aboutsummaryrefslogtreecommitdiffstats
path: root/fs/gfs2/bmap.c
blob: dec5285a02e9da456a23842f21999dd32c9dbd77 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
 */

#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>
#include <linux/iomap.h>
#include <linux/ktime.h>

#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "glock.h"
#include "inode.h"
#include "meta_io.h"
#include "quota.h"
#include "rgrp.h"
#include "log.h"
#include "super.h"
#include "trans.h"
#include "dir.h"
#include "util.h"
#include "aops.h"
#include "trace_gfs2.h"

/* This doesn't need to be that large as max 64 bit pointers in a 4k
 * block is 512, so __u16 is fine for that. It saves stack space to
 * keep it small.
 */
struct metapath {
	struct buffer_head *mp_bh[GFS2_MAX_META_HEIGHT];
	__u16 mp_list[GFS2_MAX_META_HEIGHT];
	int mp_fheight; /* find_metapath height */
	int mp_aheight; /* actual height (lookup height) */
};

static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length);

/**
 * gfs2_unstuffer_page - unstuff a stuffed inode into a block cached by a page
 * @ip: the inode
 * @dibh: the dinode buffer
 * @block: the block number that was allocated
 * @page: The (optional) page. This is looked up if @page is NULL
 *
 * Returns: errno
 */

static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
			       u64 block, struct page *page)
{
	struct inode *inode = &ip->i_inode;
	struct buffer_head *bh;
	int release = 0;

	if (!page || page->index) {
		page = find_or_create_page(inode->i_mapping, 0, GFP_NOFS);
		if (!page)
			return -ENOMEM;
		release = 1;
	}

	if (!PageUptodate(page)) {
		void *kaddr = kmap(page);
		u64 dsize = i_size_read(inode);
 
		if (dsize > gfs2_max_stuffed_size(ip))
			dsize = gfs2_max_stuffed_size(ip);

		memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize);
		memset(kaddr + dsize, 0, PAGE_SIZE - dsize);
		kunmap(page);

		SetPageUptodate(page);
	}

	if (!page_has_buffers(page))
		create_empty_buffers(page, BIT(inode->i_blkbits),
				     BIT(BH_Uptodate));

	bh = page_buffers(page);

	if (!buffer_mapped(bh))
		map_bh(bh, inode->i_sb, block);

	set_buffer_uptodate(bh);
	if (gfs2_is_jdata(ip))
		gfs2_trans_add_data(ip->i_gl, bh);
	else {
		mark_buffer_dirty(bh);
		gfs2_ordered_add_inode(ip);
	}

	if (release) {
		unlock_page(page);
		put_page(page);
	}

	return 0;
}

/**
 * gfs2_unstuff_dinode - Unstuff a dinode when the data has grown too big
 * @ip: The GFS2 inode to unstuff
 * @page: The (optional) page. This is looked up if the @page is NULL
 *
 * This routine unstuffs a dinode and returns it to a "normal" state such
 * that the height can be grown in the traditional way.
 *
 * Returns: errno
 */

int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page)
{
	struct buffer_head *bh, *dibh;
	struct gfs2_dinode *di;
	u64 block = 0;
	int isdir = gfs2_is_dir(ip);
	int error;

	down_write(&ip->i_rw_mutex);

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (error)
		goto out;

	if (i_size_read(&ip->i_inode)) {
		/* Get a free block, fill it with the stuffed data,
		   and write it out to disk */

		unsigned int n = 1;
		error = gfs2_alloc_blocks(ip, &block, &n, 0, NULL);
		if (error)
			goto out_brelse;
		if (isdir) {
			gfs2_trans_remove_revoke(GFS2_SB(&ip->i_inode), block, 1);
			error = gfs2_dir_get_new_buffer(ip, block, &bh);
			if (error)
				goto out_brelse;
			gfs2_buffer_copy_tail(bh, sizeof(struct gfs2_meta_header),
					      dibh, sizeof(struct gfs2_dinode));
			brelse(bh);
		} else {
			error = gfs2_unstuffer_page(ip, dibh, block, page);
			if (error)
				goto out_brelse;
		}
	}

	/*  Set up the pointer to the new block  */

	gfs2_trans_add_meta(ip->i_gl, dibh);
	di = (struct gfs2_dinode *)dibh->b_data;
	gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));

	if (i_size_read(&ip->i_inode)) {
		*(__be64 *)(di + 1) = cpu_to_be64(block);
		gfs2_add_inode_blocks(&ip->i_inode, 1);
		di->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode));
	}

	ip->i_height = 1;
	di->di_height = cpu_to_be16(1);

out_brelse:
	brelse(dibh);
out:
	up_write(&ip->i_rw_mutex);
	return error;
}


/**
 * find_metapath - Find path through the metadata tree
 * @sdp: The superblock
 * @block: The disk block to look up
 * @mp: The metapath to return the result in
 * @height: The pre-calculated height of the metadata tree
 *
 *   This routine returns a struct metapath structure that defines a path
 *   through the metadata of inode "ip" to get to block "block".
 *
 *   Example:
 *   Given:  "ip" is a height 3 file, "offset" is 101342453, and this is a
 *   filesystem with a blocksize of 4096.
 *
 *   find_metapath() would return a struct metapath structure set to:
 *   mp_fheight = 3, mp_list[0] = 0, mp_list[1] = 48, and mp_list[2] = 165.
 *
 *   That means that in order to get to the block containing the byte at
 *   offset 101342453, we would load the indirect block pointed to by pointer
 *   0 in the dinode.  We would then load the indirect block pointed to by
 *   pointer 48 in that indirect block.  We would then load the data block
 *   pointed to by pointer 165 in that indirect block.
 *
 *             ----------------------------------------
 *             | Dinode |                             |
 *             |        |                            4|
 *             |        |0 1 2 3 4 5                 9|
 *             |        |                            6|
 *             ----------------------------------------
 *                       |
 *                       |
 *                       V
 *             ----------------------------------------
 *             | Indirect Block                       |
 *             |                                     5|
 *             |            4 4 4 4 4 5 5            1|
 *             |0           5 6 7 8 9 0 1            2|
 *             ----------------------------------------
 *                                |
 *                                |
 *                                V
 *             ----------------------------------------
 *             | Indirect Block                       |
 *             |                         1 1 1 1 1   5|
 *             |                         6 6 6 6 6   1|
 *             |0                        3 4 5 6 7   2|
 *             ----------------------------------------
 *                                           |
 *                                           |
 *                                           V
 *             ----------------------------------------
 *             | Data block containing offset         |
 *             |            101342453                 |
 *             |                                      |
 *             |                                      |
 *             ----------------------------------------
 *
 */

static void find_metapath(const struct gfs2_sbd *sdp, u64 block,
			  struct metapath *mp, unsigned int height)
{
	unsigned int i;

	mp->mp_fheight = height;
	for (i = height; i--;)
		mp->mp_list[i] = do_div(block, sdp->sd_inptrs);
}

static inline unsigned int metapath_branch_start(const struct metapath *mp)
{
	if (mp->mp_list[0] == 0)
		return 2;
	return 1;
}

/**
 * metaptr1 - Return the first possible metadata pointer in a metapath buffer
 * @height: The metadata height (0 = dinode)
 * @mp: The metapath
 */
static inline __be64 *metaptr1(unsigned int height, const struct metapath *mp)
{
	struct buffer_head *bh = mp->mp_bh[height];
	if (height == 0)
		return ((__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)));
	return ((__be64 *)(bh->b_data + sizeof(struct gfs2_meta_header)));
}

/**
 * metapointer - Return pointer to start of metadata in a buffer
 * @height: The metadata height (0 = dinode)
 * @mp: The metapath
 *
 * Return a pointer to the block number of the next height of the metadata
 * tree given a buffer containing the pointer to the current height of the
 * metadata tree.
 */

static inline __be64 *metapointer(unsigned int height, const struct metapath *mp)
{
	__be64 *p = metaptr1(height, mp);
	return p + mp->mp_list[height];
}

static inline const __be64 *metaend(unsigned int height, const struct metapath *mp)
{
	const struct buffer_head *bh = mp->mp_bh[height];
	return (const __be64 *)(bh->b_data + bh->b_size);
}

static void clone_metapath(struct metapath *clone, struct metapath *mp)
{
	unsigned int hgt;

	*clone = *mp;
	for (hgt = 0; hgt < mp->mp_aheight; hgt++)
		get_bh(clone->mp_bh[hgt]);
}

static void gfs2_metapath_ra(struct gfs2_glock *gl, __be64 *start, __be64 *end)
{
	const __be64 *t;

	for (t = start; t < end; t++) {
		struct buffer_head *rabh;

		if (!*t)
			continue;

		rabh = gfs2_getbuf(gl, be64_to_cpu(*t), CREATE);
		if (trylock_buffer(rabh)) {
			if (!buffer_uptodate(rabh)) {
				rabh->b_end_io = end_buffer_read_sync;
				submit_bh(REQ_OP_READ,
					  REQ_RAHEAD | REQ_META | REQ_PRIO,
					  rabh);
				continue;
			}
			unlock_buffer(rabh);
		}
		brelse(rabh);
	}
}

static int __fillup_metapath(struct gfs2_inode *ip, struct metapath *mp,
			     unsigned int x, unsigned int h)
{
	for (; x < h; x++) {
		__be64 *ptr = metapointer(x, mp);
		u64 dblock = be64_to_cpu(*ptr);
		int ret;

		if (!dblock)
			break;
		ret = gfs2_meta_indirect_buffer(ip, x + 1, dblock, &mp->mp_bh[x + 1]);
		if (ret)
			return ret;
	}
	mp->mp_aheight = x + 1;
	return 0;
}

