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 | /* * NET3 Protocol independent device support routines. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * * Derived from the non IP parts of dev.c 1.0.19 * Authors: Ross Biro, <bir7@leland.Stanford.Edu> * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * * Additional Authors: * Florian la Roche <rzsfl@rz.uni-sb.de> * Alan Cox <gw4pts@gw4pts.ampr.org> * David Hinds <dhinds@allegro.stanford.edu> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * Adam Sulmicki <adam@cfar.umd.edu> * * Changes: * Alan Cox : device private ioctl copies fields back. * Alan Cox : Transmit queue code does relevant stunts to * keep the queue safe. * Alan Cox : Fixed double lock. * Alan Cox : Fixed promisc NULL pointer trap * ???????? : Support the full private ioctl range * Alan Cox : Moved ioctl permission check into drivers * Tim Kordas : SIOCADDMULTI/SIOCDELMULTI * Alan Cox : 100 backlog just doesn't cut it when * you start doing multicast video 8) * Alan Cox : Rewrote net_bh and list manager. * Alan Cox : Fix ETH_P_ALL echoback lengths. * Alan Cox : Took out transmit every packet pass * Saved a few bytes in the ioctl handler * Alan Cox : Network driver sets packet type before calling netif_rx. Saves * a function call a packet. * Alan Cox : Hashed net_bh() * Richard Kooijman: Timestamp fixes. * Alan Cox : Wrong field in SIOCGIFDSTADDR * Alan Cox : Device lock protection. * Alan Cox : Fixed nasty side effect of device close changes. * Rudi Cilibrasi : Pass the right thing to set_mac_address() * Dave Miller : 32bit quantity for the device lock to make it work out * on a Sparc. * Bjorn Ekwall : Added KERNELD hack. * Alan Cox : Cleaned up the backlog initialise. * Craig Metz : SIOCGIFCONF fix if space for under * 1 device. * Thomas Bogendoerfer : Return ENODEV for dev_open, if there * is no device open function. * Andi Kleen : Fix error reporting for SIOCGIFCONF * Michael Chastain : Fix signed/unsigned for SIOCGIFCONF * Cyrus Durgin : Cleaned for KMOD * Adam Sulmicki : Bug Fix : Network Device Unload * A network device unload needs to purge * the backlog queue. * Paul Rusty Russel : SIOCSIFNAME */ #include <asm/uaccess.h> #include <asm/system.h> #include <asm/bitops.h> #include <linux/config.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/notifier.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/rtnetlink.h> #include <net/slhc.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <net/br.h> #include <net/dst.h> #include <net/pkt_sched.h> #include <net/profile.h> #include <linux/init.h> #include <linux/kmod.h> #ifdef CONFIG_NET_RADIO #include <linux/wireless.h> #endif /* CONFIG_NET_RADIO */ #ifdef CONFIG_PLIP extern int plip_init(void); #endif NET_PROFILE_DEFINE(dev_queue_xmit) NET_PROFILE_DEFINE(net_bh) NET_PROFILE_DEFINE(net_bh_skb) const char *if_port_text[] = { "unknown", "BNC", "10baseT", "AUI", "100baseT", "100baseTX", "100baseFX" }; /* * The list of packet types we will receive (as opposed to discard) * and the routines to invoke. * * Why 16. Because with 16 the only overlap we get on a hash of the * low nibble of the protocol value is RARP/SNAP/X.25. * * 0800 IP * 0001 802.3 * 0002 AX.25 * 0004 802.2 * 8035 RARP * 0005 SNAP * 0805 X.25 * 0806 ARP * 8137 IPX * 0009 Localtalk * 86DD IPv6 */ static struct packet_type *ptype_base[16]; /* 16 way hashed list */ static struct packet_type *ptype_all = NULL; /* Taps */ static rwlock_t ptype_lock = RW_LOCK_UNLOCKED; /* * Our notifier list */ static struct notifier_block *netdev_chain=NULL; /* * Device drivers call our routines to queue packets here. We empty the * queue in the bottom half handler. */ static struct sk_buff_head backlog; #ifdef CONFIG_NET_FASTROUTE int netdev_fastroute; int netdev_fastroute_obstacles; struct net_fastroute_stats dev_fastroute_stat; #endif static void dev_clear_backlog(struct net_device *dev); /****************************************************************************************** Protocol management and registration routines *******************************************************************************************/ /* * For efficiency */ int netdev_nit=0; /* * Add a protocol ID to the list. Now that the input handler is * smarter we can dispense with all the messy stuff that used to be * here. * * BEWARE!!! Protocol handlers, mangling input packets, * MUST BE last in hash buckets and checking protocol handlers * MUST start from promiscous ptype_all chain in net_bh. * It is true now, do not change it. * Explantion follows: if protocol handler, mangling packet, will * be the first on list, it is not able to sense, that packet * is cloned and should be copied-on-write, so that it will * change it and subsequent readers will get broken packet. * --ANK (980803) */ void dev_add_pack(struct packet_type *pt) { int hash; #ifdef CONFIG_NET_FASTROUTE /* Hack to detect packet socket */ if (pt->data) { netdev_fastroute_obstacles++; dev_clear_fastroute(pt->dev); } #endif write_lock_bh(&ptype_lock); if(pt->type==htons(ETH_P_ALL)) { netdev_nit++; pt->next=ptype_all; ptype_all=pt; } else { hash=ntohs(pt->type)&15; pt->next = ptype_base[hash]; ptype_base[hash] = pt; } write_unlock_bh(&ptype_lock); } /* * Remove a protocol ID from the list. */ void dev_remove_pack(struct packet_type *pt) { struct packet_type **pt1; if(pt->type==htons(ETH_P_ALL)) { netdev_nit--; pt1=&ptype_all; } else pt1=&ptype_base[ntohs(pt->type)&15]; write_lock_bh(&ptype_lock); for(; (*pt1)!