namei.c 69.3 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585
/*
 *  linux/fs/ext3/namei.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/fs/minix/namei.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  Big-endian to little-endian byte-swapping/bitmaps by
 *        David S. Miller (davem@caip.rutgers.edu), 1995
 *  Directory entry file type support and forward compatibility hooks
 *	for B-tree directories by Theodore Ts'o (tytso@mit.edu), 1998
 *  Hash Tree Directory indexing (c)
 *	Daniel Phillips, 2001
 *  Hash Tree Directory indexing porting
 *	Christopher Li, 2002
 *  Hash Tree Directory indexing cleanup
 *	Theodore Ts'o, 2002
 */

#include <linux/quotaops.h>
#include "ext3.h"
#include "namei.h"
#include "xattr.h"
#include "acl.h"

/*
 * define how far ahead to read directories while searching them.
 */
#define NAMEI_RA_CHUNKS  2
#define NAMEI_RA_BLOCKS  4
#define NAMEI_RA_SIZE        (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS)

static struct buffer_head *ext3_append(handle_t *handle,
					struct inode *inode,
					u32 *block, int *err)
{
	struct buffer_head *bh;

	*block = inode->i_size >> inode->i_sb->s_blocksize_bits;

	if ((bh = ext3_dir_bread(handle, inode, *block, 1, err))) {
		inode->i_size += inode->i_sb->s_blocksize;
		EXT3_I(inode)->i_disksize = inode->i_size;
		*err = ext3_journal_get_write_access(handle, bh);
		if (*err) {
			brelse(bh);
			bh = NULL;
		}
	}
	return bh;
}

#ifndef assert
#define assert(test) J_ASSERT(test)
#endif

#ifdef DX_DEBUG
#define dxtrace(command) command
#else
#define dxtrace(command)
#endif

struct fake_dirent
{
	__le32 inode;
	__le16 rec_len;
	u8 name_len;
	u8 file_type;
};

struct dx_countlimit
{
	__le16 limit;
	__le16 count;
};

struct dx_entry
{
	__le32 hash;
	__le32 block;
};

/*
 * dx_root_info is laid out so that if it should somehow get overlaid by a
 * dirent the two low bits of the hash version will be zero.  Therefore, the
 * hash version mod 4 should never be 0.  Sincerely, the paranoia department.
 */

struct dx_root
{
	struct fake_dirent dot;
	char dot_name[4];
	struct fake_dirent dotdot;
	char dotdot_name[4];
	struct dx_root_info
	{
		__le32 reserved_zero;
		u8 hash_version;
		u8 info_length; /* 8 */
		u8 indirect_levels;
		u8 unused_flags;
	}
	info;
	struct dx_entry	entries[0];
};

struct dx_node
{
	struct fake_dirent fake;
	struct dx_entry	entries[0];
};


struct dx_frame
{
	struct buffer_head *bh;
	struct dx_entry *entries;
	struct dx_entry *at;
};

struct dx_map_entry
{
	u32 hash;
	u16 offs;
	u16 size;
};

static inline unsigned dx_get_block (struct dx_entry *entry);
static void dx_set_block (struct dx_entry *entry, unsigned value);
static inline unsigned dx_get_hash (struct dx_entry *entry);
static void dx_set_hash (struct dx_entry *entry, unsigned value);
static unsigned dx_get_count (struct dx_entry *entries);
static unsigned dx_get_limit (struct dx_entry *entries);
static void dx_set_count (struct dx_entry *entries, unsigned value);
static void dx_set_limit (struct dx_entry *entries, unsigned value);
static unsigned dx_root_limit (struct inode *dir, unsigned infosize);
static unsigned dx_node_limit (struct inode *dir);
static struct dx_frame *dx_probe(struct qstr *entry,
				 struct inode *dir,
				 struct dx_hash_info *hinfo,
				 struct dx_frame *frame,
				 int *err);
static void dx_release (struct dx_frame *frames);
static int dx_make_map(struct ext3_dir_entry_2 *de, unsigned blocksize,
			struct dx_hash_info *hinfo, struct dx_map_entry map[]);
static void dx_sort_map(struct dx_map_entry *map, unsigned count);
static struct ext3_dir_entry_2 *dx_move_dirents (char *from, char *to,
		struct dx_map_entry *offsets, int count);
static struct ext3_dir_entry_2 *dx_pack_dirents(char *base, unsigned blocksize);
static void dx_insert_block (struct dx_frame *frame, u32 hash, u32 block);
static int ext3_htree_next_block(struct inode *dir, __u32 hash,
				 struct dx_frame *frame,
				 struct dx_frame *frames,
				 __u32 *start_hash);
static struct buffer_head * ext3_dx_find_entry(struct inode *dir,
			struct qstr *entry, struct ext3_dir_entry_2 **res_dir,
			int *err);
static int ext3_dx_add_entry(handle_t *handle, struct dentry *dentry,
			     struct inode *inode);

/*
 * p is at least 6 bytes before the end of page
 */
static inline struct ext3_dir_entry_2 *
ext3_next_entry(struct ext3_dir_entry_2 *p)
{
	return (struct ext3_dir_entry_2 *)((char *)p +
		ext3_rec_len_from_disk(p->rec_len));
}

/*
 * Future: use high four bits of block for coalesce-on-delete flags
 * Mask them off for now.
 */

static inline unsigned dx_get_block (struct dx_entry *entry)
{
	return le32_to_cpu(entry->block) & 0x00ffffff;
}

static inline void dx_set_block (struct dx_entry *entry, unsigned value)
{
	entry->block = cpu_to_le32(value);
}

static inline unsigned dx_get_hash (struct dx_entry *entry)
{
	return le32_to_cpu(entry->hash);
}

static inline void dx_set_hash (struct dx_entry *entry, unsigned value)
{
	entry->hash = cpu_to_le32(value);
}

static inline unsigned dx_get_count (struct dx_entry *entries)
{
	return le16_to_cpu(((struct dx_countlimit *) entries)->count);
}

static inline unsigned dx_get_limit (struct dx_entry *entries)
{
	return le16_to_cpu(((struct dx_countlimit *) entries)->limit);
}

static inline void dx_set_count (struct dx_entry *entries, unsigned value)
{
	((struct dx_countlimit *) entries)->count = cpu_to_le16(value);
}

static inline void dx_set_limit (struct dx_entry *entries, unsigned value)
{
	((struct dx_countlimit *) entries)->limit = cpu_to_le16(value);
}

static inline unsigned dx_root_limit (struct inode *dir, unsigned infosize)
{
	unsigned entry_space = dir->i_sb->s_blocksize - EXT3_DIR_REC_LEN(1) -
		EXT3_DIR_REC_LEN(2) - infosize;
	return entry_space / sizeof(struct dx_entry);
}

static inline unsigned dx_node_limit (struct inode *dir)
{
	unsigned entry_space = dir->i_sb->s_blocksize - EXT3_DIR_REC_LEN(0);
	return entry_space / sizeof(struct dx_entry);
}

/*
 * Debug
 */
#ifdef DX_DEBUG
static void dx_show_index (char * label, struct dx_entry *entries)
{
        int i, n = dx_get_count (entries);
        printk("%s index ", label);
        for (i = 0; i < n; i++)
        {
                printk("%x->%u ", i? dx_get_hash(entries + i): 0, dx_get_block(entries + i));
        }
        printk("\n");
}

struct stats
{
	unsigned names;
	unsigned space;
	unsigned bcount;
};

static struct stats dx_show_leaf(struct dx_hash_info *hinfo, struct ext3_dir_entry_2 *de,
				 int size, int show_names)
{
	unsigned names = 0, space = 0;
	char *base = (char *) de;
	struct dx_hash_info h = *hinfo;

	printk("names: ");
	while ((char *) de < base + size)
	{
		if (de->inode)
		{
			if (show_names)
			{
				int len = de->name_len;
				char *name = de->name;
				while (len--) printk("%c", *name++);
				ext3fs_dirhash(de->name, de->name_len, &h);
				printk(":%x.%u ", h.hash,
				       (unsigned) ((char *) de - base));
			}
			space += EXT3_DIR_REC_LEN(de->name_len);
			names++;
		}
		de = ext3_next_entry(de);
	}
	printk("(%i)\n", names);
	return (struct stats) { names, space, 1 };
}

struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir,
			     struct dx_entry *entries, int levels)
{
	unsigned blocksize = dir->i_sb->s_blocksize;
	unsigned count = dx_get_count (entries), names = 0, space = 0, i;
	unsigned bcount = 0;
	struct buffer_head *bh;
	int err;
	printk("%i indexed blocks...\n", count);
	for (i = 0; i < count; i++, entries++)
	{
		u32 block = dx_get_block(entries), hash = i? dx_get_hash(entries): 0;
		u32 range = i < count - 1? (dx_get_hash(entries + 1) - hash): ~hash;
		struct stats stats;
		printk("%s%3u:%03u hash %8x/%8x ",levels?"":"   ", i, block, hash, range);
		if (!(bh = ext3_bread (NULL,dir, block, 0,&err))) continue;
		stats = levels?
		   dx_show_entries(hinfo, dir, ((struct dx_node *) bh->b_data)->entries, levels - 1):
		   dx_show_leaf(hinfo, (struct ext3_dir_entry_2 *) bh->b_data, blocksize, 0);
		names += stats.names;
		space += stats.space;
		bcount += stats.bcount;
		brelse (bh);
	}
	if (bcount)
		printk("%snames %u, fullness %u (%u%%)\n", levels?"":"   ",
			names, space/bcount,(space/bcount)*100/blocksize);
	return (struct stats) { names, space, bcount};
}
#endif /* DX_DEBUG */

