of the runlist.
 *
 * Locking: - The runlist must be unlocked on entry and is unlocked on return.
 *	    - This function takes the runlist lock for writing and may modify
 *	      the runlist.
 */
int ntfs_map_runlist(ntfs_inode *ni, VCN vcn)
{
	int err = 0;

	down_write(&ni->runlist.lock);
	/* Make sure someone else didn't do the work while we were sleeping. */
	if (likely(ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn) <=
			LCN_RL_NOT_MAPPED))
		err = ntfs_map_runlist_nolock(ni, vcn, NULL);
	up_write(&ni->runlist.lock);
	return err;
}

/**
 * ntfs_attr_vcn_to_lcn_nolock - convert a vcn into a lcn given an ntfs inode
 * @ni:			ntfs inode of the attribute whose runlist to search
 * @vcn:		vcn to convert
 * @write_locked:	true if the runlist is locked for writing
 *
 * Find the virtual cluster number @vcn in the runlist of the ntfs attribute
 * described by the ntfs inode @ni and return the corresponding logical cluster
 * number (lcn).
 *
 * If the @vcn is not mapped yet, the attempt is made to map the attribute
 * extent containing the @vcn and the vcn to lcn conversion is retried.
 *
 * If @write_locked is true the caller has locked the runlist for writing and
 * if false for reading.
 *
 * Since lcns must be >= 0, we use negative return codes with special meaning:
 *
 * Return code	Meaning / Description
 * ==========================================
 *  LCN_HOLE	Hole / not allocated on disk.
 *  LCN_ENOENT	There is no such vcn in the runlist, i.e. @vcn is out of bounds.
 *  LCN_ENOMEM	Not enough memory to map runlist.
 *  LCN_EIO	Critical error (runlist/file is corrupt, i/o error, etc).
 *
 * Locking: - The runlist must be locked on entry and is left locked on return.
 *	    - If @write_locked is 'false', i.e. the runlist is locked for reading,
 *	      the lock may be dropped inside the function so you cannot rely on
 *	      the runlist still being the same when this function returns.
 */
LCN ntfs_attr_vcn_to_lcn_nolock(ntfs_inode *ni, const VCN vcn,
		const bool write_locked)
{
	LCN lcn;
	unsigned long flags;
	bool is_retry = false;

	ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, %s_locked.",
			ni->mft_no, (unsigned long long)vcn,
			write_locked ? "write" : "read");
	BUG_ON(!ni);
	BUG_ON(!NInoNonResident(ni));
	BUG_ON(vcn < 0);
	if (!ni->runlist.rl) {
		read_lock_irqsave(&ni->size_lock, flags);
		if (!ni->allocated_size) {
			read_unlock_irqrestore(&ni->size_lock, flags);
			return LCN_ENOENT;
		}
		read_unlock_irqrestore(&ni->size_lock, flags);
	}
retry_remap:
	/* Convert vcn to lcn.  If that fails map the runlist and retry once. */
	lcn = ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn);
	if (likely(lcn >= LCN_HOLE)) {
		ntfs_debug("Done, lcn 0x%llx.", (long long)lcn);
		return lcn;
	}
	if (lcn != LCN_RL_NOT_MAPPED) {
		if (lcn != LCN_ENOENT)
			lcn = LCN_EIO;
	} else if (!is_retry) {
		int err;

		if (!write_locked) {
			up_read(&ni->runlist.lock);
			down_write(&ni->runlist.lock);
			if (unlikely(ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn) !=
					LCN_RL_NOT_MAPPED)) {
				up_write(&ni->runlist.lock);
				down_read(&ni->runlist.lock);
				goto retry_remap;
			}
		}
		err = ntfs_map_runlist_nolock(ni, vcn, NULL);
		if (!write_locked) {
			up_write(&ni->runlist.lock);
			down_read(&ni->runlist.lock);
		}
		if (likely(!err)) {
			is_retry = true;
			goto retry_remap;
		}
		if (err == -ENOENT)
			lcn = LCN_ENOENT;
		else if (err == -ENOMEM)
			lcn = LCN_ENOMEM;
		else
			lcn = LCN_EIO;
	}
	if (lcn != LCN_ENOENT)
		ntfs_error(ni->vol->sb, "Failed with error code %lli.",
				(long long)lcn);
	return lcn;
}

/**
 * ntfs_attr_find_vcn_nolock - find a vcn in the runlist of an ntfs inode
 * @ni:		ntfs inode describing the runlist to search
 * @vcn:	vcn to find
 * @ctx:	active attribute search context if present or NULL if not
 *
 * Find the virtual cluster number @vcn in the runlist described by the ntfs
 * inode @ni and return the address of the runlist element containing the @vcn.
 *
 * If the @vcn is not mapped yet, the attempt is made to map the attribute
 * extent containing the @vcn and the vcn to lcn conversion is retried.
 *
 * If @ctx is specified, it is an active search context of @ni and its base mft
 * record.  This is needed when ntfs_attr_find_vcn_nolock() encounters unmapped
 * runlist fragments and allows their mapping.  If you do not have the mft
 * record mapped, you can specify @ctx as NULL and ntfs_attr_find_vcn_nolock()
 * will perform the necessary mapping and unmapping.
 *
 * Note, ntfs_attr_find_vcn_nolock() saves the state of @ctx on entry and
 * restores it before returning.  Thus, @ctx will be left pointing to the same
 * attribute on return as on entry.  However, the actual pointers in @ctx may
 * point to different memory locations on return, so you must remember to reset
 * any cached pointers from the @ctx, i.e. after the call to
 * ntfs_attr_find_vcn_nolock(), you will probably want to do:
 *	m = ctx->mrec;
 *	a = ctx->attr;
 * Assuming you cache ctx->attr in a variable @a of type ATTR_RECORD * and that
 * you cache ctx->mrec in a variable @m of type MFT_RECORD *.
 * Note you need to distinguish between the lcn of the returned runlist element
 * being >= 0 and LCN_HOLE.  In the later case you have to return zeroes on
 * read and allocate clusters on write.
 *
 * Return the runlist element containing the @vcn on success and
 * ERR_PTR(-errno) on error.  You need to test the return value with IS_ERR()
 * to decide if the return is success or failure and PTR_ERR() to get to the
 * error code if IS_ERR() is true.
 *
 * The possible error return codes are:
 *	-ENOENT - No such vcn in the runlist, i.e. @vcn is out of bounds.
 *	-ENOMEM - Not enough memory to map runlist.
 *	-EIO	- Critical error (runlist/file is corrupt, i/o error, etc).
 *
 * WARNING: If @ctx is supplied, regardless of whether success or failure is
 *	    returned, you need to check IS_ERR(@ctx->mrec) and if 'true' the @ctx
 *	    is no longer valid, i.e. you need to either call
 *	    ntfs_attr_reinit_search_ctx() or ntfs_attr_put_search_ctx() on it.
 *	    In that case PTR_ERR(@ctx->mrec) will give you the error code for
 *	    why the mapping of the old inode failed.
 *
 * Locking: - The runlist described by @ni must be locked for writing on entry
 *	      and is locked on return.  Note the runlist may be modified when
 *	      needed runlist fragments need to be mapped.
 *	    - If @ctx is NULL, the base mft record of @ni must not be mapped on
 *	      entry and it will be left unmapped on return.
 *	    - If @ctx is not NULL, the base mft record must be mapped on entry
 *	      and it will be left mapped on return.
 */
runlist_element *ntfs_attr_find_vcn_nolock(ntfs_inode *ni, const VCN vcn,
		ntfs_attr_search_ctx *ctx)
{
	unsigned long flags;
	runlist_element *rl;
	int err = 0;
	bool is_retry = false;

	ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, with%s ctx.",
			ni->mft_no, (unsigned long long)vcn, ctx ? "" : "out");
	BUG_ON(!ni);
	BUG_ON(!NInoNonResident(ni));
	BUG_ON(vcn < 0);
	if (!ni->runlist.rl) {
		read_lock_irqsave(&ni->size_lock, flags);
		if (!ni->allocated_size) {
			read_unlock_irqrestore(&ni->size_lock, flags);
			return ERR_PTR(-ENOENT);
		}
		read_unlock_irqrestore(&ni->size_lock, flags);
	}
retry_remap:
	rl = ni->runlist.rl;
	if (likely(rl && vcn >= rl[0].vcn)) {
		while (likely(rl->length)) {
			if (unlikely(vcn < rl[1].vcn)) {
				if (likely(rl->lcn >= LCN_HOLE)) {
					ntfs_debug("Done.");
					return rl;
				}
				break;
			}
			rl++;
		}
		if (likely(rl->lcn != LCN_RL_NOT_MAPPED)) {
			if (likely(rl->lcn == LCN_ENOENT))
				err = -ENOENT;
			else
				err = -EIO;
		}
	}
	if (!err && !is_retry) {
		/*
		 * If the search context is invalid we cannot map the unmapped
		 * region.
		 */
		if (IS_ERR(ctx->mrec))
			err = PTR_ERR(ctx->mrec);
		else {
			/*
			 * The @vcn is in an unmapped region, map the runlist
			 * and retry.
			 */
			err = ntfs_map_runlist_nolock(ni, vcn, ctx);
			if (likely(!err)) {
				is_retry = true;
				goto retry_remap;
			}
		}
		if (err == -EINVAL)
			err = -EIO;
	} else if (!err)
		err = -EIO;
	if (err != -ENOENT)
		ntfs_error(ni->vol->sb, "Failed with error code %i.", err);
	return ERR_PTR(err);
}

/**
 * ntfs_attr_find - find (next) attribute in mft record
 * @type:	attribute type to find
 * @name:	attribute name to find (optional, i.e. NULL means don't care)
 * @name_len:	attribute name length (only needed if @name present)
 * @ic:		IGNORE_CASE or CASE_SENSITIVE (ignored if @name not present)
 * @val:	attribute value to find (optional, resident attributes only)
 * @val_len:	attribute value length
 * @ctx:	search context with mft record and attribute to search from
 *
 * You should not need to call this function directly.  Use ntfs_attr_lookup()
 * instead.
 *
 * ntfs_attr_find() takes a search context @ctx as parameter and searches the
 * mft record specified by @ctx->mrec, beginning at @ctx->attr, for an
 * attribute of @type, optionally @name and @val.
 *
 * If the attribute is found, ntfs_attr_find() returns 0 and @ctx->attr will
 * point to the found attribute.
 *
 * If the attribute is not found, ntfs_attr_find() returns -ENOENT and
 * @ctx->attr will point to the attribute before which the attribute being
 * searched for would need to be inserted if such an action were to be desired.
 *
 * On actual error, ntfs_attr_find() returns -EIO.  In this case @ctx->attr is
 * undefined and in particular do not rely on it not changing.
 *
 * If @ctx->is_first is 'true', the search begins with @ctx->attr itself.  If it
 * is 'false', the search begins after @ctx->attr.
 *
 * If @ic is IGNORE_CASE, the @name comparisson is not case sensitive and
 * @ctx->ntfs_ino must be set to the ntfs inode to which the mft record
 * @ctx->mrec belongs.  This is so we can get at the ntfs volume and hence at
 * the upcase table.  If @ic is CASE_SENSITIVE, the comparison is case
 * sensitive.  When @name is present, @name_len is the @name length in Unicode
 * characters.
 *
 * If @name is not present (NULL), we assume that the unnamed attribute is
 * being searched for.
 *
 * Finally, the resident attribute value @val is looked for, if present.  If
 * @val is not present (NULL), @val_len is ignored.
 *
 * ntfs_attr_find() only searches the specified mft record and it ignores the
 * presence of an attribute list attribute (unless it is the one being searched
 * for, obviously).  If you need to take attribute lists into consideration,
 * use ntfs_attr_lookup() instead (see below).  This also means that you cannot
 * use ntfs_attr_find() to search for extent records of non-resident
 * attributes, as extents with lowest_vcn != 0 are usually described by the
 * attribute list attribute only. - Note that it is possible that the first
 * extent is only in the attribute list while the last extent is in the base
 * mft record, so do not rely on being able to find the first extent in the
 * base mft record.
 *
 * Warning: Never use @val when looking for attribute types which can be
 *	    non-resident as this most likely will result in a crash!
 */
static int ntfs_attr_find(const ATTR_TYPE type, const ntfschar *name,
		const u32 name_len, const IGNORE_CASE_BOOL ic,
		const u8 *val, const u32 val_len, ntfs_attr_search_ctx *ctx)
{
	ATTR_RECORD *a;
	ntfs_volume *vol = ctx->ntfs_ino->vol;
	ntfschar *upcase = vol->upcase;
	u32 upcase_len = vol->upcase_len;

