/* The kernel log module. * * This is an abstracted module. As Linux and BSD kernel log is conceptually the * same, we do not do different input plugins for them but use * imklog in both cases, just with different "backend drivers" for * the different platforms. This also enables a rsyslog.conf to * be used on multiple platforms without the need to take care of * what the kernel log is coming from. * * See platform-specific files (e.g. linux.c, bsd.c) in the plugin's * working directory. For other systems with similar kernel logging * functionality, no new input plugin shall be written but rather a * driver be developed for imklog. Please note that imklog itself is * mostly concerned with handling the interface. Any real action happens * in the drivers, as things may be pretty different on different * platforms. * * Please note that this file replaces the klogd daemon that was * also present in pre-v3 versions of rsyslog. * * Copyright (C) 2008 by Rainer Gerhards and Adiscon GmbH * * This file is part of rsyslog. * * Rsyslog is free software: you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation, either version 3 of the License, or * (at your option) any later version. * * Rsyslog is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with Rsyslog. If not, see . * * A copy of the GPL can be found in the file "COPYING" in this distribution. */ #include "config.h" #include "rsyslog.h" #include #include #include #include #include #include "dirty.h" #include "cfsysline.h" #include "obj.h" #include "msg.h" #include "module-template.h" #include "datetime.h" #include "imklog.h" #include "glbl.h" #include "unicode-helper.h" MODULE_TYPE_INPUT /* Module static data */ DEF_IMOD_STATIC_DATA DEFobjCurrIf(datetime) DEFobjCurrIf(glbl) /* configuration settings */ int dbgPrintSymbols = 0; /* this one is extern so the helpers can access it! */ int symbols_twice = 0; int use_syscall = 0; int symbol_lookup = 0; /* on recent kernels > 2.6, the kernel does this */ int bPermitNonKernel = 0; /* permit logging of messages not having LOG_KERN facility */ int iFacilIntMsg; /* the facility to use for internal messages (set by driver) */ /* TODO: configuration for the following directives must be implemented. It * was not done yet because we either do not yet have a config handler for * that type or I thought it was acceptable to push it to a later stage when * I gained more handson experience with the input module interface (and the * changes resulting from that). -- rgerhards, 2007-12-20 */ char *symfile = NULL; int console_log_level = -1; /* enqueue the the kernel message into the message queue. * The provided msg string is not freed - thus must be done * by the caller. * rgerhards, 2008-04-12 */ static rsRetVal enqMsg(uchar *msg, uchar* pszTag, int iFacility, int iSeverity) { DEFiRet; msg_t *pMsg; assert(msg != NULL); assert(pszTag != NULL); CHKiRet(msgConstruct(&pMsg)); MsgSetFlowControlType(pMsg, eFLOWCTL_LIGHT_DELAY); MsgSetInputName(pMsg, UCHAR_CONSTANT("imklog"), sizeof("imklog")-1); MsgSetRawMsg(pMsg, (char*)msg); MsgSetMSG(pMsg, (char*)msg); MsgSetRcvFrom(pMsg, glbl.GetLocalHostName()); MsgSetRcvFromIP(pMsg, (uchar*)"127.0.0.1"); MsgSetHOSTNAME(pMsg, glbl.GetLocalHostName()); MsgSetTAG(pMsg, (char*)pszTag); pMsg->iFacility = LOG_FAC(iFacility); pMsg->iSeverity = LOG_PRI(iSeverity); pMsg->bParseHOSTNAME = 0; CHKiRet(submitMsg(pMsg)); finalize_it: RETiRet; } /* parse the PRI from a kernel message. At least BSD seems to have * non-kernel messages inside the kernel log... * Expected format: "". piPri is only valid if the function * successfully returns. If there was a proper pri ppSz is advanced to the * position right after ">". * rgerhards, 2008-04-14 */ static rsRetVal parsePRI(uchar **ppSz, int *piPri) { DEFiRet; int i; uchar *pSz; assert(ppSz != NULL); pSz = *ppSz; assert(pSz != NULL); assert(piPri != NULL); if(*pSz != '<' || !isdigit(*(pSz+1))) ABORT_FINALIZE(RS_RET_INVALID_PRI); ++pSz; i = 0; while(isdigit(*pSz)) { i = i * 10 + *pSz++ - '0'; } if(*pSz != '>') ABORT_FINALIZE(RS_RET_INVALID_PRI); /* OK, we have a valid PRI */ *piPri = i; *ppSz = pSz + 1; /* update msg ptr to position after PRI */ finalize_it: RETiRet; } /* log an imklog-internal message * rgerhards, 2008-04-14 */ rsRetVal imklogLogIntMsg(int priority, char *fmt, ...) { DEFiRet; va_list ap; uchar msgBuf[2048]; /* we use the same size as sysklogd to remain compatible */ uchar *pLogMsg; va_start(ap, fmt); vsnprintf((char*)msgBuf, sizeof(msgBuf) / sizeof(char), fmt, ap); pLogMsg = msgBuf; va_end(ap); iRet = enqMsg((uchar*)pLogMsg, (uchar*) ((iFacilIntMsg == LOG_KERN) ? "kernel:" : "imklog:"), iFacilIntMsg, LOG_PRI(priority)); RETiRet; } /* log a kernel message * rgerhards, 2008-04-14 */ rsRetVal Syslog(int priority, uchar *pMsg) { DEFiRet; rsRetVal localRet; /* Output using syslog */ localRet = parsePRI(&pMsg, &priority); if(localRet != RS_RET_INVALID_PRI && localRet != RS_RET_OK) FINALIZE; /* if we don't get the pri, we use whatever we were supplied */ /* ignore non-kernel messages if not permitted */ if(bPermitNonKernel == 0 && LOG_FAC(priority) != LOG_KERN) FINALIZE; /* silently ignore */ iRet = enqMsg((uchar*)pMsg, (uchar*) "kernel:", LOG_FAC(priority), LOG_PRI(priority)); finalize_it: RETiRet; } /* helper for some klog drivers which need to know the MaxLine global setting. They can * not obtain it themselfs, because they are no modules and can not query the object hander. * It would probably be a good idea to extend the interface to support it, but so far * we create a (sufficiently valid) work-around. -- rgerhards, 2008-11-24 */ int klog_getMaxLine(void) { return glbl.GetMaxLine(); } BEGINrunInput CODESTARTrunInput /* this is an endless loop - it is terminated when the thread is * signalled to do so. This, however, is handled by the framework, * right into the sleep below. */ while(!pThrd->bShallStop) { /* klogLogKMsg() waits for the next kernel message, obtains it * and then submits it to the rsyslog main queue. * rgerhards, 2008-04-09 */ CHKiRet(klogLogKMsg()); } finalize_it: ENDrunInput BEGINwillRun CODESTARTwillRun iRet = klogWillRun(); ENDwillRun BEGINafterRun CODESTARTafterRun iRet = klogAfterRun(); ENDafterRun BEGINmodExit CODESTARTmodExit /* release objects we used */ objRelease(glbl, CORE_COMPONENT); objRelease(datetime, CORE_COMPONENT); ENDmodExit BEGINqueryEtryPt CODESTARTqueryEtryPt CODEqueryEtryPt_STD_IMOD_QUERIES ENDqueryEtryPt static rsRetVal resetConfigVariables(uchar __attribute__((unused)) *pp, void __attribute__((unused)) *pVal) { dbgPrintSymbols = 0; symbols_twice = 0; use_syscall = 0; symfile = NULL; symbol_lookup = 0; bPermitNonKernel = 0; iFacilIntMsg = klogFacilIntMsg(); return RS_RET_OK; } BEGINmodInit() CODESTARTmodInit *ipIFVersProvided = CURR_MOD_IF_VERSION; /* we only support the current interface specification */ CODEmodInit_QueryRegCFSLineHdlr CHKiRet(objUse(datetime, CORE_COMPONENT)); CHKiRet(objUse(glbl, CORE_COMPONENT)); iFacilIntMsg = klogFacilIntMsg(); CHKiRet(omsdRegCFSLineHdlr((uchar *)"debugprintkernelsymbols", 0, eCmdHdlrBinary, NULL, &dbgPrintSymbols, STD_LOADABLE_MODULE_ID)); CHKiRet(omsdRegCFSLineHdlr((uchar *)"klogsymbollookup", 0, eCmdHdlrBinary, NULL, &symbol_lookup, STD_LOADABLE_MODULE_ID)); CHKiRet(omsdRegCFSLineHdlr((uchar *)"klogsymbolstwice", 0, eCmdHdlrBinary, NULL, &symbols_twice, STD_LOADABLE_MODULE_ID)); CHKiRet(omsdRegCFSLineHdlr((uchar *)"klogusesyscallinterface", 0, eCmdHdlrBinary, NULL, &use_syscall, STD_LOADABLE_MODULE_ID)); CHKiRet(omsdRegCFSLineHdlr((uchar *)"klogpermitnonkernelfacility", 0, eCmdHdlrBinary, NULL, &bPermitNonKernel, STD_LOADABLE_MODULE_ID)); CHKiRet(omsdRegCFSLineHdlr((uchar *)"kloginternalmsgfacility", 0, eCmdHdlrFacility, NULL, &iFacilIntMsg, STD_LOADABLE_MODULE_ID)); CHKiRet(omsdRegCFSLineHdlr((uchar *)"resetconfigvariables", 1, eCmdHdlrCustomHandler, resetConfigVariables, NULL, STD_LOADABLE_MODULE_ID)); ENDmodInit /* vim:set ai: */ a> 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 
/*
 * Copyright (c) 2000-2006 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include <linux/log2.h>

#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_imap.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_dir2_sf.h"
#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_buf_item.h"
#include "xfs_inode_item.h"
#include "xfs_btree.h"
#include "xfs_alloc.h"
#include "xfs_ialloc.h"
#include "xfs_bmap.h"
#include "xfs_rw.h"
#include "xfs_error.h"
#include "xfs_utils.h"
#include "xfs_dir2_trace.h"
#include "xfs_quota.h"
#include "xfs_acl.h"
#include "xfs_filestream.h"
#include "xfs_vnodeops.h"

kmem_zone_t *xfs_ifork_zone;
kmem_zone_t *xfs_inode_zone;

/*
 * Used in xfs_itruncate().  This is the maximum number of extents
 * freed from a file in a single transaction.
 */
#define	XFS_ITRUNC_MAX_EXTENTS	2

STATIC int xfs_iflush_int(xfs_inode_t *, xfs_buf_t *);
STATIC int xfs_iformat_local(xfs_inode_t *, xfs_dinode_t *, int, int);
STATIC int xfs_iformat_extents(xfs_inode_t *, xfs_dinode_t *, int);
STATIC int xfs_iformat_btree(xfs_inode_t *, xfs_dinode_t *, int);

#ifdef DEBUG
/*
 * Make sure that the extents in the given memory buffer
 * are valid.
 */
STATIC void
xfs_validate_extents(
	xfs_ifork_t		*ifp,
	int			nrecs,
	xfs_exntfmt_t		fmt)
{
	xfs_bmbt_irec_t		irec;
	xfs_bmbt_rec_host_t	rec;
	int			i;

	for (i = 0; i < nrecs; i++) {
		xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, i);
		rec.l0 = get_unaligned(&ep->l0);
		rec.l1 = get_unaligned(&ep->l1);
		xfs_bmbt_get_all(&rec, &irec);
		if (fmt == XFS_EXTFMT_NOSTATE)
			ASSERT(irec.br_state == XFS_EXT_NORM);
	}
}
#else /* DEBUG */
#define xfs_validate_extents(ifp, nrecs, fmt)
#endif /* DEBUG */

/*
 * Check that none of the inode's in the buffer have a next
 * unlinked field of 0.
 */
#if defined(DEBUG)
void
xfs_inobp_check(
	xfs_mount_t	*mp,
	xfs_buf_t	*bp)
{
	int		i;
	int		j;
	xfs_dinode_t	*dip;

	j = mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog;

	for (i = 0; i < j; i++) {
		dip = (xfs_dinode_t *)xfs_buf_offset(bp,
					i * mp->m_sb.sb_inodesize);
		if (!dip->di_next_unlinked)  {
			xfs_fs_cmn_err(CE_ALERT, mp,
				"Detected a bogus zero next_unlinked field in incore inode buffer 0x%p.  About to pop an ASSERT.",
				bp);
			ASSERT(dip->di_next_unlinked);
		}
	}
}
#endif

/*
 * Find the buffer associated with the given inode map
 * We do basic validation checks on the buffer once it has been
 * retrieved from disk.
 */
STATIC int
xfs_imap_to_bp(
	xfs_mount_t	*mp,
	xfs_trans_t	*tp,
	xfs_imap_t	*imap,
	xfs_buf_t	**bpp,
	uint		buf_flags,
	uint		imap_flags)
{
	int		error;
	int		i;
	int		ni;
	xfs_buf_t	*bp;

	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
				   (int)imap->im_len, buf_flags, &bp);
	if (error) {
		if (error != EAGAIN) {
			cmn_err(CE_WARN,
				"xfs_imap_to_bp: xfs_trans_read_buf()returned "
				"an error %d on %s.  Returning error.",
				error, mp->m_fsname);
		} else {
			ASSERT(buf_flags & XFS_BUF_TRYLOCK);
		}
		return error;
	}

	/*
	 * Validate the magic number and version of every inode in the buffer
	 * (if DEBUG kernel) or the first inode in the buffer, otherwise.
	 */
#ifdef DEBUG
	ni = BBTOB(imap->im_len) >> mp->m_sb.sb_inodelog;
#else	/* usual case */
	ni = 1;
#endif

	for (i = 0; i < ni; i++) {
		int		di_ok;
		xfs_dinode_t	*dip;

		dip = (xfs_dinode_t *)xfs_buf_offset(bp,
					(i << mp->m_sb.sb_inodelog));
		di_ok = be16_to_cpu(dip->di_core.di_magic) == XFS_DINODE_MAGIC &&
			    XFS_DINODE_GOOD_VERSION(dip->di_core.di_version);
		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
						XFS_ERRTAG_ITOBP_INOTOBP,
						XFS_RANDOM_ITOBP_INOTOBP))) {
			if (imap_flags & XFS_IMAP_BULKSTAT) {
				xfs_trans_brelse(tp, bp);
				return XFS_ERROR(EINVAL);
			}
			XFS_CORRUPTION_ERROR("xfs_imap_to_bp",
						XFS_ERRLEVEL_HIGH, mp, dip);
#ifdef DEBUG
			cmn_err(CE_PANIC,
					"Device %s - bad inode magic/vsn "
					"daddr %lld #%d (magic=%x)",
				XFS_BUFTARG_NAME(mp->m_ddev_targp),
				(unsigned long long)imap->im_blkno, i,
				be16_to_cpu(dip->di_core.di_magic));
#endif
			xfs_trans_brelse(tp, bp);
			return XFS_ERROR(EFSCORRUPTED);
		}
	}

	xfs_inobp_check(mp, bp);

	/*
	 * Mark the buffer as an inode buffer now that it looks good
	 */
	XFS_BUF_SET_VTYPE(bp, B_FS_INO);

	*bpp = bp;
	return 0;
}

/*
 * This routine is called to map an inode number within a file
 * system to the buffer containing the on-disk version of the
 * inode.  It returns a pointer to the buffer containing the
 * on-disk inode in the bpp parameter, and in the dip parameter
 * it returns a pointer to the on-disk inode within that buffer.
 *
 * If a non-zero error is returned, then the contents of bpp and
 * dipp are undefined.
 *
 * Use xfs_imap() to determine the size and location of the
 * buffer to read from disk.
 */
STATIC int
xfs_inotobp(
	xfs_mount_t	*mp,
	xfs_trans_t	*tp,
	xfs_ino_t	ino,
	xfs_dinode_t	**dipp,
	xfs_buf_t	**bpp,
	int		*offset)
{
	xfs_imap_t	imap;
	xfs_buf_t	*bp;
	int		error;

	imap.im_blkno = 0;
	error = xfs_imap(mp, tp, ino, &imap, XFS_IMAP_LOOKUP);
	if (error)
		return error;

	error = xfs_imap_to_bp(mp, tp, &imap, &bp, XFS_BUF_LOCK, 0);
	if (error)
		return error;

	*dipp = (xfs_dinode_t *)xfs_buf_offset(bp, imap.im_boffset);
	*bpp = bp;
	*offset = imap.im_boffset;
	return 0;
}


/*
 * This routine is called to map an inode to the buffer containing
 * the on-disk version of the inode.  It returns a pointer to the
 * buffer containing the on-disk inode in the bpp parameter, and in
 * the dip parameter it returns a pointer to the on-disk inode within
 * that buffer.
 *
 * If a non-zero error is returned, then the contents of bpp and
 * dipp are undefined.
 *
 * If the inode is new and has not yet been initialized, use xfs_imap()
 * to determine the size and location of the buffer to read from disk.
 * If the inode has already been mapped to its buffer and read in once,
 * then use the mapping information stored in the inode rather than
 * calling xfs_imap().  This allows us to avoid the overhead of looking
 * at the inode btree for small block file systems (see xfs_dilocate()).
 * We can tell whether the inode has been mapped in before by comparing
 * its disk block address to 0.  Only uninitialized inodes will have
 * 0 for the disk block address.
 */
int
xfs_itobp(
	xfs_mount_t	*mp,
	xfs_trans_t	*tp,
	xfs_inode_t	*ip,
	xfs_dinode_t	**dipp,
	xfs_buf_t	**bpp,
	xfs_daddr_t	bno,
	uint		imap_flags,
	uint		buf_flags)
{
	xfs_imap_t	imap;
	xfs_buf_t	*bp;
	int		error;

	if (ip->i_blkno == (xfs_daddr_t)0) {
		imap.im_blkno = bno;
		error = xfs_imap(mp, tp, ip->i_ino, &imap,
					XFS_IMAP_LOOKUP | imap_flags);
		if (error)
			return error;

		/*
		 * Fill in the fields in the inode that will be used to
		 * map the inode to its buffer from now on.
		 */
		ip->i_blkno = imap.im_blkno;
		ip->i_len = imap.im_len;
		ip->i_boffset = imap.im_boffset;
	} else {
		/*
		 * We've already mapped the inode once, so just use the
		 * mapping that we saved the first time.
		 */
		imap.im_blkno = ip->i_blkno;
		imap.im_len = ip->i_len;
		imap.im_boffset = ip->i_boffset;
	}
	ASSERT(bno == 0 || bno == imap.im_blkno);

	error = xfs_imap_to_bp(mp, tp, &imap, &bp, buf_flags, imap_flags);
	if (error)
		return error;

	if (!bp) {
		ASSERT(buf_flags & XFS_BUF_TRYLOCK);
		ASSERT(tp == NULL);
		*bpp = NULL;
		return EAGAIN;
	}

	*dipp = (xfs_dinode_t *)xfs_buf_offset(bp, imap.im_boffset);
	*bpp = bp;
	return 0;
}

