| 5 1 1 5 2 2 2 2 2 5 3 3 16 16 5 5 5 16 16 4 5 16 16 16 16 16 5 78 76 79 76 79 79 5 5 4 3 3 3 3 3 79 76 76 79 79 77 6 6 2 6 6 2 2 2 6 79 79 75 75 76 5 1 1 5 5 4 5 1 1 4 3 2 2 2 1 1 3 3 2 3 5 5 5 5 3 5 5 5 5 5 2 5 5 5 9 10 10 13 13 13 13 10 9 8 8 13 13 11 10 8 8 8 8 8 8 8 1 1 8 10 1 10 10 10 10 10 13 13 13 13 13 13 13 13 13 14 13 13 13 11 5 11 11 11 79 79 79 38 7 35 34 34 34 35 77 11 79 79 77 78 79 76 76 70 71 79 79 77 16 16 14 14 14 8 6 5 46 8 8 6 4 8 4 8 8 8 4 1 4 8 8 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 5 6 4 6 39 33 39 39 39 8 1 8 39 39 39 39 8 1 8 6 8 8 5 1 8 8 8 8 8 38 66 67 67 67 67 1 66 66 67 64 66 67 67 41 41 41 41 21 2 2 1 3 2 3 3 3 3 3 1 2 3 3 3 3 3 74 76 75 9 9 8 9 9 5 3 3 5 5 3 3 3 3 3 1 1 3 3 3 3 3 3 3 3 3 2 3 3 3 5 3 3 5 5 5 3 3 3 1 1 3 3 2 3 3 2 5 5 5 5 5 3 2 3 4 2 2 6 5 2 3 3 3 2 2 5 5 3 4 4 5 5 5 4 4 5 5 5 5 5 5 5 5 4 5 4 4 4 4 4 3 4 4 3 3 1 1 1 4 1 1 1 5 3 3 3 5 3 5 5 5 3 3 2 2 2 2 2 2 2 3 3 2 2 3 3 2 2 1 3 2 3 3 3 3 3 2 2 6 6 6 6 6 3 3 6 1 1 1 69 9 9 62 62 62 61 62 61 62 62 62 62 62 62 70 71 70 67 68 66 4 67 66 3 3 3 2 2 2 2 3 3 3 3 3 3 3 3 3 3 3 3 6 6 6 6 6 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. */ #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/buffer_head.h> #include <linux/blkdev.h> #include <linux/gfs2_ondisk.h> #include <linux/crc32.h> #include <linux/iomap.h> #include <linux/ktime.h> #include "gfs2.h" #include "incore.h" #include "bmap.h" #include "glock.h" #include "inode.h" #include "meta_io.h" #include "quota.h" #include "rgrp.h" #include "log.h" #include "super.h" #include "trans.h" #include "dir.h" #include "util.h" #include "aops.h" #include "trace_gfs2.h" /* This doesn't need to be that large as max 64 bit pointers in a 4k * block is 512, so __u16 is fine for that. It saves stack space to * keep it small. */ struct metapath { struct buffer_head *mp_bh[GFS2_MAX_META_HEIGHT]; __u16 mp_list[GFS2_MAX_META_HEIGHT]; int mp_fheight; /* find_metapath height */ int mp_aheight; /* actual height (lookup height) */ }; static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length); /** * gfs2_unstuffer_folio - unstuff a stuffed inode into a block cached by a folio * @ip: the inode * @dibh: the dinode buffer * @block: the block number that was allocated * @folio: The folio. * * Returns: errno */ static int gfs2_unstuffer_folio(struct gfs2_inode *ip, struct buffer_head *dibh, u64 block, struct folio *folio) { struct inode *inode = &ip->i_inode; if (!folio_test_uptodate(folio)) { void *kaddr = kmap_local_folio(folio, 0); u64 dsize = i_size_read(inode); memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize); memset(kaddr + dsize, 0, folio_size(folio) - dsize); kunmap_local(kaddr); folio_mark_uptodate(folio); } if (gfs2_is_jdata(ip)) { struct buffer_head *bh = folio_buffers(folio); if (!bh) bh = create_empty_buffers(folio, BIT(inode->i_blkbits), BIT(BH_Uptodate)); if (!buffer_mapped(bh)) map_bh(bh, inode->i_sb, block); set_buffer_uptodate(bh); gfs2_trans_add_data(ip->i_gl, bh); } else { folio_mark_dirty(folio); gfs2_ordered_add_inode(ip); } return 0; } static int __gfs2_unstuff_inode(struct gfs2_inode *ip, struct folio *folio) { struct buffer_head *bh, *dibh; struct gfs2_dinode *di; u64 block = 0; int isdir = gfs2_is_dir(ip); int error; error = gfs2_meta_inode_buffer(ip, &dibh); if (error) return error; if (i_size_read(&ip->i_inode)) { /* Get a free block, fill it with the stuffed data, and write it out to disk */ unsigned int n = 1; error = gfs2_alloc_blocks(ip, &block, &n, 0); if (error) goto out_brelse; if (isdir) { gfs2_trans_remove_revoke(GFS2_SB(&ip->i_inode), block, 1); error = gfs2_dir_get_new_buffer(ip, block, &bh); if (error) goto out_brelse; gfs2_buffer_copy_tail(bh, sizeof(struct gfs2_meta_header), dibh, sizeof(struct gfs2_dinode)); brelse(bh); } else { error = gfs2_unstuffer_folio(ip, dibh, block, folio); if (error) goto out_brelse; } } /* Set up the pointer to the new block */ gfs2_trans_add_meta(ip->i_gl, dibh); di = (struct gfs2_dinode *)dibh->b_data; gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode)); if (i_size_read(&ip->i_inode)) { *(__be64 *)(di + 1) = cpu_to_be64(block); gfs2_add_inode_blocks(&ip->i_inode, 1); di->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode)); } ip->i_height = 1; di->di_height = cpu_to_be16(1); out_brelse: brelse(dibh); return error; } /** * gfs2_unstuff_dinode - Unstuff a dinode when the data has grown too big * @ip: The GFS2 inode to unstuff * * This routine unstuffs a dinode and returns it to a "normal" state such * that the height can be grown in the traditional way. * * Returns: errno */ int gfs2_unstuff_dinode(struct gfs2_inode *ip) { struct inode *inode = &ip->i_inode; struct folio *folio; int error; down_write(&ip->i_rw_mutex); folio = filemap_grab_folio(inode->i_mapping, 0); error = PTR_ERR(folio); if (IS_ERR(folio)) goto out; error = __gfs2_unstuff_inode(ip, folio); folio_unlock(folio); folio_put(folio); out: up_write(&ip->i_rw_mutex); return error; } /** * find_metapath - Find path through the metadata tree * @sdp: The superblock * @block: The disk block to look up * @mp: The metapath to return the result in * @height: The pre-calculated height of the metadata tree * * This routine returns a struct metapath structure that defines a path * through the metadata of inode "ip" to get to block "block". * * Example: * Given: "ip" is a height 3 file, "offset" is 101342453, and this is a * filesystem with a blocksize of 4096. * * find_metapath() would return a struct metapath structure set to: * mp_fheight = 3, mp_list[0] = 0, mp_list[1] = 48, and mp_list[2] = 165. * * That means that in order to get to the block containing the byte at * offset 101342453, we would load the indirect block pointed to by pointer * 0 in the dinode. We would then load the indirect block pointed to by * pointer 48 in that indirect block. We would then load the data block * pointed to by pointer 165 in that indirect block. * * ---------------------------------------- * | Dinode | | * | | 4| * | |0 1 2 3 4 5 9| * | | 6| * ---------------------------------------- * | * | * V * ---------------------------------------- * | Indirect Block | * | 5| * | 4 4 4 4 4 5 5 1| * |0 5 6 7 8 9 0 1 2| * ---------------------------------------- * | * | * V * ---------------------------------------- * | Indirect Block | * | 1 1 1 1 1 5| * | 6 6 6 6 6 1| * |0 3 4 5 6 7 2| * ---------------------------------------- * | * | * V * ---------------------------------------- * | Data block containing offset | * | 101342453 | * | | * | | * ---------------------------------------- * */ static void find_metapath(const struct gfs2_sbd *sdp, u64 block, struct metapath *mp, unsigned int height) { unsigned int i; mp->mp_fheight = height; for (i = height; i--;) mp->mp_list[i] = do_div(block, sdp->sd_inptrs); } static inline unsigned int metapath_branch_start(const struct metapath *mp) { if (mp->mp_list[0] == 0) return 2; return 1; } /** * metaptr1 - Return the first possible metadata pointer in a metapath buffer * @height: The metadata height (0 = dinode) * @mp: The metapath */ static inline __be64 *metaptr1(unsigned int height, const struct metapath *mp) { struct buffer_head *bh = mp->mp_bh[height]; if (height == 0) return ((__be64 *)(bh->b_data + sizeof(struct gfs2_dinode))); return ((__be64 *)(bh->b_data + sizeof(struct gfs2_meta_header))); } /** * metapointer - Return pointer to start of metadata in a buffer * @height: The metadata height (0 = dinode) * @mp: The metapath * * Return a pointer to the block number of the next height of the metadata * tree given a buffer containing the pointer to the current height of the * metadata tree. */ static inline __be64 *metapointer(unsigned int height, const struct metapath *mp) { __be64 *p = metaptr1(height, mp); return p + mp->mp_list[height]; } static inline const __be64 *metaend(unsigned int height, const struct metapath *mp) { const struct buffer_head *bh = mp->mp_bh[height]; return (const __be64 *)(bh->b_data + bh->b_size); } static void clone_metapath(struct metapath *clone, struct metapath *mp) { unsigned int hgt; *clone = *mp; for (hgt = 0; hgt < mp->mp_aheight; hgt++) get_bh(clone->mp_bh[hgt]); } static void gfs2_metapath_ra(struct gfs2_glock *gl, __be64 *start, __be64 *end) { const __be64 *t; for (t = start; t < end; t++) { struct buffer_head *rabh; if (!*t) continue; rabh = gfs2_getbuf(gl, be64_to_cpu(*t), CREATE); if (trylock_buffer(rabh)) { if (!buffer_uptodate(rabh)) { rabh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ | REQ_RAHEAD | REQ_META | REQ_PRIO, rabh); continue; } unlock_buffer(rabh); } brelse(rabh); } } static inline struct buffer_head * metapath_dibh(struct metapath *mp) { return mp->mp_bh[0]; } static int __fillup_metapath(struct gfs2_inode *ip, struct metapath *mp, unsigned int x, unsigned int h) { for (; x < h; x++) { __be64 *ptr = metapointer(x, mp); u64 dblock = be64_to_cpu(*ptr); int ret; if (!dblock) break; ret = gfs2_meta_buffer(ip, GFS2_METATYPE_IN, dblock, &mp->mp_bh[x + 1]); if (ret) return ret; } mp->mp_aheight = x + 1; return 0; } /** * lookup_metapath - Walk the metadata tree to a specific point * @ip: The inode * @mp: The metapath * * Assumes that the inode's buffer has already been looked up and * hooked onto mp->mp_bh[0] and that the metapath has been initialised * by find_metapath(). * * If this function encounters part of the tree which has not been * allocated, it returns the current height of the tree at the point * at which it found the unallocated block. Blocks which are found are * added to the mp->mp_bh[] list. * * Returns: error */ static int lookup_metapath(struct gfs2_inode *ip, struct metapath *mp) { return __fillup_metapath(ip, mp, 0, ip->i_height - 1); } /** * fillup_metapath - fill up buffers for the metadata path to a specific height * @ip: The inode * @mp: The metapath * @h: The height to which it should be mapped * * Similar to lookup_metapath, but does lookups for a range of heights * * Returns: error or the number of buffers filled */ static int fillup_metapath(struct gfs2_inode *ip, struct metapath *mp, int h) { unsigned int x = 0; int ret; if (h) { /* find the first buffer we need to look up. */ for (x = h - 1; x > 0; x--) { if (mp->mp_bh[x]) break; } } ret = __fillup_metapath(ip, mp, x, h); if (ret) return ret; return mp->mp_aheight - x - 1; } static sector_t metapath_to_block(struct gfs2_sbd *sdp, struct metapath *mp) { sector_t factor = 1, block = 0; int hgt; for (hgt = mp->mp_fheight - 1; hgt >= 0; hgt--) { if (hgt < mp->mp_aheight) block += mp->mp_list[hgt] * factor; factor *= sdp->sd_inptrs; } return block; } static void release_metapath(struct metapath *mp) { int i; for (i = 0; i < GFS2_MAX_META_HEIGHT; i++) { if (mp->mp_bh[i] == NULL) break; brelse(mp->mp_bh[i]); mp->mp_bh[i] = NULL; } } /** * gfs2_extent_length - Returns length of an extent of blocks * @bh: The metadata block * @ptr: Current position in @bh * @eob: Set to 1 if we hit "end of block" * * Returns: The length of the extent (minimum of one block) */ static inline unsigned int gfs2_extent_length(struct buffer_head *bh, __be64 *ptr, int *eob) { const __be64 *end = (__be64 *)(bh->b_data + bh->b_size); const __be64 *first = ptr; u64 d = be64_to_cpu(*ptr); *eob = 0; do { ptr++; if (ptr >= end) break; d++; } while(be64_to_cpu(*ptr) == d); if (ptr >= end) *eob = 1; return ptr - first; } enum walker_status { WALK_STOP, WALK_FOLLOW, WALK_CONTINUE }; /* * gfs2_metadata_walker - walk an indirect block * @mp: Metapath to indirect block * @ptrs: Number of pointers to look at * * When returning WALK_FOLLOW, the walker must update @mp to point at the right * indirect block to follow. */ typedef enum walker_status (*gfs2_metadata_walker)(struct metapath *mp, unsigned int ptrs); /* * gfs2_walk_metadata - walk a tree of indirect blocks * @inode: The inode * @mp: Starting point of walk * @max_len: Maximum number of blocks to walk * @walker: Called during the walk * * Returns 1 if the walk was stopped by @walker, 0 if we went past @max_len or * past the end of metadata, and a negative error code otherwise. */ static int gfs2_walk_metadata(struct inode *inode, struct metapath *mp, u64 max_len, gfs2_metadata_walker walker) { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); u64 factor = 1; unsigned int hgt; int ret; /* * The walk starts in the lowest allocated indirect block, which may be * before the position indicated by @mp. Adjust @max_len accordingly * to avoid a short walk. */ for (hgt = mp->mp_fheight - 1; hgt >= mp->mp_aheight; hgt--) { max_len += mp->mp_list[hgt] * factor; mp->mp_list[hgt] = 0; factor *= sdp->sd_inptrs; } for (;;) { u16 