aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ocfs2/aops.c
blob: eb1ce30412dc3e09d1fbd4c8e890d86c2d0a4c9f (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
/* -*- mode: c; c-basic-offset: 8; -*-
 * vim: noexpandtab sw=8 ts=8 sts=0:
 *
 * Copyright (C) 2002, 2004 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This program 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; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <asm/byteorder.h>
#include <linux/swap.h>
#include <linux/pipe_fs_i.h>
#include <linux/mpage.h>
#include <linux/quotaops.h>
#include <linux/blkdev.h>
#include <linux/uio.h>

#include <cluster/masklog.h>

#include "ocfs2.h"

#include "alloc.h"
#include "aops.h"
#include "dlmglue.h"
#include "extent_map.h"
#include "file.h"
#include "inode.h"
#include "journal.h"
#include "suballoc.h"
#include "super.h"
#include "symlink.h"
#include "refcounttree.h"
#include "ocfs2_trace.h"

#include "buffer_head_io.h"
#include "dir.h"
#include "namei.h"
#include "sysfile.h"

static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
				   struct buffer_head *bh_result, int create)
{
	int err = -EIO;
	int status;
	struct ocfs2_dinode *fe = NULL;
	struct buffer_head *bh = NULL;
	struct buffer_head *buffer_cache_bh = NULL;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	void *kaddr;

	trace_ocfs2_symlink_get_block(
			(unsigned long long)OCFS2_I(inode)->ip_blkno,
			(unsigned long long)iblock, bh_result, create);

	BUG_ON(ocfs2_inode_is_fast_symlink(inode));

	if ((iblock << inode->i_sb->s_blocksize_bits) > PATH_MAX + 1) {
		mlog(ML_ERROR, "block offset > PATH_MAX: %llu",
		     (unsigned long long)iblock);
		goto bail;
	}

	status = ocfs2_read_inode_block(inode, &bh);
	if (status < 0) {
		mlog_errno(status);
		goto bail;
	}
	fe = (struct ocfs2_dinode *) bh->b_data;

	if ((u64)iblock >= ocfs2_clusters_to_blocks(inode->i_sb,
						    le32_to_cpu(fe->i_clusters))) {
		err = -ENOMEM;
		mlog(ML_ERROR, "block offset is outside the allocated size: "
		     "%llu\n", (unsigned long long)iblock);
		goto bail;
	}

	/* We don't use the page cache to create symlink data, so if
	 * need be, copy it over from the buffer cache. */
	if (!buffer_uptodate(bh_result) && ocfs2_inode_is_new(inode)) {
		u64 blkno = le64_to_cpu(fe->id2.i_list.l_recs[0].e_blkno) +
			    iblock;
		buffer_cache_bh = sb_getblk(osb->sb, blkno);
		if (!buffer_cache_bh) {
			err = -ENOMEM;
			mlog(ML_ERROR, "couldn't getblock for symlink!\n");
			goto bail;
		}

		/* we haven't locked out transactions, so a commit
		 * could've happened. Since we've got a reference on
		 * the bh, even if it commits while we're doing the
		 * copy, the data is still good. */
		if (buffer_jbd(buffer_cache_bh)
		    && ocfs2_inode_is_new(inode)) {
			kaddr = kmap_atomic(bh_result->b_page);
			if (!kaddr) {
				mlog(ML_ERROR, "couldn't kmap!\n");
				goto bail;
			}
			memcpy(kaddr + (bh_result->b_size * iblock),
			       buffer_cache_bh->b_data,
			       bh_result->b_size);
			kunmap_atomic(kaddr);
			set_buffer_uptodate(bh_result);
		}
		brelse(buffer_cache_bh);
	}

	map_bh(bh_result, inode->i_sb,
	       le64_to_cpu(fe->id2.i_list.l_recs[0].e_blkno) + iblock);

	err = 0;

bail:
	brelse(bh);

	return err;
}

static int ocfs2_lock_get_block(struct inode *inode, sector_t iblock,
		    struct buffer_head *bh_result, int create)
{
	int ret = 0;
	struct ocfs2_inode_info *oi = OCFS2_I(inode);

	down_read(&oi->ip_alloc_sem);
	ret = ocfs2_get_block(inode, iblock, bh_result, create);
	up_read(&oi->ip_alloc_sem);

	return ret;
}

int ocfs2_get_block(struct inode *inode, sector_t iblock,
		    struct buffer_head *bh_result, int create)
{
	int err = 0;
	unsigned int ext_flags;
	u64 max_blocks = bh_result->b_size >> inode->i_blkbits;
	u64 p_blkno, count, past_eof;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);

	trace_ocfs2_get_block((unsigned long long)OCFS2_I(inode)->ip_blkno,
			      (unsigned long long)iblock, bh_result, create);

	if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SYSTEM_FILE)
		mlog(ML_NOTICE, "get_block on system inode 0x%p (%lu)\n",
		     inode, inode->i_ino);

	if (S_ISLNK(inode->i_mode)) {
		/* this always does I/O for some reason. */
		err = ocfs2_symlink_get_block(inode, iblock, bh_result, create);
		goto bail;
	}

	err = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno, &count,
					  &ext_flags);
	if (err) {
		mlog(ML_ERROR, "Error %d from get_blocks(0x%p, %llu, 1, "
		     "%llu, NULL)\n", err, inode, (unsigned long long)iblock,
		     (unsigned long long)p_blkno);
		goto bail;
	}

	if (max_blocks < count)
		count = max_blocks;

	/*
	 * ocfs2 never allocates in this function - the only time we
	 * need to use BH_New is when we're extending i_size on a file
	 * system which doesn't support holes, in which case BH_New
	 * allows __block_write_begin() to zero.
	 *
	 * If we see this on a sparse file system, then a truncate has
	 * raced us and removed the cluster. In this case, we clear
	 * the buffers dirty and uptodate bits and let the buffer code
	 * ignore it as a hole.
	 */
	if (create && p_blkno == 0 && ocfs2_sparse_alloc(osb)) {
		clear_buffer_dirty(bh_result);
		clear_buffer_uptodate(bh_result);
		goto bail;
	}

	/* Treat the unwritten extent as a hole for zeroing purposes. */
	if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
		map_bh(bh_result, inode->i_sb, p_blkno);

	bh_result->b_size = count << inode->i_blkbits;

	if (!ocfs2_sparse_alloc(osb)) {
		if (p_blkno == 0) {
			err = -EIO;
			mlog(ML_ERROR,
			     "iblock = %llu p_blkno = %llu blkno=(%llu)\n",
			     (unsigned long long)iblock,
			     (unsigned long long)p_blkno,
			     (unsigned long long)OCFS2_I(inode)->ip_blkno);
			mlog(ML_ERROR, "Size %llu, clusters %u\n", (unsigned long long)i_size_read(inode), OCFS2_I(inode)->ip_clusters);
			dump_stack();
			goto bail;
		}
	}

	past_eof = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));

	trace_ocfs2_get_block_end((unsigned long long)OCFS2_I(inode)->ip_blkno,
				  (unsigned long long)past_eof);
	if (create && (iblock >= past_eof))
		set_buffer_new(bh_result);

bail:
	if (err < 0)
		err = -EIO;

	return err;
}

int ocfs2_read_inline_data(struct inode *inode, struct page *page,
			   struct buffer_head *di_bh)
{
	void *kaddr;
	loff_t size;
	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;

	if (!(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL)) {
		ocfs2_error(inode->i_sb, "Inode %llu lost inline data flag\n",
			    (unsigned long long)OCFS2_I(inode)->ip_blkno);
		return -EROFS;
	}

	size = i_size_read(inode);

	if (size > PAGE_SIZE ||
	    size > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) {
		ocfs2_error(inode->i_sb,
			    "Inode %llu has with inline data has bad size: %Lu\n",
			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
			    (unsigned long long)size);
		return -EROFS;
	}

	kaddr = kmap_atomic(page);
	if (size)
		memcpy(kaddr, di->id2.i_data.id_data, size);
	/* Clear the remaining part of the page */
	memset(kaddr + size, 0, PAGE_SIZE - size);
	flush_dcache_page(page);
	kunmap_atomic(kaddr);

	SetPageUptodate(page);

	return 0;
}

static int ocfs2_readpage_inline(struct inode *inode, struct page *page)
{
	int ret;
	struct buffer_head *di_bh = NULL;

	BUG_ON(!PageLocked(page));
	BUG_ON(!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL));

	ret = ocfs2_read_inode_block(inode, &di_bh);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_read_inline_data(inode, page, di_bh);
out:
	unlock_page(page);

	brelse(di_bh);
	return ret;
}

static int ocfs2_readpage(struct file *file, struct page *page)
{
	struct inode *inode = page->mapping->host;
	struct ocfs2_inode_info *oi = OCFS2_I(inode);
	loff_t start = (loff_t)page->index << PAGE_SHIFT;
	int ret, unlock = 1;

	trace_ocfs2_readpage((unsigned long long)oi->ip_blkno,
			     (page ? page->index : 0));

	ret = ocfs2_inode_lock_with_page(inode, NULL, 0, page);
	if (ret != 0) {
		if (ret == AOP_TRUNCATED_PAGE)
			unlock = 0;
		mlog_errno(ret);
		goto out;
	}

	if (down_read_trylock(&oi->ip_alloc_sem) == 0) {
		/*
		 * Unlock the page and cycle ip_alloc_sem so that we don't
		 * busyloop waiting for ip_alloc_sem to unlock
		 */
		ret = AOP_TRUNCATED_PAGE;
		unlock_page(page);
		unlock = 0;
		down_read(&oi->ip_alloc_sem);
		up_read(&oi->ip_alloc_sem);
		goto out_inode_unlock;
	}