/*
 * Move inode type and inode format specific information from the
 * on-disk inode to the in-core inode.  For fifos, devs, and sockets
 * this means set if_rdev to the proper value.  For files, directories,
 * and symlinks this means to bring in the in-line data or extent
 * pointers.  For a file in B-tree format, only the root is immediately
 * brought in-core.  The rest will be in-lined in if_extents when it
 * is first referenced (see xfs_iread_extents()).
 */
STATIC int
xfs_iformat(
	xfs_inode_t		*ip,
	xfs_dinode_t		*dip)
{
	xfs_attr_shortform_t	*atp;
	int			size;
	int			error;
	xfs_fsize_t             di_size;
	ip->i_df.if_ext_max =
		XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t);
	error = 0;

	if (unlikely(be32_to_cpu(dip->di_core.di_nextents) +
		     be16_to_cpu(dip->di_core.di_anextents) >
		     be64_to_cpu(dip->di_core.di_nblocks))) {
		xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
			"corrupt dinode %Lu, extent total = %d, nblocks = %Lu.",
			(unsigned long long)ip->i_ino,
			(int)(be32_to_cpu(dip->di_core.di_nextents) +
			      be16_to_cpu(dip->di_core.di_anextents)),
			(unsigned long long)
				be64_to_cpu(dip->di_core.di_nblocks));
		XFS_CORRUPTION_ERROR("xfs_iformat(1)", XFS_ERRLEVEL_LOW,
				     ip->i_mount, dip);
		return XFS_ERROR(EFSCORRUPTED);
	}

	if (unlikely(dip->di_core.di_forkoff > ip->i_mount->m_sb.sb_inodesize)) {
		xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
			"corrupt dinode %Lu, forkoff = 0x%x.",
			(unsigned long long)ip->i_ino,
			dip->di_core.di_forkoff);
		XFS_CORRUPTION_ERROR("xfs_iformat(2)", XFS_ERRLEVEL_LOW,
				     ip->i_mount, dip);
		return XFS_ERROR(EFSCORRUPTED);
	}

	switch (ip->i_d.di_mode & S_IFMT) {
	case S_IFIFO:
	case S_IFCHR:
	case S_IFBLK:
	case S_IFSOCK:
		if (unlikely(dip->di_core.di_format != XFS_DINODE_FMT_DEV)) {
			XFS_CORRUPTION_ERROR("xfs_iformat(3)", XFS_ERRLEVEL_LOW,
					      ip->i_mount, dip);
			return XFS_ERROR(EFSCORRUPTED);
		}
		ip->i_d.di_size = 0;
		ip->i_size = 0;
		ip->i_df.if_u2.if_rdev = be32_to_cpu(dip->di_u.di_dev);
		break;

	case S_IFREG:
	case S_IFLNK:
	case S_IFDIR:
		switch (dip->di_core.di_format) {
		case XFS_DINODE_FMT_LOCAL:
			/*
			 * no local regular files yet
			 */
			if (unlikely((be16_to_cpu(dip->di_core.di_mode) & S_IFMT) == S_IFREG)) {
				xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
					"corrupt inode %Lu "
					"(local format for regular file).",
					(unsigned long long) ip->i_ino);
				XFS_CORRUPTION_ERROR("xfs_iformat(4)",
						     XFS_ERRLEVEL_LOW,
						     ip->i_mount, dip);
				return XFS_ERROR(EFSCORRUPTED);
			}

			di_size = be64_to_cpu(dip->di_core.di_size);
			if (unlikely(di_size > XFS_DFORK_DSIZE(dip, ip->i_mount))) {
				xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
					"corrupt inode %Lu "
					"(bad size %Ld for local inode).",
					(unsigned long long) ip->i_ino,
					(long long) di_size);
				XFS_CORRUPTION_ERROR("xfs_iformat(5)",
						     XFS_ERRLEVEL_LOW,
						     ip->i_mount, dip);
				return XFS_ERROR(EFSCORRUPTED);
			}

			size = (int)di_size;
			error = xfs_iformat_local(ip, dip, XFS_DATA_FORK, size);
			break;
		case XFS_DINODE_FMT_EXTENTS:
			error = xfs_iformat_extents(ip, dip, XFS_DATA_FORK);
			break;
		case XFS_DINODE_FMT_BTREE:
			error = xfs_iformat_btree(ip, dip, XFS_DATA_FORK);
			break;
		default:
			XFS_ERROR_REPORT("xfs_iformat(6)", XFS_ERRLEVEL_LOW,
					 ip->i_mount);
			return XFS_ERROR(EFSCORRUPTED);
		}
		break;

	default:
		XFS_ERROR_REPORT("xfs_iformat(7)", XFS_ERRLEVEL_LOW, ip->i_mount);
		return XFS_ERROR(EFSCORRUPTED);
	}
	if (error) {
		return error;
	}
	if (!XFS_DFORK_Q(dip))
		return 0;
	ASSERT(ip->i_afp == NULL);
	ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP);
	ip->i_afp->if_ext_max =
		XFS_IFORK_ASIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t);
	switch (dip->di_core.di_aformat) {
	case XFS_DINODE_FMT_LOCAL:
		atp = (xfs_attr_shortform_t *)XFS_DFORK_APTR(dip);
		size = be16_to_cpu(atp->hdr.totsize);
		error = xfs_iformat_local(ip, dip, XFS_ATTR_FORK, size);
		break;
	case XFS_DINODE_FMT_EXTENTS:
		error = xfs_iformat_extents(ip, dip, XFS_ATTR_FORK);
		break;
	case XFS_DINODE_FMT_BTREE:
		error = xfs_iformat_btree(ip, dip, XFS_ATTR_FORK);
		break;
	default:
		error = XFS_ERROR(EFSCORRUPTED);
		break;
	}
	if (error) {
		kmem_zone_free(xfs_ifork_zone, ip->i_afp);
		ip->i_afp = NULL;
		xfs_idestroy_fork(ip, XFS_DATA_FORK);
	}
	return error;
}

/*
 * The file is in-lined in the on-disk inode.
 * If it fits into if_inline_data, then copy
 * it there, otherwise allocate a buffer for it
 * and copy the data there.  Either way, set
 * if_data to point at the data.
 * If we allocate a buffer for the data, make
 * sure that its size is a multiple of 4 and
 * record the real size in i_real_bytes.
 */
STATIC int
xfs_iformat_local(
	xfs_inode_t	*ip,
	xfs_dinode_t	*dip,
	int		whichfork,
	int		size)
{
	xfs_ifork_t	*ifp;
	int		real_size;

	/*
	 * If the size is unreasonable, then something
	 * is wrong and we just bail out rather than crash in
	 * kmem_alloc() or memcpy() below.
	 */
	if (unlikely(size > XFS_DFORK_SIZE(dip, ip->i_mount, whichfork))) {
		xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
			"corrupt inode %Lu "
			"(bad size %d for local fork, size = %d).",
			(unsigned long long) ip->i_ino, size,
			XFS_DFORK_SIZE(dip, ip->i_mount, whichfork));
		XFS_CORRUPTION_ERROR("xfs_iformat_local", XFS_ERRLEVEL_LOW,
				     ip->i_mount, dip);
		return XFS_ERROR(EFSCORRUPTED);
	}
	ifp = XFS_IFORK_PTR(ip, whichfork);
	real_size = 0;
	if (size == 0)
		ifp->if_u1.if_data = NULL;
	else if (size <= sizeof(ifp->if_u2.if_inline_data))
		ifp->if_u1.if_data = ifp->if_u2.if_inline_data;
	else {
		real_size = roundup(size, 4);
		ifp->if_u1.if_data = kmem_alloc(real_size, KM_SLEEP);
	}
	ifp->if_bytes = size;
	ifp->if_real_bytes = real_size;
	if (size)
		memcpy(ifp->if_u1.if_data, XFS_DFORK_PTR(dip, whichfork), size);
	ifp->if_flags &= ~XFS_IFEXTENTS;
	ifp->if_flags |= XFS_IFINLINE;
	return 0;
}

/*
 * The file consists of a set of extents all
 * of which fit into the on-disk inode.
 * If there are few enough extents to fit into
 * the if_inline_ext, then copy them there.
 * Otherwise allocate a buffer for them and copy
 * them into it.  Either way, set if_extents
 * to point at the extents.
 */
STATIC int
xfs_iformat_extents(
	xfs_inode_t	*ip,
	xfs_dinode_t	*dip,
	int		whichfork)
{
	xfs_bmbt_rec_t	*dp;
	xfs_ifork_t	*ifp;
	int		nex;
	int		size;
	int		i;

	ifp = XFS_IFORK_PTR(ip, whichfork);
	nex = XFS_DFORK_NEXTENTS(dip, whichfork);
	size = nex * (uint)sizeof(xfs_bmbt_rec_t);

	/*
	 * If the number of extents is unreasonable, then something
	 * is wrong and we just bail out rather than crash in
	 * kmem_alloc() or memcpy() below.
	 */
	if (unlikely(size < 0 || size > XFS_DFORK_SIZE(dip, ip->i_mount, whichfork))) {
		xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
			"corrupt inode %Lu ((a)extents = %d).",
			(unsigned long long) ip->i_ino, nex);
		XFS_CORRUPTION_ERROR("xfs_iformat_extents(1)", XFS_ERRLEVEL_LOW,
				     ip->i_mount, dip);
		return XFS_ERROR(EFSCORRUPTED);
	}

	ifp->if_real_bytes = 0;
	if (nex == 0)
		ifp->if_u1.if_extents = NULL;
	else if (nex <= XFS_INLINE_EXTS)
		ifp->if_u1.if_extents = ifp->if_u2.if_inline_ext;
	else
		xfs_iext_add(ifp, 0, nex);

	ifp->if_bytes = size;
	if (size) {
		dp = (xfs_bmbt_rec_t *) XFS_DFORK_PTR(dip, whichfork);
		xfs_validate_extents(ifp, nex, XFS_EXTFMT_INODE(ip));
		for (i = 0; i < nex; i++, dp++) {
			xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, i);
			ep->l0 = be64_to_cpu(get_unaligned(&dp->l0));
			ep->l1 = be64_to_cpu(get_unaligned(&dp->l1));
		}
		XFS_BMAP_TRACE_EXLIST(ip, nex, whichfork);
		if (whichfork != XFS_DATA_FORK ||
			XFS_EXTFMT_INODE(ip) == XFS_EXTFMT_NOSTATE)
				if (unlikely(xfs_check_nostate_extents(
				    ifp, 0, nex))) {
					XFS_ERROR_REPORT("xfs_iformat_extents(2)",
							 XFS_ERRLEVEL_LOW,
							 ip->i_mount);
					return XFS_ERROR(EFSCORRUPTED);
				}
	}
	ifp->if_flags |= XFS_IFEXTENTS;
	return 0;
}

/*
 * The file has too many extents to fit into
 * the inode, so they are in B-tree format.
 * Allocate a buffer for the root of the B-tree
 * and copy the root into it.  The i_extents
 * field will remain NULL until all of the
 * extents are read in (when they are needed).
 */
STATIC int
xfs_iformat_btree(
	xfs_inode_t		*ip,
	xfs_dinode_t		*dip,
	int			whichfork)
{
	xfs_bmdr_block_t	*dfp;
	xfs_ifork_t		*ifp;
	/* REFERENCED */
	int			nrecs;
	int			size;

	ifp = XFS_IFORK_PTR(ip, whichfork);
	dfp = (xfs_bmdr_block_t *)XFS_DFORK_PTR(dip, whichfork);
	size = XFS_BMAP_BROOT_SPACE(dfp);
	nrecs = XFS_BMAP_BROOT_NUMRECS(dfp);

	/*
	 * blow out if -- fork has less extents than can fit in
	 * fork (fork shouldn't be a btree format), root btree
	 * block has more records than can fit into the fork,
	 * or the number of extents is greater than the number of
	 * blocks.
	 */
	if (unlikely(XFS_IFORK_NEXTENTS(ip, whichfork) <= ifp->if_ext_max
	    || XFS_BMDR_SPACE_CALC(nrecs) >
			XFS_DFORK_SIZE(dip, ip->i_mount, whichfork)
	    || XFS_IFORK_NEXTENTS(ip, whichfork) > ip->i_d.di_nblocks)) {
		xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
			"corrupt inode %Lu (btree).",
			(unsigned long long) ip->i_ino);
		XFS_ERROR_REPORT("xfs_iformat_btree", XFS_ERRLEVEL_LOW,
				 ip->i_mount);
		return XFS_ERROR(EFSCORRUPTED);
	}

	ifp->if_broot_bytes = size;
	ifp->if_broot = kmem_alloc(size, KM_SLEEP);
	ASSERT(ifp->if_broot != NULL);
	/*
	 * Copy and convert from the on-disk structure
	 * to the in-memory structure.
	 */
	xfs_bmdr_to_bmbt(dfp, XFS_DFORK_SIZE(dip, ip->i_mount, whichfork),
		ifp->if_broot, size);
	ifp->if_flags &= ~XFS_IFEXTENTS;
	ifp->if_flags |= XFS_IFBROOT;

	return 0;
}

void
xfs_dinode_from_disk(
	xfs_icdinode_t		*to,
	xfs_dinode_core_t	*from)
{
	to->di_magic = be16_to_cpu(from->di_magic);
	to->di_mode = be16_to_cpu(from->di_mode);
	to->di_version = from ->di_version;
	to->di_format = from->di_format;
	to->di_onlink = be16_to_cpu(from->di_onlink);
	to->di_uid = be32_to_cpu(from->di_uid);
	to->di_gid = be32_to_cpu(from->di_gid);
	to->di_nlink = be32_to_cpu(from->di_nlink);
	to->di_projid = be16_to_cpu(from->di_projid);
	memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
	to->di_flushiter = be16_to_cpu(from->di_flushiter);
	to->di_atime.t_sec = be32_to_cpu(from->di_atime.t_sec);
	to->di_atime.t_nsec = be32_to_cpu(from->di_atime.t_nsec);
	to->di_mtime.t_sec = be32_to_cpu(from->di_mtime.t_sec);
	to->di_mtime.t_nsec = be32_to_cpu(from->di_mtime.t_nsec);
	to->di_ctime.t_sec = be32_to_cpu(from->di_ctime.t_sec);
	to->di_ctime.t_nsec = be32_to_cpu(from->di_ctime.t_nsec);
	to->di_size = be64_to_cpu(from->di_size);
	to->di_nblocks = be64_to_cpu(from->di_nblocks);
	to->di_extsize = be32_to_cpu(from->di_extsize);
	to->di_nextents = be32_to_cpu(from->di_nextents);
	to->di_anextents = be16_to_cpu(from->di_anextents);
	to->di_forkoff = from->di_forkoff;
	to->di_aformat	= from->di_aformat;
	to->di_dmevmask	= be32_to_cpu(from->di_dmevmask);
	to->di_dmstate	= be16_to_cpu(from->di_dmstate);
	to->di_flags	= be16_to_cpu(from->di_flags);
	to->di_gen	= be32_to_cpu(from->di_gen);
}

void
xfs_dinode_to_disk(
	xfs_dinode_core_t	*to,
	xfs_icdinode_t		*from)
{
	to->di_magic = cpu_to_be16(from->di_magic);
	to->di_mode = cpu_to_be16(from->di_mode);
	to->di_version = from ->di_version;
	to->di_format = from->di_format;
	to->di_onlink = cpu_to_be16(from->di_onlink);
	to->di_uid = cpu_to_be32(from->di_uid);
	to->di_gid = cpu_to_be32(from->di_gid);
	to->di_nlink = cpu_to_be32(from->di_nlink);
	to->di_projid = cpu_to_be16(from->di_projid);
	memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
	to->di_flushiter = cpu_to_be16(from->di_flushiter);
	to->di_atime.t_sec = cpu_to_be32(from->di_atime.t_sec);
	to->di_atime.t_nsec = cpu_to_be32(from->di_atime.t_nsec);
	to->di_mtime.t_sec = cpu_to_be32(from->di_mtime.t_sec);
	to->di_mtime.t_nsec = cpu_to_be32(from->di_mtime.t_nsec);
	to->di_ctime.t_sec = cpu_to_be32(from->di_ctime.t_sec);
	to->di_ctime.t_nsec = cpu_to_be32(from->di_ctime.t_nsec);
	to->di_size = cpu_to_be64(from->di_size);
	to->di_nblocks = cpu_to_be64(from->di_nblocks);
	to->di_extsize = cpu_to_be32(from->di_extsize);
	to->di_nextents = cpu_to_be32(from->di_nextents);
	to->di_anextents = cpu_to_be16(from->di_anextents);
	to->di_forkoff = from->di_forkoff;
	to->di_aformat = from->di_aformat;
	to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
	to->di_dmstate = cpu_to_be16(from->di_dmstate);
	to->di_flags = cpu_to_be16(from->di_flags);
	to->di_gen = cpu_to_be32(from->di_gen);
}

STATIC uint
_xfs_dic2xflags(
	__uint16_t		di_flags)
{
	uint			flags = 0;

	if (di_flags & XFS_DIFLAG_ANY) {
		if (di_flags & XFS_DIFLAG_REALTIME)
			flags |= XFS_XFLAG_REALTIME;
		if (di_flags & XFS_DIFLAG_PREALLOC)
			flags |= XFS_XFLAG_PREALLOC;
		if (di_flags & XFS_DIFLAG_IMMUTABLE)
			flags |= XFS_XFLAG_IMMUTABLE;
		if (di_flags & XFS_DIFLAG_APPEND)
			flags |= XFS_XFLAG_APPEND;
		if (di_flags & XFS_DIFLAG_SYNC)
			flags |= XFS_XFLAG_SYNC;
		if (di_flags & XFS_DIFLAG_NOATIME)
			flags |= XFS_XFLAG_NOATIME;
		if (di_flags & XFS_DIFLAG_NODUMP)
			flags |= XFS_XFLAG_NODUMP;
		if (di_flags & XFS_DIFLAG_RTINHERIT)
			flags |= XFS_XFLAG_RTINHERIT;
		if (di_flags & XFS_DIFLAG_PROJINHERIT)
			flags |= XFS_XFLAG_PROJINHERIT;
		if (di_flags & XFS_DIFLAG_NOSYMLINKS)
			flags |= XFS_XFLAG_NOSYMLINKS;
		if (di_flags & XFS_DIFLAG_EXTSIZE)
			flags |= XFS_XFLAG_EXTSIZE;
		if (di_flags & XFS_DIFLAG_EXTSZINHERIT)
			flags |= XFS_XFLAG_EXTSZINHERIT;
		if (di_flags & XFS_DIFLAG_NODEFRAG)
			flags |= XFS_XFLAG_NODEFRAG;
		if (di_flags & XFS_DIFLAG_FILESTREAM)
			flags |= XFS_XFLAG_FILESTREAM;
	}

	return flags;
}

uint
xfs_ip2xflags(
	xfs_inode_t		*ip)
{
	xfs_icdinode_t		*dic = &ip->i_d;

	return _xfs_dic2xflags(dic->di_flags) |
				(XFS_IFORK_Q(ip) ? XFS_XFLAG_HASATTR : 0);
}

uint
xfs_dic2xflags(
	xfs_dinode_t		*dip)
{
	xfs_dinode_core_t	*dic = &dip->di_core;

	return _xfs_dic2xflags(be16_to_cpu(dic->di_flags)) |
				(XFS_DFORK_Q(dip) ? XFS_XFLAG_HASATTR : 0);
}

/*
 * Given a mount structure and an inode number, return a pointer
 * to a newly allocated in-core inode corresponding to the given
 * inode number.
 *
 * Initialize the inode's attributes and extent pointers if it
 * already has them (it will not if the inode has no links).
 */
int
xfs_iread(
	xfs_mount_t	*mp,
	xfs_trans_t	*tp,
	xfs_ino_t	ino,
	xfs_inode_t	**ipp,
	xfs_daddr_t	bno,
	uint		imap_flags)
{
	xfs_buf_t	*bp;
	xfs_dinode_t	*dip;
	xfs_inode_t	*ip;
	int		error;

	ASSERT(xfs_inode_zone != NULL);

	ip = kmem_zone_zalloc(xfs_inode_zone, KM_SLEEP);
	ip->i_ino = ino;
	ip->i_mount = mp;
	atomic_set(&ip->i_iocount, 0);
	spin_lock_init(&ip->i_flags_lock);

	/*
	 * Get pointer's to the on-disk inode and the buffer containing it.
	 * If the inode number refers to a block outside the file system
	 * then xfs_itobp() will return NULL.  In this case we should
	 * return NULL as well.  Set i_blkno to 0 so that xfs_itobp() will
	 * know that this is a new incore inode.
	 */
	error = xfs_itobp(mp, tp, ip, &dip, &bp, bno, imap_flags, XFS_BUF_LOCK);
	if (error) {
		kmem_zone_free(xfs_inode_zone, ip);
		return error;
	}

	/*
	 * Initialize inode's trace buffers.
	 * Do this before xfs_iformat in case it adds entries.
	 */
#ifdef	XFS_INODE_TRACE
	ip->i_trace = ktrace_alloc(INODE_TRACE_SIZE, KM_SLEEP);
#endif
#ifdef XFS_BMAP_TRACE
	ip->i_xtrace = ktrace_alloc(XFS_BMAP_KTRACE_SIZE, KM_SLEEP);
#endif
#ifdef XFS_BMBT_TRACE
	ip->i_btrace = ktrace_alloc(XFS_BMBT_KTRACE_SIZE, KM_SLEEP);
#endif
#ifdef XFS_RW_TRACE
	ip->i_rwtrace = ktrace_alloc(XFS_RW_KTRACE_SIZE, KM_SLEEP);
#endif
#ifdef XFS_ILOCK_TRACE
	ip->i_lock_trace = ktrace_alloc(XFS_ILOCK_KTRACE_SIZE, KM_SLEEP);
#endif
#ifdef XFS_DIR2_TRACE
	ip->i_dir_trace = ktrace_alloc(XFS_DIR2_KTRACE_SIZE, KM_SLEEP);
#endif

	/*
	 * If we got something that isn't an inode it means someone
	 * (nfs or dmi) has a stale handle.
	 */
	if (be16_to_cpu(dip->di_core.di_magic) != XFS_DINODE_MAGIC) {
		kmem_zone_free(xfs_inode_zone, ip);
		xfs_trans_brelse(tp, bp);
#ifdef DEBUG
		xfs_fs_cmn_err(CE_ALERT, mp, "xfs_iread: "
				"dip->di_core.di_magic (0x%x) != "
				"XFS_DINODE_MAGIC (0x%x)",
				be16_to_cpu(dip->di_core.di_magic),
				XFS_DINODE_MAGIC);
#endif /* DEBUG */
		return XFS_ERROR(EINVAL);
	}

	/*
	 * If the on-disk inode is already linked to a directory
	 * entry, copy all of the inode into the in-core inode.
	 * xfs_iformat() handles copying in the inode format
	 * specific information.
	 * Otherwise, just get the truly permanent information.
	 */
	if (dip->di_core.di_mode) {
		xfs_dinode_from_disk(&ip->i_d, &dip->di_core);
		error = xfs_iformat(ip, dip);
		if (error)  {
			kmem_zone_free(xfs_inode_zone, ip);
			xfs_trans_brelse(tp, bp);
#ifdef DEBUG
			xfs_fs_cmn_err(CE_ALERT, mp, "xfs_iread: "
					"xfs_iformat() returned error %d",
					error);
#endif /* DEBUG */
			return error;
		}
	} else {
		ip->i_d.di_magic = be16_to_cpu(dip->di_core.di_magic);
		ip->i_d.di_version = dip->di_core.di_version;
		ip->i_d.di_gen = be32_to_cpu(dip->di_core.di_gen);
		ip->i_d.di_flushiter = be16_to_cpu(dip->di_core.di_flushiter);
		/*
		 * Make sure to pull in the mode here as well in
		 * case the inode is released without being used.
		 * This ensures that xfs_inactive() will see that
		 * the inode is already free and not try to mess
		 * with the uninitialized part of it.
		 */
		ip->i_d.di_mode = 0;
		/*
		 * Initialize the per-fork minima and maxima for a new
		 * inode here.  xfs_iformat will do it for old inodes.
		 */
		ip->i_df.if_ext_max =
			XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t);
	}

	INIT_LIST_HEAD(&ip->i_reclaim);