/**
 * lookup_metapath - Walk the metadata tree to a specific point
 * @ip: The inode
 * @mp: The metapath
 *
 * Assumes that the inode's buffer has already been looked up and
 * hooked onto mp->mp_bh[0] and that the metapath has been initialised
 * by find_metapath().
 *
 * If this function encounters part of the tree which has not been
 * allocated, it returns the current height of the tree at the point
 * at which it found the unallocated block. Blocks which are found are
 * added to the mp->mp_bh[] list.
 *
 * Returns: error
 */

static int lookup_metapath(struct gfs2_inode *ip, struct metapath *mp)
{
	return __fillup_metapath(ip, mp, 0, ip->i_height - 1);
}

/**
 * fillup_metapath - fill up buffers for the metadata path to a specific height
 * @ip: The inode
 * @mp: The metapath
 * @h: The height to which it should be mapped
 *
 * Similar to lookup_metapath, but does lookups for a range of heights
 *
 * Returns: error or the number of buffers filled
 */

static int fillup_metapath(struct gfs2_inode *ip, struct metapath *mp, int h)
{
	unsigned int x = 0;
	int ret;

	if (h) {
		/* find the first buffer we need to look up. */
		for (x = h - 1; x > 0; x--) {
			if (mp->mp_bh[x])
				break;
		}
	}
	ret = __fillup_metapath(ip, mp, x, h);
	if (ret)
		return ret;
	return mp->mp_aheight - x - 1;
}

static sector_t metapath_to_block(struct gfs2_sbd *sdp, struct metapath *mp)
{
	sector_t factor = 1, block = 0;
	int hgt;

	for (hgt = mp->mp_fheight - 1; hgt >= 0; hgt--) {
		if (hgt < mp->mp_aheight)
			block += mp->mp_list[hgt] * factor;
		factor *= sdp->sd_inptrs;
	}
	return block;
}

static void release_metapath(struct metapath *mp)
{
	int i;

	for (i = 0; i < GFS2_MAX_META_HEIGHT; i++) {
		if (mp->mp_bh[i] == NULL)
			break;
		brelse(mp->mp_bh[i]);
		mp->mp_bh[i] = NULL;
	}
}

/**
 * gfs2_extent_length - Returns length of an extent of blocks
 * @bh: The metadata block
 * @ptr: Current position in @bh
 * @limit: Max extent length to return
 * @eob: Set to 1 if we hit "end of block"
 *
 * Returns: The length of the extent (minimum of one block)
 */

static inline unsigned int gfs2_extent_length(struct buffer_head *bh, __be64 *ptr, size_t limit, int *eob)
{
	const __be64 *end = (__be64 *)(bh->b_data + bh->b_size);
	const __be64 *first = ptr;
	u64 d = be64_to_cpu(*ptr);

	*eob = 0;
	do {
		ptr++;
		if (ptr >= end)
			break;
		d++;
	} while(be64_to_cpu(*ptr) == d);
	if (ptr >= end)
		*eob = 1;
	return ptr - first;
}

enum walker_status { WALK_STOP, WALK_FOLLOW, WALK_CONTINUE };

/*
 * gfs2_metadata_walker - walk an indirect block
 * @mp: Metapath to indirect block
 * @ptrs: Number of pointers to look at
 *
 * When returning WALK_FOLLOW, the walker must update @mp to point at the right
 * indirect block to follow.
 */
typedef enum walker_status (*gfs2_metadata_walker)(struct metapath *mp,
						   unsigned int ptrs);

/*
 * gfs2_walk_metadata - walk a tree of indirect blocks
 * @inode: The inode
 * @mp: Starting point of walk
 * @max_len: Maximum number of blocks to walk
 * @walker: Called during the walk
 *
 * Returns 1 if the walk was stopped by @walker, 0 if we went past @max_len or
 * past the end of metadata, and a negative error code otherwise.
 */

static int gfs2_walk_metadata(struct inode *inode, struct metapath *mp,
		u64 max_len, gfs2_metadata_walker walker)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	u64 factor = 1;
	unsigned int hgt;
	int ret;

	/*
	 * The walk starts in the lowest allocated indirect block, which may be
	 * before the position indicated by @mp.  Adjust @max_len accordingly
	 * to avoid a short walk.
	 */
	for (hgt = mp->mp_fheight - 1; hgt >= mp->mp_aheight; hgt--) {
		max_len += mp->mp_list[hgt] * factor;
		mp->mp_list[hgt] = 0;
		factor *= sdp->sd_inptrs;
	}

	for (;;) {
		u16 start = mp->mp_list[hgt];
		enum walker_status status;
		unsigned int ptrs;
		u64 len;

		/* Walk indirect block. */
		ptrs = (hgt >= 1 ? sdp->sd_inptrs : sdp->sd_diptrs) - start;
		len = ptrs * factor;
		if (len > max_len)
			ptrs = DIV_ROUND_UP_ULL(max_len, factor);
		status = walker(mp, ptrs);
		switch (status) {
		case WALK_STOP:
			return 1;
		case WALK_FOLLOW:
			BUG_ON(mp->mp_aheight == mp->mp_fheight);
			ptrs = mp->mp_list[hgt] - start;
			len = ptrs * factor;
			break;
		case WALK_CONTINUE:
			break;
		}
		if (len >= max_len)
			break;
		max_len -= len;
		if (status == WALK_FOLLOW)
			goto fill_up_metapath;

lower_metapath:
		/* Decrease height of metapath. */
		brelse(mp->mp_bh[hgt]);
		mp->mp_bh[hgt] = NULL;
		mp->mp_list[hgt] = 0;
		if (!hgt)
			break;
		hgt--;
		factor *= sdp->sd_inptrs;

		/* Advance in metadata tree. */
		(mp->mp_list[hgt])++;
		if (hgt) {
			if (mp->mp_list[hgt] >= sdp->sd_inptrs)
				goto lower_metapath;
		} else {
			if (mp->mp_list[hgt] >= sdp->sd_diptrs)
				break;
		}

fill_up_metapath:
		/* Increase height of metapath. */
		ret = fillup_metapath(ip, mp, ip->i_height - 1);
		if (ret < 0)
			return ret;
		hgt += ret;
		for (; ret; ret--)
			do_div(factor, sdp->sd_inptrs);
		mp->mp_aheight = hgt + 1;
	}
	return 0;
}

static enum walker_status gfs2_hole_walker(struct metapath *mp,
					   unsigned int ptrs)
{
	const __be64 *start, *ptr, *end;
	unsigned int hgt;

	hgt = mp->mp_aheight - 1;
	start = metapointer(hgt, mp);
	end = start + ptrs;

	for (ptr = start; ptr < end; ptr++) {
		if (*ptr) {
			mp->mp_list[hgt] += ptr - start;
			if (mp->mp_aheight == mp->mp_fheight)
				return WALK_STOP;
			return WALK_FOLLOW;
		}
	}
	return WALK_CONTINUE;
}

/**
 * gfs2_hole_size - figure out the size of a hole
 * @inode: The inode
 * @lblock: The logical starting block number
 * @len: How far to look (in blocks)
 * @mp: The metapath at lblock
 * @iomap: The iomap to store the hole size in
 *
 * This function modifies @mp.
 *
 * Returns: errno on error
 */
static int gfs2_hole_size(struct inode *inode, sector_t lblock, u64 len,
			  struct metapath *mp, struct iomap *iomap)
{
	struct metapath clone;
	u64 hole_size;
	int ret;

	clone_metapath(&clone, mp);
	ret = gfs2_walk_metadata(inode, &clone, len, gfs2_hole_walker);
	if (ret < 0)
		goto out;

	if (ret == 1)
		hole_size = metapath_to_block(GFS2_SB(inode), &clone) - lblock;
	else
		hole_size = len;
	iomap->length = hole_size << inode->i_blkbits;
	ret = 0;

out:
	release_metapath(&clone);
	return ret;
}

static inline __be64 *gfs2_indirect_init(struct metapath *mp,
					 struct gfs2_glock *gl, unsigned int i,
					 unsigned offset, u64 bn)
{
	__be64 *ptr = (__be64 *)(mp->mp_bh[i - 1]->b_data +
		       ((i > 1) ? sizeof(struct gfs2_meta_header) :
				 sizeof(struct gfs2_dinode)));
	BUG_ON(i < 1);
	BUG_ON(mp->mp_bh[i] != NULL);
	mp->mp_bh[i] = gfs2_meta_new(gl, bn);
	gfs2_trans_add_meta(gl, mp->mp_bh[i]);
	gfs2_metatype_set(mp->mp_bh[i], GFS2_METATYPE_IN, GFS2_FORMAT_IN);
	gfs2_buffer_clear_tail(mp->mp_bh[i], sizeof(struct gfs2_meta_header));
	ptr += offset;
	*ptr = cpu_to_be64(bn);
	return ptr;
}

enum alloc_state {
	ALLOC_DATA = 0,
	ALLOC_GROW_DEPTH = 1,
	ALLOC_GROW_HEIGHT = 2,
	/* ALLOC_UNSTUFF = 3,   TBD and rather complicated */
};

/**
 * gfs2_iomap_alloc - Build a metadata tree of the requested height
 * @inode: The GFS2 inode
 * @iomap: The iomap structure
 * @mp: The metapath, with proper height information calculated
 *
 * In this routine we may have to alloc:
 *   i) Indirect blocks to grow the metadata tree height
 *  ii) Indirect blocks to fill in lower part of the metadata tree
 * iii) Data blocks
 *
 * This function is called after gfs2_iomap_get, which works out the
 * total number of blocks which we need via gfs2_alloc_size.
 *
 * We then do the actual allocation asking for an extent at a time (if
 * enough contiguous free blocks are available, there will only be one
 * allocation request per call) and uses the state machine to initialise
 * the blocks in order.
 *
 * Right now, this function will allocate at most one indirect block
 * worth of data -- with a default block size of 4K, that's slightly
 * less than 2M.  If this limitation is ever removed to allow huge
 * allocations, we would probably still want to limit the iomap size we
 * return to avoid stalling other tasks during huge writes; the next
 * iomap iteration would then find the blocks already allocated.
 *
 * Returns: errno on error
 */

static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
			    struct metapath *mp)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	struct buffer_head *dibh = mp->mp_bh[0];
	u64 bn;
	unsigned n, i, blks, alloced = 0, iblks = 0, branch_start = 0;
	size_t dblks = iomap->length >> inode->i_blkbits;
	const unsigned end_of_metadata = mp->mp_fheight - 1;
	int ret;
	enum alloc_state state;
	__be64 *ptr;
	__be64 zero_bn = 0;