	/*
	 * Iterate over attributes in mft record starting at @ctx->attr, or the
	 * attribute following that, if @ctx->is_first is 'true'.
	 */
	if (ctx->is_first) {
		a = ctx->attr;
		ctx->is_first = false;
	} else
		a = (ATTR_RECORD*)((u8*)ctx->attr +
				le32_to_cpu(ctx->attr->length));
	for (;;	a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length))) {
		if ((u8*)a < (u8*)ctx->mrec || (u8*)a > (u8*)ctx->mrec +
				le32_to_cpu(ctx->mrec->bytes_allocated))
			break;
		ctx->attr = a;
		if (unlikely(le32_to_cpu(a->type) > le32_to_cpu(type) ||
				a->type == AT_END))
			return -ENOENT;
		if (unlikely(!a->length))
			break;
		if (a->type != type)
			continue;
		/*
		 * If @name is present, compare the two names.  If @name is
		 * missing, assume we want an unnamed attribute.
		 */
		if (!name) {
			/* The search failed if the found attribute is named. */
			if (a->name_length)
				return -ENOENT;
		} else if (!ntfs_are_names_equal(name, name_len,
			    (ntfschar*)((u8*)a + le16_to_cpu(a->name_offset)),
			    a->name_length, ic, upcase, upcase_len)) {
			register int rc;

			rc = ntfs_collate_names(name, name_len,
					(ntfschar*)((u8*)a +
					le16_to_cpu(a->name_offset)),
					a->name_length, 1, IGNORE_CASE,
					upcase, upcase_len);
			/*
			 * If @name collates before a->name, there is no
			 * matching attribute.
			 */
			if (rc == -1)
				return -ENOENT;
			/* If the strings are not equal, continue search. */
			if (rc)
				continue;
			rc = ntfs_collate_names(name, name_len,
					(ntfschar*)((u8*)a +
					le16_to_cpu(a->name_offset)),
					a->name_length, 1, CASE_SENSITIVE,
					upcase, upcase_len);
			if (rc == -1)
				return -ENOENT;
			if (rc)
				continue;
		}
		/*
		 * The names match or @name not present and attribute is
		 * unnamed.  If no @val specified, we have found the attribute
		 * and are done.
		 */
		if (!val)
			return 0;
		/* @val is present; compare values. */
		else {
			register int rc;

			rc = memcmp(val, (u8*)a + le16_to_cpu(
					a->data.resident.value_offset),
					min_t(u32, val_len, le32_to_cpu(
					a->data.resident.value_length)));
			/*
			 * If @val collates before the current attribute's
			 * value, there is no matching attribute.
			 */
			if (!rc) {
				register u32 avl;

				avl = le32_to_cpu(
						a->data.resident.value_length);
				if (val_len == avl)
					return 0;
				if (val_len < avl)
					return -ENOENT;
			} else if (rc < 0)
				return -ENOENT;
		}
	}
	ntfs_error(vol->sb, "Inode is corrupt.  Run chkdsk.");
	NVolSetErrors(vol);
	return -EIO;
}

/**
 * load_attribute_list - load an attribute list into memory
 * @vol:		ntfs volume from which to read
 * @runlist:		runlist of the attribute list
 * @al_start:		destination buffer
 * @size:		size of the destination buffer in bytes
 * @initialized_size:	initialized size of the attribute list
 *
 * Walk the runlist @runlist and load all clusters from it copying them into
 * the linear buffer @al. The maximum number of bytes copied to @al is @size
 * bytes. Note, @size does not need to be a multiple of the cluster size. If
 * @initialized_size is less than @size, the region in @al between
 * @initialized_size and @size will be zeroed and not read from disk.
 *
 * Return 0 on success or -errno on error.
 */
int load_attribute_list(ntfs_volume *vol, runlist *runlist, u8 *al_start,
		const s64 size, const s64 initialized_size)
{
	LCN lcn;
	u8 *al = al_start;
	u8 *al_end = al + initialized_size;
	runlist_element *rl;
	struct buffer_head *bh;
	struct super_block *sb;
	unsigned long block_size;
	unsigned long block, max_block;
	int err = 0;
	unsigned char block_size_bits;

	ntfs_debug("Entering.");
	if (!vol || !runlist || !al || size <= 0 || initialized_size < 0 ||
			initialized_size > size)
		return -EINVAL;
	if (!initialized_size) {
		memset(al, 0, size);
		return 0;
	}
	sb = vol->sb;
	block_size = sb->s_blocksize;
	block_size_bits = sb->s_blocksize_bits;
	down_read(&runlist->lock);
	rl = runlist->rl;
	if (!rl) {
		ntfs_error(sb, "Cannot read attribute list since runlist is "
				"missing.");
		goto err_out;	
	}
	/* Read all clusters specified by the runlist one run at a time. */
	while (rl->length) {
		lcn = ntfs_rl_vcn_to_lcn(rl, rl->vcn);
		ntfs_debug("Reading vcn = 0x%llx, lcn = 0x%llx.",
				(unsigned long long)rl->vcn,
				(unsigned long long)lcn);
		/* The attribute list cannot be sparse. */
		if (lcn < 0) {
			ntfs_error(sb, "ntfs_rl_vcn_to_lcn() failed.  Cannot "
					"read attribute list.");
			goto err_out;
		}
		block = lcn << vol->cluster_size_bits >> block_size_bits;
		/* Read the run from device in chunks of block_size bytes. */
		max_block = block + (rl->length << vol->cluster_size_bits >>
				block_size_bits);
		ntfs_debug("max_block = 0x%lx.", max_block);
		do {
			ntfs_debug("Reading block = 0x%lx.", block);
			bh = sb_bread(sb, block);
			if (!bh) {
				ntfs_error(sb, "sb_bread() failed. Cannot "
						"read attribute list.");
				goto err_out;
			}
			if (al + block_size >= al_end)
				goto do_final;
			memcpy(al, bh->b_data, block_size);
			brelse(bh);
			al += block_size;
		} while (++block < max_block);
		rl++;
	}
	if (initialized_size < size) {
initialize:
		memset(al_start + initialized_size, 0, size - initialized_size);
	}
done:
	up_read(&runlist->lock);
	return err;
do_final:
	if (al < al_end) {
		/*
		 * Partial block.
		 *
		 * Note: The attribute list can be smaller than its allocation
		 * by multiple clusters.  This has been encountered by at least
		 * two people running Windows XP, thus we cannot do any
		 * truncation sanity checking here. (AIA)
		 */
		memcpy(al, bh->b_data, al_end - al);
		brelse(bh);
		if (initialized_size < size)
			goto initialize;
		goto done;
	}
	brelse(bh);
	/* Real overflow! */
	ntfs_error(sb, "Attribute list buffer overflow. Read attribute list "
			"is truncated.");
err_out:
	err = -EIO;
	goto done;
}

/**
 * ntfs_external_attr_find - find an attribute in the attribute list of an inode
 * @type:	attribute type to find
 * @name:	attribute name to find (optional, i.e. NULL means don't care)
 * @name_len:	attribute name length (only needed if @name present)
 * @ic:		IGNORE_CASE or CASE_SENSITIVE (ignored if @name not present)
 * @lowest_vcn:	lowest vcn to find (optional, non-resident attributes only)
 * @val:	attribute value to find (optional, resident attributes only)
 * @val_len:	attribute value length
 * @ctx:	search context with mft record and attribute to search from
 *
 * You should not need to call this function directly.  Use ntfs_attr_lookup()
 * instead.
 *
 * Find an attribute by searching the attribute list for the corresponding
 * attribute list entry.  Having found the entry, map the mft record if the
 * attribute is in a different mft record/inode, ntfs_attr_find() the attribute
 * in there and return it.
 *
 * On first search @ctx->ntfs_ino must be the base mft record and @ctx must
 * have been obtained from a call to ntfs_attr_get_search_ctx().  On subsequent
 * calls @ctx->ntfs_ino can be any extent inode, too (@ctx->base_ntfs_ino is
 * then the base inode).
 *
 * After finishing with the attribute/mft record you need to call
 * ntfs_attr_put_search_ctx() to cleanup the search context (unmapping any
 * mapped inodes, etc).
 *
 * If the attribute is found, ntfs_external_attr_find() returns 0 and
 * @ctx->attr will point to the found attribute.  @ctx->mrec will point to the
 * mft record in which @ctx->attr is located and @ctx->al_entry will point to
 * the attribute list entry for the attribute.
 *
 * If the attribute is not found, ntfs_external_attr_find() returns -ENOENT and
 * @ctx->attr will point to the attribute in the base mft record before which
 * the attribute being searched for would need to be inserted if such an action
 * were to be desired.  @ctx->mrec will point to the mft record in which
 * @ctx->attr is located and @ctx->al_entry will point to the attribute list
 * entry of the attribute before which the attribute being searched for would
 * need to be inserted if such an action were to be desired.
 *
 * Thus to insert the not found attribute, one wants to add the attribute to
 * @ctx->mrec (the base mft record) and if there is not enough space, the
 * attribute should be placed in a newly allocated extent mft record.  The
 * attribute list entry for the inserted attribute should be inserted in the
 * attribute list attribute at @ctx->al_entry.
 *
 * On actual error, ntfs_external_attr_find() returns -EIO.  In this case
 * @ctx->attr is undefined and in particular do not rely on it not changing.
 */
static int ntfs_external_attr_find(const ATTR_TYPE type,
		const ntfschar *name, const u32 name_len,
		const IGNORE_CASE_BOOL ic, const VCN lowest_vcn,
		const u8 *val, const u32 val_len, ntfs_attr_search_ctx *ctx)
{
	ntfs_inode *base_ni, *ni;
	ntfs_volume *vol;
	ATTR_LIST_ENTRY *al_entry, *next_al_entry;
	u8 *al_start, *al_end;
	ATTR_RECORD *a;
	ntfschar *al_name;
	u32 al_name_len;
	int err = 0;
	static const char *es = " Unmount and run chkdsk.";