	/*
	 * The inode format changed when we moved the link count and
	 * made it 32 bits long.  If this is an old format inode,
	 * convert it in memory to look like a new one.  If it gets
	 * flushed to disk we will convert back before flushing or
	 * logging it.  We zero out the new projid field and the old link
	 * count field.  We'll handle clearing the pad field (the remains
	 * of the old uuid field) when we actually convert the inode to
	 * the new format. We don't change the version number so that we
	 * can distinguish this from a real new format inode.
	 */
	if (ip->i_d.di_version == XFS_DINODE_VERSION_1) {
		ip->i_d.di_nlink = ip->i_d.di_onlink;
		ip->i_d.di_onlink = 0;
		ip->i_d.di_projid = 0;
	}

	ip->i_delayed_blks = 0;
	ip->i_size = ip->i_d.di_size;

	/*
	 * Mark the buffer containing the inode as something to keep
	 * around for a while.  This helps to keep recently accessed
	 * meta-data in-core longer.
	 */
	 XFS_BUF_SET_REF(bp, XFS_INO_REF);

	/*
	 * Use xfs_trans_brelse() to release the buffer containing the
	 * on-disk inode, because it was acquired with xfs_trans_read_buf()
	 * in xfs_itobp() above.  If tp is NULL, this is just a normal
	 * brelse().  If we're within a transaction, then xfs_trans_brelse()
	 * will only release the buffer if it is not dirty within the
	 * transaction.  It will be OK to release the buffer in this case,
	 * because inodes on disk are never destroyed and we will be
	 * locking the new in-core inode before putting it in the hash
	 * table where other processes can find it.  Thus we don't have
	 * to worry about the inode being changed just because we released
	 * the buffer.
	 */
	xfs_trans_brelse(tp, bp);
	*ipp = ip;
	return 0;
}

/*
 * Read in extents from a btree-format inode.
 * Allocate and fill in if_extents.  Real work is done in xfs_bmap.c.
 */
int
xfs_iread_extents(
	xfs_trans_t	*tp,
	xfs_inode_t	*ip,
	int		whichfork)
{
	int		error;
	xfs_ifork_t	*ifp;
	xfs_extnum_t	nextents;
	size_t		size;

	if (unlikely(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE)) {
		XFS_ERROR_REPORT("xfs_iread_extents", XFS_ERRLEVEL_LOW,
				 ip->i_mount);
		return XFS_ERROR(EFSCORRUPTED);
	}
	nextents = XFS_IFORK_NEXTENTS(ip, whichfork);
	size = nextents * sizeof(xfs_bmbt_rec_t);
	ifp = XFS_IFORK_PTR(ip, whichfork);

	/*
	 * We know that the size is valid (it's checked in iformat_btree)
	 */
	ifp->if_lastex = NULLEXTNUM;
	ifp->if_bytes = ifp->if_real_bytes = 0;
	ifp->if_flags |= XFS_IFEXTENTS;
	xfs_iext_add(ifp, 0, nextents);
	error = xfs_bmap_read_extents(tp, ip, whichfork);
	if (error) {
		xfs_iext_destroy(ifp);
		ifp->if_flags &= ~XFS_IFEXTENTS;
		return error;
	}
	xfs_validate_extents(ifp, nextents, XFS_EXTFMT_INODE(ip));
	return 0;
}

/*
 * Allocate an inode on disk and return a copy of its in-core version.
 * The in-core inode is locked exclusively.  Set mode, nlink, and rdev
 * appropriately within the inode.  The uid and gid for the inode are
 * set according to the contents of the given cred structure.
 *
 * Use xfs_dialloc() to allocate the on-disk inode. If xfs_dialloc()
 * has a free inode available, call xfs_iget()
 * to obtain the in-core version of the allocated inode.  Finally,
 * fill in the inode and log its initial contents.  In this case,
 * ialloc_context would be set to NULL and call_again set to false.
 *
 * If xfs_dialloc() does not have an available inode,
 * it will replenish its supply by doing an allocation. Since we can
 * only do one allocation within a transaction without deadlocks, we
 * must commit the current transaction before returning the inode itself.
 * In this case, therefore, we will set call_again to true and return.
 * The caller should then commit the current transaction, start a new
 * transaction, and call xfs_ialloc() again to actually get the inode.
 *
 * To ensure that some other process does not grab the inode that
 * was allocated during the first call to xfs_ialloc(), this routine
 * also returns the [locked] bp pointing to the head of the freelist
 * as ialloc_context.  The caller should hold this buffer across
 * the commit and pass it back into this routine on the second call.
 *
 * If we are allocating quota inodes, we do not have a parent inode
 * to attach to or associate with (i.e. pip == NULL) because they
 * are not linked into the directory structure - they are attached
 * directly to the superblock - and so have no parent.
 */
int
xfs_ialloc(
	xfs_trans_t	*tp,
	xfs_inode_t	*pip,
	mode_t		mode,
	xfs_nlink_t	nlink,
	xfs_dev_t	rdev,
	cred_t		*cr,
	xfs_prid_t	prid,
	int		okalloc,
	xfs_buf_t	**ialloc_context,
	boolean_t	*call_again,
	xfs_inode_t	**ipp)
{
	xfs_ino_t	ino;
	xfs_inode_t	*ip;
	bhv_vnode_t	*vp;
	uint		flags;
	int		error;

	/*
	 * Call the space management code to pick
	 * the on-disk inode to be allocated.
	 */
	error = xfs_dialloc(tp, pip ? pip->i_ino : 0, mode, okalloc,
			    ialloc_context, call_again, &ino);
	if (error != 0) {
		return error;
	}
	if (*call_again || ino == NULLFSINO) {
		*ipp = NULL;
		return 0;
	}
	ASSERT(*ialloc_context == NULL);

	/*
	 * Get the in-core inode with the lock held exclusively.
	 * This is because we're setting fields here we need
	 * to prevent others from looking at until we're done.
	 */
	error = xfs_trans_iget(tp->t_mountp, tp, ino,
				XFS_IGET_CREATE, XFS_ILOCK_EXCL, &ip);
	if (error != 0) {
		return error;
	}
	ASSERT(ip != NULL);

	vp = XFS_ITOV(ip);
	ip->i_d.di_mode = (__uint16_t)mode;
	ip->i_d.di_onlink = 0;
	ip->i_d.di_nlink = nlink;
	ASSERT(ip->i_d.di_nlink == nlink);
	ip->i_d.di_uid = current_fsuid(cr);
	ip->i_d.di_gid = current_fsgid(cr);
	ip->i_d.di_projid = prid;
	memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));

	/*
	 * If the superblock version is up to where we support new format
	 * inodes and this is currently an old format inode, then change
	 * the inode version number now.  This way we only do the conversion
	 * here rather than here and in the flush/logging code.
	 */
	if (xfs_sb_version_hasnlink(&tp->t_mountp->m_sb) &&
	    ip->i_d.di_version == XFS_DINODE_VERSION_1) {
		ip->i_d.di_version = XFS_DINODE_VERSION_2;
		/*
		 * We've already zeroed the old link count, the projid field,
		 * and the pad field.
		 */
	}

	/*
	 * Project ids won't be stored on disk if we are using a version 1 inode.
	 */
	if ((prid != 0) && (ip->i_d.di_version == XFS_DINODE_VERSION_1))
		xfs_bump_ino_vers2(tp, ip);

	if (pip && XFS_INHERIT_GID(pip)) {
		ip->i_d.di_gid = pip->i_d.di_gid;
		if ((pip->i_d.di_mode & S_ISGID) && (mode & S_IFMT) == S_IFDIR) {
			ip->i_d.di_mode |= S_ISGID;
		}
	}

	/*
	 * If the group ID of the new file does not match the effective group
	 * ID or one of the supplementary group IDs, the S_ISGID bit is cleared
	 * (and only if the irix_sgid_inherit compatibility variable is set).
	 */
	if ((irix_sgid_inherit) &&
	    (ip->i_d.di_mode & S_ISGID) &&
	    (!in_group_p((gid_t)ip->i_d.di_gid))) {
		ip->i_d.di_mode &= ~S_ISGID;
	}

	ip->i_d.di_size = 0;
	ip->i_size = 0;
	ip->i_d.di_nextents = 0;
	ASSERT(ip->i_d.di_nblocks == 0);
	xfs_ichgtime(ip, XFS_ICHGTIME_CHG|XFS_ICHGTIME_ACC|XFS_ICHGTIME_MOD);
	/*
	 * di_gen will have been taken care of in xfs_iread.
	 */
	ip->i_d.di_extsize = 0;
	ip->i_d.di_dmevmask = 0;
	ip->i_d.di_dmstate = 0;
	ip->i_d.di_flags = 0;
	flags = XFS_ILOG_CORE;
	switch (mode & S_IFMT) {
	case S_IFIFO:
	case S_IFCHR:
	case S_IFBLK:
	case S_IFSOCK:
		ip->i_d.di_format = XFS_DINODE_FMT_DEV;
		ip->i_df.if_u2.if_rdev = rdev;
		ip->i_df.if_flags = 0;
		flags |= XFS_ILOG_DEV;
		break;
	case S_IFREG:
		if (pip && xfs_inode_is_filestream(pip)) {
			error = xfs_filestream_associate(pip, ip);
			if (error < 0)
				return -error;
			if (!error)
				xfs_iflags_set(ip, XFS_IFILESTREAM);
		}
		/* fall through */
	case S_IFDIR:
		if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) {
			uint	di_flags = 0;

			if ((mode & S_IFMT) == S_IFDIR) {
				if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
					di_flags |= XFS_DIFLAG_RTINHERIT;
				if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
					di_flags |= XFS_DIFLAG_EXTSZINHERIT;
					ip->i_d.di_extsize = pip->i_d.di_extsize;
				}
			} else if ((mode & S_IFMT) == S_IFREG) {
				if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
					di_flags |= XFS_DIFLAG_REALTIME;
				if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
					di_flags |= XFS_DIFLAG_EXTSIZE;
					ip->i_d.di_extsize = pip->i_d.di_extsize;
				}
			}
			if ((pip->i_d.di_flags & XFS_DIFLAG_NOATIME) &&
			    xfs_inherit_noatime)
				di_flags |= XFS_DIFLAG_NOATIME;
			if ((pip->i_d.di_flags & XFS_DIFLAG_NODUMP) &&
			    xfs_inherit_nodump)
				di_flags |= XFS_DIFLAG_NODUMP;
			if ((pip->i_d.di_flags & XFS_DIFLAG_SYNC) &&
			    xfs_inherit_sync)
				di_flags |= XFS_DIFLAG_SYNC;
			if ((pip->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) &&
			    xfs_inherit_nosymlinks)
				di_flags |= XFS_DIFLAG_NOSYMLINKS;
			if (pip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
				di_flags |= XFS_DIFLAG_PROJINHERIT;
			if ((pip->i_d.di_flags & XFS_DIFLAG_NODEFRAG) &&
			    xfs_inherit_nodefrag)
				di_flags |= XFS_DIFLAG_NODEFRAG;
			if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM)
				di_flags |= XFS_DIFLAG_FILESTREAM;
			ip->i_d.di_flags |= di_flags;
		}
		/* FALLTHROUGH */
	case S_IFLNK:
		ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS;
		ip->i_df.if_flags = XFS_IFEXTENTS;
		ip->i_df.if_bytes = ip->i_df.if_real_bytes = 0;
		ip->i_df.if_u1.if_extents = NULL;
		break;
	default:
		ASSERT(0);
	}
	/*
	 * Attribute fork settings for new inode.
	 */
	ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS;
	ip->i_d.di_anextents = 0;

	/*
	 * Log the new values stuffed into the inode.
	 */
	xfs_trans_log_inode(tp, ip, flags);

	/* now that we have an i_mode we can setup inode ops and unlock */
	xfs_initialize_vnode(tp->t_mountp, vp, ip);

	*ipp = ip;
	return 0;
}

/*
 * Check to make sure that there are no blocks allocated to the
 * file beyond the size of the file.  We don't check this for
 * files with fixed size extents or real time extents, but we
 * at least do it for regular files.
 */
#ifdef DEBUG
void
xfs_isize_check(
	xfs_mount_t	*mp,
	xfs_inode_t	*ip,
	xfs_fsize_t	isize)
{
	xfs_fileoff_t	map_first;
	int		nimaps;
	xfs_bmbt_irec_t	imaps[2];

	if ((ip->i_d.di_mode & S_IFMT) != S_IFREG)
		return;

	if (XFS_IS_REALTIME_INODE(ip))
		return;

	if (ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE)
		return;

	nimaps = 2;
	map_first = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize);
	/*
	 * The filesystem could be shutting down, so bmapi may return
	 * an error.
	 */
	if (xfs_bmapi(NULL, ip, map_first,
			 (XFS_B_TO_FSB(mp,
				       (xfs_ufsize_t)XFS_MAXIOFFSET(mp)) -
			  map_first),
			 XFS_BMAPI_ENTIRE, NULL, 0, imaps, &nimaps,
			 NULL, NULL))
	    return;
	ASSERT(nimaps == 1);
	ASSERT(imaps[0].br_startblock == HOLESTARTBLOCK);
}
#endif	/* DEBUG */

/*
 * Calculate the last possible buffered byte in a file.  This must
 * include data that was buffered beyond the EOF by the write code.
 * This also needs to deal with overflowing the xfs_fsize_t type
 * which can happen for sizes near the limit.
 *
 * We also need to take into account any blocks beyond the EOF.  It
 * may be the case that they were buffered by a write which failed.
 * In that case the pages will still be in memory, but the inode size
 * will never have been updated.
 */
xfs_fsize_t
xfs_file_last_byte(
	xfs_inode_t	*ip)
{
	xfs_mount_t	*mp;
	xfs_fsize_t	last_byte;
	xfs_fileoff_t	last_block;
	xfs_fileoff_t	size_last_block;
	int		error;

	ASSERT(ismrlocked(&(ip->i_iolock), MR_UPDATE | MR_ACCESS));

	mp = ip->i_mount;
	/*
	 * Only check for blocks beyond the EOF if the extents have
	 * been read in.  This eliminates the need for the inode lock,
	 * and it also saves us from looking when it really isn't
	 * necessary.
	 */
	if (ip->i_df.if_flags & XFS_IFEXTENTS) {
		error = xfs_bmap_last_offset(NULL, ip, &last_block,
			XFS_DATA_FORK);
		if (error) {
			last_block = 0;
		}
	} else {
		last_block = 0;
	}
	size_last_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)ip->i_size);
	last_block = XFS_FILEOFF_MAX(last_block, size_last_block);

	last_byte = XFS_FSB_TO_B(mp, last_block);
	if (last_byte < 0) {
		return XFS_MAXIOFFSET(mp);
	}
	last_byte += (1 << mp->m_writeio_log);
	if (last_byte < 0) {
		return XFS_MAXIOFFSET(mp);
	}
	return last_byte;
}

#if defined(XFS_RW_TRACE)
STATIC void
xfs_itrunc_trace(
	int		tag,
	xfs_inode_t	*ip,
	int		flag,
	xfs_fsize_t	new_size,
	xfs_off_t	toss_start,
	xfs_off_t	toss_finish)
{
	if (ip->i_rwtrace == NULL) {
		return;
	}

	ktrace_enter(ip->i_rwtrace,
		     (void*)((long)tag),
		     (void*)ip,
		     (void*)(unsigned long)((ip->i_d.di_size >> 32) & 0xffffffff),
		     (void*)(unsigned long)(ip->i_d.di_size & 0xffffffff),
		     (void*)((long)flag),
		     (void*)(unsigned long)((new_size >> 32) & 0xffffffff),
		     (void*)(unsigned long)(new_size & 0xffffffff),
		     (void*)(unsigned long)((toss_start >> 32) & 0xffffffff),
		     (void*)(unsigned long)(toss_start & 0xffffffff),
		     (void*)(unsigned long)((toss_finish >> 32) & 0xffffffff),
		     (void*)(unsigned long)(toss_finish & 0xffffffff),
		     (void*)(unsigned long)current_cpu(),
		     (void*)(unsigned long)current_pid(),
		     (void*)NULL,
		     (void*)NULL,
		     (void*)NULL);
}
#else
#define	xfs_itrunc_trace(tag, ip, flag, new_size, toss_start, toss_finish)
#endif

/*
 * Start the truncation of the file to new_size.  The new size
 * must be smaller than the current size.  This routine will
 * clear the buffer and page caches of file data in the removed
 * range, and xfs_itruncate_finish() will remove the underlying
 * disk blocks.
 *
 * The inode must have its I/O lock locked EXCLUSIVELY, and it
 * must NOT have the inode lock held at all.  This is because we're
 * calling into the buffer/page cache code and we can't hold the
 * inode lock when we do so.
 *
 * We need to wait for any direct I/Os in flight to complete before we
 * proceed with the truncate. This is needed to prevent the extents
 * being read or written by the direct I/Os from being removed while the
 * I/O is in flight as there is no other method of synchronising
 * direct I/O with the truncate operation.  Also, because we hold
 * the IOLOCK in exclusive mode, we prevent new direct I/Os from being
 * started until the truncate completes and drops the lock. Essentially,
 * the vn_iowait() call forms an I/O barrier that provides strict ordering
 * between direct I/Os and the truncate operation.
 *
 * The flags parameter can have either the value XFS_ITRUNC_DEFINITE
 * or XFS_ITRUNC_MAYBE.  The XFS_ITRUNC_MAYBE value should be used
 * in the case that the caller is locking things out of order and
 * may not be able to call xfs_itruncate_finish() with the inode lock
 * held without dropping the I/O lock.  If the caller must drop the
 * I/O lock before calling xfs_itruncate_finish(), then xfs_itruncate_start()
 * must be called again with all the same restrictions as the initial
 * call.
 */
int
xfs_itruncate_start(
	xfs_inode_t	*ip,
	uint		flags,
	xfs_fsize_t	new_size)
{
	xfs_fsize_t	last_byte;
	xfs_off_t	toss_start;
	xfs_mount_t	*mp;
	bhv_vnode_t	*vp;
	int		error = 0;

	ASSERT(ismrlocked(&ip->i_iolock, MR_UPDATE) != 0);
	ASSERT((new_size == 0) || (new_size <= ip->i_size));
	ASSERT((flags == XFS_ITRUNC_DEFINITE) ||
	       (flags == XFS_ITRUNC_MAYBE));

	mp = ip->i_mount;
	vp = XFS_ITOV(ip);

	/* wait for the completion of any pending DIOs */
	if (new_size < ip->i_size)
		vn_iowait(ip);

	/*
	 * Call toss_pages or flushinval_pages to get rid of pages
	 * overlapping the region being removed.  We have to use
	 * the less efficient flushinval_pages in the case that the
	 * caller may not be able to finish the truncate without
	 * dropping the inode's I/O lock.  Make sure
	 * to catch any pages brought in by buffers overlapping
	 * the EOF by searching out beyond the isize by our
	 * block size. We round new_size up to a block boundary
	 * so that we don't toss things on the same block as
	 * new_size but before it.
	 *
	 * Before calling toss_page or flushinval_pages, make sure to
	 * call remapf() over the same region if the file is mapped.
	 * This frees up mapped file references to the pages in the
	 * given range and for the flushinval_pages case it ensures
	 * that we get the latest mapped changes flushed out.
	 */
	toss_start = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size);
	toss_start = XFS_FSB_TO_B(mp, toss_start);
	if (toss_start < 0) {
		/*
		 * The place to start tossing is beyond our maximum
		 * file size, so there is no way that the data extended
		 * out there.
		 */
		return 0;
	}
	last_byte = xfs_file_last_byte(ip);
	xfs_itrunc_trace(XFS_ITRUNC_START, ip, flags, new_size, toss_start,
			 last_byte);
	if (last_byte > toss_start) {
		if (flags & XFS_ITRUNC_DEFINITE) {
			xfs_tosspages(ip, toss_start,
					-1, FI_REMAPF_LOCKED);
		} else {
			error = xfs_flushinval_pages(ip, toss_start,
					-1, FI_REMAPF_LOCKED);
		}
	}

#ifdef DEBUG
	if (new_size == 0) {
		ASSERT(VN_CACHED(vp) == 0);
	}
#endif
	return error;
}

/*
 * Shrink the file to the given new_size.  The new
 * size must be smaller than the current size.
 * This will free up the underlying blocks
 * in the removed range after a call to xfs_itruncate_start()
 * or xfs_atruncate_start().
 *
 * The transaction passed to this routine must have made
 * a permanent log reservation of at least XFS_ITRUNCATE_LOG_RES.
 * This routine may commit the given transaction and
 * start new ones, so make sure everything involved in
 * the transaction is tidy before calling here.
 * Some transaction will be returned to the caller to be
 * committed.  The incoming transaction must already include
 * the inode, and both inode locks must be held exclusively.
 * The inode must also be "held" within the transaction.  On
 * return the inode will be "held" within the returned transaction.
 * This routine does NOT require any disk space to be reserved
 * for it within the transaction.
 *
 * The fork parameter must be either xfs_attr_fork or xfs_data_fork,
 * and it indicates the fork which is to be truncated.  For the
 * attribute fork we only support truncation to size 0.
 *
 * We use the sync parameter to indicate whether or not the first
 * transaction we perform might have to be synchronous.  For the attr fork,
 * it needs to be so if the unlink of the inode is not yet known to be
 * permanent in the log.  This keeps us from freeing and reusing the
 * blocks of the attribute fork before the unlink of the inode becomes
 * permanent.
 *
 * For the data fork, we normally have to run synchronously if we're
 * being called out of the inactive path or we're being called
 * out of the create path where we're truncating an existing file.
 * Either way, the truncate needs to be sync so blocks don't reappear
 * in the file with altered data in case of a crash.  wsync filesystems
 * can run the first case async because anything that shrinks the inode
 * has to run sync so by the time we're called here from inactive, the
 * inode size is permanently set to 0.
 *
 * Calls from the truncate path always need to be sync unless we're
 * in a wsync filesystem and the file has already been unlinked.
 *
 * The caller is responsible for correctly setting the sync parameter.
 * It gets too hard for us to guess here which path we're being called
 * out of just based on inode state.
 */
int
xfs_itruncate_finish(
	xfs_trans_t	**tp,
	xfs_inode_t	*ip,
	xfs_fsize_t	new_size,
	int		fork,
	int		sync)
{
	xfs_fsblock_t	first_block;
	xfs_fileoff_t	first_unmap_block;
	xfs_fileoff_t	last_block;
	xfs_filblks_t	unmap_len=0;
	xfs_mount_t	*mp;
	xfs_trans_t	*ntp;
	int		done;
	int		committed;
	xfs_bmap_free_t	free_list;
	int		error;