	BUG_ON(mp->mp_aheight < 1);
	BUG_ON(dibh == NULL);
	BUG_ON(dblks < 1);

	gfs2_trans_add_meta(ip->i_gl, dibh);

	down_write(&ip->i_rw_mutex);

	if (mp->mp_fheight == mp->mp_aheight) {
		/* Bottom indirect block exists */
		state = ALLOC_DATA;
	} else {
		/* Need to allocate indirect blocks */
		if (mp->mp_fheight == ip->i_height) {
			/* Writing into existing tree, extend tree down */
			iblks = mp->mp_fheight - mp->mp_aheight;
			state = ALLOC_GROW_DEPTH;
		} else {
			/* Building up tree height */
			state = ALLOC_GROW_HEIGHT;
			iblks = mp->mp_fheight - ip->i_height;
			branch_start = metapath_branch_start(mp);
			iblks += (mp->mp_fheight - branch_start);
		}
	}

	/* start of the second part of the function (state machine) */

	blks = dblks + iblks;
	i = mp->mp_aheight;
	do {
		n = blks - alloced;
		ret = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL);
		if (ret)
			goto out;
		alloced += n;
		if (state != ALLOC_DATA || gfs2_is_jdata(ip))
			gfs2_trans_remove_revoke(sdp, bn, n);
		switch (state) {
		/* Growing height of tree */
		case ALLOC_GROW_HEIGHT:
			if (i == 1) {
				ptr = (__be64 *)(dibh->b_data +
						 sizeof(struct gfs2_dinode));
				zero_bn = *ptr;
			}
			for (; i - 1 < mp->mp_fheight - ip->i_height && n > 0;
			     i++, n--)
				gfs2_indirect_init(mp, ip->i_gl, i, 0, bn++);
			if (i - 1 == mp->mp_fheight - ip->i_height) {
				i--;
				gfs2_buffer_copy_tail(mp->mp_bh[i],
						sizeof(struct gfs2_meta_header),
						dibh, sizeof(struct gfs2_dinode));
				gfs2_buffer_clear_tail(dibh,
						sizeof(struct gfs2_dinode) +
						sizeof(__be64));
				ptr = (__be64 *)(mp->mp_bh[i]->b_data +
					sizeof(struct gfs2_meta_header));
				*ptr = zero_bn;
				state = ALLOC_GROW_DEPTH;
				for(i = branch_start; i < mp->mp_fheight; i++) {
					if (mp->mp_bh[i] == NULL)
						break;
					brelse(mp->mp_bh[i]);
					mp->mp_bh[i] = NULL;
				}
				i = branch_start;
			}
			if (n == 0)
				break;
		/* fall through - To branching from existing tree */
		case ALLOC_GROW_DEPTH:
			if (i > 1 && i < mp->mp_fheight)
				gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[i-1]);
			for (; i < mp->mp_fheight && n > 0; i++, n--)
				gfs2_indirect_init(mp, ip->i_gl, i,
						   mp->mp_list[i-1], bn++);
			if (i == mp->mp_fheight)
				state = ALLOC_DATA;
			if (n == 0)
				break;
		/* fall through - To tree complete, adding data blocks */
		case ALLOC_DATA:
			BUG_ON(n > dblks);
			BUG_ON(mp->mp_bh[end_of_metadata] == NULL);
			gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[end_of_metadata]);
			dblks = n;
			ptr = metapointer(end_of_metadata, mp);
			iomap->addr = bn << inode->i_blkbits;
			iomap->flags |= IOMAP_F_MERGED | IOMAP_F_NEW;
			while (n-- > 0)
				*ptr++ = cpu_to_be64(bn++);
			break;
		}
	} while (iomap->addr == IOMAP_NULL_ADDR);

	iomap->type = IOMAP_MAPPED;
	iomap->length = (u64)dblks << inode->i_blkbits;
	ip->i_height = mp->mp_fheight;
	gfs2_add_inode_blocks(&ip->i_inode, alloced);
	gfs2_dinode_out(ip, dibh->b_data);
out:
	up_write(&ip->i_rw_mutex);
	return ret;
}

#define IOMAP_F_GFS2_BOUNDARY IOMAP_F_PRIVATE

/**
 * gfs2_alloc_size - Compute the maximum allocation size
 * @inode: The inode
 * @mp: The metapath
 * @size: Requested size in blocks
 *
 * Compute the maximum size of the next allocation at @mp.
 *
 * Returns: size in blocks
 */
static u64 gfs2_alloc_size(struct inode *inode, struct metapath *mp, u64 size)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	const __be64 *first, *ptr, *end;

	/*
	 * For writes to stuffed files, this function is called twice via
	 * gfs2_iomap_get, before and after unstuffing. The size we return the
	 * first time needs to be large enough to get the reservation and
	 * allocation sizes right.  The size we return the second time must
	 * be exact or else gfs2_iomap_alloc won't do the right thing.
	 */

	if (gfs2_is_stuffed(ip) || mp->mp_fheight != mp->mp_aheight) {
		unsigned int maxsize = mp->mp_fheight > 1 ?
			sdp->sd_inptrs : sdp->sd_diptrs;
		maxsize -= mp->mp_list[mp->mp_fheight - 1];
		if (size > maxsize)
			size = maxsize;
		return size;
	}

	first = metapointer(ip->i_height - 1, mp);
	end = metaend(ip->i_height - 1, mp);
	if (end - first > size)
		end = first + size;
	for (ptr = first; ptr < end; ptr++) {
		if (*ptr)
			break;
	}
	return ptr - first;
}

/**
 * gfs2_iomap_get - Map blocks from an inode to disk blocks
 * @inode: The inode
 * @pos: Starting position in bytes
 * @length: Length to map, in bytes
 * @flags: iomap flags
 * @iomap: The iomap structure
 * @mp: The metapath
 *
 * Returns: errno
 */
static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
			  unsigned flags, struct iomap *iomap,
			  struct metapath *mp)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	loff_t size = i_size_read(inode);
	__be64 *ptr;
	sector_t lblock;
	sector_t lblock_stop;
	int ret;
	int eob;
	u64 len;
	struct buffer_head *dibh = NULL, *bh;
	u8 height;

	if (!length)
		return -EINVAL;

	down_read(&ip->i_rw_mutex);

	ret = gfs2_meta_inode_buffer(ip, &dibh);
	if (ret)
		goto unlock;
	mp->mp_bh[0] = dibh;

	if (gfs2_is_stuffed(ip)) {
		if (flags & IOMAP_WRITE) {
			loff_t max_size = gfs2_max_stuffed_size(ip);

			if (pos + length > max_size)
				goto unstuff;
			iomap->length = max_size;
		} else {
			if (pos >= size) {
				if (flags & IOMAP_REPORT) {
					ret = -ENOENT;
					goto unlock;
				} else {
					iomap->offset = pos;
					iomap->length = length;
					goto hole_found;
				}
			}
			iomap->length = size;
		}
		iomap->addr = (ip->i_no_addr << inode->i_blkbits) +
			      sizeof(struct gfs2_dinode);
		iomap->type = IOMAP_INLINE;
		iomap->inline_data = dibh->b_data + sizeof(struct gfs2_dinode);
		goto out;
	}

unstuff:
	lblock = pos >> inode->i_blkbits;
	iomap->offset = lblock << inode->i_blkbits;
	lblock_stop = (pos + length - 1) >> inode->i_blkbits;
	len = lblock_stop - lblock + 1;
	iomap->length = len << inode->i_blkbits;

	height = ip->i_height;
	while ((lblock + 1) * sdp->sd_sb.sb_bsize > sdp->sd_heightsize[height])
		height++;
	find_metapath(sdp, lblock, mp, height);
	if (height > ip->i_height || gfs2_is_stuffed(ip))
		goto do_alloc;

	ret = lookup_metapath(ip, mp);
	if (ret)
		goto unlock;

	if (mp->mp_aheight != ip->i_height)
		goto do_alloc;

	ptr = metapointer(ip->i_height - 1, mp);
	if (*ptr == 0)
		goto do_alloc;

	bh = mp->mp_bh[ip->i_height - 1];
	len = gfs2_extent_length(bh, ptr, len, &eob);

	iomap->addr = be64_to_cpu(*ptr) << inode->i_blkbits;
	iomap->length = len << inode->i_blkbits;
	iomap->type = IOMAP_MAPPED;
	iomap->flags |= IOMAP_F_MERGED;
	if (eob)
		iomap->flags |= IOMAP_F_GFS2_BOUNDARY;

out:
	iomap->bdev = inode->i_sb->s_bdev;
unlock:
	up_read(&ip->i_rw_mutex);
	return ret;

do_alloc:
	if (flags & IOMAP_REPORT) {
		if (pos >= size)
			ret = -ENOENT;
		else if (height == ip->i_height)
			ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
		else
			iomap->length = size - iomap->offset;
	} else if (flags & IOMAP_WRITE) {
		u64 alloc_size;

		if (flags & IOMAP_DIRECT)
			goto out;  /* (see gfs2_file_direct_write) */

		len = gfs2_alloc_size(inode, mp, len);
		alloc_size = len << inode->i_blkbits;
		if (alloc_size < iomap->length)
			iomap->length = alloc_size;
	} else {
		if (pos < size && height == ip->i_height)
			ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
	}
hole_found:
	iomap->addr = IOMAP_NULL_ADDR;
	iomap->type = IOMAP_HOLE;
	goto out;
}

