Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 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 | /* * kernel/lvm.c * * Copyright (C) 1997 - 2000 Heinz Mauelshagen, Sistina Software * * February-November 1997 * April-May,July-August,November 1998 * January-March,May,July,September,October 1999 * January,February,July,September-November 2000 * January 2001 * * * LVM driver is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2, or (at your option) * any later version. * * LVM driver 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 GNU CC; see the file COPYING. If not, write to * the Free Software Foundation, 59 Temple Place - Suite 330, * Boston, MA 02111-1307, USA. * */ /* * Changelog * * 09/11/1997 - added chr ioctls VG_STATUS_GET_COUNT * and VG_STATUS_GET_NAMELIST * 18/01/1998 - change lvm_chr_open/close lock handling * 30/04/1998 - changed LV_STATUS ioctl to LV_STATUS_BYNAME and * - added LV_STATUS_BYINDEX ioctl * - used lvm_status_byname_req_t and * lvm_status_byindex_req_t vars * 04/05/1998 - added multiple device support * 08/05/1998 - added support to set/clear extendable flag in volume group * 09/05/1998 - changed output of lvm_proc_get_global_info() because of * support for free (eg. longer) logical volume names * 12/05/1998 - added spin_locks (thanks to Pascal van Dam * <pascal@ramoth.xs4all.nl>) * 25/05/1998 - fixed handling of locked PEs in lvm_map() and lvm_chr_ioctl() * 26/05/1998 - reactivated verify_area by access_ok * 07/06/1998 - used vmalloc/vfree instead of kmalloc/kfree to go * beyond 128/256 KB max allocation limit per call * - #ifdef blocked spin_lock calls to avoid compile errors * with 2.0.x * 11/06/1998 - another enhancement to spinlock code in lvm_chr_open() * and use of LVM_VERSION_CODE instead of my own macros * (thanks to Michael Marxmeier <mike@msede.com>) * 07/07/1998 - added statistics in lvm_map() * 08/07/1998 - saved statistics in lvm_do_lv_extend_reduce() * 25/07/1998 - used __initfunc macro * 02/08/1998 - changes for official char/block major numbers * 07/08/1998 - avoided init_module() and cleanup_module() to be static * 30/08/1998 - changed VG lv_open counter from sum of LV lv_open counters * to sum of LVs open (no matter how often each is) * 01/09/1998 - fixed lvm_gendisk.part[] index error * 07/09/1998 - added copying of lv_current_pe-array * in LV_STATUS_BYINDEX ioctl * 17/11/1998 - added KERN_* levels to printk * 13/01/1999 - fixed LV index bug in lvm_do_lv_create() which hit lvrename * 07/02/1999 - fixed spinlock handling bug in case of LVM_RESET * by moving spinlock code from lvm_chr_open() * to lvm_chr_ioctl() * - added LVM_LOCK_LVM ioctl to lvm_chr_ioctl() * - allowed LVM_RESET and retrieval commands to go ahead; * only other update ioctls are blocked now * - fixed pv->pe to NULL for pv_status * - using lv_req structure in lvm_chr_ioctl() now * - fixed NULL ptr reference bug in lvm_do_lv_extend_reduce() * caused by uncontiguous PV array in lvm_chr_ioctl(VG_REDUCE) * 09/02/1999 - changed BLKRASET and BLKRAGET in lvm_chr_ioctl() to * handle lgoical volume private read ahead sector * - implemented LV read_ahead handling with lvm_blk_read() * and lvm_blk_write() * 10/02/1999 - implemented 2.[12].* support function lvm_hd_name() * to be used in drivers/block/genhd.c by disk_name() * 12/02/1999 - fixed index bug in lvm_blk_ioctl(), HDIO_GETGEO * - enhanced gendisk insert/remove handling * 16/02/1999 - changed to dynamic block minor number allocation to * have as much as 99 volume groups with 256 logical volumes * as the grand total; this allows having 1 volume group with * up to 256 logical volumes in it * 21/02/1999 - added LV open count information to proc filesystem * - substituted redundant LVM_RESET code by calls * to lvm_do_vg_remove() * 22/02/1999 - used schedule_timeout() to be more responsive * in case of lvm_do_vg_remove() with lots of logical volumes * 19/03/1999 - fixed NULL pointer bug in module_init/lvm_init * 17/05/1999 - used DECLARE_WAIT_QUEUE_HEAD macro (>2.3.0) * - enhanced lvm_hd_name support * 03/07/1999 - avoided use of KERNEL_VERSION macro based ifdefs and * memcpy_tofs/memcpy_fromfs macro redefinitions * 06/07/1999 - corrected reads/writes statistic counter copy in case * of striped logical volume * 28/07/1999 - implemented snapshot logical volumes * - lvm_chr_ioctl * - LV_STATUS_BYINDEX * - LV_STATUS_BYNAME * - lvm_do_lv_create * - lvm_do_lv_remove * - lvm_map * - new lvm_snapshot_remap_block * - new lvm_snapshot_remap_new_block * 08/10/1999 - implemented support for multiple snapshots per * original logical volume * 12/10/1999 - support for 2.3.19 * 11/11/1999 - support for 2.3.28 * 21/11/1999 - changed lvm_map() interface to buffer_head based * 19/12/1999 - support for 2.3.33 * 01/01/2000 - changed locking concept in lvm_map(), * lvm_do_vg_create() and lvm_do_lv_remove() * 15/01/2000 - fixed PV_FLUSH bug in lvm_chr_ioctl() * 24/01/2000 - ported to 2.3.40 including Alan Cox's pointer changes etc. * 29/01/2000 - used kmalloc/kfree again for all small structures * 20/01/2000 - cleaned up lvm_chr_ioctl by moving code * to seperated functions * - avoided "/dev/" in proc filesystem output * - avoided inline strings functions lvm_strlen etc. * 14/02/2000 - support for 2.3.43 * - integrated Andrea Arcagneli's snapshot code * 25/06/2000 - james (chip) , IKKHAYD! roffl * 26/06/2000 - enhanced lv_extend_reduce for snapshot logical volume support * 06/09/2000 - added devfs support * 07/09/2000 - changed IOP version to 9 * - started to add new char ioctl LV_STATUS_BYDEV_T to support * getting an lv_t based on the dev_t of the Logical Volume * 14/09/2000 - enhanced lvm_do_lv_create to upcall VFS functions * to sync and lock, activate snapshot and unlock the FS * (to support journaled filesystems) * 18/09/2000 - hardsector size support * 27/09/2000 - implemented lvm_do_lv_rename() and lvm_do_vg_rename() * 30/10/2000 - added Andi Kleen's LV_BMAP ioctl to support LILO * 01/11/2000 - added memory information on hash tables to * lvm_proc_get_global_info() * 02/11/2000 - implemented /proc/lvm/ hierarchy * 22/11/2000 - changed lvm_do_create_proc_entry_of_pv () to work * with devfs * 26/11/2000 - corrected #ifdef locations for PROC_FS * 28/11/2000 - fixed lvm_do_vg_extend() NULL pointer BUG * - fixed lvm_do_create_proc_entry_of_pv() buffer tampering BUG * 08/01/2001 - Removed conditional compiles related to PROC_FS, * procfs is always supported now. (JT) * 12/01/2001 - avoided flushing logical volume in case of shrinking * because of unnecessary overhead in case of heavy updates * 25/01/2001 - Allow RO open of an inactive LV so it can be reactivated. * 31/01/2001 - If you try and BMAP a snapshot you now get an -EPERM * 01/02/2001 - factored __remap_snapshot out of lvm_map * 12/02/2001 - move devfs code to create VG before LVs * 14/02/2001 - tidied device defines for blk.h * - tidied debug statements * - more lvm_map tidying * 14/02/2001 - bug: vg[] member not set back to NULL if activation fails * 28/02/2001 - introduced the P_DEV macro and changed some internel * functions to be static [AD] * 28/02/2001 - factored lvm_get_snapshot_use_rate out of blk_ioctl [AD] * - fixed user address accessing bug in lvm_do_lv_create() * where the check for an existing LV takes place right at * the beginning * 01/03/2001 - Add VG_CREATE_OLD for IOP 10 compatibility * 02/03/2001 - Don't destroy usermode pointers in lv_t structures duing LV_ * STATUS_BYxxx and remove redundant lv_t variables from same. * 05/03/2001 - restore copying pe_t array in lvm_do_lv_status_byname. For * lvdisplay -v (PC) * - restore copying pe_t array in lvm_do_lv_status_byindex (HM) * - added copying pe_t array in lvm_do_lv_status_bydev (HM) * - enhanced lvm_do_lv_status_by{name,index,dev} to be capable * to copy the lv_block_exception_t array to userspace (HM) * 08/03/2001 - factored lvm_do_pv_flush out of lvm_chr_ioctl [HM] * 09/03/2001 - Added _lock_open_count to ensure we only drop the lock * when the locking process closes. * 05/04/2001 - lvm_map bugs: don't use b_blocknr/b_dev in lvm_map, it * destroys stacking devices. call b_end_io on failed maps. * (Jens Axboe) * - Defer writes to an extent that is being moved [JT + AD] * 28/05/2001 - implemented missing BLKSSZGET ioctl [AD] * 28/12/2001 - buffer_head -> bio * removed huge allocation of a lv_t on stack * (Anders Gustafsson) * */ #define MAJOR_NR LVM_BLK_MAJOR #define DEVICE_OFF(device) #define LOCAL_END_REQUEST /* lvm_do_lv_create calls fsync_dev_lockfs()/unlockfs() */ /* #define LVM_VFS_ENHANCEMENT */ #include <linux/config.