=NULL; pt1=&((*pt1)->next)) { if(pt==(*pt1)) { *pt1=pt->next; #ifdef CONFIG_NET_FASTROUTE if (pt->data) netdev_fastroute_obstacles--; #endif write_unlock_bh(&ptype_lock); return; } } write_unlock_bh(&ptype_lock); printk(KERN_WARNING "dev_remove_pack: %p not found.\n", pt); } /***************************************************************************************** Device Interface Subroutines ******************************************************************************************/ /* * Find an interface by name. May be called under rtnl semaphore * or dev_base_lock. */ struct net_device *__dev_get_by_name(const char *name) { struct net_device *dev; for (dev = dev_base; dev != NULL; dev = dev->next) { if (strcmp(dev->name, name) == 0) return dev; } return NULL; } /* * Find an interface by name. Any context, dev_put() to release. */ struct net_device *dev_get_by_name(const char *name) { struct net_device *dev; read_lock(&dev_base_lock); dev = __dev_get_by_name(name); if (dev) dev_hold(dev); read_unlock(&dev_base_lock); return dev; } /* Return value is changed to int to prevent illegal usage in future. It is still legal to use to check for device existance. */ int dev_get(const char *name) { struct net_device *dev; read_lock(&dev_base_lock); dev = __dev_get_by_name(name); read_unlock(&dev_base_lock); return dev != NULL; } /* * Find an interface by index. May be called under rtnl semaphore * or dev_base_lock. */ struct net_device * __dev_get_by_index(int ifindex) { struct net_device *dev; for (dev = dev_base; dev != NULL; dev = dev->next) { if (dev->ifindex == ifindex) return dev; } return NULL; } /* * Find an interface by index. Any context, dev_put() to release. */ struct net_device * dev_get_by_index(int ifindex) { struct net_device *dev; read_lock(&dev_base_lock); dev = __dev_get_by_index(ifindex); if (dev) dev_hold(dev); read_unlock(&dev_base_lock); return dev; } /* * Find an interface by ll addr. May be called only under rtnl semaphore. */ struct net_device *dev_getbyhwaddr(unsigned short type, char *ha) { struct net_device *dev; ASSERT_RTNL(); for (dev = dev_base; dev != NULL; dev = dev->next) { if (dev->type == type && memcmp(dev->dev_addr, ha, dev->addr_len) == 0) return dev; } return NULL; } /* * Passed a format string - eg "lt%d" it will try and find a suitable * id. Not efficient for many devices, not called a lot.. */ int dev_alloc_name(struct net_device *dev, const char *name) { int i; char buf[32]; /* * If you need over 100 please also fix the algorithm... */ for(i=0;i<100;i++) { sprintf(buf,name,i); if(__dev_get_by_name(buf)==NULL) { strcpy(dev->name, buf); return i; } } return -ENFILE; /* Over 100 of the things .. bail out! */ } struct net_device *dev_alloc(const char *name, int *err) { struct net_device *dev=kmalloc(sizeof(struct net_device)+16, GFP_KERNEL); if(dev==NULL) { *err=-ENOBUFS; return NULL; } memset(dev, 0, sizeof(struct net_device)); dev->name=(char *)(dev+1); /* Name string space */ *err=dev_alloc_name(dev,name); if(*err<0) { kfree(dev); return NULL; } return dev; } void netdev_state_change(struct net_device *dev) { if (dev->flags&IFF_UP) notifier_call_chain(&netdev_chain, NETDEV_CHANGE, dev); } /* * Find and possibly load an interface. */ #ifdef CONFIG_KMOD void dev_load(const char *name) { if(!__dev_get_by_name(name) && capable(CAP_SYS_MODULE)) request_module(name); } #else extern inline void dev_load(const char *unused){;} #endif static int default_rebuild_header(struct sk_buff *skb) { printk(KERN_DEBUG "%s: default_rebuild_header called -- BUG!\n", skb->dev ? skb->dev->name : "NULL!!!"); kfree_skb(skb); return 1; } /* * Prepare an interface for use. */ int dev_open(struct net_device *dev) { int ret = 0; /* * Is it already up? */ if (dev->flags&IFF_UP) return 0; /* * Call device private open method */ if (dev->open) ret = dev->open(dev); /* * If it went open OK then: */ if (ret == 0) { /* * nil rebuild_header routine, * that should be never called and used as just bug trap. */ if (dev->rebuild_header == NULL) dev->rebuild_header = default_rebuild_header; /* * Set the flags. */ dev->flags |= (IFF_UP | IFF_RUNNING); /* * Initialize multicasting status */ dev_mc_upload(dev); /* * Wakeup transmit queue engine */ dev_activate(dev); /* * ... and announce new interface. */ notifier_call_chain(&netdev_chain, NETDEV_UP, dev); } return(ret); } #ifdef CONFIG_NET_FASTROUTE static void dev_do_clear_fastroute(struct net_device *dev) { if (dev->accept_fastpath) { int i; for (i=0; i<=NETDEV_FASTROUTE_HMASK; i++) { struct dst_entry *dst; write_lock_irq(&dev->fastpath_lock); dst = dev->fastpath[i]; dev->fastpath[i] = NULL; write_unlock_irq(&dev->fastpath_lock); dst_release(dst); } } } void dev_clear_fastroute(struct net_device *dev) { if (dev) { dev_do_clear_fastroute(dev); } else { read_lock(&dev_base_lock); for (dev = dev_base; dev; dev = dev->next) dev_do_clear_fastroute(dev); read_unlock(&dev_base_lock); } } #endif /* * Completely shutdown an interface. */ int dev_close(struct net_device *dev) { if (!