/**
 * gfs2_lblk_to_dblk - convert logical block to disk block
 * @inode: the inode of the file we're mapping
 * @lblock: the block relative to the start of the file
 * @dblock: the returned dblock, if no error
 *
 * This function maps a single block from a file logical block (relative to
 * the start of the file) to a file system absolute block using iomap.
 *
 * Returns: the absolute file system block, or an error
 */
int gfs2_lblk_to_dblk(struct inode *inode, u32 lblock, u64 *dblock)
{
	struct iomap iomap = { };
	struct metapath mp = { .mp_aheight = 1, };
	loff_t pos = (loff_t)lblock << inode->i_blkbits;
	int ret;

	ret = gfs2_iomap_get(inode, pos, i_blocksize(inode), 0, &iomap, &mp);
	release_metapath(&mp);
	if (ret == 0)
		*dblock = iomap.addr >> inode->i_blkbits;

	return ret;
}

static int gfs2_write_lock(struct inode *inode)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	int error;

	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
	error = gfs2_glock_nq(&ip->i_gh);
	if (error)
		goto out_uninit;
	if (&ip->i_inode == sdp->sd_rindex) {
		struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);

		error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE,
					   GL_NOCACHE, &m_ip->i_gh);
		if (error)
			goto out_unlock;
	}
	return 0;

out_unlock:
	gfs2_glock_dq(&ip->i_gh);
out_uninit:
	gfs2_holder_uninit(&ip->i_gh);
	return error;
}

static void gfs2_write_unlock(struct inode *inode)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);

	if (&ip->i_inode == sdp->sd_rindex) {
		struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);

		gfs2_glock_dq_uninit(&m_ip->i_gh);
	}
	gfs2_glock_dq_uninit(&ip->i_gh);
}

static int gfs2_iomap_page_prepare(struct inode *inode, loff_t pos,
				   unsigned len, struct iomap *iomap)
{
	unsigned int blockmask = i_blocksize(inode) - 1;
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	unsigned int blocks;

	blocks = ((pos & blockmask) + len + blockmask) >> inode->i_blkbits;
	return gfs2_trans_begin(sdp, RES_DINODE + blocks, 0);
}

static void gfs2_iomap_page_done(struct inode *inode, loff_t pos,
				 unsigned copied, struct page *page,
				 struct iomap *iomap)
{
	struct gfs2_trans *tr = current->journal_info;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);

	if (page && !gfs2_is_stuffed(ip))
		gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);

	if (tr->tr_num_buf_new)
		__mark_inode_dirty(inode, I_DIRTY_DATASYNC);

	gfs2_trans_end(sdp);
}

static const struct iomap_page_ops gfs2_iomap_page_ops = {
	.page_prepare = gfs2_iomap_page_prepare,
	.page_done = gfs2_iomap_page_done,
};

static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
				  loff_t length, unsigned flags,
				  struct iomap *iomap,
				  struct metapath *mp)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	bool unstuff;
	int ret;

	unstuff = gfs2_is_stuffed(ip) &&
		  pos + length > gfs2_max_stuffed_size(ip);

	if (unstuff || iomap->type == IOMAP_HOLE) {
		unsigned int data_blocks, ind_blocks;
		struct gfs2_alloc_parms ap = {};
		unsigned int rblocks;
		struct gfs2_trans *tr;

		gfs2_write_calc_reserv(ip, iomap->length, &data_blocks,
				       &ind_blocks);
		ap.target = data_blocks + ind_blocks;
		ret = gfs2_quota_lock_check(ip, &ap);
		if (ret)
			return ret;

		ret = gfs2_inplace_reserve(ip, &ap);
		if (ret)
			goto out_qunlock;

		rblocks = RES_DINODE + ind_blocks;
		if (gfs2_is_jdata(ip))
			rblocks += data_blocks;
		if (ind_blocks || data_blocks)
			rblocks += RES_STATFS + RES_QUOTA;
		if (inode == sdp->sd_rindex)
			rblocks += 2 * RES_STATFS;
		rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks);

		ret = gfs2_trans_begin(sdp, rblocks,
				       iomap->length >> inode->i_blkbits);
		if (ret)
			goto out_trans_fail;

		if (unstuff) {
			ret = gfs2_unstuff_dinode(ip, NULL);
			if (ret)
				goto out_trans_end;
			release_metapath(mp);
			ret = gfs2_iomap_get(inode, iomap->offset,
					     iomap->length, flags, iomap, mp);
			if (ret)
				goto out_trans_end;
		}

		if (iomap->type == IOMAP_HOLE) {
			ret = gfs2_iomap_alloc(inode, iomap, mp);
			if (ret) {
				gfs2_trans_end(sdp);
				gfs2_inplace_release(ip);
				punch_hole(ip, iomap->offset, iomap->length);
				goto out_qunlock;
			}
		}

		tr = current->journal_info;
		if (tr->tr_num_buf_new)
			__mark_inode_dirty(inode, I_DIRTY_DATASYNC);

		gfs2_trans_end(sdp);
	}

	if (gfs2_is_stuffed(ip) || gfs2_is_jdata(ip))
		iomap->page_ops = &gfs2_iomap_page_ops;
	return 0;

out_trans_end:
	gfs2_trans_end(sdp);
out_trans_fail:
	gfs2_inplace_release(ip);
out_qunlock:
	gfs2_quota_unlock(ip);
	return ret;
}

static inline bool gfs2_iomap_need_write_lock(unsigned flags)
{
	return (flags & IOMAP_WRITE) && !(flags & IOMAP_DIRECT);
}

static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
			    unsigned flags, struct iomap *iomap)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct metapath mp = { .mp_aheight = 1, };
	int ret;

	iomap->flags |= IOMAP_F_BUFFER_HEAD;

	trace_gfs2_iomap_start(ip, pos, length, flags);
	if (gfs2_iomap_need_write_lock(flags)) {
		ret = gfs2_write_lock(inode);
		if (ret)
			goto out;
	}

	ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
	if (ret)
		goto out_unlock;

	switch(flags & (IOMAP_WRITE | IOMAP_ZERO)) {
	case IOMAP_WRITE:
		if (flags & IOMAP_DIRECT) {
			/*
			 * Silently fall back to buffered I/O for stuffed files
			 * or if we've got a hole (see gfs2_file_direct_write).
			 */
			if (iomap->type != IOMAP_MAPPED)
				ret = -ENOTBLK;
			goto out_unlock;
		}
		break;
	case IOMAP_ZERO:
		if (iomap->type == IOMAP_HOLE)
			goto out_unlock;
		break;
	default:
		goto out_unlock;
	}

	ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap, &mp);

out_unlock:
	if (ret && gfs2_iomap_need_write_lock(flags))
		gfs2_write_unlock(inode);
	release_metapath(&mp);
out:
	trace_gfs2_iomap_end(ip, iomap, ret);
	return ret;
}

static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length,
			  ssize_t written, unsigned flags, struct iomap *iomap)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);

	switch (flags & (IOMAP_WRITE | IOMAP_ZERO)) {
	case IOMAP_WRITE:
		if (flags & IOMAP_DIRECT)
			return 0;
		break;
	case IOMAP_ZERO:
		 if (iomap->type == IOMAP_HOLE)
			 return 0;
		 break;
	default:
		 return 0;
	}

	if (!gfs2_is_stuffed(ip))
		gfs2_ordered_add_inode(ip);

	if (inode == sdp->sd_rindex)
		adjust_fs_space(inode);

	gfs2_inplace_release(ip);

	if (ip->i_qadata && ip->i_qadata->qa_qd_num)
		gfs2_quota_unlock(ip);

	if (length != written && (iomap->flags & IOMAP_F_NEW)) {
		/* Deallocate blocks that were just allocated. */
		loff_t blockmask = i_blocksize(inode) - 1;
		loff_t end = (pos + length) & ~blockmask;

		pos = (pos + written + blockmask) & ~blockmask;
		if (pos < end) {
			truncate_pagecache_range(inode, pos, end - 1);
			punch_hole(ip, pos, end - pos);
		}
	}

	if (unlikely(!written))
		goto out_unlock;

	if (iomap->flags & IOMAP_F_SIZE_CHANGED)
		mark_inode_dirty(inode);
	set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);

out_unlock:
	if (gfs2_iomap_need_write_lock(flags))
		gfs2_write_unlock(inode);
	return 0;
}

const struct iomap_ops gfs2_iomap_ops = {
	.iomap_begin = gfs2_iomap_begin,
	.iomap_end = gfs2_iomap_end,
};