	ni = ctx->ntfs_ino;
	base_ni = ctx->base_ntfs_ino;
	ntfs_debug("Entering for inode 0x%lx, type 0x%x.", ni->mft_no, type);
	if (!base_ni) {
		/* First call happens with the base mft record. */
		base_ni = ctx->base_ntfs_ino = ctx->ntfs_ino;
		ctx->base_mrec = ctx->mrec;
	}
	if (ni == base_ni)
		ctx->base_attr = ctx->attr;
	if (type == AT_END)
		goto not_found;
	vol = base_ni->vol;
	al_start = base_ni->attr_list;
	al_end = al_start + base_ni->attr_list_size;
	if (!ctx->al_entry)
		ctx->al_entry = (ATTR_LIST_ENTRY*)al_start;
	/*
	 * Iterate over entries in attribute list starting at @ctx->al_entry,
	 * or the entry following that, if @ctx->is_first is 'true'.
	 */
	if (ctx->is_first) {
		al_entry = ctx->al_entry;
		ctx->is_first = false;
	} else
		al_entry = (ATTR_LIST_ENTRY*)((u8*)ctx->al_entry +
				le16_to_cpu(ctx->al_entry->length));
	for (;; al_entry = next_al_entry) {
		/* Out of bounds check. */
		if ((u8*)al_entry < base_ni->attr_list ||
				(u8*)al_entry > al_end)
			break;	/* Inode is corrupt. */
		ctx->al_entry = al_entry;
		/* Catch the end of the attribute list. */
		if ((u8*)al_entry == al_end)
			goto not_found;
		if (!al_entry->length)
			break;
		if ((u8*)al_entry + 6 > al_end || (u8*)al_entry +
				le16_to_cpu(al_entry->length) > al_end)
			break;
		next_al_entry = (ATTR_LIST_ENTRY*)((u8*)al_entry +
				le16_to_cpu(al_entry->length));
		if (le32_to_cpu(al_entry->type) > le32_to_cpu(type))
			goto not_found;
		if (type != al_entry->type)
			continue;
		/*
		 * If @name is present, compare the two names.  If @name is
		 * missing, assume we want an unnamed attribute.
		 */
		al_name_len = al_entry->name_length;
		al_name = (ntfschar*)((u8*)al_entry + al_entry->name_offset);
		if (!name) {
			if (al_name_len)
				goto not_found;
		} else if (!ntfs_are_names_equal(al_name, al_name_len, name,
				name_len, ic, vol->upcase, vol->upcase_len)) {
			register int rc;

			rc = ntfs_collate_names(name, name_len, al_name,
					al_name_len, 1, IGNORE_CASE,
					vol->upcase, vol->upcase_len);
			/*
			 * If @name collates before al_name, there is no
			 * matching attribute.
			 */
			if (rc == -1)
				goto not_found;
			/* If the strings are not equal, continue search. */
			if (rc)
				continue;
			/*
			 * FIXME: Reverse engineering showed 0, IGNORE_CASE but
			 * that is inconsistent with ntfs_attr_find().  The
			 * subsequent rc checks were also different.  Perhaps I
			 * made a mistake in one of the two.  Need to recheck
			 * which is correct or at least see what is going on...
			 * (AIA)
			 */
			rc = ntfs_collate_names(name, name_len, al_name,
					al_name_len, 1, CASE_SENSITIVE,
					vol->upcase, vol->upcase_len);
			if (rc == -1)
				goto not_found;
			if (rc)
				continue;
		}
		/*
		 * The names match or @name not present and attribute is
		 * unnamed.  Now check @lowest_vcn.  Continue search if the
		 * next attribute list entry still fits @lowest_vcn.  Otherwise
		 * we have reached the right one or the search has failed.
		 */
		if (lowest_vcn && (u8*)next_al_entry >= al_start	    &&
				(u8*)next_al_entry + 6 < al_end		    &&
				(u8*)next_al_entry + le16_to_cpu(
					next_al_entry->length) <= al_end    &&
				sle64_to_cpu(next_al_entry->lowest_vcn) <=
					lowest_vcn			    &&
				next_al_entry->type == al_entry->type	    &&
				next_al_entry->name_length == al_name_len   &&
				ntfs_are_names_equal((ntfschar*)((u8*)
					next_al_entry +
					next_al_entry->name_offset),
					next_al_entry->name_length,
					al_name, al_name_len, CASE_SENSITIVE,
					vol->upcase, vol->upcase_len))
			continue;
		if (MREF_LE(al_entry->mft_reference) == ni->mft_no) {
			if (MSEQNO_LE(al_entry->mft_reference) != ni->seq_no) {
				ntfs_error(vol->sb, "Found stale mft "
						"reference in attribute list "
						"of base inode 0x%lx.%s",
						base_ni->mft_no, es);
				err = -EIO;
				break;
			}
		} else { /* Mft references do not match. */
			/* If there is a mapped record unmap it first. */
			if (ni != base_ni)
				unmap_extent_mft_record(ni);
			/* Do we want the base record back? */
			if (MREF_LE(al_entry->mft_reference) ==
					base_ni->mft_no) {
				ni = ctx->ntfs_ino = base_ni;
				ctx->mrec = ctx->base_mrec;
			} else {
				/* We want an extent record. */
				ctx->mrec = map_extent_mft_record(base_ni,
						le64_to_cpu(
						al_entry->mft_reference), &ni);
				if (IS_ERR(ctx->mrec)) {
					ntfs_error(vol->sb, "Failed to map "
							"extent mft record "
							"0x%lx of base inode "
							"0x%lx.%s",
							MREF_LE(al_entry->
							mft_reference),
							base_ni->mft_no, es);
					err = PTR_ERR(ctx->mrec);
					if (err == -ENOENT)
						err = -EIO;
					/* Cause @ctx to be sanitized below. */
					ni = NULL;
					break;
				}
				ctx->ntfs_ino = ni;
			}
			ctx->attr = (ATTR_RECORD*)((u8*)ctx->mrec +
					le16_to_cpu(ctx->mrec->attrs_offset));
		}
		/*
		 * ctx->vfs_ino, ctx->mrec, and ctx->attr now point to the
		 * mft record containing the attribute represented by the
		 * current al_entry.
		 */
		/*
		 * We could call into ntfs_attr_find() to find the right
		 * attribute in this mft record but this would be less
		 * efficient and not quite accurate as ntfs_attr_find() ignores
		 * the attribute instance numbers for example which become
		 * important when one plays with attribute lists.  Also,
		 * because a proper match has been found in the attribute list
		 * entry above, the comparison can now be optimized.  So it is
		 * worth re-implementing a simplified ntfs_attr_find() here.
		 */
		a = ctx->attr;
		/*
		 * Use a manual loop so we can still use break and continue
		 * with the same meanings as above.
		 */
do_next_attr_loop:
		if ((u8*)a < (u8*)ctx->mrec || (u8*)a > (u8*)ctx->mrec +
				le32_to_cpu(ctx->mrec->bytes_allocated))
			break;
		if (a->type == AT_END)
			break;
		if (!a->length)
			break;
		if (al_entry->instance != a->instance)
			goto do_next_attr;
		/*
		 * If the type and/or the name are mismatched between the
		 * attribute list entry and the attribute record, there is
		 * corruption so we break and return error EIO.
		 */
		if (al_entry->type != a->type)
			break;
		if (!ntfs_are_names_equal((ntfschar*)((u8*)a +
				le16_to_cpu(a->name_offset)), a->name_length,
				al_name, al_name_len, CASE_SENSITIVE,
				vol->upcase, vol->upcase_len))
			break;
		ctx->attr = a;
		/*
		 * If no @val specified or @val specified and it matches, we
		 * have found it!
		 */
		if (!val || (!a->non_resident && le32_to_cpu(
				a->data.resident.value_length) == val_len &&
				!memcmp((u8*)a +
				le16_to_cpu(a->data.resident.value_offset),
				val, val_len))) {
			ntfs_debug("Done, found.");
			return 0;
		}
do_next_attr:
		/* Proceed to the next attribute in the current mft record. */
		a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length));
		goto do_next_attr_loop;
	}
	if (!err) {
		ntfs_error(vol->sb, "Base inode 0x%lx contains corrupt "
				"attribute list attribute.%s", base_ni->mft_no,
				es);
		err = -EIO;
	}
	if (ni != base_ni) {
		if (ni)
			unmap_extent_mft_record(ni);
		ctx->ntfs_ino = base_ni;
		ctx->mrec = ctx->base_mrec;
		ctx->attr = ctx->base_attr;
	}
	if (err != -ENOMEM)
		NVolSetErrors(vol);
	return err;
not_found:
	/*
	 * If we were looking for AT_END, we reset the search context @ctx and
	 * use ntfs_attr_find() to seek to the end of the base mft record.
	 */
	if (type == AT_END) {
		ntfs_attr_reinit_search_ctx(ctx);
		return ntfs_attr_find(AT_END, name, name_len, ic, val, val_len,
				ctx);
	}
	/*
	 * The attribute was not found.  Before we return, we want to ensure
	 * @ctx->mrec and @ctx->attr indicate the position at which the
	 * attribute should be inserted in the base mft record.  Since we also
	 * want to preserve @ctx->al_entry we cannot reinitialize the search
	 * context using ntfs_attr_reinit_search_ctx() as this would set
	 * @ctx->al_entry to NULL.  Thus we do the necessary bits manually (see
	 * ntfs_attr_init_search_ctx() below).  Note, we _only_ preserve
	 * @ctx->al_entry as the remaining fields (base_*) are identical to
	 * their non base_ counterparts and we cannot set @ctx->base_attr
	 * correctly yet as we do not know what @ctx->attr will be set to by
	 * the call to ntfs_attr_find() below.
	 */
	if (ni != base_ni)
		unmap_extent_mft_record(ni);
	ctx->mrec = ctx->base_mrec;
	ctx->attr = (ATTR_RECORD*)((u8*)ctx->mrec +
			le16_to_cpu(ctx->mrec->attrs_offset));
	ctx->is_first = true;
	ctx->ntfs_ino = base_ni;
	ctx->base_ntfs_ino = NULL;
	ctx->base_mrec = NULL;
	ctx->base_attr = NULL;
	/*
	 * In case there are multiple matches in the base mft record, need to
	 * keep enumerating until we get an attribute not found response (or
	 * another error), otherwise we would keep returning the same attribute
	 * over and over again and all programs using us for enumeration would
	 * lock up in a tight loop.
	 */
	do {
		err = ntfs_attr_find(type, name, name_len, ic, val, val_len,
				ctx);
	} while (!err);
	ntfs_debug("Done, not found.");
	return err;
}

/**
 * ntfs_attr_lookup - find an attribute in an ntfs inode
 * @type:	attribute type to find
 * @name:	attribute name to find (optional, i.e. NULL means don't care)
 * @name_len:	attribute name length (only needed if @name present)
 * @ic:		IGNORE_CASE or CASE_SENSITIVE (ignored if @name not present)
 * @lowest_vcn:	lowest vcn to find (optional, non-resident attributes only)
 * @val:	attribute value to find (optional, resident attributes only)
 * @val_len:	attribute value length
 * @ctx:	search context with mft record and attribute to search from
 *
 * Find an attribute in an ntfs inode.  On first search @ctx->ntfs_ino must
 * be the base mft record and @ctx must have been obtained from a call to
 * ntfs_attr_get_search_ctx().
 *
 * This function transparently handles attribute lists and @ctx is used to
 * continue searches where they were left off at.
 *
 * After finishing with the attribute/mft record you need to call
 * ntfs_attr_put_search_ctx() to cleanup the search context (unmapping any
 * mapped inodes, etc).
 *
 * Return 0 if the search was successful and -errno if not.
 *
 * When 0, @ctx->attr is the found attribute and it is in mft record
 * @ctx->mrec.  If an attribute list attribute is present, @ctx->al_entry is
 * the attribute list entry of the found attribute.
 *
 * When -ENOENT, @ctx->attr is the attribute which collates just after the
 * attribute being searched for, i.e. if one wants to add the attribute to the
 * mft record this is the correct place to insert it into.  If an attribute
 * list attribute is present, @ctx->al_entry is the attribute list entry which
 * collates just after the attribute list entry of the attribute being searched
 * for, i.e. if one wants to add the attribute to the mft record this is the
 * correct place to insert its attribute list entry into.
 *
 * When -errno != -ENOENT, an error occurred during the lookup.  @ctx->attr is
 * then undefined and in particular you should not rely on it not changing.
 */
int ntfs_attr_lookup(const ATTR_TYPE type, const ntfschar *name,
		const u32 name_len, const IGNORE_CASE_BOOL ic,
		const VCN lowest_vcn, const u8 *val, const u32 val_len,
		ntfs_attr_search_ctx *ctx)
{
	ntfs_inode *base_ni;

	ntfs_debug("Entering.");
	BUG_ON(IS_ERR(ctx->mrec));
	if (ctx->base_ntfs_ino)
		base_ni = ctx->base_ntfs_ino;
	else
		base_ni = ctx->ntfs_ino;
	/* Sanity check, just for debugging really. */
	BUG_ON(!base_ni);
	if (!NInoAttrList(base_ni) || type == AT_ATTRIBUTE_LIST)
		return ntfs_attr_find(type, name, name_len, ic, val, val_len,
				ctx);
	return ntfs_external_attr_find(type, name, name_len, ic, lowest_vcn,
			val, val_len, ctx);
}