	/*
	 * i_size might have just been updated as we grabed the meta lock.  We
	 * might now be discovering a truncate that hit on another node.
	 * block_read_full_page->get_block freaks out if it is asked to read
	 * beyond the end of a file, so we check here.  Callers
	 * (generic_file_read, vm_ops->fault) are clever enough to check i_size
	 * and notice that the page they just read isn't needed.
	 *
	 * XXX sys_readahead() seems to get that wrong?
	 */
	if (start >= i_size_read(inode)) {
		zero_user(page, 0, PAGE_SIZE);
		SetPageUptodate(page);
		ret = 0;
		goto out_alloc;
	}

	if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL)
		ret = ocfs2_readpage_inline(inode, page);
	else
		ret = block_read_full_page(page, ocfs2_get_block);
	unlock = 0;

out_alloc:
	up_read(&oi->ip_alloc_sem);
out_inode_unlock:
	ocfs2_inode_unlock(inode, 0);
out:
	if (unlock)
		unlock_page(page);
	return ret;
}

/*
 * This is used only for read-ahead. Failures or difficult to handle
 * situations are safe to ignore.
 *
 * Right now, we don't bother with BH_Boundary - in-inode extent lists
 * are quite large (243 extents on 4k blocks), so most inodes don't
 * grow out to a tree. If need be, detecting boundary extents could
 * trivially be added in a future version of ocfs2_get_block().
 */
static int ocfs2_readpages(struct file *filp, struct address_space *mapping,
			   struct list_head *pages, unsigned nr_pages)
{
	int ret, err = -EIO;
	struct inode *inode = mapping->host;
	struct ocfs2_inode_info *oi = OCFS2_I(inode);
	loff_t start;
	struct page *last;

	/*
	 * Use the nonblocking flag for the dlm code to avoid page
	 * lock inversion, but don't bother with retrying.
	 */
	ret = ocfs2_inode_lock_full(inode, NULL, 0, OCFS2_LOCK_NONBLOCK);
	if (ret)
		return err;

	if (down_read_trylock(&oi->ip_alloc_sem) == 0) {
		ocfs2_inode_unlock(inode, 0);
		return err;
	}

	/*
	 * Don't bother with inline-data. There isn't anything
	 * to read-ahead in that case anyway...
	 */
	if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL)
		goto out_unlock;

	/*
	 * Check whether a remote node truncated this file - we just
	 * drop out in that case as it's not worth handling here.
	 */
	last = list_entry(pages->prev, struct page, lru);
	start = (loff_t)last->index << PAGE_SHIFT;
	if (start >= i_size_read(inode))
		goto out_unlock;

	err = mpage_readpages(mapping, pages, nr_pages, ocfs2_get_block);

out_unlock:
	up_read(&oi->ip_alloc_sem);
	ocfs2_inode_unlock(inode, 0);

	return err;
}

/* Note: Because we don't support holes, our allocation has
 * already happened (allocation writes zeros to the file data)
 * so we don't have to worry about ordered writes in
 * ocfs2_writepage.
 *
 * ->writepage is called during the process of invalidating the page cache
 * during blocked lock processing.  It can't block on any cluster locks
 * to during block mapping.  It's relying on the fact that the block
 * mapping can't have disappeared under the dirty pages that it is
 * being asked to write back.
 */
static int ocfs2_writepage(struct page *page, struct writeback_control *wbc)
{
	trace_ocfs2_writepage(
		(unsigned long long)OCFS2_I(page->mapping->host)->ip_blkno,
		page->index);

	return block_write_full_page(page, ocfs2_get_block, wbc);
}

/* Taken from ext3. We don't necessarily need the full blown
 * functionality yet, but IMHO it's better to cut and paste the whole
 * thing so we can avoid introducing our own bugs (and easily pick up
 * their fixes when they happen) --Mark */
int walk_page_buffers(	handle_t *handle,
			struct buffer_head *head,
			unsigned from,
			unsigned to,
			int *partial,
			int (*fn)(	handle_t *handle,
					struct buffer_head *bh))
{
	struct buffer_head *bh;
	unsigned block_start, block_end;
	unsigned blocksize = head->b_size;
	int err, ret = 0;
	struct buffer_head *next;

	for (	bh = head, block_start = 0;
		ret == 0 && (bh != head || !block_start);
	    	block_start = block_end, bh = next)
	{
		next = bh->b_this_page;
		block_end = block_start + blocksize;
		if (block_end <= from || block_start >= to) {
			if (partial && !buffer_uptodate(bh))
				*partial = 1;
			continue;
		}
		err = (*fn)(handle, bh);
		if (!ret)
			ret = err;
	}
	return ret;
}

static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block)
{
	sector_t status;
	u64 p_blkno = 0;
	int err = 0;
	struct inode *inode = mapping->host;

	trace_ocfs2_bmap((unsigned long long)OCFS2_I(inode)->ip_blkno,
			 (unsigned long long)block);

	/*
	 * The swap code (ab-)uses ->bmap to get a block mapping and then
	 * bypasseѕ the file system for actual I/O.  We really can't allow
	 * that on refcounted inodes, so we have to skip out here.  And yes,
	 * 0 is the magic code for a bmap error..
	 */
	if (ocfs2_is_refcount_inode(inode))
		return 0;

	/* We don't need to lock journal system files, since they aren't
	 * accessed concurrently from multiple nodes.
	 */
	if (!INODE_JOURNAL(inode)) {
		err = ocfs2_inode_lock(inode, NULL, 0);
		if (err) {
			if (err != -ENOENT)
				mlog_errno(err);
			goto bail;
		}
		down_read(&OCFS2_I(inode)->ip_alloc_sem);
	}

	if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL))
		err = ocfs2_extent_map_get_blocks(inode, block, &p_blkno, NULL,
						  NULL);

	if (!INODE_JOURNAL(inode)) {
		up_read(&OCFS2_I(inode)->ip_alloc_sem);
		ocfs2_inode_unlock(inode, 0);
	}

	if (err) {
		mlog(ML_ERROR, "get_blocks() failed, block = %llu\n",
		     (unsigned long long)block);
		mlog_errno(err);
		goto bail;
	}

bail:
	status = err ? 0 : p_blkno;

	return status;
}

static int ocfs2_releasepage(struct page *page, gfp_t wait)
{
	if (!page_has_buffers(page))
		return 0;
	return try_to_free_buffers(page);
}

static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb,
					    u32 cpos,
					    unsigned int *start,
					    unsigned int *end)
{
	unsigned int cluster_start = 0, cluster_end = PAGE_SIZE;

	if (unlikely(PAGE_SHIFT > osb->s_clustersize_bits)) {
		unsigned int cpp;

		cpp = 1 << (PAGE_SHIFT - osb->s_clustersize_bits);

		cluster_start = cpos % cpp;
		cluster_start = cluster_start << osb->s_clustersize_bits;

		cluster_end = cluster_start + osb->s_clustersize;
	}

	BUG_ON(cluster_start > PAGE_SIZE);
	BUG_ON(cluster_end > PAGE_SIZE);

	if (start)
		*start = cluster_start;
	if (end)
		*end = cluster_end;
}

/*
 * 'from' and 'to' are the region in the page to avoid zeroing.
 *
 * If pagesize > clustersize, this function will avoid zeroing outside
 * of the cluster boundary.
 *
 * from == to == 0 is code for "zero the entire cluster region"
 */
static void ocfs2_clear_page_regions(struct page *page,
				     struct ocfs2_super *osb, u32 cpos,
				     unsigned from, unsigned to)
{
	void *kaddr;
	unsigned int cluster_start, cluster_end;

	ocfs2_figure_cluster_boundaries(osb, cpos, &cluster_start, &cluster_end);

	kaddr = kmap_atomic(page);

	if (from || to) {
		if (from > cluster_start)
			memset(kaddr + cluster_start, 0, from - cluster_start);
		if (to < cluster_end)
			memset(kaddr + to, 0, cluster_end - to);
	} else {
		memset(kaddr + cluster_start, 0, cluster_end - cluster_start);
	}

	kunmap_atomic(kaddr);
}

/*
 * Nonsparse file systems fully allocate before we get to the write
 * code. This prevents ocfs2_write() from tagging the write as an
 * allocating one, which means ocfs2_map_page_blocks() might try to
 * read-in the blocks at the tail of our file. Avoid reading them by
 * testing i_size against each block offset.
 */
static int ocfs2_should_read_blk(struct inode *inode, struct page *page,
				 unsigned int block_start)
{
	u64 offset = page_offset(page) + block_start;

	if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
		return 1;

	if (i_size_read(inode) > offset)
		return 1;

	return 0;
}

/*
 * Some of this taken from __block_write_begin(). We already have our
 * mapping by now though, and the entire write will be allocating or
 * it won't, so not much need to use BH_New.
 *
 * This will also skip zeroing, which is handled externally.
 */
int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno,
			  struct inode *inode, unsigned int from,
			  unsigned int to, int new)
{
	int ret = 0;
	struct buffer_head *head, *bh, *wait[2], **wait_bh = wait;
	unsigned int block_end, block_start;
	unsigned int bsize = i_blocksize(inode);

	if (!page_has_buffers(page))
		create_empty_buffers(page, bsize, 0);

	head = page_buffers(page);
	for (bh = head, block_start = 0; bh != head || !block_start;
	     bh = bh->b_this_page, block_start += bsize) {
		block_end = block_start + bsize;

		clear_buffer_new(bh);