/**
 * gfs2_block_map - Map one or more blocks of an inode to a disk block
 * @inode: The inode
 * @lblock: The logical block number
 * @bh_map: The bh to be mapped
 * @create: True if its ok to alloc blocks to satify the request
 *
 * The size of the requested mapping is defined in bh_map->b_size.
 *
 * Clears buffer_mapped(bh_map) and leaves bh_map->b_size unchanged
 * when @lblock is not mapped.  Sets buffer_mapped(bh_map) and
 * bh_map->b_size to indicate the size of the mapping when @lblock and
 * successive blocks are mapped, up to the requested size.
 *
 * Sets buffer_boundary() if a read of metadata will be required
 * before the next block can be mapped. Sets buffer_new() if new
 * blocks were allocated.
 *
 * Returns: errno
 */

int gfs2_block_map(struct inode *inode, sector_t lblock,
		   struct buffer_head *bh_map, int create)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	loff_t pos = (loff_t)lblock << inode->i_blkbits;
	loff_t length = bh_map->b_size;
	struct metapath mp = { .mp_aheight = 1, };
	struct iomap iomap = { };
	int ret;

	clear_buffer_mapped(bh_map);
	clear_buffer_new(bh_map);
	clear_buffer_boundary(bh_map);
	trace_gfs2_bmap(ip, bh_map, lblock, create, 1);

	if (create) {
		ret = gfs2_iomap_get(inode, pos, length, IOMAP_WRITE, &iomap, &mp);
		if (!ret && iomap.type == IOMAP_HOLE)
			ret = gfs2_iomap_alloc(inode, &iomap, &mp);
		release_metapath(&mp);
	} else {
		ret = gfs2_iomap_get(inode, pos, length, 0, &iomap, &mp);
		release_metapath(&mp);
	}
	if (ret)
		goto out;

	if (iomap.length > bh_map->b_size) {
		iomap.length = bh_map->b_size;
		iomap.flags &= ~IOMAP_F_GFS2_BOUNDARY;
	}
	if (iomap.addr != IOMAP_NULL_ADDR)
		map_bh(bh_map, inode->i_sb, iomap.addr >> inode->i_blkbits);
	bh_map->b_size = iomap.length;
	if (iomap.flags & IOMAP_F_GFS2_BOUNDARY)
		set_buffer_boundary(bh_map);
	if (iomap.flags & IOMAP_F_NEW)
		set_buffer_new(bh_map);

out:
	trace_gfs2_bmap(ip, bh_map, lblock, create, ret);
	return ret;
}

/*
 * Deprecated: do not use in new code
 */
int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsigned *extlen)
{
	struct buffer_head bh = { .b_state = 0, .b_blocknr = 0 };
	int ret;
	int create = *new;

	BUG_ON(!extlen);
	BUG_ON(!dblock);
	BUG_ON(!new);

	bh.b_size = BIT(inode->i_blkbits + (create ? 0 : 5));
	ret = gfs2_block_map(inode, lblock, &bh, create);
	*extlen = bh.b_size >> inode->i_blkbits;
	*dblock = bh.b_blocknr;
	if (buffer_new(&bh))
		*new = 1;
	else
		*new = 0;
	return ret;
}

/*
 * NOTE: Never call gfs2_block_zero_range with an open transaction because it
 * uses iomap write to perform its actions, which begin their own transactions
 * (iomap_begin, page_prepare, etc.)
 */
static int gfs2_block_zero_range(struct inode *inode, loff_t from,
				 unsigned int length)
{
	BUG_ON(current->journal_info);
	return iomap_zero_range(inode, from, length, NULL, &gfs2_iomap_ops);
}

#define GFS2_JTRUNC_REVOKES 8192

/**
 * gfs2_journaled_truncate - Wrapper for truncate_pagecache for jdata files
 * @inode: The inode being truncated
 * @oldsize: The original (larger) size
 * @newsize: The new smaller size
 *
 * With jdata files, we have to journal a revoke for each block which is
 * truncated. As a result, we need to split this into separate transactions
 * if the number of pages being truncated gets too large.
 */

static int gfs2_journaled_truncate(struct inode *inode, u64 oldsize, u64 newsize)
{
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	u64 max_chunk = GFS2_JTRUNC_REVOKES * sdp->sd_vfs->s_blocksize;
	u64 chunk;
	int error;

	while (oldsize != newsize) {
		struct gfs2_trans *tr;
		unsigned int offs;

		chunk = oldsize - newsize;
		if (chunk > max_chunk)
			chunk = max_chunk;

		offs = oldsize & ~PAGE_MASK;
		if (offs && chunk > PAGE_SIZE)
			chunk = offs + ((chunk - offs) & PAGE_MASK);

		truncate_pagecache(inode, oldsize - chunk);
		oldsize -= chunk;

		tr = current->journal_info;
		if (!test_bit(TR_TOUCHED, &tr->tr_flags))
			continue;

		gfs2_trans_end(sdp);
		error = gfs2_trans_begin(sdp, RES_DINODE, GFS2_JTRUNC_REVOKES);
		if (error)
			return error;
	}

	return 0;
}

static int trunc_start(struct inode *inode, u64 newsize)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	struct buffer_head *dibh = NULL;
	int journaled = gfs2_is_jdata(ip);
	u64 oldsize = inode->i_size;
	int error;

	if (!gfs2_is_stuffed(ip)) {
		unsigned int blocksize = i_blocksize(inode);
		unsigned int offs = newsize & (blocksize - 1);
		if (offs) {
			error = gfs2_block_zero_range(inode, newsize,
						      blocksize - offs);
			if (error)
				return error;
		}
	}
	if (journaled)
		error = gfs2_trans_begin(sdp, RES_DINODE + RES_JDATA, GFS2_JTRUNC_REVOKES);
	else
		error = gfs2_trans_begin(sdp, RES_DINODE, 0);
	if (error)
		return error;

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (error)
		goto out;

	gfs2_trans_add_meta(ip->i_gl, dibh);

	if (gfs2_is_stuffed(ip))
		gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode) + newsize);
	else
		ip->i_diskflags |= GFS2_DIF_TRUNC_IN_PROG;

	i_size_write(inode, newsize);
	ip->i_inode.i_mtime = ip->i_inode.i_ctime = current_time(&ip->i_inode);
	gfs2_dinode_out(ip, dibh->b_data);

	if (journaled)
		error = gfs2_journaled_truncate(inode, oldsize, newsize);
	else
		truncate_pagecache(inode, newsize);

out:
	brelse(dibh);
	if (current->journal_info)
		gfs2_trans_end(sdp);
	return error;
}

int gfs2_iomap_get_alloc(struct inode *inode, loff_t pos, loff_t length,
			 struct iomap *iomap)
{
	struct metapath mp = { .mp_aheight = 1, };
	int ret;

	ret = gfs2_iomap_get(inode, pos, length, IOMAP_WRITE, iomap, &mp);
	if (!ret && iomap->type == IOMAP_HOLE)
		ret = gfs2_iomap_alloc(inode, iomap, &mp);
	release_metapath(&mp);
	return ret;
}

/**
 * sweep_bh_for_rgrps - find an rgrp in a meta buffer and free blocks therein
 * @ip: inode
 * @rg_gh: holder of resource group glock
 * @bh: buffer head to sweep
 * @start: starting point in bh
 * @end: end point in bh
 * @meta: true if bh points to metadata (rather than data)
 * @btotal: place to keep count of total blocks freed
 *
 * We sweep a metadata buffer (provided by the metapath) for blocks we need to
 * free, and free them all. However, we do it one rgrp at a time. If this
 * block has references to multiple rgrps, we break it into individual
 * transactions. This allows other processes to use the rgrps while we're
 * focused on a single one, for better concurrency / performance.
 * At every transaction boundary, we rewrite the inode into the journal.
 * That way the bitmaps are kept consistent with the inode and we can recover
 * if we're interrupted by power-outages.
 *
 * Returns: 0, or return code if an error occurred.
 *          *btotal has the total number of blocks freed
 */
static int sweep_bh_for_rgrps(struct gfs2_inode *ip, struct gfs2_holder *rd_gh,
			      struct buffer_head *bh, __be64 *start, __be64 *end,
			      bool meta, u32 *btotal)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct gfs2_rgrpd *rgd;
	struct gfs2_trans *tr;
	__be64 *p;
	int blks_outside_rgrp;
	u64 bn, bstart, isize_blks;
	s64 blen; /* needs to be s64 or gfs2_add_inode_blocks breaks */
	int ret = 0;
	bool buf_in_tr = false; /* buffer was added to transaction */

more_rgrps:
	rgd = NULL;
	if (gfs2_holder_initialized(rd_gh)) {
		rgd = gfs2_glock2rgrp(rd_gh->gh_gl);
		gfs2_assert_withdraw(sdp,
			     gfs2_glock_is_locked_by_me(rd_gh->gh_gl));
	}
	blks_outside_rgrp = 0;
	bstart = 0;
	blen = 0;

	for (p = start; p < end; p++) {
		if (!*p)
			continue;
		bn = be64_to_cpu(*p);

		if (rgd) {
			if (!rgrp_contains_block(rgd, bn)) {
				blks_outside_rgrp++;
				continue;
			}
		} else {
			rgd = gfs2_blk2rgrpd(sdp, bn, true);
			if (unlikely(!rgd)) {
				ret = -EIO;
				goto out;
			}
			ret = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE,
						 0, rd_gh);
			if (ret)
				goto out;

			/* Must be done with the rgrp glock held: */
			if (gfs2_rs_active(&ip->i_res) &&
			    rgd == ip->i_res.rs_rbm.rgd)
				gfs2_rs_deltree(&ip->i_res);
		}

		/* The size of our transactions will be unknown until we
		   actually process all the metadata blocks that relate to
		   the rgrp. So we estimate. We know it can't be more than
		   the dinode's i_blocks and we don't want to exceed the
		   journal flush threshold, sd_log_thresh2. */
		if (current->journal_info == NULL) {
			unsigned int jblocks_rqsted, revokes;

			jblocks_rqsted = rgd->rd_length + RES_DINODE +
				RES_INDIRECT;
			isize_blks = gfs2_get_inode_blocks(&ip->i_inode);
			if (isize_blks > atomic_read(&sdp->sd_log_thresh2))
				jblocks_rqsted +=
					atomic_read(&sdp->sd_log_thresh2);
			else
				jblocks_rqsted += isize_blks;
			revokes = jblocks_rqsted;
			if (meta)
				revokes += end - start;
			else if (ip->i_depth)
				revokes += sdp->sd_inptrs;
			ret = gfs2_trans_begin(sdp, jblocks_rqsted, revokes);
			if (ret)
				goto out_unlock;
			down_write(&ip->i_rw_mutex);
		}
		/* check if we will exceed the transaction blocks requested */
		tr = current->journal_info;
		if (tr->tr_num_buf_new + RES_STATFS +
		    RES_QUOTA >= atomic_read(&sdp->sd_log_thresh2)) {
			/* We set blks_outside_rgrp to ensure the loop will
			   be repeated for the same rgrp, but with a new
			   transaction. */
			blks_outside_rgrp++;
			/* This next part is tricky. If the buffer was added
			   to the transaction, we've already set some block
			   pointers to 0, so we better follow through and free
			   them, or we will introduce corruption (so break).
			   This may be impossible, or at least rare, but I
			   decided to cover the case regardless.