start = mp->mp_list[hgt]; enum walker_status status; unsigned int ptrs; u64 len; /* Walk indirect block. */ ptrs = (hgt >= 1 ? sdp->sd_inptrs : sdp->sd_diptrs) - start; len = ptrs * factor; if (len > max_len) ptrs = DIV_ROUND_UP_ULL(max_len, factor); status = walker(mp, ptrs); switch (status) { case WALK_STOP: return 1; case WALK_FOLLOW: BUG_ON(mp->mp_aheight == mp->mp_fheight); ptrs = mp->mp_list[hgt] - start; len = ptrs * factor; break; case WALK_CONTINUE: break; } if (len >= max_len) break; max_len -= len; if (status == WALK_FOLLOW) goto fill_up_metapath; lower_metapath: /* Decrease height of metapath. */ brelse(mp->mp_bh[hgt]); mp->mp_bh[hgt] = NULL; mp->mp_list[hgt] = 0; if (!hgt) break; hgt--; factor *= sdp->sd_inptrs; /* Advance in metadata tree. */ (mp->mp_list[hgt])++; if (hgt) { if (mp->mp_list[hgt] >= sdp->sd_inptrs) goto lower_metapath; } else { if (mp->mp_list[hgt] >= sdp->sd_diptrs) break; } fill_up_metapath: /* Increase height of metapath. */ ret = fillup_metapath(ip, mp, ip->i_height - 1); if (ret < 0) return ret; hgt += ret; for (; ret; ret--) do_div(factor, sdp->sd_inptrs); mp->mp_aheight = hgt + 1; } return 0; } static enum walker_status gfs2_hole_walker(struct metapath *mp, unsigned int ptrs) { const __be64 *start, *ptr, *end; unsigned int hgt; hgt = mp->mp_aheight - 1; start = metapointer(hgt, mp); end = start + ptrs; for (ptr = start; ptr < end; ptr++) { if (*ptr) { mp->mp_list[hgt] += ptr - start; if (mp->mp_aheight == mp->mp_fheight) return WALK_STOP; return WALK_FOLLOW; } } return WALK_CONTINUE; } /** * gfs2_hole_size - figure out the size of a hole * @inode: The inode * @lblock: The logical starting block number * @len: How far to look (in blocks) * @mp: The metapath at lblock * @iomap: The iomap to store the hole size in * * This function modifies @mp. * * Returns: errno on error */ static int gfs2_hole_size(struct inode *inode, sector_t lblock, u64 len, struct metapath *mp, struct iomap *iomap) { struct metapath clone; u64 hole_size; int ret; clone_metapath(&clone, mp); ret = gfs2_walk_metadata(inode, &clone, len, gfs2_hole_walker); if (ret < 0) goto out; if (ret == 1) hole_size = metapath_to_block(GFS2_SB(inode), &clone) - lblock; else hole_size = len; iomap->length = hole_size << inode->i_blkbits; ret = 0; out: release_metapath(&clone); return ret; } static inline void gfs2_indirect_init(struct metapath *mp, struct gfs2_glock *gl, unsigned int i, unsigned offset, u64 bn) { __be64 *ptr = (__be64 *)(mp->mp_bh[i - 1]->b_data + ((i > 1) ? sizeof(struct gfs2_meta_header) : sizeof(struct gfs2_dinode))); BUG_ON(i < 1); BUG_ON(mp->mp_bh[i] != NULL); mp->mp_bh[i] = gfs2_meta_new(gl, bn); gfs2_trans_add_meta(gl, mp->mp_bh[i]); gfs2_metatype_set(mp->mp_bh[i], GFS2_METATYPE_IN, GFS2_FORMAT_IN); gfs2_buffer_clear_tail(mp->mp_bh[i], sizeof(struct gfs2_meta_header)); ptr += offset; *ptr = cpu_to_be64(bn); } enum alloc_state { ALLOC_DATA = 0, ALLOC_GROW_DEPTH = 1, ALLOC_GROW_HEIGHT = 2, /* ALLOC_UNSTUFF = 3, TBD and rather complicated */ }; /** * __gfs2_iomap_alloc - Build a metadata tree of the requested height * @inode: The GFS2 inode * @iomap: The iomap structure * @mp: The metapath, with proper height information calculated * * In this routine we may have to alloc: * i) Indirect blocks to grow the metadata tree height * ii) Indirect blocks to fill in lower part of the metadata tree * iii) Data blocks * * This function is called after __gfs2_iomap_get, which works out the * total number of blocks which we need via gfs2_alloc_size. * * We then do the actual allocation asking for an extent at a time (if * enough contiguous free blocks are available, there will only be one * allocation request per call) and uses the state machine to initialise * the blocks in order. * * Right now, this function will allocate at most one indirect block * worth of data -- with a default block size of 4K, that's slightly * less than 2M. If this limitation is ever removed to allow huge * allocations, we would probably still want to limit the iomap size we * return to avoid stalling other tasks during huge writes; the next * iomap iteration would then find the blocks already allocated. * * Returns: errno on error */ static int __gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap, struct metapath *mp) { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); struct buffer_head *dibh = metapath_dibh(mp); u64 bn; unsigned n, i, blks, alloced = 0, iblks = 0, branch_start = 0; size_t dblks = iomap->length >> inode->i_blkbits; const unsigned end_of_metadata = mp->mp_fheight - 1; int ret; enum alloc_state state; __be64 *ptr; __be64 zero_bn = 0; BUG_ON(mp->mp_aheight < 1); BUG_ON(dibh == NULL); BUG_ON(dblks < 1); gfs2_trans_add_meta(ip->i_gl, dibh); down_write(&ip->i_rw_mutex); if (mp->mp_fheight == mp->mp_aheight) { /* Bottom indirect block exists */ state = ALLOC_DATA; } else { /* Need to allocate indirect blocks */ if (mp->mp_fheight == ip->i_height) { /* Writing into existing tree, extend tree down */ iblks = mp->mp_fheight - mp->mp_aheight; state = ALLOC_GROW_DEPTH; } else { /* Building up tree height */ state = ALLOC_GROW_HEIGHT; iblks = mp->mp_fheight - ip->i_height; branch_start = metapath_branch_start(mp); iblks += (mp->mp_fheight - branch_start); } } /* start of the second part of the function (state machine) */ blks = dblks + iblks; i = mp->mp_aheight; do { n = blks - alloced; ret = gfs2_alloc_blocks(ip, &bn, &n, 0); if (ret) goto out; alloced += n; if (state != ALLOC_DATA || gfs2_is_jdata(ip)) gfs2_trans_remove_revoke(sdp, bn, n); switch (state) { /* Growing height of tree */ case ALLOC_GROW_HEIGHT: if (i == 1) { ptr = (__be64 *)(dibh->b_data + sizeof(struct gfs2_dinode)); zero_bn = *ptr; } for (; i - 1 < mp->mp_fheight - ip->i_height && n > 0; i++, n--) gfs2_indirect_init(mp, ip->i_gl, i, 0, bn++); if (i - 1 == mp->mp_fheight - ip->i_height) { i--; gfs2_buffer_copy_tail(mp->mp_bh[i], sizeof(struct gfs2_meta_header), dibh, sizeof(struct gfs2_dinode)); gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode) + sizeof(__be64)); ptr = (__be64 *)(mp->mp_bh[i]->b_data + sizeof(struct gfs2_meta_header)); *ptr = zero_bn; state = ALLOC_GROW_DEPTH; for(i = branch_start; i < mp->mp_fheight; i++) { if (mp->mp_bh[i] == NULL) break; brelse(mp->mp_bh[i]); mp->mp_bh[i] = NULL; } i = branch_start; } if (n == 0) break; fallthrough; /* To branching from existing tree */ case ALLOC_GROW_DEPTH: if (i > 1 && i < mp->mp_fheight) gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[i-1]); for (; i < mp->mp_fheight && n > 0; i++, n--) gfs2_indirect_init(mp, ip->i_gl, i, mp->mp_list[i-1], bn++); if (i == mp->mp_fheight) state = ALLOC_DATA; if (n == 0) break; fallthrough; /* To tree complete, adding data blocks */ case ALLOC_DATA: BUG_ON(n > dblks); BUG_ON(mp->mp_bh[end_of_metadata] == NULL); gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[end_of_metadata]); dblks = n; ptr = metapointer(end_of_metadata, mp); iomap->addr = bn << inode->i_blkbits; iomap->flags |= IOMAP_F_MERGED | IOMAP_F_NEW; while (n-- > 0) *ptr++ = cpu_to_be64(bn++); break; } } while (iomap->addr == IOMAP_NULL_ADDR); iomap->type = IOMAP_MAPPED; iomap->length = (u64)dblks << inode->i_blkbits; ip->i_height = mp->mp_fheight; gfs2_add_inode_blocks(&ip->i_inode, alloced); gfs2_dinode_out(ip, dibh->b_data); out: up_write(&ip->i_rw_mutex); return ret; } #define IOMAP_F_GFS2_BOUNDARY IOMAP_F_PRIVATE /** * gfs2_alloc_size - Compute the maximum allocation size * @inode: The inode * @mp: The metapath * @size: Requested size in blocks * * Compute the maximum size of the next allocation at @mp. * * Returns: size in blocks */ static u64 gfs2_alloc_size(struct inode *inode, struct metapath *mp, u64 size) { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); const __be64 *first, *ptr, *end; /* * For writes to stuffed files, this function is called twice via * __gfs2_iomap_get, before and after unstuffing. The size we return the * first time needs to be large enough to get the reservation and * allocation sizes right. The size we return the second time must * be exact or else __gfs2_iomap_alloc won't do the right thing. */ if (gfs2_is_stuffed(ip) || mp->mp_fheight != mp->mp_aheight) { unsigned int maxsize = mp->mp_fheight > 1 ? sdp->sd_inptrs : sdp->sd_diptrs; maxsize -= mp->mp_list[mp->mp_fheight - 1]; if (size > maxsize) size = maxsize; return size; } first = metapointer(ip->i_height - 1, mp); end = metaend(ip->i_height - 1, mp); if (end - first > size) end = first + size; for (ptr = first; ptr < end; ptr++) { if (*ptr) break; } return ptr - first; } /** * __gfs2_iomap_get - Map blocks from an inode to disk blocks * @inode: The inode * @pos: Starting position in bytes * @length: Length to map, in bytes * @flags: iomap flags * @iomap: The iomap structure * @mp: The metapath * * Returns: errno */ static int __gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length, unsigned flags, struct iomap *iomap, struct metapath *mp) { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); loff_t size = i_size_read(inode); __be64 *ptr; sector_t lblock; sector_t lblock_stop; int ret; int eob; u64 len; struct buffer_head *dibh = NULL, *bh; u8 height; if (!length) return -EINVAL; down_read(&ip->i_rw_mutex); ret = gfs2_meta_inode_buffer(ip, &dibh); if (ret) goto unlock; mp->mp_bh[0] = dibh; if (gfs2_is_stuffed(ip)) { if (flags & IOMAP_WRITE) { loff_t max_size = gfs2_max_stuffed_size(ip); if (pos + length > max_size) goto unstuff; iomap->length = max_size; } else { if (pos >= size) { if (flags & IOMAP_REPORT) { ret = -ENOENT; goto unlock; } else { iomap->offset = pos; iomap->length = length; goto hole_found; } } iomap->length = size; } iomap->addr = (ip->i_no_addr << inode->i_blkbits) + sizeof(struct gfs2_dinode); iomap->type = IOMAP_INLINE; iomap->inline_data = dibh->b_data + sizeof(struct gfs2_dinode); goto out; } unstuff: lblock = pos >> inode->i_blkbits; iomap->offset = lblock << inode->i_blkbits; lblock_stop = (pos + length - 1) >> inode->i_blkbits; len = lblock_stop - lblock + 1; iomap->length = len << inode->i_blkbits; height = ip->i_height; while ((lblock + 1) * sdp->sd_sb.sb_bsize > sdp->sd_heightsize[height]) height++; find_metapath(sdp, lblock, mp, height); if (height > ip->i_height || gfs2_is_stuffed(ip)) goto do_alloc; ret = lookup_metapath(ip, mp); if (ret) goto unlock; if (mp->mp_aheight != ip->i_height) goto do_alloc; ptr = metapointer(ip->i_height - 1, mp); if (*ptr == 0) goto do_alloc; bh = mp->mp_bh[ip->i_height - 1]; len = gfs2_extent_length(bh, ptr, &eob); iomap->addr = be64_to_cpu(*ptr) << inode->i_blkbits; iomap->length = len << inode->i_blkbits; iomap->type = IOMAP_MAPPED; iomap->flags |= IOMAP_F_MERGED; if (eob) iomap->flags |= IOMAP_F_GFS2_BOUNDARY; out: iomap->bdev = inode->i_sb->s_bdev; unlock: up_read(&ip->i_rw_mutex); return ret; do_alloc: if (flags & IOMAP_REPORT) { if (pos >= size) ret = -ENOENT; else if (height == ip->i_height) ret = gfs2_hole_size(inode, lblock, len, mp, iomap); else iomap->length = size - iomap->offset; } else if (flags & IOMAP_WRITE) { u64 alloc_size; if (flags & IOMAP_DIRECT) goto out; /* (see gfs2_file_direct_write) */ len = gfs2_alloc_size(inode, mp, len); alloc_size = len << inode->i_blkbits; if (alloc_size < iomap->length) iomap->length = alloc_size; } else { if (pos < size && height == ip->i_height) ret = gfs2_hole_size(inode, lblock, len, mp, iomap); } hole_found: iomap->addr = IOMAP_NULL_ADDR; iomap->type = IOMAP_HOLE; goto out; } static struct folio * gfs2_iomap_get_folio(struct iomap_iter *iter, loff_t pos, unsigned len) { struct inode *inode = iter->inode; struct gfs2_inode *ip = GFS2_I(inode); unsigned int blockmask = i_blocksize(inode) - 1; struct gfs2_sbd *sdp = GFS2_SB(inode); unsigned int blocks; struct folio *folio; int status; if (!gfs2_is_jdata(ip) && !gfs2_is_stuffed(ip)) return iomap_get_folio(iter, pos, len); blocks = ((pos & blockmask) + len + blockmask) >> inode->i_blkbits; status = gfs2_trans_begin(sdp, RES_DINODE + blocks, 0); if (status) return ERR_PTR(status); folio = iomap_get_folio(iter, pos, len); if (IS_ERR(folio)) gfs2_trans_end(sdp); return folio; } static void gfs2_iomap_put_folio(struct inode *inode, loff_t pos, unsigned copied, struct folio *folio) { struct gfs2_trans *tr = current->journal_info; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); if (gfs2_is_jdata(ip) && !gfs2_is_stuffed(ip)) gfs2_trans_add_databufs(ip->i_gl, folio, offset_in_folio(folio, pos), copied); folio_unlock(folio); folio_put(folio); if (gfs2_is_jdata(ip) || gfs2_is_stuffed(ip)) { if (tr->tr_num_buf_new) __mark_inode_dirty(inode, I_DIRTY_DATASYNC); gfs2_trans_end(sdp); } } const struct