		/*
		 * Ignore blocks outside of our i/o range -
		 * they may belong to unallocated clusters.
		 */
		if (block_start >= to || block_end <= from) {
			if (PageUptodate(page))
				set_buffer_uptodate(bh);
			continue;
		}

		/*
		 * For an allocating write with cluster size >= page
		 * size, we always write the entire page.
		 */
		if (new)
			set_buffer_new(bh);

		if (!buffer_mapped(bh)) {
			map_bh(bh, inode->i_sb, *p_blkno);
			clean_bdev_bh_alias(bh);
		}

		if (PageUptodate(page)) {
			if (!buffer_uptodate(bh))
				set_buffer_uptodate(bh);
		} else if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
			   !buffer_new(bh) &&
			   ocfs2_should_read_blk(inode, page, block_start) &&
			   (block_start < from || block_end > to)) {
			ll_rw_block(REQ_OP_READ, 0, 1, &bh);
			*wait_bh++=bh;
		}

		*p_blkno = *p_blkno + 1;
	}

	/*
	 * If we issued read requests - let them complete.
	 */
	while(wait_bh > wait) {
		wait_on_buffer(*--wait_bh);
		if (!buffer_uptodate(*wait_bh))
			ret = -EIO;
	}

	if (ret == 0 || !new)
		return ret;

	/*
	 * If we get -EIO above, zero out any newly allocated blocks
	 * to avoid exposing stale data.
	 */
	bh = head;
	block_start = 0;
	do {
		block_end = block_start + bsize;
		if (block_end <= from)
			goto next_bh;
		if (block_start >= to)
			break;

		zero_user(page, block_start, bh->b_size);
		set_buffer_uptodate(bh);
		mark_buffer_dirty(bh);

next_bh:
		block_start = block_end;
		bh = bh->b_this_page;
	} while (bh != head);

	return ret;
}

#if (PAGE_SIZE >= OCFS2_MAX_CLUSTERSIZE)
#define OCFS2_MAX_CTXT_PAGES	1
#else
#define OCFS2_MAX_CTXT_PAGES	(OCFS2_MAX_CLUSTERSIZE / PAGE_SIZE)
#endif

#define OCFS2_MAX_CLUSTERS_PER_PAGE	(PAGE_SIZE / OCFS2_MIN_CLUSTERSIZE)

struct ocfs2_unwritten_extent {
	struct list_head	ue_node;
	struct list_head	ue_ip_node;
	u32			ue_cpos;
	u32			ue_phys;
};

/*
 * Describe the state of a single cluster to be written to.
 */
struct ocfs2_write_cluster_desc {
	u32		c_cpos;
	u32		c_phys;
	/*
	 * Give this a unique field because c_phys eventually gets
	 * filled.
	 */
	unsigned	c_new;
	unsigned	c_clear_unwritten;
	unsigned	c_needs_zero;
};

struct ocfs2_write_ctxt {
	/* Logical cluster position / len of write */
	u32				w_cpos;
	u32				w_clen;

	/* First cluster allocated in a nonsparse extend */
	u32				w_first_new_cpos;

	/* Type of caller. Must be one of buffer, mmap, direct.  */
	ocfs2_write_type_t		w_type;

	struct ocfs2_write_cluster_desc	w_desc[OCFS2_MAX_CLUSTERS_PER_PAGE];

	/*
	 * This is true if page_size > cluster_size.
	 *
	 * It triggers a set of special cases during write which might
	 * have to deal with allocating writes to partial pages.
	 */
	unsigned int			w_large_pages;

	/*
	 * Pages involved in this write.
	 *
	 * w_target_page is the page being written to by the user.
	 *
	 * w_pages is an array of pages which always contains
	 * w_target_page, and in the case of an allocating write with
	 * page_size < cluster size, it will contain zero'd and mapped
	 * pages adjacent to w_target_page which need to be written
	 * out in so that future reads from that region will get
	 * zero's.
	 */
	unsigned int			w_num_pages;
	struct page			*w_pages[OCFS2_MAX_CTXT_PAGES];
	struct page			*w_target_page;

	/*
	 * w_target_locked is used for page_mkwrite path indicating no unlocking
	 * against w_target_page in ocfs2_write_end_nolock.
	 */
	unsigned int			w_target_locked:1;

	/*
	 * ocfs2_write_end() uses this to know what the real range to
	 * write in the target should be.
	 */
	unsigned int			w_target_from;
	unsigned int			w_target_to;

	/*
	 * We could use journal_current_handle() but this is cleaner,
	 * IMHO -Mark
	 */
	handle_t			*w_handle;

	struct buffer_head		*w_di_bh;

	struct ocfs2_cached_dealloc_ctxt w_dealloc;

	struct list_head		w_unwritten_list;
	unsigned int			w_unwritten_count;
};

void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
{
	int i;

	for(i = 0; i < num_pages; i++) {
		if (pages[i]) {
			unlock_page(pages[i]);
			mark_page_accessed(pages[i]);
			put_page(pages[i]);
		}
	}
}

static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc)
{
	int i;

	/*
	 * w_target_locked is only set to true in the page_mkwrite() case.
	 * The intent is to allow us to lock the target page from write_begin()
	 * to write_end(). The caller must hold a ref on w_target_page.
	 */
	if (wc->w_target_locked) {
		BUG_ON(!wc->w_target_page);
		for (i = 0; i < wc->w_num_pages; i++) {
			if (wc->w_target_page == wc->w_pages[i]) {
				wc->w_pages[i] = NULL;
				break;
			}
		}
		mark_page_accessed(wc->w_target_page);
		put_page(wc->w_target_page);
	}
	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
}

static void ocfs2_free_unwritten_list(struct inode *inode,
				 struct list_head *head)
{
	struct ocfs2_inode_info *oi = OCFS2_I(inode);
	struct ocfs2_unwritten_extent *ue = NULL, *tmp = NULL;

	list_for_each_entry_safe(ue, tmp, head, ue_node) {
		list_del(&ue->ue_node);
		spin_lock(&oi->ip_lock);
		list_del(&ue->ue_ip_node);
		spin_unlock(&oi->ip_lock);
		kfree(ue);
	}
}

static void ocfs2_free_write_ctxt(struct inode *inode,
				  struct ocfs2_write_ctxt *wc)
{
	ocfs2_free_unwritten_list(inode, &wc->w_unwritten_list);
	ocfs2_unlock_pages(wc);
	brelse(wc->w_di_bh);
	kfree(wc);
}

static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
				  struct ocfs2_super *osb, loff_t pos,
				  unsigned len, ocfs2_write_type_t type,
				  struct buffer_head *di_bh)
{
	u32 cend;
	struct ocfs2_write_ctxt *wc;

	wc = kzalloc(sizeof(struct ocfs2_write_ctxt), GFP_NOFS);
	if (!wc)
		return -ENOMEM;

	wc->w_cpos = pos >> osb->s_clustersize_bits;
	wc->w_first_new_cpos = UINT_MAX;
	cend = (pos + len - 1) >> osb->s_clustersize_bits;
	wc->w_clen = cend - wc->w_cpos + 1;
	get_bh(di_bh);
	wc->w_di_bh = di_bh;
	wc->w_type = type;

	if (unlikely(PAGE_SHIFT > osb->s_clustersize_bits))
		wc->w_large_pages = 1;
	else
		wc->w_large_pages = 0;

	ocfs2_init_dealloc_ctxt(&wc->w_dealloc);
	INIT_LIST_HEAD(&wc->w_unwritten_list);

	*wcp = wc;

	return 0;
}

/*
 * If a page has any new buffers, zero them out here, and mark them uptodate
 * and dirty so they'll be written out (in order to prevent uninitialised
 * block data from leaking). And clear the new bit.
 */
static void ocfs2_zero_new_buffers(struct page *page, unsigned from, unsigned to)
{
	unsigned int block_start, block_end;
	struct buffer_head *head, *bh;