/**
 * ntfs_attr_init_search_ctx - initialize an attribute search context
 * @ctx:	attribute search context to initialize
 * @ni:		ntfs inode with which to initialize the search context
 * @mrec:	mft record with which to initialize the search context
 *
 * Initialize the attribute search context @ctx with @ni and @mrec.
 */
static inline void ntfs_attr_init_search_ctx(ntfs_attr_search_ctx *ctx,
		ntfs_inode *ni, MFT_RECORD *mrec)
{
	*ctx = (ntfs_attr_search_ctx) {
		.mrec = mrec,
		/* Sanity checks are performed elsewhere. */
		.attr = (ATTR_RECORD*)((u8*)mrec +
				le16_to_cpu(mrec->attrs_offset)),
		.is_first = true,
		.ntfs_ino = ni,
	};
}

/**
 * ntfs_attr_reinit_search_ctx - reinitialize an attribute search context
 * @ctx:	attribute search context to reinitialize
 *
 * Reinitialize the attribute search context @ctx, unmapping an associated
 * extent mft record if present, and initialize the search context again.
 *
 * This is used when a search for a new attribute is being started to reset
 * the search context to the beginning.
 */
void ntfs_attr_reinit_search_ctx(ntfs_attr_search_ctx *ctx)
{
	if (likely(!ctx->base_ntfs_ino)) {
		/* No attribute list. */
		ctx->is_first = true;
		/* Sanity checks are performed elsewhere. */
		ctx->attr = (ATTR_RECORD*)((u8*)ctx->mrec +
				le16_to_cpu(ctx->mrec->attrs_offset));
		/*
		 * This needs resetting due to ntfs_external_attr_find() which
		 * can leave it set despite having zeroed ctx->base_ntfs_ino.
		 */
		ctx->al_entry = NULL;
		return;
	} /* Attribute list. */
	if (ctx->ntfs_ino != ctx->base_ntfs_ino)
		unmap_extent_mft_record(ctx->ntfs_ino);
	ntfs_attr_init_search_ctx(ctx, ctx->base_ntfs_ino, ctx->base_mrec);
	return;
}

/**
 * ntfs_attr_get_search_ctx - allocate/initialize a new attribute search context
 * @ni:		ntfs inode with which to initialize the search context
 * @mrec:	mft record with which to initialize the search context
 *
 * Allocate a new attribute search context, initialize it with @ni and @mrec,
 * and return it. Return NULL if allocation failed.
 */
ntfs_attr_search_ctx *ntfs_attr_get_search_ctx(ntfs_inode *ni, MFT_RECORD *mrec)
{
	ntfs_attr_search_ctx *ctx;

	ctx = kmem_cache_alloc(ntfs_attr_ctx_cache, GFP_NOFS);
	if (ctx)
		ntfs_attr_init_search_ctx(ctx, ni, mrec);
	return ctx;
}

/**
 * ntfs_attr_put_search_ctx - release an attribute search context
 * @ctx:	attribute search context to free
 *
 * Release the attribute search context @ctx, unmapping an associated extent
 * mft record if present.
 */
void ntfs_attr_put_search_ctx(ntfs_attr_search_ctx *ctx)
{
	if (ctx->base_ntfs_ino && ctx->ntfs_ino != ctx->base_ntfs_ino)
		unmap_extent_mft_record(ctx->ntfs_ino);
	kmem_cache_free(ntfs_attr_ctx_cache, ctx);
	return;
}

#ifdef NTFS_RW

/**
 * ntfs_attr_find_in_attrdef - find an attribute in the $AttrDef system file
 * @vol:	ntfs volume to which the attribute belongs
 * @type:	attribute type which to find
 *
 * Search for the attribute definition record corresponding to the attribute
 * @type in the $AttrDef system file.
 *
 * Return the attribute type definition record if found and NULL if not found.
 */
static ATTR_DEF *ntfs_attr_find_in_attrdef(const ntfs_volume *vol,
		const ATTR_TYPE type)
{
	ATTR_DEF *ad;

	BUG_ON(!vol->attrdef);
	BUG_ON(!type);
	for (ad = vol->attrdef; (u8*)ad - (u8*)vol->attrdef <
			vol->attrdef_size && ad->type; ++ad) {
		/* We have not found it yet, carry on searching. */
		if (likely(le32_to_cpu(ad->type) < le32_to_cpu(type)))
			continue;
		/* We found the attribute; return it. */
		if (likely(ad->type == type))
			return ad;
		/* We have gone too far already.  No point in continuing. */
		break;
	}
	/* Attribute not found. */
	ntfs_debug("Attribute type 0x%x not found in $AttrDef.",
			le32_to_cpu(type));
	return NULL;
}

/**
 * ntfs_attr_size_bounds_check - check a size of an attribute type for validity
 * @vol:	ntfs volume to which the attribute belongs
 * @type:	attribute type which to check
 * @size:	size which to check
 *
 * Check whether the @size in bytes is valid for an attribute of @type on the
 * ntfs volume @vol.  This information is obtained from $AttrDef system file.
 *
 * Return 0 if valid, -ERANGE if not valid, or -ENOENT if the attribute is not
 * listed in $AttrDef.
 */
int ntfs_attr_size_bounds_check(const ntfs_volume *vol, const ATTR_TYPE type,
		const s64 size)
{
	ATTR_DEF *ad;

	BUG_ON(size < 0);
	/*
	 * $ATTRIBUTE_LIST has a maximum size of 256kiB, but this is not
	 * listed in $AttrDef.
	 */
	if (unlikely(type == AT_ATTRIBUTE_LIST && size > 256 * 1024))
		return -ERANGE;
	/* Get the $AttrDef entry for the attribute @type. */
	ad = ntfs_attr_find_in_attrdef(vol, type);
	if (unlikely(!ad))
		return -ENOENT;
	/* Do the bounds check. */
	if (((sle64_to_cpu(ad->min_size) > 0) &&
			size < sle64_to_cpu(ad->min_size)) ||
			((sle64_to_cpu(ad->max_size) > 0) && size >
			sle64_to_cpu(ad->max_size)))
		return -ERANGE;
	return 0;
}

/**
 * ntfs_attr_can_be_non_resident - check if an attribute can be non-resident
 * @vol:	ntfs volume to which the attribute belongs
 * @type:	attribute type which to check
 *
 * Check whether the attribute of @type on the ntfs volume @vol is allowed to
 * be non-resident.  This information is obtained from $AttrDef system file.
 *
 * Return 0 if the attribute is allowed to be non-resident, -EPERM if not, and
 * -ENOENT if the attribute is not listed in $AttrDef.
 */
int ntfs_attr_can_be_non_resident(const ntfs_volume *vol, const ATTR_TYPE type)
{
	ATTR_DEF *ad;

	/* Find the attribute definition record in $AttrDef. */
	ad = ntfs_attr_find_in_attrdef(vol, type);
	if (unlikely(!ad))
		return -ENOENT;
	/* Check the flags and return the result. */
	if (ad->flags & ATTR_DEF_RESIDENT)
		return -EPERM;
	return 0;
}

/**
 * ntfs_attr_can_be_resident - check if an attribute can be resident
 * @vol:	ntfs volume to which the attribute belongs
 * @type:	attribute type which to check
 *
 * Check whether the attribute of @type on the ntfs volume @vol is allowed to
 * be resident.  This information is derived from our ntfs knowledge and may
 * not be completely accurate, especially when user defined attributes are
 * present.  Basically we allow everything to be resident except for index
 * allocation and $EA attributes.
 *
 * Return 0 if the attribute is allowed to be non-resident and -EPERM if not.
 *
 * Warning: In the system file $MFT the attribute $Bitmap must be non-resident
 *	    otherwise windows will not boot (blue screen of death)!  We cannot
 *	    check for this here as we do not know which inode's $Bitmap is
 *	    being asked about so the caller needs to special case this.
 */
int ntfs_attr_can_be_resident(const ntfs_volume *vol, const ATTR_TYPE type)
{
	if (type == AT_INDEX_ALLOCATION)
		return -EPERM;
	return 0;
}

/**
 * ntfs_attr_record_resize - resize an attribute record
 * @m:		mft record containing attribute record
 * @a:		attribute record to resize
 * @new_size:	new size in bytes to which to resize the attribute record @a
 *
 * Resize the attribute record @a, i.e. the resident part of the attribute, in
 * the mft record @m to @new_size bytes.
 *
 * Return 0 on success and -errno on error.  The following error codes are
 * defined:
 *	-ENOSPC	- Not enough space in the mft record @m to perform the resize.
 *
 * Note: On error, no modifications have been performed whatsoever.
 *
 * Warning: If you make a record smaller without having copied all the data you
 *	    are interested in the data may be overwritten.
 */
int ntfs_attr_record_resize(MFT_RECORD *m, ATTR_RECORD *a, u32 new_size)
{
	ntfs_debug("Entering for new_size %u.", new_size);
	/* Align to 8 bytes if it is not already done. */
	if (new_size & 7)
		new_size = (new_size + 7) & ~7;
	/* If the actual attribute length has changed, move things around. */
	if (new_size != le32_to_cpu(a->length)) {
		u32 new_muse = le32_to_cpu(m->bytes_in_use) -
				le32_to_cpu(a->length) + new_size;
		/* Not enough space in this mft record. */
		if (new_muse > le32_to_cpu(m->bytes_allocated))
			return -ENOSPC;
		/* Move attributes following @a to their new location. */
		memmove((u8*)a + new_size, (u8*)a + le32_to_cpu(a->length),
				le32_to_cpu(m->bytes_in_use) - ((u8*)a -
				(u8*)m) - le32_to_cpu(a->length));
		/* Adjust @m to reflect the change in used space. */
		m->bytes_in_use = cpu_to_le32(new_muse);
		/* Adjust @a to reflect the new size. */
		if (new_size >= offsetof(ATTR_REC, length) + sizeof(a->length))
			a->length = cpu_to_le32(new_size);
	}
	return 0;
}

/**
 * ntfs_resident_attr_value_resize - resize the value of a resident attribute
 * @m:		mft record containing attribute record
 * @a:		attribute record whose value to resize
 * @new_size:	new size in bytes to which to resize the attribute value of @a
 *
 * Resize the value of the attribute @a in the mft record @m to @new_size bytes.
 * If the value is made bigger, the newly allocated space is cleared.
 *
 * Return 0 on success and -errno on error.  The following error codes are
 * defined:
 *	-ENOSPC	- Not enough space in the mft record @m to perform the resize.
 *
 * Note: On error, no modifications have been performed whatsoever.
 *
 * Warning: If you make a record smaller without having copied all the data you
 *	    are interested in the data may be overwritten.
 */
int ntfs_resident_attr_value_resize(MFT_RECORD *m, ATTR_RECORD *a,
		const u32 new_size)
{
	u32 old_size;