iomap_write_ops gfs2_iomap_write_ops = { .get_folio = gfs2_iomap_get_folio, .put_folio = gfs2_iomap_put_folio, }; static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, loff_t length, unsigned flags, struct iomap *iomap, struct metapath *mp) { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); bool unstuff; int ret; unstuff = gfs2_is_stuffed(ip) && pos + length > gfs2_max_stuffed_size(ip); if (unstuff || iomap->type == IOMAP_HOLE) { unsigned int data_blocks, ind_blocks; struct gfs2_alloc_parms ap = {}; unsigned int rblocks; struct gfs2_trans *tr; gfs2_write_calc_reserv(ip, iomap->length, &data_blocks, &ind_blocks); ap.target = data_blocks + ind_blocks; ret = gfs2_quota_lock_check(ip, &ap); if (ret) return ret; ret = gfs2_inplace_reserve(ip, &ap); if (ret) goto out_qunlock; rblocks = RES_DINODE + ind_blocks; if (gfs2_is_jdata(ip)) rblocks += data_blocks; if (ind_blocks || data_blocks) rblocks += RES_STATFS + RES_QUOTA; if (inode == sdp->sd_rindex) rblocks += 2 * RES_STATFS; rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks); ret = gfs2_trans_begin(sdp, rblocks, iomap->length >> inode->i_blkbits); if (ret) goto out_trans_fail; if (unstuff) { ret = gfs2_unstuff_dinode(ip); if (ret) goto out_trans_end; release_metapath(mp); ret = __gfs2_iomap_get(inode, iomap->offset, iomap->length, flags, iomap, mp); if (ret) goto out_trans_end; } if (iomap->type == IOMAP_HOLE) { ret = __gfs2_iomap_alloc(inode, iomap, mp); if (ret) { gfs2_trans_end(sdp); gfs2_inplace_release(ip); punch_hole(ip, iomap->offset, iomap->length); goto out_qunlock; } } tr = current->journal_info; if (tr->tr_num_buf_new) __mark_inode_dirty(inode, I_DIRTY_DATASYNC); gfs2_trans_end(sdp); } return 0; out_trans_end: gfs2_trans_end(sdp); out_trans_fail: gfs2_inplace_release(ip); out_qunlock: gfs2_quota_unlock(ip); return ret; } static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, unsigned flags, struct iomap *iomap, struct iomap *srcmap) { struct gfs2_inode *ip = GFS2_I(inode); struct metapath mp = { .mp_aheight = 1, }; int ret; if (gfs2_is_jdata(ip)) iomap->flags |= IOMAP_F_BUFFER_HEAD; trace_gfs2_iomap_start(ip, pos, length, flags); ret = __gfs2_iomap_get(inode, pos, length, flags, iomap, &mp); if (ret) goto out_unlock; switch(flags & (IOMAP_WRITE | IOMAP_ZERO)) { case IOMAP_WRITE: if (flags & IOMAP_DIRECT) { /* * Silently fall back to buffered I/O for stuffed files * or if we've got a hole (see gfs2_file_direct_write). */ if (iomap->type != IOMAP_MAPPED) ret = -ENOTBLK; goto out_unlock; } break; case IOMAP_ZERO: if (iomap->type == IOMAP_HOLE) goto out_unlock; break; default: goto out_unlock; } ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap, &mp); out_unlock: release_metapath(&mp); trace_gfs2_iomap_end(ip, iomap, ret); return ret; } static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length, ssize_t written, unsigned flags, struct iomap *iomap) { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); switch (flags & (IOMAP_WRITE | IOMAP_ZERO)) { case IOMAP_WRITE: if (flags & IOMAP_DIRECT) return 0; break; case IOMAP_ZERO: if (iomap->type == IOMAP_HOLE) return 0; break; default: return 0; } if (!gfs2_is_stuffed(ip)) gfs2_ordered_add_inode(ip); if (inode == sdp->sd_rindex) adjust_fs_space(inode); gfs2_inplace_release(ip); if (ip->i_qadata && ip->i_qadata->qa_qd_num) gfs2_quota_unlock(ip); if (length != written && (iomap->flags & IOMAP_F_NEW)) { /* Deallocate blocks that were just allocated. */ loff_t hstart = round_up(pos + written, i_blocksize(inode)); loff_t hend = iomap->offset + iomap->length; if (hstart < hend) { truncate_pagecache_range(inode, hstart, hend - 1); punch_hole(ip, hstart, hend - hstart); } } if (unlikely(!written)) return 0; if (iomap->flags & IOMAP_F_SIZE_CHANGED) mark_inode_dirty(inode); set_bit(GLF_DIRTY, &ip->i_gl->gl_flags); return 0; } const struct iomap_ops gfs2_iomap_ops = { .iomap_begin = gfs2_iomap_begin, .iomap_end = gfs2_iomap_end, }; /** * gfs2_block_map - Map one or more blocks of an inode to a disk block * @inode: The inode * @lblock: The logical block number * @bh_map: The bh to be mapped * @create: True if its ok to alloc blocks to satify the request * * The size of the requested mapping is defined in bh_map->b_size. * * Clears buffer_mapped(bh_map) and leaves bh_map->b_size unchanged * when @lblock is not mapped. Sets buffer_mapped(bh_map) and * bh_map->b_size to indicate the size of the mapping when @lblock and * successive blocks are mapped, up to the requested size. * * Sets buffer_boundary() if a read of metadata will be required * before the next block can be mapped. Sets buffer_new() if new * blocks were allocated. * * Returns: errno */ int gfs2_block_map(struct inode *inode, sector_t lblock, struct buffer_head *bh_map, int create) { struct gfs2_inode *ip = GFS2_I(inode); loff_t pos = (loff_t)lblock << inode->i_blkbits; loff_t length = bh_map->b_size; struct iomap iomap = { }; int ret; clear_buffer_mapped(bh_map); clear_buffer_new(bh_map); clear_buffer_boundary(bh_map); trace_gfs2_bmap(ip, bh_map, lblock, create, 1); if (!create) ret = gfs2_iomap_get(inode, pos, length, &iomap); else ret = gfs2_iomap_alloc(inode, pos, length, &iomap); if (ret) goto out; if (iomap.length > bh_map->b_size) { iomap.length = bh_map->b_size; iomap.flags &= ~IOMAP_F_GFS2_BOUNDARY; } if (iomap.addr != IOMAP_NULL_ADDR) map_bh(bh_map, inode->i_sb, iomap.addr >> inode->i_blkbits); bh_map->b_size = iomap.length; if (iomap.flags & IOMAP_F_GFS2_BOUNDARY) set_buffer_boundary(bh_map); if (iomap.flags & IOMAP_F_NEW) set_buffer_new(bh_map); out: trace_gfs2_bmap(ip, bh_map, lblock, create, ret); return ret; } int gfs2_get_extent(struct inode *inode, u64 lblock, u64 *dblock, unsigned int *extlen) { unsigned int blkbits = inode->i_blkbits; struct iomap iomap = { }; unsigned int len; int ret; ret = gfs2_iomap_get(inode, lblock << blkbits, *extlen << blkbits, &iomap); if (ret) return ret; if (iomap.type != IOMAP_MAPPED) return -EIO; *dblock = iomap.addr >> blkbits; len = iomap.length >> blkbits; if (len < *extlen) *extlen = len; return 0; } int gfs2_alloc_extent(struct inode *inode, u64 lblock, u64 *dblock, unsigned int *extlen, bool *new) { unsigned int blkbits = inode->i_blkbits; struct iomap iomap = { }; unsigned int len; int ret; ret = gfs2_iomap_alloc(inode, lblock << blkbits, *extlen << blkbits, &iomap); if (ret) return ret; if (iomap.type != IOMAP_MAPPED) return -EIO; *dblock = iomap.addr >> blkbits; len = iomap.length >> blkbits; if (len < *extlen) *extlen = len; *new = iomap.flags & IOMAP_F_NEW; return 0; } /* * NOTE: Never call gfs2_block_zero_range with an open transaction because it * uses iomap write to perform its actions, which begin their own transactions * (iomap_begin, get_folio, etc.) */ static int gfs2_block_zero_range(struct inode *inode, loff_t from, loff_t length) { BUG_ON(current->journal_info); if (from >= inode->i_size) return 0; length = min(length, inode->i_size - from); return iomap_zero_range(inode, from, length, NULL, &gfs2_iomap_ops, &gfs2_iomap_write_ops, NULL); } #define GFS2_JTRUNC_REVOKES 8192 /** * gfs2_journaled_truncate - Wrapper for truncate_pagecache for jdata files * @inode: The inode being truncated * @oldsize: The original (larger) size * @newsize: The new smaller size * * With jdata files, we have to journal a revoke for each block which is * truncated. As a result, we need to split this into separate transactions * if the number of pages being truncated gets too large. */ static int gfs2_journaled_truncate(struct inode *inode, u64 oldsize, u64 newsize) { struct gfs2_sbd *sdp = GFS2_SB(inode); u64 max_chunk = GFS2_JTRUNC_REVOKES * sdp->sd_vfs->s_blocksize; u64 chunk; int error; while (oldsize != newsize) { struct gfs2_trans *tr; unsigned int offs; chunk = oldsize - newsize; if (chunk > max_chunk) chunk = max_chunk; offs = oldsize & ~PAGE_MASK; if (offs && chunk > PAGE_SIZE) chunk = offs + ((chunk - offs) & PAGE_MASK); truncate_pagecache(inode, oldsize - chunk); oldsize -= chunk; tr = current->journal_info; if (!test_bit(TR_TOUCHED, &tr->tr_flags)) continue; gfs2_trans_end(sdp); error = gfs2_trans_begin(sdp, RES_DINODE, GFS2_JTRUNC_REVOKES); if (error) return error; } return 0; } static int trunc_start(struct inode *inode, u64 newsize) { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); struct buffer_head *dibh = NULL; int journaled = gfs2_is_jdata(ip); u64 oldsize = inode->i_size; int error; if (!gfs2_is_stuffed(ip)) { unsigned int blocksize = i_blocksize(inode); unsigned int offs = newsize & (blocksize - 1); if (offs) { error = gfs2_block_zero_range(inode, newsize, blocksize - offs); if (error) return error; } } if (journaled) error = gfs2_trans_begin(sdp, RES_DINODE + RES_JDATA, GFS2_JTRUNC_REVOKES); else error = gfs2_trans_begin(sdp, RES_DINODE, 0); if (error) return error; error = gfs2_meta_inode_buffer(ip, &dibh); if (error) goto out; gfs2_trans_add_meta(ip->i_gl, dibh); if (gfs2_is_stuffed(ip)) gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode) + newsize); else ip->i_diskflags |= GFS2_DIF_TRUNC_IN_PROG; i_size_write(inode, newsize); inode_set_mtime_to_ts(&ip->i_inode, inode_set_ctime_current(&ip->i_inode)); gfs2_dinode_out(ip, dibh->b_data); if (journaled) error = gfs2_journaled_truncate(inode, oldsize, newsize); else truncate_pagecache(inode, newsize); out: brelse(dibh); if (current->journal_info) gfs2_trans_end(sdp); return error; } int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length, struct iomap *iomap) { struct metapath mp = { .mp_aheight = 1, }; int ret; ret = __gfs2_iomap_get(inode, pos, length, 0, iomap, &mp); release_metapath(&mp); return ret; } int gfs2_iomap_alloc(struct inode *inode, loff_t pos, loff_t length, struct iomap *iomap) { struct metapath mp = { .mp_aheight = 1, }; int ret; ret = __gfs2_iomap_get(inode, pos, length, IOMAP_WRITE, iomap, &mp); if (!ret && iomap->type == IOMAP_HOLE) ret = __gfs2_iomap_alloc(inode, iomap, &mp); release_metapath(&mp); return ret; } /** * sweep_bh_for_rgrps - find an rgrp in a meta buffer and free blocks therein * @ip: inode * @rd_gh: holder of resource group glock * @bh: buffer head to sweep * @start: starting point in bh * @end: end point in bh * @meta: true if bh points to metadata (rather than data) * @btotal: place to keep count of total blocks freed * * We sweep a metadata buffer (provided by the metapath) for blocks we need to * free, and free them all. However, we do it one rgrp at a time. If this * block has references to multiple rgrps, we break it into individual * transactions. This allows other processes to use the rgrps while we're * focused on a single one, for better concurrency / performance. * At every transaction boundary, we rewrite the inode into the journal. * That way the bitmaps are kept consistent with the inode and we can recover * if we're interrupted by power-outages. * * Returns: 0, or return code if an error occurred. * *btotal has the total number of blocks freed */ static int sweep_bh_for_rgrps(struct gfs2_inode *ip, struct gfs2_holder *rd_gh, struct buffer_head *bh, __be64 *start, __be64 *end, bool meta, u32 *btotal) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_rgrpd *rgd; struct gfs2_trans *tr; __be64 *p; int blks_outside_rgrp; u64 bn, bstart, isize_blks; s64 blen; /* needs to be s64 or gfs2_add_inode_blocks breaks */ int ret = 0; bool buf_in_tr = false; /* buffer was added to transaction */ more_rgrps: rgd = NULL; if (gfs2_holder_initialized(rd_gh)) { rgd = gfs2_glock2rgrp(rd_gh->gh_gl); gfs2_assert_withdraw(sdp, gfs2_glock_is_locked_by_me(rd_gh->gh_gl)); } blks_outside_rgrp = 0; bstart = 0; blen = 0; for (p = start; p < end; p++) { if (!