			   If the buffer was not added to the transaction
			   (this call), doing so would exceed our transaction
			   size, so we need to end the transaction and start a
			   new one (so goto). */

			if (buf_in_tr)
				break;
			goto out_unlock;
		}

		gfs2_trans_add_meta(ip->i_gl, bh);
		buf_in_tr = true;
		*p = 0;
		if (bstart + blen == bn) {
			blen++;
			continue;
		}
		if (bstart) {
			__gfs2_free_blocks(ip, rgd, bstart, (u32)blen, meta);
			(*btotal) += blen;
			gfs2_add_inode_blocks(&ip->i_inode, -blen);
		}
		bstart = bn;
		blen = 1;
	}
	if (bstart) {
		__gfs2_free_blocks(ip, rgd, bstart, (u32)blen, meta);
		(*btotal) += blen;
		gfs2_add_inode_blocks(&ip->i_inode, -blen);
	}
out_unlock:
	if (!ret && blks_outside_rgrp) { /* If buffer still has non-zero blocks
					    outside the rgrp we just processed,
					    do it all over again. */
		if (current->journal_info) {
			struct buffer_head *dibh;

			ret = gfs2_meta_inode_buffer(ip, &dibh);
			if (ret)
				goto out;

			/* Every transaction boundary, we rewrite the dinode
			   to keep its di_blocks current in case of failure. */
			ip->i_inode.i_mtime = ip->i_inode.i_ctime =
				current_time(&ip->i_inode);
			gfs2_trans_add_meta(ip->i_gl, dibh);
			gfs2_dinode_out(ip, dibh->b_data);
			brelse(dibh);
			up_write(&ip->i_rw_mutex);
			gfs2_trans_end(sdp);
			buf_in_tr = false;
		}
		gfs2_glock_dq_uninit(rd_gh);
		cond_resched();
		goto more_rgrps;
	}
out:
	return ret;
}

static bool mp_eq_to_hgt(struct metapath *mp, __u16 *list, unsigned int h)
{
	if (memcmp(mp->mp_list, list, h * sizeof(mp->mp_list[0])))
		return false;
	return true;
}

/**
 * find_nonnull_ptr - find a non-null pointer given a metapath and height
 * @mp: starting metapath
 * @h: desired height to search
 *
 * Assumes the metapath is valid (with buffers) out to height h.
 * Returns: true if a non-null pointer was found in the metapath buffer
 *          false if all remaining pointers are NULL in the buffer
 */
static bool find_nonnull_ptr(struct gfs2_sbd *sdp, struct metapath *mp,
			     unsigned int h,
			     __u16 *end_list, unsigned int end_aligned)
{
	struct buffer_head *bh = mp->mp_bh[h];
	__be64 *first, *ptr, *end;

	first = metaptr1(h, mp);
	ptr = first + mp->mp_list[h];
	end = (__be64 *)(bh->b_data + bh->b_size);
	if (end_list && mp_eq_to_hgt(mp, end_list, h)) {
		bool keep_end = h < end_aligned;
		end = first + end_list[h] + keep_end;
	}

	while (ptr < end) {
		if (*ptr) { /* if we have a non-null pointer */
			mp->mp_list[h] = ptr - first;
			h++;
			if (h < GFS2_MAX_META_HEIGHT)
				mp->mp_list[h] = 0;
			return true;
		}
		ptr++;
	}
	return false;
}

enum dealloc_states {
	DEALLOC_MP_FULL = 0,    /* Strip a metapath with all buffers read in */
	DEALLOC_MP_LOWER = 1,   /* lower the metapath strip height */
	DEALLOC_FILL_MP = 2,  /* Fill in the metapath to the given height. */
	DEALLOC_DONE = 3,       /* process complete */
};

static inline void
metapointer_range(struct metapath *mp, int height,
		  __u16 *start_list, unsigned int start_aligned,
		  __u16 *end_list, unsigned int end_aligned,
		  __be64 **start, __be64 **end)
{
	struct buffer_head *bh = mp->mp_bh[height];
	__be64 *first;

	first = metaptr1(height, mp);
	*start = first;
	if (mp_eq_to_hgt(mp, start_list, height)) {
		bool keep_start = height < start_aligned;
		*start = first + start_list[height] + keep_start;
	}
	*end = (__be64 *)(bh->b_data + bh->b_size);
	if (end_list && mp_eq_to_hgt(mp, end_list, height)) {
		bool keep_end = height < end_aligned;
		*end = first + end_list[height] + keep_end;
	}
}

static inline bool walk_done(struct gfs2_sbd *sdp,
			     struct metapath *mp, int height,
			     __u16 *end_list, unsigned int end_aligned)
{
	__u16 end;

	if (end_list) {
		bool keep_end = height < end_aligned;
		if (!mp_eq_to_hgt(mp, end_list, height))
			return false;
		end = end_list[height] + keep_end;
	} else
		end = (height > 0) ? sdp->sd_inptrs : sdp->sd_diptrs;
	return mp->mp_list[height] >= end;
}

/**
 * punch_hole - deallocate blocks in a file
 * @ip: inode to truncate
 * @offset: the start of the hole
 * @length: the size of the hole (or 0 for truncate)
 *
 * Punch a hole into a file or truncate a file at a given position.  This
 * function operates in whole blocks (@offset and @length are rounded
 * accordingly); partially filled blocks must be cleared otherwise.
 *
 * This function works from the bottom up, and from the right to the left. In
 * other words, it strips off the highest layer (data) before stripping any of
 * the metadata. Doing it this way is best in case the operation is interrupted
 * by power failure, etc.  The dinode is rewritten in every transaction to
 * guarantee integrity.
 */
static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	u64 maxsize = sdp->sd_heightsize[ip->i_height];
	struct metapath mp = {};
	struct buffer_head *dibh, *bh;
	struct gfs2_holder rd_gh;
	unsigned int bsize_shift = sdp->sd_sb.sb_bsize_shift;
	u64 lblock = (offset + (1 << bsize_shift) - 1) >> bsize_shift;
	__u16 start_list[GFS2_MAX_META_HEIGHT];
	__u16 __end_list[GFS2_MAX_META_HEIGHT], *end_list = NULL;
	unsigned int start_aligned, uninitialized_var(end_aligned);
	unsigned int strip_h = ip->i_height - 1;
	u32 btotal = 0;
	int ret, state;
	int mp_h; /* metapath buffers are read in to this height */
	u64 prev_bnr = 0;
	__be64 *start, *end;

	if (offset >= maxsize) {
		/*
		 * The starting point lies beyond the allocated meta-data;
		 * there are no blocks do deallocate.
		 */
		return 0;
	}

	/*
	 * The start position of the hole is defined by lblock, start_list, and
	 * start_aligned.  The end position of the hole is defined by lend,
	 * end_list, and end_aligned.
	 *
	 * start_aligned and end_aligned define down to which height the start
	 * and end positions are aligned to the metadata tree (i.e., the
	 * position is a multiple of the metadata granularity at the height
	 * above).  This determines at which heights additional meta pointers
	 * needs to be preserved for the remaining data.
	 */

	if (length) {
		u64 end_offset = offset + length;
		u64 lend;

		/*
		 * Clip the end at the maximum file size for the given height:
		 * that's how far the metadata goes; files bigger than that
		 * will have additional layers of indirection.
		 */
		if (end_offset > maxsize)
			end_offset = maxsize;
		lend = end_offset >> bsize_shift;

		if (lblock >= lend)
			return 0;

		find_metapath(sdp, lend, &mp, ip->i_height);
		end_list = __end_list;
		memcpy(end_list, mp.mp_list, sizeof(mp.mp_list));

		for (mp_h = ip->i_height - 1; mp_h > 0; mp_h--) {
			if (end_list[mp_h])
				break;
		}
		end_aligned = mp_h;
	}

	find_metapath(sdp, lblock, &mp, ip->i_height);
	memcpy(start_list, mp.mp_list, sizeof(start_list));

	for (mp_h = ip->i_height - 1; mp_h > 0; mp_h--) {
		if (start_list[mp_h])
			break;
	}
	start_aligned = mp_h;

	ret = gfs2_meta_inode_buffer(ip, &dibh);
	if (ret)
		return ret;

	mp.mp_bh[0] = dibh;
	ret = lookup_metapath(ip, &mp);
	if (ret)
		goto out_metapath;