	BUG_ON(!PageLocked(page));
	if (!page_has_buffers(page))
		return;

	bh = head = page_buffers(page);
	block_start = 0;
	do {
		block_end = block_start + bh->b_size;

		if (buffer_new(bh)) {
			if (block_end > from && block_start < to) {
				if (!PageUptodate(page)) {
					unsigned start, end;

					start = max(from, block_start);
					end = min(to, block_end);

					zero_user_segment(page, start, end);
					set_buffer_uptodate(bh);
				}

				clear_buffer_new(bh);
				mark_buffer_dirty(bh);
			}
		}

		block_start = block_end;
		bh = bh->b_this_page;
	} while (bh != head);
}

/*
 * Only called when we have a failure during allocating write to write
 * zero's to the newly allocated region.
 */
static void ocfs2_write_failure(struct inode *inode,
				struct ocfs2_write_ctxt *wc,
				loff_t user_pos, unsigned user_len)
{
	int i;
	unsigned from = user_pos & (PAGE_SIZE - 1),
		to = user_pos + user_len;
	struct page *tmppage;

	if (wc->w_target_page)
		ocfs2_zero_new_buffers(wc->w_target_page, from, to);

	for(i = 0; i < wc->w_num_pages; i++) {
		tmppage = wc->w_pages[i];

		if (tmppage && page_has_buffers(tmppage)) {
			if (ocfs2_should_order_data(inode))
				ocfs2_jbd2_file_inode(wc->w_handle, inode);

			block_commit_write(tmppage, from, to);
		}
	}
}

static int ocfs2_prepare_page_for_write(struct inode *inode, u64 *p_blkno,
					struct ocfs2_write_ctxt *wc,
					struct page *page, u32 cpos,
					loff_t user_pos, unsigned user_len,
					int new)
{
	int ret;
	unsigned int map_from = 0, map_to = 0;
	unsigned int cluster_start, cluster_end;
	unsigned int user_data_from = 0, user_data_to = 0;

	ocfs2_figure_cluster_boundaries(OCFS2_SB(inode->i_sb), cpos,
					&cluster_start, &cluster_end);

	/* treat the write as new if the a hole/lseek spanned across
	 * the page boundary.
	 */
	new = new | ((i_size_read(inode) <= page_offset(page)) &&
			(page_offset(page) <= user_pos));

	if (page == wc->w_target_page) {
		map_from = user_pos & (PAGE_SIZE - 1);
		map_to = map_from + user_len;

		if (new)
			ret = ocfs2_map_page_blocks(page, p_blkno, inode,
						    cluster_start, cluster_end,
						    new);
		else
			ret = ocfs2_map_page_blocks(page, p_blkno, inode,
						    map_from, map_to, new);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		user_data_from = map_from;
		user_data_to = map_to;
		if (new) {
			map_from = cluster_start;
			map_to = cluster_end;
		}
	} else {
		/*
		 * If we haven't allocated the new page yet, we
		 * shouldn't be writing it out without copying user
		 * data. This is likely a math error from the caller.
		 */
		BUG_ON(!new);

		map_from = cluster_start;
		map_to = cluster_end;

		ret = ocfs2_map_page_blocks(page, p_blkno, inode,
					    cluster_start, cluster_end, new);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}
	}

	/*
	 * Parts of newly allocated pages need to be zero'd.
	 *
	 * Above, we have also rewritten 'to' and 'from' - as far as
	 * the rest of the function is concerned, the entire cluster
	 * range inside of a page needs to be written.
	 *
	 * We can skip this if the page is up to date - it's already
	 * been zero'd from being read in as a hole.
	 */
	if (new && !PageUptodate(page))
		ocfs2_clear_page_regions(page, OCFS2_SB(inode->i_sb),
					 cpos, user_data_from, user_data_to);

	flush_dcache_page(page);

out:
	return ret;
}

/*
 * This function will only grab one clusters worth of pages.
 */
static int ocfs2_grab_pages_for_write(struct address_space *mapping,
				      struct ocfs2_write_ctxt *wc,
				      u32 cpos, loff_t user_pos,
				      unsigned user_len, int new,
				      struct page *mmap_page)
{
	int ret = 0, i;
	unsigned long start, target_index, end_index, index;
	struct inode *inode = mapping->host;
	loff_t last_byte;

	target_index = user_pos >> PAGE_SHIFT;

	/*
	 * Figure out how many pages we'll be manipulating here. For
	 * non allocating write, we just change the one
	 * page. Otherwise, we'll need a whole clusters worth.  If we're
	 * writing past i_size, we only need enough pages to cover the
	 * last page of the write.
	 */
	if (new) {
		wc->w_num_pages = ocfs2_pages_per_cluster(inode->i_sb);
		start = ocfs2_align_clusters_to_page_index(inode->i_sb, cpos);
		/*
		 * We need the index *past* the last page we could possibly
		 * touch.  This is the page past the end of the write or
		 * i_size, whichever is greater.
		 */
		last_byte = max(user_pos + user_len, i_size_read(inode));
		BUG_ON(last_byte < 1);
		end_index = ((last_byte - 1) >> PAGE_SHIFT) + 1;
		if ((start + wc->w_num_pages) > end_index)
			wc->w_num_pages = end_index - start;
	} else {
		wc->w_num_pages = 1;
		start = target_index;
	}
	end_index = (user_pos + user_len - 1) >> PAGE_SHIFT;

	for(i = 0; i < wc->w_num_pages; i++) {
		index = start + i;

		if (index >= target_index && index <= end_index &&
		    wc->w_type == OCFS2_WRITE_MMAP) {
			/*
			 * ocfs2_pagemkwrite() is a little different
			 * and wants us to directly use the page
			 * passed in.
			 */
			lock_page(mmap_page);

			/* Exit and let the caller retry */
			if (mmap_page->mapping != mapping) {
				WARN_ON(mmap_page->mapping);
				unlock_page(mmap_page);
				ret = -EAGAIN;
				goto out;
			}

			get_page(mmap_page);
			wc->w_pages[i] = mmap_page;
			wc->w_target_locked = true;
		} else if (index >= target_index && index <= end_index &&
			   wc->w_type == OCFS2_WRITE_DIRECT) {
			/* Direct write has no mapping page. */
			wc->w_pages[i] = NULL;
			continue;
		} else {
			wc->w_pages[i] = find_or_create_page(mapping, index,
							     GFP_NOFS);
			if (!wc->w_pages[i]) {
				ret = -ENOMEM;
				mlog_errno(ret);
				goto out;
			}
		}
		wait_for_stable_page(wc->w_pages[i]);

		if (index == target_index)
			wc->w_target_page = wc->w_pages[i];
	}
out:
	if (ret)
		wc->w_target_locked = false;
	return ret;
}

/*
 * Prepare a single cluster for write one cluster into the file.
 */
static int ocfs2_write_cluster(struct address_space *mapping,
			       u32 *phys, unsigned int new,
			       unsigned int clear_unwritten,
			       unsigned int should_zero,
			       struct ocfs2_alloc_context *data_ac,
			       struct ocfs2_alloc_context *meta_ac,
			       struct ocfs2_write_ctxt *wc, u32 cpos,
			       loff_t user_pos, unsigned user_len)
{
	int ret, i;
	u64 p_blkno;
	struct inode *inode = mapping->host;
	struct ocfs2_extent_tree et;
	int bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1);

	if (new) {
		u32 tmp_pos;

		/*
		 * This is safe to call with the page locks - it won't take
		 * any additional semaphores or cluster locks.
		 */
		tmp_pos = cpos;
		ret = ocfs2_add_inode_data(OCFS2_SB(inode->i_sb), inode,
					   &tmp_pos, 1, !clear_unwritten,
					   wc->w_di_bh, wc->w_handle,
					   data_ac, meta_ac, NULL);
		/*
		 * This shouldn't happen because we must have already
		 * calculated the correct meta data allocation required. The
		 * internal tree allocation code should know how to increase
		 * transaction credits itself.
		 *
		 * If need be, we could handle -EAGAIN for a
		 * RESTART_TRANS here.
		 */
		mlog_bug_on_msg(ret == -EAGAIN,
				"Inode %llu: EAGAIN return during allocation.\n",
				(unsigned long long)OCFS2_I(inode)->ip_blkno);
		if (ret < 0) {
			mlog_errno(ret);
			goto out;
		}
	} else if (clear_unwritten) {
		ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode),
					      wc->w_di_bh);
		ret = ocfs2_mark_extent_written(inode, &et,
						wc->w_handle, cpos, 1, *phys,
						meta_ac, &wc->w_dealloc);
		if (ret < 0) {
			mlog_errno(ret);
			goto out;
		}
	}

	/*
	 * The only reason this should fail is due to an inability to
	 * find the extent added.
	 */
	ret = ocfs2_get_clusters(inode, cpos, phys, NULL, NULL);
	if (ret < 0) {
		mlog(ML_ERROR, "Get physical blkno failed for inode %llu, "
			    "at logical cluster %u",
			    (unsigned long long)OCFS2_I(inode)->ip_blkno, cpos);
		goto out;
	}

	BUG_ON(*phys == 0);

	p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, *phys);
	if (!should_zero)
		p_blkno += (user_pos >> inode->i_sb->s_blocksize_bits) & (u64)(bpc - 1);

	for(i = 0; i < wc->w_num_pages; i++) {
		int tmpret;

		/* This is the direct io target page. */
		if (wc->w_pages[i] == NULL) {
			p_blkno++;
			continue;
		}

		tmpret = ocfs2_prepare_page_for_write(inode, &p_blkno, wc,
						      wc->w_pages[i], cpos,
						      user_pos, user_len,
						      should_zero);
		if (tmpret) {
			mlog_errno(tmpret);
			if (ret == 0)
				ret = tmpret;
		}
	}