*p) continue; bn = be64_to_cpu(*p); if (rgd) { if (!rgrp_contains_block(rgd, bn)) { blks_outside_rgrp++; continue; } } else { rgd = gfs2_blk2rgrpd(sdp, bn, true); if (unlikely(!rgd)) { ret = -EIO; goto out; } ret = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, LM_FLAG_NODE_SCOPE, rd_gh); if (ret) goto out; /* Must be done with the rgrp glock held: */ if (gfs2_rs_active(&ip->i_res) && rgd == ip->i_res.rs_rgd) gfs2_rs_deltree(&ip->i_res); } /* The size of our transactions will be unknown until we actually process all the metadata blocks that relate to the rgrp. So we estimate. We know it can't be more than the dinode's i_blocks and we don't want to exceed the journal flush threshold, sd_log_thresh2. */ if (current->journal_info == NULL) { unsigned int jblocks_rqsted, revokes; jblocks_rqsted = rgd->rd_length + RES_DINODE + RES_INDIRECT; isize_blks = gfs2_get_inode_blocks(&ip->i_inode); if (isize_blks > atomic_read(&sdp->sd_log_thresh2)) jblocks_rqsted += atomic_read(&sdp->sd_log_thresh2); else jblocks_rqsted += isize_blks; revokes = jblocks_rqsted; if (meta) revokes += end - start; else if (ip->i_depth) revokes += sdp->sd_inptrs; ret = gfs2_trans_begin(sdp, jblocks_rqsted, revokes); if (ret) goto out_unlock; down_write(&ip->i_rw_mutex); } /* check if we will exceed the transaction blocks requested */ tr = current->journal_info; if (tr->tr_num_buf_new + RES_STATFS + RES_QUOTA >= atomic_read(&sdp->sd_log_thresh2)) { /* We set blks_outside_rgrp to ensure the loop will be repeated for the same rgrp, but with a new transaction. */ blks_outside_rgrp++; /* This next part is tricky. If the buffer was added to the transaction, we've already set some block pointers to 0, so we better follow through and free them, or we will introduce corruption (so break). This may be impossible, or at least rare, but I decided to cover the case regardless. If the buffer was not added to the transaction (this call), doing so would exceed our transaction size, so we need to end the transaction and start a new one (so goto). */ if (buf_in_tr) break; goto out_unlock; } gfs2_trans_add_meta(ip->i_gl, bh); buf_in_tr = true; *p = 0; if (bstart + blen == bn) { blen++; continue; } if (bstart) { __gfs2_free_blocks(ip, rgd, bstart, (u32)blen, meta); (*btotal) += blen; gfs2_add_inode_blocks(&ip->i_inode, -blen); } bstart = bn; blen = 1; } if (bstart) { __gfs2_free_blocks(ip, rgd, bstart, (u32)blen, meta); (*btotal) += blen; gfs2_add_inode_blocks(&ip->i_inode, -blen); } out_unlock: if (!ret && blks_outside_rgrp) { /* If buffer still has non-zero blocks outside the rgrp we just processed, do it all over again. */ if (current->journal_info) { struct buffer_head *dibh; ret = gfs2_meta_inode_buffer(ip, &dibh); if (ret) goto out; /* Every transaction boundary, we rewrite the dinode to keep its di_blocks current in case of failure. */ inode_set_mtime_to_ts(&ip->i_inode, inode_set_ctime_current(&ip->i_inode)); gfs2_trans_add_meta(ip->i_gl, dibh); gfs2_dinode_out(ip, dibh->b_data); brelse(dibh); up_write(&ip->i_rw_mutex); gfs2_trans_end(sdp); buf_in_tr = false; } gfs2_glock_dq_uninit(rd_gh); cond_resched(); goto more_rgrps; } out: return ret; } static bool mp_eq_to_hgt(struct metapath *mp, __u16 *list, unsigned int h) { if (memcmp(mp->mp_list, list, h * sizeof(mp->mp_list[0]))) return false; return true; } /** * find_nonnull_ptr - find a non-null pointer given a metapath and height * @sdp: The superblock * @mp: starting metapath * @h: desired height to search * @end_list: See punch_hole(). * @end_aligned: See punch_hole(). * * Assumes the metapath is valid (with buffers) out to height h. * Returns: true if a non-null pointer was found in the metapath buffer * false if all remaining pointers are NULL in the buffer */ static bool find_nonnull_ptr(struct gfs2_sbd *sdp, struct metapath *mp, unsigned int h, __u16 *end_list, unsigned int end_aligned) { struct buffer_head *bh = mp->mp_bh[h]; __be64 *first, *ptr, *end; first = metaptr1(h, mp); ptr = first + mp->mp_list[h]; end = (__be64 *)(bh->b_data + bh->b_size); if (end_list && mp_eq_to_hgt(mp, end_list, h)) { bool keep_end = h < end_aligned; end = first + end_list[h] + keep_end; } while (ptr < end) { if (*ptr) { /* if we have a non-null pointer */ mp->mp_list[h] = ptr - first; h++; if (h < GFS2_MAX_META_HEIGHT) mp->mp_list[h] = 0; return true; } ptr++; } return false; } enum dealloc_states { DEALLOC_MP_FULL = 0, /* Strip a metapath with all buffers read in */ DEALLOC_MP_LOWER = 1, /* lower the metapath strip height */ DEALLOC_FILL_MP = 2, /* Fill in the metapath to the given height. */ DEALLOC_DONE = 3, /* process complete */ }; static inline void metapointer_range(struct metapath *mp, int height, __u16 *start_list, unsigned int start_aligned, __u16 *end_list, unsigned int end_aligned, __be64 **start, __be64 **end) { struct buffer_head *bh = mp->mp_bh[height]; __be64 *first; first = metaptr1(height, mp); *start = first; if (mp_eq_to_hgt(mp, start_list, height)) { bool keep_start = height < start_aligned; *start = first + start_list[height] + keep_start; } *end = (__be64 *)(bh->b_data + bh->b_size); if (end_list && mp_eq_to_hgt(mp, end_list, height)) { bool keep_end = height < end_aligned; *end = first + end_list[height] + keep_end; } } static inline bool walk_done(struct gfs2_sbd *sdp, struct metapath *mp, int height, __u16 *end_list, unsigned int end_aligned) { __u16 end; if (end_list) { bool keep_end = height < end_aligned; if (!mp_eq_to_hgt(mp, end_list, height)) return false; end = end_list[height] + keep_end; } else end = (height > 0) ? sdp->sd_inptrs : sdp->sd_diptrs; return mp->mp_list[height] >= end; } /** * punch_hole - deallocate blocks in a file * @ip: inode to truncate * @offset: the start of the hole * @length: the size of the hole (or 0 for truncate) * * Punch a hole into a file or truncate a file at a given position. This * function operates in whole blocks (@offset and @length are rounded * accordingly); partially filled blocks must be cleared otherwise. * * This function works from the bottom up, and from the right to the left. In * other words, it strips off the highest layer (data) before stripping any of * the metadata. Doing it this way is best in case the operation is interrupted * by power failure, etc. The dinode is rewritten in every transaction to * guarantee integrity. */ static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); u64 maxsize = sdp->sd_heightsize[ip->i_height]; struct metapath mp = {}; struct buffer_head *dibh, *bh; struct gfs2_holder rd_gh; unsigned int bsize_shift = sdp->sd_sb.sb_bsize_shift; unsigned int bsize = 1 << bsize_shift; u64 lblock = (offset + bsize - 1) >> bsize_shift; __u16 start_list[GFS2_MAX_META_HEIGHT]; __u16 __end_list[GFS2_MAX_META_HEIGHT], *end_list = NULL; unsigned int start_aligned, end_aligned; unsigned int strip_h = ip->i_height - 1; u32 btotal = 0; int ret, state; int mp_h; /* metapath buffers are read in to this height */ u64 prev_bnr = 0; __be64 *start, *end; if (offset + bsize - 1 >= maxsize) { /* * The starting point lies beyond the allocated metadata; * there are no blocks to deallocate. */ return 0; } /* * The start position of the hole is defined by lblock, start_list, and * start_aligned. The end position of the hole is defined by lend, * end_list, and end_aligned. * * start_aligned and end_aligned define down to which height the start * and end positions are aligned to the metadata tree (i.e., the * position is a multiple of the metadata granularity at the height * above). This determines at which heights additional meta pointers * needs to be preserved for the remaining data. */ if (length) { u64 end_offset = offset + length; u64 lend; /* * Clip the end at the maximum file size for the given height: * that's how far the metadata goes; files bigger than that * will have additional layers of indirection. */ if (end_offset > maxsize) end_offset = maxsize; lend = end_offset >> bsize_shift; if (lblock >= lend) return 0; find_metapath(sdp, lend, &mp, ip->i_height); end_list = __end_list; memcpy(end_list, mp.mp_list, sizeof(mp.mp_list)); for (mp_h = ip->i_height - 1; mp_h > 0; mp_h--) { if (end_list[mp_h]) break; } end_aligned = mp_h; } find_metapath(sdp, lblock, &mp, ip->i_height); memcpy(start_list, mp.mp_list, sizeof(start_list)); for (mp_h = ip->i_height - 1; mp_h > 0; mp_h--) { if (start_list[mp_h]) break; } start_aligned = mp_h; ret = gfs2_meta_inode_buffer(ip, &dibh); if (ret) return ret; mp.mp_bh[0] = dibh; ret = lookup_metapath(ip, &mp); if (ret) goto out_metapath; /* issue read-ahead on metadata */ for (mp_h = 0; mp_h < mp.mp_aheight - 1; mp_h++) { metapointer_range(&mp, mp_h, start_list, start_aligned, end_list, end_aligned, &start, &end); gfs2_metapath_ra(ip->i_gl, start, end); } if (mp.mp_aheight == ip->i_height) state = DEALLOC_MP_FULL; /* We have a complete metapath */ else state = DEALLOC_FILL_MP; /* deal with partial metapath */ ret = gfs2_rindex_update(sdp); if (ret) goto out_metapath; ret = gfs2_quota_hold(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE); if (ret) goto out_metapath; gfs2_holder_mark_uninitialized(&rd_gh); mp_h = strip_h; while (state != DEALLOC_DONE) { switch (state) { /* Truncate a full metapath at the given strip height. * Note that strip_h == mp_h in order to be in this state. */ case DEALLOC_MP_FULL: bh = mp.mp_bh[mp_h]; gfs2_assert_withdraw(sdp, bh); if (gfs2_assert_withdraw(sdp, prev_bnr != bh->b_blocknr)) { fs_emerg(sdp, "inode %llu, block:%llu, i_h:%u, " "s_h:%u, mp_h:%u\n", (unsigned long long)ip->i_no_addr, prev_bnr, ip->i_height, strip_h, mp_h); } prev_bnr = bh->b_blocknr; if (gfs2_metatype_check(sdp, bh, (mp_h ? GFS2_METATYPE_IN : GFS2_METATYPE_DI))) { ret = -EIO; goto out; } /* * Below, passing end_aligned as 0 gives us the * metapointer range excluding the end point: the end * point is the first metapath we must not deallocate! */ metapointer_range(&mp, mp_h, start_list, start_aligned, end_list, 0 /* end_aligned */, &start, &end); ret = sweep_bh_for_rgrps(ip, &rd_gh, mp.mp_bh[mp_h], start, end, mp_h != ip->i_height - 1, &btotal); /* If we hit an error or just swept dinode buffer, just exit. */ if (ret || !mp_h) { state = DEALLOC_DONE; break; } state = DEALLOC_MP_LOWER; break; /* lower the metapath strip height */ case DEALLOC_MP_LOWER: /* We're done with the current buffer, so release it, unless it's the dinode buffer. Then back up to the previous pointer. */ if (mp_h) { brelse(mp.mp_bh[mp_h]); mp.mp_bh[mp_h] = NULL; } /* If we can't get any lower in height, we've stripped off all we can. Next step is to back up and start stripping the previous level of metadata. */ if (mp_h == 0) { strip_h--; memcpy(mp.mp_list, start_list, sizeof(start_list)); mp_h = strip_h; state = DEALLOC_FILL_MP; break; } mp.mp_list[mp_h] = 0; mp_h--; /* search one metadata height down */ mp.mp_list[mp_h]++; if (walk_done(sdp, &mp, mp_h, end_list, end_aligned)) break; /* Here we've found a part of the metapath that is not * allocated. We need to search at that height for the * next non-null pointer. */ if (find_nonnull_ptr(sdp, &mp, mp_h, end_list, end_aligned)) { state = DEALLOC_FILL_MP; mp_h++; } /* No more non-null pointers at this height. Back up to the previous height and try again. */ break; /* loop around in the same state */ /* Fill the metapath with buffers to the given height. */ case DEALLOC_FILL_MP: /* Fill the buffers out to the current height. */ ret = fillup_metapath(ip, &mp, mp_h); if (ret < 0) goto out; /* On the first pass, issue read-ahead on metadata. */ if (mp.mp_aheight > 1 && strip_h == ip->i_height - 1) { unsigned int height = mp.mp_aheight - 1; /* No read-ahead for data blocks. */ if (mp.mp_aheight - 1 == strip_h) height--; for (; height >= mp.mp_aheight - ret; height--) { metapointer_range(&mp, height, start_list, start_aligned, end_list, end_aligned, &start, &end); gfs2_metapath_ra(ip->i_gl, start, end); } } /* If buffers found for the entire strip height */ if (mp.mp_aheight - 1 == strip_h) { state = DEALLOC_MP_FULL; break; } if (mp.mp_aheight < ip->i_height) /* We have a partial height */ mp_h = mp.mp_aheight - 1; /* If we find a non-null block pointer, crawl a bit higher up in the metapath and try again, otherwise we need to look lower for a new starting point. */ if (find_nonnull_ptr(sdp, &mp, mp_h, end_list, end_aligned)) mp_h++; else state = DEALLOC_MP_LOWER; break; } } if (btotal) { if (current->journal_info == NULL) { ret = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS + RES_QUOTA, 0); if (ret) goto out; down_write(&ip->i_rw_mutex); } gfs2_statfs_change(sdp, 0, +btotal, 0); gfs2_quota_change(ip, -(s64)btotal, ip->i_inode.i_uid, ip->i_inode.i_gid); inode_set_mtime_to_ts(&ip->i_inode, inode_set_ctime_current(&ip->i_inode)); gfs2_trans_add_meta(ip->i_gl, dibh); gfs2_dinode_out(ip, dibh->b_data); up_write(&ip->i_rw_mutex); gfs2_trans_end(sdp); } out: if (gfs2_holder_initialized(&rd_gh)) gfs2_glock_dq_uninit(&rd_gh); if (current->journal_info) { up_write(&ip->i_rw_mutex); gfs2_trans_end(sdp); cond_resched(); } gfs2_quota_unhold(ip); out_metapath: release_metapath(&mp); return ret; } static int trunc_end(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct buffer_head *dibh; int error; error = gfs2_trans_begin(sdp, RES_DINODE, 0); if (error) return error; down_write(&ip->i_rw_mutex); error = gfs2_meta_inode_buffer(ip, &dibh); if (error) goto out; if (!i_size_read(&ip->i_inode)) { ip->i_height = 0; ip->i_goal = ip->i_no_addr; gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode)); gfs2_ordered_del_inode(ip); } inode_set_mtime_to_ts(&ip->i_inode, inode_set_ctime_current(&ip->i_inode)); ip->i_diskflags &= ~GFS2_DIF_TRUNC_IN_PROG; gfs2_trans_add_meta(ip->i_gl, dibh); gfs2_dinode_out(ip, dibh->b_data); brelse(dibh); out: up_write(&ip->i_rw_mutex); gfs2_trans_end(sdp); return error; } /** * do_shrink - make a file smaller * @inode: the inode * @newsize: the size to make the file * * Called with an exclusive lock on @inode. The @size must * be equal to or smaller than the current inode size. * * Returns: errno */ static int do_shrink(struct inode *inode, u64 newsize) { struct gfs2_inode *ip = GFS2_I(inode); int error; error = trunc_start(inode, newsize); if (error < 0) return error; if (gfs2_is_stuffed(ip)) return 0; error = punch_hole(ip, newsize, 0); if (error == 0) error = trunc_end(ip); return error; } /** * do_grow - Touch and update inode size * @inode: The inode * @size: The new size * * This function updates the timestamps on the inode and * may also increase the size of the inode. This function * must not be called with @size any smaller than the current * inode size. * * Although it is not strictly required to unstuff files here, * earlier versions of GFS2 have a bug in the stuffed file reading * code which will result in a buffer overrun if the size is larger * than the max stuffed file size. In order to prevent this from * occurring, such files are unstuffed, but in other cases we can * just update the inode size directly. * * Returns: 0 on success, or -ve on error */ static int do_grow(struct inode *inode, u64 size) { struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_alloc_parms ap = { .target = 1, }; struct buffer_head *dibh; int error; int unstuff = 0; if (gfs2_is_stuffed(ip) && size > gfs2_max_stuffed_size(ip)) { error = gfs2_quota_lock_check(ip, &ap); if (error) return error; error = gfs2_inplace_reserve(ip, &ap); if (error) goto do_grow_qunlock; unstuff = 1; } error = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS + RES_RG_BIT + (unstuff && gfs2_is_jdata(ip) ? RES_JDATA : 0) + (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF ? 0 : RES_QUOTA), 0); if (error) goto do_grow_release; if (unstuff) { error = gfs2_unstuff_dinode(ip); if (error) goto do_end_trans; } error = gfs2_meta_inode_buffer(ip, &dibh); if (error) goto do_end_trans; truncate_setsize(inode, size); inode_set_mtime_to_ts(&ip->i_inode, inode_set_ctime_current(&ip->i_inode)); gfs2_trans_add_meta(ip->i_gl, dibh); gfs2_dinode_out(ip, dibh->b_data); brelse(dibh); do_end_trans: gfs2_trans_end(sdp); do_grow_release: if (unstuff) { gfs2_inplace_release(ip); do_grow_qunlock: gfs2_quota_unlock(ip); } return error; } /** * gfs2_setattr_size - make a file a given size * @inode: the inode * @newsize: the size to make the file * * The file size can grow, shrink, or stay the same size. This * is called holding i_rwsem and an exclusive glock on the inode * in question. * * Returns: errno */ int gfs2_setattr_size(struct inode *inode, u64 newsize) { struct gfs2_inode *ip = GFS2_I(inode); int ret; BUG_ON(!S_ISREG(inode->i_mode)); ret = inode_newsize_ok(inode, newsize); if (ret) return ret; inode_dio_wait(inode); ret = gfs2_qa_get(ip); if (ret) goto out; if (newsize >= inode->i_size) { ret = do_grow(inode, newsize); goto out; } ret = do_shrink(inode, newsize); out: gfs2_rs_delete(ip); gfs2_qa_put(ip); return ret; } int gfs2_truncatei_resume(struct gfs2_inode *ip) { int error; error = punch_hole(ip, i_size_read(&ip->i_inode), 0); if (!error) error = trunc_end(ip); return error; } int gfs2_file_dealloc(struct gfs2_inode *ip) { return punch_hole(ip, 0, 0); } /** * gfs2_free_journal_extents - Free cached journal bmap info * @jd: The journal * */ void gfs2_free_journal_extents(struct gfs2_jdesc *jd) { struct gfs2_journal_extent *jext; while(!list_empty(&jd->extent_list)) { jext = list_first_entry(&jd->extent_list, struct gfs2_journal_extent, list); list_del(&jext->list); kfree(jext); } } /** * gfs2_add_jextent - Add or merge a new extent to extent cache * @jd: The journal descriptor * @lblock: The logical block at start of new extent * @dblock: The physical block at start of new extent * @blocks: Size of extent in fs blocks * * Returns: 0 on success or -ENOMEM */ static int gfs2_add_jextent(struct gfs2_jdesc *jd, u64 lblock, u64 dblock, u64 blocks) { struct gfs2_journal_extent *jext; if (!list_empty(&jd->extent_list)) { jext = list_last_entry(&jd->extent_list, struct gfs2_journal_extent, list); if ((jext->dblock + jext->blocks) == dblock) { jext->blocks += blocks; return 0; } } jext = kzalloc(sizeof(struct gfs2_journal_extent), GFP_NOFS); if (jext == NULL) return -ENOMEM; jext->dblock = dblock; jext->lblock = lblock; jext->blocks = blocks; list_add_tail(&jext->list, &jd->extent_list); jd->nr_extents++; return 0; } /** * gfs2_map_journal_extents - Cache journal bmap info * @sdp: The super block * @jd: The journal to map * * Create a reusable "extent" mapping from all logical * blocks to all physical blocks for the given journal. This will save * us time when writing journal blocks. Most journals will have only one * extent that maps all their logical blocks. That's because gfs2.mkfs * arranges the journal blocks sequentially to maximize performance. * So the extent would map the first block for the entire file length. * However, gfs2_jadd can happen while file activity is happening, so * those journals may not be sequential. Less likely is the case where * the users created their own journals by mounting the metafs and * laying it out. But it's still possible. These journals might have * several extents. * * Returns: 0 on success, or error on failure */ int gfs2_map_journal_extents(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd) { u64 lblock = 0; u64 lblock_stop; struct gfs2_inode *ip = GFS2_I(jd->jd_inode); struct buffer_head bh; unsigned int shift = sdp->sd_sb.sb_bsize_shift; u64 size; int rc; ktime_t start, end; start = ktime_get(); lblock_stop = i_size_read(jd->jd_inode) >> shift; size = (lblock_stop - lblock) << shift; jd->nr_extents = 0; WARN_ON(!list_empty(&jd->extent_list)); do { bh.b_state = 0; bh.b_blocknr = 0; bh.b_size = size; rc = gfs2_block_map(jd->jd_inode, lblock, &bh, 0); if (rc || !buffer_mapped(&bh)) goto fail; rc = gfs2_add_jextent(jd, lblock, bh.b_blocknr, bh.b_size >> shift); if (rc) goto fail; size -= bh.b_size; lblock += (bh.b_size >> ip->i_inode.i_blkbits); } while(size > 0); end = ktime_get(); fs_info(sdp, "journal %d mapped with %u extents in %lldms\n", jd->jd_jid, jd->nr_extents, ktime_ms_delta(end, start)); return 0; fail: fs_warn(sdp, "error %d mapping journal %u at offset %llu (extent %u)\n", rc, jd->jd_jid, (unsigned long long)(i_size_read(jd->jd_inode) - size), jd->nr_extents); fs_warn(sdp, "bmap=%d lblock=%llu block=%llu, state=0x%08lx, size=%llu\n", rc, (unsigned long long)lblock, (unsigned long long)bh.b_blocknr, bh.b_state, (unsigned long long)bh.b_size); gfs2_free_journal_extents(jd); return rc; } /** * gfs2_write_alloc_required - figure out if a write will require an allocation * @ip: the file being written to * @offset: the offset to write to * @len: the number of bytes being written * * Returns: 1 if an alloc is required, 0 otherwise */ int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset, unsigned int len) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct buffer_head bh; unsigned int shift; u64 lblock, lblock_stop, size; u64 end_of_file; if (!len) return 0; if (gfs2_is_stuffed(ip)) { if (offset + len > gfs2_max_stuffed_size(ip)) return 1; return 0; } shift = sdp->sd_sb.sb_bsize_shift; BUG_ON(gfs2_is_dir(ip)); end_of_file = (i_size_read(&ip->i_inode) + sdp->sd_sb.sb_bsize - 1) >> shift; lblock = offset >> shift; lblock_stop = (offset + len + sdp->sd_sb.sb_bsize - 1) >> shift; if (lblock_stop > end_of_file && ip != GFS2_I(sdp->sd_rindex)) return 1; size = (lblock_stop - lblock) << shift; do { bh.b_state = 0; bh.b_size = size; gfs2_block_map(&ip->i_inode, lblock, &bh, 0); if (!buffer_mapped(&bh)) return 1; size -= bh.b_size; lblock += (bh.b_size >> ip->i_inode.i_blkbits); } while(size > 0); return 0; } static int stuffed_zero_range(struct inode *inode, loff_t offset, loff_t length) { struct gfs2_inode *ip = GFS2_I(inode); struct buffer_head *dibh; int error; if (offset >= inode->i_size) return 0; if (offset + length > inode->i_size) length = inode->i_size - offset; error = gfs2_meta_inode_buffer(ip, &dibh); if (error) return error; gfs2_trans_add_meta(ip->i_gl, dibh); memset(dibh->b_data + sizeof(struct gfs2_dinode) + offset, 0, length); brelse(dibh); return 0; } static int gfs2_journaled_truncate_range(struct inode *inode, loff_t offset, loff_t length) { struct gfs2_sbd *sdp = GFS2_SB(inode); loff_t max_chunk = GFS2_JTRUNC_REVOKES * sdp->sd_vfs->s_blocksize; int error; while (length) { struct gfs2_trans *tr; loff_t chunk; unsigned int offs; chunk = length; if (chunk > max_chunk) chunk = max_chunk; offs = offset & ~PAGE_MASK; if (offs && chunk > PAGE_SIZE) chunk = offs + ((chunk - offs) & PAGE_MASK); truncate_pagecache_range(inode, offset, chunk); offset += chunk; length -= chunk; tr = current->journal_info; if (!test_bit(TR_TOUCHED, &tr->tr_flags)) continue; gfs2_trans_end(sdp); error = gfs2_trans_begin(sdp, RES_DINODE, GFS2_JTRUNC_REVOKES); if (error) return error; } return 0; } int __gfs2_punch_hole(struct file *file, loff_t offset, loff_t length) { struct inode *inode = file_inode(file); struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); unsigned int blocksize = i_blocksize(inode); loff_t start, end; int error; if (!gfs2_is_stuffed(ip)) { unsigned int start_off, end_len; start_off = offset & (blocksize - 1); end_len = (offset + length) & (blocksize - 1); if (start_off) { unsigned int len = length; if (length > blocksize - start_off) len = blocksize - start_off; error = gfs2_block_zero_range(inode, offset, len); if (error) goto out; if (start_off + length < blocksize) end_len = 0; } if (end_len) { error = gfs2_block_zero_range(inode, offset + length - end_len, end_len); if (error) goto out; } } start = round_down(offset, blocksize); end = round_up(offset + length, blocksize) - 1; error = filemap_write_and_wait_range(inode->i_mapping, start, end); if (error) return error; if (gfs2_is_jdata(ip)) error = gfs2_trans_begin(sdp, RES_DINODE + 2 * RES_JDATA, GFS2_JTRUNC_REVOKES); else error = gfs2_trans_begin(sdp, RES_DINODE, 0); if (error) return error; if (gfs2_is_stuffed(ip)) { error = stuffed_zero_range(inode, offset, length); if (error) goto out; } if (gfs2_is_jdata(ip)) { BUG_ON(!current->journal_info); gfs2_journaled_truncate_range(inode, offset, length); } else truncate_pagecache_range(inode, offset, offset + length - 1); file_update_time(file); mark_inode_dirty(inode); if (current->journal_info) gfs2_trans_end(sdp); if (!gfs2_is_stuffed(ip)) error = punch_hole(ip, offset, length); out: if (current->journal_info) gfs2_trans_end(sdp); return error; } static ssize_t gfs2_writeback_range(struct iomap_writepage_ctx *wpc, struct folio *folio, u64 offset, unsigned int len, u64 end_pos) { if (WARN_ON_ONCE(gfs2_is_stuffed(GFS2_I(wpc->inode)))) return -EIO; if (offset < wpc->iomap.offset || offset >= wpc->iomap.offset + wpc->iomap.length) { int ret; memset(&wpc->iomap, 0, sizeof(wpc->iomap)); ret = gfs2_iomap_get(wpc->inode, offset, INT_MAX, &wpc->iomap); if (ret) return ret; } return iomap_add_to_ioend(wpc, folio, offset, end_pos, len); } const struct iomap_writeback_ops gfs2_writeback_ops = { .writeback_range = gfs2_writeback_range, .writeback_submit = iomap_ioend_writeback_submit, }; |