(dev->flags&IFF_UP)) return 0; dev_deactivate(dev); /* * Call the device specific close. This cannot fail. * Only if device is UP */ if (dev->stop) dev->stop(dev); if (dev->start) printk("dev_close: bug %s still running\n", dev->name); /* * Device is now down. */ dev_clear_backlog(dev); dev->flags&=~(IFF_UP|IFF_RUNNING); #ifdef CONFIG_NET_FASTROUTE dev_clear_fastroute(dev); #endif /* * Tell people we are going down */ notifier_call_chain(&netdev_chain, NETDEV_DOWN, dev); return(0); } /* * Device change register/unregister. These are not inline or static * as we export them to the world. */ int register_netdevice_notifier(struct notifier_block *nb) { return notifier_chain_register(&netdev_chain, nb); } int unregister_netdevice_notifier(struct notifier_block *nb) { return notifier_chain_unregister(&netdev_chain,nb); } /* * Support routine. Sends outgoing frames to any network * taps currently in use. */ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { struct packet_type *ptype; get_fast_time(&skb->stamp); read_lock(&ptype_lock); for (ptype = ptype_all; ptype!=NULL; ptype = ptype->next) { /* Never send packets back to the socket * they originated from - MvS (miquels@drinkel.ow.org) */ if ((ptype->dev == dev || !ptype->dev) && ((struct sock *)ptype->data != skb->sk)) { struct sk_buff *skb2; if ((skb2 = skb_clone(skb, GFP_ATOMIC)) == NULL) break; /* skb->nh should be correctly set by sender, so that the second statement is just protection against buggy protocols. */ skb2->mac.raw = skb2->data; if (skb2->nh.raw < skb2->data || skb2->nh.raw >= skb2->tail) { if (net_ratelimit()) printk(KERN_DEBUG "protocol %04x is buggy, dev %s\n", skb2->protocol, dev->name); skb2->nh.raw = skb2->data; if (dev->hard_header) skb2->nh.raw += dev->hard_header_len; } skb2->h.raw = skb2->nh.raw; skb2->pkt_type = PACKET_OUTGOING; skb2->rx_dev = skb->dev; dev_hold(skb2->rx_dev); ptype->func(skb2, skb->dev, ptype); } } read_unlock(&ptype_lock); } /* * Fast path for loopback frames. */ void dev_loopback_xmit(struct sk_buff *skb) { struct sk_buff *newskb=skb_clone(skb, GFP_ATOMIC); if (newskb==NULL) return; newskb->mac.raw = newskb->data; skb_pull(newskb, newskb->nh.raw - newskb->data); newskb->pkt_type = PACKET_LOOPBACK; newskb->ip_summed = CHECKSUM_UNNECESSARY; if (newskb->dst==NULL) printk(KERN_DEBUG "BUG: packet without dst looped back 1\n"); netif_rx(newskb); } int dev_queue_xmit(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct Qdisc *q; /* Grab device queue */ spin_lock_bh(&dev->queue_lock); q = dev->qdisc; if (q->enqueue) { int ret = q->enqueue(skb, q); /* If the device is not busy, kick it. * Otherwise or if queue is not empty after kick, * add it to run list. */ if (dev->tbusy || __qdisc_wakeup(dev)) qdisc_run(q); spin_unlock_bh(&dev->queue_lock); return ret; } /* The device has no queue. Common case for software devices: loopback, all the sorts of tunnels... Really, it is unlikely that xmit_lock protection is necessary here. (f.e. loopback and IP tunnels are clean ignoring statistics counters.) However, it is possible, that they rely on protection made by us here. Check this and shot the lock. It is not prone from deadlocks. Either shot noqueue qdisc, it is even simpler 8) */ if (dev->flags&IFF_UP) { if (dev->xmit_lock_owner != smp_processor_id()) { spin_unlock(&dev->queue_lock); spin_lock(&dev->xmit_lock); dev->xmit_lock_owner = smp_processor_id(); if (netdev_nit) dev_queue_xmit_nit(skb,dev); if (dev->hard_start_xmit(skb, dev) == 0) { dev->xmit_lock_owner = -1; spin_unlock_bh(&dev->xmit_lock); return 0; } dev->xmit_lock_owner = -1; spin_unlock_bh(&dev->xmit_lock); if (net_ratelimit()) printk(KERN_DEBUG "Virtual device %s asks to queue packet!\n", dev->name); kfree_skb(skb); return -ENETDOWN; } else { /* Recursion is detected! It is possible, unfortunately */ if (net_ratelimit()) printk(KERN_DEBUG "Dead loop on virtual device %s, fix it urgently!\n", dev->name); } } spin_unlock_bh(&dev->queue_lock); kfree_skb(skb); return -ENETDOWN; } /*======================================================================= Receiver rotutines =======================================================================*/ int netdev_dropping = 0; int netdev_max_backlog = 300; atomic_t netdev_rx_dropped; #ifdef CONFIG_NET_HW_FLOWCONTROL int netdev_throttle_events; static unsigned long netdev_fc_mask = 1; unsigned long netdev_fc_xoff = 0; spinlock_t netdev_fc_lock = SPIN_LOCK_UNLOCKED; static struct { void (*stimul)(struct net_device *); struct net_device *dev; } netdev_fc_slots[32]; int netdev_register_fc(struct net_device *dev, void (*stimul)(struct net_device *dev)) { int bit = 0; unsigned long flags; spin_lock_irqsave(&netdev_fc_lock, flags); if (netdev_fc_mask != ~0UL) { bit = ffz(netdev_fc_mask); netdev_fc_slots[bit].stimul = stimul; netdev_fc_slots[bit].dev = dev; set_bit(bit, &netdev_fc_mask); clear_bit(bit, &netdev_fc_xoff); } spin_unlock_irqrestore(&netdev_fc_lock, flags); return bit; } void netdev_unregister_fc(int bit) { unsigned long flags; spin_lock_irqsave(&netdev_fc_lock, flags); if (bit > 0) { netdev_fc_slots[bit].stimul = NULL; netdev_fc_slots[bit].dev = NULL; clear_bit(bit, &netdev_fc_mask); clear_bit(bit, &netdev_fc_xoff); } spin_unlock_irqrestore(&netdev_fc_lock, flags); } static void netdev_wakeup(void) { unsigned long xoff; spin_lock_irq(&netdev_fc_lock); xoff = netdev_fc_xoff; netdev_fc_xoff = 0; netdev_dropping = 0; netdev_throttle_events++; while (xoff) { int i = ffz(~xoff); xoff &= ~(1<<i); netdev_fc_slots[i].stimul(netdev_fc_slots[i].dev); } spin_unlock_irq(&netdev_fc_lock); } #endif static void dev_clear_backlog(struct net_device *dev) { struct sk_buff_head garbage; /* * * Let now clear backlog queue. -AS * */ skb_queue_head_init(&garbage); spin_lock_irq(&backlog.lock); if (backlog.qlen) { struct sk_buff *prev, *curr; curr = backlog.next; while (curr != (struct sk_buff *)(&backlog)) { curr=curr->next; if (curr->prev->dev == dev) { prev = curr->prev; __skb_unlink(prev, &backlog); __skb_queue_tail(&garbage, prev); } } } spin_unlock_irq(&backlog.lock); if (garbage.qlen) { #ifdef CONFIG_NET_HW_FLOWCONTROL if (netdev_dropping) netdev_wakeup(); #else netdev_dropping = 0; #endif skb_queue_purge(&garbage); } } /* * Receive a packet from a device driver and queue it for the upper * (protocol) levels. It always succeeds. */ void netif_rx(struct sk_buff *skb) { if(skb->stamp.tv_sec==0) get_fast_time(&skb->stamp); /* The code is rearranged so that the path is the most short when CPU is congested, but is still operating. */ if (backlog.qlen <= netdev_max_backlog) { if (backlog.qlen) { if (netdev_dropping == 0) { if (skb->rx_dev) dev_put(skb->rx_dev); skb->rx_dev = skb->dev; dev_hold(skb->rx_dev); skb_queue_tail(&backlog,skb); mark_bh(NET_BH); return; } atomic_inc(&netdev_rx_dropped); kfree_skb(skb); return; } #ifdef CONFIG_NET_HW_FLOWCONTROL if (netdev_dropping) netdev_wakeup(); #else netdev_dropping = 0; #endif if (skb->rx_dev) dev_put(skb->rx_dev); skb->rx_dev = skb->dev; dev_hold(skb->rx_dev); skb_queue_tail(&backlog,skb); mark_bh(NET_BH); return; } netdev_dropping = 1; atomic_inc(&netdev_rx_dropped); kfree_skb(skb); } #ifdef CONFIG_BRIDGE static inline void handle_bridge(struct sk_buff *skb, unsigned short type) { if (br_stats.flags & BR_UP && br_protocol_ok(ntohs(type))) { /* * We pass the bridge a complete frame. This means * recovering the MAC header first. */ int offset; skb=skb_clone(skb, GFP_ATOMIC); if(skb==NULL) return; offset=skb->data-skb->mac.raw; skb_push(skb,offset); /* Put header back on for bridge */ if(br_receive_frame(skb)) return; kfree_skb(skb); } return; } #endif /* * When we are called the queue is ready to grab, the interrupts are * on and hardware can interrupt and queue to the receive queue as we * run with no problems. * This is run as a bottom half after an interrupt handler that does * mark_bh(NET_BH); */ void net_bh(void) { struct packet_type *ptype; struct packet_type *pt_prev; unsigned short type; unsigned long start_time = jiffies; NET_PROFILE_ENTER(net_bh); /* * Can we send anything now? We want to clear the * decks for any more sends that get done as we * process the input. This also minimises the * latency on a transmit interrupt bh. */ if (qdisc_pending()) qdisc_run_queues(); /* * Any data left to process. This may occur because a * mark_bh() is done after we empty the queue including * that from the device which does a mark_bh() just after */ /* * While the queue is not empty.. * * Note that the queue never shrinks due to * an interrupt, so we can do this test without * disabling interrupts. */ while (!skb_queue_empty(&backlog)) { struct sk_buff * skb; /* Give chance to other bottom halves to run */ if (jiffies - start_time > 1) goto net_bh_break; /* * We have a packet. Therefore the queue has shrunk */ skb = skb_dequeue(&backlog); #ifdef CONFIG_NET_FASTROUTE if (skb->pkt_type == PACKET_FASTROUTE) { dev_queue_xmit(skb); continue; } #endif /* * Bump the pointer to the next structure. * * On entry to the protocol layer. skb->data and * skb->nh.raw point to the MAC and encapsulated data */ /* XXX until we figure out every place to modify.. */ skb->h.raw = skb->nh.raw = skb->data; if (skb->mac.raw < skb->head || skb->mac.raw > skb->data) { printk(KERN_CRIT "%s: wrong mac.raw ptr, proto=%04x\n", skb->dev->name, skb->protocol); kfree_skb(skb); continue; } /* * Fetch the packet protocol ID. */ type = skb->protocol; #ifdef CONFIG_BRIDGE /* * If we are bridging then pass the frame up to the * bridging code (if this protocol is to be bridged). * If it is bridged then move on */ handle_bridge(skb, type); #endif /* * We got a packet ID. Now loop over the "known protocols" * list. There are two lists. The ptype_all list of taps (normally empty) * and the main protocol list which is hashed perfectly for normal protocols. */ pt_prev = NULL; read_lock(&ptype_lock); for (ptype = ptype_all; ptype!=NULL; ptype=ptype->next) { if (!ptype->dev || ptype->dev == skb->dev) { if(pt_prev) { struct sk_buff *skb2; if (pt_prev->data == NULL) skb2 = skb_clone(skb, GFP_ATOMIC); else { skb2 = skb; atomic_inc(&skb2->users); } if(skb2) pt_prev->func(skb2, skb->dev, pt_prev); } pt_prev=ptype; } } for (ptype = ptype_base[ntohs(type)&15]; ptype != NULL; ptype = ptype->next) { if (ptype->type == type && (!ptype->dev || ptype->dev==skb->dev)) { /* * We already have a match queued. Deliver * to it and then remember the new match */ if(pt_prev) { struct sk_buff *skb2; if (pt_prev->data == NULL) skb2 = skb_clone(skb, GFP_ATOMIC); else { skb2 = skb; atomic_inc(&skb2->users); } /* * Kick the protocol handler. This should be fast * and efficient code. */ if(skb2) pt_prev->func(skb2, skb->dev, pt_prev); } /* Remember the current last to do */ pt_prev=ptype; } } /* End of protocol list loop */ /* * Is there a last item to send to ? */ if(pt_prev) pt_prev->func(skb, skb->dev, pt_prev); /* * Has an unknown packet has been received ? */ else { kfree_skb(skb); } read_unlock(&ptype_lock); } /* End of queue loop */ /* * We have emptied the queue */ /* * One last output flush. */ if (qdisc_pending()) qdisc_run_queues(); #ifdef CONFIG_NET_HW_FLOWCONTROL if (netdev_dropping) netdev_wakeup(); #else netdev_dropping = 0; #endif NET_PROFILE_LEAVE(net_bh); return; net_bh_break: mark_bh(NET_BH); NET_PROFILE_LEAVE(net_bh); return; } /* Protocol dependent address dumping routines */ static gifconf_func_t * gifconf_list [NPROTO]; int register_gifconf(unsigned int family, gifconf_func_t * gifconf) { if (family>=NPROTO) return -EINVAL; gifconf_list[family] = gifconf; return 0; } /* * Map an interface index to its name (SIOCGIFNAME) */ /* * We need this ioctl for efficient implementation of the * if_indextoname() function required by the IPv6 API. Without * it, we would have to search all the interfaces to find a * match. --pb */ static int dev_ifname(struct ifreq *arg) { struct net_device *dev; struct ifreq ifr; /* * Fetch the caller's info block. */ if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) return -EFAULT; read_lock(&dev_base_lock); dev = __dev_get_by_index(ifr.ifr_ifindex); if (!dev) { read_unlock(&dev_base_lock); return -ENODEV; } strcpy(ifr.ifr_name, dev->name); read_unlock(&dev_base_lock); if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) return -EFAULT; return 0; } /* * Perform a SIOCGIFCONF call. This structure will change * size eventually, and there is nothing I can do about it. * Thus we will need a 'compatibility mode'. */ static int dev_ifconf(char *arg) { struct ifconf ifc; struct net_device *dev; char *pos; int len; int total; int i; /* * Fetch the caller's info block. */ if (copy_from_user(&ifc, arg, sizeof(struct ifconf))) return -EFAULT; pos = ifc.ifc_buf; len = ifc.ifc_len; /* * Loop over the interfaces, and write an info block for each. */ total = 0; for (dev = dev_base; dev != NULL; dev = dev->next) { for (i=0; i<NPROTO; i++) { if (gifconf_list[i]) { int done; if (pos==NULL) { done = gifconf_list[i](dev, NULL, 0); } else { done = gifconf_list[i](dev, pos+total, len-total); } if (done<0) { return -EFAULT; } total += done; } } } /* * All done. Write the updated control block back to the caller. */ ifc.ifc_len = total; if (copy_to_user(arg, &ifc, sizeof(struct ifconf))) return -EFAULT; /* * Both BSD and Solaris return 0 here, so we do too. */ return 0; } /* * This is invoked by the /proc filesystem handler to display a device * in detail. */ #ifdef CONFIG_PROC_FS static int sprintf_stats(char *buffer, struct net_device *dev) { struct net_device_stats *stats = (dev->get_stats ? dev->get_stats(dev): NULL); int size; if (stats) size = sprintf(buffer, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu %8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n", dev->name, stats->rx_bytes, stats->rx_packets, stats->rx_errors, stats->rx_dropped + stats->rx_missed_errors, stats->rx_fifo_errors, stats->rx_length_errors + stats->rx_over_errors + stats->rx_crc_errors + stats->rx_frame_errors, stats->rx_compressed, stats->multicast, stats->tx_bytes, stats->tx_packets, stats->tx_errors, stats->tx_dropped, stats->tx_fifo_errors, stats->collisions, stats->tx_carrier_errors + stats->tx_aborted_errors + stats->tx_window_errors + stats->tx_heartbeat_errors, stats->tx_compressed); else size = sprintf(buffer, "%6s: No statistics available.\n", dev->name); return size; } /* * Called from the PROCfs module. This now uses the new arbitrary sized /proc/net interface * to create /proc/net/dev */ static int dev_get_info(char *buffer, char **start, off_t offset, int length) { int len=0; off_t begin=0; off_t pos=0; int size; struct net_device *dev; size = sprintf(buffer, "Inter-| Receive | Transmit\n" " face |bytes packets errs drop fifo frame compressed multicast|bytes packets errs drop fifo colls carrier compressed\n"); pos+=size; len+=size; read_lock(&dev_base_lock); for (dev = dev_base; dev != NULL; dev = dev->next) { size = sprintf_stats(buffer+len, dev); len+=size; pos=begin+len; if(pos<offset) { len=0; begin=pos; } if(pos>offset+length) break; } read_unlock(&dev_base_lock); *start=buffer+(offset-begin); /* Start of wanted data */ len-=(offset-begin); /* Start slop */ if(len>length) len=length; /* Ending slop */ if (len<0) len=0; return len; } static int dev_proc_stats(char *buffer, char **start, off_t offset, int length, int *eof, void *data) { int len; len = sprintf(buffer, "%08x %08x %08x %08x %08x\n", atomic_read(&netdev_rx_dropped), #ifdef CONFIG_NET_HW_FLOWCONTROL netdev_throttle_events, #else 0, #endif #ifdef CONFIG_NET_FASTROUTE dev_fastroute_stat.hits, dev_fastroute_stat.succeed, dev_fastroute_stat.deferred #else 0, 0, 0 #endif ); len -= offset; if (len > length) len = length; if(len < 0) len = 0; *start = buffer + offset; *eof = 1; return len; } #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_NET_RADIO #ifdef CONFIG_PROC_FS /* * Print one entry of /proc/net/wireless * This is a clone of /proc/net/dev (just above) */ static int sprintf_wireless_stats(char *buffer, struct net_device *dev) { /* Get stats from the driver */ struct iw_statistics *stats = (dev->get_wireless_stats ? dev->get_wireless_stats(dev) : (struct iw_statistics *) NULL); int size; if(stats != (struct iw_statistics *) NULL) size = sprintf(buffer, "%6s: %02x %3d%c %3d%c %3d%c %5d %5d %5d\n", dev->name, stats->status, stats->qual.qual, stats->qual.updated & 1 ? '.' : ' ', stats->qual.level, stats->qual.updated & 2 ? '.' : ' ', stats->qual.noise, stats->qual.updated & 4 ? '.' : ' ', stats->discard.nwid, stats->discard.code, stats->discard.misc); else size = 0; return size; } /* * Print info for /proc/net/wireless (print all entries) * This is a clone of /proc/net/dev (just above) */ static int