/*
 * Probe for a directory leaf block to search.
 *
 * dx_probe can return ERR_BAD_DX_DIR, which means there was a format
 * error in the directory index, and the caller should fall back to
 * searching the directory normally.  The callers of dx_probe **MUST**
 * check for this error code, and make sure it never gets reflected
 * back to userspace.
 */
static struct dx_frame *
dx_probe(struct qstr *entry, struct inode *dir,
	 struct dx_hash_info *hinfo, struct dx_frame *frame_in, int *err)
{
	unsigned count, indirect;
	struct dx_entry *at, *entries, *p, *q, *m;
	struct dx_root *root;
	struct buffer_head *bh;
	struct dx_frame *frame = frame_in;
	u32 hash;

	frame->bh = NULL;
	if (!(bh = ext3_dir_bread(NULL, dir, 0, 0, err))) {
		*err = ERR_BAD_DX_DIR;
		goto fail;
	}
	root = (struct dx_root *) bh->b_data;
	if (root->info.hash_version != DX_HASH_TEA &&
	    root->info.hash_version != DX_HASH_HALF_MD4 &&
	    root->info.hash_version != DX_HASH_LEGACY) {
		ext3_warning(dir->i_sb, __func__,
			     "Unrecognised inode hash code %d",
			     root->info.hash_version);
		brelse(bh);
		*err = ERR_BAD_DX_DIR;
		goto fail;
	}
	hinfo->hash_version = root->info.hash_version;
	if (hinfo->hash_version <= DX_HASH_TEA)
		hinfo->hash_version += EXT3_SB(dir->i_sb)->s_hash_unsigned;
	hinfo->seed = EXT3_SB(dir->i_sb)->s_hash_seed;
	if (entry)
		ext3fs_dirhash(entry->name, entry->len, hinfo);
	hash = hinfo->hash;

	if (root->info.unused_flags & 1) {
		ext3_warning(dir->i_sb, __func__,
			     "Unimplemented inode hash flags: %#06x",
			     root->info.unused_flags);
		brelse(bh);
		*err = ERR_BAD_DX_DIR;
		goto fail;
	}

	if ((indirect = root->info.indirect_levels) > 1) {
		ext3_warning(dir->i_sb, __func__,
			     "Unimplemented inode hash depth: %#06x",
			     root->info.indirect_levels);
		brelse(bh);
		*err = ERR_BAD_DX_DIR;
		goto fail;
	}

	entries = (struct dx_entry *) (((char *)&root->info) +
				       root->info.info_length);

	if (dx_get_limit(entries) != dx_root_limit(dir,
						   root->info.info_length)) {
		ext3_warning(dir->i_sb, __func__,
			     "dx entry: limit != root limit");
		brelse(bh);
		*err = ERR_BAD_DX_DIR;
		goto fail;
	}

	dxtrace (printk("Look up %x", hash));
	while (1)
	{
		count = dx_get_count(entries);
		if (!count || count > dx_get_limit(entries)) {
			ext3_warning(dir->i_sb, __func__,
				     "dx entry: no count or count > limit");
			brelse(bh);
			*err = ERR_BAD_DX_DIR;
			goto fail2;
		}

		p = entries + 1;
		q = entries + count - 1;
		while (p <= q)
		{
			m = p + (q - p)/2;
			dxtrace(printk("."));
			if (dx_get_hash(m) > hash)
				q = m - 1;
			else
				p = m + 1;
		}

		if (0) // linear search cross check
		{
			unsigned n = count - 1;
			at = entries;
			while (n--)
			{
				dxtrace(printk(","));
				if (dx_get_hash(++at) > hash)
				{
					at--;
					break;
				}
			}
			assert (at == p - 1);
		}

		at = p - 1;
		dxtrace(printk(" %x->%u\n", at == entries? 0: dx_get_hash(at), dx_get_block(at)));
		frame->bh = bh;
		frame->entries = entries;
		frame->at = at;
		if (!indirect--) return frame;
		if (!(bh = ext3_dir_bread(NULL, dir, dx_get_block(at), 0, err))) {
			*err = ERR_BAD_DX_DIR;
			goto fail2;
		}
		at = entries = ((struct dx_node *) bh->b_data)->entries;
		if (dx_get_limit(entries) != dx_node_limit (dir)) {
			ext3_warning(dir->i_sb, __func__,
				     "dx entry: limit != node limit");
			brelse(bh);
			*err = ERR_BAD_DX_DIR;
			goto fail2;
		}
		frame++;
		frame->bh = NULL;
	}
fail2:
	while (frame >= frame_in) {
		brelse(frame->bh);
		frame--;
	}
fail:
	if (*err == ERR_BAD_DX_DIR)
		ext3_warning(dir->i_sb, __func__,
			     "Corrupt dir inode %ld, running e2fsck is "
			     "recommended.", dir->i_ino);
	return NULL;
}

static void dx_release (struct dx_frame *frames)
{
	if (frames[0].bh == NULL)
		return;

	if (((struct dx_root *) frames[0].bh->b_data)->info.indirect_levels)
		brelse(frames[1].bh);
	brelse(frames[0].bh);
}

/*
 * This function increments the frame pointer to search the next leaf
 * block, and reads in the necessary intervening nodes if the search
 * should be necessary.  Whether or not the search is necessary is
 * controlled by the hash parameter.  If the hash value is even, then
 * the search is only continued if the next block starts with that
 * hash value.  This is used if we are searching for a specific file.
 *
 * If the hash value is HASH_NB_ALWAYS, then always go to the next block.
 *
 * This function returns 1 if the caller should continue to search,
 * or 0 if it should not.  If there is an error reading one of the
 * index blocks, it will a negative error code.
 *
 * If start_hash is non-null, it will be filled in with the starting
 * hash of the next page.
 */
static int ext3_htree_next_block(struct inode *dir, __u32 hash,
				 struct dx_frame *frame,
				 struct dx_frame *frames,
				 __u32 *start_hash)
{
	struct dx_frame *p;
	struct buffer_head *bh;
	int err, num_frames = 0;
	__u32 bhash;

	p = frame;
	/*
	 * Find the next leaf page by incrementing the frame pointer.
	 * If we run out of entries in the interior node, loop around and
	 * increment pointer in the parent node.  When we break out of
	 * this loop, num_frames indicates the number of interior
	 * nodes need to be read.
	 */
	while (1) {
		if (++(p->at) < p->entries + dx_get_count(p->entries))
			break;
		if (p == frames)
			return 0;
		num_frames++;
		p--;
	}

	/*
	 * If the hash is 1, then continue only if the next page has a
	 * continuation hash of any value.  This is used for readdir
	 * handling.  Otherwise, check to see if the hash matches the
	 * desired contiuation hash.  If it doesn't, return since
	 * there's no point to read in the successive index pages.
	 */
	bhash = dx_get_hash(p->at);
	if (start_hash)
		*start_hash = bhash;
	if ((hash & 1) == 0) {
		if ((bhash & ~1) != hash)
			return 0;
	}
	/*
	 * If the hash is HASH_NB_ALWAYS, we always go to the next
	 * block so no check is necessary
	 */
	while (num_frames--) {
		if (!(bh = ext3_dir_bread(NULL, dir, dx_get_block(p->at),
					  0, &err)))
			return err; /* Failure */
		p++;
		brelse (p->bh);
		p->bh = bh;
		p->at = p->entries = ((struct dx_node *) bh->b_data)->entries;
	}
	return 1;
}


/*
 * This function fills a red-black tree with information from a
 * directory block.  It returns the number directory entries loaded
 * into the tree.  If there is an error it is returned in err.
 */
static int htree_dirblock_to_tree(struct file *dir_file,
				  struct inode *dir, int block,
				  struct dx_hash_info *hinfo,
				  __u32 start_hash, __u32 start_minor_hash)
{
	struct buffer_head *bh;
	struct ext3_dir_entry_2 *de, *top;
	int err = 0, count = 0;

	dxtrace(printk("In htree dirblock_to_tree: block %d\n", block));

	if (!(bh = ext3_dir_bread(NULL, dir, block, 0, &err)))
		return err;

	de = (struct ext3_dir_entry_2 *) bh->b_data;
	top = (struct ext3_dir_entry_2 *) ((char *) de +
					   dir->i_sb->s_blocksize -
					   EXT3_DIR_REC_LEN(0));
	for (; de < top; de = ext3_next_entry(de)) {
		if (!ext3_check_dir_entry("htree_dirblock_to_tree", dir, de, bh,
					(block<<EXT3_BLOCK_SIZE_BITS(dir->i_sb))
						+((char *)de - bh->b_data))) {
			/* silently ignore the rest of the block */
			break;
		}
		ext3fs_dirhash(de->name, de->name_len, hinfo);
		if ((hinfo->hash < start_hash) ||
		    ((hinfo->hash == start_hash) &&
		     (hinfo->minor_hash < start_minor_hash)))
			continue;
		if (de->inode == 0)
			continue;
		if ((err = ext3_htree_store_dirent(dir_file,
				   hinfo->hash, hinfo->minor_hash, de)) != 0) {
			brelse(bh);
			return err;
		}
		count++;
	}
	brelse(bh);
	return count;
}


/*
 * This function fills a red-black tree with information from a
 * directory.  We start scanning the directory in hash order, starting
 * at start_hash and start_minor_hash.
 *
 * This function returns the number of entries inserted into the tree,
 * or a negative error code.
 */
int ext3_htree_fill_tree(struct file *dir_file, __u32 start_hash,
			 __u32 start_minor_hash, __u32 *next_hash)
{
	struct dx_hash_info hinfo;
	struct ext3_dir_entry_2 *de;
	struct dx_frame frames[2], *frame;
	struct inode *dir;
	int block, err;
	int count = 0;
	int ret;
	__u32 hashval;

	dxtrace(printk("In htree_fill_tree, start hash: %x:%x\n", start_hash,
		       start_minor_hash));
	dir = file_inode(dir_file);
	if (!(EXT3_I(dir)->i_flags & EXT3_INDEX_FL)) {
		hinfo.hash_version = EXT3_SB(dir->i_sb)->s_def_hash_version;
		if (hinfo.hash_version <= DX_HASH_TEA)
			hinfo.hash_version +=
				EXT3_SB(dir->i_sb)->s_hash_unsigned;
		hinfo.seed = EXT3_SB(dir->i_sb)->s_hash_seed;
		count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo,
					       start_hash, start_minor_hash);
		*next_hash = ~0;
		return count;
	}
	hinfo.hash = start_hash;
	hinfo.minor_hash = 0;
	frame = dx_probe(NULL, file_inode(dir_file), &hinfo, frames, &err);
	if (!frame)
		return err;

	/* Add '.' and '..' from the htree header */
	if (!start_hash && !start_minor_hash) {
		de = (struct ext3_dir_entry_2 *) frames[0].bh->b_data;
		if ((err = ext3_htree_store_dirent(dir_file, 0, 0, de)) != 0)
			goto errout;
		count++;
	}
	if (start_hash < 2 || (start_hash ==2 && start_minor_hash==0)) {
		de = (struct ext3_dir_entry_2 *) frames[0].bh->b_data;
		de = ext3_next_entry(de);
		if ((err = ext3_htree_store_dirent(dir_file, 2, 0, de)) != 0)
			goto errout;
		count++;
	}

	while (1) {
		block = dx_get_block(frame->at);
		ret = htree_dirblock_to_tree(dir_file, dir, block, &hinfo,
					     start_hash, start_minor_hash);
		if (ret < 0) {
			err = ret;
			goto errout;
		}
		count += ret;
		hashval = ~0;
		ret = ext3_htree_next_block(dir, HASH_NB_ALWAYS,
					    frame, frames, &hashval);
		*next_hash = hashval;
		if (ret < 0) {
			err = ret;
			goto errout;
		}
		/*
		 * Stop if:  (a) there are no more entries, or
		 * (b) we have inserted at least one entry and the
		 * next hash value is not a continuation
		 */
		if ((ret == 0) ||
		    (count && ((hashval & 1) == 0)))
			break;
	}
	dx_release(frames);
	dxtrace(printk("Fill tree: returned %d entries, next hash: %x\n",
		       count, *next_hash));
	return count;
errout:
	dx_release(frames);
	return (err);
}