	/*
	 * We only have cleanup to do in case of allocating write.
	 */
	if (ret && new)
		ocfs2_write_failure(inode, wc, user_pos, user_len);

out:

	return ret;
}

static int ocfs2_write_cluster_by_desc(struct address_space *mapping,
				       struct ocfs2_alloc_context *data_ac,
				       struct ocfs2_alloc_context *meta_ac,
				       struct ocfs2_write_ctxt *wc,
				       loff_t pos, unsigned len)
{
	int ret, i;
	loff_t cluster_off;
	unsigned int local_len = len;
	struct ocfs2_write_cluster_desc *desc;
	struct ocfs2_super *osb = OCFS2_SB(mapping->host->i_sb);

	for (i = 0; i < wc->w_clen; i++) {
		desc = &wc->w_desc[i];

		/*
		 * We have to make sure that the total write passed in
		 * doesn't extend past a single cluster.
		 */
		local_len = len;
		cluster_off = pos & (osb->s_clustersize - 1);
		if ((cluster_off + local_len) > osb->s_clustersize)
			local_len = osb->s_clustersize - cluster_off;

		ret = ocfs2_write_cluster(mapping, &desc->c_phys,
					  desc->c_new,
					  desc->c_clear_unwritten,
					  desc->c_needs_zero,
					  data_ac, meta_ac,
					  wc, desc->c_cpos, pos, local_len);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		len -= local_len;
		pos += local_len;
	}

	ret = 0;
out:
	return ret;
}

/*
 * ocfs2_write_end() wants to know which parts of the target page it
 * should complete the write on. It's easiest to compute them ahead of
 * time when a more complete view of the write is available.
 */
static void ocfs2_set_target_boundaries(struct ocfs2_super *osb,
					struct ocfs2_write_ctxt *wc,
					loff_t pos, unsigned len, int alloc)
{
	struct ocfs2_write_cluster_desc *desc;

	wc->w_target_from = pos & (PAGE_SIZE - 1);
	wc->w_target_to = wc->w_target_from + len;

	if (alloc == 0)
		return;

	/*
	 * Allocating write - we may have different boundaries based
	 * on page size and cluster size.
	 *
	 * NOTE: We can no longer compute one value from the other as
	 * the actual write length and user provided length may be
	 * different.
	 */

	if (wc->w_large_pages) {
		/*
		 * We only care about the 1st and last cluster within
		 * our range and whether they should be zero'd or not. Either
		 * value may be extended out to the start/end of a
		 * newly allocated cluster.
		 */
		desc = &wc->w_desc[0];
		if (desc->c_needs_zero)
			ocfs2_figure_cluster_boundaries(osb,
							desc->c_cpos,
							&wc->w_target_from,
							NULL);

		desc = &wc->w_desc[wc->w_clen - 1];
		if (desc->c_needs_zero)
			ocfs2_figure_cluster_boundaries(osb,
							desc->c_cpos,
							NULL,
							&wc->w_target_to);
	} else {
		wc->w_target_from = 0;
		wc->w_target_to = PAGE_SIZE;
	}
}

/*
 * Check if this extent is marked UNWRITTEN by direct io. If so, we need not to
 * do the zero work. And should not to clear UNWRITTEN since it will be cleared
 * by the direct io procedure.
 * If this is a new extent that allocated by direct io, we should mark it in
 * the ip_unwritten_list.
 */
static int ocfs2_unwritten_check(struct inode *inode,
				 struct ocfs2_write_ctxt *wc,
				 struct ocfs2_write_cluster_desc *desc)
{
	struct ocfs2_inode_info *oi = OCFS2_I(inode);
	struct ocfs2_unwritten_extent *ue = NULL, *new = NULL;
	int ret = 0;

	if (!desc->c_needs_zero)
		return 0;

retry:
	spin_lock(&oi->ip_lock);
	/* Needs not to zero no metter buffer or direct. The one who is zero
	 * the cluster is doing zero. And he will clear unwritten after all
	 * cluster io finished. */
	list_for_each_entry(ue, &oi->ip_unwritten_list, ue_ip_node) {
		if (desc->c_cpos == ue->ue_cpos) {
			BUG_ON(desc->c_new);
			desc->c_needs_zero = 0;
			desc->c_clear_unwritten = 0;
			goto unlock;
		}
	}

	if (wc->w_type != OCFS2_WRITE_DIRECT)
		goto unlock;

	if (new == NULL) {
		spin_unlock(&oi->ip_lock);
		new = kmalloc(sizeof(struct ocfs2_unwritten_extent),
			     GFP_NOFS);
		if (new == NULL) {
			ret = -ENOMEM;
			goto out;
		}
		goto retry;
	}
	/* This direct write will doing zero. */
	new->ue_cpos = desc->c_cpos;
	new->ue_phys = desc->c_phys;
	desc->c_clear_unwritten = 0;
	list_add_tail(&new->ue_ip_node, &oi->ip_unwritten_list);
	list_add_tail(&new->ue_node, &wc->w_unwritten_list);
	wc->w_unwritten_count++;
	new = NULL;
unlock:
	spin_unlock(&oi->ip_lock);
out:
	kfree(new);
	return ret;
}

/*
 * Populate each single-cluster write descriptor in the write context
 * with information about the i/o to be done.
 *
 * Returns the number of clusters that will have to be allocated, as
 * well as a worst case estimate of the number of extent records that
 * would have to be created during a write to an unwritten region.
 */
static int ocfs2_populate_write_desc(struct inode *inode,
				     struct ocfs2_write_ctxt *wc,
				     unsigned int *clusters_to_alloc,
				     unsigned int *extents_to_split)
{
	int ret;
	struct ocfs2_write_cluster_desc *desc;
	unsigned int num_clusters = 0;
	unsigned int ext_flags = 0;
	u32 phys = 0;
	int i;

	*clusters_to_alloc = 0;
	*extents_to_split = 0;

	for (i = 0; i < wc->w_clen; i++) {
		desc = &wc->w_desc[i];
		desc->c_cpos = wc->w_cpos + i;

		if (num_clusters == 0) {
			/*
			 * Need to look up the next extent record.
			 */
			ret = ocfs2_get_clusters(inode, desc->c_cpos, &phys,
						 &num_clusters, &ext_flags);
			if (ret) {
				mlog_errno(ret);
				goto out;
			}

			/* We should already CoW the refcountd extent. */
			BUG_ON(ext_flags & OCFS2_EXT_REFCOUNTED);

			/*
			 * Assume worst case - that we're writing in
			 * the middle of the extent.
			 *
			 * We can assume that the write proceeds from
			 * left to right, in which case the extent
			 * insert code is smart enough to coalesce the
			 * next splits into the previous records created.
			 */
			if (ext_flags & OCFS2_EXT_UNWRITTEN)
				*extents_to_split = *extents_to_split + 2;
		} else if (phys) {
			/*
			 * Only increment phys if it doesn't describe
			 * a hole.
			 */
			phys++;
		}

		/*
		 * If w_first_new_cpos is < UINT_MAX, we have a non-sparse
		 * file that got extended.  w_first_new_cpos tells us
		 * where the newly allocated clusters are so we can
		 * zero them.
		 */
		if (desc->c_cpos >= wc->w_first_new_cpos) {
			BUG_ON(phys == 0);
			desc->c_needs_zero = 1;
		}

		desc->c_phys = phys;
		if (phys == 0) {
			desc->c_new = 1;
			desc->c_needs_zero = 1;
			desc->c_clear_unwritten = 1;
			*clusters_to_alloc = *clusters_to_alloc + 1;
		}

		if (ext_flags & OCFS2_EXT_UNWRITTEN) {
			desc->c_clear_unwritten = 1;
			desc->c_needs_zero = 1;
		}

		ret = ocfs2_unwritten_check(inode, wc, desc);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		num_clusters--;
	}

	ret = 0;
out:
	return ret;
}

static int ocfs2_write_begin_inline(struct address_space *mapping,
				    struct inode *inode,
				    struct ocfs2_write_ctxt *wc)
{
	int ret;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct page *page;
	handle_t *handle;
	struct ocfs2_dinode *di = (struct ocfs2_dinode *)wc->w_di_bh->b_data;

	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		mlog_errno(ret);
		goto out;
	}

	page = find_or_create_page(mapping, 0, GFP_NOFS);
	if (!page) {
		ocfs2_commit_trans(osb, handle);
		ret = -ENOMEM;
		mlog_errno(ret);
		goto out;
	}
	/*
	 * If we don't set w_num_pages then this page won't get unlocked
	 * and freed on cleanup of the write context.
	 */
	wc->w_pages[0] = wc->w_target_page = page;
	wc->w_num_pages = 1;