| 38 2 16 4 3 3 2 16 3 3 1 25 24 25 24 24 24 20 24 4 2 20 20 4 20 20 20 20 20 4 4 4 4 4 4 3 2 2 4 4 4 5 4 3 2 1 1 1 20 19 19 19 5 3 16 18 12 10 1 12 1 11 11 11 2 5 6 11 9 2 2 8 2 6 2 1 8 8 11 11 13 13 12 8 3 1 2 2 1 10 10 2 13 13 20 1 19 19 19 19 16 18 18 17 3 15 15 14 1 15 1 14 3 15 15 10 1 15 15 7 8 15 15 15 5 15 20 26 26 1 24 25 1 23 6 6 1 5 23 22 2 21 2 20 1 19 6 13 12 26 33 33 1 34 7 12 12 34 26 25 13 26 26 26 1 1 1 1 126 42 124 1 23 23 12 12 12 12 1 3 3 2 65 1 1 1 1 1 4 2 2 1 3 2 1 1 1 2 1 5 4 3 2 1 1 2 1 2 1 1 1 1 1 4 3 1 1 2 2 1 2 2 2 2 2 2 2 15 15 2 1 1 5 1 1 2 16 26 42 3 126 126 126 126 66 42 1 9 9 9 9 1 1 9 9 8 1 9 9 5 5 5 5 5 5 5 5 5 5 5 4 4 4 1 3 3 3 2 1 1 1 1 1 2 3 34 26 11 34 34 1 33 27 26 19 19 19 13 3 25 25 8 19 33 22 33 14 33 11 33 11 33 31 31 31 31 31 31 31 31 31 31 31 31 30 31 31 28 31 31 31 31 31 23 23 13 13 13 13 13 23 2 2 2 2 2 1 1 21 21 21 19 19 19 1 19 11 11 18 5 14 2 12 2 12 18 12 40 10 9 9 9 38 39 40 40 2 48 42 42 41 20 20 20 20 20 20 20 20 4 4 24 24 24 24 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * History: * Started: Aug 9 by Lawrence Foard (entropy@world.std.com), * to allow user process control of SCSI devices. * Development Sponsored by Killy Corp. NY NY * * Original driver (sg.c): * Copyright (C) 1992 Lawrence Foard * Version 2 and 3 extensions to driver: * Copyright (C) 1998 - 2014 Douglas Gilbert */ static int sg_version_num = 30536; /* 2 digits for each component */ #define SG_VERSION_STR "3.5.36" /* * D. P. Gilbert (dgilbert@interlog.com), notes: * - scsi logging is available via SCSI_LOG_TIMEOUT macros. First * the kernel/module needs to be built with CONFIG_SCSI_LOGGING * (otherwise the macros compile to empty statements). * */ #include <linux/module.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/errno.h> #include <linux/mtio.h> #include <linux/ioctl.h> #include <linux/major.h> #include <linux/slab.h> #include <linux/fcntl.h> #include <linux/init.h> #include <linux/poll.h> #include <linux/moduleparam.h> #include <linux/cdev.h> #include <linux/idr.h> #include <linux/seq_file.h> #include <linux/blkdev.h> #include <linux/delay.h> #include <linux/blktrace_api.h> #include <linux/mutex.h> #include <linux/atomic.h> #include <linux/ratelimit.h> #include <linux/uio.h> #include <linux/cred.h> /* for sg_check_file_access() */ #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_dbg.h> #include <scsi/scsi_device.h> #include <scsi/scsi_driver.h> #include <scsi/scsi_eh.h> #include <scsi/scsi_host.h> #include <scsi/scsi_ioctl.h> #include <scsi/scsi_tcq.h> #include <scsi/sg.h> #include "scsi_logging.h" #ifdef CONFIG_SCSI_PROC_FS #include <linux/proc_fs.h> static char *sg_version_date = "20140603"; static int sg_proc_init(void); #endif #define SG_ALLOW_DIO_DEF 0 #define SG_MAX_DEVS (1 << MINORBITS) /* SG_MAX_CDB_SIZE should be 260 (spc4r37 section 3.1.30) however the type * of sg_io_hdr::cmd_len can only represent 255. All SCSI commands greater * than 16 bytes are "variable length" whose length is a multiple of 4 */ #define SG_MAX_CDB_SIZE 252 #define SG_DEFAULT_TIMEOUT mult_frac(SG_DEFAULT_TIMEOUT_USER, HZ, USER_HZ) static int sg_big_buff = SG_DEF_RESERVED_SIZE; /* N.B. This variable is readable and writeable via /proc/scsi/sg/def_reserved_size . Each time sg_open() is called a buffer of this size (or less if there is not enough memory) will be reserved for use by this file descriptor. [Deprecated usage: this variable is also readable via /proc/sys/kernel/sg-big-buff if the sg driver is built into the kernel (i.e. it is not a module).] */ static int def_reserved_size = -1; /* picks up init parameter */ static int sg_allow_dio = SG_ALLOW_DIO_DEF; static int scatter_elem_sz = SG_SCATTER_SZ; static int scatter_elem_sz_prev = SG_SCATTER_SZ; #define SG_SECTOR_SZ 512 static int sg_add_device(struct device *); static void sg_remove_device(struct device *); static DEFINE_IDR(sg_index_idr); static DEFINE_RWLOCK(sg_index_lock); /* Also used to lock file descriptor list for device */ static struct class_interface sg_interface = { .add_dev = sg_add_device, .remove_dev = sg_remove_device, }; typedef struct sg_scatter_hold { /* holding area for scsi scatter gather info */ unsigned short k_use_sg; /* Count of kernel scatter-gather pieces */ unsigned sglist_len; /* size of malloc'd scatter-gather list ++ */ unsigned bufflen; /* Size of (aggregate) data buffer */ struct page **pages; int page_order; char dio_in_use; /* 0->indirect IO (or mmap), 1->dio */ unsigned char cmd_opcode; /* first byte of command */ } Sg_scatter_hold; struct sg_device; /* forward declarations */ struct sg_fd; typedef struct sg_request { /* SG_MAX_QUEUE requests outstanding per file */ struct list_head entry; /* list entry */ struct sg_fd *parentfp; /* NULL -> not in use */ Sg_scatter_hold data; /* hold buffer, perhaps scatter list */ sg_io_hdr_t header; /* scsi command+info, see <scsi/sg.h> */ unsigned char sense_b[SCSI_SENSE_BUFFERSIZE]; char res_used; /* 1 -> using reserve buffer, 0 -> not ... */ char orphan; /* 1 -> drop on sight, 0 -> normal */ char sg_io_owned; /* 1 -> packet belongs to SG_IO */ /* done protected by rq_list_lock */ char done; /* 0->before bh, 1->before read, 2->read */ struct request *rq; struct bio *bio; struct execute_work ew; } Sg_request; typedef struct sg_fd { /* holds the state of a file descriptor */ struct list_head sfd_siblings; /* protected by device's sfd_lock */ struct sg_device *parentdp; /* owning device */ wait_queue_head_t read_wait; /* queue read until command done */ rwlock_t rq_list_lock; /* protect access to list in req_arr */ struct mutex f_mutex; /* protect against changes in this fd */ int timeout; /* defaults to SG_DEFAULT_TIMEOUT */ int timeout_user; /* defaults to SG_DEFAULT_TIMEOUT_USER */ Sg_scatter_hold reserve; /* buffer held for this file descriptor */ struct list_head rq_list; /* head of request list */ struct fasync_struct *async_qp; /* used by asynchronous notification */ Sg_request req_arr[SG_MAX_QUEUE]; /* used as singly-linked list */ char force_packid; /* 1 -> pack_id input to read(), 0 -> ignored */ char cmd_q; /* 1 -> allow command queuing, 0 -> don't */ unsigned char next_cmd_len; /* 0: automatic, >0: use on next write() */ char keep_orphan; /* 0 -> drop orphan (def), 1 -> keep for read() */ char mmap_called; /* 0 -> mmap() never called on this fd */ char res_in_use; /* 1 -> 'reserve' array in use */ struct kref f_ref; struct execute_work ew; } Sg_fd; typedef struct sg_device { /* holds the state of each scsi generic device */ struct scsi_device *device; wait_queue_head_t open_wait; /* queue open() when O_EXCL present */ struct mutex open_rel_lock; /* held when in open() or release() */ int sg_tablesize; /* adapter's max scatter-gather table size */ u32 index; /* device index number */ struct list_head sfds; rwlock_t sfd_lock; /* protect access to sfd list */ atomic_t detaching; /* 0->device usable, 1->device detaching */ bool exclude; /* 1->open(O_EXCL) succeeded and is active */ int open_cnt; /* count of opens (perhaps < num(sfds) ) */ char sgdebug; /* 0->off, 1->sense, 9->dump dev, 10-> all devs */ char name[DISK_NAME_LEN]; struct cdev * cdev; /* char_dev [sysfs: /sys/cdev/major/sg<n>] */ struct kref d_ref; } Sg_device; /* tasklet or soft irq callback */ static enum rq_end_io_ret sg_rq_end_io(struct request *rq, blk_status_t status); static int sg_start_req(Sg_request *srp, unsigned char *cmd); static int sg_finish_rem_req(Sg_request * srp); static int sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size); static ssize_t sg_new_read(Sg_fd * sfp, char __user *buf, size_t count, Sg_request * srp); static ssize_t sg_new_write(Sg_fd *sfp, struct file *file, const char __user *buf, size_t count, int blocking, int read_only, int sg_io_owned, Sg_request **o_srp); static int sg_common_write(Sg_fd * sfp, Sg_request * srp, unsigned char *cmnd, int timeout, int blocking); static int sg_read_oxfer(Sg_request * srp, char __user *outp, int num_read_xfer); static void sg_remove_scat(Sg_fd * sfp, Sg_scatter_hold * schp); static void sg_build_reserve(Sg_fd * sfp, int req_size); static void sg_link_reserve(Sg_fd * sfp, Sg_request * srp, int size); static void sg_unlink_reserve(Sg_fd * sfp, Sg_request * srp); static Sg_fd *sg_add_sfp(Sg_device * sdp); static void sg_remove_sfp(struct kref *); static Sg_request *sg_get_rq_mark(Sg_fd * sfp, int pack_id, bool *busy); static Sg_request *sg_add_request(Sg_fd * sfp); static int sg_remove_request(Sg_fd * sfp, Sg_request * srp); static Sg_device *sg_get_dev(int dev); static void sg_device_destroy(struct kref *kref); #define SZ_SG_HEADER sizeof(struct sg_header) #define SZ_SG_IO_HDR sizeof(sg_io_hdr_t) #define SZ_SG_IOVEC sizeof(sg_iovec_t) #define SZ_SG_REQ_INFO sizeof(sg_req_info_t) #define sg_printk(prefix, sdp, fmt, a...) \ sdev_prefix_printk(prefix, (sdp)->device, (sdp)->name, fmt, ##a) /* * The SCSI interfaces that use read() and write() as an asynchronous variant of * ioctl(..., SG_IO, ...) are fundamentally unsafe, since there are lots of ways * to trigger read() and write() calls from various contexts with elevated * privileges. This can lead to kernel memory corruption (e.g. if these * interfaces are called through splice()) and privilege escalation inside * userspace (e.g. if a process with access to such a device passes a file * descriptor to a SUID binary as stdin/stdout/stderr). * * This function provides protection for the legacy API by restricting the * calling context. */ static int sg_check_file_access(struct file *filp, const char *caller) { if (filp->f_cred != current_real_cred()) { pr_err_once("%s: process %d (%s) changed security contexts after opening file descriptor, this is not allowed.\n", caller, task_tgid_vnr(current), current->comm); return -EPERM; } return 0; } static int sg_allow_access(struct file *filp, unsigned char *cmd) { struct sg_fd *sfp = filp->private_data; if (sfp->parentdp->device->type == TYPE_SCANNER) return 0; if (!scsi_cmd_allowed(cmd, filp->f_mode & FMODE_WRITE)) return -EPERM; return 0; } static int open_wait(Sg_device *sdp, int flags) { int retval = 0; if (flags & O_EXCL) { while (sdp->open_cnt > 0) { mutex_unlock(&sdp->open_rel_lock); retval = wait_event_interruptible(sdp->open_wait, (atomic_read(&sdp->detaching) || !sdp->open_cnt)); mutex_lock(&sdp->open_rel_lock); if (retval) /* -ERESTARTSYS */ return retval; if (atomic_read(&sdp->detaching)) return -ENODEV; } } else { while (sdp->exclude) { mutex_unlock(&sdp->open_rel_lock); retval = wait_event_interruptible(sdp->open_wait, (atomic_read(&sdp->detaching) || !sdp->exclude)); mutex_lock(&sdp->open_rel_lock); if (retval) /* -ERESTARTSYS */ return retval; if (atomic_read(&sdp->detaching)) return -ENODEV; } } return retval; } /* Returns 0 on success, else a negated errno value */ static int sg_open(struct inode *inode, struct file *filp) { int dev = iminor(inode); int flags = filp->f_flags; struct request_queue *q; struct scsi_device *device; Sg_device *sdp; Sg_fd *sfp; int retval; nonseekable_open(inode, filp); if ((flags & O_EXCL) && (O_RDONLY == (flags & O_ACCMODE))) return -EPERM; /* Can't lock it with read only access */ sdp = sg_get_dev(dev); if (IS_ERR(sdp)) return PTR_ERR(sdp); SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_open: flags=0x%x\n", flags)); /* This driver's module count bumped by fops_get in <linux/fs.h> */ /* Prevent the device driver from vanishing while we sleep */ device = sdp->device; retval = scsi_device_get(device); if (retval) goto sg_put; /* scsi_block_when_processing_errors() may block so bypass * check if O_NONBLOCK. Permits SCSI commands to be issued * during error recovery. Tread carefully. */ if (!((flags & O_NONBLOCK) || scsi_block_when_processing_errors(device))) { retval = -ENXIO; /* we are in error recovery for this device */ goto sdp_put; } mutex_lock(&sdp->open_rel_lock); if (flags & O_NONBLOCK) { if (flags & O_EXCL) { if (sdp->open_cnt > 0) { retval = -EBUSY; goto error_mutex_locked; } } else { if (sdp->exclude) { retval = -EBUSY; goto error_mutex_locked; } } } else { retval = open_wait(sdp, flags); if (retval) /* -ERESTARTSYS or -ENODEV */ goto error_mutex_locked; } /* N.B. at this point we are holding the open_rel_lock */ if (flags & O_EXCL) sdp->exclude = true; if (sdp->open_cnt < 1) { /* no existing opens */ sdp->sgdebug = 0; q = device->request_queue; sdp->sg_tablesize = queue_max_segments(q); } sfp = sg_add_sfp(sdp); if (IS_ERR(sfp)) { retval = PTR_ERR(sfp); goto out_undo; } filp->private_data = sfp; sdp->open_cnt++; mutex_unlock(&sdp->open_rel_lock); retval = 0; sg_put: kref_put(&sdp->d_ref, sg_device_destroy); return retval; out_undo: if (flags & O_EXCL) { sdp->exclude = false; /* undo if error */ wake_up_interruptible(&sdp->open_wait); } error_mutex_locked: mutex_unlock(&sdp->open_rel_lock); sdp_put: kref_put(&sdp->d_ref, sg_device_destroy); scsi_device_put(device); return retval; } /* Release resources associated with a successful sg_open() * Returns 0 on success, else a negated errno value */ static int sg_release(struct inode *inode, struct file *filp) { Sg_device *sdp; Sg_fd *sfp; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_release\n")); mutex_lock(&sdp->open_rel_lock); sdp->open_cnt--; /* possibly many open()s waiting on exlude clearing, start many; * only open(O_EXCL)s wait on 0==open_cnt so only start one */ if (sdp->exclude) { sdp->exclude = false; wake_up_interruptible_all(&sdp->open_wait); } else if (0 == sdp->open_cnt) { wake_up_interruptible(&sdp->open_wait); } mutex_unlock(&sdp->open_rel_lock); kref_put(&sfp->f_ref, sg_remove_sfp); return 0; } static int get_sg_io_pack_id(int *pack_id, void __user *buf, size_t count) { struct sg_header __user *old_hdr = buf; int reply_len; if (count >= SZ_SG_HEADER) { /* negative reply_len means v3 format, otherwise v1/v2 */ if (get_user(reply_len, &old_hdr->reply_len)) return -EFAULT; if (reply_len >= 0) return get_user(*pack_id, &old_hdr->pack_id); if (in_compat_syscall() && count >= sizeof(struct compat_sg_io_hdr)) { struct compat_sg_io_hdr __user *hp = buf; return get_user(*pack_id, &hp->pack_id); } if (count >= sizeof(struct sg_io_hdr)) { struct sg_io_hdr __user *hp = buf; return get_user(*pack_id, &hp->pack_id); } } /* no valid header was passed, so ignore the pack_id */ *pack_id = -1; return 0; } static ssize_t sg_read(struct file *filp, char __user *buf, size_t count, loff_t * ppos) { Sg_device *sdp; Sg_fd *sfp; Sg_request *srp; int req_pack_id = -1; bool busy; sg_io_hdr_t *hp; struct sg_header *old_hdr; int retval; /* * This could cause a response to be stranded. Close the associated * file descriptor to free up any resources being held. */ retval = sg_check_file_access(filp, __func__); if (retval) return retval; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_read: count=%d\n", (int) count)); if (sfp->force_packid) retval = get_sg_io_pack_id(&req_pack_id, buf, count); if (retval) return retval; srp = sg_get_rq_mark(sfp, req_pack_id, &busy); if (!srp) { /* now wait on packet to arrive */ if (filp->f_flags & O_NONBLOCK) return -EAGAIN; retval = wait_event_interruptible(sfp->read_wait, ((srp = sg_get_rq_mark(sfp, req_pack_id, &busy)) || (!busy && atomic_read(&sdp->detaching)))); if (!srp) /* signal or detaching */ return retval ? retval : -ENODEV; } if (srp->header.interface_id != '\0') return sg_new_read(sfp, buf, count, srp); hp = &srp->header; old_hdr = kzalloc(SZ_SG_HEADER, GFP_KERNEL); if (!old_hdr) return -ENOMEM; old_hdr->reply_len = (int) hp->timeout; old_hdr->pack_len = old_hdr->reply_len; /* old, strange behaviour */ old_hdr->pack_id = hp->pack_id; old_hdr->twelve_byte = ((srp->data.cmd_opcode >= 0xc0) && (12 == hp->cmd_len)) ? 