	/* Resize the resident part of the attribute record. */
	if (ntfs_attr_record_resize(m, a,
			le16_to_cpu(a->data.resident.value_offset) + new_size))
		return -ENOSPC;
	/*
	 * The resize succeeded!  If we made the attribute value bigger, clear
	 * the area between the old size and @new_size.
	 */
	old_size = le32_to_cpu(a->data.resident.value_length);
	if (new_size > old_size)
		memset((u8*)a + le16_to_cpu(a->data.resident.value_offset) +
				old_size, 0, new_size - old_size);
	/* Finally update the length of the attribute value. */
	a->data.resident.value_length = cpu_to_le32(new_size);
	return 0;
}

/**
 * ntfs_attr_make_non_resident - convert a resident to a non-resident attribute
 * @ni:		ntfs inode describing the attribute to convert
 * @data_size:	size of the resident data to copy to the non-resident attribute
 *
 * Convert the resident ntfs attribute described by the ntfs inode @ni to a
 * non-resident one.
 *
 * @data_size must be equal to the attribute value size.  This is needed since
 * we need to know the size before we can map the mft record and our callers
 * always know it.  The reason we cannot simply read the size from the vfs
 * inode i_size is that this is not necessarily uptodate.  This happens when
 * ntfs_attr_make_non_resident() is called in the ->truncate call path(s).
 *
 * Return 0 on success and -errno on error.  The following error return codes
 * are defined:
 *	-EPERM	- The attribute is not allowed to be non-resident.
 *	-ENOMEM	- Not enough memory.
 *	-ENOSPC	- Not enough disk space.
 *	-EINVAL	- Attribute not defined on the volume.
 *	-EIO	- I/o error or other error.
 * Note that -ENOSPC is also returned in the case that there is not enough
 * space in the mft record to do the conversion.  This can happen when the mft
 * record is already very full.  The caller is responsible for trying to make
 * space in the mft record and trying again.  FIXME: Do we need a separate
 * error return code for this kind of -ENOSPC or is it always worth trying
 * again in case the attribute may then fit in a resident state so no need to
 * make it non-resident at all?  Ho-hum...  (AIA)
 *
 * NOTE to self: No changes in the attribute list are required to move from
 *		 a resident to a non-resident attribute.
 *
 * Locking: - The caller must hold i_mutex on the inode.
 */
int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size)
{
	s64 new_size;
	struct inode *vi = VFS_I(ni);
	ntfs_volume *vol = ni->vol;
	ntfs_inode *base_ni;
	MFT_RECORD *m;
	ATTR_RECORD *a;
	ntfs_attr_search_ctx *ctx;
	struct page *page;
	runlist_element *rl;
	u8 *kaddr;
	unsigned long flags;
	int mp_size, mp_ofs, name_ofs, arec_size, err, err2;
	u32 attr_size;
	u8 old_res_attr_flags;

	/* Check that the attribute is allowed to be non-resident. */
	err = ntfs_attr_can_be_non_resident(vol, ni->type);
	if (unlikely(err)) {
		if (err == -EPERM)
			ntfs_debug("Attribute is not allowed to be "
					"non-resident.");
		else
			ntfs_debug("Attribute not defined on the NTFS "
					"volume!");
		return err;
	}
	/*
	 * FIXME: Compressed and encrypted attributes are not supported when
	 * writing and we should never have gotten here for them.
	 */
	BUG_ON(NInoCompressed(ni));
	BUG_ON(NInoEncrypted(ni));
	/*
	 * The size needs to be aligned to a cluster boundary for allocation
	 * purposes.
	 */
	new_size = (data_size + vol->cluster_size - 1) &
			~(vol->cluster_size - 1);
	if (new_size > 0) {
		/*
		 * Will need the page later and since the page lock nests
		 * outside all ntfs locks, we need to get the page now.
		 */
		page = find_or_create_page(vi->i_mapping, 0,
				mapping_gfp_mask(vi->i_mapping));
		if (unlikely(!page))
			return -ENOMEM;
		/* Start by allocating clusters to hold the attribute value. */
		rl = ntfs_cluster_alloc(vol, 0, new_size >>
				vol->cluster_size_bits, -1, DATA_ZONE, true);
		if (IS_ERR(rl)) {
			err = PTR_ERR(rl);
			ntfs_debug("Failed to allocate cluster%s, error code "
					"%i.", (new_size >>
					vol->cluster_size_bits) > 1 ? "s" : "",
					err);
			goto page_err_out;
		}
	} else {
		rl = NULL;
		page = NULL;
	}
	/* Determine the size of the mapping pairs array. */
	mp_size = ntfs_get_size_for_mapping_pairs(vol, rl, 0, -1);
	if (unlikely(mp_size < 0)) {
		err = mp_size;
		ntfs_debug("Failed to get size for mapping pairs array, error "
				"code %i.", err);
		goto rl_err_out;
	}
	down_write(&ni->runlist.lock);
	if (!NInoAttr(ni))
		base_ni = ni;
	else
		base_ni = ni->ext.base_ntfs_ino;
	m = map_mft_record(base_ni);
	if (IS_ERR(m)) {
		err = PTR_ERR(m);
		m = NULL;
		ctx = NULL;
		goto err_out;
	}
	ctx = ntfs_attr_get_search_ctx(base_ni, m);
	if (unlikely(!ctx)) {
		err = -ENOMEM;
		goto err_out;
	}
	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
			CASE_SENSITIVE, 0, NULL, 0, ctx);
	if (unlikely(err)) {
		if (err == -ENOENT)
			err = -EIO;
		goto err_out;
	}
	m = ctx->mrec;
	a = ctx->attr;
	BUG_ON(NInoNonResident(ni));
	BUG_ON(a->non_resident);
	/*
	 * Calculate new offsets for the name and the mapping pairs array.
	 */
	if (NInoSparse(ni) || NInoCompressed(ni))
		name_ofs = (offsetof(ATTR_REC,
				data.non_resident.compressed_size) +
				sizeof(a->data.non_resident.compressed_size) +
				7) & ~7;
	else
		name_ofs = (offsetof(ATTR_REC,
				data.non_resident.compressed_size) + 7) & ~7;
	mp_ofs = (name_ofs + a->name_length * sizeof(ntfschar) + 7) & ~7;
	/*
	 * Determine the size of the resident part of the now non-resident
	 * attribute record.
	 */
	arec_size = (mp_ofs + mp_size + 7) & ~7;
	/*
	 * If the page is not uptodate bring it uptodate by copying from the
	 * attribute value.
	 */
	attr_size = le32_to_cpu(a->data.resident.value_length);
	BUG_ON(attr_size != data_size);
	if (page && !PageUptodate(page)) {
		kaddr = kmap_atomic(page, KM_USER0);
		memcpy(kaddr, (u8*)a +
				le16_to_cpu(a->data.resident.value_offset),
				attr_size);
		memset(kaddr + attr_size, 0, PAGE_CACHE_SIZE - attr_size);
		kunmap_atomic(kaddr, KM_USER0);
		flush_dcache_page(page);
		SetPageUptodate(page);
	}
	/* Backup the attribute flag. */
	old_res_attr_flags = a->data.resident.flags;
	/* Resize the resident part of the attribute record. */
	err = ntfs_attr_record_resize(m, a, arec_size);
	if (unlikely(err))
		goto err_out;
	/*
	 * Convert the resident part of the attribute record to describe a
	 * non-resident attribute.
	 */
	a->non_resident = 1;
	/* Move the attribute name if it exists and update the offset. */
	if (a->name_length)
		memmove((u8*)a + name_ofs, (u8*)a + le16_to_cpu(a->name_offset),
				a->name_length * sizeof(ntfschar));
	a->name_offset = cpu_to_le16(name_ofs);
	/* Setup the fields specific to non-resident attributes. */
	a->data.non_resident.lowest_vcn = 0;
	a->data.non_resident.highest_vcn = cpu_to_sle64((new_size - 1) >>
			vol->cluster_size_bits);
	a->data.non_resident.mapping_pairs_offset = cpu_to_le16(mp_ofs);
	memset(&a->data.non_resident.reserved, 0,
			sizeof(a->data.non_resident.reserved));
	a->data.non_resident.allocated_size = cpu_to_sle64(new_size);
	a->data.non_resident.data_size =
			a->data.non_resident.initialized_size =
			cpu_to_sle64(attr_size);
	if (NInoSparse(ni) || NInoCompressed(ni)) {
		a->data.non_resident.compression_unit = 0;
		if (NInoCompressed(ni) || vol->major_ver < 3)
			a->data.non_resident.compression_unit = 4;
		a->data.non_resident.compressed_size =
				a->data.non_resident.allocated_size;
	} else
		a->data.non_resident.compression_unit = 0;
	/* Generate the mapping pairs array into the attribute record. */
	err = ntfs_mapping_pairs_build(vol, (u8*)a + mp_ofs,
			arec_size - mp_ofs, rl, 0, -1, NULL);
	if (unlikely(err)) {
		ntfs_debug("Failed to build mapping pairs, error code %i.",
				err);
		goto undo_err_out;
	}
	/* Setup the in-memory attribute structure to be non-resident. */
	ni->runlist.rl = rl;
	write_lock_irqsave(&ni->size_lock, flags);
	ni->allocated_size = new_size;
	if (NInoSparse(ni) || NInoCompressed(ni)) {
		ni->itype.compressed.size = ni->allocated_size;
		if (a->data.non_resident.compression_unit) {
			ni->itype.compressed.block_size = 1U << (a->data.
					non_resident.compression_unit +
					vol->cluster_size_bits);
			ni->itype.compressed.block_size_bits =
					ffs(ni->itype.compressed.block_size) -
					1;
			ni->itype.compressed.block_clusters = 1U <<
					a->data.non_resident.compression_unit;
		} else {
			ni->itype.compressed.block_size = 0;
			ni->itype.compressed.block_size_bits = 0;
			ni->itype.compressed.block_clusters = 0;
		}
		vi->i_blocks = ni->itype.compressed.size >> 9;
	} else
		vi->i_blocks = ni->allocated_size >> 9;
	write_unlock_irqrestore(&ni->size_lock, flags);
	/*
	 * This needs to be last since the address space operations ->readpage
	 * and ->writepage can run concurrently with us as they are not
	 * serialized on i_mutex.  Note, we are not allowed to fail once we flip
	 * this switch, which is another reason to do this last.
	 */
	NInoSetNonResident(ni);
	/* Mark the mft record dirty, so it gets written back. */
	flush_dcache_mft_record_page(ctx->ntfs_ino);
	mark_mft_record_dirty(ctx->ntfs_ino);
	ntfs_attr_put_search_ctx(ctx);
	unmap_mft_record(base_ni);
	up_write(&ni->runlist.lock);
	if (page) {
		set_page_dirty(page);
		unlock_page(page);
		mark_page_accessed(page);
		page_cache_release(page);
	}
	ntfs_debug("Done.");
	return 0;
undo_err_out:
	/* Convert the attribute back into a resident attribute. */
	a->non_resident = 0;
	/* Move the attribute name if it exists and update the offset. */
	name_ofs = (offsetof(ATTR_RECORD, data.resident.reserved) +
			sizeof(a->data.resident.reserved) + 7) & ~7;
	if (a->name_length)
		memmove((u8*)a + name_ofs, (u8*)a + le16_to_cpu(a->name_offset),
				a->name_length * sizeof(ntfschar));
	mp_ofs = (name_ofs + a->name_length * sizeof(ntfschar) + 7) & ~7;
	a->name_offset = cpu_to_le16(name_ofs);
	arec_size = (mp_ofs + attr_size + 7) & ~7;
	/* Resize the resident part of the attribute record. */
	err2 = ntfs_attr_record_resize(m, a, arec_size);
	if (unlikely(err2)) {
		/*
		 * This cannot happen (well if memory corruption is at work it
		 * could happen in theory), but deal with it as well as we can.
		 * If the old size is too small, truncate the attribute,
		 * otherwise simply give it a larger allocated size.
		 * FIXME: Should check whether chkdsk complains when the
		 * allocated size is much bigger than the resident value size.
		 */
		arec_size = le32_to_cpu(a->length);
		if ((mp_ofs + attr_size) > arec_size) {
			err2 = attr_size;
			attr_size = arec_size - mp_ofs;
			ntfs_error(vol->sb, "Failed to undo partial resident "
					"to non-resident attribute "
					"conversion.  Truncating inode 0x%lx, "
					"attribute type 0x%x from %i bytes to "
					"%i bytes to maintain metadata "
					"consistency.  THIS MEANS YOU ARE "
					"LOSING %i BYTES DATA FROM THIS %s.",
					vi->i_ino,
					(unsigned)le32_to_cpu(ni->type),
					err2, attr_size, err2 - attr_size,
					((ni->type == AT_DATA) &&
					!ni->name_len) ? "FILE": "ATTRIBUTE");
			write_lock_irqsave(&ni->size_lock, flags);
			ni->initialized_size = attr_size;
			i_size_write(vi, attr_size);
			write_unlock_irqrestore(&ni->size_lock, flags);
		}
	}
	/* Setup the fields specific to resident attributes. */
	a->data.resident.value_length = cpu_to_le32(attr_size);
	a->data.resident.value_offset = cpu_to_le16(mp_ofs);
	a->data.resident.flags = old_res_attr_flags;
	memset(&a->data.resident.reserved, 0,
			sizeof(a->data.resident.reserved));
	/* Copy the data from the page back to the attribute value. */
	if (page) {
		kaddr = kmap_atomic(page, KM_USER0);
		memcpy((u8*)a + mp_ofs, kaddr, attr_size);
		kunmap_atomic(kaddr, KM_USER0);
	}
	/* Setup the allocated size in the ntfs inode in case it changed. */
	write_lock_irqsave(&ni->size_lock, flags);
	ni->allocated_size = arec_size - mp_ofs;
	write_unlock_irqrestore(&ni->size_lock, flags);
	/* Mark the mft record dirty, so it gets written back. */
	flush_dcache_mft_record_page(ctx->ntfs_ino);
	mark_mft_record_dirty(ctx->ntfs_ino);
err_out:
	if (ctx)
		ntfs_attr_put_search_ctx(ctx);
	if (m)
		unmap_mft_record(base_ni);
	ni->runlist.rl = NULL;
	up_write(&ni->runlist.lock);
rl_err_out:
	if (rl) {
		if (ntfs_cluster_free_from_rl(vol, rl) < 0) {
			ntfs_error(vol->sb, "Failed to release allocated "
					"cluster(s) in error code path.  Run "
					"chkdsk to recover the lost "
					"cluster(s).");
			NVolSetErrors(vol);
		}
		ntfs_free(rl);
page_err_out:
		unlock_page(page);
		page_cache_release(page);
	}
	if (err == -EINVAL)
		err = -EIO;
	return err;
}