	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
				      OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		ocfs2_commit_trans(osb, handle);

		mlog_errno(ret);
		goto out;
	}

	if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL))
		ocfs2_set_inode_data_inline(inode, di);

	if (!PageUptodate(page)) {
		ret = ocfs2_read_inline_data(inode, page, wc->w_di_bh);
		if (ret) {
			ocfs2_commit_trans(osb, handle);

			goto out;
		}
	}

	wc->w_handle = handle;
out:
	return ret;
}

int ocfs2_size_fits_inline_data(struct buffer_head *di_bh, u64 new_size)
{
	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;

	if (new_size <= le16_to_cpu(di->id2.i_data.id_count))
		return 1;
	return 0;
}

static int ocfs2_try_to_write_inline_data(struct address_space *mapping,
					  struct inode *inode, loff_t pos,
					  unsigned len, struct page *mmap_page,
					  struct ocfs2_write_ctxt *wc)
{
	int ret, written = 0;
	loff_t end = pos + len;
	struct ocfs2_inode_info *oi = OCFS2_I(inode);
	struct ocfs2_dinode *di = NULL;

	trace_ocfs2_try_to_write_inline_data((unsigned long long)oi->ip_blkno,
					     len, (unsigned long long)pos,
					     oi->ip_dyn_features);

	/*
	 * Handle inodes which already have inline data 1st.
	 */
	if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
		if (mmap_page == NULL &&
		    ocfs2_size_fits_inline_data(wc->w_di_bh, end))
			goto do_inline_write;

		/*
		 * The write won't fit - we have to give this inode an
		 * inline extent list now.
		 */
		ret = ocfs2_convert_inline_data_to_extents(inode, wc->w_di_bh);
		if (ret)
			mlog_errno(ret);
		goto out;
	}

	/*
	 * Check whether the inode can accept inline data.
	 */
	if (oi->ip_clusters != 0 || i_size_read(inode) != 0)
		return 0;

	/*
	 * Check whether the write can fit.
	 */
	di = (struct ocfs2_dinode *)wc->w_di_bh->b_data;
	if (mmap_page ||
	    end > ocfs2_max_inline_data_with_xattr(inode->i_sb, di))
		return 0;

do_inline_write:
	ret = ocfs2_write_begin_inline(mapping, inode, wc);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	/*
	 * This signals to the caller that the data can be written
	 * inline.
	 */
	written = 1;
out:
	return written ? written : ret;
}

/*
 * This function only does anything for file systems which can't
 * handle sparse files.
 *
 * What we want to do here is fill in any hole between the current end
 * of allocation and the end of our write. That way the rest of the
 * write path can treat it as an non-allocating write, which has no
 * special case code for sparse/nonsparse files.
 */
static int ocfs2_expand_nonsparse_inode(struct inode *inode,
					struct buffer_head *di_bh,
					loff_t pos, unsigned len,
					struct ocfs2_write_ctxt *wc)
{
	int ret;
	loff_t newsize = pos + len;

	BUG_ON(ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)));

	if (newsize <= i_size_read(inode))
		return 0;

	ret = ocfs2_extend_no_holes(inode, di_bh, newsize, pos);
	if (ret)
		mlog_errno(ret);

	/* There is no wc if this is call from direct. */
	if (wc)
		wc->w_first_new_cpos =
			ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode));

	return ret;
}

static int ocfs2_zero_tail(struct inode *inode, struct buffer_head *di_bh,
			   loff_t pos)
{
	int ret = 0;

	BUG_ON(!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)));
	if (pos > i_size_read(inode))
		ret = ocfs2_zero_extend(inode, di_bh, pos);

	return ret;
}

int ocfs2_write_begin_nolock(struct address_space *mapping,
			     loff_t pos, unsigned len, ocfs2_write_type_t type,
			     struct page **pagep, void **fsdata,
			     struct buffer_head *di_bh, struct page *mmap_page)
{
	int ret, cluster_of_pages, credits = OCFS2_INODE_UPDATE_CREDITS;
	unsigned int clusters_to_alloc, extents_to_split, clusters_need = 0;
	struct ocfs2_write_ctxt *wc;
	struct inode *inode = mapping->host;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct ocfs2_dinode *di;
	struct ocfs2_alloc_context *data_ac = NULL;
	struct ocfs2_alloc_context *meta_ac = NULL;
	handle_t *handle;
	struct ocfs2_extent_tree et;
	int try_free = 1, ret1;

try_again:
	ret = ocfs2_alloc_write_ctxt(&wc, osb, pos, len, type, di_bh);
	if (ret) {
		mlog_errno(ret);
		return ret;
	}

	if (ocfs2_supports_inline_data(osb)) {
		ret = ocfs2_try_to_write_inline_data(mapping, inode, pos, len,
						     mmap_page, wc);
		if (ret == 1) {
			ret = 0;
			goto success;
		}
		if (ret < 0) {
			mlog_errno(ret);
			goto out;
		}
	}

	/* Direct io change i_size late, should not zero tail here. */
	if (type != OCFS2_WRITE_DIRECT) {
		if (ocfs2_sparse_alloc(osb))
			ret = ocfs2_zero_tail(inode, di_bh, pos);
		else
			ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,
							   len, wc);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}
	}

	ret = ocfs2_check_range_for_refcount(inode, pos, len);
	if (ret < 0) {
		mlog_errno(ret);
		goto out;
	} else if (ret == 1) {
		clusters_need = wc->w_clen;
		ret = ocfs2_refcount_cow(inode, di_bh,
					 wc->w_cpos, wc->w_clen, UINT_MAX);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}
	}

	ret = ocfs2_populate_write_desc(inode, wc, &clusters_to_alloc,
					&extents_to_split);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}
	clusters_need += clusters_to_alloc;

	di = (struct ocfs2_dinode *)wc->w_di_bh->b_data;

	trace_ocfs2_write_begin_nolock(
			(unsigned long long)OCFS2_I(inode)->ip_blkno,
			(long long)i_size_read(inode),
			le32_to_cpu(di->i_clusters),
			pos, len, type, mmap_page,
			clusters_to_alloc, extents_to_split);

	/*
	 * We set w_target_from, w_target_to here so that
	 * ocfs2_write_end() knows which range in the target page to
	 * write out. An allocation requires that we write the entire
	 * cluster range.
	 */
	if (clusters_to_alloc || extents_to_split) {
		/*
		 * XXX: We are stretching the limits of
		 * ocfs2_lock_allocators(). It greatly over-estimates
		 * the work to be done.
		 */
		ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode),
					      wc->w_di_bh);
		ret = ocfs2_lock_allocators(inode, &et,
					    clusters_to_alloc, extents_to_split,
					    &data_ac, &meta_ac);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}

		if (data_ac)
			data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv;

		credits = ocfs2_calc_extend_credits(inode->i_sb,
						    &di->id2.i_list);
	} else if (type == OCFS2_WRITE_DIRECT)
		/* direct write needs not to start trans if no extents alloc. */
		goto success;

	/*
	 * We have to zero sparse allocated clusters, unwritten extent clusters,
	 * and non-sparse clusters we just extended.  For non-sparse writes,
	 * we know zeros will only be needed in the first and/or last cluster.
	 */
	if (wc->w_clen && (wc->w_desc[0].c_needs_zero ||
			   wc->w_desc[wc->w_clen - 1].c_needs_zero))
		cluster_of_pages = 1;
	else
		cluster_of_pages = 0;

	ocfs2_set_target_boundaries(osb, wc, pos, len, cluster_of_pages);

	handle = ocfs2_start_trans(osb, credits);
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		mlog_errno(ret);
		goto out;
	}

	wc->w_handle = handle;

	if (clusters_to_alloc) {
		ret = dquot_alloc_space_nodirty(inode,
			ocfs2_clusters_to_bytes(osb->sb, clusters_to_alloc));
		if (ret)
			goto out_commit;
	}

	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
				      OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto out_quota;
	}

	/*
	 * Fill our page array first. That way we've grabbed enough so
	 * that we can zero and flush if we error after adding the
	 * extent.
	 */
	ret = ocfs2_grab_pages_for_write(mapping, wc, wc->w_cpos, pos, len,
					 cluster_of_pages, mmap_page);
	if (ret && ret != -EAGAIN) {
		mlog_errno(ret);
		goto out_quota;
	}

	/*
	 * ocfs2_grab_pages_for_write() returns -EAGAIN if it could not lock
	 * the target page. In this case, we exit with no error and no target
	 * page. This will trigger the caller, page_mkwrite(), to re-try
	 * the operation.
	 */
	if (ret == -EAGAIN) {
		BUG_ON(wc->w_target_page);
		ret = 0;
		goto out_quota;
	}

	ret = ocfs2_write_cluster_by_desc(mapping, data_ac, meta_ac, wc, pos,
					  len);
	if (ret) {
		mlog_errno(ret);
		goto out_quota;
	}

	if (data_ac)
		ocfs2_free_alloc_context(data_ac);
	if (meta_ac)
		ocfs2_free_alloc_context(meta_ac);

success:
	if (pagep)
		*pagep = wc->w_target_page;
	*fsdata = wc;
	return 0;
out_quota:
	if (clusters_to_alloc)
		dquot_free_space(inode,
			  ocfs2_clusters_to_bytes(osb->sb, clusters_to_alloc));
out_commit:
	ocfs2_commit_trans(osb, handle);

out:
	/*
	 * The mmapped page won't be unlocked in ocfs2_free_write_ctxt(),
	 * even in case of error here like ENOSPC and ENOMEM. So, we need
	 * to unlock the target page manually to prevent deadlocks when
	 * retrying again on ENOSPC, or when returning non-VM_FAULT_LOCKED
	 * to VM code.
	 */
	if (wc->w_target_locked)
		unlock_page(mmap_page);

	ocfs2_free_write_ctxt(inode, wc);

	if (data_ac) {
		ocfs2_free_alloc_context(data_ac);
		data_ac = NULL;
	}
	if (meta_ac) {
		ocfs2_free_alloc_context(meta_ac);
		meta_ac = NULL;
	}

	if (ret == -ENOSPC && try_free) {
		/*
		 * Try to free some truncate log so that we can have enough
		 * clusters to allocate.
		 */
		try_free = 0;

		ret1 = ocfs2_try_to_free_truncate_log(osb, clusters_need);
		if (ret1 == 1)
			goto try_again;

		if (ret1 < 0)
			mlog_errno(ret1);
	}

	return ret;
}

static int ocfs2_write_begin(struct file *file, struct address_space *mapping,
			     loff_t pos, unsigned len, unsigned flags,
			     struct page **pagep, void **fsdata)
{
	int ret;
	struct buffer_head *di_bh = NULL;
	struct inode *inode = mapping->host;

	ret = ocfs2_inode_lock(inode, &di_bh, 1);
	if (ret) {
		mlog_errno(ret);
		return ret;
	}