	ASSERT(ismrlocked(&ip->i_iolock, MR_UPDATE) != 0);
	ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE) != 0);
	ASSERT((new_size == 0) || (new_size <= ip->i_size));
	ASSERT(*tp != NULL);
	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
	ASSERT(ip->i_transp == *tp);
	ASSERT(ip->i_itemp != NULL);
	ASSERT(ip->i_itemp->ili_flags & XFS_ILI_HOLD);


	ntp = *tp;
	mp = (ntp)->t_mountp;
	ASSERT(! XFS_NOT_DQATTACHED(mp, ip));

	/*
	 * We only support truncating the entire attribute fork.
	 */
	if (fork == XFS_ATTR_FORK) {
		new_size = 0LL;
	}
	first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size);
	xfs_itrunc_trace(XFS_ITRUNC_FINISH1, ip, 0, new_size, 0, 0);
	/*
	 * The first thing we do is set the size to new_size permanently
	 * on disk.  This way we don't have to worry about anyone ever
	 * being able to look at the data being freed even in the face
	 * of a crash.  What we're getting around here is the case where
	 * we free a block, it is allocated to another file, it is written
	 * to, and then we crash.  If the new data gets written to the
	 * file but the log buffers containing the free and reallocation
	 * don't, then we'd end up with garbage in the blocks being freed.
	 * As long as we make the new_size permanent before actually
	 * freeing any blocks it doesn't matter if they get writtten to.
	 *
	 * The callers must signal into us whether or not the size
	 * setting here must be synchronous.  There are a few cases
	 * where it doesn't have to be synchronous.  Those cases
	 * occur if the file is unlinked and we know the unlink is
	 * permanent or if the blocks being truncated are guaranteed
	 * to be beyond the inode eof (regardless of the link count)
	 * and the eof value is permanent.  Both of these cases occur
	 * only on wsync-mounted filesystems.  In those cases, we're
	 * guaranteed that no user will ever see the data in the blocks
	 * that are being truncated so the truncate can run async.
	 * In the free beyond eof case, the file may wind up with
	 * more blocks allocated to it than it needs if we crash
	 * and that won't get fixed until the next time the file
	 * is re-opened and closed but that's ok as that shouldn't
	 * be too many blocks.
	 *
	 * However, we can't just make all wsync xactions run async
	 * because there's one call out of the create path that needs
	 * to run sync where it's truncating an existing file to size
	 * 0 whose size is > 0.
	 *
	 * It's probably possible to come up with a test in this
	 * routine that would correctly distinguish all the above
	 * cases from the values of the function parameters and the
	 * inode state but for sanity's sake, I've decided to let the
	 * layers above just tell us.  It's simpler to correctly figure
	 * out in the layer above exactly under what conditions we
	 * can run async and I think it's easier for others read and
	 * follow the logic in case something has to be changed.
	 * cscope is your friend -- rcc.
	 *
	 * The attribute fork is much simpler.
	 *
	 * For the attribute fork we allow the caller to tell us whether
	 * the unlink of the inode that led to this call is yet permanent
	 * in the on disk log.  If it is not and we will be freeing extents
	 * in this inode then we make the first transaction synchronous
	 * to make sure that the unlink is permanent by the time we free
	 * the blocks.
	 */
	if (fork == XFS_DATA_FORK) {
		if (ip->i_d.di_nextents > 0) {
			/*
			 * If we are not changing the file size then do
			 * not update the on-disk file size - we may be
			 * called from xfs_inactive_free_eofblocks().  If we
			 * update the on-disk file size and then the system
			 * crashes before the contents of the file are
			 * flushed to disk then the files may be full of
			 * holes (ie NULL files bug).
			 */
			if (ip->i_size != new_size) {
				ip->i_d.di_size = new_size;
				ip->i_size = new_size;
				xfs_trans_log_inode(ntp, ip, XFS_ILOG_CORE);
			}
		}
	} else if (sync) {
		ASSERT(!(mp->m_flags & XFS_MOUNT_WSYNC));
		if (ip->i_d.di_anextents > 0)
			xfs_trans_set_sync(ntp);
	}
	ASSERT(fork == XFS_DATA_FORK ||
		(fork == XFS_ATTR_FORK &&
			((sync && !(mp->m_flags & XFS_MOUNT_WSYNC)) ||
			 (sync == 0 && (mp->m_flags & XFS_MOUNT_WSYNC)))));

	/*
	 * Since it is possible for space to become allocated beyond
	 * the end of the file (in a crash where the space is allocated
	 * but the inode size is not yet updated), simply remove any
	 * blocks which show up between the new EOF and the maximum
	 * possible file size.  If the first block to be removed is
	 * beyond the maximum file size (ie it is the same as last_block),
	 * then there is nothing to do.
	 */
	last_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_MAXIOFFSET(mp));
	ASSERT(first_unmap_block <= last_block);
	done = 0;
	if (last_block == first_unmap_block) {
		done = 1;
	} else {
		unmap_len = last_block - first_unmap_block + 1;
	}
	while (!done) {
		/*
		 * Free up up to XFS_ITRUNC_MAX_EXTENTS.  xfs_bunmapi()
		 * will tell us whether it freed the entire range or
		 * not.  If this is a synchronous mount (wsync),
		 * then we can tell bunmapi to keep all the
		 * transactions asynchronous since the unlink
		 * transaction that made this inode inactive has
		 * already hit the disk.  There's no danger of
		 * the freed blocks being reused, there being a
		 * crash, and the reused blocks suddenly reappearing
		 * in this file with garbage in them once recovery
		 * runs.
		 */
		XFS_BMAP_INIT(&free_list, &first_block);
		error = xfs_bunmapi(ntp, ip,
				    first_unmap_block, unmap_len,
				    XFS_BMAPI_AFLAG(fork) |
				      (sync ? 0 : XFS_BMAPI_ASYNC),
				    XFS_ITRUNC_MAX_EXTENTS,
				    &first_block, &free_list,
				    NULL, &done);
		if (error) {
			/*
			 * If the bunmapi call encounters an error,
			 * return to the caller where the transaction
			 * can be properly aborted.  We just need to
			 * make sure we're not holding any resources
			 * that we were not when we came in.
			 */
			xfs_bmap_cancel(&free_list);
			return error;
		}

		/*
		 * Duplicate the transaction that has the permanent
		 * reservation and commit the old transaction.
		 */
		error = xfs_bmap_finish(tp, &free_list, &committed);
		ntp = *tp;
		if (error) {
			/*
			 * If the bmap finish call encounters an error,
			 * return to the caller where the transaction
			 * can be properly aborted.  We just need to
			 * make sure we're not holding any resources
			 * that we were not when we came in.
			 *
			 * Aborting from this point might lose some
			 * blocks in the file system, but oh well.
			 */
			xfs_bmap_cancel(&free_list);
			if (committed)
				goto error_join;
			return error;
		}

		if (committed) {
			/*
			 * The first xact was committed, so add the inode to
			 * the new one.  Mark it dirty so it will be logged and
			 * moved forward in the log as part of every commit.
			 */
			xfs_trans_ijoin(ntp, ip,
					XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
			xfs_trans_ihold(ntp, ip);
			xfs_trans_log_inode(ntp, ip, XFS_ILOG_CORE);
		}
		ntp = xfs_trans_dup(ntp);
		error = xfs_trans_commit(*tp, 0);
		*tp = ntp;
		if (error)
			goto error_join;
		error = xfs_trans_reserve(ntp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
					  XFS_TRANS_PERM_LOG_RES,
					  XFS_ITRUNCATE_LOG_COUNT);
		if (error)
			goto error_join;

	}
	/*
	 * Only update the size in the case of the data fork, but
	 * always re-log the inode so that our permanent transaction
	 * can keep on rolling it forward in the log.
	 */
	if (fork == XFS_DATA_FORK) {
		xfs_isize_check(mp, ip, new_size);
		/*
		 * If we are not changing the file size then do
		 * not update the on-disk file size - we may be
		 * called from xfs_inactive_free_eofblocks().  If we
		 * update the on-disk file size and then the system
		 * crashes before the contents of the file are
		 * flushed to disk then the files may be full of
		 * holes (ie NULL files bug).
		 */
		if (ip->i_size != new_size) {
			ip->i_d.di_size = new_size;
			ip->i_size = new_size;
		}
	}
	xfs_trans_log_inode(ntp, ip, XFS_ILOG_CORE);
	ASSERT((new_size != 0) ||
	       (fork == XFS_ATTR_FORK) ||
	       (ip->i_delayed_blks == 0));
	ASSERT((new_size != 0) ||
	       (fork == XFS_ATTR_FORK) ||
	       (ip->i_d.di_nextents == 0));
	xfs_itrunc_trace(XFS_ITRUNC_FINISH2, ip, 0, new_size, 0, 0);
	return 0;

error_join:
	/*
	 * Add the inode being truncated to the next chained transaction.  This
	 * keeps things simple for the higher level code, because it always
	 * knows that the inode is locked and held in the transaction that
	 * returns to it whether errors occur or not.  We don't mark the inode
	 * dirty so that this transaction can be easily aborted if possible.
	 */
	xfs_trans_ijoin(ntp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
	xfs_trans_ihold(ntp, ip);
	return error;
}


/*
 * xfs_igrow_start
 *
 * Do the first part of growing a file: zero any data in the last
 * block that is beyond the old EOF.  We need to do this before
 * the inode is joined to the transaction to modify the i_size.
 * That way we can drop the inode lock and call into the buffer
 * cache to get the buffer mapping the EOF.
 */
int
xfs_igrow_start(
	xfs_inode_t	*ip,
	xfs_fsize_t	new_size,
	cred_t		*credp)
{
	ASSERT(ismrlocked(&(ip->i_lock), MR_UPDATE) != 0);
	ASSERT(ismrlocked(&(ip->i_iolock), MR_UPDATE) != 0);
	ASSERT(new_size > ip->i_size);

	/*
	 * Zero any pages that may have been created by
	 * xfs_write_file() beyond the end of the file
	 * and any blocks between the old and new file sizes.
	 */
	return xfs_zero_eof(ip, new_size, ip->i_size);
}

/*
 * xfs_igrow_finish
 *
 * This routine is called to extend the size of a file.
 * The inode must have both the iolock and the ilock locked
 * for update and it must be a part of the current transaction.
 * The xfs_igrow_start() function must have been called previously.
 * If the change_flag is not zero, the inode change timestamp will
 * be updated.
 */
void
xfs_igrow_finish(
	xfs_trans_t	*tp,
	xfs_inode_t	*ip,
	xfs_fsize_t	new_size,
	int		change_flag)
{
	ASSERT(ismrlocked(&(ip->i_lock), MR_UPDATE) != 0);
	ASSERT(ismrlocked(&(ip->i_iolock), MR_UPDATE) != 0);
	ASSERT(ip->i_transp == tp);
	ASSERT(new_size > ip->i_size);

	/*
	 * Update the file size.  Update the inode change timestamp
	 * if change_flag set.
	 */
	ip->i_d.di_size = new_size;
	ip->i_size = new_size;
	if (change_flag)
		xfs_ichgtime(ip, XFS_ICHGTIME_CHG);
	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

}


/*
 * This is called when the inode's link count goes to 0.
 * We place the on-disk inode on a list in the AGI.  It
 * will be pulled from this list when the inode is freed.
 */
int
xfs_iunlink(
	xfs_trans_t	*tp,
	xfs_inode_t	*ip)
{
	xfs_mount_t	*mp;
	xfs_agi_t	*agi;
	xfs_dinode_t	*dip;
	xfs_buf_t	*agibp;
	xfs_buf_t	*ibp;
	xfs_agnumber_t	agno;
	xfs_daddr_t	agdaddr;
	xfs_agino_t	agino;
	short		bucket_index;
	int		offset;
	int		error;
	int		agi_ok;

	ASSERT(ip->i_d.di_nlink == 0);
	ASSERT(ip->i_d.di_mode != 0);
	ASSERT(ip->i_transp == tp);

	mp = tp->t_mountp;

	agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
	agdaddr = XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp));

	/*
	 * Get the agi buffer first.  It ensures lock ordering
	 * on the list.
	 */
	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, agdaddr,
				   XFS_FSS_TO_BB(mp, 1), 0, &agibp);
	if (error)
		return error;

	/*
	 * Validate the magic number of the agi block.
	 */
	agi = XFS_BUF_TO_AGI(agibp);
	agi_ok =
		be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC &&
		XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum));
	if (unlikely(XFS_TEST_ERROR(!agi_ok, mp, XFS_ERRTAG_IUNLINK,
			XFS_RANDOM_IUNLINK))) {
		XFS_CORRUPTION_ERROR("xfs_iunlink", XFS_ERRLEVEL_LOW, mp, agi);
		xfs_trans_brelse(tp, agibp);
		return XFS_ERROR(EFSCORRUPTED);
	}
	/*
	 * Get the index into the agi hash table for the
	 * list this inode will go on.
	 */
	agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
	ASSERT(agino != 0);
	bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
	ASSERT(agi->agi_unlinked[bucket_index]);
	ASSERT(be32_to_cpu(agi->agi_unlinked[bucket_index]) != agino);

	if (be32_to_cpu(agi->agi_unlinked[bucket_index]) != NULLAGINO) {
		/*
		 * There is already another inode in the bucket we need
		 * to add ourselves to.  Add us at the front of the list.
		 * Here we put the head pointer into our next pointer,
		 * and then we fall through to point the head at us.
		 */
		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0, XFS_BUF_LOCK);
		if (error)
			return error;

		ASSERT(be32_to_cpu(dip->di_next_unlinked) == NULLAGINO);
		/* both on-disk, don't endian flip twice */
		dip->di_next_unlinked = agi->agi_unlinked[bucket_index];
		offset = ip->i_boffset +
			offsetof(xfs_dinode_t, di_next_unlinked);
		xfs_trans_inode_buf(tp, ibp);
		xfs_trans_log_buf(tp, ibp, offset,
				  (offset + sizeof(xfs_agino_t) - 1));
		xfs_inobp_check(mp, ibp);
	}

	/*
	 * Point the bucket head pointer at the inode being inserted.
	 */
	ASSERT(agino != 0);
	agi->agi_unlinked[bucket_index] = cpu_to_be32(agino);
	offset = offsetof(xfs_agi_t, agi_unlinked) +
		(sizeof(xfs_agino_t) * bucket_index);
	xfs_trans_log_buf(tp, agibp, offset,
			  (offset + sizeof(xfs_agino_t) - 1));
	return 0;
}

/*
 * Pull the on-disk inode from the AGI unlinked list.
 */
STATIC int
xfs_iunlink_remove(
	xfs_trans_t	*tp,
	xfs_inode_t	*ip)
{
	xfs_ino_t	next_ino;
	xfs_mount_t	*mp;
	xfs_agi_t	*agi;
	xfs_dinode_t	*dip;
	xfs_buf_t	*agibp;
	xfs_buf_t	*ibp;
	xfs_agnumber_t	agno;
	xfs_daddr_t	agdaddr;
	xfs_agino_t	agino;
	xfs_agino_t	next_agino;
	xfs_buf_t	*last_ibp;
	xfs_dinode_t	*last_dip = NULL;
	short		bucket_index;
	int		offset, last_offset = 0;
	int		error;
	int		agi_ok;

	/*
	 * First pull the on-disk inode from the AGI unlinked list.
	 */
	mp = tp->t_mountp;

	agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
	agdaddr = XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp));

	/*
	 * Get the agi buffer first.  It ensures lock ordering
	 * on the list.
	 */
	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, agdaddr,
				   XFS_FSS_TO_BB(mp, 1), 0, &agibp);
	if (error) {
		cmn_err(CE_WARN,
			"xfs_iunlink_remove: xfs_trans_read_buf()  returned an error %d on %s.  Returning error.",
			error, mp->m_fsname);
		return error;
	}
	/*
	 * Validate the magic number of the agi block.
	 */
	agi = XFS_BUF_TO_AGI(agibp);
	agi_ok =
		be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC &&
		XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum));
	if (unlikely(XFS_TEST_ERROR(!agi_ok, mp, XFS_ERRTAG_IUNLINK_REMOVE,
			XFS_RANDOM_IUNLINK_REMOVE))) {
		XFS_CORRUPTION_ERROR("xfs_iunlink_remove", XFS_ERRLEVEL_LOW,
				     mp, agi);
		xfs_trans_brelse(tp, agibp);
		cmn_err(CE_WARN,
			"xfs_iunlink_remove: XFS_TEST_ERROR()  returned an error on %s.  Returning EFSCORRUPTED.",
			 mp->m_fsname);
		return XFS_ERROR(EFSCORRUPTED);
	}
	/*
	 * Get the index into the agi hash table for the
	 * list this inode will go on.
	 */
	agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
	ASSERT(agino != 0);
	bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
	ASSERT(be32_to_cpu(agi->agi_unlinked[bucket_index]) != NULLAGINO);
	ASSERT(agi->agi_unlinked[bucket_index]);

	if (be32_to_cpu(agi->agi_unlinked[bucket_index]) == agino) {
		/*
		 * We're at the head of the list.  Get the inode's
		 * on-disk buffer to see if there is anyone after us
		 * on the list.  Only modify our next pointer if it
		 * is not already NULLAGINO.  This saves us the overhead
		 * of dealing with the buffer when there is no need to
		 * change it.
		 */
		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0, XFS_BUF_LOCK);
		if (error) {
			cmn_err(CE_WARN,
				"xfs_iunlink_remove: xfs_itobp()  returned an error %d on %s.  Returning error.",
				error, mp->m_fsname);
			return error;
		}
		next_agino = be32_to_cpu(dip->di_next_unlinked);
		ASSERT(next_agino != 0);
		if (next_agino != NULLAGINO) {
			dip->di_next_unlinked = cpu_to_be32(NULLAGINO);
			offset = ip->i_boffset +
				offsetof(xfs_dinode_t, di_next_unlinked);
			xfs_trans_inode_buf(tp, ibp);
			xfs_trans_log_buf(tp, ibp, offset,
					  (offset + sizeof(xfs_agino_t) - 1));
			xfs_inobp_check(mp, ibp);
		} else {
			xfs_trans_brelse(tp, ibp);
		}
		/*
		 * Point the bucket head pointer at the next inode.
		 */
		ASSERT(next_agino != 0);
		ASSERT(next_agino != agino);
		agi->agi_unlinked[bucket_index] = cpu_to_be32(next_agino);
		offset = offsetof(xfs_agi_t, agi_unlinked) +
			(sizeof(xfs_agino_t) * bucket_index);
		xfs_trans_log_buf(tp, agibp, offset,
				  (offset + sizeof(xfs_agino_t) - 1));
	} else {
		/*
		 * We need to search the list for the inode being freed.
		 */
		next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
		last_ibp = NULL;
		while (next_agino != agino) {
			/*
			 * If the last inode wasn't the one pointing to
			 * us, then release its buffer since we're not
			 * going to do anything with it.
			 */
			if (last_ibp != NULL) {
				xfs_trans_brelse(tp, last_ibp);
			}
			next_ino = XFS_AGINO_TO_INO(mp, agno, next_agino);
			error = xfs_inotobp(mp, tp, next_ino, &last_dip,
					    &last_ibp, &last_offset);
			if (error) {
				cmn_err(CE_WARN,
			"xfs_iunlink_remove: xfs_inotobp()  returned an error %d on %s.  Returning error.",
					error, mp->m_fsname);
				return error;
			}
			next_agino = be32_to_cpu(last_dip->di_next_unlinked);
			ASSERT(next_agino != NULLAGINO);
			ASSERT(next_agino != 0);
		}
		/*
		 * Now last_ibp points to the buffer previous to us on
		 * the unlinked list.  Pull us from the list.
		 */
		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0, XFS_BUF_LOCK);
		if (error) {
			cmn_err(CE_WARN,
				"xfs_iunlink_remove: xfs_itobp()  returned an error %d on %s.  Returning error.",
				error, mp->m_fsname);
			return error;
		}
		next_agino = be32_to_cpu(dip->di_next_unlinked);
		ASSERT(next_agino != 0);
		ASSERT(next_agino != agino);
		if (next_agino != NULLAGINO) {
			dip->di_next_unlinked = cpu_to_be32(NULLAGINO);
			offset = ip->i_boffset +
				offsetof(xfs_dinode_t, di_next_unlinked);
			xfs_trans_inode_buf(tp, ibp);
			xfs_trans_log_buf(tp, ibp, offset,
					  (offset + sizeof(xfs_agino_t) - 1));
			xfs_inobp_check(mp, ibp);
		} else {
			xfs_trans_brelse(tp, ibp);
		}
		/*
		 * Point the previous inode on the list to the next inode.
		 */
		last_dip->di_next_unlinked = cpu_to_be32(next_agino);
		ASSERT(next_agino != 0);
		offset = last_offset + offsetof(xfs_dinode_t, di_next_unlinked);
		xfs_trans_inode_buf(tp, last_ibp);
		xfs_trans_log_buf(tp, last_ibp, offset,
				  (offset + sizeof(xfs_agino_t) - 1));
		xfs_inobp_check(mp, last_ibp);
	}
	return 0;
}