/*
 * Directory block splitting, compacting
 */

/*
 * Create map of hash values, offsets, and sizes, stored at end of block.
 * Returns number of entries mapped.
 */
static int dx_make_map(struct ext3_dir_entry_2 *de, unsigned blocksize,
		struct dx_hash_info *hinfo, struct dx_map_entry *map_tail)
{
	int count = 0;
	char *base = (char *) de;
	struct dx_hash_info h = *hinfo;

	while ((char *) de < base + blocksize)
	{
		if (de->name_len && de->inode) {
			ext3fs_dirhash(de->name, de->name_len, &h);
			map_tail--;
			map_tail->hash = h.hash;
			map_tail->offs = (u16) ((char *) de - base);
			map_tail->size = le16_to_cpu(de->rec_len);
			count++;
			cond_resched();
		}
		/* XXX: do we need to check rec_len == 0 case? -Chris */
		de = ext3_next_entry(de);
	}
	return count;
}

/* Sort map by hash value */
static void dx_sort_map (struct dx_map_entry *map, unsigned count)
{
        struct dx_map_entry *p, *q, *top = map + count - 1;
        int more;
        /* Combsort until bubble sort doesn't suck */
        while (count > 2)
	{
                count = count*10/13;
                if (count - 9 < 2) /* 9, 10 -> 11 */
                        count = 11;
                for (p = top, q = p - count; q >= map; p--, q--)
                        if (p->hash < q->hash)
                                swap(*p, *q);
        }
        /* Garden variety bubble sort */
        do {
                more = 0;
                q = top;
                while (q-- > map)
		{
                        if (q[1].hash >= q[0].hash)
				continue;
                        swap(*(q+1), *q);
                        more = 1;
		}
	} while(more);
}

static void dx_insert_block(struct dx_frame *frame, u32 hash, u32 block)
{
	struct dx_entry *entries = frame->entries;
	struct dx_entry *old = frame->at, *new = old + 1;
	int count = dx_get_count(entries);

	assert(count < dx_get_limit(entries));
	assert(old < entries + count);
	memmove(new + 1, new, (char *)(entries + count) - (char *)(new));
	dx_set_hash(new, hash);
	dx_set_block(new, block);
	dx_set_count(entries, count + 1);
}

static void ext3_update_dx_flag(struct inode *inode)
{
	if (!EXT3_HAS_COMPAT_FEATURE(inode->i_sb,
				     EXT3_FEATURE_COMPAT_DIR_INDEX))
		EXT3_I(inode)->i_flags &= ~EXT3_INDEX_FL;
}

/*
 * NOTE! unlike strncmp, ext3_match returns 1 for success, 0 for failure.
 *
 * `len <= EXT3_NAME_LEN' is guaranteed by caller.
 * `de != NULL' is guaranteed by caller.
 */
static inline int ext3_match (int len, const char * const name,
			      struct ext3_dir_entry_2 * de)
{
	if (len != de->name_len)
		return 0;
	if (!de->inode)
		return 0;
	return !memcmp(name, de->name, len);
}

/*
 * Returns 0 if not found, -1 on failure, and 1 on success
 */
static inline int search_dirblock(struct buffer_head * bh,
				  struct inode *dir,
				  struct qstr *child,
				  unsigned long offset,
				  struct ext3_dir_entry_2 ** res_dir)
{
	struct ext3_dir_entry_2 * de;
	char * dlimit;
	int de_len;
	const char *name = child->name;
	int namelen = child->len;

	de = (struct ext3_dir_entry_2 *) bh->b_data;
	dlimit = bh->b_data + dir->i_sb->s_blocksize;
	while ((char *) de < dlimit) {
		/* this code is executed quadratically often */
		/* do minimal checking `by hand' */

		if ((char *) de + namelen <= dlimit &&
		    ext3_match (namelen, name, de)) {
			/* found a match - just to be sure, do a full check */
			if (!ext3_check_dir_entry("ext3_find_entry",
						  dir, de, bh, offset))
				return -1;
			*res_dir = de;
			return 1;
		}
		/* prevent looping on a bad block */
		de_len = ext3_rec_len_from_disk(de->rec_len);
		if (de_len <= 0)
			return -1;
		offset += de_len;
		de = (struct ext3_dir_entry_2 *) ((char *) de + de_len);
	}
	return 0;
}


/*
 *	ext3_find_entry()
 *
 * finds an entry in the specified directory with the wanted name. It
 * returns the cache buffer in which the entry was found, and the entry
 * itself (as a parameter - res_dir). It does NOT read the inode of the
 * entry - you'll have to do that yourself if you want to.
 *
 * The returned buffer_head has ->b_count elevated.  The caller is expected
 * to brelse() it when appropriate.
 */
static struct buffer_head *ext3_find_entry(struct inode *dir,
					struct qstr *entry,
					struct ext3_dir_entry_2 **res_dir)
{
	struct super_block * sb;
	struct buffer_head * bh_use[NAMEI_RA_SIZE];
	struct buffer_head * bh, *ret = NULL;
	unsigned long start, block, b;
	const u8 *name = entry->name;
	int ra_max = 0;		/* Number of bh's in the readahead
				   buffer, bh_use[] */
	int ra_ptr = 0;		/* Current index into readahead
				   buffer */
	int num = 0;
	int nblocks, i, err;
	int namelen;

	*res_dir = NULL;
	sb = dir->i_sb;
	namelen = entry->len;
	if (namelen > EXT3_NAME_LEN)
		return NULL;
	if ((namelen <= 2) && (name[0] == '.') &&
	    (name[1] == '.' || name[1] == 0)) {
		/*
		 * "." or ".." will only be in the first block
		 * NFS may look up ".."; "." should be handled by the VFS
		 */
		block = start = 0;
		nblocks = 1;
		goto restart;
	}
	if (is_dx(dir)) {
		bh = ext3_dx_find_entry(dir, entry, res_dir, &err);
		/*
		 * On success, or if the error was file not found,
		 * return.  Otherwise, fall back to doing a search the
		 * old fashioned way.
		 */
		if (bh || (err != ERR_BAD_DX_DIR))
			return bh;
		dxtrace(printk("ext3_find_entry: dx failed, falling back\n"));
	}
	nblocks = dir->i_size >> EXT3_BLOCK_SIZE_BITS(sb);
	start = EXT3_I(dir)->i_dir_start_lookup;
	if (start >= nblocks)
		start = 0;
	block = start;
restart:
	do {
		/*
		 * We deal with the read-ahead logic here.
		 */
		if (ra_ptr >= ra_max) {
			/* Refill the readahead buffer */
			ra_ptr = 0;
			b = block;
			for (ra_max = 0; ra_max < NAMEI_RA_SIZE; ra_max++) {
				/*
				 * Terminate if we reach the end of the
				 * directory and must wrap, or if our
				 * search has finished at this block.
				 */
				if (b >= nblocks || (num && block == start)) {
					bh_use[ra_max] = NULL;
					break;
				}
				num++;
				bh = ext3_getblk(NULL, dir, b++, 0, &err);
				bh_use[ra_max] = bh;
				if (bh && !bh_uptodate_or_lock(bh)) {
					get_bh(bh);
					bh->b_end_io = end_buffer_read_sync;
					submit_bh(READ | REQ_META | REQ_PRIO,
						  bh);
				}
			}
		}
		if ((bh = bh_use[ra_ptr++]) == NULL)
			goto next;
		wait_on_buffer(bh);
		if (!buffer_uptodate(bh)) {
			/* read error, skip block & hope for the best */
			ext3_error(sb, __func__, "reading directory #%lu "
				   "offset %lu", dir->i_ino, block);
			brelse(bh);
			goto next;
		}
		i = search_dirblock(bh, dir, entry,
			    block << EXT3_BLOCK_SIZE_BITS(sb), res_dir);
		if (i == 1) {
			EXT3_I(dir)->i_dir_start_lookup = block;
			ret = bh;
			goto cleanup_and_exit;
		} else {
			brelse(bh);
			if (i < 0)
				goto cleanup_and_exit;
		}
	next:
		if (++block >= nblocks)
			block = 0;
	} while (block != start);

	/*
	 * If the directory has grown while we were searching, then
	 * search the last part of the directory before giving up.
	 */
	block = nblocks;
	nblocks = dir->i_size >> EXT3_BLOCK_SIZE_BITS(sb);
	if (block < nblocks) {
		start = 0;
		goto restart;
	}

cleanup_and_exit:
	/* Clean up the read-ahead blocks */
	for (; ra_ptr < ra_max; ra_ptr++)
		brelse (bh_use[ra_ptr]);
	return ret;
}

static struct buffer_head * ext3_dx_find_entry(struct inode *dir,
			struct qstr *entry, struct ext3_dir_entry_2 **res_dir,
			int *err)
{
	struct super_block *sb = dir->i_sb;
	struct dx_hash_info	hinfo;
	struct dx_frame frames[2], *frame;
	struct buffer_head *bh;
	unsigned long block;
	int retval;

	if (!(frame = dx_probe(entry, dir, &hinfo, frames, err)))
		return NULL;
	do {
		block = dx_get_block(frame->at);
		if (!(bh = ext3_dir_bread (NULL, dir, block, 0, err)))
			goto errout;

		retval = search_dirblock(bh, dir, entry,
					 block << EXT3_BLOCK_SIZE_BITS(sb),
					 res_dir);
		if (retval == 1) {
			dx_release(frames);
			return bh;
		}
		brelse(bh);
		if (retval == -1) {
			*err = ERR_BAD_DX_DIR;
			goto errout;
		}

		/* Check to see if we should continue to search */
		retval = ext3_htree_next_block(dir, hinfo.hash, frame,
					       frames, NULL);
		if (retval < 0) {
			ext3_warning(sb, __func__,
			     "error reading index page in directory #%lu",
			     dir->i_ino);
			*err = retval;
			goto errout;
		}
	} while (retval == 1);