	/* issue read-ahead on metadata */
	for (mp_h = 0; mp_h < mp.mp_aheight - 1; mp_h++) {
		metapointer_range(&mp, mp_h, start_list, start_aligned,
				  end_list, end_aligned, &start, &end);
		gfs2_metapath_ra(ip->i_gl, start, end);
	}

	if (mp.mp_aheight == ip->i_height)
		state = DEALLOC_MP_FULL; /* We have a complete metapath */
	else
		state = DEALLOC_FILL_MP; /* deal with partial metapath */

	ret = gfs2_rindex_update(sdp);
	if (ret)
		goto out_metapath;

	ret = gfs2_quota_hold(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
	if (ret)
		goto out_metapath;
	gfs2_holder_mark_uninitialized(&rd_gh);

	mp_h = strip_h;

	while (state != DEALLOC_DONE) {
		switch (state) {
		/* Truncate a full metapath at the given strip height.
		 * Note that strip_h == mp_h in order to be in this state. */
		case DEALLOC_MP_FULL:
			bh = mp.mp_bh[mp_h];
			gfs2_assert_withdraw(sdp, bh);
			if (gfs2_assert_withdraw(sdp,
						 prev_bnr != bh->b_blocknr)) {
				fs_emerg(sdp, "inode %llu, block:%llu, i_h:%u,"
					 "s_h:%u, mp_h:%u\n",
				       (unsigned long long)ip->i_no_addr,
				       prev_bnr, ip->i_height, strip_h, mp_h);
			}
			prev_bnr = bh->b_blocknr;

			if (gfs2_metatype_check(sdp, bh,
						(mp_h ? GFS2_METATYPE_IN :
							GFS2_METATYPE_DI))) {
				ret = -EIO;
				goto out;
			}

			/*
			 * Below, passing end_aligned as 0 gives us the
			 * metapointer range excluding the end point: the end
			 * point is the first metapath we must not deallocate!
			 */

			metapointer_range(&mp, mp_h, start_list, start_aligned,
					  end_list, 0 /* end_aligned */,
					  &start, &end);
			ret = sweep_bh_for_rgrps(ip, &rd_gh, mp.mp_bh[mp_h],
						 start, end,
						 mp_h != ip->i_height - 1,
						 &btotal);

			/* If we hit an error or just swept dinode buffer,
			   just exit. */
			if (ret || !mp_h) {
				state = DEALLOC_DONE;
				break;
			}
			state = DEALLOC_MP_LOWER;
			break;

		/* lower the metapath strip height */
		case DEALLOC_MP_LOWER:
			/* We're done with the current buffer, so release it,
			   unless it's the dinode buffer. Then back up to the
			   previous pointer. */
			if (mp_h) {
				brelse(mp.mp_bh[mp_h]);
				mp.mp_bh[mp_h] = NULL;
			}
			/* If we can't get any lower in height, we've stripped
			   off all we can. Next step is to back up and start
			   stripping the previous level of metadata. */
			if (mp_h == 0) {
				strip_h--;
				memcpy(mp.mp_list, start_list, sizeof(start_list));
				mp_h = strip_h;
				state = DEALLOC_FILL_MP;
				break;
			}
			mp.mp_list[mp_h] = 0;
			mp_h--; /* search one metadata height down */
			mp.mp_list[mp_h]++;
			if (walk_done(sdp, &mp, mp_h, end_list, end_aligned))
				break;
			/* Here we've found a part of the metapath that is not
			 * allocated. We need to search at that height for the
			 * next non-null pointer. */
			if (find_nonnull_ptr(sdp, &mp, mp_h, end_list, end_aligned)) {
				state = DEALLOC_FILL_MP;
				mp_h++;
			}
			/* No more non-null pointers at this height. Back up
			   to the previous height and try again. */
			break; /* loop around in the same state */

		/* Fill the metapath with buffers to the given height. */
		case DEALLOC_FILL_MP:
			/* Fill the buffers out to the current height. */
			ret = fillup_metapath(ip, &mp, mp_h);
			if (ret < 0)
				goto out;

			/* On the first pass, issue read-ahead on metadata. */
			if (mp.mp_aheight > 1 && strip_h == ip->i_height - 1) {
				unsigned int height = mp.mp_aheight - 1;

				/* No read-ahead for data blocks. */
				if (mp.mp_aheight - 1 == strip_h)
					height--;

				for (; height >= mp.mp_aheight - ret; height--) {
					metapointer_range(&mp, height,
							  start_list, start_aligned,
							  end_list, end_aligned,
							  &start, &end);
					gfs2_metapath_ra(ip->i_gl, start, end);
				}
			}

			/* If buffers found for the entire strip height */
			if (mp.mp_aheight - 1 == strip_h) {
				state = DEALLOC_MP_FULL;
				break;
			}
			if (mp.mp_aheight < ip->i_height) /* We have a partial height */
				mp_h = mp.mp_aheight - 1;

			/* If we find a non-null block pointer, crawl a bit
			   higher up in the metapath and try again, otherwise
			   we need to look lower for a new starting point. */
			if (find_nonnull_ptr(sdp, &mp, mp_h, end_list, end_aligned))
				mp_h++;
			else
				state = DEALLOC_MP_LOWER;
			break;
		}
	}

	if (btotal) {
		if (current->journal_info == NULL) {
			ret = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS +
					       RES_QUOTA, 0);
			if (ret)
				goto out;
			down_write(&ip->i_rw_mutex);
		}
		gfs2_statfs_change(sdp, 0, +btotal, 0);
		gfs2_quota_change(ip, -(s64)btotal, ip->i_inode.i_uid,
				  ip->i_inode.i_gid);
		ip->i_inode.i_mtime = ip->i_inode.i_ctime = current_time(&ip->i_inode);
		gfs2_trans_add_meta(ip->i_gl, dibh);
		gfs2_dinode_out(ip, dibh->b_data);
		up_write(&ip->i_rw_mutex);
		gfs2_trans_end(sdp);
	}

out:
	if (gfs2_holder_initialized(&rd_gh))
		gfs2_glock_dq_uninit(&rd_gh);
	if (current->journal_info) {
		up_write(&ip->i_rw_mutex);
		gfs2_trans_end(sdp);
		cond_resched();
	}
	gfs2_quota_unhold(ip);
out_metapath:
	release_metapath(&mp);
	return ret;
}

static int trunc_end(struct gfs2_inode *ip)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct buffer_head *dibh;
	int error;

	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
	if (error)
		return error;

	down_write(&ip->i_rw_mutex);

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (error)
		goto out;

	if (!i_size_read(&ip->i_inode)) {
		ip->i_height = 0;
		ip->i_goal = ip->i_no_addr;
		gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
		gfs2_ordered_del_inode(ip);
	}
	ip->i_inode.i_mtime = ip->i_inode.i_ctime = current_time(&ip->i_inode);
	ip->i_diskflags &= ~GFS2_DIF_TRUNC_IN_PROG;

	gfs2_trans_add_meta(ip->i_gl, dibh);
	gfs2_dinode_out(ip, dibh->b_data);
	brelse(dibh);

out:
	up_write(&ip->i_rw_mutex);
	gfs2_trans_end(sdp);
	return error;
}

/**
 * do_shrink - make a file smaller
 * @inode: the inode
 * @newsize: the size to make the file
 *
 * Called with an exclusive lock on @inode. The @size must
 * be equal to or smaller than the current inode size.
 *
 * Returns: errno
 */

static int do_shrink(struct inode *inode, u64 newsize)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	int error;

	error = trunc_start(inode, newsize);
	if (error < 0)
		return error;
	if (gfs2_is_stuffed(ip))
		return 0;

	error = punch_hole(ip, newsize, 0);
	if (error == 0)
		error = trunc_end(ip);

	return error;
}

void gfs2_trim_blocks(struct inode *inode)
{
	int ret;

	ret = do_shrink(inode, inode->i_size);
	WARN_ON(ret != 0);
}

/**
 * do_grow - Touch and update inode size
 * @inode: The inode
 * @size: The new size
 *
 * This function updates the timestamps on the inode and
 * may also increase the size of the inode. This function
 * must not be called with @size any smaller than the current
 * inode size.
 *
 * Although it is not strictly required to unstuff files here,
 * earlier versions of GFS2 have a bug in the stuffed file reading
 * code which will result in a buffer overrun if the size is larger
 * than the max stuffed file size. In order to prevent this from
 * occurring, such files are unstuffed, but in other cases we can
 * just update the inode size directly.
 *
 * Returns: 0 on success, or -ve on error
 */

static int do_grow(struct inode *inode, u64 size)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	struct gfs2_alloc_parms ap = { .target = 1, };
	struct buffer_head *dibh;
	int error;
	int unstuff = 0;

	if (gfs2_is_stuffed(ip) && size > gfs2_max_stuffed_size(ip)) {
		error = gfs2_quota_lock_check(ip, &ap);
		if (error)
			return error;

		error = gfs2_inplace_reserve(ip, &ap);
		if (error)
			goto do_grow_qunlock;
		unstuff = 1;
	}

	error = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS + RES_RG_BIT +
				 (unstuff &&
				  gfs2_is_jdata(ip) ? RES_JDATA : 0) +
				 (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF ?
				  0 : RES_QUOTA), 0);
	if (error)
		goto do_grow_release;

	if (unstuff) {
		error = gfs2_unstuff_dinode(ip, NULL);
		if (error)
			goto do_end_trans;
	}

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (error)
		goto do_end_trans;

	truncate_setsize(inode, size);
	ip->i_inode.i_mtime = ip->i_inode.i_ctime = current_time(&ip->i_inode);
	gfs2_trans_add_meta(ip->i_gl, dibh);
	gfs2_dinode_out(ip, dibh->b_data);
	brelse(dibh);

do_end_trans:
	gfs2_trans_end(sdp);
do_grow_release:
	if (unstuff) {
		gfs2_inplace_release(ip);
do_grow_qunlock:
		gfs2_quota_unlock(ip);
	}
	return error;
}

/**
 * gfs2_setattr_size - make a file a given size
 * @inode: the inode
 * @newsize: the size to make the file
 *
 * The file size can grow, shrink, or stay the same size. This
 * is called holding i_rwsem and an exclusive glock on the inode
 * in question.
 *
 * Returns: errno
 */

int gfs2_setattr_size(struct inode *inode, u64 newsize)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	int ret;