STATIC void
xfs_ifree_cluster(
	xfs_inode_t	*free_ip,
	xfs_trans_t	*tp,
	xfs_ino_t	inum)
{
	xfs_mount_t		*mp = free_ip->i_mount;
	int			blks_per_cluster;
	int			nbufs;
	int			ninodes;
	int			i, j, found, pre_flushed;
	xfs_daddr_t		blkno;
	xfs_buf_t		*bp;
	xfs_inode_t		*ip, **ip_found;
	xfs_inode_log_item_t	*iip;
	xfs_log_item_t		*lip;
	xfs_perag_t		*pag = xfs_get_perag(mp, inum);

	if (mp->m_sb.sb_blocksize >= XFS_INODE_CLUSTER_SIZE(mp)) {
		blks_per_cluster = 1;
		ninodes = mp->m_sb.sb_inopblock;
		nbufs = XFS_IALLOC_BLOCKS(mp);
	} else {
		blks_per_cluster = XFS_INODE_CLUSTER_SIZE(mp) /
					mp->m_sb.sb_blocksize;
		ninodes = blks_per_cluster * mp->m_sb.sb_inopblock;
		nbufs = XFS_IALLOC_BLOCKS(mp) / blks_per_cluster;
	}

	ip_found = kmem_alloc(ninodes * sizeof(xfs_inode_t *), KM_NOFS);

	for (j = 0; j < nbufs; j++, inum += ninodes) {
		blkno = XFS_AGB_TO_DADDR(mp, XFS_INO_TO_AGNO(mp, inum),
					 XFS_INO_TO_AGBNO(mp, inum));


		/*
		 * Look for each inode in memory and attempt to lock it,
		 * we can be racing with flush and tail pushing here.
		 * any inode we get the locks on, add to an array of
		 * inode items to process later.
		 *
		 * The get the buffer lock, we could beat a flush
		 * or tail pushing thread to the lock here, in which
		 * case they will go looking for the inode buffer
		 * and fail, we need some other form of interlock
		 * here.
		 */
		found = 0;
		for (i = 0; i < ninodes; i++) {
			read_lock(&pag->pag_ici_lock);
			ip = radix_tree_lookup(&pag->pag_ici_root,
					XFS_INO_TO_AGINO(mp, (inum + i)));

			/* Inode not in memory or we found it already,
			 * nothing to do
			 */
			if (!ip || xfs_iflags_test(ip, XFS_ISTALE)) {
				read_unlock(&pag->pag_ici_lock);
				continue;
			}

			if (xfs_inode_clean(ip)) {
				read_unlock(&pag->pag_ici_lock);
				continue;
			}

			/* If we can get the locks then add it to the
			 * list, otherwise by the time we get the bp lock
			 * below it will already be attached to the
			 * inode buffer.
			 */

			/* This inode will already be locked - by us, lets
			 * keep it that way.
			 */

			if (ip == free_ip) {
				if (xfs_iflock_nowait(ip)) {
					xfs_iflags_set(ip, XFS_ISTALE);
					if (xfs_inode_clean(ip)) {
						xfs_ifunlock(ip);
					} else {
						ip_found[found++] = ip;
					}
				}
				read_unlock(&pag->pag_ici_lock);
				continue;
			}

			if (xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
				if (xfs_iflock_nowait(ip)) {
					xfs_iflags_set(ip, XFS_ISTALE);

					if (xfs_inode_clean(ip)) {
						xfs_ifunlock(ip);
						xfs_iunlock(ip, XFS_ILOCK_EXCL);
					} else {
						ip_found[found++] = ip;
					}
				} else {
					xfs_iunlock(ip, XFS_ILOCK_EXCL);
				}
			}
			read_unlock(&pag->pag_ici_lock);
		}

		bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno, 
					mp->m_bsize * blks_per_cluster,
					XFS_BUF_LOCK);

		pre_flushed = 0;
		lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *);
		while (lip) {
			if (lip->li_type == XFS_LI_INODE) {
				iip = (xfs_inode_log_item_t *)lip;
				ASSERT(iip->ili_logged == 1);
				lip->li_cb = (void(*)(xfs_buf_t*,xfs_log_item_t*)) xfs_istale_done;
				spin_lock(&mp->m_ail_lock);
				iip->ili_flush_lsn = iip->ili_item.li_lsn;
				spin_unlock(&mp->m_ail_lock);
				xfs_iflags_set(iip->ili_inode, XFS_ISTALE);
				pre_flushed++;
			}
			lip = lip->li_bio_list;
		}

		for (i = 0; i < found; i++) {
			ip = ip_found[i];
			iip = ip->i_itemp;

			if (!iip) {
				ip->i_update_core = 0;
				xfs_ifunlock(ip);
				xfs_iunlock(ip, XFS_ILOCK_EXCL);
				continue;
			}

			iip->ili_last_fields = iip->ili_format.ilf_fields;
			iip->ili_format.ilf_fields = 0;
			iip->ili_logged = 1;
			spin_lock(&mp->m_ail_lock);
			iip->ili_flush_lsn = iip->ili_item.li_lsn;
			spin_unlock(&mp->m_ail_lock);

			xfs_buf_attach_iodone(bp,
				(void(*)(xfs_buf_t*,xfs_log_item_t*))
				xfs_istale_done, (xfs_log_item_t *)iip);
			if (ip != free_ip) {
				xfs_iunlock(ip, XFS_ILOCK_EXCL);
			}
		}

		if (found || pre_flushed)
			xfs_trans_stale_inode_buf(tp, bp);
		xfs_trans_binval(tp, bp);
	}

	kmem_free(ip_found, ninodes * sizeof(xfs_inode_t *));
	xfs_put_perag(mp, pag);
}

/*
 * This is called to return an inode to the inode free list.
 * The inode should already be truncated to 0 length and have
 * no pages associated with it.  This routine also assumes that
 * the inode is already a part of the transaction.
 *
 * The on-disk copy of the inode will have been added to the list
 * of unlinked inodes in the AGI. We need to remove the inode from
 * that list atomically with respect to freeing it here.
 */
int
xfs_ifree(
	xfs_trans_t	*tp,
	xfs_inode_t	*ip,
	xfs_bmap_free_t	*flist)
{
	int			error;
	int			delete;
	xfs_ino_t		first_ino;
	xfs_dinode_t    	*dip;
	xfs_buf_t       	*ibp;

	ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE));
	ASSERT(ip->i_transp == tp);
	ASSERT(ip->i_d.di_nlink == 0);
	ASSERT(ip->i_d.di_nextents == 0);
	ASSERT(ip->i_d.di_anextents == 0);
	ASSERT((ip->i_d.di_size == 0 && ip->i_size == 0) ||
	       ((ip->i_d.di_mode & S_IFMT) != S_IFREG));
	ASSERT(ip->i_d.di_nblocks == 0);

	/*
	 * Pull the on-disk inode from the AGI unlinked list.
	 */
	error = xfs_iunlink_remove(tp, ip);
	if (error != 0) {
		return error;
	}

	error = xfs_difree(tp, ip->i_ino, flist, &delete, &first_ino);
	if (error != 0) {
		return error;
	}
	ip->i_d.di_mode = 0;		/* mark incore inode as free */
	ip->i_d.di_flags = 0;
	ip->i_d.di_dmevmask = 0;
	ip->i_d.di_forkoff = 0;		/* mark the attr fork not in use */
	ip->i_df.if_ext_max =
		XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t);
	ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS;
	ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS;
	/*
	 * Bump the generation count so no one will be confused
	 * by reincarnations of this inode.
	 */
	ip->i_d.di_gen++;

	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

	error = xfs_itobp(ip->i_mount, tp, ip, &dip, &ibp, 0, 0, XFS_BUF_LOCK);
	if (error)
		return error;

        /*
	* Clear the on-disk di_mode. This is to prevent xfs_bulkstat
	* from picking up this inode when it is reclaimed (its incore state
	* initialzed but not flushed to disk yet). The in-core di_mode is
	* already cleared  and a corresponding transaction logged.
	* The hack here just synchronizes the in-core to on-disk
	* di_mode value in advance before the actual inode sync to disk.
	* This is OK because the inode is already unlinked and would never
	* change its di_mode again for this inode generation.
	* This is a temporary hack that would require a proper fix
	* in the future.
	*/
	dip->di_core.di_mode = 0;

	if (delete) {
		xfs_ifree_cluster(ip, tp, first_ino);
	}

	return 0;
}

/*
 * Reallocate the space for if_broot based on the number of records
 * being added or deleted as indicated in rec_diff.  Move the records
 * and pointers in if_broot to fit the new size.  When shrinking this
 * will eliminate holes between the records and pointers created by
 * the caller.  When growing this will create holes to be filled in
 * by the caller.
 *
 * The caller must not request to add more records than would fit in
 * the on-disk inode root.  If the if_broot is currently NULL, then
 * if we adding records one will be allocated.  The caller must also
 * not request that the number of records go below zero, although
 * it can go to zero.
 *
 * ip -- the inode whose if_broot area is changing
 * ext_diff -- the change in the number of records, positive or negative,
 *	 requested for the if_broot array.
 */
void
xfs_iroot_realloc(
	xfs_inode_t		*ip,
	int			rec_diff,
	int			whichfork)
{
	int			cur_max;
	xfs_ifork_t		*ifp;
	xfs_bmbt_block_t	*new_broot;
	int			new_max;
	size_t			new_size;
	char			*np;
	char			*op;

	/*
	 * Handle the degenerate case quietly.
	 */
	if (rec_diff == 0) {
		return;
	}

	ifp = XFS_IFORK_PTR(ip, whichfork);
	if (rec_diff > 0) {
		/*
		 * If there wasn't any memory allocated before, just
		 * allocate it now and get out.
		 */
		if (ifp->if_broot_bytes == 0) {
			new_size = (size_t)XFS_BMAP_BROOT_SPACE_CALC(rec_diff);
			ifp->if_broot = (xfs_bmbt_block_t*)kmem_alloc(new_size,
								     KM_SLEEP);
			ifp->if_broot_bytes = (int)new_size;
			return;
		}

		/*
		 * If there is already an existing if_broot, then we need
		 * to realloc() it and shift the pointers to their new
		 * location.  The records don't change location because
		 * they are kept butted up against the btree block header.
		 */
		cur_max = XFS_BMAP_BROOT_MAXRECS(ifp->if_broot_bytes);
		new_max = cur_max + rec_diff;
		new_size = (size_t)XFS_BMAP_BROOT_SPACE_CALC(new_max);
		ifp->if_broot = (xfs_bmbt_block_t *)
		  kmem_realloc(ifp->if_broot,
				new_size,
				(size_t)XFS_BMAP_BROOT_SPACE_CALC(cur_max), /* old size */
				KM_SLEEP);
		op = (char *)XFS_BMAP_BROOT_PTR_ADDR(ifp->if_broot, 1,
						      ifp->if_broot_bytes);
		np = (char *)XFS_BMAP_BROOT_PTR_ADDR(ifp->if_broot, 1,
						      (int)new_size);
		ifp->if_broot_bytes = (int)new_size;
		ASSERT(ifp->if_broot_bytes <=
			XFS_IFORK_SIZE(ip, whichfork) + XFS_BROOT_SIZE_ADJ);
		memmove(np, op, cur_max * (uint)sizeof(xfs_dfsbno_t));
		return;
	}

	/*
	 * rec_diff is less than 0.  In this case, we are shrinking the
	 * if_broot buffer.  It must already exist.  If we go to zero
	 * records, just get rid of the root and clear the status bit.
	 */
	ASSERT((ifp->if_broot != NULL) && (ifp->if_broot_bytes > 0));
	cur_max = XFS_BMAP_BROOT_MAXRECS(ifp->if_broot_bytes);
	new_max = cur_max + rec_diff;
	ASSERT(new_max >= 0);
	if (new_max > 0)
		new_size = (size_t)XFS_BMAP_BROOT_SPACE_CALC(new_max);
	else
		new_size = 0;
	if (new_size > 0) {
		new_broot = (xfs_bmbt_block_t *)kmem_alloc(new_size, KM_SLEEP);
		/*
		 * First copy over the btree block header.
		 */
		memcpy(new_broot, ifp->if_broot, sizeof(xfs_bmbt_block_t));
	} else {
		new_broot = NULL;
		ifp->if_flags &= ~XFS_IFBROOT;
	}

	/*
	 * Only copy the records and pointers if there are any.
	 */
	if (new_max > 0) {
		/*
		 * First copy the records.
		 */
		op = (char *)XFS_BMAP_BROOT_REC_ADDR(ifp->if_broot, 1,
						     ifp->if_broot_bytes);
		np = (char *)XFS_BMAP_BROOT_REC_ADDR(new_broot, 1,
						     (int)new_size);
		memcpy(np, op, new_max * (uint)sizeof(xfs_bmbt_rec_t));

		/*
		 * Then copy the pointers.
		 */
		op = (char *)XFS_BMAP_BROOT_PTR_ADDR(ifp->if_broot, 1,
						     ifp->if_broot_bytes);
		np = (char *)XFS_BMAP_BROOT_PTR_ADDR(new_broot, 1,
						     (int)new_size);
		memcpy(np, op, new_max * (uint)sizeof(xfs_dfsbno_t));
	}
	kmem_free(ifp->if_broot, ifp->if_broot_bytes);
	ifp->if_broot = new_broot;
	ifp->if_broot_bytes = (int)new_size;
	ASSERT(ifp->if_broot_bytes <=
		XFS_IFORK_SIZE(ip, whichfork) + XFS_BROOT_SIZE_ADJ);
	return;
}


/*
 * This is called when the amount of space needed for if_data
 * is increased or decreased.  The change in size is indicated by
 * the number of bytes that need to be added or deleted in the
 * byte_diff parameter.
 *
 * If the amount of space needed has decreased below the size of the
 * inline buffer, then switch to using the inline buffer.  Otherwise,
 * use kmem_realloc() or kmem_alloc() to adjust the size of the buffer
 * to what is needed.
 *
 * ip -- the inode whose if_data area is changing
 * byte_diff -- the change in the number of bytes, positive or negative,
 *	 requested for the if_data array.
 */
void
xfs_idata_realloc(
	xfs_inode_t	*ip,
	int		byte_diff,
	int		whichfork)
{
	xfs_ifork_t	*ifp;
	int		new_size;
	int		real_size;

	if (byte_diff == 0) {
		return;
	}

	ifp = XFS_IFORK_PTR(ip, whichfork);
	new_size = (int)ifp->if_bytes + byte_diff;
	ASSERT(new_size >= 0);

	if (new_size == 0) {
		if (ifp->if_u1.if_data != ifp->if_u2.if_inline_data) {
			kmem_free(ifp->if_u1.if_data, ifp->if_real_bytes);
		}
		ifp->if_u1.if_data = NULL;
		real_size = 0;
	} else if (new_size <= sizeof(ifp->if_u2.if_inline_data)) {
		/*
		 * If the valid extents/data can fit in if_inline_ext/data,
		 * copy them from the malloc'd vector and free it.
		 */
		if (ifp->if_u1.if_data == NULL) {
			ifp->if_u1.if_data = ifp->if_u2.if_inline_data;
		} else if (ifp->if_u1.if_data != ifp->if_u2.if_inline_data) {
			ASSERT(ifp->if_real_bytes != 0);
			memcpy(ifp->if_u2.if_inline_data, ifp->if_u1.if_data,
			      new_size);
			kmem_free(ifp->if_u1.if_data, ifp->if_real_bytes);
			ifp->if_u1.if_data = ifp->if_u2.if_inline_data;
		}
		real_size = 0;
	} else {
		/*
		 * Stuck with malloc/realloc.
		 * For inline data, the underlying buffer must be
		 * a multiple of 4 bytes in size so that it can be
		 * logged and stay on word boundaries.  We enforce
		 * that here.
		 */
		real_size = roundup(new_size, 4);
		if (ifp->if_u1.if_data == NULL) {
			ASSERT(ifp->if_real_bytes == 0);
			ifp->if_u1.if_data = kmem_alloc(real_size, KM_SLEEP);
		} else if (ifp->if_u1.if_data != ifp->if_u2.if_inline_data) {
			/*
			 * Only do the realloc if the underlying size
			 * is really changing.
			 */
			if (ifp->if_real_bytes != real_size) {
				ifp->if_u1.if_data =
					kmem_realloc(ifp->if_u1.if_data,
							real_size,
							ifp->if_real_bytes,
							KM_SLEEP);
			}
		} else {
			ASSERT(ifp->if_real_bytes == 0);
			ifp->if_u1.if_data = kmem_alloc(real_size, KM_SLEEP);
			memcpy(ifp->if_u1.if_data, ifp->if_u2.if_inline_data,
				ifp->if_bytes);
		}
	}
	ifp->if_real_bytes = real_size;
	ifp->if_bytes = new_size;
	ASSERT(ifp->if_bytes <= XFS_IFORK_SIZE(ip, whichfork));
}




/*
 * Map inode to disk block and offset.
 *
 * mp -- the mount point structure for the current file system
 * tp -- the current transaction
 * ino -- the inode number of the inode to be located
 * imap -- this structure is filled in with the information necessary
 *	 to retrieve the given inode from disk
 * flags -- flags to pass to xfs_dilocate indicating whether or not
 *	 lookups in the inode btree were OK or not
 */
int
xfs_imap(
	xfs_mount_t	*mp,
	xfs_trans_t	*tp,
	xfs_ino_t	ino,
	xfs_imap_t	*imap,
	uint		flags)
{
	xfs_fsblock_t	fsbno;
	int		len;
	int		off;
	int		error;

	fsbno = imap->im_blkno ?
		XFS_DADDR_TO_FSB(mp, imap->im_blkno) : NULLFSBLOCK;
	error = xfs_dilocate(mp, tp, ino, &fsbno, &len, &off, flags);
	if (error)
		return error;

	imap->im_blkno = XFS_FSB_TO_DADDR(mp, fsbno);
	imap->im_len = XFS_FSB_TO_BB(mp, len);
	imap->im_agblkno = XFS_FSB_TO_AGBNO(mp, fsbno);
	imap->im_ioffset = (ushort)off;
	imap->im_boffset = (ushort)(off << mp->m_sb.sb_inodelog);

	/*
	 * If the inode number maps to a block outside the bounds
	 * of the file system then return NULL rather than calling
	 * read_buf and panicing when we get an error from the
	 * driver.
	 */
	if ((imap->im_blkno + imap->im_len) >
	    XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) {
		xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: "
			"(imap->im_blkno (0x%llx) + imap->im_len (0x%llx)) > "
			" XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) (0x%llx)",
			(unsigned long long) imap->im_blkno,
			(unsigned long long) imap->im_len,
			XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks));
		return EINVAL;
	}
	return 0;
}

void
xfs_idestroy_fork(
	xfs_inode_t	*ip,
	int		whichfork)
{
	xfs_ifork_t	*ifp;

	ifp = XFS_IFORK_PTR(ip, whichfork);
	if (ifp->if_broot != NULL) {
		kmem_free(ifp->if_broot, ifp->if_broot_bytes);
		ifp->if_broot = NULL;
	}

	/*
	 * If the format is local, then we can't have an extents
	 * array so just look for an inline data array.  If we're
	 * not local then we may or may not have an extents list,
	 * so check and free it up if we do.
	 */
	if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) {
		if ((ifp->if_u1.if_data != ifp->if_u2.if_inline_data) &&
		    (ifp->if_u1.if_data != NULL)) {
			ASSERT(ifp->if_real_bytes != 0);
			kmem_free(ifp->if_u1.if_data, ifp->if_real_bytes);
			ifp->if_u1.if_data = NULL;
			ifp->if_real_bytes = 0;
		}
	} else if ((ifp->if_flags & XFS_IFEXTENTS) &&
		   ((ifp->if_flags & XFS_IFEXTIREC) ||
		    ((ifp->if_u1.if_extents != NULL) &&
		     (ifp->if_u1.if_extents != ifp->if_u2.if_inline_ext)))) {
		ASSERT(ifp->if_real_bytes != 0);
		xfs_iext_destroy(ifp);
	}
	ASSERT(ifp->if_u1.if_extents == NULL ||
	       ifp->if_u1.if_extents == ifp->if_u2.if_inline_ext);
	ASSERT(ifp->if_real_bytes == 0);
	if (whichfork == XFS_ATTR_FORK) {
		kmem_zone_free(xfs_ifork_zone, ip->i_afp);
		ip->i_afp = NULL;
	}
}

/*
 * This is called free all the memory associated with an inode.
 * It must free the inode itself and any buffers allocated for
 * if_extents/if_data and if_broot.  It must also free the lock
 * associated with the inode.
 */
void
xfs_idestroy(
	xfs_inode_t	*ip)
{
	switch (ip->i_d.di_mode & S_IFMT) {
	case S_IFREG:
	case S_IFDIR:
	case S_IFLNK:
		xfs_idestroy_fork(ip, XFS_DATA_FORK);
		break;
	}
	if (ip->i_afp)
		xfs_idestroy_fork(ip, XFS_ATTR_FORK);
	mrfree(&ip->i_lock);
	mrfree(&ip->i_iolock);
	freesema(&ip->i_flock);