/**
 * ntfs_attr_extend_allocation - extend the allocated space of an attribute
 * @ni:			ntfs inode of the attribute whose allocation to extend
 * @new_alloc_size:	new size in bytes to which to extend the allocation to
 * @new_data_size:	new size in bytes to which to extend the data to
 * @data_start:		beginning of region which is required to be non-sparse
 *
 * Extend the allocated space of an attribute described by the ntfs inode @ni
 * to @new_alloc_size bytes.  If @data_start is -1, the whole extension may be
 * implemented as a hole in the file (as long as both the volume and the ntfs
 * inode @ni have sparse support enabled).  If @data_start is >= 0, then the
 * region between the old allocated size and @data_start - 1 may be made sparse
 * but the regions between @data_start and @new_alloc_size must be backed by
 * actual clusters.
 *
 * If @new_data_size is -1, it is ignored.  If it is >= 0, then the data size
 * of the attribute is extended to @new_data_size.  Note that the i_size of the
 * vfs inode is not updated.  Only the data size in the base attribute record
 * is updated.  The caller has to update i_size separately if this is required.
 * WARNING: It is a BUG() for @new_data_size to be smaller than the old data
 * size as well as for @new_data_size to be greater than @new_alloc_size.
 *
 * For resident attributes this involves resizing the attribute record and if
 * necessary moving it and/or other attributes into extent mft records and/or
 * converting the attribute to a non-resident attribute which in turn involves
 * extending the allocation of a non-resident attribute as described below.
 *
 * For non-resident attributes this involves allocating clusters in the data
 * zone on the volume (except for regions that are being made sparse) and
 * extending the run list to describe the allocated clusters as well as
 * updating the mapping pairs array of the attribute.  This in turn involves
 * resizing the attribute record and if necessary moving it and/or other
 * attributes into extent mft records and/or splitting the attribute record
 * into multiple extent attribute records.
 *
 * Also, the attribute list attribute is updated if present and in some of the
 * above cases (the ones where extent mft records/attributes come into play),
 * an attribute list attribute is created if not already present.
 *
 * Return the new allocated size on success and -errno on error.  In the case
 * that an error is encountered but a partial extension at least up to
 * @data_start (if present) is possible, the allocation is partially extended
 * and this is returned.  This means the caller must check the returned size to
 * determine if the extension was partial.  If @data_start is -1 then partial
 * allocations are not performed.
 *
 * WARNING: Do not call ntfs_attr_extend_allocation() for $MFT/$DATA.
 *
 * Locking: This function takes the runlist lock of @ni for writing as well as
 * locking the mft record of the base ntfs inode.  These locks are maintained
 * throughout execution of the function.  These locks are required so that the
 * attribute can be resized safely and so that it can for example be converted
 * from resident to non-resident safely.
 *
 * TODO: At present attribute list attribute handling is not implemented.
 *
 * TODO: At present it is not safe to call this function for anything other
 * than the $DATA attribute(s) of an uncompressed and unencrypted file.
 */
s64 ntfs_attr_extend_allocation(ntfs_inode *ni, s64 new_alloc_size,
		const s64 new_data_size, const s64 data_start)
{
	VCN vcn;
	s64 ll, allocated_size, start = data_start;
	struct inode *vi = VFS_I(ni);
	ntfs_volume *vol = ni->vol;
	ntfs_inode *base_ni;
	MFT_RECORD *m;
	ATTR_RECORD *a;
	ntfs_attr_search_ctx *ctx;
	runlist_element *rl, *rl2;
	unsigned long flags;
	int err, mp_size;
	u32 attr_len = 0; /* Silence stupid gcc warning. */
	bool mp_rebuilt;