dev_get_wireless_info(char * buffer, char **start, off_t offset, int length) { int len = 0; off_t begin = 0; off_t pos = 0; int size; struct net_device * dev; size = sprintf(buffer, "Inter-|sta| Quality | Discarded packets\n" " face |tus|link level noise| nwid crypt misc\n"); pos+=size; len+=size; read_lock(&dev_base_lock); for(dev = dev_base; dev != NULL; dev = dev->next) { size = sprintf_wireless_stats(buffer+len, dev); len+=size; pos=begin+len; if(pos < offset) { len=0; begin=pos; } if(pos > offset + length) break; } read_unlock(&dev_base_lock); *start = buffer + (offset - begin); /* Start of wanted data */ len -= (offset - begin); /* Start slop */ if(len > length) len = length; /* Ending slop */ if (len<0) len=0; return len; } #endif /* CONFIG_PROC_FS */ #endif /* CONFIG_NET_RADIO */ void dev_set_promiscuity(struct net_device *dev, int inc) { unsigned short old_flags = dev->flags; dev->flags |= IFF_PROMISC; if ((dev->promiscuity += inc) == 0) dev->flags &= ~IFF_PROMISC; if (dev->flags^old_flags) { #ifdef CONFIG_NET_FASTROUTE if (dev->flags&IFF_PROMISC) { netdev_fastroute_obstacles++; dev_clear_fastroute(dev); } else netdev_fastroute_obstacles--; #endif dev_mc_upload(dev); printk(KERN_INFO "device %s %s promiscuous mode\n", dev->name, (dev->flags&IFF_PROMISC) ? "entered" : "left"); } } void dev_set_allmulti(struct net_device *dev, int inc) { unsigned short old_flags = dev->flags; dev->flags |= IFF_ALLMULTI; if ((dev->allmulti += inc) == 0) dev->flags &= ~IFF_ALLMULTI; if (dev->flags^old_flags) dev_mc_upload(dev); } int dev_change_flags(struct net_device *dev, unsigned flags) { int ret; int old_flags = dev->flags; /* * Set the flags on our device. */ dev->flags = (flags & (IFF_DEBUG|IFF_NOTRAILERS|IFF_RUNNING|IFF_NOARP| IFF_SLAVE|IFF_MASTER|IFF_DYNAMIC| IFF_MULTICAST|IFF_PORTSEL|IFF_AUTOMEDIA)) | (dev->flags & (IFF_UP|IFF_VOLATILE|IFF_PROMISC|IFF_ALLMULTI)); /* * Load in the correct multicast list now the flags have changed. */ dev_mc_upload(dev); /* * Have we downed the interface. We handle IFF_UP ourselves * according to user attempts to set it, rather than blindly * setting it. */ ret = 0; if ((old_flags^flags)&IFF_UP) /* Bit is different ? */ { ret = ((old_flags & IFF_UP) ? dev_close : dev_open)(dev); if (ret == 0) dev_mc_upload(dev); } if (dev->flags&IFF_UP && ((old_flags^dev->flags)&~(IFF_UP|IFF_RUNNING|IFF_PROMISC|IFF_ALLMULTI|IFF_VOLATILE))) notifier_call_chain(&netdev_chain, NETDEV_CHANGE, dev); if ((flags^dev->gflags)&IFF_PROMISC) { int inc = (flags&IFF_PROMISC) ? +1 : -1; dev->gflags ^= IFF_PROMISC; dev_set_promiscuity(dev, inc); } /* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI is important. Some (broken) drivers set IFF_PROMISC, when IFF_ALLMULTI is requested not asking us and not reporting. */ if ((flags^dev->gflags)&IFF_ALLMULTI) { int inc = (flags&IFF_ALLMULTI) ? +1 : -1; dev->gflags ^= IFF_ALLMULTI; dev_set_allmulti(dev, inc); } return ret; } /* * Perform the SIOCxIFxxx calls. */ static int dev_ifsioc(struct ifreq *ifr, unsigned int cmd) { struct net_device *dev; int err; if ((dev = __dev_get_by_name(ifr->ifr_name)) == NULL) return -ENODEV; switch(cmd) { case SIOCGIFFLAGS: /* Get interface flags */ ifr->ifr_flags = (dev->flags&~(IFF_PROMISC|IFF_ALLMULTI)) |(dev->gflags&(IFF_PROMISC|IFF_ALLMULTI)); return 0; case SIOCSIFFLAGS: /* Set interface flags */ return dev_change_flags(dev, ifr->ifr_flags); case SIOCGIFMETRIC: /* Get the metric on the interface (currently unused) */ ifr->ifr_metric = 0; return 0; case SIOCSIFMETRIC: /* Set the metric on the interface (currently unused) */ return -EOPNOTSUPP; case SIOCGIFMTU: /* Get the MTU of a device */ ifr->ifr_mtu = dev->mtu; return 0; case SIOCSIFMTU: /* Set the MTU of a device */ if (ifr->ifr_mtu == dev->mtu) return 0; /* * MTU must be positive. */ if (ifr->ifr_mtu<0) return -EINVAL; if (dev->change_mtu) err = dev->change_mtu(dev, ifr->ifr_mtu); else { dev->mtu = ifr->ifr_mtu; err = 0; } if (!err && dev->flags&IFF_UP) notifier_call_chain(&netdev_chain, NETDEV_CHANGEMTU, dev); return err; case SIOCGIFHWADDR: memcpy(ifr->ifr_hwaddr.sa_data,dev->dev_addr, MAX_ADDR_LEN); ifr->ifr_hwaddr.sa_family=dev->type; return 0; case SIOCSIFHWADDR: if(dev->set_mac_address==NULL) return -EOPNOTSUPP; if(ifr->ifr_hwaddr.sa_family!=dev->type) return -EINVAL; err=dev->set_mac_address(dev,&ifr->ifr_hwaddr); if (!err) notifier_call_chain(&netdev_chain, NETDEV_CHANGEADDR, dev); return err; case SIOCSIFHWBROADCAST: if(ifr->ifr_hwaddr.sa_family!=dev->type) return -EINVAL; memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, MAX_ADDR_LEN); notifier_call_chain(&netdev_chain, NETDEV_CHANGEADDR, dev); return 0; case SIOCGIFMAP: ifr->ifr_map.mem_start=dev->mem_start; ifr->ifr_map.mem_end=dev->mem_end; ifr->ifr_map.base_addr=dev->base_addr; ifr->ifr_map.irq=dev->irq; ifr->ifr_map.dma=dev->dma; ifr->ifr_map.port=dev->if_port; return 0; case SIOCSIFMAP: if (dev->set_config) return dev->set_config(dev,&ifr->ifr_map); return -EOPNOTSUPP; case SIOCADDMULTI: if(dev->set_multicast_list==NULL || ifr->ifr_hwaddr.sa_family!=AF_UNSPEC) return -EINVAL; dev_mc_add(dev,ifr->ifr_hwaddr.sa_data, dev->addr_len, 1); return 0; case SIOCDELMULTI: if(dev->set_multicast_list==NULL || ifr->ifr_hwaddr.sa_family!