	/*
	 * Take alloc sem here to prevent concurrent lookups. That way
	 * the mapping, zeroing and tree manipulation within
	 * ocfs2_write() will be safe against ->readpage(). This
	 * should also serve to lock out allocation from a shared
	 * writeable region.
	 */
	down_write(&OCFS2_I(inode)->ip_alloc_sem);

	ret = ocfs2_write_begin_nolock(mapping, pos, len, OCFS2_WRITE_BUFFER,
				       pagep, fsdata, di_bh, NULL);
	if (ret) {
		mlog_errno(ret);
		goto out_fail;
	}

	brelse(di_bh);

	return 0;

out_fail:
	up_write(&OCFS2_I(inode)->ip_alloc_sem);

	brelse(di_bh);
	ocfs2_inode_unlock(inode, 1);

	return ret;
}

static void ocfs2_write_end_inline(struct inode *inode, loff_t pos,
				   unsigned len, unsigned *copied,
				   struct ocfs2_dinode *di,
				   struct ocfs2_write_ctxt *wc)
{
	void *kaddr;

	if (unlikely(*copied < len)) {
		if (!PageUptodate(wc->w_target_page)) {
			*copied = 0;
			return;
		}
	}

	kaddr = kmap_atomic(wc->w_target_page);
	memcpy(di->id2.i_data.id_data + pos, kaddr + pos, *copied);
	kunmap_atomic(kaddr);

	trace_ocfs2_write_end_inline(
	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
	     (unsigned long long)pos, *copied,
	     le16_to_cpu(di->id2.i_data.id_count),
	     le16_to_cpu(di->i_dyn_features));
}

int ocfs2_write_end_nolock(struct address_space *mapping,
			   loff_t pos, unsigned len, unsigned copied, void *fsdata)
{
	int i, ret;
	unsigned from, to, start = pos & (PAGE_SIZE - 1);
	struct inode *inode = mapping->host;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct ocfs2_write_ctxt *wc = fsdata;
	struct ocfs2_dinode *di = (struct ocfs2_dinode *)wc->w_di_bh->b_data;
	handle_t *handle = wc->w_handle;
	struct page *tmppage;

	BUG_ON(!list_empty(&wc->w_unwritten_list));

	if (handle) {
		ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode),
				wc->w_di_bh, OCFS2_JOURNAL_ACCESS_WRITE);
		if (ret) {
			copied = ret;
			mlog_errno(ret);
			goto out;
		}
	}

	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
		ocfs2_write_end_inline(inode, pos, len, &copied, di, wc);
		goto out_write_size;
	}

	if (unlikely(copied < len) && wc->w_target_page) {
		if (!PageUptodate(wc->w_target_page))
			copied = 0;

		ocfs2_zero_new_buffers(wc->w_target_page, start+copied,
				       start+len);
	}
	if (wc->w_target_page)
		flush_dcache_page(wc->w_target_page);

	for(i = 0; i < wc->w_num_pages; i++) {
		tmppage = wc->w_pages[i];

		/* This is the direct io target page. */
		if (tmppage == NULL)
			continue;

		if (tmppage == wc->w_target_page) {
			from = wc->w_target_from;
			to = wc->w_target_to;

			BUG_ON(from > PAGE_SIZE ||
			       to > PAGE_SIZE ||
			       to < from);
		} else {
			/*
			 * Pages adjacent to the target (if any) imply
			 * a hole-filling write in which case we want
			 * to flush their entire range.
			 */
			from = 0;
			to = PAGE_SIZE;
		}

		if (page_has_buffers(tmppage)) {
			if (handle && ocfs2_should_order_data(inode))
				ocfs2_jbd2_file_inode(handle, inode);
			block_commit_write(tmppage, from, to);
		}
	}

out_write_size:
	/* Direct io do not update i_size here. */
	if (wc->w_type != OCFS2_WRITE_DIRECT) {
		pos += copied;
		if (pos > i_size_read(inode)) {
			i_size_write(inode, pos);
			mark_inode_dirty(inode);
		}
		inode->i_blocks = ocfs2_inode_sector_count(inode);
		di->i_size = cpu_to_le64((u64)i_size_read(inode));
		inode->i_mtime = inode->i_ctime = current_time(inode);
		di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
		di->i_mtime_nsec = di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
		ocfs2_update_inode_fsync_trans(handle, inode, 1);
	}
	if (handle)
		ocfs2_journal_dirty(handle, wc->w_di_bh);

out:
	/* unlock pages before dealloc since it needs acquiring j_trans_barrier
	 * lock, or it will cause a deadlock since journal commit threads holds
	 * this lock and will ask for the page lock when flushing the data.
	 * put it here to preserve the unlock order.
	 */
	ocfs2_unlock_pages(wc);

	if (handle)
		ocfs2_commit_trans(osb, handle);

	ocfs2_run_deallocs(osb, &wc->w_dealloc);

	brelse(wc->w_di_bh);
	kfree(wc);

	return copied;
}

static int ocfs2_write_end(struct file *file, struct address_space *mapping,
			   loff_t pos, unsigned len, unsigned copied,
			   struct page *page, void *fsdata)
{
	int ret;
	struct inode *inode = mapping->host;

	ret = ocfs2_write_end_nolock(mapping, pos, len, copied, fsdata);

	up_write(&OCFS2_I(inode)->ip_alloc_sem);
	ocfs2_inode_unlock(inode, 1);

	return ret;
}

struct ocfs2_dio_write_ctxt {
	struct list_head	dw_zero_list;
	unsigned		dw_zero_count;
	int			dw_orphaned;
	pid_t			dw_writer_pid;
};

static struct ocfs2_dio_write_ctxt *
ocfs2_dio_alloc_write_ctx(struct buffer_head *bh, int *alloc)
{
	struct ocfs2_dio_write_ctxt *dwc = NULL;

	if (bh->b_private)
		return bh->b_private;

	dwc = kmalloc(sizeof(struct ocfs2_dio_write_ctxt), GFP_NOFS);
	if (dwc == NULL)
		return NULL;
	INIT_LIST_HEAD(&dwc->dw_zero_list);
	dwc->dw_zero_count = 0;
	dwc->dw_orphaned = 0;
	dwc->dw_writer_pid = task_pid_nr(current);
	bh->b_private = dwc;
	*alloc = 1;

	return dwc;
}

static void ocfs2_dio_free_write_ctx(struct inode *inode,
				     struct ocfs2_dio_write_ctxt *dwc)
{
	ocfs2_free_unwritten_list(inode, &dwc->dw_zero_list);
	kfree(dwc);
}

/*
 * TODO: Make this into a generic get_blocks function.
 *
 * From do_direct_io in direct-io.c:
 *  "So what we do is to permit the ->get_blocks function to populate
 *   bh.b_size with the size of IO which is permitted at this offset and
 *   this i_blkbits."
 *
 * This function is called directly from get_more_blocks in direct-io.c.
 *
 * called like this: dio->get_blocks(dio->inode, fs_startblk,
 * 					fs_count, map_bh, dio->rw == WRITE);
 */
static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock,
			       struct buffer_head *bh_result, int create)
{
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct ocfs2_inode_info *oi = OCFS2_I(inode);
	struct ocfs2_write_ctxt *wc;
	struct ocfs2_write_cluster_desc *desc = NULL;
	struct ocfs2_dio_write_ctxt *dwc = NULL;
	struct buffer_head *di_bh = NULL;
	u64 p_blkno;
	loff_t pos = iblock << inode->i_sb->s_blocksize_bits;
	unsigned len, total_len = bh_result->b_size;
	int ret = 0, first_get_block = 0;

	len = osb->s_clustersize - (pos & (osb->s_clustersize - 1));
	len = min(total_len, len);

	mlog(0, "get block of %lu at %llu:%u req %u\n",
			inode->i_ino, pos, len, total_len);

	/*
	 * Because we need to change file size in ocfs2_dio_end_io_write(), or
	 * we may need to add it to orphan dir. So can not fall to fast path
	 * while file size will be changed.
	 */
	if (pos + total_len <= i_size_read(inode)) {