#ifdef DEBUG
	read_lock_irqsave(&ni->size_lock, flags);
	allocated_size = ni->allocated_size;
	read_unlock_irqrestore(&ni->size_lock, flags);
	ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, "
			"old_allocated_size 0x%llx, "
			"new_allocated_size 0x%llx, new_data_size 0x%llx, "
			"data_start 0x%llx.", vi->i_ino,
			(unsigned)le32_to_cpu(ni->type),
			(unsigned long long)allocated_size,
			(unsigned long long)new_alloc_size,
			(unsigned long long)new_data_size,
			(unsigned long long)start);
#endif
retry_extend:
	/*
	 * For non-resident attributes, @start and @new_size need to be aligned
	 * to cluster boundaries for allocation purposes.
	 */
	if (NInoNonResident(ni)) {
		if (start > 0)
			start &= ~(s64)vol->cluster_size_mask;
		new_alloc_size = (new_alloc_size + vol->cluster_size - 1) &
				~(s64)vol->cluster_size_mask;
	}
	BUG_ON(new_data_size >= 0 && new_data_size > new_alloc_size);
	/* Check if new size is allowed in $AttrDef. */
	err = ntfs_attr_size_bounds_check(vol, ni->type, new_alloc_size);
	if (unlikely(err)) {
		/* Only emit errors when the write will fail completely. */
		read_lock_irqsave(&ni->size_lock, flags);
		allocated_size = ni->allocated_size;
		read_unlock_irqrestore(&ni->size_lock, flags);
		if (start < 0 || start >= allocated_size) {
			if (err == -ERANGE) {
				ntfs_error(vol->sb, "Cannot extend allocation "
						"of inode 0x%lx, attribute "
						"type 0x%x, because the new "
						"allocation would exceed the "
						"maximum allowed size for "
						"this attribute type.",
						vi->i_ino, (unsigned)
						le32_to_cpu(ni->type));
			} else {
				ntfs_error(vol->sb, "Cannot extend allocation "
						"of inode 0x%lx, attribute "
						"type 0x%x, because this "
						"attribute type is not "
						"defined on the NTFS volume.  "
						"Possible corruption!  You "
						"should run chkdsk!",
						vi->i_ino, (unsigned)
						le32_to_cpu(ni->type));
			}
		}
		/* Translate error code to be POSIX conformant for write(2). */
		if (err == -ERANGE)
			err = -EFBIG;
		else
			err = -EIO;
		return err;
	}
	if (!NInoAttr(ni))
		base_ni = ni;
	else
		base_ni = ni->ext.base_ntfs_ino;
	/*
	 * We will be modifying both the runlist (if non-resident) and the mft
	 * record so lock them both down.
	 */
	down_write(&ni->runlist.lock);
	m = map_mft_record(base_ni);
	if (IS_ERR(m)) {
		err = PTR_ERR(m);
		m = NULL;
		ctx = NULL;
		goto err_out;
	}
	ctx = ntfs_attr_get_search_ctx(base_ni, m);
	if (unlikely(!ctx)) {
		err = -ENOMEM;
		goto err_out;
	}
	read_lock_irqsave(&ni->size_lock, flags);
	allocated_size = ni->allocated_size;
	read_unlock_irqrestore(&ni->size_lock, flags);
	/*
	 * If non-resident, seek to the last extent.  If resident, there is
	 * only one extent, so seek to that.
	 */
	vcn = NInoNonResident(ni) ? allocated_size >> vol->cluster_size_bits :
			0;
	/*
	 * Abort if someone did the work whilst we waited for the locks.  If we
	 * just converted the attribute from resident to non-resident it is
	 * likely that exactly this has happened already.  We cannot quite
	 * abort if we need to update the data size.
	 */
	if (unlikely(new_alloc_size <= allocated_size)) {
		ntfs_debug("Allocated size already exceeds requested size.");
		new_alloc_size = allocated_size;
		if (new_data_size < 0)
			goto done;
		/*
		 * We want the first attribute extent so that we can update the
		 * data size.
		 */
		vcn = 0;
	}
	err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
			CASE_SENSITIVE, vcn, NULL, 0, ctx);
	if (unlikely(err)) {
		if (err == -ENOENT)
			err = -EIO;
		goto err_out;
	}
	m = ctx->mrec;
	a = ctx->attr;
	/* Use goto to reduce indentation. */
	if (a->non_resident)
		goto do_non_resident_extend;
	BUG_ON(NInoNonResident(ni));
	/* The total length of the attribute value. */
	attr_len = le32_to_cpu(a->data.resident.value_length);
	/*
	 * Extend the attribute record to be able to store the new attribute
	 * size.  ntfs_attr_record_resize() will not do anything if the size is
	 * not changing.
	 */
	if (new_alloc_size < vol->mft_record_size &&
			!ntfs_attr_record_resize(m, a,
			le16_to_cpu(a->data.resident.value_offset) +
			new_alloc_size)) {
		/* The resize succeeded! */
		write_lock_irqsave(&ni->size_lock, flags);
		ni->allocated_size = le32_to_cpu(a->length) -
				le16_to_cpu(a->data.resident.value_offset);
		write_unlock_irqrestore(&ni->size_lock, flags);
		if (new_data_size >= 0) {
			BUG_ON(new_data_size < attr_len);
			a->data.resident.value_length =
					cpu_to_le32((u32)new_data_size);
		}
		goto flush_done;
	}
	/*
	 * We have to drop all the locks so we can call
	 * ntfs_attr_make_non_resident().  This could be optimised by try-
	 * locking the first page cache page and only if that fails dropping
	 * the locks, locking the page, and redoing all the locking and
	 * lookups.  While this would be a huge optimisation, it is not worth
	 * it as this is definitely a slow code path.
	 */
	ntfs_attr_put_search_ctx(ctx);
	unmap_mft_record(base_ni);
	up_write(&ni->runlist.lock);
	/*
	 * Not enough space in the mft record, try to make the attribute
	 * non-resident and if successful restart the extension process.
	 */
	err = ntfs_attr_make_non_resident(ni, attr_len);
	if (likely(!err))
		goto retry_extend;
	/*
	 * Could not make non-resident.  If this is due to this not being
	 * permitted for this attribute type or there not being enough space,
	 * try to make other attributes non-resident.  Otherwise fail.
	 */
	if (unlikely(err != -EPERM && err != -ENOSPC)) {
		/* Only emit errors when the write will fail completely. */
		read_lock_irqsave(&ni->size_lock, flags);
		allocated_size = ni->allocated_size;
		read_unlock_irqrestore(&ni->size_lock, flags);
		if (start < 0 || start >= allocated_size)
			ntfs_error(vol->sb, "Cannot extend allocation of "
					"inode 0x%lx, attribute type 0x%x, "
					"because the conversion from resident "
					"to non-resident attribute failed "
					"with error code %i.", vi->i_ino,
					(unsigned)le32_to_cpu(ni->type), err);
		if (err != -ENOMEM)
			err = -EIO;
		goto conv_err_out;
	}
	/* TODO: Not implemented from here, abort. */
	read_lock_irqsave(&ni->size_lock, flags);
	allocated_size = ni->allocated_size;
	read_unlock_irqrestore(&ni->size_lock, flags);
	if (start < 0 || start >= allocated_size) {
		if (err == -ENOSPC)
			ntfs_error(vol->sb, "Not enough space in the mft "
					"record/on disk for the non-resident "
					"attribute value.  This case is not "
					"implemented yet.");
		else /* if (err == -EPERM) */
			ntfs_error(vol->sb, "This attribute type may not be "
					"non-resident.  This case is not "
					"implemented yet.");
	}
	err = -EOPNOTSUPP;
	goto conv_err_out;
#if 0
	// TODO: Attempt to make other attributes non-resident.
	if (!err)
		goto do_resident_extend;
	/*
	 * Both the attribute list attribute and the standard information
	 * attribute must remain in the base inode.  Thus, if this is one of
	 * these attributes, we have to try to move other attributes out into
	 * extent mft records instead.
	 */
	if (ni->type == AT_ATTRIBUTE_LIST ||
			ni->type == AT_STANDARD_INFORMATION) {
		// TODO: Attempt to move other attributes into extent mft
		// records.
		err = -EOPNOTSUPP;
		if (!err)
			goto do_resident_extend;
		goto err_out;
	}
	// TODO: Attempt to move this attribute to an extent mft record, but
	// only if it is not already the only attribute in an mft record in
	// which case there would be nothing to gain.
	err = -EOPNOTSUPP;
	if (!err)
		goto do_resident_extend;
	/* There is nothing we can do to make enough space. )-: */
	goto err_out;
#endif
do_non_resident_extend:
	BUG_ON(!NInoNonResident(ni));
	if (new_alloc_size == allocated_size) {
		BUG_ON(vcn);
		goto alloc_done;
	}
	/*
	 * If the data starts after the end of the old allocation, this is a
	 * $DATA attribute and sparse attributes are enabled on the volume and
	 * for this inode, then create a sparse region between the old
	 * allocated size and the start of the data.  Otherwise simply proceed
	 * with filling the whole space between the old allocated size and the
	 * new allocated size with clusters.
	 */
	if ((start >= 0 && start <= allocated_size) || ni->type != AT_DATA ||
			!NVolSparseEnabled(vol) || NInoSparseDisabled(ni))
		goto skip_sparse;
	// TODO: This is not implemented yet.  We just fill in with real
	// clusters for now...
	ntfs_debug("Inserting holes is not-implemented yet.  Falling back to "
			"allocating real clusters instead.");
skip_sparse:
	rl = ni->runlist.rl;
	if (likely(rl)) {
		/* Seek to the end of the runlist. */
		while (rl->length)
			rl++;
	}
	/* If this attribute extent is not mapped, map it now. */
	if (unlikely(!rl || rl->lcn == LCN_RL_NOT_MAPPED ||
			(rl->lcn == LCN_ENOENT && rl > ni->runlist.rl &&
			(rl-1)->lcn == LCN_RL_NOT_MAPPED))) {
		if (!rl && !allocated_size)
			goto first_alloc;
		rl = ntfs_mapping_pairs_decompress(vol, a, ni->runlist.rl);
		if (IS_ERR(rl)) {
			err = PTR_ERR(rl);
			if (start < 0 || start >= allocated_size)
				ntfs_error(vol->sb, "Cannot extend allocation "
						"of inode 0x%lx, attribute "
						"type 0x%x, because the "
						"mapping of a runlist "
						"fragment failed with error "
						"code %i.", vi->i_ino,
						(unsigned)le32_to_cpu(ni->type),
						err);
			if (err != -ENOMEM)
				err = -EIO;
			goto err_out;
		}
		ni->runlist.rl = rl;
		/* Seek to the end of the runlist. */
		while (rl->length)
			rl++;
	}
	/*
	 * We now know the runlist of the last extent is mapped and @rl is at
	 * the end of the runlist.  We want to begin allocating clusters
	 * starting at the last allocated cluster to reduce fragmentation.  If
	 * there are no valid LCNs in the attribute we let the cluster
	 * allocator choose the starting cluster.
	 */
	/* If the last LCN is a hole or simillar seek back to last real LCN. */
	while (rl->lcn < 0 && rl > ni->runlist.rl)
		rl--;
first_alloc:
	// FIXME: Need to implement partial allocations so at least part of the
	// write can be performed when start >= 0.  (Needed for POSIX write(2)
	// conformance.)
	rl2 = ntfs_cluster_alloc(vol, allocated_size >> vol->cluster_size_bits,
			(new_alloc_size - allocated_size) >>
			vol->cluster_size_bits, (rl && (rl->lcn >= 0)) ?
			rl->lcn + rl->length : -1, DATA_ZONE, true);
	if (IS_ERR(rl2)) {
		err = PTR_ERR(rl2);
		if (start < 0 || start >= allocated_size)
			ntfs_error(vol->sb, "Cannot extend allocation of "
					"inode 0x%lx, attribute type 0x%x, "
					"because the allocation of clusters "
					"failed with error code %i.", vi->i_ino,
					(unsigned)le32_to_cpu(ni->type), err);
		if (err != -ENOMEM && err != -ENOSPC)
			err = -EIO;
		goto err_out;
	}
	rl = ntfs_runlists_merge(ni->runlist.rl, rl2);
	if (IS_ERR(rl)) {
		err = PTR_ERR(rl);
		if (start < 0 || start >= allocated_size)
			ntfs_error(vol->sb, "Cannot extend allocation of "
					"inode 0x%lx, attribute type 0x%x, "
					"because the runlist merge failed "
					"with error code %i.", vi->i_ino,
					(unsigned)le32_to_cpu(ni->type), err);
		if (err != -ENOMEM)
			err = -EIO;
		if (ntfs_cluster_free_from_rl(vol, rl2)) {
			ntfs_error(vol->sb, "Failed to release allocated "
					"cluster(s) in error code path.  Run "
					"chkdsk to recover the lost "
					"cluster(s).");
			NVolSetErrors(vol);
		}
		ntfs_free(rl2);
		goto err_out;
	}
	ni->runlist.rl = rl;
	ntfs_debug("Allocated 0x%llx clusters.", (long long)(new_alloc_size -
			allocated_size) >> vol->cluster_size_bits);
	/* Find the runlist element with which the attribute extent starts. */
	ll = sle64_to_cpu(a->data.non_resident.lowest_vcn);
	rl2 = ntfs_rl_find_vcn_nolock(rl, ll);
	BUG_ON(!rl2);
	BUG_ON(!rl2->length);
	BUG_ON(rl2->lcn < LCN_HOLE);
	mp_rebuilt = false;
	/* Get the size for the new mapping pairs array for this extent. */
	mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, ll, -1);
	if (unlikely(mp_size <= 0)) {
		err = mp_size;
		if (start < 0 || start >= allocated_size)
			ntfs_error(vol->sb, "Cannot extend allocation of "
					"inode 0x%lx, attribute type 0x%x, "
					"because determining the size for the "
					"mapping pairs failed with error code "
					"%i.", vi->i_ino,
					(unsigned)le32_to_cpu(ni->type), err);
		err = -EIO;
		goto undo_alloc;
	}
	/* Extend the attribute record to fit the bigger mapping pairs array. */
	attr_len = le32_to_cpu(a->length);
	err = ntfs_attr_record_resize(m, a, mp_size +
			le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
	if (unlikely(err)) {
		BUG_ON(err != -ENOSPC);
		// TODO: Deal with this by moving this extent to a new mft
		// record or by starting a new extent in a new mft record,
		// possibly by extending this extent partially and filling it
		// and creating a new extent for the remainder, or by making
		// other attributes non-resident and/or by moving other
		// attributes out of this mft record.
		if (start < 0 || start >= allocated_size)
			ntfs_error(vol->sb, "Not enough space in the mft "
					"record for the extended attribute "
					"record.  This case is not "
					"implemented yet.");
		err = -EOPNOTSUPP;
		goto undo_alloc;
	}
	mp_rebuilt = true;
	/* Generate the mapping pairs array directly into the attr record. */
	err = ntfs_mapping_pairs_build(vol, (u8*)a +
			le16_to_cpu(a->data.non_resident.mapping_pairs_offset),
			mp_size, rl2, ll, -1, NULL);
	if (unlikely(err)) {
		if (start < 0 || start >= allocated_size)
			ntfs_error(vol->sb, "Cannot extend allocation of "
					"inode 0x%lx, attribute type 0x%x, "
					"because building the mapping pairs "
					"failed with error code %i.", vi->i_ino,
					(unsigned)le32_to_cpu(ni->type), err);
		err = -EIO;
		goto undo_alloc;
	}
	/* Update the highest_vcn. */
	a->data.non_resident.highest_vcn = cpu_to_sle64((new_alloc_size >>
			vol->cluster_size_bits) - 1);
	/*
	 * We now have extended the allocated size of the attribute.  Reflect
	 * this in the ntfs_inode structure and the attribute record.
	 */
	if (a->data.non_resident.lowest_vcn) {
		/*
		 * We are not in the first attribute extent, switch to it, but
		 * first ensure the changes will make it to disk later.
		 */
		flush_dcache_mft_record_page(ctx->ntfs_ino);
		mark_mft_record_dirty(ctx->ntfs_ino);
		ntfs_attr_reinit_search_ctx(ctx);
		err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
				CASE_SENSITIVE, 0, NULL, 0, ctx);
		if (unlikely(err))
			goto restore_undo_alloc;
		/* @m is not used any more so no need to set it. */
		a = ctx->attr;
	}
	write_lock_irqsave(&ni->size_lock, flags);
	ni->allocated_size = new_alloc_size;
	a->data.non_resident.allocated_size = cpu_to_sle64(new_alloc_size);
	/*
	 * FIXME: This would fail if @ni is a directory, $MFT, or an index,
	 * since those can have sparse/compressed set.  For example can be
	 * set compressed even though it is not compressed itself and in that
	 * case the bit means that files are to be created compressed in the
	 * directory...  At present this is ok as this code is only called for
	 * regular files, and only for their $DATA attribute(s).
	 * FIXME: The calculation is wrong if we created a hole above.  For now
	 * it does not matter as we never create holes.
	 */
	if (NInoSparse(ni) || NInoCompressed(ni)) {
		ni->itype.compressed.size += new_alloc_size - allocated_size;
		a->data.non_resident.compressed_size =
				cpu_to_sle64(ni->itype.compressed.size);
		vi->i_blocks = ni->itype.compressed.size >> 9;
	} else
		vi->i_blocks = new_alloc_size >> 9;
	write_unlock_irqrestore(&ni->size_lock, flags);
alloc_done:
	if (new_data_size >= 0) {
		BUG_ON(new_data_size <
				sle64_to_cpu(a->data.non_resident.data_size));
		a->data.non_resident.data_size = cpu_to_sle64(new_data_size);
	}
flush_done:
	/* Ensure the changes make it to disk. */
	flush_dcache_mft_record_page(ctx->ntfs_ino);
	mark_mft_record_dirty(ctx->ntfs_ino);
done:
	ntfs_attr_put_search_ctx(ctx);
	unmap_mft_record(base_ni);
	up_write(&ni->runlist.lock);
	ntfs_debug("Done, new_allocated_size 0x%llx.",
			(unsigned long long)new_alloc_size);
	return new_alloc_size;
restore_undo_alloc:
	if (start < 0 || start >= allocated_size)
		ntfs_error(vol->sb, "Cannot complete extension of allocation "
				"of inode 0x%lx, attribute type 0x%x, because "
				"lookup of first attribute extent failed with "
				"error code %i.", vi->i_ino,
				(unsigned)le32_to_cpu(ni->type), err);
	if (err == -ENOENT)
		err = -EIO;
	ntfs_attr_reinit_search_ctx(ctx);
	if (ntfs_attr_lookup(ni->type, ni->name, ni->name_len, CASE_SENSITIVE,
			allocated_size >> vol->cluster_size_bits, NULL, 0,
			ctx)) {
		ntfs_error(vol->sb, "Failed to find last attribute extent of "
				"attribute in error code path.  Run chkdsk to "
				"recover.");
		write_lock_irqsave(&ni->size_lock, flags);
		ni->allocated_size = new_alloc_size;
		/*
		 * FIXME: This would fail if @ni is a directory...  See above.
		 * FIXME: The calculation is wrong if we created a hole above.
		 * For now it does not matter as we never create holes.
		 */
		if (NInoSparse(ni) || NInoCompressed(ni)) {
			ni->itype.compressed.size += new_alloc_size -
					allocated_size;
			vi->i_blocks = ni->itype.compressed.size >> 9;
		} else
			vi->i_blocks = new_alloc_size >> 9;
		write_unlock_irqrestore(&ni->size_lock, flags);
		ntfs_attr_put_search_ctx(ctx);
		unmap_mft_record(base_ni);
		up_write(&ni->runlist.lock);
		/*
		 * The only thing that is now wrong is the allocated size of the
		 * base attribute extent which chkdsk should be able to fix.
		 */
		NVolSetErrors(vol);
		return err;
	}
	ctx->attr->data.non_resident.highest_vcn = cpu_to_sle64(
			(allocated_size >> vol->cluster_size_bits) - 1);
undo_alloc:
	ll = allocated_size >> vol->cluster_size_bits;
	if (ntfs_cluster_free(ni, ll, -1, ctx) < 0) {
		ntfs_error(vol->sb, "Failed to release allocated cluster(s) "
				"in error code path.  Run chkdsk to recover "
				"the lost cluster(s).");
		NVolSetErrors(vol);
	}
	m = ctx->mrec;
	a = ctx->attr;
	/*
	 * If the runlist truncation fails and/or the search context is no
	 * longer valid, we cannot resize the attribute record or build the
	 * mapping pairs array thus we mark the inode bad so that no access to
	 * the freed clusters can happen.
	 */
	if (ntfs_rl_truncate_nolock(vol, &ni->runlist, ll) || IS_ERR(m)) {
		ntfs_error(vol->sb, "Failed to %s in error code path.  Run "
				"chkdsk to recover.", IS_ERR(m) ?
				"restore attribute search context" :
				"truncate attribute runlist");
		NVolSetErrors(vol);
	} else if (mp_rebuilt) {
		if (ntfs_attr_record_resize(m, a, attr_len)) {
			ntfs_error(vol->sb, "Failed to restore attribute "
					"record in error code path.  Run "
					"chkdsk to recover.");
			NVolSetErrors(vol);
		} else /* if (success) */ {
			if (ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(
					a->data.non_resident.
					mapping_pairs_offset), attr_len -
					le16_to_cpu(a->data.non_resident.
					mapping_pairs_offset), rl2, ll, -1,
					NULL)) {
				ntfs_error(vol->sb, "Failed to restore "
						"mapping pairs array in error "
						"code path.  Run chkdsk to "
						"recover.");
				NVolSetErrors(vol);
			}
			flush_dcache_mft_record_page(ctx->ntfs_ino);
			mark_mft_record_dirty(ctx->ntfs_ino);
		}
	}
err_out:
	if (ctx)
		ntfs_attr_put_search_ctx(ctx);
	if (m)
		unmap_mft_record(base_ni);
	up_write(&ni->runlist.lock);
conv_err_out:
	ntfs_debug("Failed.  Returning error code %i.", err);
	return err;
}