	*err = -ENOENT;
errout:
	dxtrace(printk("%s not found\n", entry->name));
	dx_release (frames);
	return NULL;
}

static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags)
{
	struct inode * inode;
	struct ext3_dir_entry_2 * de;
	struct buffer_head * bh;

	if (dentry->d_name.len > EXT3_NAME_LEN)
		return ERR_PTR(-ENAMETOOLONG);

	bh = ext3_find_entry(dir, &dentry->d_name, &de);
	inode = NULL;
	if (bh) {
		unsigned long ino = le32_to_cpu(de->inode);
		brelse (bh);
		if (!ext3_valid_inum(dir->i_sb, ino)) {
			ext3_error(dir->i_sb, "ext3_lookup",
				   "bad inode number: %lu", ino);
			return ERR_PTR(-EIO);
		}
		inode = ext3_iget(dir->i_sb, ino);
		if (inode == ERR_PTR(-ESTALE)) {
			ext3_error(dir->i_sb, __func__,
					"deleted inode referenced: %lu",
					ino);
			return ERR_PTR(-EIO);
		}
	}
	return d_splice_alias(inode, dentry);
}


struct dentry *ext3_get_parent(struct dentry *child)
{
	unsigned long ino;
	struct qstr dotdot = QSTR_INIT("..", 2);
	struct ext3_dir_entry_2 * de;
	struct buffer_head *bh;

	bh = ext3_find_entry(child->d_inode, &dotdot, &de);
	if (!bh)
		return ERR_PTR(-ENOENT);
	ino = le32_to_cpu(de->inode);
	brelse(bh);

	if (!ext3_valid_inum(child->d_inode->i_sb, ino)) {
		ext3_error(child->d_inode->i_sb, "ext3_get_parent",
			   "bad inode number: %lu", ino);
		return ERR_PTR(-EIO);
	}

	return d_obtain_alias(ext3_iget(child->d_inode->i_sb, ino));
}

#define S_SHIFT 12
static unsigned char ext3_type_by_mode[S_IFMT >> S_SHIFT] = {
	[S_IFREG >> S_SHIFT]	= EXT3_FT_REG_FILE,
	[S_IFDIR >> S_SHIFT]	= EXT3_FT_DIR,
	[S_IFCHR >> S_SHIFT]	= EXT3_FT_CHRDEV,
	[S_IFBLK >> S_SHIFT]	= EXT3_FT_BLKDEV,
	[S_IFIFO >> S_SHIFT]	= EXT3_FT_FIFO,
	[S_IFSOCK >> S_SHIFT]	= EXT3_FT_SOCK,
	[S_IFLNK >> S_SHIFT]	= EXT3_FT_SYMLINK,
};

static inline void ext3_set_de_type(struct super_block *sb,
				struct ext3_dir_entry_2 *de,
				umode_t mode) {
	if (EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_FILETYPE))
		de->file_type = ext3_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
}

/*
 * Move count entries from end of map between two memory locations.
 * Returns pointer to last entry moved.
 */
static struct ext3_dir_entry_2 *
dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count)
{
	unsigned rec_len = 0;

	while (count--) {
		struct ext3_dir_entry_2 *de = (struct ext3_dir_entry_2 *) (from + map->offs);
		rec_len = EXT3_DIR_REC_LEN(de->name_len);
		memcpy (to, de, rec_len);
		((struct ext3_dir_entry_2 *) to)->rec_len =
				ext3_rec_len_to_disk(rec_len);
		de->inode = 0;
		map++;
		to += rec_len;
	}
	return (struct ext3_dir_entry_2 *) (to - rec_len);
}

/*
 * Compact each dir entry in the range to the minimal rec_len.
 * Returns pointer to last entry in range.
 */
static struct ext3_dir_entry_2 *dx_pack_dirents(char *base, unsigned blocksize)
{
	struct ext3_dir_entry_2 *next, *to, *prev;
	struct ext3_dir_entry_2 *de = (struct ext3_dir_entry_2 *)base;
	unsigned rec_len = 0;

	prev = to = de;
	while ((char *)de < base + blocksize) {
		next = ext3_next_entry(de);
		if (de->inode && de->name_len) {
			rec_len = EXT3_DIR_REC_LEN(de->name_len);
			if (de > to)
				memmove(to, de, rec_len);
			to->rec_len = ext3_rec_len_to_disk(rec_len);
			prev = to;
			to = (struct ext3_dir_entry_2 *) (((char *) to) + rec_len);
		}
		de = next;
	}
	return prev;
}

/*
 * Split a full leaf block to make room for a new dir entry.
 * Allocate a new block, and move entries so that they are approx. equally full.
 * Returns pointer to de in block into which the new entry will be inserted.
 */
static struct ext3_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
			struct buffer_head **bh,struct dx_frame *frame,
			struct dx_hash_info *hinfo, int *error)
{
	unsigned blocksize = dir->i_sb->s_blocksize;
	unsigned count, continued;
	struct buffer_head *bh2;
	u32 newblock;
	u32 hash2;
	struct dx_map_entry *map;
	char *data1 = (*bh)->b_data, *data2;
	unsigned split, move, size;
	struct ext3_dir_entry_2 *de = NULL, *de2;
	int	err = 0, i;

	bh2 = ext3_append (handle, dir, &newblock, &err);
	if (!(bh2)) {
		brelse(*bh);
		*bh = NULL;
		goto errout;
	}

	BUFFER_TRACE(*bh, "get_write_access");
	err = ext3_journal_get_write_access(handle, *bh);
	if (err)
		goto journal_error;

	BUFFER_TRACE(frame->bh, "get_write_access");
	err = ext3_journal_get_write_access(handle, frame->bh);
	if (err)
		goto journal_error;

	data2 = bh2->b_data;

	/* create map in the end of data2 block */
	map = (struct dx_map_entry *) (data2 + blocksize);
	count = dx_make_map ((struct ext3_dir_entry_2 *) data1,
			     blocksize, hinfo, map);
	map -= count;
	dx_sort_map (map, count);
	/* Split the existing block in the middle, size-wise */
	size = 0;
	move = 0;
	for (i = count-1; i >= 0; i--) {
		/* is more than half of this entry in 2nd half of the block? */
		if (size + map[i].size/2 > blocksize/2)
			break;
		size += map[i].size;
		move++;
	}
	/* map index at which we will split */
	split = count - move;
	hash2 = map[split].hash;
	continued = hash2 == map[split - 1].hash;
	dxtrace(printk("Split block %i at %x, %i/%i\n",
		dx_get_block(frame->at), hash2, split, count-split));

	/* Fancy dance to stay within two buffers */
	de2 = dx_move_dirents(data1, data2, map + split, count - split);
	de = dx_pack_dirents(data1,blocksize);
	de->rec_len = ext3_rec_len_to_disk(data1 + blocksize - (char *) de);
	de2->rec_len = ext3_rec_len_to_disk(data2 + blocksize - (char *) de2);
	dxtrace(dx_show_leaf (hinfo, (struct ext3_dir_entry_2 *) data1, blocksize, 1));
	dxtrace(dx_show_leaf (hinfo, (struct ext3_dir_entry_2 *) data2, blocksize, 1));

	/* Which block gets the new entry? */
	if (hinfo->hash >= hash2)
	{
		swap(*bh, bh2);
		de = de2;
	}
	dx_insert_block (frame, hash2 + continued, newblock);
	err = ext3_journal_dirty_metadata (handle, bh2);
	if (err)
		goto journal_error;
	err = ext3_journal_dirty_metadata (handle, frame->bh);
	if (err)
		goto journal_error;
	brelse (bh2);
	dxtrace(dx_show_index ("frame", frame->entries));
	return de;

journal_error:
	brelse(*bh);
	brelse(bh2);
	*bh = NULL;
	ext3_std_error(dir->i_sb, err);
errout:
	*error = err;
	return NULL;
}


/*
 * Add a new entry into a directory (leaf) block.  If de is non-NULL,
 * it points to a directory entry which is guaranteed to be large
 * enough for new directory entry.  If de is NULL, then
 * add_dirent_to_buf will attempt search the directory block for
 * space.  It will return -ENOSPC if no space is available, and -EIO
 * and -EEXIST if directory entry already exists.
 *
 * NOTE!  bh is NOT released in the case where ENOSPC is returned.  In
 * all other cases bh is released.
 */
static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
			     struct inode *inode, struct ext3_dir_entry_2 *de,
			     struct buffer_head * bh)
{
	struct inode	*dir = dentry->d_parent->d_inode;
	const char	*name = dentry->d_name.name;
	int		namelen = dentry->d_name.len;
	unsigned long	offset = 0;
	unsigned short	reclen;
	int		nlen, rlen, err;
	char		*top;

	reclen = EXT3_DIR_REC_LEN(namelen);
	if (!de) {
		de = (struct ext3_dir_entry_2 *)bh->b_data;
		top = bh->b_data + dir->i_sb->s_blocksize - reclen;
		while ((char *) de <= top) {
			if (!ext3_check_dir_entry("ext3_add_entry", dir, de,
						  bh, offset)) {
				brelse (bh);
				return -EIO;
			}
			if (ext3_match (namelen, name, de)) {
				brelse (bh);
				return -EEXIST;
			}
			nlen = EXT3_DIR_REC_LEN(de->name_len);
			rlen = ext3_rec_len_from_disk(de->rec_len);
			if ((de->inode? rlen - nlen: rlen) >= reclen)
				break;
			de = (struct ext3_dir_entry_2 *)((char *)de + rlen);
			offset += rlen;
		}
		if ((char *) de > top)
			return -ENOSPC;
	}
	BUFFER_TRACE(bh, "get_write_access");
	err = ext3_journal_get_write_access(handle, bh);
	if (err) {
		ext3_std_error(dir->i_sb, err);
		brelse(bh);
		return err;
	}

	/* By now the buffer is marked for journaling */
	nlen = EXT3_DIR_REC_LEN(de->name_len);
	rlen = ext3_rec_len_from_disk(de->rec_len);
	if (de->inode) {
		struct ext3_dir_entry_2 *de1 = (struct ext3_dir_entry_2 *)((char *)de + nlen);
		de1->rec_len = ext3_rec_len_to_disk(rlen - nlen);
		de->rec_len = ext3_rec_len_to_disk(nlen);
		de = de1;
	}
	de->file_type = EXT3_FT_UNKNOWN;
	if (inode) {
		de->inode = cpu_to_le32(inode->i_ino);
		ext3_set_de_type(dir->i_sb, de, inode->i_mode);
	} else
		de->inode = 0;
	de->name_len = namelen;
	memcpy (de->name, name, namelen);
	/*
	 * XXX shouldn't update any times until successful
	 * completion of syscall, but too many callers depend
	 * on this.
	 *
	 * XXX similarly, too many callers depend on
	 * ext3_new_inode() setting the times, but error
	 * recovery deletes the inode, so the worst that can
	 * happen is that the times are slightly out of date
	 * and/or different from the directory change time.
	 */
	dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
	ext3_update_dx_flag(dir);
	dir->i_version++;
	ext3_mark_inode_dirty(handle, dir);
	BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
	err = ext3_journal_dirty_metadata(handle, bh);
	if (err)
		ext3_std_error(dir->i_sb, err);
	brelse(bh);
	return 0;
}