#ifdef XFS_INODE_TRACE
	ktrace_free(ip->i_trace);
#endif
#ifdef XFS_BMAP_TRACE
	ktrace_free(ip->i_xtrace);
#endif
#ifdef XFS_BMBT_TRACE
	ktrace_free(ip->i_btrace);
#endif
#ifdef XFS_RW_TRACE
	ktrace_free(ip->i_rwtrace);
#endif
#ifdef XFS_ILOCK_TRACE
	ktrace_free(ip->i_lock_trace);
#endif
#ifdef XFS_DIR2_TRACE
	ktrace_free(ip->i_dir_trace);
#endif
	if (ip->i_itemp) {
		/*
		 * Only if we are shutting down the fs will we see an
		 * inode still in the AIL. If it is there, we should remove
		 * it to prevent a use-after-free from occurring.
		 */
		xfs_mount_t	*mp = ip->i_mount;
		xfs_log_item_t	*lip = &ip->i_itemp->ili_item;

		ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
				       XFS_FORCED_SHUTDOWN(ip->i_mount));
		if (lip->li_flags & XFS_LI_IN_AIL) {
			spin_lock(&mp->m_ail_lock);
			if (lip->li_flags & XFS_LI_IN_AIL)
				xfs_trans_delete_ail(mp, lip);
			else
				spin_unlock(&mp->m_ail_lock);
		}
		xfs_inode_item_destroy(ip);
	}
	kmem_zone_free(xfs_inode_zone, ip);
}


/*
 * Increment the pin count of the given buffer.
 * This value is protected by ipinlock spinlock in the mount structure.
 */
void
xfs_ipin(
	xfs_inode_t	*ip)
{
	ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE));

	atomic_inc(&ip->i_pincount);
}

/*
 * Decrement the pin count of the given inode, and wake up
 * anyone in xfs_iwait_unpin() if the count goes to 0.  The
 * inode must have been previously pinned with a call to xfs_ipin().
 */
void
xfs_iunpin(
	xfs_inode_t	*ip)
{
	ASSERT(atomic_read(&ip->i_pincount) > 0);

	if (atomic_dec_and_test(&ip->i_pincount))
		wake_up(&ip->i_ipin_wait);
}

/*
 * This is called to unpin an inode. It can be directed to wait or to return
 * immediately without waiting for the inode to be unpinned.  The caller must
 * have the inode locked in at least shared mode so that the buffer cannot be
 * subsequently pinned once someone is waiting for it to be unpinned.
 */
STATIC void
__xfs_iunpin_wait(
	xfs_inode_t	*ip,
	int		wait)
{
	xfs_inode_log_item_t	*iip = ip->i_itemp;

	ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE | MR_ACCESS));
	if (atomic_read(&ip->i_pincount) == 0)
		return;

	/* Give the log a push to start the unpinning I/O */
	xfs_log_force(ip->i_mount, (iip && iip->ili_last_lsn) ?
				iip->ili_last_lsn : 0, XFS_LOG_FORCE);
	if (wait)
		wait_event(ip->i_ipin_wait, (atomic_read(&ip->i_pincount) == 0));
}

static inline void
xfs_iunpin_wait(
	xfs_inode_t	*ip)
{
	__xfs_iunpin_wait(ip, 1);
}

static inline void
xfs_iunpin_nowait(
	xfs_inode_t	*ip)
{
	__xfs_iunpin_wait(ip, 0);
}


/*
 * xfs_iextents_copy()
 *
 * This is called to copy the REAL extents (as opposed to the delayed
 * allocation extents) from the inode into the given buffer.  It
 * returns the number of bytes copied into the buffer.
 *
 * If there are no delayed allocation extents, then we can just
 * memcpy() the extents into the buffer.  Otherwise, we need to
 * examine each extent in turn and skip those which are delayed.
 */
int
xfs_iextents_copy(
	xfs_inode_t		*ip,
	xfs_bmbt_rec_t		*dp,
	int			whichfork)
{
	int			copied;
	int			i;
	xfs_ifork_t		*ifp;
	int			nrecs;
	xfs_fsblock_t		start_block;

	ifp = XFS_IFORK_PTR(ip, whichfork);
	ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE|MR_ACCESS));
	ASSERT(ifp->if_bytes > 0);

	nrecs = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
	XFS_BMAP_TRACE_EXLIST(ip, nrecs, whichfork);
	ASSERT(nrecs > 0);

	/*
	 * There are some delayed allocation extents in the
	 * inode, so copy the extents one at a time and skip
	 * the delayed ones.  There must be at least one
	 * non-delayed extent.
	 */
	copied = 0;
	for (i = 0; i < nrecs; i++) {
		xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, i);
		start_block = xfs_bmbt_get_startblock(ep);
		if (ISNULLSTARTBLOCK(start_block)) {
			/*
			 * It's a delayed allocation extent, so skip it.
			 */
			continue;
		}

		/* Translate to on disk format */
		put_unaligned(cpu_to_be64(ep->l0), &dp->l0);
		put_unaligned(cpu_to_be64(ep->l1), &dp->l1);
		dp++;
		copied++;
	}
	ASSERT(copied != 0);
	xfs_validate_extents(ifp, copied, XFS_EXTFMT_INODE(ip));

	return (copied * (uint)sizeof(xfs_bmbt_rec_t));
}

/*
 * Each of the following cases stores data into the same region
 * of the on-disk inode, so only one of them can be valid at
 * any given time. While it is possible to have conflicting formats
 * and log flags, e.g. having XFS_ILOG_?DATA set when the fork is
 * in EXTENTS format, this can only happen when the fork has
 * changed formats after being modified but before being flushed.
 * In these cases, the format always takes precedence, because the
 * format indicates the current state of the fork.
 */
/*ARGSUSED*/
STATIC void
xfs_iflush_fork(
	xfs_inode_t		*ip,
	xfs_dinode_t		*dip,
	xfs_inode_log_item_t	*iip,
	int			whichfork,
	xfs_buf_t		*bp)
{
	char			*cp;
	xfs_ifork_t		*ifp;
	xfs_mount_t		*mp;
#ifdef XFS_TRANS_DEBUG
	int			first;
#endif
	static const short	brootflag[2] =
		{ XFS_ILOG_DBROOT, XFS_ILOG_ABROOT };
	static const short	dataflag[2] =
		{ XFS_ILOG_DDATA, XFS_ILOG_ADATA };
	static const short	extflag[2] =
		{ XFS_ILOG_DEXT, XFS_ILOG_AEXT };

	if (!iip)
		return;
	ifp = XFS_IFORK_PTR(ip, whichfork);
	/*
	 * This can happen if we gave up in iformat in an error path,
	 * for the attribute fork.
	 */
	if (!ifp) {
		ASSERT(whichfork == XFS_ATTR_FORK);
		return;
	}
	cp = XFS_DFORK_PTR(dip, whichfork);
	mp = ip->i_mount;
	switch (XFS_IFORK_FORMAT(ip, whichfork)) {
	case XFS_DINODE_FMT_LOCAL:
		if ((iip->ili_format.ilf_fields & dataflag[whichfork]) &&
		    (ifp->if_bytes > 0)) {
			ASSERT(ifp->if_u1.if_data != NULL);
			ASSERT(ifp->if_bytes <= XFS_IFORK_SIZE(ip, whichfork));
			memcpy(cp, ifp->if_u1.if_data, ifp->if_bytes);
		}
		break;

	case XFS_DINODE_FMT_EXTENTS:
		ASSERT((ifp->if_flags & XFS_IFEXTENTS) ||
		       !(iip->ili_format.ilf_fields & extflag[whichfork]));
		ASSERT((xfs_iext_get_ext(ifp, 0) != NULL) ||
			(ifp->if_bytes == 0));
		ASSERT((xfs_iext_get_ext(ifp, 0) == NULL) ||
			(ifp->if_bytes > 0));
		if ((iip->ili_format.ilf_fields & extflag[whichfork]) &&
		    (ifp->if_bytes > 0)) {
			ASSERT(XFS_IFORK_NEXTENTS(ip, whichfork) > 0);
			(void)xfs_iextents_copy(ip, (xfs_bmbt_rec_t *)cp,
				whichfork);
		}
		break;

	case XFS_DINODE_FMT_BTREE:
		if ((iip->ili_format.ilf_fields & brootflag[whichfork]) &&
		    (ifp->if_broot_bytes > 0)) {
			ASSERT(ifp->if_broot != NULL);
			ASSERT(ifp->if_broot_bytes <=
			       (XFS_IFORK_SIZE(ip, whichfork) +
				XFS_BROOT_SIZE_ADJ));
			xfs_bmbt_to_bmdr(ifp->if_broot, ifp->if_broot_bytes,
				(xfs_bmdr_block_t *)cp,
				XFS_DFORK_SIZE(dip, mp, whichfork));
		}
		break;

	case XFS_DINODE_FMT_DEV:
		if (iip->ili_format.ilf_fields & XFS_ILOG_DEV) {
			ASSERT(whichfork == XFS_DATA_FORK);
			dip->di_u.di_dev = cpu_to_be32(ip->i_df.if_u2.if_rdev);
		}
		break;

	case XFS_DINODE_FMT_UUID:
		if (iip->ili_format.ilf_fields & XFS_ILOG_UUID) {
			ASSERT(whichfork == XFS_DATA_FORK);
			memcpy(&dip->di_u.di_muuid, &ip->i_df.if_u2.if_uuid,
				sizeof(uuid_t));
		}
		break;

	default:
		ASSERT(0);
		break;
	}
}

STATIC int
xfs_iflush_cluster(
	xfs_inode_t	*ip,
	xfs_buf_t	*bp)
{
	xfs_mount_t		*mp = ip->i_mount;
	xfs_perag_t		*pag = xfs_get_perag(mp, ip->i_ino);
	unsigned long		first_index, mask;
	int			ilist_size;
	xfs_inode_t		**ilist;
	xfs_inode_t		*iq;
	int			nr_found;
	int			clcount = 0;
	int			bufwasdelwri;
	int			i;

	ASSERT(pag->pagi_inodeok);
	ASSERT(pag->pag_ici_init);

	ilist_size = XFS_INODE_CLUSTER_SIZE(mp) * sizeof(xfs_inode_t *);
	ilist = kmem_alloc(ilist_size, KM_MAYFAIL);
	if (!ilist)
		return 0;

	mask = ~(((XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_inodelog)) - 1);
	first_index = XFS_INO_TO_AGINO(mp, ip->i_ino) & mask;
	read_lock(&pag->pag_ici_lock);
	/* really need a gang lookup range call here */
	nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void**)ilist,
					first_index,
					XFS_INODE_CLUSTER_SIZE(mp));
	if (nr_found == 0)
		goto out_free;

	for (i = 0; i < nr_found; i++) {
		iq = ilist[i];
		if (iq == ip)
			continue;
		/* if the inode lies outside this cluster, we're done. */
		if ((XFS_INO_TO_AGINO(mp, iq->i_ino) & mask) != first_index)
			break;
		/*
		 * Do an un-protected check to see if the inode is dirty and
		 * is a candidate for flushing.  These checks will be repeated
		 * later after the appropriate locks are acquired.
		 */
		if (xfs_inode_clean(iq) && xfs_ipincount(iq) == 0)
			continue;

		/*
		 * Try to get locks.  If any are unavailable or it is pinned,
		 * then this inode cannot be flushed and is skipped.
		 */

		if (!xfs_ilock_nowait(iq, XFS_ILOCK_SHARED))
			continue;
		if (!xfs_iflock_nowait(iq)) {
			xfs_iunlock(iq, XFS_ILOCK_SHARED);
			continue;
		}
		if (xfs_ipincount(iq)) {
			xfs_ifunlock(iq);
			xfs_iunlock(iq, XFS_ILOCK_SHARED);
			continue;
		}

		/*
		 * arriving here means that this inode can be flushed.  First
		 * re-check that it's dirty before flushing.
		 */
		if (!xfs_inode_clean(iq)) {
			int	error;
			error = xfs_iflush_int(iq, bp);
			if (error) {
				xfs_iunlock(iq, XFS_ILOCK_SHARED);
				goto cluster_corrupt_out;
			}
			clcount++;
		} else {
			xfs_ifunlock(iq);
		}
		xfs_iunlock(iq, XFS_ILOCK_SHARED);
	}

	if (clcount) {
		XFS_STATS_INC(xs_icluster_flushcnt);
		XFS_STATS_ADD(xs_icluster_flushinode, clcount);
	}

out_free:
	read_unlock(&pag->pag_ici_lock);
	kmem_free(ilist, ilist_size);
	return 0;


cluster_corrupt_out:
	/*
	 * Corruption detected in the clustering loop.  Invalidate the
	 * inode buffer and shut down the filesystem.
	 */
	read_unlock(&pag->pag_ici_lock);
	/*
	 * Clean up the buffer.  If it was B_DELWRI, just release it --
	 * brelse can handle it with no problems.  If not, shut down the
	 * filesystem before releasing the buffer.
	 */
	bufwasdelwri = XFS_BUF_ISDELAYWRITE(bp);
	if (bufwasdelwri)
		xfs_buf_relse(bp);

	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);

	if (!bufwasdelwri) {
		/*
		 * Just like incore_relse: if we have b_iodone functions,
		 * mark the buffer as an error and call them.  Otherwise
		 * mark it as stale and brelse.
		 */
		if (XFS_BUF_IODONE_FUNC(bp)) {
			XFS_BUF_CLR_BDSTRAT_FUNC(bp);
			XFS_BUF_UNDONE(bp);
			XFS_BUF_STALE(bp);
			XFS_BUF_SHUT(bp);
			XFS_BUF_ERROR(bp,EIO);
			xfs_biodone(bp);
		} else {
			XFS_BUF_STALE(bp);
			xfs_buf_relse(bp);
		}
	}

	/*
	 * Unlocks the flush lock
	 */
	xfs_iflush_abort(iq);
	kmem_free(ilist, ilist_size);
	return XFS_ERROR(EFSCORRUPTED);
}

/*
 * xfs_iflush() will write a modified inode's changes out to the
 * inode's on disk home.  The caller must have the inode lock held
 * in at least shared mode and the inode flush semaphore must be
 * held as well.  The inode lock will still be held upon return from
 * the call and the caller is free to unlock it.
 * The inode flush lock will be unlocked when the inode reaches the disk.
 * The flags indicate how the inode's buffer should be written out.
 */
int
xfs_iflush(
	xfs_inode_t		*ip,
	uint			flags)
{
	xfs_inode_log_item_t	*iip;
	xfs_buf_t		*bp;
	xfs_dinode_t		*dip;
	xfs_mount_t		*mp;
	int			error;
	int			noblock = (flags == XFS_IFLUSH_ASYNC_NOBLOCK);
	enum { INT_DELWRI = (1 << 0), INT_ASYNC = (1 << 1) };

	XFS_STATS_INC(xs_iflush_count);

	ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE|MR_ACCESS));
	ASSERT(issemalocked(&(ip->i_flock)));
	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
	       ip->i_d.di_nextents > ip->i_df.if_ext_max);

	iip = ip->i_itemp;
	mp = ip->i_mount;

	/*
	 * If the inode isn't dirty, then just release the inode
	 * flush lock and do nothing.
	 */
	if (xfs_inode_clean(ip)) {
		ASSERT((iip != NULL) ?
			 !(iip->ili_item.li_flags & XFS_LI_IN_AIL) : 1);
		xfs_ifunlock(ip);
		return 0;
	}

	/*
	 * We can't flush the inode until it is unpinned, so wait for it if we
	 * are allowed to block.  We know noone new can pin it, because we are
	 * holding the inode lock shared and you need to hold it exclusively to
	 * pin the inode.
	 *
	 * If we are not allowed to block, force the log out asynchronously so
	 * that when we come back the inode will be unpinned. If other inodes
	 * in the same cluster are dirty, they will probably write the inode
	 * out for us if they occur after the log force completes.
	 */
	if (noblock && xfs_ipincount(ip)) {
		xfs_iunpin_nowait(ip);
		xfs_ifunlock(ip);
		return EAGAIN;
	}
	xfs_iunpin_wait(ip);

	/*
	 * This may have been unpinned because the filesystem is shutting
	 * down forcibly. If that's the case we must not write this inode
	 * to disk, because the log record didn't make it to disk!
	 */
	if (XFS_FORCED_SHUTDOWN(mp)) {
		ip->i_update_core = 0;
		if (iip)
			iip->ili_format.ilf_fields = 0;
		xfs_ifunlock(ip);
		return XFS_ERROR(EIO);
	}

	/*
	 * Decide how buffer will be flushed out.  This is done before
	 * the call to xfs_iflush_int because this field is zeroed by it.
	 */
	if (iip != NULL && iip->ili_format.ilf_fields != 0) {
		/*
		 * Flush out the inode buffer according to the directions
		 * of the caller.  In the cases where the caller has given
		 * us a choice choose the non-delwri case.  This is because
		 * the inode is in the AIL and we need to get it out soon.
		 */
		switch (flags) {
		case XFS_IFLUSH_SYNC:
		case XFS_IFLUSH_DELWRI_ELSE_SYNC:
			flags = 0;
			break;
		case XFS_IFLUSH_ASYNC_NOBLOCK:
		case XFS_IFLUSH_ASYNC:
		case XFS_IFLUSH_DELWRI_ELSE_ASYNC:
			flags = INT_ASYNC;
			break;
		case XFS_IFLUSH_DELWRI:
			flags = INT_DELWRI;
			break;
		default:
			ASSERT(0);
			flags = 0;
			break;
		}
	} else {
		switch (flags) {
		case XFS_IFLUSH_DELWRI_ELSE_SYNC:
		case XFS_IFLUSH_DELWRI_ELSE_ASYNC:
		case XFS_IFLUSH_DELWRI:
			flags = INT_DELWRI;
			break;
		case XFS_IFLUSH_ASYNC_NOBLOCK:
		case XFS_IFLUSH_ASYNC:
			flags = INT_ASYNC;
			break;
		case XFS_IFLUSH_SYNC:
			flags = 0;
			break;
		default:
			ASSERT(0);
			flags = 0;
			break;
		}
	}

	/*
	 * Get the buffer containing the on-disk inode.
	 */
	error = xfs_itobp(mp, NULL, ip, &dip, &bp, 0, 0,
				noblock ? XFS_BUF_TRYLOCK : XFS_BUF_LOCK);
	if (error || !bp) {
		xfs_ifunlock(ip);
		return error;
	}

	/*
	 * First flush out the inode that xfs_iflush was called with.
	 */
	error = xfs_iflush_int(ip, bp);
	if (error)
		goto corrupt_out;

	/*
	 * If the buffer is pinned then push on the log now so we won't
	 * get stuck waiting in the write for too long.
	 */
	if (XFS_BUF_ISPINNED(bp))
		xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE);

	/*
	 * inode clustering:
	 * see if other inodes can be gathered into this write
	 */
	error = xfs_iflush_cluster(ip, bp);
	if (error)
		goto cluster_corrupt_out;

	if (flags & INT_DELWRI) {
		xfs_bdwrite(mp, bp);
	} else if (flags & INT_ASYNC) {
		error = xfs_bawrite(mp, bp);
	} else {
		error = xfs_bwrite(mp, bp);
	}
	return error;

corrupt_out:
	xfs_buf_relse(bp);
	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
cluster_corrupt_out:
	/*
	 * Unlocks the flush lock
	 */
	xfs_iflush_abort(ip);
	return XFS_ERROR(EFSCORRUPTED);
}


STATIC int
xfs_iflush_int(
	xfs_inode_t		*ip,
	xfs_buf_t		*bp)
{
	xfs_inode_log_item_t	*iip;
	xfs_dinode_t		*dip;
	xfs_mount_t		*mp;
#ifdef XFS_TRANS_DEBUG
	int			first;
#endif

	ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE|MR_ACCESS));
	ASSERT(issemalocked(&(ip->i_flock)));
	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
	       ip->i_d.di_nextents > ip->i_df.if_ext_max);

	iip = ip->i_itemp;
	mp = ip->i_mount;


	/*
	 * If the inode isn't dirty, then just release the inode
	 * flush lock and do nothing.
	 */
	if (xfs_inode_clean(ip)) {
		xfs_ifunlock(ip);
		return 0;
	}

	/* set *dip = inode's place in the buffer */
	dip = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_boffset);

	/*
	 * Clear i_update_core before copying out the data.
	 * This is for coordination with our timestamp updates
	 * that don't hold the inode lock. They will always
	 * update the timestamps BEFORE setting i_update_core,
	 * so if we clear i_update_core after they set it we
	 * are guaranteed to see their updates to the timestamps.
	 * I believe that this depends on strongly ordered memory
	 * semantics, but we have that.  We use the SYNCHRONIZE
	 * macro to make sure that the compiler does not reorder
	 * the i_update_core access below the data copy below.
	 */
	ip->i_update_core = 0;
	SYNCHRONIZE();