/**
 * ntfs_attr_set - fill (a part of) an attribute with a byte
 * @ni:		ntfs inode describing the attribute to fill
 * @ofs:	offset inside the attribute at which to start to fill
 * @cnt:	number of bytes to fill
 * @val:	the unsigned 8-bit value with which to fill the attribute
 *
 * Fill @cnt bytes of the attribute described by the ntfs inode @ni starting at
 * byte offset @ofs inside the attribute with the constant byte @val.
 *
 * This function is effectively like memset() applied to an ntfs attribute.
 * Note thie function actually only operates on the page cache pages belonging
 * to the ntfs attribute and it marks them dirty after doing the memset().
 * Thus it relies on the vm dirty page write code paths to cause the modified
 * pages to be written to the mft record/disk.
 *
 * Return 0 on success and -errno on error.  An error code of -ESPIPE means
 * that @ofs + @cnt were outside the end of the attribute and no write was
 * performed.
 */
int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
{
	ntfs_volume *vol = ni->vol;
	struct address_space *mapping;
	struct page *page;
	u8 *kaddr;
	pgoff_t idx, end;
	unsigned start_ofs, end_ofs, size;

	ntfs_debug("Entering for ofs 0x%llx, cnt 0x%llx, val 0x%hx.",
			(long long)ofs, (long long)cnt, val);
	BUG_ON(ofs < 0);
	BUG_ON(cnt < 0);
	if (!cnt)
		goto done;
	/*
	 * FIXME: Compressed and encrypted attributes are not supported when
	 * writing and we should never have gotten here for them.
	 */
	BUG_ON(NInoCompressed(ni));
	BUG_ON(NInoEncrypted(ni));
	mapping = VFS_I(ni)->i_mapping;
	/* Work out the starting index and page offset. */
	idx = ofs >> PAGE_CACHE_SHIFT;
	start_ofs = ofs & ~PAGE_CACHE_MASK;
	/* Work out the ending index and page offset. */
	end = ofs + cnt;
	end_ofs = end & ~PAGE_CACHE_MASK;
	/* If the end is outside the inode size return -ESPIPE. */
	if (unlikely(end > i_size_read(VFS_I(ni)))) {
		ntfs_error(vol->sb, "Request exceeds end of attribute.");
		return -ESPIPE;
	}
	end >>= PAGE_CACHE_SHIFT;
	/* If there is a first partial page, need to do it the slow way. */
	if (start_ofs) {
		page = read_mapping_page(mapping, idx, NULL);
		if (IS_ERR(page)) {
			ntfs_error(vol->sb, "Failed to read first partial "
					"page (error, index 0x%lx).", idx);
			return PTR_ERR(page);
		}
		/*
		 * If the last page is the same as the first page, need to
		 * limit the write to the end offset.
		 */
		size = PAGE_CACHE_SIZE;
		if (idx == end)
			size = end_ofs;
		kaddr = kmap_atomic(page, KM_USER0);
		memset(kaddr + start_ofs, val, size - start_ofs);
		flush_dcache_page(page);
		kunmap_atomic(kaddr, KM_USER0);
		set_page_dirty(page);
		page_cache_release(page);
		balance_dirty_pages_ratelimited(mapping);
		cond_resched();
		if (idx == end)
			goto done;
		idx++;
	}
	/* Do the whole pages the fast way. */
	for (; idx < end; idx++) {
		/* Find or create the current page.  (The page is locked.) */
		page = grab_cache_page(mapping, idx);
		if (unlikely(!page)) {
			ntfs_error(vol->sb, "Insufficient memory to grab "
					"page (index 0x%lx).", idx);
			return -ENOMEM;
		}
		kaddr = kmap_atomic(page, KM_USER0);
		memset(kaddr, val, PAGE_CACHE_SIZE);
		flush_dcache_page(page);
		kunmap_atomic(kaddr, KM_USER0);
		/*
		 * If the page has buffers, mark them uptodate since buffer
		 * state and not page state is definitive in 2.6 kernels.
		 */
		if (page_has_buffers(page)) {
			struct buffer_head *bh, *head;

			bh = head = page_buffers(page);
			do {
				set_buffer_uptodate(bh);
			} while ((bh = bh->b_this_page) != head);
		}
		/* Now that buffers are uptodate, set the page uptodate, too. */
		SetPageUptodate(page);
		/*
		 * Set the page and all its buffers dirty and mark the inode
		 * dirty, too.  The VM will write the page later on.
		 */
		set_page_dirty(page);
		/* Finally unlock and release the page. */
		unlock_page(page);
		page_cache_release(page);
		balance_dirty_pages_ratelimited(mapping);
		cond_resched();
	}
	/* If there is a last partial page, need to do it the slow way. */
	if (end_ofs) {
		page = read_mapping_page(mapping, idx, NULL);
		if (IS_ERR(page)) {
			ntfs_error(vol->sb, "Failed to read last partial page "
					"(error, index 0x%lx).", idx);
			return PTR_ERR(page);
		}
		kaddr = kmap_atomic(page, KM_USER0);
		memset(kaddr, val, end_ofs);
		flush_dcache_page(page);
		kunmap_atomic(kaddr, KM_USER0);
		set_page_dirty(page);
		page_cache_release(page);
		balance_dirty_pages_ratelimited(mapping);
		cond_resched();
	}
done:
	ntfs_debug("Done.");
	return 0;
}

#endif /* NTFS_RW */