/*
 * This converts a one block unindexed directory to a 3 block indexed
 * directory, and adds the dentry to the indexed directory.
 */
static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
			    struct inode *inode, struct buffer_head *bh)
{
	struct inode	*dir = dentry->d_parent->d_inode;
	const char	*name = dentry->d_name.name;
	int		namelen = dentry->d_name.len;
	struct buffer_head *bh2;
	struct dx_root	*root;
	struct dx_frame	frames[2], *frame;
	struct dx_entry *entries;
	struct ext3_dir_entry_2	*de, *de2;
	char		*data1, *top;
	unsigned	len;
	int		retval;
	unsigned	blocksize;
	struct dx_hash_info hinfo;
	u32		block;
	struct fake_dirent *fde;

	blocksize =  dir->i_sb->s_blocksize;
	dxtrace(printk(KERN_DEBUG "Creating index: inode %lu\n", dir->i_ino));
	retval = ext3_journal_get_write_access(handle, bh);
	if (retval) {
		ext3_std_error(dir->i_sb, retval);
		brelse(bh);
		return retval;
	}
	root = (struct dx_root *) bh->b_data;

	/* The 0th block becomes the root, move the dirents out */
	fde = &root->dotdot;
	de = (struct ext3_dir_entry_2 *)((char *)fde +
			ext3_rec_len_from_disk(fde->rec_len));
	if ((char *) de >= (((char *) root) + blocksize)) {
		ext3_error(dir->i_sb, __func__,
			   "invalid rec_len for '..' in inode %lu",
			   dir->i_ino);
		brelse(bh);
		return -EIO;
	}
	len = ((char *) root) + blocksize - (char *) de;

	bh2 = ext3_append (handle, dir, &block, &retval);
	if (!(bh2)) {
		brelse(bh);
		return retval;
	}
	EXT3_I(dir)->i_flags |= EXT3_INDEX_FL;
	data1 = bh2->b_data;

	memcpy (data1, de, len);
	de = (struct ext3_dir_entry_2 *) data1;
	top = data1 + len;
	while ((char *)(de2 = ext3_next_entry(de)) < top)
		de = de2;
	de->rec_len = ext3_rec_len_to_disk(data1 + blocksize - (char *) de);
	/* Initialize the root; the dot dirents already exist */
	de = (struct ext3_dir_entry_2 *) (&root->dotdot);
	de->rec_len = ext3_rec_len_to_disk(blocksize - EXT3_DIR_REC_LEN(2));
	memset (&root->info, 0, sizeof(root->info));
	root->info.info_length = sizeof(root->info);
	root->info.hash_version = EXT3_SB(dir->i_sb)->s_def_hash_version;
	entries = root->entries;
	dx_set_block (entries, 1);
	dx_set_count (entries, 1);
	dx_set_limit (entries, dx_root_limit(dir, sizeof(root->info)));

	/* Initialize as for dx_probe */
	hinfo.hash_version = root->info.hash_version;
	if (hinfo.hash_version <= DX_HASH_TEA)
		hinfo.hash_version += EXT3_SB(dir->i_sb)->s_hash_unsigned;
	hinfo.seed = EXT3_SB(dir->i_sb)->s_hash_seed;
	ext3fs_dirhash(name, namelen, &hinfo);
	frame = frames;
	frame->entries = entries;
	frame->at = entries;
	frame->bh = bh;
	bh = bh2;
	/*
	 * Mark buffers dirty here so that if do_split() fails we write a
	 * consistent set of buffers to disk.
	 */
	ext3_journal_dirty_metadata(handle, frame->bh);
	ext3_journal_dirty_metadata(handle, bh);
	de = do_split(handle,dir, &bh, frame, &hinfo, &retval);
	if (!de) {
		ext3_mark_inode_dirty(handle, dir);
		dx_release(frames);
		return retval;
	}
	dx_release(frames);

	return add_dirent_to_buf(handle, dentry, inode, de, bh);
}

/*
 *	ext3_add_entry()
 *
 * adds a file entry to the specified directory, using the same
 * semantics as ext3_find_entry(). It returns NULL if it failed.
 *
 * NOTE!! The inode part of 'de' is left at 0 - which means you
 * may not sleep between calling this and putting something into
 * the entry, as someone else might have used it while you slept.
 */
static int ext3_add_entry (handle_t *handle, struct dentry *dentry,
	struct inode *inode)
{
	struct inode *dir = dentry->d_parent->d_inode;
	struct buffer_head * bh;
	struct ext3_dir_entry_2 *de;
	struct super_block * sb;
	int	retval;
	int	dx_fallback=0;
	unsigned blocksize;
	u32 block, blocks;

	sb = dir->i_sb;
	blocksize = sb->s_blocksize;
	if (!dentry->d_name.len)
		return -EINVAL;
	if (is_dx(dir)) {
		retval = ext3_dx_add_entry(handle, dentry, inode);
		if (!retval || (retval != ERR_BAD_DX_DIR))
			return retval;
		EXT3_I(dir)->i_flags &= ~EXT3_INDEX_FL;
		dx_fallback++;
		ext3_mark_inode_dirty(handle, dir);
	}
	blocks = dir->i_size >> sb->s_blocksize_bits;
	for (block = 0; block < blocks; block++) {
		if (!(bh = ext3_dir_bread(handle, dir, block, 0, &retval)))
			return retval;

		retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
		if (retval != -ENOSPC)
			return retval;

		if (blocks == 1 && !dx_fallback &&
		    EXT3_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_DIR_INDEX))
			return make_indexed_dir(handle, dentry, inode, bh);
		brelse(bh);
	}
	bh = ext3_append(handle, dir, &block, &retval);
	if (!bh)
		return retval;
	de = (struct ext3_dir_entry_2 *) bh->b_data;
	de->inode = 0;
	de->rec_len = ext3_rec_len_to_disk(blocksize);
	return add_dirent_to_buf(handle, dentry, inode, de, bh);
}

/*
 * Returns 0 for success, or a negative error value
 */
static int ext3_dx_add_entry(handle_t *handle, struct dentry *dentry,
			     struct inode *inode)
{
	struct dx_frame frames[2], *frame;
	struct dx_entry *entries, *at;
	struct dx_hash_info hinfo;
	struct buffer_head * bh;
	struct inode *dir = dentry->d_parent->d_inode;
	struct super_block * sb = dir->i_sb;
	struct ext3_dir_entry_2 *de;
	int err;

	frame = dx_probe(&dentry->d_name, dir, &hinfo, frames, &err);
	if (!frame)
		return err;
	entries = frame->entries;
	at = frame->at;

	if (!(bh = ext3_dir_bread(handle, dir, dx_get_block(frame->at), 0, &err)))
		goto cleanup;

	BUFFER_TRACE(bh, "get_write_access");
	err = ext3_journal_get_write_access(handle, bh);
	if (err)
		goto journal_error;

	err = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
	if (err != -ENOSPC) {
		bh = NULL;
		goto cleanup;
	}

	/* Block full, should compress but for now just split */
	dxtrace(printk("using %u of %u node entries\n",
		       dx_get_count(entries), dx_get_limit(entries)));
	/* Need to split index? */
	if (dx_get_count(entries) == dx_get_limit(entries)) {
		u32 newblock;
		unsigned icount = dx_get_count(entries);
		int levels = frame - frames;
		struct dx_entry *entries2;
		struct dx_node *node2;
		struct buffer_head *bh2;

		if (levels && (dx_get_count(frames->entries) ==
			       dx_get_limit(frames->entries))) {
			ext3_warning(sb, __func__,
				     "Directory index full!");
			err = -ENOSPC;
			goto cleanup;
		}
		bh2 = ext3_append (handle, dir, &newblock, &err);
		if (!(bh2))
			goto cleanup;
		node2 = (struct dx_node *)(bh2->b_data);
		entries2 = node2->entries;
		memset(&node2->fake, 0, sizeof(struct fake_dirent));
		node2->fake.rec_len = ext3_rec_len_to_disk(sb->s_blocksize);
		BUFFER_TRACE(frame->bh, "get_write_access");
		err = ext3_journal_get_write_access(handle, frame->bh);
		if (err)
			goto journal_error;
		if (levels) {
			unsigned icount1 = icount/2, icount2 = icount - icount1;
			unsigned hash2 = dx_get_hash(entries + icount1);
			dxtrace(printk("Split index %i/%i\n", icount1, icount2));

			BUFFER_TRACE(frame->bh, "get_write_access"); /* index root */
			err = ext3_journal_get_write_access(handle,
							     frames[0].bh);
			if (err)
				goto journal_error;

			memcpy ((char *) entries2, (char *) (entries + icount1),
				icount2 * sizeof(struct dx_entry));
			dx_set_count (entries, icount1);
			dx_set_count (entries2, icount2);
			dx_set_limit (entries2, dx_node_limit(dir));

			/* Which index block gets the new entry? */
			if (at - entries >= icount1) {
				frame->at = at = at - entries - icount1 + entries2;
				frame->entries = entries = entries2;
				swap(frame->bh, bh2);
			}
			dx_insert_block (frames + 0, hash2, newblock);
			dxtrace(dx_show_index ("node", frames[1].entries));
			dxtrace(dx_show_index ("node",
			       ((struct dx_node *) bh2->b_data)->entries));
			err = ext3_journal_dirty_metadata(handle, bh2);
			if (err)
				goto journal_error;
			brelse (bh2);
		} else {
			dxtrace(printk("Creating second level index...\n"));
			memcpy((char *) entries2, (char *) entries,
			       icount * sizeof(struct dx_entry));
			dx_set_limit(entries2, dx_node_limit(dir));

			/* Set up root */
			dx_set_count(entries, 1);
			dx_set_block(entries + 0, newblock);
			((struct dx_root *) frames[0].bh->b_data)->info.indirect_levels = 1;

			/* Add new access path frame */
			frame = frames + 1;
			frame->at = at = at - entries + entries2;
			frame->entries = entries = entries2;
			frame->bh = bh2;
			err = ext3_journal_get_write_access(handle,
							     frame->bh);
			if (err)
				goto journal_error;
		}
		err = ext3_journal_dirty_metadata(handle, frames[0].bh);
		if (err)
			goto journal_error;
	}
	de = do_split(handle, dir, &bh, frame, &hinfo, &err);
	if (!de)
		goto cleanup;
	err = add_dirent_to_buf(handle, dentry, inode, de, bh);
	bh = NULL;
	goto cleanup;

journal_error:
	ext3_std_error(dir->i_sb, err);
cleanup:
	if (bh)
		brelse(bh);
	dx_release(frames);
	return err;
}

/*
 * ext3_delete_entry deletes a directory entry by merging it with the
 * previous entry
 */
static int ext3_delete_entry (handle_t *handle,
			      struct inode * dir,
			      struct ext3_dir_entry_2 * de_del,
			      struct buffer_head * bh)
{
	struct ext3_dir_entry_2 * de, * pde;
	int i;

	i = 0;
	pde = NULL;
	de = (struct ext3_dir_entry_2 *) bh->b_data;
	while (i < bh->b_size) {
		if (!ext3_check_dir_entry("ext3_delete_entry", dir, de, bh, i))
			return -EIO;
		if (de == de_del)  {
			int err;