	/*
	 * Make sure to get the latest atime from the Linux inode.
	 */
	xfs_synchronize_atime(ip);

	if (XFS_TEST_ERROR(be16_to_cpu(dip->di_core.di_magic) != XFS_DINODE_MAGIC,
			       mp, XFS_ERRTAG_IFLUSH_1, XFS_RANDOM_IFLUSH_1)) {
		xfs_cmn_err(XFS_PTAG_IFLUSH, CE_ALERT, mp,
		    "xfs_iflush: Bad inode %Lu magic number 0x%x, ptr 0x%p",
			ip->i_ino, be16_to_cpu(dip->di_core.di_magic), dip);
		goto corrupt_out;
	}
	if (XFS_TEST_ERROR(ip->i_d.di_magic != XFS_DINODE_MAGIC,
				mp, XFS_ERRTAG_IFLUSH_2, XFS_RANDOM_IFLUSH_2)) {
		xfs_cmn_err(XFS_PTAG_IFLUSH, CE_ALERT, mp,
			"xfs_iflush: Bad inode %Lu, ptr 0x%p, magic number 0x%x",
			ip->i_ino, ip, ip->i_d.di_magic);
		goto corrupt_out;
	}
	if ((ip->i_d.di_mode & S_IFMT) == S_IFREG) {
		if (XFS_TEST_ERROR(
		    (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
		    (ip->i_d.di_format != XFS_DINODE_FMT_BTREE),
		    mp, XFS_ERRTAG_IFLUSH_3, XFS_RANDOM_IFLUSH_3)) {
			xfs_cmn_err(XFS_PTAG_IFLUSH, CE_ALERT, mp,
				"xfs_iflush: Bad regular inode %Lu, ptr 0x%p",
				ip->i_ino, ip);
			goto corrupt_out;
		}
	} else if ((ip->i_d.di_mode & S_IFMT) == S_IFDIR) {
		if (XFS_TEST_ERROR(
		    (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
		    (ip->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
		    (ip->i_d.di_format != XFS_DINODE_FMT_LOCAL),
		    mp, XFS_ERRTAG_IFLUSH_4, XFS_RANDOM_IFLUSH_4)) {
			xfs_cmn_err(XFS_PTAG_IFLUSH, CE_ALERT, mp,
				"xfs_iflush: Bad directory inode %Lu, ptr 0x%p",
				ip->i_ino, ip);
			goto corrupt_out;
		}
	}
	if (XFS_TEST_ERROR(ip->i_d.di_nextents + ip->i_d.di_anextents >
				ip->i_d.di_nblocks, mp, XFS_ERRTAG_IFLUSH_5,
				XFS_RANDOM_IFLUSH_5)) {
		xfs_cmn_err(XFS_PTAG_IFLUSH, CE_ALERT, mp,
			"xfs_iflush: detected corrupt incore inode %Lu, total extents = %d, nblocks = %Ld, ptr 0x%p",
			ip->i_ino,
			ip->i_d.di_nextents + ip->i_d.di_anextents,
			ip->i_d.di_nblocks,
			ip);
		goto corrupt_out;
	}
	if (XFS_TEST_ERROR(ip->i_d.di_forkoff > mp->m_sb.sb_inodesize,
				mp, XFS_ERRTAG_IFLUSH_6, XFS_RANDOM_IFLUSH_6)) {
		xfs_cmn_err(XFS_PTAG_IFLUSH, CE_ALERT, mp,
			"xfs_iflush: bad inode %Lu, forkoff 0x%x, ptr 0x%p",
			ip->i_ino, ip->i_d.di_forkoff, ip);
		goto corrupt_out;
	}
	/*
	 * bump the flush iteration count, used to detect flushes which
	 * postdate a log record during recovery.
	 */

	ip->i_d.di_flushiter++;

	/*
	 * Copy the dirty parts of the inode into the on-disk
	 * inode.  We always copy out the core of the inode,
	 * because if the inode is dirty at all the core must
	 * be.
	 */
	xfs_dinode_to_disk(&dip->di_core, &ip->i_d);

	/* Wrap, we never let the log put out DI_MAX_FLUSH */
	if (ip->i_d.di_flushiter == DI_MAX_FLUSH)
		ip->i_d.di_flushiter = 0;

	/*
	 * If this is really an old format inode and the superblock version
	 * has not been updated to support only new format inodes, then
	 * convert back to the old inode format.  If the superblock version
	 * has been updated, then make the conversion permanent.
	 */
	ASSERT(ip->i_d.di_version == XFS_DINODE_VERSION_1 ||
	       xfs_sb_version_hasnlink(&mp->m_sb));
	if (ip->i_d.di_version == XFS_DINODE_VERSION_1) {
		if (!xfs_sb_version_hasnlink(&mp->m_sb)) {
			/*
			 * Convert it back.
			 */
			ASSERT(ip->i_d.di_nlink <= XFS_MAXLINK_1);
			dip->di_core.di_onlink = cpu_to_be16(ip->i_d.di_nlink);
		} else {
			/*
			 * The superblock version has already been bumped,
			 * so just make the conversion to the new inode
			 * format permanent.
			 */
			ip->i_d.di_version = XFS_DINODE_VERSION_2;
			dip->di_core.di_version =  XFS_DINODE_VERSION_2;
			ip->i_d.di_onlink = 0;
			dip->di_core.di_onlink = 0;
			memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
			memset(&(dip->di_core.di_pad[0]), 0,
			      sizeof(dip->di_core.di_pad));
			ASSERT(ip->i_d.di_projid == 0);
		}
	}

	xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK, bp);
	if (XFS_IFORK_Q(ip))
		xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK, bp);
	xfs_inobp_check(mp, bp);

	/*
	 * We've recorded everything logged in the inode, so we'd
	 * like to clear the ilf_fields bits so we don't log and
	 * flush things unnecessarily.  However, we can't stop
	 * logging all this information until the data we've copied
	 * into the disk buffer is written to disk.  If we did we might
	 * overwrite the copy of the inode in the log with all the
	 * data after re-logging only part of it, and in the face of
	 * a crash we wouldn't have all the data we need to recover.
	 *
	 * What we do is move the bits to the ili_last_fields field.
	 * When logging the inode, these bits are moved back to the
	 * ilf_fields field.  In the xfs_iflush_done() routine we
	 * clear ili_last_fields, since we know that the information
	 * those bits represent is permanently on disk.  As long as
	 * the flush completes before the inode is logged again, then
	 * both ilf_fields and ili_last_fields will be cleared.
	 *
	 * We can play with the ilf_fields bits here, because the inode
	 * lock must be held exclusively in order to set bits there
	 * and the flush lock protects the ili_last_fields bits.
	 * Set ili_logged so the flush done
	 * routine can tell whether or not to look in the AIL.
	 * Also, store the current LSN of the inode so that we can tell
	 * whether the item has moved in the AIL from xfs_iflush_done().
	 * In order to read the lsn we need the AIL lock, because
	 * it is a 64 bit value that cannot be read atomically.
	 */
	if (iip != NULL && iip->ili_format.ilf_fields != 0) {
		iip->ili_last_fields = iip->ili_format.ilf_fields;
		iip->ili_format.ilf_fields = 0;
		iip->ili_logged = 1;

		ASSERT(sizeof(xfs_lsn_t) == 8);	/* don't lock if it shrinks */
		spin_lock(&mp->m_ail_lock);
		iip->ili_flush_lsn = iip->ili_item.li_lsn;
		spin_unlock(&mp->m_ail_lock);

		/*
		 * Attach the function xfs_iflush_done to the inode's
		 * buffer.  This will remove the inode from the AIL
		 * and unlock the inode's flush lock when the inode is
		 * completely written to disk.
		 */
		xfs_buf_attach_iodone(bp, (void(*)(xfs_buf_t*,xfs_log_item_t*))
				      xfs_iflush_done, (xfs_log_item_t *)iip);

		ASSERT(XFS_BUF_FSPRIVATE(bp, void *) != NULL);
		ASSERT(XFS_BUF_IODONE_FUNC(bp) != NULL);
	} else {
		/*
		 * We're flushing an inode which is not in the AIL and has
		 * not been logged but has i_update_core set.  For this
		 * case we can use a B_DELWRI flush and immediately drop
		 * the inode flush lock because we can avoid the whole
		 * AIL state thing.  It's OK to drop the flush lock now,
		 * because we've already locked the buffer and to do anything
		 * you really need both.
		 */
		if (iip != NULL) {
			ASSERT(iip->ili_logged == 0);
			ASSERT(iip->ili_last_fields == 0);
			ASSERT((iip->ili_item.li_flags & XFS_LI_IN_AIL) == 0);
		}
		xfs_ifunlock(ip);
	}

	return 0;

corrupt_out:
	return XFS_ERROR(EFSCORRUPTED);
}


/*
 * Flush all inactive inodes in mp.
 */
void
xfs_iflush_all(
	xfs_mount_t	*mp)
{
	xfs_inode_t	*ip;
	bhv_vnode_t	*vp;

 again:
	XFS_MOUNT_ILOCK(mp);
	ip = mp->m_inodes;
	if (ip == NULL)
		goto out;

	do {
		/* Make sure we skip markers inserted by sync */
		if (ip->i_mount == NULL) {
			ip = ip->i_mnext;
			continue;
		}

		vp = XFS_ITOV_NULL(ip);
		if (!vp) {
			XFS_MOUNT_IUNLOCK(mp);
			xfs_finish_reclaim(ip, 0, XFS_IFLUSH_ASYNC);
			goto again;
		}

		ASSERT(vn_count(vp) == 0);

		ip = ip->i_mnext;
	} while (ip != mp->m_inodes);
 out:
	XFS_MOUNT_IUNLOCK(mp);
}

#ifdef XFS_ILOCK_TRACE
ktrace_t	*xfs_ilock_trace_buf;

void
xfs_ilock_trace(xfs_inode_t *ip, int lock, unsigned int lockflags, inst_t *ra)
{
	ktrace_enter(ip->i_lock_trace,
		     (void *)ip,
		     (void *)(unsigned long)lock, /* 1 = LOCK, 3=UNLOCK, etc */
		     (void *)(unsigned long)lockflags, /* XFS_ILOCK_EXCL etc */
		     (void *)ra,		/* caller of ilock */
		     (void *)(unsigned long)current_cpu(),
		     (void *)(unsigned long)current_pid(),
		     NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL,NULL);
}
#endif

/*
 * Return a pointer to the extent record at file index idx.
 */
xfs_bmbt_rec_host_t *
xfs_iext_get_ext(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	xfs_extnum_t	idx)		/* index of target extent */
{
	ASSERT(idx >= 0);
	if ((ifp->if_flags & XFS_IFEXTIREC) && (idx == 0)) {
		return ifp->if_u1.if_ext_irec->er_extbuf;
	} else if (ifp->if_flags & XFS_IFEXTIREC) {
		xfs_ext_irec_t	*erp;		/* irec pointer */
		int		erp_idx = 0;	/* irec index */
		xfs_extnum_t	page_idx = idx;	/* ext index in target list */

		erp = xfs_iext_idx_to_irec(ifp, &page_idx, &erp_idx, 0);
		return &erp->er_extbuf[page_idx];
	} else if (ifp->if_bytes) {
		return &ifp->if_u1.if_extents[idx];
	} else {
		return NULL;
	}
}

/*
 * Insert new item(s) into the extent records for incore inode
 * fork 'ifp'.  'count' new items are inserted at index 'idx'.
 */
void
xfs_iext_insert(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	xfs_extnum_t	idx,		/* starting index of new items */
	xfs_extnum_t	count,		/* number of inserted items */
	xfs_bmbt_irec_t	*new)		/* items to insert */
{
	xfs_extnum_t	i;		/* extent record index */

	ASSERT(ifp->if_flags & XFS_IFEXTENTS);
	xfs_iext_add(ifp, idx, count);
	for (i = idx; i < idx + count; i++, new++)
		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, i), new);
}

/*
 * This is called when the amount of space required for incore file
 * extents needs to be increased. The ext_diff parameter stores the
 * number of new extents being added and the idx parameter contains
 * the extent index where the new extents will be added. If the new
 * extents are being appended, then we just need to (re)allocate and
 * initialize the space. Otherwise, if the new extents are being
 * inserted into the middle of the existing entries, a bit more work
 * is required to make room for the new extents to be inserted. The
 * caller is responsible for filling in the new extent entries upon
 * return.
 */
void
xfs_iext_add(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	xfs_extnum_t	idx,		/* index to begin adding exts */
	int		ext_diff)	/* number of extents to add */
{
	int		byte_diff;	/* new bytes being added */
	int		new_size;	/* size of extents after adding */
	xfs_extnum_t	nextents;	/* number of extents in file */

	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
	ASSERT((idx >= 0) && (idx <= nextents));
	byte_diff = ext_diff * sizeof(xfs_bmbt_rec_t);
	new_size = ifp->if_bytes + byte_diff;
	/*
	 * If the new number of extents (nextents + ext_diff)
	 * fits inside the inode, then continue to use the inline
	 * extent buffer.
	 */
	if (nextents + ext_diff <= XFS_INLINE_EXTS) {
		if (idx < nextents) {
			memmove(&ifp->if_u2.if_inline_ext[idx + ext_diff],
				&ifp->if_u2.if_inline_ext[idx],
				(nextents - idx) * sizeof(xfs_bmbt_rec_t));
			memset(&ifp->if_u2.if_inline_ext[idx], 0, byte_diff);
		}
		ifp->if_u1.if_extents = ifp->if_u2.if_inline_ext;
		ifp->if_real_bytes = 0;
		ifp->if_lastex = nextents + ext_diff;
	}
	/*
	 * Otherwise use a linear (direct) extent list.
	 * If the extents are currently inside the inode,
	 * xfs_iext_realloc_direct will switch us from
	 * inline to direct extent allocation mode.
	 */
	else if (nextents + ext_diff <= XFS_LINEAR_EXTS) {
		xfs_iext_realloc_direct(ifp, new_size);
		if (idx < nextents) {
			memmove(&ifp->if_u1.if_extents[idx + ext_diff],
				&ifp->if_u1.if_extents[idx],
				(nextents - idx) * sizeof(xfs_bmbt_rec_t));
			memset(&ifp->if_u1.if_extents[idx], 0, byte_diff);
		}
	}
	/* Indirection array */
	else {
		xfs_ext_irec_t	*erp;
		int		erp_idx = 0;
		int		page_idx = idx;

		ASSERT(nextents + ext_diff > XFS_LINEAR_EXTS);
		if (ifp->if_flags & XFS_IFEXTIREC) {
			erp = xfs_iext_idx_to_irec(ifp, &page_idx, &erp_idx, 1);
		} else {
			xfs_iext_irec_init(ifp);
			ASSERT(ifp->if_flags & XFS_IFEXTIREC);
			erp = ifp->if_u1.if_ext_irec;
		}
		/* Extents fit in target extent page */
		if (erp && erp->er_extcount + ext_diff <= XFS_LINEAR_EXTS) {
			if (page_idx < erp->er_extcount) {
				memmove(&erp->er_extbuf[page_idx + ext_diff],
					&erp->er_extbuf[page_idx],
					(erp->er_extcount - page_idx) *
					sizeof(xfs_bmbt_rec_t));
				memset(&erp->er_extbuf[page_idx], 0, byte_diff);
			}
			erp->er_extcount += ext_diff;
			xfs_iext_irec_update_extoffs(ifp, erp_idx + 1, ext_diff);
		}
		/* Insert a new extent page */
		else if (erp) {
			xfs_iext_add_indirect_multi(ifp,
				erp_idx, page_idx, ext_diff);
		}
		/*
		 * If extent(s) are being appended to the last page in
		 * the indirection array and the new extent(s) don't fit
		 * in the page, then erp is NULL and erp_idx is set to
		 * the next index needed in the indirection array.
		 */
		else {
			int	count = ext_diff;

			while (count) {
				erp = xfs_iext_irec_new(ifp, erp_idx);
				erp->er_extcount = count;
				count -= MIN(count, (int)XFS_LINEAR_EXTS);
				if (count) {
					erp_idx++;
				}
			}
		}
	}
	ifp->if_bytes = new_size;
}

/*
 * This is called when incore extents are being added to the indirection
 * array and the new extents do not fit in the target extent list. The
 * erp_idx parameter contains the irec index for the target extent list
 * in the indirection array, and the idx parameter contains the extent
 * index within the list. The number of extents being added is stored
 * in the count parameter.
 *
 *    |-------|   |-------|
 *    |       |   |       |    idx - number of extents before idx
 *    |  idx  |   | count |
 *    |       |   |       |    count - number of extents being inserted at idx
 *    |-------|   |-------|
 *    | count |   | nex2  |    nex2 - number of extents after idx + count
 *    |-------|   |-------|
 */
void
xfs_iext_add_indirect_multi(
	xfs_ifork_t	*ifp,			/* inode fork pointer */
	int		erp_idx,		/* target extent irec index */
	xfs_extnum_t	idx,			/* index within target list */
	int		count)			/* new extents being added */
{
	int		byte_diff;		/* new bytes being added */
	xfs_ext_irec_t	*erp;			/* pointer to irec entry */
	xfs_extnum_t	ext_diff;		/* number of extents to add */
	xfs_extnum_t	ext_cnt;		/* new extents still needed */
	xfs_extnum_t	nex2;			/* extents after idx + count */
	xfs_bmbt_rec_t	*nex2_ep = NULL;	/* temp list for nex2 extents */
	int		nlists;			/* number of irec's (lists) */

	ASSERT(ifp->if_flags & XFS_IFEXTIREC);
	erp = &ifp->if_u1.if_ext_irec[erp_idx];
	nex2 = erp->er_extcount - idx;
	nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;

	/*
	 * Save second part of target extent list
	 * (all extents past */
	if (nex2) {
		byte_diff = nex2 * sizeof(xfs_bmbt_rec_t);
		nex2_ep = (xfs_bmbt_rec_t *) kmem_alloc(byte_diff, KM_SLEEP);
		memmove(nex2_ep, &erp->er_extbuf[idx], byte_diff);
		erp->er_extcount -= nex2;
		xfs_iext_irec_update_extoffs(ifp, erp_idx + 1, -nex2);
		memset(&erp->er_extbuf[idx], 0, byte_diff);
	}

	/*
	 * Add the new extents to the end of the target
	 * list, then allocate new irec record(s) and
	 * extent buffer(s) as needed to store the rest
	 * of the new extents.
	 */
	ext_cnt = count;
	ext_diff = MIN(ext_cnt, (int)XFS_LINEAR_EXTS - erp->er_extcount);
	if (ext_diff) {
		erp->er_extcount += ext_diff;
		xfs_iext_irec_update_extoffs(ifp, erp_idx + 1, ext_diff);
		ext_cnt -= ext_diff;
	}
	while (ext_cnt) {
		erp_idx++;
		erp = xfs_iext_irec_new(ifp, erp_idx);
		ext_diff = MIN(ext_cnt, (int)XFS_LINEAR_EXTS);
		erp->er_extcount = ext_diff;
		xfs_iext_irec_update_extoffs(ifp, erp_idx + 1, ext_diff);
		ext_cnt -= ext_diff;
	}

	/* Add nex2 extents back to indirection array */
	if (nex2) {
		xfs_extnum_t	ext_avail;
		int		i;

		byte_diff = nex2 * sizeof(xfs_bmbt_rec_t);
		ext_avail = XFS_LINEAR_EXTS - erp->er_extcount;
		i = 0;
		/*
		 * If nex2 extents fit in the current page, append
		 * nex2_ep after the new extents.
		 */
		if (nex2 <= ext_avail) {
			i = erp->er_extcount;
		}
		/*
		 * Otherwise, check if space is available in the
		 * next page.
		 */
		else if ((erp_idx < nlists - 1) &&
			 (nex2 <= (ext_avail = XFS_LINEAR_EXTS -
			  ifp->if_u1.if_ext_irec[erp_idx+1].er_extcount))) {
			erp_idx++;
			erp++;
			/* Create a hole for nex2 extents */
			memmove(&erp->er_extbuf[nex2], erp->er_extbuf,
				erp->er_extcount * sizeof(xfs_bmbt_rec_t));
		}
		/*
		 * Final choice, create a new extent page for
		 * nex2 extents.
		 */
		else {
			erp_idx++;
			erp = xfs_iext_irec_new(ifp, erp_idx);
		}
		memmove(&erp->er_extbuf[i], nex2_ep, byte_diff);
		kmem_free(nex2_ep, byte_diff);
		erp->er_extcount += nex2;
		xfs_iext_irec_update_extoffs(ifp, erp_idx + 1, nex2);
	}
}

/*
 * This is called when the amount of space required for incore file
 * extents needs to be decreased. The ext_diff parameter stores the
 * number of extents to be removed and the idx parameter contains
 * the extent index where the extents will be removed from.
 *
 * If the amount of space needed has decreased below the linear
 * limit, XFS_IEXT_BUFSZ, then switch to using the contiguous
 * extent array.  Otherwise, use kmem_realloc() to adjust the
 * size to what is needed.
 */
void
xfs_iext_remove(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	xfs_extnum_t	idx,		/* index to begin removing exts */
	int		ext_diff)	/* number of extents to remove */
{
	xfs_extnum_t	nextents;	/* number of extents in file */
	int		new_size;	/* size of extents after removal */

	ASSERT(ext_diff > 0);
	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
	new_size = (nextents - ext_diff) * sizeof(xfs_bmbt_rec_t);

	if (new_size == 0) {
		xfs_iext_destroy(ifp);
	} else if (ifp->if_flags & XFS_IFEXTIREC) {
		xfs_iext_remove_indirect(ifp, idx, ext_diff);
	} else if (ifp->if_real_bytes) {
		xfs_iext_remove_direct(ifp, idx, ext_diff);
	} else {
		xfs_iext_remove_inline(ifp, idx, ext_diff);
	}
	ifp->if_bytes = new_size;
}

/*
 * This removes ext_diff extents from the inline buffer, beginning
 * at extent index idx.
 */
void
xfs_iext_remove_inline(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	xfs_extnum_t	idx,		/* index to begin removing exts */
	int		ext_diff)	/* number of extents to remove */
{
	int		nextents;	/* number of extents in file */