1 : 0; old_hdr->target_status = hp->masked_status; old_hdr->host_status = hp->host_status; old_hdr->driver_status = hp->driver_status; if ((CHECK_CONDITION & hp->masked_status) || (srp->sense_b[0] & 0x70) == 0x70) { old_hdr->driver_status = DRIVER_SENSE; memcpy(old_hdr->sense_buffer, srp->sense_b, sizeof (old_hdr->sense_buffer)); } switch (hp->host_status) { /* This setup of 'result' is for backward compatibility and is best ignored by the user who should use target, host + driver status */ case DID_OK: case DID_PASSTHROUGH: case DID_SOFT_ERROR: old_hdr->result = 0; break; case DID_NO_CONNECT: case DID_BUS_BUSY: case DID_TIME_OUT: old_hdr->result = EBUSY; break; case DID_BAD_TARGET: case DID_ABORT: case DID_PARITY: case DID_RESET: case DID_BAD_INTR: old_hdr->result = EIO; break; case DID_ERROR: old_hdr->result = (srp->sense_b[0] == 0 && hp->masked_status == GOOD) ? 0 : EIO; break; default: old_hdr->result = EIO; break; } /* Now copy the result back to the user buffer. */ if (count >= SZ_SG_HEADER) { if (copy_to_user(buf, old_hdr, SZ_SG_HEADER)) { retval = -EFAULT; goto free_old_hdr; } buf += SZ_SG_HEADER; if (count > old_hdr->reply_len) count = old_hdr->reply_len; if (count > SZ_SG_HEADER) { if (sg_read_oxfer(srp, buf, count - SZ_SG_HEADER)) { retval = -EFAULT; goto free_old_hdr; } } } else count = (old_hdr->result == 0) ? 0 : -EIO; sg_finish_rem_req(srp); sg_remove_request(sfp, srp); retval = count; free_old_hdr: kfree(old_hdr); return retval; } static ssize_t sg_new_read(Sg_fd * sfp, char __user *buf, size_t count, Sg_request * srp) { sg_io_hdr_t *hp = &srp->header; int err = 0, err2; int len; if (in_compat_syscall()) { if (count < sizeof(struct compat_sg_io_hdr)) { err = -EINVAL; goto err_out; } } else if (count < SZ_SG_IO_HDR) { err = -EINVAL; goto err_out; } hp->sb_len_wr = 0; if ((hp->mx_sb_len > 0) && hp->sbp) { if ((CHECK_CONDITION & hp->masked_status) || (srp->sense_b[0] & 0x70) == 0x70) { int sb_len = SCSI_SENSE_BUFFERSIZE; sb_len = (hp->mx_sb_len > sb_len) ? sb_len : hp->mx_sb_len; len = 8 + (int) srp->sense_b[7]; /* Additional sense length field */ len = (len > sb_len) ? sb_len : len; if (copy_to_user(hp->sbp, srp->sense_b, len)) { err = -EFAULT; goto err_out; } hp->driver_status = DRIVER_SENSE; hp->sb_len_wr = len; } } if (hp->masked_status || hp->host_status || hp->driver_status) hp->info |= SG_INFO_CHECK; err = put_sg_io_hdr(hp, buf); err_out: err2 = sg_finish_rem_req(srp); sg_remove_request(sfp, srp); return err ? : err2 ? : count; } static ssize_t sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos) { int mxsize, cmd_size, k; int input_size, blocking; unsigned char opcode; Sg_device *sdp; Sg_fd *sfp; Sg_request *srp; struct sg_header old_hdr; sg_io_hdr_t *hp; unsigned char cmnd[SG_MAX_CDB_SIZE]; int retval; retval = sg_check_file_access(filp, __func__); if (retval) return retval; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_write: count=%d\n", (int) count)); if (atomic_read(&sdp->detaching)) return -ENODEV; if (!((filp->f_flags & O_NONBLOCK) || scsi_block_when_processing_errors(sdp->device))) return -ENXIO; if (count < SZ_SG_HEADER) return -EIO; if (copy_from_user(&old_hdr, buf, SZ_SG_HEADER)) return -EFAULT; blocking = !(filp->f_flags & O_NONBLOCK); if (old_hdr.reply_len < 0) return sg_new_write(sfp, filp, buf, count, blocking, 0, 0, NULL); if (count < (SZ_SG_HEADER + 6)) return -EIO; /* The minimum scsi command length is 6 bytes. */ buf += SZ_SG_HEADER; if (get_user(opcode, buf)) return -EFAULT; if (!(srp = sg_add_request(sfp))) { SCSI_LOG_TIMEOUT(1, sg_printk(KERN_INFO, sdp, "sg_write: queue full\n")); return -EDOM; } mutex_lock(&sfp->f_mutex); if (sfp->next_cmd_len > 0) { cmd_size = sfp->next_cmd_len; sfp->next_cmd_len = 0; /* reset so only this write() effected */ } else { cmd_size = COMMAND_SIZE(opcode); /* based on SCSI command group */ if ((opcode >= 0xc0) && old_hdr.twelve_byte) cmd_size = 12; } mutex_unlock(&sfp->f_mutex); SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sdp, "sg_write: scsi opcode=0x%02x, cmd_size=%d\n", (int) opcode, cmd_size)); /* Determine buffer size. */ input_size = count - cmd_size; mxsize = (input_size > old_hdr.reply_len) ? input_size : old_hdr.reply_len; mxsize -= SZ_SG_HEADER; input_size -= SZ_SG_HEADER; if (input_size < 0) { sg_remove_request(sfp, srp); return -EIO; /* User did not pass enough bytes for this command. */ } hp = &srp->header; hp->interface_id = '\0'; /* indicator of old interface tunnelled */ hp->cmd_len = (unsigned char) cmd_size; hp->iovec_count = 0; hp->mx_sb_len = 0; if (input_size > 0) hp->dxfer_direction = (old_hdr.reply_len > SZ_SG_HEADER) ? SG_DXFER_TO_FROM_DEV : SG_DXFER_TO_DEV; else hp->dxfer_direction = (mxsize > 0) ? SG_DXFER_FROM_DEV : SG_DXFER_NONE; hp->dxfer_len = mxsize; if ((hp->dxfer_direction == SG_DXFER_TO_DEV) || (hp->dxfer_direction == SG_DXFER_TO_FROM_DEV)) hp->dxferp = (char __user *)buf + cmd_size; else hp->dxferp = NULL; hp->sbp = NULL; hp->timeout = old_hdr.reply_len; /* structure abuse ... */ hp->flags = input_size; /* structure abuse ... */ hp->pack_id = old_hdr.pack_id; hp->usr_ptr = NULL; if (copy_from_user(cmnd, buf, cmd_size)) { sg_remove_request(sfp, srp); return -EFAULT; } /* * SG_DXFER_TO_FROM_DEV is functionally equivalent to SG_DXFER_FROM_DEV, * but is is possible that the app intended SG_DXFER_TO_DEV, because there * is a non-zero input_size, so emit a warning. */ if (hp->dxfer_direction == SG_DXFER_TO_FROM_DEV) { printk_ratelimited(KERN_WARNING "sg_write: data in/out %d/%d bytes " "for SCSI command 0x%x-- guessing " "data in;\n program %s not setting " "count and/or reply_len properly\n", old_hdr.reply_len - (int)SZ_SG_HEADER, input_size, (unsigned int) cmnd[0], current->comm); } k = sg_common_write(sfp, srp, cmnd, sfp->timeout, blocking); return (k < 0) ? k : count; } static ssize_t sg_new_write(Sg_fd *sfp, struct file *file, const char __user *buf, size_t count, int blocking, int read_only, int sg_io_owned, Sg_request **o_srp) { int k; Sg_request *srp; sg_io_hdr_t *hp; unsigned char cmnd[SG_MAX_CDB_SIZE]; int timeout; unsigned long ul_timeout; if (count < SZ_SG_IO_HDR) return -EINVAL; sfp->cmd_q = 1; /* when sg_io_hdr seen, set command queuing on */ if (!(srp = sg_add_request(sfp))) { SCSI_LOG_TIMEOUT(1, sg_printk(KERN_INFO, sfp->parentdp, "sg_new_write: queue full\n")); return -EDOM; } srp->sg_io_owned = sg_io_owned; hp = &srp->header; if (get_sg_io_hdr(hp, buf)) { sg_remove_request(sfp, srp); return -EFAULT; } hp->duration = jiffies_to_msecs(jiffies); if (hp->interface_id != 'S') { sg_remove_request(sfp, srp); return -ENOSYS; } if (hp->flags & SG_FLAG_MMAP_IO) { if (hp->dxfer_len > sfp->reserve.bufflen) { sg_remove_request(sfp, srp); return -ENOMEM; /* MMAP_IO size must fit in reserve buffer */ } if (hp->flags & SG_FLAG_DIRECT_IO) { sg_remove_request(sfp, srp); return -EINVAL; /* either MMAP_IO or DIRECT_IO (not both) */ } if (sfp->res_in_use) { sg_remove_request(sfp, srp); return -EBUSY; /* reserve buffer already being used */ } } ul_timeout = msecs_to_jiffies(srp->header.timeout); timeout = (ul_timeout < INT_MAX) ? ul_timeout : INT_MAX; if ((!hp->cmdp) || (hp->cmd_len < 6) || (hp->cmd_len > sizeof (cmnd))) { sg_remove_request(sfp, srp); return -EMSGSIZE; } if (copy_from_user(cmnd, hp->cmdp, hp->cmd_len)) { sg_remove_request(sfp, srp); return -EFAULT; } if (read_only && sg_allow_access(file, cmnd)) { sg_remove_request(sfp, srp); return -EPERM; } k = sg_common_write(sfp, srp, cmnd, timeout, blocking); if (k < 0) return k; if (o_srp) *o_srp = srp; return count; } static int sg_common_write(Sg_fd * sfp, Sg_request * srp, unsigned char *cmnd, int timeout, int blocking) { int k, at_head; Sg_device *sdp = sfp->parentdp; sg_io_hdr_t *hp = &srp->header; srp->data.cmd_opcode = cmnd[0]; /* hold opcode of command */ hp->status = 0; hp->masked_status = 0; hp->msg_status = 0; hp->info = 0; hp->host_status = 0; hp->driver_status = 0; hp->resid = 0; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp, "sg_common_write: scsi opcode=0x%02x, cmd_size=%d\n", (int) cmnd[0], (int) hp->cmd_len)); if (hp->dxfer_len >= SZ_256M) { sg_remove_request(sfp, srp); return -EINVAL; } k = sg_start_req(srp, cmnd); if (k) { SCSI_LOG_TIMEOUT(1, sg_printk(KERN_INFO, sfp->parentdp, "sg_common_write: start_req err=%d\n", k)); sg_finish_rem_req(srp); sg_remove_request(sfp, srp); return k; /* probably out of space --> ENOMEM */ } if (atomic_read(&sdp->detaching)) { if (srp->bio) { blk_mq_free_request(srp->rq); srp->rq = NULL; } sg_finish_rem_req(srp); sg_remove_request(sfp, srp); return -ENODEV; } if (hp->interface_id != '\0' && /* v3 (or later) interface */ (SG_FLAG_Q_AT_TAIL & hp->flags)) at_head = 0; else at_head = 1; srp->rq->timeout = timeout; kref_get(&sfp->f_ref); /* sg_rq_end_io() does kref_put(). */ srp->rq->end_io = sg_rq_end_io; blk_execute_rq_nowait(srp->rq, at_head); return 0; } static int srp_done(Sg_fd *sfp, Sg_request *srp) { unsigned long flags; int ret; read_lock_irqsave(&sfp->rq_list_lock, flags); ret = srp->done; read_unlock_irqrestore(&sfp->rq_list_lock, flags); return ret; } static int max_sectors_bytes(struct request_queue *q) { unsigned int max_sectors = queue_max_sectors(q); max_sectors = min_t(unsigned int, max_sectors, INT_MAX >> 9); return max_sectors << 9; } static void sg_fill_request_table(Sg_fd *sfp, sg_req_info_t *rinfo) { Sg_request *srp; int val; unsigned int ms; val = 0; list_for_each_entry(srp, &sfp->rq_list, entry) { if (val >= SG_MAX_QUEUE) break; rinfo[val].req_state = srp->done + 1; rinfo[val].problem = srp->header.masked_status & srp->header.host_status & srp->header.driver_status; if (srp->done) rinfo[val].duration = srp->header.duration; else { ms = jiffies_to_msecs(jiffies); rinfo[val].duration = (ms > srp->header.duration) ? (ms - srp->header.duration) : 0; } rinfo[val].orphan = srp->orphan; rinfo[val].sg_io_owned = srp->sg_io_owned; rinfo[val].pack_id = srp->header.pack_id; rinfo[val].usr_ptr = srp->header.usr_ptr; val++; } } #ifdef CONFIG_COMPAT struct compat_sg_req_info { /* used by SG_GET_REQUEST_TABLE ioctl() */ char req_state; char orphan; char sg_io_owned; char problem; int pack_id; compat_uptr_t usr_ptr; unsigned int duration; int unused; }; static int put_compat_request_table(struct compat_sg_req_info __user *o, struct sg_req_info *rinfo) { int i; for (i = 0; i < SG_MAX_QUEUE; i++) { if (copy_to_user(o + i, rinfo + i, offsetof(sg_req_info_t, usr_ptr)) || put_user((uintptr_t)rinfo[i].usr_ptr, &o[i].usr_ptr) || put_user(rinfo[i].duration, &o[i].duration) || put_user(rinfo[i].unused, &o[i].unused)) return -EFAULT; } return 0; } #endif static long sg_ioctl_common(struct file *filp, Sg_device *sdp, Sg_fd *sfp, unsigned int cmd_in, void __user *p) { int __user *ip = p; int result, val, read_only; Sg_request *srp; unsigned long