=AF_UNSPEC) return -EINVAL; dev_mc_delete(dev,ifr->ifr_hwaddr.sa_data,dev->addr_len, 1); return 0; case SIOCGIFINDEX: ifr->ifr_ifindex = dev->ifindex; return 0; case SIOCGIFTXQLEN: ifr->ifr_qlen = dev->tx_queue_len; return 0; case SIOCSIFTXQLEN: if(ifr->ifr_qlen<0) return -EINVAL; dev->tx_queue_len = ifr->ifr_qlen; return 0; case SIOCSIFNAME: if (dev->flags&IFF_UP) return -EBUSY; if (__dev_get_by_name(ifr->ifr_newname)) return -EEXIST; memcpy(dev->name, ifr->ifr_newname, IFNAMSIZ); dev->name[IFNAMSIZ-1] = 0; notifier_call_chain(&netdev_chain, NETDEV_CHANGENAME, dev); return 0; /* * Unknown or private ioctl */ default: if(cmd >= SIOCDEVPRIVATE && cmd <= SIOCDEVPRIVATE + 15) { if (dev->do_ioctl) return dev->do_ioctl(dev, ifr, cmd); return -EOPNOTSUPP; } #ifdef CONFIG_NET_RADIO if(cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) { if (dev->do_ioctl) return dev->do_ioctl(dev, ifr, cmd); return -EOPNOTSUPP; } #endif /* CONFIG_NET_RADIO */ } return -EINVAL; } /* * This function handles all "interface"-type I/O control requests. The actual * 'doing' part of this is dev_ifsioc above. */ int dev_ioctl(unsigned int cmd, void *arg) { struct ifreq ifr; int ret; char *colon; /* One special case: SIOCGIFCONF takes ifconf argument and requires shared lock, because it sleeps writing to user space. */ if (cmd == SIOCGIFCONF) { rtnl_shlock(); ret = dev_ifconf((char *) arg); rtnl_shunlock(); return ret; } if (cmd == SIOCGIFNAME) { return dev_ifname((struct ifreq *)arg); } if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) return -EFAULT; ifr.ifr_name[IFNAMSIZ-1] = 0; colon = strchr(ifr.ifr_name, ':'); if (colon) *colon = 0; /* * See which interface the caller is talking about. */ switch(cmd) { /* * These ioctl calls: * - can be done by all. * - atomic and do not require locking. * - return a value */ case SIOCGIFFLAGS: case SIOCGIFMETRIC: case SIOCGIFMTU: case SIOCGIFHWADDR: case SIOCGIFSLAVE: case SIOCGIFMAP: case SIOCGIFINDEX: case SIOCGIFTXQLEN: dev_load(ifr.ifr_name); read_lock(&dev_base_lock); ret = dev_ifsioc(&ifr, cmd); read_unlock(&dev_base_lock); if (!ret) { if (colon) *colon = ':'; if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) return -EFAULT; } return ret; /* * These ioctl calls: * - require superuser power. * - require strict serialization. * - do not return a value */ case SIOCSIFFLAGS: case SIOCSIFMETRIC: case SIOCSIFMTU: case SIOCSIFMAP: case SIOCSIFHWADDR: case SIOCSIFSLAVE: case SIOCADDMULTI: case SIOCDELMULTI: case SIOCSIFHWBROADCAST: case SIOCSIFTXQLEN: case SIOCSIFNAME: if (!capable(CAP_NET_ADMIN)) return -EPERM; dev_load(ifr.ifr_name); rtnl_lock(); ret = dev_ifsioc(&ifr, cmd); rtnl_unlock(); return ret; case SIOCGIFMEM: /* Get the per device memory space. We can add this but currently do not support it */ case SIOCSIFMEM: /* Set the per device memory buffer space. Not applicable in our case */ case SIOCSIFLINK: return -EINVAL; /* * Unknown or private ioctl. */ default: if (cmd >= SIOCDEVPRIVATE && cmd <= SIOCDEVPRIVATE + 15) { dev_load(ifr.ifr_name); rtnl_lock(); ret = dev_ifsioc(&ifr, cmd); rtnl_unlock(); if (!ret && copy_to_user(arg, &ifr, sizeof(struct ifreq))) return -EFAULT; return ret; } #ifdef CONFIG_NET_RADIO if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) { dev_load(ifr.ifr_name); if (IW_IS_SET(cmd)) { if (!suser()) return -EPERM; } rtnl_lock(); ret = dev_ifsioc(&ifr, cmd); rtnl_unlock(); if (!ret && IW_IS_GET(cmd) && copy_to_user(arg, &ifr, sizeof(struct ifreq))) return -EFAULT; return ret; } #endif /* CONFIG_NET_RADIO */ return -EINVAL; } } int dev_new_index(void) { static int ifindex; for (;;) { if (++ifindex <= 0) ifindex=1; if (__dev_get_by_index(ifindex) == NULL) return ifindex; } } static int dev_boot_phase = 1; int register_netdevice(struct net_device *dev) { struct net_device *d, **dp; spin_lock_init(&dev->queue_lock); spin_lock_init(&dev->xmit_lock); dev->xmit_lock_owner = -1; #ifdef CONFIG_NET_FASTROUTE dev->fastpath_lock=RW_LOCK_UNLOCKED; #endif if (dev_boot_phase) { /* This is NOT bug, but I am not sure, that all the devices, initialized before netdev module is started are sane. Now they are chained to device boot list and probed later. If a module is initialized before netdev, but assumes that dev->init is really called by register_netdev(), it will fail. So that this message should be printed for a while. */ printk(KERN_INFO "early initialization of device %s is deferred\n", dev->name); /* Check for existence, and append to tail of chain */ for (dp=&dev_base; (d=*dp) != NULL; dp=&d->next) { if (d == dev || strcmp(d->name, dev->name) == 0) { return -EEXIST; } } dev->next = NULL; write_lock_bh(&dev_base_lock); *dp = dev; dev_hold(dev); write_unlock_bh(&dev_base_lock); return 0; } dev->iflink = -1; /* Init, if this function is available */ if (dev->init && dev->init(dev) != 0) return -EIO; dev->ifindex = dev_new_index(); if (dev->iflink == -1) dev->iflink = dev->ifindex; /* Check for existence, and append to tail of chain */ for (dp=&dev_base; (d=*dp) != NULL; dp=&d->next) { if (d == dev || strcmp(d->name, dev->name) == 0) { return -EEXIST; } } /* * nil rebuild_header routine, * that should be never called and used as just bug trap. */ if (dev->rebuild_header == NULL) dev->rebuild_header = default_rebuild_header; dev->next = NULL; dev_init_scheduler(dev); write_lock_bh(&dev_base_lock); *dp = dev; dev_hold(dev); dev->deadbeaf = 0; write_unlock_bh(&dev_base_lock); /* Notify protocols, that a new device appeared. */ notifier_call_chain(&netdev_chain, NETDEV_REGISTER, dev); return 0; } int netdev_finish_unregister(struct net_device *dev) { BUG_TRAP(dev->ip_ptr==NULL); BUG_TRAP(dev->ip6_ptr==NULL); BUG_TRAP(dev->dn_ptr==NULL); if (!dev->deadbeaf) { printk("Freeing alive device %p, %s\n", dev, dev->name); return 0; } #ifdef NET_REFCNT_DEBUG printk(KERN_DEBUG "netdev_finish_unregister: %s%s.