	BUG_ON(!S_ISREG(inode->i_mode));

	ret = inode_newsize_ok(inode, newsize);
	if (ret)
		return ret;

	inode_dio_wait(inode);

	ret = gfs2_rsqa_alloc(ip);
	if (ret)
		goto out;

	if (newsize >= inode->i_size) {
		ret = do_grow(inode, newsize);
		goto out;
	}

	ret = do_shrink(inode, newsize);
out:
	gfs2_rsqa_delete(ip, NULL);
	return ret;
}

int gfs2_truncatei_resume(struct gfs2_inode *ip)
{
	int error;
	error = punch_hole(ip, i_size_read(&ip->i_inode), 0);
	if (!error)
		error = trunc_end(ip);
	return error;
}

int gfs2_file_dealloc(struct gfs2_inode *ip)
{
	return punch_hole(ip, 0, 0);
}

/**
 * gfs2_free_journal_extents - Free cached journal bmap info
 * @jd: The journal
 *
 */

void gfs2_free_journal_extents(struct gfs2_jdesc *jd)
{
	struct gfs2_journal_extent *jext;

	while(!list_empty(&jd->extent_list)) {
		jext = list_entry(jd->extent_list.next, struct gfs2_journal_extent, list);
		list_del(&jext->list);
		kfree(jext);
	}
}

/**
 * gfs2_add_jextent - Add or merge a new extent to extent cache
 * @jd: The journal descriptor
 * @lblock: The logical block at start of new extent
 * @dblock: The physical block at start of new extent
 * @blocks: Size of extent in fs blocks
 *
 * Returns: 0 on success or -ENOMEM
 */

static int gfs2_add_jextent(struct gfs2_jdesc *jd, u64 lblock, u64 dblock, u64 blocks)
{
	struct gfs2_journal_extent *jext;

	if (!list_empty(&jd->extent_list)) {
		jext = list_entry(jd->extent_list.prev, struct gfs2_journal_extent, list);
		if ((jext->dblock + jext->blocks) == dblock) {
			jext->blocks += blocks;
			return 0;
		}
	}

	jext = kzalloc(sizeof(struct gfs2_journal_extent), GFP_NOFS);
	if (jext == NULL)
		return -ENOMEM;
	jext->dblock = dblock;
	jext->lblock = lblock;
	jext->blocks = blocks;
	list_add_tail(&jext->list, &jd->extent_list);
	jd->nr_extents++;
	return 0;
}

/**
 * gfs2_map_journal_extents - Cache journal bmap info
 * @sdp: The super block
 * @jd: The journal to map
 *
 * Create a reusable "extent" mapping from all logical
 * blocks to all physical blocks for the given journal.  This will save
 * us time when writing journal blocks.  Most journals will have only one
 * extent that maps all their logical blocks.  That's because gfs2.mkfs
 * arranges the journal blocks sequentially to maximize performance.
 * So the extent would map the first block for the entire file length.
 * However, gfs2_jadd can happen while file activity is happening, so
 * those journals may not be sequential.  Less likely is the case where
 * the users created their own journals by mounting the metafs and
 * laying it out.  But it's still possible.  These journals might have
 * several extents.
 *
 * Returns: 0 on success, or error on failure
 */

int gfs2_map_journal_extents(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd)
{
	u64 lblock = 0;
	u64 lblock_stop;
	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
	struct buffer_head bh;
	unsigned int shift = sdp->sd_sb.sb_bsize_shift;
	u64 size;
	int rc;
	ktime_t start, end;

	start = ktime_get();
	lblock_stop = i_size_read(jd->jd_inode) >> shift;
	size = (lblock_stop - lblock) << shift;
	jd->nr_extents = 0;
	WARN_ON(!list_empty(&jd->extent_list));

	do {
		bh.b_state = 0;
		bh.b_blocknr = 0;
		bh.b_size = size;
		rc = gfs2_block_map(jd->jd_inode, lblock, &bh, 0);
		if (rc || !buffer_mapped(&bh))
			goto fail;
		rc = gfs2_add_jextent(jd, lblock, bh.b_blocknr, bh.b_size >> shift);
		if (rc)
			goto fail;
		size -= bh.b_size;
		lblock += (bh.b_size >> ip->i_inode.i_blkbits);
	} while(size > 0);

	end = ktime_get();
	fs_info(sdp, "journal %d mapped with %u extents in %lldms\n", jd->jd_jid,
		jd->nr_extents, ktime_ms_delta(end, start));
	return 0;

fail:
	fs_warn(sdp, "error %d mapping journal %u at offset %llu (extent %u)\n",
		rc, jd->jd_jid,
		(unsigned long long)(i_size_read(jd->jd_inode) - size),
		jd->nr_extents);
	fs_warn(sdp, "bmap=%d lblock=%llu block=%llu, state=0x%08lx, size=%llu\n",
		rc, (unsigned long long)lblock, (unsigned long long)bh.b_blocknr,
		bh.b_state, (unsigned long long)bh.b_size);
	gfs2_free_journal_extents(jd);
	return rc;
}

/**
 * gfs2_write_alloc_required - figure out if a write will require an allocation
 * @ip: the file being written to
 * @offset: the offset to write to
 * @len: the number of bytes being written
 *
 * Returns: 1 if an alloc is required, 0 otherwise
 */

int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
			      unsigned int len)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct buffer_head bh;
	unsigned int shift;
	u64 lblock, lblock_stop, size;
	u64 end_of_file;

	if (!len)
		return 0;

	if (gfs2_is_stuffed(ip)) {
		if (offset + len > gfs2_max_stuffed_size(ip))
			return 1;
		return 0;
	}

	shift = sdp->sd_sb.sb_bsize_shift;
	BUG_ON(gfs2_is_dir(ip));
	end_of_file = (i_size_read(&ip->i_inode) + sdp->sd_sb.sb_bsize - 1) >> shift;
	lblock = offset >> shift;
	lblock_stop = (offset + len + sdp->sd_sb.sb_bsize - 1) >> shift;
	if (lblock_stop > end_of_file && ip != GFS2_I(sdp->sd_rindex))
		return 1;

	size = (lblock_stop - lblock) << shift;
	do {
		bh.b_state = 0;
		bh.b_size = size;
		gfs2_block_map(&ip->i_inode, lblock, &bh, 0);
		if (!buffer_mapped(&bh))
			return 1;
		size -= bh.b_size;
		lblock += (bh.b_size >> ip->i_inode.i_blkbits);
	} while(size > 0);

	return 0;
}

static int stuffed_zero_range(struct inode *inode, loff_t offset, loff_t length)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct buffer_head *dibh;
	int error;

	if (offset >= inode->i_size)
		return 0;
	if (offset + length > inode->i_size)
		length = inode->i_size - offset;

	error = gfs2_meta_inode_buffer(ip, &dibh);
	if (error)
		return error;
	gfs2_trans_add_meta(ip->i_gl, dibh);
	memset(dibh->b_data + sizeof(struct gfs2_dinode) + offset, 0,
	       length);
	brelse(dibh);
	return 0;
}

static int gfs2_journaled_truncate_range(struct inode *inode, loff_t offset,
					 loff_t length)
{
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	loff_t max_chunk = GFS2_JTRUNC_REVOKES * sdp->sd_vfs->s_blocksize;
	int error;

	while (length) {
		struct gfs2_trans *tr;
		loff_t chunk;
		unsigned int offs;

		chunk = length;
		if (chunk > max_chunk)
			chunk = max_chunk;

		offs = offset & ~PAGE_MASK;
		if (offs && chunk > PAGE_SIZE)
			chunk = offs + ((chunk - offs) & PAGE_MASK);

		truncate_pagecache_range(inode, offset, chunk);
		offset += chunk;
		length -= chunk;

		tr = current->journal_info;
		if (!test_bit(TR_TOUCHED, &tr->tr_flags))
			continue;

		gfs2_trans_end(sdp);
		error = gfs2_trans_begin(sdp, RES_DINODE, GFS2_JTRUNC_REVOKES);
		if (error)
			return error;
	}
	return 0;
}

int __gfs2_punch_hole(struct file *file, loff_t offset, loff_t length)
{
	struct inode *inode = file_inode(file);
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	unsigned int blocksize = i_blocksize(inode);
	loff_t start, end;
	int error;

	if (!gfs2_is_stuffed(ip)) {
		unsigned int start_off, end_len;

		start_off = offset & (blocksize - 1);
		end_len = (offset + length) & (blocksize - 1);
		if (start_off) {
			unsigned int len = length;
			if (length > blocksize - start_off)
				len = blocksize - start_off;
			error = gfs2_block_zero_range(inode, offset, len);
			if (error)
				goto out;
			if (start_off + length < blocksize)
				end_len = 0;
		}
		if (end_len) {
			error = gfs2_block_zero_range(inode,
				offset + length - end_len, end_len);
			if (error)
				goto out;
		}
	}

	start = round_down(offset, blocksize);
	end = round_up(offset + length, blocksize) - 1;
	error = filemap_write_and_wait_range(inode->i_mapping, start, end);
	if (error)
		return error;

	if (gfs2_is_jdata(ip))
		error = gfs2_trans_begin(sdp, RES_DINODE + 2 * RES_JDATA,
					 GFS2_JTRUNC_REVOKES);
	else
		error = gfs2_trans_begin(sdp, RES_DINODE, 0);
	if (error)
		return error;

	if (gfs2_is_stuffed(ip)) {
		error = stuffed_zero_range(inode, offset, length);
		if (error)
			goto out;
	}

	if (gfs2_is_jdata(ip)) {
		BUG_ON(!current->journal_info);
		gfs2_journaled_truncate_range(inode, offset, length);
	} else
		truncate_pagecache_range(inode, offset, offset + length - 1);

	file_update_time(file);
	mark_inode_dirty(inode);

	if (current->journal_info)
		gfs2_trans_end(sdp);

	if (!gfs2_is_stuffed(ip))
		error = punch_hole(ip, offset, length);

out:
	if (current->journal_info)
		gfs2_trans_end(sdp);
	return error;
}