			BUFFER_TRACE(bh, "get_write_access");
			err = ext3_journal_get_write_access(handle, bh);
			if (err)
				goto journal_error;

			if (pde)
				pde->rec_len = ext3_rec_len_to_disk(
					ext3_rec_len_from_disk(pde->rec_len) +
					ext3_rec_len_from_disk(de->rec_len));
			else
				de->inode = 0;
			dir->i_version++;
			BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
			err = ext3_journal_dirty_metadata(handle, bh);
			if (err) {
journal_error:
				ext3_std_error(dir->i_sb, err);
				return err;
			}
			return 0;
		}
		i += ext3_rec_len_from_disk(de->rec_len);
		pde = de;
		de = ext3_next_entry(de);
	}
	return -ENOENT;
}

static int ext3_add_nondir(handle_t *handle,
		struct dentry *dentry, struct inode *inode)
{
	int err = ext3_add_entry(handle, dentry, inode);
	if (!err) {
		ext3_mark_inode_dirty(handle, inode);
		unlock_new_inode(inode);
		d_instantiate(dentry, inode);
		return 0;
	}
	drop_nlink(inode);
	unlock_new_inode(inode);
	iput(inode);
	return err;
}

/*
 * By the time this is called, we already have created
 * the directory cache entry for the new file, but it
 * is so far negative - it has no inode.
 *
 * If the create succeeds, we fill in the inode information
 * with d_instantiate().
 */
static int ext3_create (struct inode * dir, struct dentry * dentry, umode_t mode,
		bool excl)
{
	handle_t *handle;
	struct inode * inode;
	int err, retries = 0;

	dquot_initialize(dir);

retry:
	handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) +
					EXT3_INDEX_EXTRA_TRANS_BLOCKS + 3 +
					EXT3_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
	if (IS_ERR(handle))
		return PTR_ERR(handle);

	if (IS_DIRSYNC(dir))
		handle->h_sync = 1;

	inode = ext3_new_inode (handle, dir, &dentry->d_name, mode);
	err = PTR_ERR(inode);
	if (!IS_ERR(inode)) {
		inode->i_op = &ext3_file_inode_operations;
		inode->i_fop = &ext3_file_operations;
		ext3_set_aops(inode);
		err = ext3_add_nondir(handle, dentry, inode);
	}
	ext3_journal_stop(handle);
	if (err == -ENOSPC && ext3_should_retry_alloc(dir->i_sb, &retries))
		goto retry;
	return err;
}

static int ext3_mknod (struct inode * dir, struct dentry *dentry,
			umode_t mode, dev_t rdev)
{
	handle_t *handle;
	struct inode *inode;
	int err, retries = 0;

	if (!new_valid_dev(rdev))
		return -EINVAL;

	dquot_initialize(dir);

retry:
	handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) +
					EXT3_INDEX_EXTRA_TRANS_BLOCKS + 3 +
					EXT3_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
	if (IS_ERR(handle))
		return PTR_ERR(handle);

	if (IS_DIRSYNC(dir))
		handle->h_sync = 1;

	inode = ext3_new_inode (handle, dir, &dentry->d_name, mode);
	err = PTR_ERR(inode);
	if (!IS_ERR(inode)) {
		init_special_inode(inode, inode->i_mode, rdev);
#ifdef CONFIG_EXT3_FS_XATTR
		inode->i_op = &ext3_special_inode_operations;
#endif
		err = ext3_add_nondir(handle, dentry, inode);
	}
	ext3_journal_stop(handle);
	if (err == -ENOSPC && ext3_should_retry_alloc(dir->i_sb, &retries))
		goto retry;
	return err;
}

static int ext3_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
{
	handle_t *handle;
	struct inode *inode;
	int err, retries = 0;

	dquot_initialize(dir);

retry:
	handle = ext3_journal_start(dir, EXT3_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
			  4 + EXT3_XATTR_TRANS_BLOCKS);

	if (IS_ERR(handle))
		return PTR_ERR(handle);

	inode = ext3_new_inode (handle, dir, NULL, mode);
	err = PTR_ERR(inode);
	if (!IS_ERR(inode)) {
		inode->i_op = &ext3_file_inode_operations;
		inode->i_fop = &ext3_file_operations;
		ext3_set_aops(inode);
		d_tmpfile(dentry, inode);
		err = ext3_orphan_add(handle, inode);
		if (err)
			goto err_unlock_inode;
		mark_inode_dirty(inode);
		unlock_new_inode(inode);
	}
	ext3_journal_stop(handle);
	if (err == -ENOSPC && ext3_should_retry_alloc(dir->i_sb, &retries))
		goto retry;
	return err;
err_unlock_inode:
	ext3_journal_stop(handle);
	unlock_new_inode(inode);
	return err;
}

static int ext3_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
{
	handle_t *handle;
	struct inode * inode;
	struct buffer_head * dir_block = NULL;
	struct ext3_dir_entry_2 * de;
	int err, retries = 0;

	if (dir->i_nlink >= EXT3_LINK_MAX)
		return -EMLINK;

	dquot_initialize(dir);

retry:
	handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) +
					EXT3_INDEX_EXTRA_TRANS_BLOCKS + 3 +
					EXT3_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
	if (IS_ERR(handle))
		return PTR_ERR(handle);

	if (IS_DIRSYNC(dir))
		handle->h_sync = 1;

	inode = ext3_new_inode (handle, dir, &dentry->d_name, S_IFDIR | mode);
	err = PTR_ERR(inode);
	if (IS_ERR(inode))
		goto out_stop;

	inode->i_op = &ext3_dir_inode_operations;
	inode->i_fop = &ext3_dir_operations;
	inode->i_size = EXT3_I(inode)->i_disksize = inode->i_sb->s_blocksize;
	if (!(dir_block = ext3_dir_bread(handle, inode, 0, 1, &err)))
		goto out_clear_inode;

	BUFFER_TRACE(dir_block, "get_write_access");
	err = ext3_journal_get_write_access(handle, dir_block);
	if (err)
		goto out_clear_inode;

	de = (struct ext3_dir_entry_2 *) dir_block->b_data;
	de->inode = cpu_to_le32(inode->i_ino);
	de->name_len = 1;
	de->rec_len = ext3_rec_len_to_disk(EXT3_DIR_REC_LEN(de->name_len));
	strcpy (de->name, ".");
	ext3_set_de_type(dir->i_sb, de, S_IFDIR);
	de = ext3_next_entry(de);
	de->inode = cpu_to_le32(dir->i_ino);
	de->rec_len = ext3_rec_len_to_disk(inode->i_sb->s_blocksize -
					EXT3_DIR_REC_LEN(1));
	de->name_len = 2;
	strcpy (de->name, "..");
	ext3_set_de_type(dir->i_sb, de, S_IFDIR);
	set_nlink(inode, 2);
	BUFFER_TRACE(dir_block, "call ext3_journal_dirty_metadata");
	err = ext3_journal_dirty_metadata(handle, dir_block);
	if (err)
		goto out_clear_inode;

	err = ext3_mark_inode_dirty(handle, inode);
	if (!err)
		err = ext3_add_entry (handle, dentry, inode);

	if (err) {
out_clear_inode:
		clear_nlink(inode);
		unlock_new_inode(inode);
		ext3_mark_inode_dirty(handle, inode);
		iput (inode);
		goto out_stop;
	}
	inc_nlink(dir);
	ext3_update_dx_flag(dir);
	err = ext3_mark_inode_dirty(handle, dir);
	if (err)
		goto out_clear_inode;

	unlock_new_inode(inode);
	d_instantiate(dentry, inode);
out_stop:
	brelse(dir_block);
	ext3_journal_stop(handle);
	if (err == -ENOSPC && ext3_should_retry_alloc(dir->i_sb, &retries))
		goto retry;
	return err;
}

/*
 * routine to check that the specified directory is empty (for rmdir)
 */
static int empty_dir (struct inode * inode)
{
	unsigned long offset;
	struct buffer_head * bh;
	struct ext3_dir_entry_2 * de, * de1;
	struct super_block * sb;
	int err = 0;

	sb = inode->i_sb;
	if (inode->i_size < EXT3_DIR_REC_LEN(1) + EXT3_DIR_REC_LEN(2) ||
	    !(bh = ext3_dir_bread(NULL, inode, 0, 0, &err))) {
		if (err)
			ext3_error(inode->i_sb, __func__,
				   "error %d reading directory #%lu offset 0",
				   err, inode->i_ino);
		else
			ext3_warning(inode->i_sb, __func__,
				     "bad directory (dir #%lu) - no data block",
				     inode->i_ino);
		return 1;
	}
	de = (struct ext3_dir_entry_2 *) bh->b_data;
	de1 = ext3_next_entry(de);
	if (le32_to_cpu(de->inode) != inode->i_ino ||
			!le32_to_cpu(de1->inode) ||
			strcmp (".", de->name) ||
			strcmp ("..", de1->name)) {
		ext3_warning (inode->i_sb, "empty_dir",
			      "bad directory (dir #%lu) - no `.' or `..'",
			      inode->i_ino);
		brelse (bh);
		return 1;
	}
	offset = ext3_rec_len_from_disk(de->rec_len) +
			ext3_rec_len_from_disk(de1->rec_len);
	de = ext3_next_entry(de1);
	while (offset < inode->i_size ) {
		if (!bh ||
			(void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
			err = 0;
			brelse (bh);
			if (!(bh = ext3_dir_bread (NULL, inode,
				offset >> EXT3_BLOCK_SIZE_BITS(sb), 0, &err))) {
				if (err)
					ext3_error(sb, __func__,
						   "error %d reading directory"
						   " #%lu offset %lu",
						   err, inode->i_ino, offset);
				offset += sb->s_blocksize;
				continue;
			}
			de = (struct ext3_dir_entry_2 *) bh->b_data;
		}
		if (!ext3_check_dir_entry("empty_dir", inode, de, bh, offset)) {
			de = (struct ext3_dir_entry_2 *)(bh->b_data +
							 sb->s_blocksize);
			offset = (offset | (sb->s_blocksize - 1)) + 1;
			continue;
		}
		if (le32_to_cpu(de->inode)) {
			brelse (bh);
			return 0;
		}
		offset += ext3_rec_len_from_disk(de->rec_len);
		de = ext3_next_entry(de);
	}
	brelse (bh);
	return 1;
}

/* ext3_orphan_add() links an unlinked or truncated inode into a list of
 * such inodes, starting at the superblock, in case we crash before the
 * file is closed/deleted, or in case the inode truncate spans multiple
 * transactions and the last transaction is not recovered after a crash.
 *
 * At filesystem recovery time, we walk this list deleting unlinked
 * inodes and truncating linked inodes in ext3_orphan_cleanup().
 */
int ext3_orphan_add(handle_t *handle, struct inode *inode)
{
	struct super_block *sb = inode->i_sb;
	struct ext3_iloc iloc;
	int err = 0, rc;

	mutex_lock(&EXT3_SB(sb)->s_orphan_lock);
	if (!list_empty(&EXT3_I(inode)->i_orphan))
		goto out_unlock;