\n", dev->name, dev->new_style?"":", old style"); #endif if (dev->destructor) dev->destructor(dev); if (dev->new_style) kfree(dev); return 0; } int unregister_netdevice(struct net_device *dev) { unsigned long now; struct net_device *d, **dp; /* If device is running, close it first. */ if (dev->flags & IFF_UP) dev_close(dev); BUG_TRAP(dev->deadbeaf==0); dev->deadbeaf = 1; /* And unlink it from device chain. */ for (dp = &dev_base; (d=*dp) != NULL; dp=&d->next) { if (d == dev) { write_lock_bh(&dev_base_lock); *dp = d->next; write_unlock_bh(&dev_base_lock); break; } } if (d == NULL) { printk(KERN_DEBUG "unregister_netdevice: device %s/%p never was registered\n", dev->name, dev); return -ENODEV; } if (dev_boot_phase == 0) { #ifdef CONFIG_NET_FASTROUTE dev_clear_fastroute(dev); #endif /* Shutdown queueing discipline. */ dev_shutdown(dev); /* Notify protocols, that we are about to destroy this device. They should clean all the things. */ notifier_call_chain(&netdev_chain, NETDEV_UNREGISTER, dev); /* * Flush the multicast chain */ dev_mc_discard(dev); } if (dev->uninit) dev->uninit(dev); if (dev->new_style) { #ifdef NET_REFCNT_DEBUG if (atomic_read(&dev->refcnt) != 1) printk(KERN_DEBUG "unregister_netdevice: holding %s refcnt=%d\n", dev->name, atomic_read(&dev->refcnt)-1); #endif dev_put(dev); return 0; } /* Last reference is our one */ if (atomic_read(&dev->refcnt) == 1) { dev_put(dev); return 0; } #ifdef NET_REFCNT_DEBUG printk("unregister_netdevice: waiting %s refcnt=%d\n", dev->name, atomic_read(&dev->refcnt)); #endif /* EXPLANATION. If dev->refcnt is not 1 now (1 is our own reference) it means that someone in the kernel still has reference to this device and we cannot release it. "New style" devices have destructors, hence we can return from this function and destructor will do all the work later. "Old style" devices expect that device is free of any references upon exit from this function. WE CANNOT MAKE such release without delay. Note that it is not new feature. Referencing devices after they are released occured in 2.0 and 2.2. Now we just can know about each fact of illegal usage. So, we linger for 10*HZ (it is an arbitrary number) After 1 second, we start to rebroadcast unregister notifications in hope that careless clients will release the device. If timeout expired, we have no choice how to cross fingers and return. Real alternative would be block here forever and we will make it eventually, when all peaceful citizens will be notified and repaired. */ now = jiffies; while (atomic_read(&dev->refcnt) != 1) { if ((jiffies - now) > 1*HZ) { /* Rebroadcast unregister notification */ notifier_call_chain(&netdev_chain, NETDEV_UNREGISTER, dev); } current->state = TASK_INTERRUPTIBLE; schedule_timeout(HZ/4); current->state = TASK_RUNNING; if ((jiffies - now) > 10*HZ) break; } if (atomic_read(&dev->refcnt) != 1) printk("unregister_netdevice: Old style device %s leaked(refcnt=%d). Wait for crash.\n", dev->name, atomic_read(&dev->refcnt)-1); dev_put(dev); return 0; } /* * Initialize the DEV module. At boot time this walks the device list and * unhooks any devices that fail to initialise (normally hardware not * present) and leaves us with a valid list of present and active devices. * */ extern void net_device_init(void); extern void ip_auto_config(void); int __init net_dev_init(void) { struct net_device *dev, **dp; #ifdef CONFIG_NET_SCHED pktsched_init(); #endif /* * Initialise the packet receive queue. */ skb_queue_head_init(&backlog); /* * The bridge has to be up before the devices */ #ifdef CONFIG_BRIDGE br_init(); #endif #ifdef CONFIG_NET_PROFILE net_profile_init(); NET_PROFILE_REGISTER(dev_queue_xmit); NET_PROFILE_REGISTER(net_bh); #if 0 NET_PROFILE_REGISTER(net_bh_skb); #endif #endif /* * Add the devices. * If the call to dev->init fails, the dev is removed * from the chain disconnecting the device until the * next reboot. * * NB At boot phase networking is dead. No locking is required. * But we still preserve dev_base_lock for sanity. */ dp = &dev_base; while ((dev = *dp) != NULL) { spin_lock_init(&dev->queue_lock); spin_lock_init(&dev->xmit_lock); dev->xmit_lock_owner = -1; dev->iflink = -1; dev_hold(dev); /* * We can allocate the name ahead of time. If the * init fails the name will be reissued correctly. */ if (strchr(dev->name, '%')) dev_alloc_name(dev, dev->name); if (dev->init && dev->init(dev)) { /* * It failed to come up. Unhook it. */ write_lock_bh(&dev_base_lock); *dp = dev->next; dev->deadbeaf = 1; write_unlock_bh(&dev_base_lock); dev_put(dev); } else { dp = &dev->next; dev->ifindex = dev_new_index(); if (dev->iflink == -1) dev->iflink = dev->ifindex; if (dev->rebuild_header == NULL) dev->rebuild_header = default_rebuild_header; dev_init_scheduler(dev); } } #ifdef CONFIG_PROC_FS proc_net_create("dev", 0, dev_get_info); create_proc_read_entry("net/dev_stat", 0, 0, dev_proc_stats, NULL); #ifdef CONFIG_NET_RADIO proc_net_create("wireless", 0, dev_get_wireless_info); #endif /* CONFIG_NET_RADIO */ #endif /* CONFIG_PROC_FS */ init_bh(NET_BH, net_bh); dev_boot_phase = 0; dst_init(); dev_mcast_init(); /* * Initialise network devices */ net_device_init(); #ifdef CONFIG_IP_PNP ip_auto_config(); #endif return 0; } |