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/hdreg.h> #include <linux/stat.h> #include <linux/fs.h> #include <linux/proc_fs.h> #include <linux/blkdev.h> #include <linux/genhd.h> #include <linux/locks.h> #include <linux/devfs_fs_kernel.h> #include <linux/smp_lock.h> #include <asm/ioctl.h> #include <asm/uaccess.h> #ifdef CONFIG_KERNELD #include <linux/kerneld.h> #endif #include <linux/blk.h> #include <linux/blkpg.h> #include <linux/errno.h> #include <linux/lvm.h> #include "lvm-internal.h" #define LVM_CORRECT_READ_AHEAD( a) \ if ( a < LVM_MIN_READ_AHEAD || \ a > LVM_MAX_READ_AHEAD) a = LVM_MAX_READ_AHEAD; #ifndef WRITEA # define WRITEA WRITE #endif /* * External function prototypes */ static int lvm_make_request_fn(request_queue_t*, struct bio *); static int lvm_blk_ioctl(struct inode *, struct file *, uint, ulong); static int lvm_blk_open(struct inode *, struct file *); static int lvm_blk_close(struct inode *, struct file *); static int lvm_get_snapshot_use_rate(lv_t *lv_ptr, void *arg); static int lvm_user_bmap(struct inode *, struct lv_bmap *); static int lvm_chr_open(struct inode *, struct file *); static int lvm_chr_close(struct inode *, struct file *); static int lvm_chr_ioctl(struct inode *, struct file *, uint, ulong); /* End external function prototypes */ /* * Internal function prototypes */ static void lvm_cleanup(void); static void lvm_init_vars(void); #ifdef LVM_HD_NAME extern void (*lvm_hd_name_ptr) (char *, int); #endif static int lvm_map(struct bio *); static int lvm_do_lock_lvm(void); static int lvm_do_le_remap(vg_t *, void *); static int lvm_do_pv_create(pv_t *, vg_t *, ulong); static int lvm_do_pv_remove(vg_t *, ulong); static int lvm_do_lv_create(int, char *, lv_t *); static int lvm_do_lv_extend_reduce(int, char *, lv_t *); static int lvm_do_lv_remove(int, char *, int); static int lvm_do_lv_rename(vg_t *, lv_req_t *, lv_t *); static int lvm_do_lv_status_byname(vg_t *r, void *); static int lvm_do_lv_status_byindex(vg_t *, void *); static int lvm_do_lv_status_bydev(vg_t *, void *); static int lvm_do_pe_lock_unlock(vg_t *r, void *); static int lvm_do_pv_change(vg_t*, void*); static int lvm_do_pv_status(vg_t *, void *); static int lvm_do_pv_flush(void *); static int lvm_do_vg_create(void *, int minor); static int lvm_do_vg_extend(vg_t *, void *); static int lvm_do_vg_reduce(vg_t *, void *); static int lvm_do_vg_rename(vg_t *, void *); static int lvm_do_vg_remove(int); static void lvm_geninit(struct gendisk *); static void __update_hardsectsize(lv_t *lv); static void _queue_io(struct bio *bh, int rw); static struct bio *_dequeue_io(void); static void _flush_io(struct bio *bh); static int _open_pv(pv_t *pv); static void _close_pv(pv_t *pv); static unsigned long _sectors_to_k(unsigned long sect); #ifdef LVM_HD_NAME void lvm_hd_name(char *, int); #endif /* END Internal function prototypes */ /* variables */ char *lvm_version = "LVM version "LVM_RELEASE_NAME"("LVM_RELEASE_DATE")"; ushort lvm_iop_version = LVM_DRIVER_IOP_VERSION; int loadtime = 0; const char *const lvm_name = LVM_NAME; /* volume group descriptor area pointers */ vg_t *vg[ABS_MAX_VG]; /* map from block minor number to VG and LV numbers */ typedef struct { int vg_number; int lv_number; } vg_lv_map_t; static vg_lv_map_t vg_lv_map[ABS_MAX_LV]; /* Request structures (lvm_chr_ioctl()) */ static pv_change_req_t pv_change_req; static pv_status_req_t pv_status_req; volatile static pe_lock_req_t pe_lock_req; static le_remap_req_t le_remap_req; static lv_req_t lv_req; #ifdef LVM_TOTAL_RESET static int lvm_reset_spindown = 0; #endif static char pv_name[NAME_LEN]; /* static char rootvg[NAME_LEN] = { 0, }; */ static int lock = 0; static int _lock_open_count = 0; static uint vg_count = 0; static long lvm_chr_open_count = 0; static DECLARE_WAIT_QUEUE_HEAD(lvm_wait); static spinlock_t lvm_lock = SPIN_LOCK_UNLOCKED; static spinlock_t lvm_snapshot_lock = SPIN_LOCK_UNLOCKED; static struct bio *_pe_requests; static DECLARE_RWSEM(_pe_lock); struct file_operations lvm_chr_fops = { open: lvm_chr_open, release: lvm_chr_close, ioctl: lvm_chr_ioctl, }; /* block device operations structure needed for 2.3.38? and above */ struct block_device_operations lvm_blk_dops = { owner: THIS_MODULE, open: lvm_blk_open, release: lvm_blk_close, ioctl: lvm_blk_ioctl, }; /* gendisk structures */ static struct hd_struct lvm_hd_struct[MAX_LV]; static int lvm_blocksizes[MAX_LV]; static int lvm_size[MAX_LV]; static struct gendisk lvm_gendisk = { major: MAJOR_NR, major_name: LVM_NAME, minor_shift: 0, part: lvm_hd_struct, sizes: lvm_size, nr_real: MAX_LV, }; /* * Driver initialization... */ int lvm_init(void) { if (devfs_register_chrdev(LVM_CHAR_MAJOR, lvm_name, &lvm_chr_fops) < 0) { printk(KERN_ERR "%s -- devfs_register_chrdev failed\n", lvm_name); return -EIO; } if (devfs_register_blkdev(MAJOR_NR, lvm_name, &lvm_blk_dops) < 0) { printk("%s -- devfs_register_blkdev failed\n", lvm_name); if (devfs_unregister_chrdev(LVM_CHAR_MAJOR, lvm_name) < 0) printk(KERN_ERR "%s -- devfs_unregister_chrdev failed\n", lvm_name); return -EIO; } lvm_init_fs(); lvm_init_vars(); lvm_geninit(&lvm_gendisk); add_gendisk(&lvm_gendisk); #ifdef LVM_HD_NAME /* reference from drivers/block/genhd.c */ lvm_hd_name_ptr = lvm_hd_name; #endif blk_queue_make_request(BLK_DEFAULT_QUEUE(MAJOR_NR), lvm_make_request_fn); /* initialise the pe lock */ pe_lock_req.lock = UNLOCK_PE; /* optional read root VGDA */ /* if ( *rootvg != 0) vg_read_with_pv_and_lv ( rootvg, &vg); */ #ifdef MODULE printk(KERN_INFO "%s module loaded\n", lvm_version); #else printk(KERN_INFO "%s\n", lvm_version); #endif return 0; } /* lvm_init() */ /* * cleanup... */ static void lvm_cleanup(void) { if (devfs_unregister_chrdev(LVM_CHAR_MAJOR, lvm_name) < 0) printk(KERN_ERR "%s -- devfs_unregister_chrdev failed\n", lvm_name); if (devfs_unregister_blkdev(MAJOR_NR, lvm_name) < 0) printk(KERN_ERR "%s -- devfs_unregister_blkdev failed\n", lvm_name); del_gendisk(&lvm_gendisk); blk_clear(MAJOR_NR); #ifdef LVM_HD_NAME /* reference from linux/drivers/block/genhd.c */ lvm_hd_name_ptr = NULL; #endif /* unregister with procfs and devfs */ lvm_fin_fs(); #ifdef MODULE printk(KERN_INFO "%s -- Module successfully deactivated\n", lvm_name); #endif return; } /* lvm_cleanup() */ /* * support function to initialize lvm variables */ static void __init lvm_init_vars(void) { int v; loadtime = CURRENT_TIME; lvm_lock = lvm_snapshot_lock = SPIN_LOCK_UNLOCKED; pe_lock_req.lock = UNLOCK_PE; pe_lock_req.data.lv_dev = NODEV; pe_lock_req.data.pv_dev = NODEV; pe_lock_req.data.pv_offset = 0; /* Initialize VG pointers */ for (v = 0; v < ABS_MAX_VG; v++) vg[v] = NULL; /* Initialize LV -> VG association */ for (v = 0; v < ABS_MAX_LV; v++) { /* index ABS_MAX_VG never used for real VG */ vg_lv_map[v].vg_number = ABS_MAX_VG; vg_lv_map[v].lv_number = -1; } return; } /* lvm_init_vars() */ /******************************************************************** * * Character device functions * ********************************************************************/ #define MODE_TO_STR(mode) (mode) & FMODE_READ ? "READ" : "", \ (mode) & FMODE_WRITE ? "WRITE" : "" /* * character device open routine */ static int lvm_chr_open(struct inode *inode, struct file *file) { unsigned int minor = minor(inode->i_rdev); P_DEV("chr_open MINOR: %d VG#: %d mode: %s%s lock: %d\n", minor, VG_CHR(minor), MODE_TO_STR(file->f_mode), lock); /* super user validation */ if (!capable(CAP_SYS_ADMIN)) return -EACCES; /* Group special file open */ if (VG_CHR(minor) > MAX_VG) return -ENXIO; spin_lock(&lvm_lock); if(lock == current->pid) _lock_open_count++; spin_unlock(&lvm_lock); lvm_chr_open_count++; MOD_INC_USE_COUNT; return 0; } /* lvm_chr_open() */ /* * character device i/o-control routine * * Only one changing process can do changing ioctl at one time, * others will block. * */ static int lvm_chr_ioctl(struct inode *inode, struct file *file, uint command, ulong a) { int minor = minor(inode->i_rdev); uint extendable, l, v; void *arg = (void *) a; lv_t lv; vg_t* vg_ptr = vg[VG_CHR(minor)]; /* otherwise cc will complain about unused variables */ (void) lvm_lock; P_IOCTL("chr MINOR: %d command: 0x%X arg: %p VG#: %d mode: %s%s\n", minor, command, arg, VG_CHR(minor), MODE_TO_STR(file->f_mode)); #ifdef LVM_TOTAL_RESET if (lvm_reset_spindown > 0) return -EACCES; #endif /* Main command switch */ switch (command) { case LVM_LOCK_LVM: /* lock the LVM */ return lvm_do_lock_lvm(); case LVM_GET_IOP_VERSION: /* check lvm version to ensure driver/tools+lib interoperability */ if (copy_to_user(arg, &lvm_iop_version, sizeof(ushort)) != 0) return -EFAULT; return 0; #ifdef LVM_TOTAL_RESET case LVM_RESET: /* lock reset function */ lvm_reset_spindown = 1; for (v = 0; v < ABS_MAX_VG; v++) { if (vg[v] != NULL) lvm_do_vg_remove(v); } #ifdef MODULE while (GET_USE_COUNT(&__this_module) < 1) MOD_INC_USE_COUNT; while (GET_USE_COUNT(&__this_module) > 1) MOD_DEC_USE_COUNT; #endif /* MODULE */ lock = 0; /* release lock */ wake_up_interruptible(&lvm_wait); return 0; #endif /* LVM_TOTAL_RESET */ case LE_REMAP: /* remap a logical extent (after moving the physical extent) */ return lvm_do_le_remap(vg_ptr,arg); case PE_LOCK_UNLOCK: /* lock/unlock i/o to a physical extent to move it to another physical volume (move's done in user space's pvmove) */ return lvm_do_pe_lock_unlock(vg_ptr,arg); case VG_CREATE_OLD: /* create a VGDA */ return lvm_do_vg_create(arg, minor); case VG_CREATE: /* create a VGDA, assume VG number is filled in */ return lvm_do_vg_create(arg, -1); case VG_EXTEND: /* extend a volume group */ return lvm_do_vg_extend(vg_ptr, arg); case VG_REDUCE: /* reduce a volume group */ return lvm_do_vg_reduce(vg_ptr, arg); case VG_RENAME: /* rename a volume group */ return lvm_do_vg_rename(vg_ptr, arg); case VG_REMOVE: /* remove an inactive VGDA */ return lvm_do_vg_remove(minor); case VG_SET_EXTENDABLE: /* set/clear extendability flag of volume group */ if (vg_ptr == NULL) return -ENXIO; if (copy_from_user(&extendable, arg, sizeof(extendable)) != 0) return -EFAULT; if (extendable == VG_EXTENDABLE || extendable == ~VG_EXTENDABLE) { if (extendable == VG_EXTENDABLE) vg_ptr->vg_status |= VG_EXTENDABLE; else vg_ptr->vg_status &= ~VG_EXTENDABLE; } else return -EINVAL; return 0; case VG_STATUS: /* get volume group data (only the vg_t struct) */ if (vg_ptr == NULL) return -ENXIO; if (copy_to_user(arg, vg_ptr, sizeof(vg_t)) != 0) return -EFAULT; return 0; case VG_STATUS_GET_COUNT: /* get volume group count */ if (copy_to_user(arg, &vg_count, sizeof(vg_count)) != 0) return -EFAULT; return 0; case VG_STATUS_GET_NAMELIST: /* get volume group names */ for (l = v = 0; v < ABS_MAX_VG; v++) { if (vg[v] != NULL) { if (copy_to_user(arg + l * NAME_LEN, vg[v]->vg_name, NAME_LEN) != 0) return -EFAULT; l++; } } return 0; case LV_CREATE: case LV_EXTEND: case LV_REDUCE: case LV_REMOVE: case LV_RENAME: /* create, extend, reduce, remove or rename a logical volume */ if (vg_ptr == NULL) return -ENXIO; if (copy_from_user(&lv_req, arg, sizeof(lv_req)) != 0) return -EFAULT; if (command != LV_REMOVE) { if (copy_from_user(&lv, lv_req.lv, sizeof(lv_t)) != 0) return -EFAULT; } switch (command) { case LV_CREATE: return lvm_do_lv_create(minor, lv_req.lv_name, &lv); case LV_EXTEND: case LV_REDUCE: return lvm_do_lv_extend_reduce(minor, lv_req.lv_name, &lv); case LV_REMOVE: return lvm_do_lv_remove(minor, lv_req.lv_name, -1); case LV_RENAME: return lvm_do_lv_rename(vg_ptr, &lv_req, &lv); } case LV_STATUS_BYNAME: /* get status of a logical volume by name */ return lvm_do_lv_status_byname(vg_ptr, arg); case LV_STATUS_BYINDEX: /* get status of a logical volume by index */ return lvm_do_lv_status_byindex(vg_ptr, arg); case LV_STATUS_BYDEV: /* get status of a logical volume by device */ return lvm_do_lv_status_bydev(vg_ptr, arg); case PV_CHANGE: /* change a physical volume */ return lvm_do_pv_change(vg_ptr,arg); case PV_STATUS: /* get physical volume data (pv_t structure only) */ return lvm_do_pv_status(vg_ptr,arg); case PV_FLUSH: /* physical volume buffer flush/invalidate */ return lvm_do_pv_flush(arg); default: printk(KERN_WARNING "%s -- lvm_chr_ioctl: unknown command 0x%x\n", lvm_name, command); return -EINVAL; } return 0; } /* lvm_chr_ioctl */ /* * character device close routine */ static int lvm_chr_close(struct inode *inode, struct file *file) { P_DEV("chr_close MINOR: %d VG#: %d\n", minor(inode->i_rdev), VG_CHR(minor(inode->i_rdev))); #ifdef LVM_TOTAL_RESET if (lvm_reset_spindown > 0) { lvm_reset_spindown = 0; lvm_chr_open_count = 0; } #endif if (lvm_chr_open_count > 0) lvm_chr_open_count--; spin_lock(&lvm_lock); if(lock == current->pid) { if(!_lock_open_count) { P_DEV("chr_close: unlocking LVM for pid %d\n", lock); lock = 0; wake_up_interruptible(&lvm_wait); } else _lock_open_count--; } spin_unlock(&lvm_lock); MOD_DEC_USE_COUNT; return 0; } /* lvm_chr_close() */ /******************************************************************** * * Block device functions * ********************************************************************/ /* * block device open routine */ static int lvm_blk_open(struct inode *inode, struct file *file) { int minor = minor(inode->i_rdev); lv_t *lv_ptr; vg_t *vg_ptr = vg[VG_BLK(minor)]; P_DEV("blk_open MINOR: %d VG#: %d LV#: %d mode: %s%s\n", minor, VG_BLK(minor), LV_BLK(minor), MODE_TO_STR(file->f_mode)); #ifdef LVM_TOTAL_RESET if (lvm_reset_spindown > 0) return -EPERM; #endif if (vg_ptr != NULL && (vg_ptr->vg_status & VG_ACTIVE) && (lv_ptr = vg_ptr->lv[LV_BLK(minor)]) != NULL && LV_BLK(minor) >= 0 && LV_BLK(minor) < vg_ptr->lv_max) { /* Check parallel LV spindown (LV remove) */ if (lv_ptr->lv_status & LV_SPINDOWN) return -EPERM; /* Check inactive LV and open for read/write */ /* We need to be able to "read" an inactive LV to re-activate it again */ if ((file->f_mode & FMODE_WRITE) && (!(lv_ptr->lv_status & LV_ACTIVE))) return -EPERM; if (!(lv_ptr->lv_access & LV_WRITE) && (file->f_mode & FMODE_WRITE)) return -EACCES; /* be sure to increment VG counter */ if (lv_ptr->lv_open == 0) vg_ptr->lv_open++; lv_ptr->lv_open++; MOD_INC_USE_COUNT; P_DEV("blk_open OK, LV size %d\n", lv_ptr->lv_size); return 0; } return -ENXIO; } /* lvm_blk_open() */ /* * block device i/o-control routine */ static int lvm_blk_ioctl(struct inode *inode, struct file *file, uint command, ulong a) { int minor = minor(inode->i_rdev); vg_t *vg_ptr = vg[VG_BLK(minor)]; lv_t *lv_ptr = vg_ptr->lv[LV_BLK(minor)]; void *arg = (void *) a; struct hd_geometry *hd = (struct hd_geometry *) a; P_IOCTL("blk MINOR: %d command: 0x%X arg: %p VG#: %d LV#: %d " "mode: %s%s\n", minor, command, arg, VG_BLK(minor), LV_BLK(minor), MODE_TO_STR(file->f_mode)); switch (command) { case BLKSSZGET: /* get block device sector size as needed e.g. by fdisk */ return put_user(get_hardsect_size(inode->i_rdev), (int *) arg); case BLKGETSIZE: /* return device size */ P_IOCTL("BLKGETSIZE: %u\n", lv_ptr->lv_size); if (put_user(lv_ptr->lv_size, (unsigned long *)arg)) return -EFAULT; break; case BLKGETSIZE64: if (put_user((u64)lv_ptr->lv_size << 9, (u64 *)arg)) return -EFAULT; break; case BLKFLSBUF: /* flush buffer cache */ if (!capable(CAP_SYS_ADMIN)) return -EACCES; P_IOCTL("BLKFLSBUF\n"); fsync_dev(inode->i_rdev); invalidate_buffers(inode->i_rdev); break; case BLKRASET: /* set read ahead for block device */ if (!capable(CAP_SYS_ADMIN)) return -EACCES; P_IOCTL("BLKRASET: %ld sectors for %s\n", (long) arg, kdevname(inode->i_rdev)); if ((long) arg < LVM_MIN_READ_AHEAD || (long) arg > LVM_MAX_READ_AHEAD) return -EINVAL; lv_ptr->lv_read_ahead = (long) arg; break; case BLKRAGET: /* get current read ahead setting */ P_IOCTL("BLKRAGET %d\n", lv_ptr->lv_read_ahead); if (put_user(lv_ptr->lv_read_ahead, (long *)arg)) return -EFAULT; break; case HDIO_GETGEO: /* get disk geometry */ P_IOCTL("%s -- lvm_blk_ioctl -- HDIO_GETGEO\n", lvm_name); if (hd == NULL) return -EINVAL; { unsigned char heads = 64; unsigned char sectors = 32; long start = 0; short cylinders = lv_ptr->lv_size / heads / sectors; if (copy_to_user((char *) &hd->heads, &heads, sizeof(heads)) != 0 || copy_to_user((char *) &hd->sectors, §ors, sizeof(sectors)) != 0 || copy_to_user((short *) &hd->cylinders, &cylinders, sizeof(cylinders)) != 0 || copy_to_user((long *) &hd->start, &start, sizeof(start)) != 0) return -EFAULT; P_IOCTL("%s -- lvm_blk_ioctl -- cylinders: %d\n", lvm_name, cylinders); } break; case LV_SET_ACCESS: /* set access flags of a logical volume */ if (!capable(CAP_SYS_ADMIN)) return -EACCES; lv_ptr->lv_access = (ulong) arg; if ( lv_ptr->lv_access & LV_WRITE) set_device_ro(lv_ptr->lv_dev, 0); else set_device_ro(lv_ptr->lv_dev, 1); break; case LV_SET_STATUS: /* set status flags of a logical volume */ if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (!((ulong) arg & LV_ACTIVE) && lv_ptr->lv_open > 1) return -EPERM; lv_ptr->lv_status = (ulong) arg; break; case LV_BMAP: /* turn logical block into (dev_t, block). non privileged. */ /* don't bmap a snapshot, since the mapping can change */ if(lv_ptr->lv_access & LV_SNAPSHOT) return -EPERM; return lvm_user_bmap(inode, (struct lv_bmap *) arg); case LV_SET_ALLOCATION: /* set allocation flags of a logical volume */ if (!capable(CAP_SYS_ADMIN)) return -EACCES; lv_ptr->lv_allocation = (ulong) arg; break; case LV_SNAPSHOT_USE_RATE: return lvm_get_snapshot_use_rate(lv_ptr, arg); default: printk(KERN_WARNING "%s -- lvm_blk_ioctl: unknown command 0x%x\n", lvm_name, command); return -EINVAL; } return 0; } /* lvm_blk_ioctl() */ /* * block device close routine */ static int lvm_blk_close(struct inode *inode, struct file *file) { int minor = minor(inode->i_rdev); vg_t *vg_ptr = vg[VG_BLK(minor)]; lv_t *lv_ptr = vg_ptr->lv[LV_BLK(minor)]; P_DEV("blk_close MINOR: %d VG#: %d LV#: %d\n", minor, VG_BLK(minor), LV_BLK(minor)); if (lv_ptr->lv_open == 1) vg_ptr->lv_open--; lv_ptr->lv_open--; MOD_DEC_USE_COUNT; return 0; } /* lvm_blk_close() */ static int lvm_get_snapshot_use_rate(lv_t *lv, void *arg) { lv_snapshot_use_rate_req_t lv_rate_req; if (!(lv->lv_access & LV_SNAPSHOT)) return -EPERM; if (copy_from_user(&lv_rate_req, arg, sizeof(lv_rate_req))) return -EFAULT; if (lv_rate_req.rate < 0 || lv_rate_req.rate > 100) return -EINVAL; switch (lv_rate_req.block) { case 0: lv->lv_snapshot_use_rate = lv_rate_req.rate; if (lv->lv_remap_ptr * 100 / lv->lv_remap_end < lv->lv_snapshot_use_rate) interruptible_sleep_on(&lv->lv_snapshot_wait); break; case O_NONBLOCK: break; default: return -EINVAL; } lv_rate_req.rate = lv->lv_remap_ptr * 100 / lv->lv_remap_end; return copy_to_user(arg, &lv_rate_req, sizeof(lv_rate_req)) ? -EFAULT : 0; } static int lvm_user_bmap(struct inode *inode, struct lv_bmap *user_result) { struct bio bio; unsigned long block; int err; if (get_user(block, &user_result->lv_block)) return -EFAULT; memset(&bio,0,sizeof(bio)); bio.bi_dev = inode->i_rdev; bio.bi_size = lvm_get_blksize(bio.bi_dev); /* NEEDED by bio_sectors */ bio.bi_sector = block * bio_sectors(&bio); bio.bi_rw = READ; if ((err=lvm_map(&bio)) < 0) { printk("lvm map failed: %d\n", err); return -EINVAL; } return put_user(kdev_t_to_nr(bio.bi_dev), &user_result->lv_dev) || put_user(bio.bi_sector/bio_sectors(&bio), &user_result->lv_block) ? -EFAULT : 0; } /* * block device support function for /usr/src/linux/drivers/block/ll_rw_blk.c * (see init_module/lvm_init) */ static void __remap_snapshot(kdev_t rdev, ulong rsector, ulong pe_start, lv_t *lv, vg_t *vg) { /* copy a chunk from the origin to a snapshot device */ down_write(&lv->lv_lock); /* we must redo lvm_snapshot_remap_block in order to avoid a race condition in the gap where no lock was held */ if (!lvm_snapshot_remap_block(&rdev, &rsector, pe_start, lv) && !lvm_snapshot_COW(rdev, rsector, pe_start, rsector, vg, lv)) lvm_write_COW_table_block(vg, lv); up_write(&lv->lv_lock); } static inline void _remap_snapshot(kdev_t rdev, ulong rsector, ulong pe_start, lv_t *lv, vg_t *vg) { int r; /* check to see if this chunk is already in the snapshot */ down_read(&lv->lv_lock); r = lvm_snapshot_remap_block(&rdev, &rsector, pe_start, lv); up_read(&lv->lv_lock); if (!r) /* we haven't yet copied this block to the snapshot */ __remap_snapshot(rdev, rsector, pe_start, lv, vg); } /* * extents destined for a pe that is on the move should be deferred */ static inline int _should_defer(kdev_t pv, ulong sector, uint32_t pe_size) { return ((pe_lock_req.lock == LOCK_PE) && kdev_same(pv, pe_lock_req.data.pv_dev) && (sector >= pe_lock_req.data.pv_offset) && (sector < (pe_lock_req.data.pv_offset + pe_size))); } static inline int _defer_extent(struct bio *bh, int rw, kdev_t pv, ulong sector, uint32_t pe_size) { if (pe_lock_req.lock == LOCK_PE) { down_read(&_pe_lock); if (_should_defer(pv, sector, pe_size)) { up_read(&_pe_lock); down_write(&_pe_lock); if (_should_defer(pv, sector, pe_size)) _queue_io(bh, rw); up_write(&_pe_lock); return 1; } up_read(&_pe_lock); } return 0; } static int lvm_map(struct bio *bi) { int minor = minor(bi->bi_dev); ulong index; ulong pe_start; ulong size = bio_sectors(bi); ulong rsector_org = bi->bi_sector; ulong rsector_map; kdev_t rdev_map; vg_t *vg_this = vg[VG_BLK(minor)]; lv_t *lv = vg_this->lv[LV_BLK(minor)]; int rw = bio_rw(bi); down_read(&lv->lv_lock); if (!(lv->lv_status & LV_ACTIVE)) { printk(KERN_ALERT "%s - lvm_map: ll_rw_blk for inactive LV %s\n", lvm_name, lv->lv_name); goto bad; } if ((rw == WRITE || rw == WRITEA) && !(lv->lv_access & LV_WRITE)) { printk(KERN_CRIT "%s - lvm_map: ll_rw_blk write for readonly LV %s\n", lvm_name, lv->lv_name); goto bad; } P_MAP("%s - lvm_map minor: %d *rdev: %s *rsector: %lu size:%lu\n", lvm_name, minor, kdevname(bi->bi_dev), rsector_org, size); if (rsector_org + size > lv->lv_size) { printk(KERN_ALERT "%s - lvm_map access beyond end of device; *rsector: " "%lu or size: %lu wrong for minor: %2d\n", lvm_name, rsector_org, size, minor); goto bad; } if (lv->lv_stripes < 2) { /* linear mapping */ /* get the index */ index = rsector_org / vg_this->pe_size; pe_start = lv->lv_current_pe[index].pe; rsector_map = lv->lv_current_pe[index].pe + (rsector_org % vg_this->pe_size); rdev_map = lv->lv_current_pe[index].dev; P_MAP("lv_current_pe[%ld].pe: %d rdev: %s rsector:%ld\n", index, lv->lv_current_pe[index].pe, kdevname(rdev_map), rsector_map); } else { /* striped mapping */ ulong stripe_index; ulong stripe_length; stripe_length = vg_this->pe_size * lv->lv_stripes; stripe_index = (rsector_org % stripe_length) / lv->lv_stripesize; index = rsector_org / stripe_length + (stripe_index % lv->lv_stripes) * (lv->lv_allocated_le / lv->lv_stripes); pe_start = lv->lv_current_pe[index].pe; rsector_map = lv->lv_current_pe[index].pe + (rsector_org % stripe_length) - (stripe_index % lv->lv_stripes) * lv->lv_stripesize - stripe_index / lv->lv_stripes * (lv->lv_stripes - 1) * lv->lv_stripesize; rdev_map = lv->lv_current_pe[index].dev; P_MAP("lv_current_pe[%ld].pe: %d rdev: %s rsector:%ld\n" "stripe_length: %ld stripe_index: %ld\n", index, lv->lv_current_pe[index].pe, kdevname(rdev_map), rsector_map, stripe_length, stripe_index); } /* * Queue writes to physical extents on the move until move completes. * Don't get _pe_lock until there is a reasonable expectation that * we need to queue this request, because this is in the fast path. */ if (rw == WRITE || rw == WRITEA) { if(_defer_extent(bi, rw, rdev_map, rsector_map, vg_this->pe_size)) { up_read(&lv->lv_lock); return 0; } lv->lv_current_pe[index].writes++; /* statistic */ } else lv->lv_current_pe[index].reads++; /* statistic */ /* snapshot volume exception handling on physical device address base */ if (!(lv->lv_access & (LV_SNAPSHOT|LV_SNAPSHOT_ORG))) goto out; if (lv->lv_access & LV_SNAPSHOT) { /* remap snapshot */ if (lv->lv_block_exception) lvm_snapshot_remap_block(&rdev_map, &rsector_map, pe_start, lv); else goto bad; } else if (rw == WRITE || rw == WRITEA) { /* snapshot origin */ lv_t *snap; /* start with first snapshot and loop through all of them */ for (snap = lv->lv_snapshot_next; snap; snap = snap->lv_snapshot_next) { /* Check for inactive snapshot */ if (!(snap->lv_status & LV_ACTIVE)) continue; /* Serializes the COW with the accesses to the snapshot device */ _remap_snapshot(rdev_map, rsector_map, pe_start, snap, vg_this); } } out: bi->bi_dev = rdev_map; bi->bi_sector = rsector_map; up_read(&lv->lv_lock); return 1; bad: bio_io_error(bi); up_read(&lv->lv_lock); return -1; } /* lvm_map() */ /* * internal support functions */ #ifdef LVM_HD_NAME /* * generate "hard disk" name */ void lvm_hd_name(char *buf, int minor) { int len = 0; lv_t *lv_ptr; if (vg[VG_BLK(minor)] == NULL || (lv_ptr = vg[VG_BLK(minor)]->lv[LV_BLK(minor)]) == NULL) return; len = strlen(lv_ptr->lv_name) - 5; memcpy(buf, &lv_ptr->lv_name[5], len); buf[len] = 0; return; } #endif /* * make request function */ static int lvm_make_request_fn(request_queue_t *q, struct bio *bio) { return (lvm_map(bio) <= 0) ? 0 : 1; } /******************************************************************** * * Character device support functions * ********************************************************************/ /* * character device support function logical volume manager lock */ static int lvm_do_lock_lvm(void) { lock_try_again: spin_lock(&lvm_lock); if (lock != 0 && lock != current->pid) { P_DEV("lvm_do_lock_lvm: locked by pid %d ...