	/* Orphan handling is only valid for files with data blocks
	 * being truncated, or files being unlinked. */

	/* @@@ FIXME: Observation from aviro:
	 * I think I can trigger J_ASSERT in ext3_orphan_add().  We block
	 * here (on s_orphan_lock), so race with ext3_link() which might bump
	 * ->i_nlink. For, say it, character device. Not a regular file,
	 * not a directory, not a symlink and ->i_nlink > 0.
	 *
	 * tytso, 4/25/2009: I'm not sure how that could happen;
	 * shouldn't the fs core protect us from these sort of
	 * unlink()/link() races?
	 */
	J_ASSERT ((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
		S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);

	BUFFER_TRACE(EXT3_SB(sb)->s_sbh, "get_write_access");
	err = ext3_journal_get_write_access(handle, EXT3_SB(sb)->s_sbh);
	if (err)
		goto out_unlock;

	err = ext3_reserve_inode_write(handle, inode, &iloc);
	if (err)
		goto out_unlock;

	/* Insert this inode at the head of the on-disk orphan list... */
	NEXT_ORPHAN(inode) = le32_to_cpu(EXT3_SB(sb)->s_es->s_last_orphan);
	EXT3_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
	err = ext3_journal_dirty_metadata(handle, EXT3_SB(sb)->s_sbh);
	rc = ext3_mark_iloc_dirty(handle, inode, &iloc);
	if (!err)
		err = rc;

	/* Only add to the head of the in-memory list if all the
	 * previous operations succeeded.  If the orphan_add is going to
	 * fail (possibly taking the journal offline), we can't risk
	 * leaving the inode on the orphan list: stray orphan-list
	 * entries can cause panics at unmount time.
	 *
	 * This is safe: on error we're going to ignore the orphan list
	 * anyway on the next recovery. */
	if (!err)
		list_add(&EXT3_I(inode)->i_orphan, &EXT3_SB(sb)->s_orphan);

	jbd_debug(4, "superblock will point to %lu\n", inode->i_ino);
	jbd_debug(4, "orphan inode %lu will point to %d\n",
			inode->i_ino, NEXT_ORPHAN(inode));
out_unlock:
	mutex_unlock(&EXT3_SB(sb)->s_orphan_lock);
	ext3_std_error(inode->i_sb, err);
	return err;
}

/*
 * ext3_orphan_del() removes an unlinked or truncated inode from the list
 * of such inodes stored on disk, because it is finally being cleaned up.
 */
int ext3_orphan_del(handle_t *handle, struct inode *inode)
{
	struct list_head *prev;
	struct ext3_inode_info *ei = EXT3_I(inode);
	struct ext3_sb_info *sbi;
	unsigned long ino_next;
	struct ext3_iloc iloc;
	int err = 0;

	mutex_lock(&EXT3_SB(inode->i_sb)->s_orphan_lock);
	if (list_empty(&ei->i_orphan))
		goto out;

	ino_next = NEXT_ORPHAN(inode);
	prev = ei->i_orphan.prev;
	sbi = EXT3_SB(inode->i_sb);

	jbd_debug(4, "remove inode %lu from orphan list\n", inode->i_ino);

	list_del_init(&ei->i_orphan);

	/* If we're on an error path, we may not have a valid
	 * transaction handle with which to update the orphan list on
	 * disk, but we still need to remove the inode from the linked
	 * list in memory. */
	if (!handle)
		goto out;

	err = ext3_reserve_inode_write(handle, inode, &iloc);
	if (err)
		goto out_err;

	if (prev == &sbi->s_orphan) {
		jbd_debug(4, "superblock will point to %lu\n", ino_next);
		BUFFER_TRACE(sbi->s_sbh, "get_write_access");
		err = ext3_journal_get_write_access(handle, sbi->s_sbh);
		if (err)
			goto out_brelse;
		sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
		err = ext3_journal_dirty_metadata(handle, sbi->s_sbh);
	} else {
		struct ext3_iloc iloc2;
		struct inode *i_prev =
			&list_entry(prev, struct ext3_inode_info, i_orphan)->vfs_inode;

		jbd_debug(4, "orphan inode %lu will point to %lu\n",
			  i_prev->i_ino, ino_next);
		err = ext3_reserve_inode_write(handle, i_prev, &iloc2);
		if (err)
			goto out_brelse;
		NEXT_ORPHAN(i_prev) = ino_next;
		err = ext3_mark_iloc_dirty(handle, i_prev, &iloc2);
	}
	if (err)
		goto out_brelse;
	NEXT_ORPHAN(inode) = 0;
	err = ext3_mark_iloc_dirty(handle, inode, &iloc);

out_err:
	ext3_std_error(inode->i_sb, err);
out:
	mutex_unlock(&EXT3_SB(inode->i_sb)->s_orphan_lock);
	return err;

out_brelse:
	brelse(iloc.bh);
	goto out_err;
}

static int ext3_rmdir (struct inode * dir, struct dentry *dentry)
{
	int retval;
	struct inode * inode;
	struct buffer_head * bh;
	struct ext3_dir_entry_2 * de;
	handle_t *handle;

	/* Initialize quotas before so that eventual writes go in
	 * separate transaction */
	dquot_initialize(dir);
	dquot_initialize(dentry->d_inode);

	handle = ext3_journal_start(dir, EXT3_DELETE_TRANS_BLOCKS(dir->i_sb));
	if (IS_ERR(handle))
		return PTR_ERR(handle);

	retval = -ENOENT;
	bh = ext3_find_entry(dir, &dentry->d_name, &de);
	if (!bh)
		goto end_rmdir;

	if (IS_DIRSYNC(dir))
		handle->h_sync = 1;

	inode = dentry->d_inode;

	retval = -EIO;
	if (le32_to_cpu(de->inode) != inode->i_ino)
		goto end_rmdir;

	retval = -ENOTEMPTY;
	if (!empty_dir (inode))
		goto end_rmdir;

	retval = ext3_delete_entry(handle, dir, de, bh);
	if (retval)
		goto end_rmdir;
	if (inode->i_nlink != 2)
		ext3_warning (inode->i_sb, "ext3_rmdir",
			      "empty directory has nlink!=2 (%d)",
			      inode->i_nlink);
	inode->i_version++;
	clear_nlink(inode);
	/* There's no need to set i_disksize: the fact that i_nlink is
	 * zero will ensure that the right thing happens during any
	 * recovery. */
	inode->i_size = 0;
	ext3_orphan_add(handle, inode);
	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC;
	ext3_mark_inode_dirty(handle, inode);
	drop_nlink(dir);
	ext3_update_dx_flag(dir);
	ext3_mark_inode_dirty(handle, dir);

end_rmdir:
	ext3_journal_stop(handle);
	brelse (bh);
	return retval;
}

static int ext3_unlink(struct inode * dir, struct dentry *dentry)
{
	int retval;
	struct inode * inode;
	struct buffer_head * bh;
	struct ext3_dir_entry_2 * de;
	handle_t *handle;

	trace_ext3_unlink_enter(dir, dentry);
	/* Initialize quotas before so that eventual writes go
	 * in separate transaction */
	dquot_initialize(dir);
	dquot_initialize(dentry->d_inode);

	handle = ext3_journal_start(dir, EXT3_DELETE_TRANS_BLOCKS(dir->i_sb));
	if (IS_ERR(handle))
		return PTR_ERR(handle);

	if (IS_DIRSYNC(dir))
		handle->h_sync = 1;

	retval = -ENOENT;
	bh = ext3_find_entry(dir, &dentry->d_name, &de);
	if (!bh)
		goto end_unlink;

	inode = dentry->d_inode;

	retval = -EIO;
	if (le32_to_cpu(de->inode) != inode->i_ino)
		goto end_unlink;

	if (!inode->i_nlink) {
		ext3_warning (inode->i_sb, "ext3_unlink",
			      "Deleting nonexistent file (%lu), %d",
			      inode->i_ino, inode->i_nlink);
		set_nlink(inode, 1);
	}
	retval = ext3_delete_entry(handle, dir, de, bh);
	if (retval)
		goto end_unlink;
	dir->i_ctime = dir->i_mtime = CURRENT_TIME_SEC;
	ext3_update_dx_flag(dir);
	ext3_mark_inode_dirty(handle, dir);
	drop_nlink(inode);
	if (!inode->i_nlink)
		ext3_orphan_add(handle, inode);
	inode->i_ctime = dir->i_ctime;
	ext3_mark_inode_dirty(handle, inode);
	retval = 0;

end_unlink:
	ext3_journal_stop(handle);
	brelse (bh);
	trace_ext3_unlink_exit(dentry, retval);
	return retval;
}

static int ext3_symlink (struct inode * dir,
		struct dentry *dentry, const char * symname)
{
	handle_t *handle;
	struct inode * inode;
	int l, err, retries = 0;
	int credits;

	l = strlen(symname)+1;
	if (l > dir->i_sb->s_blocksize)
		return -ENAMETOOLONG;

	dquot_initialize(dir);

	if (l > EXT3_N_BLOCKS * 4) {
		/*
		 * For non-fast symlinks, we just allocate inode and put it on
		 * orphan list in the first transaction => we need bitmap,
		 * group descriptor, sb, inode block, quota blocks, and
		 * possibly selinux xattr blocks.
		 */
		credits = 4 + EXT3_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
			  EXT3_XATTR_TRANS_BLOCKS;
	} else {
		/*
		 * Fast symlink. We have to add entry to directory
		 * (EXT3_DATA_TRANS_BLOCKS + EXT3_INDEX_EXTRA_TRANS_BLOCKS),
		 * allocate new inode (bitmap, group descriptor, inode block,
		 * quota blocks, sb is already counted in previous macros).
		 */
		credits = EXT3_DATA_TRANS_BLOCKS(dir->i_sb) +
			  EXT3_INDEX_EXTRA_TRANS_BLOCKS + 3 +
			  EXT3_MAXQUOTAS_INIT_BLOCKS(dir->i_sb);
	}
retry:
	handle = ext3_journal_start(dir, credits);
	if (IS_ERR(handle))
		return PTR_ERR(handle);

	if (IS_DIRSYNC(dir))
		handle->h_sync = 1;

	inode = ext3_new_inode (handle, dir, &dentry->d_name, S_IFLNK|S_IRWXUGO);
	err = PTR_ERR(inode);
	if (IS_ERR(inode))
		goto out_stop;