	ASSERT(!(ifp->if_flags & XFS_IFEXTIREC));
	ASSERT(idx < XFS_INLINE_EXTS);
	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
	ASSERT(((nextents - ext_diff) > 0) &&
		(nextents - ext_diff) < XFS_INLINE_EXTS);

	if (idx + ext_diff < nextents) {
		memmove(&ifp->if_u2.if_inline_ext[idx],
			&ifp->if_u2.if_inline_ext[idx + ext_diff],
			(nextents - (idx + ext_diff)) *
			 sizeof(xfs_bmbt_rec_t));
		memset(&ifp->if_u2.if_inline_ext[nextents - ext_diff],
			0, ext_diff * sizeof(xfs_bmbt_rec_t));
	} else {
		memset(&ifp->if_u2.if_inline_ext[idx], 0,
			ext_diff * sizeof(xfs_bmbt_rec_t));
	}
}

/*
 * This removes ext_diff extents from a linear (direct) extent list,
 * beginning at extent index idx. If the extents are being removed
 * from the end of the list (ie. truncate) then we just need to re-
 * allocate the list to remove the extra space. Otherwise, if the
 * extents are being removed from the middle of the existing extent
 * entries, then we first need to move the extent records beginning
 * at idx + ext_diff up in the list to overwrite the records being
 * removed, then remove the extra space via kmem_realloc.
 */
void
xfs_iext_remove_direct(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	xfs_extnum_t	idx,		/* index to begin removing exts */
	int		ext_diff)	/* number of extents to remove */
{
	xfs_extnum_t	nextents;	/* number of extents in file */
	int		new_size;	/* size of extents after removal */

	ASSERT(!(ifp->if_flags & XFS_IFEXTIREC));
	new_size = ifp->if_bytes -
		(ext_diff * sizeof(xfs_bmbt_rec_t));
	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);

	if (new_size == 0) {
		xfs_iext_destroy(ifp);
		return;
	}
	/* Move extents up in the list (if needed) */
	if (idx + ext_diff < nextents) {
		memmove(&ifp->if_u1.if_extents[idx],
			&ifp->if_u1.if_extents[idx + ext_diff],
			(nextents - (idx + ext_diff)) *
			 sizeof(xfs_bmbt_rec_t));
	}
	memset(&ifp->if_u1.if_extents[nextents - ext_diff],
		0, ext_diff * sizeof(xfs_bmbt_rec_t));
	/*
	 * Reallocate the direct extent list. If the extents
	 * will fit inside the inode then xfs_iext_realloc_direct
	 * will switch from direct to inline extent allocation
	 * mode for us.
	 */
	xfs_iext_realloc_direct(ifp, new_size);
	ifp->if_bytes = new_size;
}

/*
 * This is called when incore extents are being removed from the
 * indirection array and the extents being removed span multiple extent
 * buffers. The idx parameter contains the file extent index where we
 * want to begin removing extents, and the count parameter contains
 * how many extents need to be removed.
 *
 *    |-------|   |-------|
 *    | nex1  |   |       |    nex1 - number of extents before idx
 *    |-------|   | count |
 *    |       |   |       |    count - number of extents being removed at idx
 *    | count |   |-------|
 *    |       |   | nex2  |    nex2 - number of extents after idx + count
 *    |-------|   |-------|
 */
void
xfs_iext_remove_indirect(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	xfs_extnum_t	idx,		/* index to begin removing extents */
	int		count)		/* number of extents to remove */
{
	xfs_ext_irec_t	*erp;		/* indirection array pointer */
	int		erp_idx = 0;	/* indirection array index */
	xfs_extnum_t	ext_cnt;	/* extents left to remove */
	xfs_extnum_t	ext_diff;	/* extents to remove in current list */
	xfs_extnum_t	nex1;		/* number of extents before idx */
	xfs_extnum_t	nex2;		/* extents after idx + count */
	int		nlists;		/* entries in indirection array */
	int		page_idx = idx;	/* index in target extent list */

	ASSERT(ifp->if_flags & XFS_IFEXTIREC);
	erp = xfs_iext_idx_to_irec(ifp,  &page_idx, &erp_idx, 0);
	ASSERT(erp != NULL);
	nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
	nex1 = page_idx;
	ext_cnt = count;
	while (ext_cnt) {
		nex2 = MAX((erp->er_extcount - (nex1 + ext_cnt)), 0);
		ext_diff = MIN(ext_cnt, (erp->er_extcount - nex1));
		/*
		 * Check for deletion of entire list;
		 * xfs_iext_irec_remove() updates extent offsets.
		 */
		if (ext_diff == erp->er_extcount) {
			xfs_iext_irec_remove(ifp, erp_idx);
			ext_cnt -= ext_diff;
			nex1 = 0;
			if (ext_cnt) {
				ASSERT(erp_idx < ifp->if_real_bytes /
					XFS_IEXT_BUFSZ);
				erp = &ifp->if_u1.if_ext_irec[erp_idx];
				nex1 = 0;
				continue;
			} else {
				break;
			}
		}
		/* Move extents up (if needed) */
		if (nex2) {
			memmove(&erp->er_extbuf[nex1],
				&erp->er_extbuf[nex1 + ext_diff],
				nex2 * sizeof(xfs_bmbt_rec_t));
		}
		/* Zero out rest of page */
		memset(&erp->er_extbuf[nex1 + nex2], 0, (XFS_IEXT_BUFSZ -
			((nex1 + nex2) * sizeof(xfs_bmbt_rec_t))));
		/* Update remaining counters */
		erp->er_extcount -= ext_diff;
		xfs_iext_irec_update_extoffs(ifp, erp_idx + 1, -ext_diff);
		ext_cnt -= ext_diff;
		nex1 = 0;
		erp_idx++;
		erp++;
	}
	ifp->if_bytes -= count * sizeof(xfs_bmbt_rec_t);
	xfs_iext_irec_compact(ifp);
}

/*
 * Create, destroy, or resize a linear (direct) block of extents.
 */
void
xfs_iext_realloc_direct(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	int		new_size)	/* new size of extents */
{
	int		rnew_size;	/* real new size of extents */

	rnew_size = new_size;

	ASSERT(!(ifp->if_flags & XFS_IFEXTIREC) ||
		((new_size >= 0) && (new_size <= XFS_IEXT_BUFSZ) &&
		 (new_size != ifp->if_real_bytes)));

	/* Free extent records */
	if (new_size == 0) {
		xfs_iext_destroy(ifp);
	}
	/* Resize direct extent list and zero any new bytes */
	else if (ifp->if_real_bytes) {
		/* Check if extents will fit inside the inode */
		if (new_size <= XFS_INLINE_EXTS * sizeof(xfs_bmbt_rec_t)) {
			xfs_iext_direct_to_inline(ifp, new_size /
				(uint)sizeof(xfs_bmbt_rec_t));
			ifp->if_bytes = new_size;
			return;
		}
		if (!is_power_of_2(new_size)){
			rnew_size = roundup_pow_of_two(new_size);
		}
		if (rnew_size != ifp->if_real_bytes) {
			ifp->if_u1.if_extents =
				kmem_realloc(ifp->if_u1.if_extents,
						rnew_size,
						ifp->if_real_bytes,
						KM_SLEEP);
		}
		if (rnew_size > ifp->if_real_bytes) {
			memset(&ifp->if_u1.if_extents[ifp->if_bytes /
				(uint)sizeof(xfs_bmbt_rec_t)], 0,
				rnew_size - ifp->if_real_bytes);
		}
	}
	/*
	 * Switch from the inline extent buffer to a direct
	 * extent list. Be sure to include the inline extent
	 * bytes in new_size.
	 */
	else {
		new_size += ifp->if_bytes;
		if (!is_power_of_2(new_size)) {
			rnew_size = roundup_pow_of_two(new_size);
		}
		xfs_iext_inline_to_direct(ifp, rnew_size);
	}
	ifp->if_real_bytes = rnew_size;
	ifp->if_bytes = new_size;
}

/*
 * Switch from linear (direct) extent records to inline buffer.
 */
void
xfs_iext_direct_to_inline(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	xfs_extnum_t	nextents)	/* number of extents in file */
{
	ASSERT(ifp->if_flags & XFS_IFEXTENTS);
	ASSERT(nextents <= XFS_INLINE_EXTS);
	/*
	 * The inline buffer was zeroed when we switched
	 * from inline to direct extent allocation mode,
	 * so we don't need to clear it here.
	 */
	memcpy(ifp->if_u2.if_inline_ext, ifp->if_u1.if_extents,
		nextents * sizeof(xfs_bmbt_rec_t));
	kmem_free(ifp->if_u1.if_extents, ifp->if_real_bytes);
	ifp->if_u1.if_extents = ifp->if_u2.if_inline_ext;
	ifp->if_real_bytes = 0;
}

/*
 * Switch from inline buffer to linear (direct) extent records.
 * new_size should already be rounded up to the next power of 2
 * by the caller (when appropriate), so use new_size as it is.
 * However, since new_size may be rounded up, we can't update
 * if_bytes here. It is the caller's responsibility to update
 * if_bytes upon return.
 */
void
xfs_iext_inline_to_direct(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	int		new_size)	/* number of extents in file */
{
	ifp->if_u1.if_extents = kmem_alloc(new_size, KM_SLEEP);
	memset(ifp->if_u1.if_extents, 0, new_size);
	if (ifp->if_bytes) {
		memcpy(ifp->if_u1.if_extents, ifp->if_u2.if_inline_ext,
			ifp->if_bytes);
		memset(ifp->if_u2.if_inline_ext, 0, XFS_INLINE_EXTS *
			sizeof(xfs_bmbt_rec_t));
	}
	ifp->if_real_bytes = new_size;
}

/*
 * Resize an extent indirection array to new_size bytes.
 */
void
xfs_iext_realloc_indirect(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	int		new_size)	/* new indirection array size */
{
	int		nlists;		/* number of irec's (ex lists) */
	int		size;		/* current indirection array size */

	ASSERT(ifp->if_flags & XFS_IFEXTIREC);
	nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
	size = nlists * sizeof(xfs_ext_irec_t);
	ASSERT(ifp->if_real_bytes);
	ASSERT((new_size >= 0) && (new_size != size));
	if (new_size == 0) {
		xfs_iext_destroy(ifp);
	} else {
		ifp->if_u1.if_ext_irec = (xfs_ext_irec_t *)
			kmem_realloc(ifp->if_u1.if_ext_irec,
				new_size, size, KM_SLEEP);
	}
}

/*
 * Switch from indirection array to linear (direct) extent allocations.
 */
void
xfs_iext_indirect_to_direct(
	 xfs_ifork_t	*ifp)		/* inode fork pointer */
{
	xfs_bmbt_rec_host_t *ep;	/* extent record pointer */
	xfs_extnum_t	nextents;	/* number of extents in file */
	int		size;		/* size of file extents */

	ASSERT(ifp->if_flags & XFS_IFEXTIREC);
	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
	ASSERT(nextents <= XFS_LINEAR_EXTS);
	size = nextents * sizeof(xfs_bmbt_rec_t);

	xfs_iext_irec_compact_full(ifp);
	ASSERT(ifp->if_real_bytes == XFS_IEXT_BUFSZ);

	ep = ifp->if_u1.if_ext_irec->er_extbuf;
	kmem_free(ifp->if_u1.if_ext_irec, sizeof(xfs_ext_irec_t));
	ifp->if_flags &= ~XFS_IFEXTIREC;
	ifp->if_u1.if_extents = ep;
	ifp->if_bytes = size;
	if (nextents < XFS_LINEAR_EXTS) {
		xfs_iext_realloc_direct(ifp, size);
	}
}

/*
 * Free incore file extents.
 */
void
xfs_iext_destroy(
	xfs_ifork_t	*ifp)		/* inode fork pointer */
{
	if (ifp->if_flags & XFS_IFEXTIREC) {
		int	erp_idx;
		int	nlists;

		nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
		for (erp_idx = nlists - 1; erp_idx >= 0 ; erp_idx--) {
			xfs_iext_irec_remove(ifp, erp_idx);
		}
		ifp->if_flags &= ~XFS_IFEXTIREC;
	} else if (ifp->if_real_bytes) {
		kmem_free(ifp->if_u1.if_extents, ifp->if_real_bytes);
	} else if (ifp->if_bytes) {
		memset(ifp->if_u2.if_inline_ext, 0, XFS_INLINE_EXTS *
			sizeof(xfs_bmbt_rec_t));
	}
	ifp->if_u1.if_extents = NULL;
	ifp->if_real_bytes = 0;
	ifp->if_bytes = 0;
}

/*
 * Return a pointer to the extent record for file system block bno.
 */
xfs_bmbt_rec_host_t *			/* pointer to found extent record */
xfs_iext_bno_to_ext(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	xfs_fileoff_t	bno,		/* block number to search for */
	xfs_extnum_t	*idxp)		/* index of target extent */
{
	xfs_bmbt_rec_host_t *base;	/* pointer to first extent */
	xfs_filblks_t	blockcount = 0;	/* number of blocks in extent */
	xfs_bmbt_rec_host_t *ep = NULL;	/* pointer to target extent */
	xfs_ext_irec_t	*erp = NULL;	/* indirection array pointer */
	int		high;		/* upper boundary in search */
	xfs_extnum_t	idx = 0;	/* index of target extent */
	int		low;		/* lower boundary in search */
	xfs_extnum_t	nextents;	/* number of file extents */
	xfs_fileoff_t	startoff = 0;	/* start offset of extent */

	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
	if (nextents == 0) {
		*idxp = 0;
		return NULL;
	}
	low = 0;
	if (ifp->if_flags & XFS_IFEXTIREC) {
		/* Find target extent list */
		int	erp_idx = 0;
		erp = xfs_iext_bno_to_irec(ifp, bno, &erp_idx);
		base = erp->er_extbuf;
		high = erp->er_extcount - 1;
	} else {
		base = ifp->if_u1.if_extents;
		high = nextents - 1;
	}
	/* Binary search extent records */
	while (low <= high) {
		idx = (low + high) >> 1;
		ep = base + idx;
		startoff = xfs_bmbt_get_startoff(ep);
		blockcount = xfs_bmbt_get_blockcount(ep);
		if (bno < startoff) {
			high = idx - 1;
		} else if (bno >= startoff + blockcount) {
			low = idx + 1;
		} else {
			/* Convert back to file-based extent index */
			if (ifp->if_flags & XFS_IFEXTIREC) {
				idx += erp->er_extoff;
			}
			*idxp = idx;
			return ep;
		}
	}
	/* Convert back to file-based extent index */
	if (ifp->if_flags & XFS_IFEXTIREC) {
		idx += erp->er_extoff;
	}
	if (bno >= startoff + blockcount) {
		if (++idx == nextents) {
			ep = NULL;
		} else {
			ep = xfs_iext_get_ext(ifp, idx);
		}
	}
	*idxp = idx;
	return ep;
}

/*
 * Return a pointer to the indirection array entry containing the
 * extent record for filesystem block bno. Store the index of the
 * target irec in *erp_idxp.
 */
xfs_ext_irec_t *			/* pointer to found extent record */
xfs_iext_bno_to_irec(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	xfs_fileoff_t	bno,		/* block number to search for */
	int		*erp_idxp)	/* irec index of target ext list */
{
	xfs_ext_irec_t	*erp = NULL;	/* indirection array pointer */
	xfs_ext_irec_t	*erp_next;	/* next indirection array entry */
	int		erp_idx;	/* indirection array index */
	int		nlists;		/* number of extent irec's (lists) */
	int		high;		/* binary search upper limit */
	int		low;		/* binary search lower limit */

	ASSERT(ifp->if_flags & XFS_IFEXTIREC);
	nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
	erp_idx = 0;
	low = 0;
	high = nlists - 1;
	while (low <= high) {
		erp_idx = (low + high) >> 1;
		erp = &ifp->if_u1.if_ext_irec[erp_idx];
		erp_next = erp_idx < nlists - 1 ? erp + 1 : NULL;
		if (bno < xfs_bmbt_get_startoff(erp->er_extbuf)) {
			high = erp_idx - 1;
		} else if (erp_next && bno >=
			   xfs_bmbt_get_startoff(erp_next->er_extbuf)) {
			low = erp_idx + 1;
		} else {
			break;
		}
	}
	*erp_idxp = erp_idx;
	return erp;
}

/*
 * Return a pointer to the indirection array entry containing the
 * extent record at file extent index *idxp. Store the index of the
 * target irec in *erp_idxp and store the page index of the target
 * extent record in *idxp.
 */
xfs_ext_irec_t *
xfs_iext_idx_to_irec(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	xfs_extnum_t	*idxp,		/* extent index (file -> page) */
	int		*erp_idxp,	/* pointer to target irec */
	int		realloc)	/* new bytes were just added */
{
	xfs_ext_irec_t	*prev;		/* pointer to previous irec */
	xfs_ext_irec_t	*erp = NULL;	/* pointer to current irec */
	int		erp_idx;	/* indirection array index */
	int		nlists;		/* number of irec's (ex lists) */
	int		high;		/* binary search upper limit */
	int		low;		/* binary search lower limit */
	xfs_extnum_t	page_idx = *idxp; /* extent index in target list */

	ASSERT(ifp->if_flags & XFS_IFEXTIREC);
	ASSERT(page_idx >= 0 && page_idx <=
		ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t));
	nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
	erp_idx = 0;
	low = 0;
	high = nlists - 1;

	/* Binary search extent irec's */
	while (low <= high) {
		erp_idx = (low + high) >> 1;
		erp = &ifp->if_u1.if_ext_irec[erp_idx];
		prev = erp_idx > 0 ? erp - 1 : NULL;
		if (page_idx < erp->er_extoff || (page_idx == erp->er_extoff &&
		     realloc && prev && prev->er_extcount < XFS_LINEAR_EXTS)) {
			high = erp_idx - 1;
		} else if (page_idx > erp->er_extoff + erp->er_extcount ||
			   (page_idx == erp->er_extoff + erp->er_extcount &&
			    !realloc)) {
			low = erp_idx + 1;
		} else if (page_idx == erp->er_extoff + erp->er_extcount &&
			   erp->er_extcount == XFS_LINEAR_EXTS) {
			ASSERT(realloc);
			page_idx = 0;
			erp_idx++;
			erp = erp_idx < nlists ? erp + 1 : NULL;
			break;
		} else {
			page_idx -= erp->er_extoff;
			break;
		}
	}
	*idxp = page_idx;
	*erp_idxp = erp_idx;
	return(erp);
}

/*
 * Allocate and initialize an indirection array once the space needed
 * for incore extents increases above XFS_IEXT_BUFSZ.
 */
void
xfs_iext_irec_init(
	xfs_ifork_t	*ifp)		/* inode fork pointer */
{
	xfs_ext_irec_t	*erp;		/* indirection array pointer */
	xfs_extnum_t	nextents;	/* number of extents in file */

	ASSERT(!(ifp->if_flags & XFS_IFEXTIREC));
	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
	ASSERT(nextents <= XFS_LINEAR_EXTS);

	erp = (xfs_ext_irec_t *)
		kmem_alloc(sizeof(xfs_ext_irec_t), KM_SLEEP);

	if (nextents == 0) {
		ifp->if_u1.if_extents = kmem_alloc(XFS_IEXT_BUFSZ, KM_SLEEP);
	} else if (!ifp->if_real_bytes) {
		xfs_iext_inline_to_direct(ifp, XFS_IEXT_BUFSZ);
	} else if (ifp->if_real_bytes < XFS_IEXT_BUFSZ) {
		xfs_iext_realloc_direct(ifp, XFS_IEXT_BUFSZ);
	}
	erp->er_extbuf = ifp->if_u1.if_extents;
	erp->er_extcount = nextents;
	erp->er_extoff = 0;

	ifp->if_flags |= XFS_IFEXTIREC;
	ifp->if_real_bytes = XFS_IEXT_BUFSZ;
	ifp->if_bytes = nextents * sizeof(xfs_bmbt_rec_t);
	ifp->if_u1.if_ext_irec = erp;

	return;
}

/*
 * Allocate and initialize a new entry in the indirection array.
 */
xfs_ext_irec_t *
xfs_iext_irec_new(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	int		erp_idx)	/* index for new irec */
{
	xfs_ext_irec_t	*erp;		/* indirection array pointer */
	int		i;		/* loop counter */
	int		nlists;		/* number of irec's (ex lists) */

	ASSERT(ifp->if_flags & XFS_IFEXTIREC);
	nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;

	/* Resize indirection array */
	xfs_iext_realloc_indirect(ifp, ++nlists *
				  sizeof(xfs_ext_irec_t));
	/*
	 * Move records down in the array so the
	 * new page can use erp_idx.
	 */
	erp = ifp->if_u1.if_ext_irec;
	for (i = nlists - 1; i > erp_idx; i--) {
		memmove(&erp[i], &erp[i-1], sizeof(xfs_ext_irec_t));
	}
	ASSERT(i == erp_idx);

	/* Initialize new extent record */
	erp = ifp->if_u1.if_ext_irec;
	erp[erp_idx].er_extbuf = kmem_alloc(XFS_IEXT_BUFSZ, KM_SLEEP);
	ifp->if_real_bytes = nlists * XFS_IEXT_BUFSZ;
	memset(erp[erp_idx].er_extbuf, 0, XFS_IEXT_BUFSZ);
	erp[erp_idx].er_extcount = 0;
	erp[erp_idx].er_extoff = erp_idx > 0 ?
		erp[erp_idx-1].er_extoff + erp[erp_idx-1].er_extcount : 0;
	return (&erp[erp_idx]);
}

/*
 * Remove a record from the indirection array.
 */
void
xfs_iext_irec_remove(
	xfs_ifork_t	*ifp,		/* inode fork pointer */
	int		erp_idx)	/* irec index to remove */
{
	xfs_ext_irec_t	*erp;		/* indirection array pointer */
	int		i;		/* loop counter */
	int		nlists;		/* number of irec's (ex lists) */

	ASSERT(ifp->if_flags & XFS_IFEXTIREC);
	nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
	erp = &ifp->if_u1.if_ext_irec[erp_idx];