		/* This is the fast path for re-write. */
		ret = ocfs2_lock_get_block(inode, iblock, bh_result, create);
		if (buffer_mapped(bh_result) &&
		    !buffer_new(bh_result) &&
		    ret == 0)
			goto out;

		/* Clear state set by ocfs2_get_block. */
		bh_result->b_state = 0;
	}

	dwc = ocfs2_dio_alloc_write_ctx(bh_result, &first_get_block);
	if (unlikely(dwc == NULL)) {
		ret = -ENOMEM;
		mlog_errno(ret);
		goto out;
	}

	if (ocfs2_clusters_for_bytes(inode->i_sb, pos + total_len) >
	    ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)) &&
	    !dwc->dw_orphaned) {
		/*
		 * when we are going to alloc extents beyond file size, add the
		 * inode to orphan dir, so we can recall those spaces when
		 * system crashed during write.
		 */
		ret = ocfs2_add_inode_to_orphan(osb, inode);
		if (ret < 0) {
			mlog_errno(ret);
			goto out;
		}
		dwc->dw_orphaned = 1;
	}

	ret = ocfs2_inode_lock(inode, &di_bh, 1);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	down_write(&oi->ip_alloc_sem);

	if (first_get_block) {
		if (ocfs2_sparse_alloc(osb))
			ret = ocfs2_zero_tail(inode, di_bh, pos);
		else
			ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,
							   total_len, NULL);
		if (ret < 0) {
			mlog_errno(ret);
			goto unlock;
		}
	}

	ret = ocfs2_write_begin_nolock(inode->i_mapping, pos, len,
				       OCFS2_WRITE_DIRECT, NULL,
				       (void **)&wc, di_bh, NULL);
	if (ret) {
		mlog_errno(ret);
		goto unlock;
	}

	desc = &wc->w_desc[0];

	p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, desc->c_phys);
	BUG_ON(p_blkno == 0);
	p_blkno += iblock & (u64)(ocfs2_clusters_to_blocks(inode->i_sb, 1) - 1);

	map_bh(bh_result, inode->i_sb, p_blkno);
	bh_result->b_size = len;
	if (desc->c_needs_zero)
		set_buffer_new(bh_result);

	/* May sleep in end_io. It should not happen in a irq context. So defer
	 * it to dio work queue. */
	set_buffer_defer_completion(bh_result);

	if (!list_empty(&wc->w_unwritten_list)) {
		struct ocfs2_unwritten_extent *ue = NULL;

		ue = list_first_entry(&wc->w_unwritten_list,
				      struct ocfs2_unwritten_extent,
				      ue_node);
		BUG_ON(ue->ue_cpos != desc->c_cpos);
		/* The physical address may be 0, fill it. */
		ue->ue_phys = desc->c_phys;

		list_splice_tail_init(&wc->w_unwritten_list, &dwc->dw_zero_list);
		dwc->dw_zero_count += wc->w_unwritten_count;
	}

	ret = ocfs2_write_end_nolock(inode->i_mapping, pos, len, len, wc);
	BUG_ON(ret != len);
	ret = 0;
unlock:
	up_write(&oi->ip_alloc_sem);
	ocfs2_inode_unlock(inode, 1);
	brelse(di_bh);
out:
	if (ret < 0)
		ret = -EIO;
	return ret;
}

static int ocfs2_dio_end_io_write(struct inode *inode,
				  struct ocfs2_dio_write_ctxt *dwc,
				  loff_t offset,
				  ssize_t bytes)
{
	struct ocfs2_cached_dealloc_ctxt dealloc;
	struct ocfs2_extent_tree et;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct ocfs2_inode_info *oi = OCFS2_I(inode);
	struct ocfs2_unwritten_extent *ue = NULL;
	struct buffer_head *di_bh = NULL;
	struct ocfs2_dinode *di;
	struct ocfs2_alloc_context *data_ac = NULL;
	struct ocfs2_alloc_context *meta_ac = NULL;
	handle_t *handle = NULL;
	loff_t end = offset + bytes;
	int ret = 0, credits = 0, locked = 0;

	ocfs2_init_dealloc_ctxt(&dealloc);

	/* We do clear unwritten, delete orphan, change i_size here. If neither
	 * of these happen, we can skip all this. */
	if (list_empty(&dwc->dw_zero_list) &&
	    end <= i_size_read(inode) &&
	    !dwc->dw_orphaned)
		goto out;

	/* ocfs2_file_write_iter will get i_mutex, so we need not lock if we
	 * are in that context. */
	if (dwc->dw_writer_pid != task_pid_nr(current)) {
		inode_lock(inode);
		locked = 1;
	}

	ret = ocfs2_inode_lock(inode, &di_bh, 1);
	if (ret < 0) {
		mlog_errno(ret);
		goto out;
	}

	down_write(&oi->ip_alloc_sem);

	/* Delete orphan before acquire i_mutex. */
	if (dwc->dw_orphaned) {
		BUG_ON(dwc->dw_writer_pid != task_pid_nr(current));

		end = end > i_size_read(inode) ? end : 0;

		ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh,
				!!end, end);
		if (ret < 0)
			mlog_errno(ret);
	}

	di = (struct ocfs2_dinode *)di_bh->b_data;

	ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh);

	/* Attach dealloc with extent tree in case that we may reuse extents
	 * which are already unlinked from current extent tree due to extent
	 * rotation and merging.
	 */
	et.et_dealloc = &dealloc;

	ret = ocfs2_lock_allocators(inode, &et, 0, dwc->dw_zero_count*2,
				    &data_ac, &meta_ac);
	if (ret) {
		mlog_errno(ret);
		goto unlock;
	}

	credits = ocfs2_calc_extend_credits(inode->i_sb, &di->id2.i_list);

	handle = ocfs2_start_trans(osb, credits);
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		mlog_errno(ret);
		goto unlock;
	}
	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
				      OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto commit;
	}

	list_for_each_entry(ue, &dwc->dw_zero_list, ue_node) {
		ret = ocfs2_mark_extent_written(inode, &et, handle,
						ue->ue_cpos, 1,
						ue->ue_phys,
						meta_ac, &dealloc);
		if (ret < 0) {
			mlog_errno(ret);
			break;
		}
	}

	if (end > i_size_read(inode)) {
		ret = ocfs2_set_inode_size(handle, inode, di_bh, end);
		if (ret < 0)
			mlog_errno(ret);
	}
commit:
	ocfs2_commit_trans(osb, handle);
unlock:
	up_write(&oi->ip_alloc_sem);
	ocfs2_inode_unlock(inode, 1);
	brelse(di_bh);
out:
	if (data_ac)
		ocfs2_free_alloc_context(data_ac);
	if (meta_ac)
		ocfs2_free_alloc_context(meta_ac);
	ocfs2_run_deallocs(osb, &dealloc);
	if (locked)
		inode_unlock(inode);
	ocfs2_dio_free_write_ctx(inode, dwc);

	return ret;
}

/*
 * ocfs2_dio_end_io is called by the dio core when a dio is finished.  We're
 * particularly interested in the aio/dio case.  We use the rw_lock DLM lock
 * to protect io on one node from truncation on another.
 */
static int ocfs2_dio_end_io(struct kiocb *iocb,
			    loff_t offset,
			    ssize_t bytes,
			    void *private)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	int level;
	int ret = 0;

	/* this io's submitter should not have unlocked this before we could */
	BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));

	if (bytes <= 0)
		mlog_ratelimited(ML_ERROR, "Direct IO failed, bytes = %lld",
				 (long long)bytes);
	if (private) {
		if (bytes > 0)
			ret = ocfs2_dio_end_io_write(inode, private, offset,
						     bytes);
		else
			ocfs2_dio_free_write_ctx(inode, private);
	}

	ocfs2_iocb_clear_rw_locked(iocb);

	level = ocfs2_iocb_rw_locked_level(iocb);
	ocfs2_rw_unlock(inode, level);
	return ret;
}

static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	get_block_t *get_block;

	/*
	 * Fallback to buffered I/O if we see an inode without
	 * extents.
	 */
	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
		return 0;

	/* Fallback to buffered I/O if we do not support append dio. */
	if (iocb->ki_pos + iter->count > i_size_read(inode) &&
	    !ocfs2_supports_append_dio(osb))
		return 0;

	if (iov_iter_rw(iter) == READ)
		get_block = ocfs2_lock_get_block;
	else
		get_block = ocfs2_dio_wr_get_block;

	return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
				    iter, get_block,
				    ocfs2_dio_end_io, NULL, 0);
}

const struct address_space_operations ocfs2_aops = {
	.readpage		= ocfs2_readpage,
	.readpages		= ocfs2_readpages,
	.writepage		= ocfs2_writepage,
	.write_begin		= ocfs2_write_begin,
	.write_end		= ocfs2_write_end,
	.bmap			= ocfs2_bmap,
	.direct_IO		= ocfs2_direct_IO,
	.invalidatepage		= block_invalidatepage,
	.releasepage		= ocfs2_releasepage,
	.migratepage		= buffer_migrate_page,
	.is_partially_uptodate	= block_is_partially_uptodate,
	.error_remove_page	= generic_error_remove_page,
};

Privacy Policy