	if (l > EXT3_N_BLOCKS * 4) {
		inode->i_op = &ext3_symlink_inode_operations;
		ext3_set_aops(inode);
		/*
		 * We cannot call page_symlink() with transaction started
		 * because it calls into ext3_write_begin() which acquires page
		 * lock which ranks below transaction start (and it can also
		 * wait for journal commit if we are running out of space). So
		 * we have to stop transaction now and restart it when symlink
		 * contents is written. 
		 *
		 * To keep fs consistent in case of crash, we have to put inode
		 * to orphan list in the mean time.
		 */
		drop_nlink(inode);
		err = ext3_orphan_add(handle, inode);
		ext3_journal_stop(handle);
		if (err)
			goto err_drop_inode;
		err = __page_symlink(inode, symname, l, 1);
		if (err)
			goto err_drop_inode;
		/*
		 * Now inode is being linked into dir (EXT3_DATA_TRANS_BLOCKS
		 * + EXT3_INDEX_EXTRA_TRANS_BLOCKS), inode is also modified
		 */
		handle = ext3_journal_start(dir,
				EXT3_DATA_TRANS_BLOCKS(dir->i_sb) +
				EXT3_INDEX_EXTRA_TRANS_BLOCKS + 1);
		if (IS_ERR(handle)) {
			err = PTR_ERR(handle);
			goto err_drop_inode;
		}
		set_nlink(inode, 1);
		err = ext3_orphan_del(handle, inode);
		if (err) {
			ext3_journal_stop(handle);
			drop_nlink(inode);
			goto err_drop_inode;
		}
	} else {
		inode->i_op = &ext3_fast_symlink_inode_operations;
		memcpy((char*)&EXT3_I(inode)->i_data,symname,l);
		inode->i_size = l-1;
	}
	EXT3_I(inode)->i_disksize = inode->i_size;
	err = ext3_add_nondir(handle, dentry, inode);
out_stop:
	ext3_journal_stop(handle);
	if (err == -ENOSPC && ext3_should_retry_alloc(dir->i_sb, &retries))
		goto retry;
	return err;
err_drop_inode:
	unlock_new_inode(inode);
	iput(inode);
	return err;
}

static int ext3_link (struct dentry * old_dentry,
		struct inode * dir, struct dentry *dentry)
{
	handle_t *handle;
	struct inode *inode = old_dentry->d_inode;
	int err, retries = 0;

	if (inode->i_nlink >= EXT3_LINK_MAX)
		return -EMLINK;

	dquot_initialize(dir);

retry:
	handle = ext3_journal_start(dir, EXT3_DATA_TRANS_BLOCKS(dir->i_sb) +
					EXT3_INDEX_EXTRA_TRANS_BLOCKS + 1);
	if (IS_ERR(handle))
		return PTR_ERR(handle);

	if (IS_DIRSYNC(dir))
		handle->h_sync = 1;

	inode->i_ctime = CURRENT_TIME_SEC;
	inc_nlink(inode);
	ihold(inode);

	err = ext3_add_entry(handle, dentry, inode);
	if (!err) {
		ext3_mark_inode_dirty(handle, inode);
		/* this can happen only for tmpfile being
		 * linked the first time
		 */
		if (inode->i_nlink == 1)
			ext3_orphan_del(handle, inode);
		d_instantiate(dentry, inode);
	} else {
		drop_nlink(inode);
		iput(inode);
	}
	ext3_journal_stop(handle);
	if (err == -ENOSPC && ext3_should_retry_alloc(dir->i_sb, &retries))
		goto retry;
	return err;
}

#define PARENT_INO(buffer) \
	(ext3_next_entry((struct ext3_dir_entry_2 *)(buffer))->inode)

/*
 * Anybody can rename anything with this: the permission checks are left to the
 * higher-level routines.
 */
static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry,
			   struct inode * new_dir,struct dentry *new_dentry)
{
	handle_t *handle;
	struct inode * old_inode, * new_inode;
	struct buffer_head * old_bh, * new_bh, * dir_bh;
	struct ext3_dir_entry_2 * old_de, * new_de;
	int retval, flush_file = 0;

	dquot_initialize(old_dir);
	dquot_initialize(new_dir);

	old_bh = new_bh = dir_bh = NULL;

	/* Initialize quotas before so that eventual writes go
	 * in separate transaction */
	if (new_dentry->d_inode)
		dquot_initialize(new_dentry->d_inode);
	handle = ext3_journal_start(old_dir, 2 *
					EXT3_DATA_TRANS_BLOCKS(old_dir->i_sb) +
					EXT3_INDEX_EXTRA_TRANS_BLOCKS + 2);
	if (IS_ERR(handle))
		return PTR_ERR(handle);

	if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
		handle->h_sync = 1;

	old_bh = ext3_find_entry(old_dir, &old_dentry->d_name, &old_de);
	/*
	 *  Check for inode number is _not_ due to possible IO errors.
	 *  We might rmdir the source, keep it as pwd of some process
	 *  and merrily kill the link to whatever was created under the
	 *  same name. Goodbye sticky bit ;-<
	 */
	old_inode = old_dentry->d_inode;
	retval = -ENOENT;
	if (!old_bh || le32_to_cpu(old_de->inode) != old_inode->i_ino)
		goto end_rename;

	new_inode = new_dentry->d_inode;
	new_bh = ext3_find_entry(new_dir, &new_dentry->d_name, &new_de);
	if (new_bh) {
		if (!new_inode) {
			brelse (new_bh);
			new_bh = NULL;
		}
	}
	if (S_ISDIR(old_inode->i_mode)) {
		if (new_inode) {
			retval = -ENOTEMPTY;
			if (!empty_dir (new_inode))
				goto end_rename;
		}
		retval = -EIO;
		dir_bh = ext3_dir_bread(handle, old_inode, 0, 0, &retval);
		if (!dir_bh)
			goto end_rename;
		if (le32_to_cpu(PARENT_INO(dir_bh->b_data)) != old_dir->i_ino)
			goto end_rename;
		retval = -EMLINK;
		if (!new_inode && new_dir!=old_dir &&
				new_dir->i_nlink >= EXT3_LINK_MAX)
			goto end_rename;
	}
	if (!new_bh) {
		retval = ext3_add_entry (handle, new_dentry, old_inode);
		if (retval)
			goto end_rename;
	} else {
		BUFFER_TRACE(new_bh, "get write access");
		retval = ext3_journal_get_write_access(handle, new_bh);
		if (retval)
			goto journal_error;
		new_de->inode = cpu_to_le32(old_inode->i_ino);
		if (EXT3_HAS_INCOMPAT_FEATURE(new_dir->i_sb,
					      EXT3_FEATURE_INCOMPAT_FILETYPE))
			new_de->file_type = old_de->file_type;
		new_dir->i_version++;
		new_dir->i_ctime = new_dir->i_mtime = CURRENT_TIME_SEC;
		ext3_mark_inode_dirty(handle, new_dir);
		BUFFER_TRACE(new_bh, "call ext3_journal_dirty_metadata");
		retval = ext3_journal_dirty_metadata(handle, new_bh);
		if (retval)
			goto journal_error;
		brelse(new_bh);
		new_bh = NULL;
	}

	/*
	 * Like most other Unix systems, set the ctime for inodes on a
	 * rename.
	 */
	old_inode->i_ctime = CURRENT_TIME_SEC;
	ext3_mark_inode_dirty(handle, old_inode);

	/*
	 * ok, that's it
	 */
	if (le32_to_cpu(old_de->inode) != old_inode->i_ino ||
	    old_de->name_len != old_dentry->d_name.len ||
	    strncmp(old_de->name, old_dentry->d_name.name, old_de->name_len) ||
	    (retval = ext3_delete_entry(handle, old_dir,
					old_de, old_bh)) == -ENOENT) {
		/* old_de could have moved from under us during htree split, so
		 * make sure that we are deleting the right entry.  We might
		 * also be pointing to a stale entry in the unused part of
		 * old_bh so just checking inum and the name isn't enough. */
		struct buffer_head *old_bh2;
		struct ext3_dir_entry_2 *old_de2;

		old_bh2 = ext3_find_entry(old_dir, &old_dentry->d_name,
					  &old_de2);
		if (old_bh2) {
			retval = ext3_delete_entry(handle, old_dir,
						   old_de2, old_bh2);
			brelse(old_bh2);
		}
	}
	if (retval) {
		ext3_warning(old_dir->i_sb, "ext3_rename",
				"Deleting old file (%lu), %d, error=%d",
				old_dir->i_ino, old_dir->i_nlink, retval);
	}

	if (new_inode) {
		drop_nlink(new_inode);
		new_inode->i_ctime = CURRENT_TIME_SEC;
	}
	old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME_SEC;
	ext3_update_dx_flag(old_dir);
	if (dir_bh) {
		BUFFER_TRACE(dir_bh, "get_write_access");
		retval = ext3_journal_get_write_access(handle, dir_bh);
		if (retval)
			goto journal_error;
		PARENT_INO(dir_bh->b_data) = cpu_to_le32(new_dir->i_ino);
		BUFFER_TRACE(dir_bh, "call ext3_journal_dirty_metadata");
		retval = ext3_journal_dirty_metadata(handle, dir_bh);
		if (retval) {
journal_error:
			ext3_std_error(new_dir->i_sb, retval);
			goto end_rename;
		}
		drop_nlink(old_dir);
		if (new_inode) {
			drop_nlink(new_inode);
		} else {
			inc_nlink(new_dir);
			ext3_update_dx_flag(new_dir);
			ext3_mark_inode_dirty(handle, new_dir);
		}
	}
	ext3_mark_inode_dirty(handle, old_dir);
	if (new_inode) {
		ext3_mark_inode_dirty(handle, new_inode);
		if (!new_inode->i_nlink)
			ext3_orphan_add(handle, new_inode);
		if (ext3_should_writeback_data(new_inode))
			flush_file = 1;
	}
	retval = 0;

end_rename:
	brelse (dir_bh);
	brelse (old_bh);
	brelse (new_bh);
	ext3_journal_stop(handle);
	if (retval == 0 && flush_file)
		filemap_flush(old_inode->i_mapping);
	return retval;
}

/*
 * directories can handle most operations...
 */
const struct inode_operations ext3_dir_inode_operations = {
	.create		= ext3_create,
	.lookup		= ext3_lookup,
	.link		= ext3_link,
	.unlink		= ext3_unlink,
	.symlink	= ext3_symlink,
	.mkdir		= ext3_mkdir,
	.rmdir		= ext3_rmdir,
	.mknod		= ext3_mknod,
	.tmpfile	= ext3_tmpfile,
	.rename		= ext3_rename,
	.setattr	= ext3_setattr,
#ifdef CONFIG_EXT3_FS_XATTR
	.setxattr	= generic_setxattr,
	.getxattr	= generic_getxattr,
	.listxattr	= ext3_listxattr,
	.removexattr	= generic_removexattr,
#endif
	.get_acl	= ext3_get_acl,
	.set_acl	= ext3_set_acl,
};

const struct inode_operations ext3_special_inode_operations = {
	.setattr	= ext3_setattr,
#ifdef CONFIG_EXT3_FS_XATTR
	.setxattr	= generic_setxattr,
	.getxattr	= generic_getxattr,
	.listxattr	= ext3_listxattr,
	.removexattr	= generic_removexattr,
#endif
	.get_acl	= ext3_get_acl,
	.set_acl	= ext3_set_acl,
};