\n", lock); spin_unlock(&lvm_lock); interruptible_sleep_on(&lvm_wait); if (current->sigpending != 0) return -EINTR; #ifdef LVM_TOTAL_RESET if (lvm_reset_spindown > 0) return -EACCES; #endif goto lock_try_again; } lock = current->pid; P_DEV("lvm_do_lock_lvm: locking LVM for pid %d\n", lock); spin_unlock(&lvm_lock); return 0; } /* lvm_do_lock_lvm */ /* * character device support function lock/unlock physical extend */ static int lvm_do_pe_lock_unlock(vg_t *vg_ptr, void *arg) { pe_lock_req_t new_lock; struct bio *bh; uint p; if (vg_ptr == NULL) return -ENXIO; if (copy_from_user(&new_lock, arg, sizeof(new_lock)) != 0) return -EFAULT; switch (new_lock.lock) { case LOCK_PE: for (p = 0; p < vg_ptr->pv_max; p++) { if (vg_ptr->pv[p] != NULL && kdev_same(new_lock.data.pv_dev, vg_ptr->pv[p]->pv_dev)) break; } if (p == vg_ptr->pv_max) return -ENXIO; /* * this sync releaves memory pressure to lessen the * likelyhood of pvmove being paged out - resulting in * deadlock. * * This method of doing a pvmove is broken */ fsync_dev(pe_lock_req.data.lv_dev); down_write(&_pe_lock); if (pe_lock_req.lock == LOCK_PE) { up_write(&_pe_lock); return -EBUSY; } /* Should we do to_kdev_t() on the pv_dev and lv_dev??? */ pe_lock_req.lock = LOCK_PE; pe_lock_req.data.lv_dev = new_lock.data.lv_dev; pe_lock_req.data.pv_dev = new_lock.data.pv_dev; pe_lock_req.data.pv_offset = new_lock.data.pv_offset; up_write(&_pe_lock); /* some requests may have got through since the fsync */ fsync_dev(pe_lock_req.data.pv_dev); break; case UNLOCK_PE: down_write(&_pe_lock); pe_lock_req.lock = UNLOCK_PE; pe_lock_req.data.lv_dev = NODEV; pe_lock_req.data.pv_dev = NODEV; pe_lock_req.data.pv_offset = 0; bh = _dequeue_io(); up_write(&_pe_lock); /* handle all deferred io for this PE */ _flush_io(bh); break; default: return -EINVAL; } return 0; } /* * character device support function logical extend remap */ static int lvm_do_le_remap(vg_t *vg_ptr, void *arg) { uint l, le; lv_t *lv_ptr; if (vg_ptr == NULL) return -ENXIO; if (copy_from_user(&le_remap_req, arg, sizeof(le_remap_req_t)) != 0) return -EFAULT; for (l = 0; l < vg_ptr->lv_max; l++) { lv_ptr = vg_ptr->lv[l]; if (lv_ptr != NULL && strcmp(lv_ptr->lv_name, le_remap_req.lv_name) == 0) { for (le = 0; le < lv_ptr->lv_allocated_le; le++) { if (kdev_same(lv_ptr->lv_current_pe[le].dev, le_remap_req.old_dev) && lv_ptr->lv_current_pe[le].pe == le_remap_req.old_pe) { lv_ptr->lv_current_pe[le].dev = le_remap_req.new_dev; lv_ptr->lv_current_pe[le].pe = le_remap_req.new_pe; __update_hardsectsize(lv_ptr); return 0; } } return -EINVAL; } } return -ENXIO; } /* lvm_do_le_remap() */ /* * character device support function VGDA create */ static int lvm_do_vg_create(void *arg, int minor) { int ret = 0; ulong l, ls = 0, p, size; vg_t *vg_ptr; lv_t **snap_lv_ptr; lv_t *tmplv; if ((vg_ptr = kmalloc(sizeof(vg_t),GFP_KERNEL)) == NULL) { printk(KERN_CRIT "%s -- VG_CREATE: kmalloc error VG at line %d\n", lvm_name, __LINE__); return -ENOMEM; } /* get the volume group structure */ if (copy_from_user(vg_ptr, arg, sizeof(vg_t)) != 0) { P_IOCTL("lvm_do_vg_create ERROR: copy VG ptr %p (%d bytes)\n", arg, sizeof(vg_t)); kfree(vg_ptr); return -EFAULT; } /* VG_CREATE now uses minor number in VG structure */ if (minor == -1) minor = vg_ptr->vg_number; /* Validate it */ if (vg[VG_CHR(minor)] != NULL) { P_IOCTL("lvm_do_vg_create ERROR: VG %d in use\n", minor); kfree(vg_ptr); return -EPERM; } /* we are not that active so far... */ vg_ptr->vg_status &= ~VG_ACTIVE; vg_ptr->pe_allocated = 0; if (vg_ptr->pv_max > ABS_MAX_PV) { printk(KERN_WARNING "%s -- Can't activate VG: ABS_MAX_PV too small\n", lvm_name); kfree(vg_ptr); return -EPERM; } if (vg_ptr->lv_max > ABS_MAX_LV) { printk(KERN_WARNING "%s -- Can't activate VG: ABS_MAX_LV too small for %u\n", lvm_name, vg_ptr->lv_max); kfree(vg_ptr); return -EPERM; } /* create devfs and procfs entries */ lvm_fs_create_vg(vg_ptr); vg[VG_CHR(minor)] = vg_ptr; /* get the physical volume structures */ vg_ptr->pv_act = vg_ptr->pv_cur = 0; for (p = 0; p < vg_ptr->pv_max; p++) { pv_t *pvp; /* user space address */ if ((pvp = vg_ptr->pv[p]) != NULL) { ret = lvm_do_pv_create(pvp, vg_ptr, p); if ( ret != 0) { lvm_do_vg_remove(minor); return ret; } } } size = vg_ptr->lv_max * sizeof(lv_t *); if ((snap_lv_ptr = vmalloc ( size)) == NULL) { printk(KERN_CRIT "%s -- VG_CREATE: vmalloc error snapshot LVs at line %d\n", lvm_name, __LINE__); lvm_do_vg_remove(minor); return -EFAULT; } memset(snap_lv_ptr, 0, size); if ((tmplv = kmalloc(sizeof(lv_t),GFP_KERNEL)) == NULL) { printk(KERN_CRIT "%s -- VG_CREATE: kmalloc error LV at line %d\n", lvm_name, __LINE__); vfree(snap_lv_ptr); return -ENOMEM; } /* get the logical volume structures */ vg_ptr->lv_cur = 0; for (l = 0; l < vg_ptr->lv_max; l++) { lv_t *lvp; /* user space address */ if ((lvp = vg_ptr->lv[l]) != NULL) { if (copy_from_user(tmplv, lvp, sizeof(lv_t)) != 0) { P_IOCTL("ERROR: copying LV ptr %p (%d bytes)\n", lvp, sizeof(lv_t)); lvm_do_vg_remove(minor); vfree(snap_lv_ptr); kfree(tmplv); return -EFAULT; } if ( tmplv->lv_access & LV_SNAPSHOT) { snap_lv_ptr[ls] = lvp; vg_ptr->lv[l] = NULL; ls++; continue; } vg_ptr->lv[l] = NULL; /* only create original logical volumes for now */ if (lvm_do_lv_create(minor, tmplv->lv_name, tmplv) != 0) { lvm_do_vg_remove(minor); vfree(snap_lv_ptr); kfree(tmplv); return -EFAULT; } } } /* Second path to correct snapshot logical volumes which are not in place during first path above */ for (l = 0; l < ls; l++) { lv_t *lvp = snap_lv_ptr[l]; if (copy_from_user(tmplv, lvp, sizeof(lv_t)) != 0) { lvm_do_vg_remove(minor); vfree(snap_lv_ptr); kfree(tmplv); return -EFAULT; } if (lvm_do_lv_create(minor, tmplv->lv_name, tmplv) != 0) { lvm_do_vg_remove(minor); vfree(snap_lv_ptr); kfree(tmplv); return -EFAULT; } } vfree(snap_lv_ptr); kfree(tmplv); vg_count++; MOD_INC_USE_COUNT; /* let's go active */ vg_ptr->vg_status |= VG_ACTIVE; return 0; } /* lvm_do_vg_create() */ /* * character device support function VGDA extend */ static int lvm_do_vg_extend(vg_t *vg_ptr, void *arg) { int ret = 0; uint p; pv_t *pv_ptr; if (vg_ptr == NULL) return -ENXIO; if (vg_ptr->pv_cur < vg_ptr->pv_max) { for (p = 0; p < vg_ptr->pv_max; p++) { if ( ( pv_ptr = vg_ptr->pv[p]) == NULL) { ret = lvm_do_pv_create(arg, vg_ptr, p); if ( ret != 0) return ret; pv_ptr = vg_ptr->pv[p]; vg_ptr->pe_total += pv_ptr->pe_total; return 0; } } } return -EPERM; } /* lvm_do_vg_extend() */ /* * character device support function VGDA reduce */ static int lvm_do_vg_reduce(vg_t *vg_ptr, void *arg) { uint p; pv_t *pv_ptr; if (vg_ptr == NULL) return -ENXIO; if (copy_from_user(pv_name, arg, sizeof(pv_name)) != 0) return -EFAULT; for (p = 0; p < vg_ptr->pv_max; p++) { pv_ptr = vg_ptr->pv[p]; if (pv_ptr != NULL && strcmp(pv_ptr->pv_name, pv_name) == 0) { if (pv_ptr->lv_cur > 0) return -EPERM; lvm_do_pv_remove(vg_ptr, p); /* Make PV pointer array contiguous */ for (; p < vg_ptr->pv_max - 1; p++) vg_ptr->pv[p] = vg_ptr->pv[p + 1]; vg_ptr->pv[p + 1] = NULL; return 0; } } return -ENXIO; } /* lvm_do_vg_reduce */ /* * character device support function VG rename */ static int lvm_do_vg_rename(vg_t *vg_ptr, void *arg) { int l = 0, p = 0, len = 0; char vg_name[NAME_LEN] = { 0,}; char lv_name[NAME_LEN] = { 0,}; char *ptr = NULL; lv_t *lv_ptr = NULL; pv_t *pv_ptr = NULL; if (vg_ptr == NULL) return -ENXIO; if (copy_from_user(vg_name, arg, sizeof(vg_name)) != 0) return -EFAULT; lvm_fs_remove_vg(vg_ptr); strncpy ( vg_ptr->vg_name, vg_name, sizeof ( vg_name)-1); for ( l = 0; l < vg_ptr->lv_max; l++) { if ((lv_ptr = vg_ptr->lv[l]) == NULL) continue; strncpy(lv_ptr->vg_name, vg_name, sizeof ( vg_name)); ptr = strrchr(lv_ptr->lv_name, '/'); if (ptr == NULL) ptr = lv_ptr->lv_name; strncpy(lv_name, ptr, sizeof ( lv_name)); len = sizeof(LVM_DIR_PREFIX); strcpy(lv_ptr->lv_name, LVM_DIR_PREFIX); strncat(lv_ptr->lv_name, vg_name, NAME_LEN - len); len += strlen ( vg_name); strncat(lv_ptr->lv_name, lv_name, NAME_LEN - len); } for ( p = 0; p < vg_ptr->pv_max; p++) { if ( (pv_ptr = vg_ptr->pv[p]) == NULL) continue; strncpy(pv_ptr->vg_name, vg_name, NAME_LEN); } lvm_fs_create_vg(vg_ptr); return 0; } /* lvm_do_vg_rename */ /* * character device support function VGDA remove */ static int lvm_do_vg_remove(int minor) { int i; vg_t *vg_ptr = vg[VG_CHR(minor)]; pv_t *pv_ptr; if (vg_ptr == NULL) return -ENXIO; #ifdef LVM_TOTAL_RESET if (vg_ptr->lv_open > 0 && lvm_reset_spindown == 0) #else if (vg_ptr->lv_open > 0) #endif return -EPERM; /* let's go inactive */ vg_ptr->vg_status &= ~VG_ACTIVE; /* remove from procfs and devfs */ lvm_fs_remove_vg(vg_ptr); /* free LVs */ /* first free snapshot logical volumes */ for (i = 0; i < vg_ptr->lv_max; i++) { if (vg_ptr->lv[i] != NULL && vg_ptr->lv[i]->lv_access & LV_SNAPSHOT) { lvm_do_lv_remove(minor, NULL, i); current->state = TASK_UNINTERRUPTIBLE; schedule_timeout(1); } } /* then free the rest of the LVs */ for (i = 0; i < vg_ptr->lv_max; i++) { if (vg_ptr->lv[i] != NULL) { lvm_do_lv_remove(minor, NULL, i); current->state = TASK_UNINTERRUPTIBLE; schedule_timeout(1); } } /* free PVs */ for (i = 0; i < vg_ptr->pv_max; i++) { if ((pv_ptr = vg_ptr->pv[i]) != NULL) { P_KFREE("%s -- kfree %d\n", lvm_name, __LINE__); lvm_do_pv_remove(vg_ptr, i); } } P_KFREE("%s -- kfree %d\n", lvm_name, __LINE__); kfree(vg_ptr); vg[VG_CHR(minor)] = NULL; vg_count--; MOD_DEC_USE_COUNT; return 0; } /* lvm_do_vg_remove() */ /* * character device support function physical volume create */ static int lvm_do_pv_create(pv_t *pvp, vg_t *vg_ptr, ulong p) { pv_t *pv; int err; pv = kmalloc(sizeof(pv_t),GFP_KERNEL); if (pv == NULL) { printk(KERN_CRIT "%s -- PV_CREATE: kmalloc error PV at line %d\n", lvm_name, __LINE__); return -ENOMEM; } memset(pv, 0, sizeof(*pv)); if (copy_from_user(pv, pvp, sizeof(pv_t)) != 0) { P_IOCTL("lvm_do_pv_create ERROR: copy PV ptr %p (%d bytes)\n", pvp, sizeof(pv_t)); kfree(pv); return -EFAULT; } if ((err = _open_pv(pv))) { kfree(pv); return err; } /* We don't need the PE list in kernel space as with LVs pe_t list (see below) */ pv->pe = NULL; pv->pe_allocated = 0; pv->pv_status = PV_ACTIVE; vg_ptr->pv_act++; vg_ptr->pv_cur++; lvm_fs_create_pv(vg_ptr, pv); vg_ptr->pv[p] = pv; return 0; } /* lvm_do_pv_create() */ /* * character device support function physical volume remove */ static int lvm_do_pv_remove(vg_t *vg_ptr, ulong p) { pv_t *pv = vg_ptr->pv[p]; lvm_fs_remove_pv(vg_ptr, pv); vg_ptr->pe_total -= pv->pe_total; vg_ptr->pv_cur--; vg_ptr->pv_act--; _close_pv(pv); kfree(pv); vg_ptr->pv[p] = NULL; return 0; } static void __update_hardsectsize(lv_t *lv) { int le, e; int max_hardsectsize = 0, hardsectsize; for (le = 0; le < lv->lv_allocated_le; le++) { hardsectsize = get_hardsect_size(lv->lv_current_pe[le].dev); if (hardsectsize == 0) hardsectsize = 512; if (hardsectsize > max_hardsectsize) max_hardsectsize = hardsectsize; } /* only perform this operation on active snapshots */ if ((lv->lv_access & LV_SNAPSHOT) && (lv->lv_status & LV_ACTIVE)) { for (e = 0; e < lv->lv_remap_end; e++) { hardsectsize = get_hardsect_size( lv->lv_block_exception[e].rdev_new); if (hardsectsize == 0) hardsectsize = 512; if (hardsectsize > max_hardsectsize) max_hardsectsize = hardsectsize; } } } /* * character device support function logical volume create */ static int lvm_do_lv_create(int minor, char *lv_name, lv_t *lv) { int e, ret, l, le, l_new, p, size, activate = 1; ulong lv_status_save; lv_block_exception_t *lvbe = lv->lv_block_exception; vg_t *vg_ptr = vg[VG_CHR(minor)]; lv_t *lv_ptr = NULL; pe_t *pep; if (!(pep = lv->lv_current_pe)) return -EINVAL; if (_sectors_to_k(lv->lv_chunk_size) > LVM_SNAPSHOT_MAX_CHUNK) return -EINVAL; for (l = 0; l < vg_ptr->lv_cur; l++) { if (vg_ptr->lv[l] != NULL && strcmp(vg_ptr->lv[l]->lv_name, lv_name) == 0) return -EEXIST; } /* in case of lv_remove(), lv_create() pair */ l_new = -1; if (vg_ptr->lv[lv->lv_number] == NULL) l_new = lv->lv_number; else { for (l = 0; l < vg_ptr->lv_max; l++) { if (vg_ptr->lv[l] == NULL) if (l_new == -1) l_new = l; } } if (l_new == -1) return -EPERM; else l = l_new; if ((lv_ptr = kmalloc(sizeof(lv_t),GFP_KERNEL)) == NULL) {; printk(KERN_CRIT "%s -- LV_CREATE: kmalloc error LV at line %d\n", lvm_name, __LINE__); return -ENOMEM; } /* copy preloaded LV */ memcpy((char *) lv_ptr, (char *) lv, sizeof(lv_t)); lv_status_save = lv_ptr->lv_status; lv_ptr->lv_status &= ~LV_ACTIVE; lv_ptr->lv_snapshot_org = NULL; lv_ptr->lv_snapshot_prev = NULL; lv_ptr->lv_snapshot_next = NULL; lv_ptr->lv_block_exception = NULL; lv_ptr->lv_iobuf = NULL; lv_ptr->lv_COW_table_iobuf = NULL; lv_ptr->lv_snapshot_hash_table = NULL; lv_ptr->lv_snapshot_hash_table_size = 0; lv_ptr->lv_snapshot_hash_mask = 0; init_rwsem(&lv_ptr->lv_lock); lv_ptr->lv_snapshot_use_rate = 0; vg_ptr->lv[l] = lv_ptr; /* get the PE structures from user space if this is not a snapshot logical volume */ if (!(lv_ptr->lv_access & LV_SNAPSHOT)) { size = lv_ptr->lv_allocated_le * sizeof(pe_t); if ((lv_ptr->lv_current_pe = vmalloc(size)) == NULL) { printk(KERN_CRIT "%s -- LV_CREATE: vmalloc error LV_CURRENT_PE of %d Byte " "at line %d\n", lvm_name, size, __LINE__); P_KFREE("%s -- kfree %d\n", lvm_name, __LINE__); kfree(lv_ptr); vg_ptr->lv[l] = NULL; return -ENOMEM; } if (copy_from_user(lv_ptr->lv_current_pe, pep, size)) { P_IOCTL("ERROR: copying PE ptr %p (%d bytes)\n", pep, sizeof(size)); vfree(lv_ptr->lv_current_pe); kfree(lv_ptr); vg_ptr->lv[l] = NULL; return -EFAULT; } /* correct the PE count in PVs */ for (le = 0; le < lv_ptr->lv_allocated_le; le++) { vg_ptr->pe_allocated++; for (p = 0; p < vg_ptr->pv_cur; p++) { if (kdev_same(vg_ptr->pv[p]->pv_dev, lv_ptr->lv_current_pe[le].dev)) vg_ptr->pv[p]->pe_allocated++; } } } else { /* Get snapshot exception data and block list */ if (lvbe != NULL) { lv_ptr->lv_snapshot_org = vg_ptr->lv[LV_BLK(lv_ptr->lv_snapshot_minor)]; if (lv_ptr->lv_snapshot_org != NULL) { size = lv_ptr->lv_remap_end * sizeof(lv_block_exception_t); if(!size) { printk(KERN_WARNING "%s -- zero length exception table requested\n", lvm_name); kfree(lv_ptr); return -EINVAL; } if ((lv_ptr->lv_block_exception = vmalloc(size)) == NULL) { printk(KERN_CRIT "%s -- lvm_do_lv_create: vmalloc error LV_BLOCK_EXCEPTION " "of %d byte at line %d\n", lvm_name, size, __LINE__); P_KFREE("%s -- kfree %d\n", lvm_name, __LINE__); kfree(lv_ptr); vg_ptr->lv[l] = NULL; return -ENOMEM; } if (copy_from_user(lv_ptr->lv_block_exception, lvbe, size)) { vfree(lv_ptr->lv_block_exception); kfree(lv_ptr); vg_ptr->lv[l] = NULL; return -EFAULT; } if(lv_ptr->lv_block_exception[0].rsector_org == LVM_SNAPSHOT_DROPPED_SECTOR) { printk(KERN_WARNING "%s -- lvm_do_lv_create: snapshot has been dropped and will not be activated\n", lvm_name); activate = 0; } /* point to the original logical volume */ lv_ptr = lv_ptr->lv_snapshot_org; lv_ptr->lv_snapshot_minor = 0; lv_ptr->lv_snapshot_org = lv_ptr; /* our new one now back points to the previous last in the chain which can be the original logical volume */ lv_ptr = vg_ptr->lv[l]; /* now lv_ptr points to our new last snapshot logical volume */ lv_ptr->lv_current_pe = lv_ptr->lv_snapshot_org->lv_current_pe; lv_ptr->lv_allocated_snapshot_le = lv_ptr->lv_allocated_le; lv_ptr->lv_allocated_le = lv_ptr->lv_snapshot_org->lv_allocated_le; lv_ptr->lv_current_le = lv_ptr->lv_snapshot_org->lv_current_le; lv_ptr->lv_size = lv_ptr->lv_snapshot_org->lv_size; lv_ptr->lv_stripes = lv_ptr->lv_snapshot_org->lv_stripes; lv_ptr->lv_stripesize = lv_ptr->lv_snapshot_org->lv_stripesize; /* Update the VG PE(s) used by snapshot reserve space. */ vg_ptr->pe_allocated += lv_ptr->lv_allocated_snapshot_le; if ((ret = lvm_snapshot_alloc(lv_ptr)) != 0) { vfree(lv_ptr->lv_block_exception); kfree(lv_ptr); vg_ptr->lv[l] = NULL; return ret; } for ( e = 0; e < lv_ptr->lv_remap_ptr; e++) lvm_hash_link (lv_ptr->lv_block_exception + e, lv_ptr->lv_block_exception[e].rdev_org, lv_ptr->lv_block_exception[e].rsector_org, lv_ptr); /* need to fill the COW exception table data into the page for disk i/o */ if(lvm_snapshot_fill_COW_page(vg_ptr, lv_ptr)) { kfree(lv_ptr); vg_ptr->lv[l] = NULL; return -EINVAL; } init_waitqueue_head(&lv_ptr->lv_snapshot_wait); } else { kfree(lv_ptr); vg_ptr->lv[l] = NULL; return -EFAULT; } } else { kfree(vg_ptr->lv[l]); vg_ptr->lv[l] = NULL; return -EINVAL; } } /* if ( vg[VG_CHR(minor)]->lv[l]->lv_access & LV_SNAPSHOT) */ lv_ptr = vg_ptr->lv[l]; lvm_gendisk.part[minor(lv_ptr->lv_dev)].start_sect = 0; lvm_gendisk.part[minor(lv_ptr->lv_dev)].nr_sects = lv_ptr->lv_size; lvm_size[minor(lv_ptr->lv_dev)] = lv_ptr->lv_size >> 1; vg_lv_map[minor(lv_ptr->lv_dev)].vg_number = vg_ptr->vg_number; vg_lv_map[minor(lv_ptr->lv_dev)].lv_number = lv_ptr->lv_number; LVM_CORRECT_READ_AHEAD(lv_ptr->lv_read_ahead); vg_ptr->lv_cur++; lv_ptr->lv_status = lv_status_save; __update_hardsectsize(lv_ptr); /* optionally add our new snapshot LV */ if (lv_ptr->lv_access & LV_SNAPSHOT) { lv_t *org = lv_ptr->lv_snapshot_org, *last; /* sync the original logical volume */ fsync_dev(org->lv_dev); #ifdef LVM_VFS_ENHANCEMENT /* VFS function call to sync and lock the filesystem */ fsync_dev_lockfs(org->lv_dev); #endif down_write(&org->lv_lock); org->lv_access |= LV_SNAPSHOT_ORG; lv_ptr->lv_access &= ~LV_SNAPSHOT_ORG; /* this can only hide an userspace bug */ /* Link in the list of snapshot volumes */ for (last = org; last->lv_snapshot_next; last = last->lv_snapshot_next); lv_ptr->lv_snapshot_prev = last; last->lv_snapshot_next = lv_ptr; up_write(&org->lv_lock); } /* activate the logical volume */ if(activate) lv_ptr->lv_status |= LV_ACTIVE; else lv_ptr->lv_status &= ~LV_ACTIVE; if ( lv_ptr->lv_access & LV_WRITE) set_device_ro(lv_ptr->lv_dev, 0); else set_device_ro(lv_ptr->lv_dev, 1); #ifdef LVM_VFS_ENHANCEMENT /* VFS function call to unlock the filesystem */ if (lv_ptr->lv_access & LV_SNAPSHOT) unlockfs(lv_ptr->lv_snapshot_org->lv_dev); #endif lv_ptr->vg = vg_ptr; lvm_gendisk.part[minor(lv_ptr->lv_dev)].de = lvm_fs_create_lv(vg_ptr, lv_ptr); return 0; } /* lvm_do_lv_create() */ /* * character device support function logical volume remove */ static int lvm_do_lv_remove(int minor, char *lv_name, int l) { uint le, p; vg_t *vg_ptr = vg[VG_CHR(minor)]; lv_t *lv_ptr; if (l == -1) { for (l = 0; l < vg_ptr->lv_max; l++) { if (vg_ptr->lv[l] != NULL && strcmp(vg_ptr->lv[l]->lv_name, lv_name) == 0) { break; } } } if (l == vg_ptr->lv_max) return -ENXIO; lv_ptr = vg_ptr->lv[l]; #ifdef LVM_TOTAL_RESET if (lv_ptr->lv_open > 0 && lvm_reset_spindown == 0) #else if (lv_ptr->lv_open > 0) #endif return -EBUSY; /* check for deletion of snapshot source while snapshot volume still exists */ if ((lv_ptr->lv_access & LV_SNAPSHOT_ORG) && lv_ptr->lv_snapshot_next != NULL) return -EPERM; lvm_fs_remove_lv(vg_ptr, lv_ptr); if (lv_ptr->lv_access & LV_SNAPSHOT) { /* * Atomically make the the snapshot invisible * to the original lv before playing with it. */ lv_t * org = lv_ptr->lv_snapshot_org; down_write(&org->lv_lock); /* remove this snapshot logical volume from the chain */ lv_ptr->lv_snapshot_prev->lv_snapshot_next = lv_ptr->lv_snapshot_next; if (lv_ptr->lv_snapshot_next != NULL) { lv_ptr->lv_snapshot_next->lv_snapshot_prev = lv_ptr->lv_snapshot_prev; } /* no more snapshots? */ if (!org->lv_snapshot_next) { org->lv_access &= ~LV_SNAPSHOT_ORG; } up_write(&org->lv_lock); lvm_snapshot_release(lv_ptr); /* Update the VG PE(s) used by snapshot reserve space. */ vg_ptr->pe_allocated -= lv_ptr->lv_allocated_snapshot_le; } lv_ptr->lv_status |= LV_SPINDOWN; /* sync the buffers */ fsync_dev(lv_ptr->lv_dev); lv_ptr->lv_status &= ~LV_ACTIVE; /* invalidate the buffers */ invalidate_buffers(lv_ptr->lv_dev); /* reset generic hd */ lvm_gendisk.part[minor(lv_ptr->lv_dev)].start_sect = -1; lvm_gendisk.part[minor(lv_ptr->lv_dev)].nr_sects = 0; lvm_gendisk.part[minor(lv_ptr->lv_dev)].de = 0; lvm_size[minor(lv_ptr->lv_dev)] = 0; /* reset VG/LV mapping */ vg_lv_map[minor(lv_ptr->lv_dev)].vg_number = ABS_MAX_VG; vg_lv_map[minor(lv_ptr->lv_dev)].lv_number = -1; /* correct the PE count in PVs if this is not a snapshot logical volume */ if (!(lv_ptr->lv_access & LV_SNAPSHOT)) { /* only if this is no snapshot logical volume because we share the lv_current_pe[] structs with the original logical volume */ for (le = 0; le < lv_ptr->lv_allocated_le; le++) { vg_ptr->pe_allocated--; for (p = 0; p < vg_ptr->pv_cur; p++) { if (kdev_same(vg_ptr->pv[p]->pv_dev, lv_ptr->lv_current_pe[le].dev)) vg_ptr->pv[p]->pe_allocated--; } } vfree(lv_ptr->lv_current_pe); } P_KFREE("%s -- kfree %d\n", lvm_name, __LINE__); kfree(lv_ptr); vg_ptr->lv[l] = NULL; vg_ptr->lv_cur--; return 0; } /* lvm_do_lv_remove() */ /* * logical volume extend / reduce */ static int __extend_reduce_snapshot(vg_t *vg_ptr, lv_t *old_lv, lv_t *new_lv) { ulong size; lv_block_exception_t *lvbe; if (!new_lv->lv_block_exception) return -ENXIO; size = new_lv->lv_remap_end * sizeof(lv_block_exception_t); if ((lvbe = vmalloc(size)) == NULL) { printk(KERN_CRIT "%s -- lvm_do_lv_extend_reduce: vmalloc " "error LV_BLOCK_EXCEPTION of %lu Byte at line %d\n", lvm_name, size, __LINE__); return -ENOMEM; } if ((new_lv->lv_remap_end > old_lv->lv_remap_end) && (copy_from_user(lvbe, new_lv->lv_block_exception, size))) { vfree(lvbe); return -EFAULT; } new_lv->lv_block_exception = lvbe; if (lvm_snapshot_alloc_hash_table(new_lv)) { vfree(new_lv->lv_block_exception); return -ENOMEM; } return 0; } static int __extend_reduce(vg_t *vg_ptr, lv_t *old_lv, lv_t *new_lv) { ulong size, l, p, end; pe_t *pe; /* allocate space for new pe structures */ size = new_lv->lv_current_le * sizeof(pe_t); if ((pe = vmalloc(size)) == NULL) { printk(KERN_CRIT "%s -- lvm_do_lv_extend_reduce: " "vmalloc error LV_CURRENT_PE of %lu Byte at line %d\n", lvm_name, size, __LINE__); return -ENOMEM; } /* get the PE structures from user space */ if (copy_from_user(pe, new_lv->lv_current_pe, size)) { if(old_lv->lv_access & LV_SNAPSHOT) vfree(new_lv->lv_snapshot_hash_table); vfree(pe); return -EFAULT; } new_lv->lv_current_pe = pe; /* reduce allocation counters on PV(s) */ for (l = 0; l < old_lv->lv_allocated_le; l++) { vg_ptr->pe_allocated--; for (p = 0; p < vg_ptr->pv_cur; p++) { if (kdev_same(vg_ptr->pv[p]->pv_dev, old_lv->lv_current_pe[l].dev)) { vg_ptr->pv[p]->pe_allocated--; break; } } } /* extend the PE count in PVs */ for (l = 0; l < new_lv->lv_allocated_le; l++) { vg_ptr->pe_allocated++; for (p = 0; p < vg_ptr->pv_cur; p++) { if (kdev_same(vg_ptr->pv[p]->pv_dev, new_lv->lv_current_pe[l].dev)) { vg_ptr->pv[p]->pe_allocated++; break; } } } /* save availiable i/o statistic data */ if (old_lv->lv_stripes < 2) { /* linear logical volume */ end = min(old_lv->lv_current_le, new_lv->lv_current_le); for (l = 0; l < end; l++) { new_lv->lv_current_pe[l].reads += old_lv->lv_current_pe[l].reads; new_lv->lv_current_pe[l].writes += old_lv->lv_current_pe[l].writes; } } else { /* striped logical volume */ uint i, j, source, dest, end, old_stripe_size, new_stripe_size; old_stripe_size = old_lv->lv_allocated_le / old_lv->lv_stripes; new_stripe_size = new_lv->lv_allocated_le / new_lv->lv_stripes; end = min(old_stripe_size, new_stripe_size); for (i = source = dest = 0; i < new_lv->lv_stripes; i++) { for (j = 0; j < end; j++) { new_lv->lv_current_pe[dest + j].reads += old_lv->lv_current_pe[source + j].reads; new_lv->lv_current_pe[dest + j].writes += old_lv->lv_current_pe[source + j].writes; } source += old_stripe_size; dest += new_stripe_size; } } return 0; } static int lvm_do_lv_extend_reduce(int minor, char *lv_name, lv_t *new_lv) { int r; ulong l, e, size; vg_t *vg_ptr = vg[VG_CHR(minor)]; lv_t *old_lv; pe_t *pe; if ((pe = new_lv->lv_current_pe) == NULL) return -EINVAL; for (l = 0; l < vg_ptr->lv_max; l++) if (vg_ptr->lv[l] && !strcmp(vg_ptr->lv[l]->lv_name, lv_name)) break; if (l == vg_ptr->lv_max) return -ENXIO; old_lv = vg_ptr->lv[l]; if (old_lv->lv_access & LV_SNAPSHOT) { /* only perform this operation on active snapshots */ if (old_lv->lv_status & LV_ACTIVE) r = __extend_reduce_snapshot(vg_ptr, old_lv, new_lv); else r = -EPERM; } else r = __extend_reduce(vg_ptr, old_lv, new_lv); if(r) return r; /* copy relevent fields */ down_write(&old_lv->lv_lock); if(new_lv->lv_access & LV_SNAPSHOT) { size = (new_lv->lv_remap_end > old_lv->lv_remap_end) ? old_lv->lv_remap_ptr : new_lv->lv_remap_end; size *= sizeof(lv_block_exception_t); memcpy(new_lv->lv_block_exception, old_lv->lv_block_exception, size); old_lv->lv_remap_end = new_lv->lv_remap_end; old_lv->lv_block_exception = new_lv->lv_block_exception; old_lv->lv_snapshot_hash_table = new_lv->lv_snapshot_hash_table; old_lv->lv_snapshot_hash_table_size = new_lv->lv_snapshot_hash_table_size; old_lv->lv_snapshot_hash_mask = new_lv->lv_snapshot_hash_mask; for (e = 0; e < new_lv->lv_remap_ptr; e++) lvm_hash_link(new_lv->lv_block_exception + e, new_lv->lv_block_exception[e].rdev_org, new_lv->lv_block_exception[e].rsector_org, new_lv); } else { vfree(old_lv->lv_current_pe); vfree(old_lv->lv_snapshot_hash_table); old_lv->lv_size = new_lv->lv_size; old_lv->lv_allocated_le = new_lv->lv_allocated_le; old_lv->lv_current_le = new_lv->lv_current_le; old_lv->lv_current_pe = new_lv->lv_current_pe; lvm_gendisk.part[minor(old_lv->lv_dev)].nr_sects = old_lv->lv_size; lvm_size[minor(old_lv->lv_dev)] = old_lv->lv_size >> 1; if (old_lv->lv_access & LV_SNAPSHOT_ORG) { lv_t *snap; for(snap = old_lv->lv_snapshot_next; snap; snap = snap->lv_snapshot_next) { down_write(&snap->lv_lock); snap->lv_current_pe = old_lv->lv_current_pe; snap->lv_allocated_le = old_lv->lv_allocated_le; snap->lv_current_le = old_lv->lv_current_le; snap->lv_size = old_lv->lv_size; lvm_gendisk.part[minor(snap->lv_dev)].nr_sects = old_lv->lv_size; lvm_size[minor(snap->lv_dev)] = old_lv->lv_size >> 1; __update_hardsectsize(snap); up_write(&snap->lv_lock); } } } __update_hardsectsize(old_lv); up_write(&old_lv->lv_lock); return 0; } /* lvm_do_lv_extend_reduce() */ /* * character device support function logical volume status by name */ static int lvm_do_lv_status_byname(vg_t *vg_ptr, void *arg) { uint l; lv_status_byname_req_t lv_status_byname_req; void *saved_ptr1; void *saved_ptr2; lv_t *lv_ptr; if (vg_ptr == NULL) return -ENXIO; if (copy_from_user(&lv_status_byname_req, arg, sizeof(lv_status_byname_req_t)) != 0) return -EFAULT; if (lv_status_byname_req.lv == NULL) return -EINVAL; for (l = 0; l < vg_ptr->lv_max; l++) { if ((lv_ptr = vg_ptr->lv[l]) != NULL && strcmp(lv_ptr->lv_name, lv_status_byname_req.lv_name) == 0) { /* Save usermode pointers */ if (copy_from_user(&saved_ptr1, &lv_status_byname_req.lv->lv_current_pe, sizeof(void*)) != 0) return -EFAULT; if (copy_from_user(&saved_ptr2, &lv_status_byname_req.lv->lv_block_exception, sizeof(void*)) != 0) return -EFAULT; if (copy_to_user(lv_status_byname_req.lv, lv_ptr, sizeof(lv_t)) != 0) return -EFAULT; if (saved_ptr1 != NULL) { if (copy_to_user(saved_ptr1, lv_ptr->lv_current_pe, lv_ptr->lv_allocated_le * sizeof(pe_t)) != 0) return -EFAULT; } /* Restore usermode pointers */ if (copy_to_user(&lv_status_byname_req.lv->lv_current_pe, &saved_ptr1, sizeof(void*)) != 0) return -EFAULT; return 0; } } return -ENXIO; } /* lvm_do_lv_status_byname() */ /* * character device support function logical volume status by index */ static int lvm_do_lv_status_byindex(vg_t *vg_ptr,void *arg) { lv_status_byindex_req_t lv_status_byindex_req; void *saved_ptr1; void *saved_ptr2; lv_t *lv_ptr; if (vg_ptr == NULL) return -ENXIO; if (copy_from_user(&lv_status_byindex_req, arg, sizeof(lv_status_byindex_req)) != 0) return -EFAULT; if (lv_status_byindex_req.lv == NULL) return -EINVAL; if (lv_status_byindex_req.lv_index <0 || lv_status_byindex_req.lv_index >= MAX_LV) return -EINVAL; if ( ( lv_ptr = vg_ptr->lv[lv_status_byindex_req.lv_index]) == NULL) return -ENXIO; /* Save usermode pointers */ if (copy_from_user(&saved_ptr1, &lv_status_byindex_req.lv->lv_current_pe, sizeof(void*)) != 0) return -EFAULT; if (copy_from_user(&saved_ptr2, &lv_status_byindex_req.lv->lv_block_exception, sizeof(void*)) != 0) return -EFAULT; if (copy_to_user(lv_status_byindex_req.lv, lv_ptr, sizeof(lv_t)) != 0) return -EFAULT; if (saved_ptr1 != NULL) { if (copy_to_user(saved_ptr1, lv_ptr->lv_current_pe, lv_ptr->lv_allocated_le * sizeof(pe_t)) != 0) return -EFAULT; } /* Restore usermode pointers */ if (copy_to_user(&lv_status_byindex_req.lv->lv_current_pe, &saved_ptr1, sizeof(void *)) != 0) return -EFAULT; return 0; } /* lvm_do_lv_status_byindex() */ /* * character device support function logical volume status by device number */ static int lvm_do_lv_status_bydev(vg_t * vg_ptr, void * arg) { int l; lv_status_bydev_req_t lv_status_bydev_req; void *saved_ptr1; void *saved_ptr2; lv_t *lv_ptr; if (vg_ptr == NULL) return -ENXIO; if (copy_from_user(&lv_status_bydev_req, arg, sizeof(lv_status_bydev_req)) != 0) return -EFAULT; for ( l = 0; l < vg_ptr->lv_max; l++) { if ( vg_ptr->lv[l] == NULL) continue; if ( kdev_same(vg_ptr->lv[l]->lv_dev, to_kdev_t(lv_status_bydev_req.dev))) break; } if ( l == vg_ptr->lv_max) return -ENXIO; lv_ptr = vg_ptr->lv[l]; /* Save usermode pointers */ if (copy_from_user(&saved_ptr1, &lv_status_bydev_req.lv->lv_current_pe, sizeof(void*)) != 0) return -EFAULT; if (copy_from_user(&saved_ptr2, &lv_status_bydev_req.lv->lv_block_exception, sizeof(void*)) != 0) return -EFAULT; if (copy_to_user(lv_status_bydev_req.lv, lv_ptr, sizeof(lv_t)) != 0) return -EFAULT; if (saved_ptr1 != NULL) { if (copy_to_user(saved_ptr1, lv_ptr->lv_current_pe, lv_ptr->lv_allocated_le * sizeof(pe_t)) != 0) return -EFAULT; } /* Restore usermode pointers */ if (copy_to_user(&lv_status_bydev_req.lv->lv_current_pe, &saved_ptr1, sizeof(void *)) != 0) return -EFAULT; return 0; } /* lvm_do_lv_status_bydev() */ /* * character device support function rename a logical volume */ static int lvm_do_lv_rename(vg_t *vg_ptr, lv_req_t *lv_req, lv_t *lv) { int l = 0; int ret = 0; lv_t *lv_ptr = NULL; for (l = 0; l < vg_ptr->lv_max; l++) { if ( (lv_ptr = vg_ptr->lv[l]) == NULL) continue; if (kdev_same(lv_ptr->lv_dev, lv->lv_dev)) { lvm_fs_remove_lv(vg_ptr, lv_ptr); strncpy(lv_ptr->lv_name, lv_req->lv_name, NAME_LEN); lvm_fs_create_lv(vg_ptr, lv_ptr); break; } } if (l == vg_ptr->lv_max) ret = -ENODEV; return ret; } /* lvm_do_lv_rename */ /* * character device support function physical volume change */ static int lvm_do_pv_change(vg_t *vg_ptr, void *arg) { uint p; pv_t *pv_ptr; struct block_device *bd; if (vg_ptr == NULL) return -ENXIO; if (copy_from_user(&pv_change_req, arg, sizeof(pv_change_req)) != 0) return -EFAULT; for (p = 0; p < vg_ptr->pv_max; p++) { pv_ptr = vg_ptr->pv[p]; if (pv_ptr != NULL && strcmp(pv_ptr->pv_name, pv_change_req.pv_name) == 0) { bd = pv_ptr->bd; if (copy_from_user(pv_ptr, pv_change_req.pv, sizeof(pv_t)) != 0) return -EFAULT; pv_ptr->bd = bd; /* We don't need the PE list in kernel space as with LVs pe_t list */ pv_ptr->pe = NULL; return 0; } } return -ENXIO; } /* lvm_do_pv_change() */ /* * character device support function get physical volume status */ static int lvm_do_pv_status(vg_t *vg_ptr, void *arg) { uint p; pv_t *pv_ptr; if (vg_ptr == NULL) return -ENXIO; if (copy_from_user(&pv_status_req, arg, sizeof(pv_status_req)) != 0) return -EFAULT; for (p = 0; p < vg_ptr->pv_max; p++) { pv_ptr = vg_ptr->pv[p]; if (pv_ptr != NULL && strcmp(pv_ptr->pv_name, pv_status_req.pv_name) == 0) { if (copy_to_user(pv_status_req.pv, pv_ptr, sizeof(pv_t)) != 0) return -EFAULT; return 0; } } return -ENXIO; } /* lvm_do_pv_status() */ /* * character device support function flush and invalidate all buffers of a PV */ static int lvm_do_pv_flush(void *arg) { pv_flush_req_t pv_flush_req; if (copy_from_user(&pv_flush_req, arg, sizeof(pv_flush_req)) != 0) return -EFAULT; fsync_dev(pv_flush_req.pv_dev); invalidate_buffers(pv_flush_req.pv_dev); return 0; } /* * support function initialize gendisk variables */ static void __init lvm_geninit(struct gendisk *lvm_gdisk) { int i = 0; #ifdef DEBUG_GENDISK printk(KERN_DEBUG "%s -- lvm_gendisk\n", lvm_name); #endif for (i = 0; i < MAX_LV; i++) { lvm_gendisk.part[i].start_sect = -1; /* avoid partition check */ lvm_size[i] = lvm_gendisk.part[i].nr_sects = 0; lvm_blocksizes[i] = BLOCK_SIZE; } blk_size[MAJOR_NR] = lvm_size; blksize_size[MAJOR_NR] = lvm_blocksizes; return; } /* lvm_gen_init() */ /* Must have down_write(_pe_lock) when we enqueue buffers */ static void _queue_io(struct bio *bh, int rw) { if (bh->bi_next) BUG(); bh->bi_next = _pe_requests; _pe_requests = bh; } /* Must have down_write(_pe_lock) when we dequeue buffers */ static struct bio *_dequeue_io(void) { struct bio *bh = _pe_requests; _pe_requests = NULL; return bh; } /* * We do not need to hold _pe_lock to flush buffers. bh should be taken from * _pe_requests under down_write(_pe_lock), and then _pe_requests can be set * NULL and we drop _pe_lock. Any new buffers defered at this time will be * added to a new list, and the old buffers can have their I/O restarted * asynchronously. * * If, for some reason, the same PE is locked again before all of these writes * have finished, then these buffers will just be re-queued (i.e. no danger). */ static void _flush_io(struct bio *bh) { while (bh) { struct bio *next = bh->bi_next; bh->bi_next = NULL; /* resubmit this buffer head */ bh->bi_rw = WRITE; /* needed? */ generic_make_request(bh); bh = next; } } /* * we must open the pv's before we use them */ static int _open_pv(pv_t *pv) { int err; struct block_device *bd; if (!(bd = bdget(kdev_t_to_nr(pv->pv_dev)))) return -ENOMEM; err = blkdev_get(bd, FMODE_READ|FMODE_WRITE, 0, BDEV_FILE); if (err) return err; pv->bd = bd; return 0; } static void _close_pv(pv_t *pv) { if (pv) { struct block_device *bdev = pv->bd; pv->bd = NULL; if (bdev) blkdev_put(bdev, BDEV_FILE); } } static unsigned long _sectors_to_k(unsigned long sect) { if(SECTOR_SIZE > 1024) { return sect * (SECTOR_SIZE / 1024); } return sect / (1024 / SECTOR_SIZE); } module_init(lvm_init); module_exit(lvm_cleanup); MODULE_LICENSE("GPL"); |