iflags; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_ioctl: cmd=0x%x\n", (int) cmd_in)); read_only = (O_RDWR != (filp->f_flags & O_ACCMODE)); switch (cmd_in) { case SG_IO: if (atomic_read(&sdp->detaching)) return -ENODEV; if (!scsi_block_when_processing_errors(sdp->device)) return -ENXIO; result = sg_new_write(sfp, filp, p, SZ_SG_IO_HDR, 1, read_only, 1, &srp); if (result < 0) return result; result = wait_event_interruptible(sfp->read_wait, srp_done(sfp, srp)); write_lock_irq(&sfp->rq_list_lock); if (srp->done) { srp->done = 2; write_unlock_irq(&sfp->rq_list_lock); result = sg_new_read(sfp, p, SZ_SG_IO_HDR, srp); return (result < 0) ? result : 0; } srp->orphan = 1; write_unlock_irq(&sfp->rq_list_lock); return result; /* -ERESTARTSYS because signal hit process */ case SG_SET_TIMEOUT: result = get_user(val, ip); if (result) return result; if (val < 0) return -EIO; if (val >= mult_frac((s64)INT_MAX, USER_HZ, HZ)) val = min_t(s64, mult_frac((s64)INT_MAX, USER_HZ, HZ), INT_MAX); sfp->timeout_user = val; sfp->timeout = mult_frac(val, HZ, USER_HZ); return 0; case SG_GET_TIMEOUT: /* N.B. User receives timeout as return value */ /* strange ..., for backward compatibility */ return sfp->timeout_user; case SG_SET_FORCE_LOW_DMA: /* * N.B. This ioctl never worked properly, but failed to * return an error value. So returning '0' to keep compability * with legacy applications. */ return 0; case SG_GET_LOW_DMA: return put_user(0, ip); case SG_GET_SCSI_ID: { sg_scsi_id_t v; if (atomic_read(&sdp->detaching)) return -ENODEV; memset(&v, 0, sizeof(v)); v.host_no = sdp->device->host->host_no; v.channel = sdp->device->channel; v.scsi_id = sdp->device->id; v.lun = sdp->device->lun; v.scsi_type = sdp->device->type; v.h_cmd_per_lun = sdp->device->host->cmd_per_lun; v.d_queue_depth = sdp->device->queue_depth; if (copy_to_user(p, &v, sizeof(sg_scsi_id_t))) return -EFAULT; return 0; } case SG_SET_FORCE_PACK_ID: result = get_user(val, ip); if (result) return result; sfp->force_packid = val ? 1 : 0; return 0; case SG_GET_PACK_ID: read_lock_irqsave(&sfp->rq_list_lock, iflags); list_for_each_entry(srp, &sfp->rq_list, entry) { if ((1 == srp->done) && (!srp->sg_io_owned)) { read_unlock_irqrestore(&sfp->rq_list_lock, iflags); return put_user(srp->header.pack_id, ip); } } read_unlock_irqrestore(&sfp->rq_list_lock, iflags); return put_user(-1, ip); case SG_GET_NUM_WAITING: read_lock_irqsave(&sfp->rq_list_lock, iflags); val = 0; list_for_each_entry(srp, &sfp->rq_list, entry) { if ((1 == srp->done) && (!srp->sg_io_owned)) ++val; } read_unlock_irqrestore(&sfp->rq_list_lock, iflags); return put_user(val, ip); case SG_GET_SG_TABLESIZE: return put_user(sdp->sg_tablesize, ip); case SG_SET_RESERVED_SIZE: result = get_user(val, ip); if (result) return result; if (val < 0) return -EINVAL; val = min_t(int, val, max_sectors_bytes(sdp->device->request_queue)); mutex_lock(&sfp->f_mutex); if (val != sfp->reserve.bufflen) { if (sfp->mmap_called || sfp->res_in_use) { mutex_unlock(&sfp->f_mutex); return -EBUSY; } sg_remove_scat(sfp, &sfp->reserve); sg_build_reserve(sfp, val); } mutex_unlock(&sfp->f_mutex); return 0; case SG_GET_RESERVED_SIZE: val = min_t(int, sfp->reserve.bufflen, max_sectors_bytes(sdp->device->request_queue)); return put_user(val, ip); case SG_SET_COMMAND_Q: result = get_user(val, ip); if (result) return result; sfp->cmd_q = val ? 1 : 0; return 0; case SG_GET_COMMAND_Q: return put_user((int) sfp->cmd_q, ip); case SG_SET_KEEP_ORPHAN: result = get_user(val, ip); if (result) return result; sfp->keep_orphan = val; return 0; case SG_GET_KEEP_ORPHAN: return put_user((int) sfp->keep_orphan, ip); case SG_NEXT_CMD_LEN: result = get_user(val, ip); if (result) return result; if (val > SG_MAX_CDB_SIZE) return -ENOMEM; sfp->next_cmd_len = (val > 0) ? val : 0; return 0; case SG_GET_VERSION_NUM: return put_user(sg_version_num, ip); case SG_GET_ACCESS_COUNT: /* faked - we don't have a real access count anymore */ val = (sdp->device ? 1 : 0); return put_user(val, ip); case SG_GET_REQUEST_TABLE: { sg_req_info_t *rinfo; rinfo = kcalloc(SG_MAX_QUEUE, SZ_SG_REQ_INFO, GFP_KERNEL); if (!rinfo) return -ENOMEM; read_lock_irqsave(&sfp->rq_list_lock, iflags); sg_fill_request_table(sfp, rinfo); read_unlock_irqrestore(&sfp->rq_list_lock, iflags); #ifdef CONFIG_COMPAT if (in_compat_syscall()) result = put_compat_request_table(p, rinfo); else #endif result = copy_to_user(p, rinfo, SZ_SG_REQ_INFO * SG_MAX_QUEUE); result = result ? -EFAULT : 0; kfree(rinfo); return result; } case SG_EMULATED_HOST: if (atomic_read(&sdp->detaching)) return -ENODEV; return put_user(sdp->device->host->hostt->emulated, ip); case SCSI_IOCTL_SEND_COMMAND: if (atomic_read(&sdp->detaching)) return -ENODEV; return scsi_ioctl(sdp->device, filp->f_mode & FMODE_WRITE, cmd_in, p); case SG_SET_DEBUG: result = get_user(val, ip); if (result) return result; sdp->sgdebug = (char) val; return 0; case BLKSECTGET: return put_user(max_sectors_bytes(sdp->device->request_queue), ip); case BLKTRACESETUP: return blk_trace_setup(sdp->device->request_queue, sdp->name, MKDEV(SCSI_GENERIC_MAJOR, sdp->index), NULL, p); case BLKTRACESTART: return blk_trace_startstop(sdp->device->request_queue, 1); case BLKTRACESTOP: return blk_trace_startstop(sdp->device->request_queue, 0); case BLKTRACETEARDOWN: return blk_trace_remove(sdp->device->request_queue); case SCSI_IOCTL_GET_IDLUN: case SCSI_IOCTL_GET_BUS_NUMBER: case SCSI_IOCTL_PROBE_HOST: case SG_GET_TRANSFORM: case SG_SCSI_RESET: if (atomic_read(&sdp->detaching)) return -ENODEV; break; default: if (read_only) return -EPERM; /* don't know so take safe approach */ break; } result = scsi_ioctl_block_when_processing_errors(sdp->device, cmd_in, filp->f_flags & O_NDELAY); if (result) return result; return -ENOIOCTLCMD; } static long sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg) { void __user *p = (void __user *)arg; Sg_device *sdp; Sg_fd *sfp; int ret; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; ret = sg_ioctl_common(filp, sdp, sfp, cmd_in, p); if (ret != -ENOIOCTLCMD) return ret; return scsi_ioctl(sdp->device, filp->f_mode & FMODE_WRITE, cmd_in, p); } static __poll_t sg_poll(struct file *filp, poll_table * wait) { __poll_t res = 0; Sg_device *sdp; Sg_fd *sfp; Sg_request *srp; int count = 0; unsigned long iflags; sfp = filp->private_data; if (!sfp) return EPOLLERR; sdp = sfp->parentdp; if (!sdp) return EPOLLERR; poll_wait(filp, &sfp->read_wait, wait); read_lock_irqsave(&sfp->rq_list_lock, iflags); list_for_each_entry(srp, &sfp->rq_list, entry) { /* if any read waiting, flag it */ if ((0 == res) && (1 == srp->done) && (!srp->sg_io_owned)) res = EPOLLIN | EPOLLRDNORM; ++count; } read_unlock_irqrestore(&sfp->rq_list_lock, iflags); if (atomic_read(&sdp->detaching)) res |= EPOLLHUP; else if (!sfp->cmd_q) { if (0 == count) res |= EPOLLOUT | EPOLLWRNORM; } else if (count < SG_MAX_QUEUE) res |= EPOLLOUT | EPOLLWRNORM; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_poll: res=0x%x\n", (__force u32) res)); return res; } static int sg_fasync(int fd, struct file *filp, int mode) { Sg_device *sdp; Sg_fd *sfp; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_fasync: mode=%d\n", mode)); return fasync_helper(fd, filp, mode, &sfp->async_qp); } static vm_fault_t sg_vma_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; Sg_fd *sfp; unsigned long offset, len, sa; Sg_scatter_hold *rsv_schp; int k, length; if ((NULL == vma) || (!(sfp = (Sg_fd *) vma->vm_private_data))) return VM_FAULT_SIGBUS; rsv_schp = &sfp->reserve; offset = vmf->pgoff << PAGE_SHIFT; if (offset >= rsv_schp->bufflen) return VM_FAULT_SIGBUS; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sfp->parentdp, "sg_vma_fault: offset=%lu, scatg=%d\n", offset, rsv_schp->k_use_sg)); sa = vma->vm_start; length = 1 << (PAGE_SHIFT + rsv_schp->page_order); for (k = 0; k < rsv_schp->k_use_sg && sa < vma->vm_end; k++) { len = vma->vm_end - sa; len = (len < length) ? len : length; if (offset < len) { struct page *page = rsv_schp->pages[k] + (offset >> PAGE_SHIFT); get_page(page); /* increment page count */ vmf->page = page; return 0; /* success */ } sa += len; offset -= len; } return VM_FAULT_SIGBUS; } static const struct vm_operations_struct sg_mmap_vm_ops = { .fault = sg_vma_fault, }; static int sg_mmap(struct file *filp, struct vm_area_struct *vma) { Sg_fd *sfp; unsigned long req_sz, len, sa; Sg_scatter_hold *rsv_schp; int k, length; int ret = 0; if ((!filp) || (!vma) || (!(sfp = (Sg_fd *) filp->private_data))) return -ENXIO; req_sz = vma->vm_end - vma->vm_start; SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sfp->parentdp, "sg_mmap starting, vm_start=%p, len=%d\n", (void *) vma->vm_start, (int) req_sz)); if (vma->vm_pgoff) return -EINVAL; /* want no offset */ rsv_schp = &sfp->reserve; mutex_lock(&sfp->f_mutex); if (req_sz > rsv_schp->bufflen) { ret = -ENOMEM; /* cannot map more than reserved buffer */ goto out; } sa = vma->vm_start; length = 1 << (PAGE_SHIFT + rsv_schp->page_order); for (k = 0; k < rsv_schp->k_use_sg && sa < vma->vm_end; k++) { len = vma->vm_end - sa; len = (len < length) ? len : length; sa += len; } sfp->mmap_called = 1; vm_flags_set(vma, VM_IO | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_private_data = sfp; vma->vm_ops = &sg_mmap_vm_ops; out: mutex_unlock(&sfp->f_mutex); return ret; } static void sg_rq_end_io_usercontext(struct work_struct *work) { struct sg_request *srp = container_of(work, struct sg_request, ew.work); struct sg_fd *sfp = srp->parentfp; sg_finish_rem_req(srp); sg_remove_request(sfp, srp); kref_put(&sfp->f_ref, sg_remove_sfp); } /* * This function is a "bottom half" handler that is called by the mid * level when a command is completed (or has failed). */ static enum rq_end_io_ret sg_rq_end_io(struct request *rq, blk_status_t status) { struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(rq); struct sg_request *srp = rq->end_io_data; Sg_device *sdp; Sg_fd *sfp; unsigned long iflags; unsigned int ms; char *sense; int result, resid, done = 1; if (WARN_ON(srp->done != 0)) return RQ_END_IO_NONE; sfp = srp->parentfp; if (WARN_ON(sfp == NULL)) return RQ_END_IO_NONE; sdp = sfp->parentdp; if (unlikely(atomic_read(&sdp->detaching))) pr_info("%s: device detaching\n", __func__); sense = scmd->sense_buffer; result = scmd->result; resid = scmd->resid_len; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sdp, "sg_cmd_done: pack_id=%d, res=0x%x\n", srp->header.pack_id, result)); srp->header.resid = resid; if (0 != result) { struct scsi_sense_hdr sshdr; srp->header.status = 0xff & result; srp->header.masked_status = sg_status_byte(result); srp->header.msg_status = COMMAND_COMPLETE; srp->header.host_status = host_byte(result); srp->header.driver_status = driver_byte(result); if ((sdp->sgdebug > 0) && ((CHECK_CONDITION == srp->header.masked_status) || (COMMAND_TERMINATED == srp->header.masked_status))) __scsi_print_sense(sdp->device, __func__, sense, SCSI_SENSE_BUFFERSIZE); /* Following if statement is a patch supplied by Eric Youngdale */ if (driver_byte(result) != 0 && scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE, &sshdr) && !scsi_sense_is_deferred(&sshdr) && sshdr.sense_key == UNIT_ATTENTION && sdp->device->removable) { /* Detected possible disc change. Set the bit - this */ /* may be used if there are filesystems using this device */ sdp->device->changed = 1; } } if (scmd->sense_len) memcpy(srp->sense_b, scmd->sense_buffer, SCSI_SENSE_BUFFERSIZE); /* Rely on write phase to clean out srp status values, so no "else" */ /* * Free the request as soon as it is complete so that its resources * can be reused without waiting for userspace to read() the * result. But keep the associated bio (if any) around until * blk_rq_unmap_user() can be called from user context. */ srp->rq = NULL; blk_mq_free_request(rq); write_lock_irqsave(&sfp->rq_list_lock, iflags); if (unlikely(srp->orphan)) { if (sfp->keep_orphan) srp->sg_io_owned = 0; else done = 0; } srp->done = done; ms = jiffies_to_msecs(jiffies); srp->header.duration = (ms > srp->header.duration) ? (ms - srp->header.duration) : 0; write_unlock_irqrestore(&sfp->rq_list_lock, iflags); if (likely(done)) { /* Now wake up any sg_read() that is waiting for this * packet. */ wake_up_interruptible(&sfp->read_wait); kill_fasync(&sfp->async_qp, SIGPOLL, POLL_IN); kref_put(&sfp->f_ref, sg_remove_sfp); } else { INIT_WORK(&srp->ew.work, sg_rq_end_io_usercontext); schedule_work(&srp->ew.work); } return RQ_END_IO_NONE; } static const struct file_operations sg_fops = { .owner = THIS_MODULE, .read = sg_read, .write = sg_write, .poll = sg_poll, .unlocked_ioctl = sg_ioctl, .compat_ioctl = compat_ptr_ioctl, .open = sg_open, .mmap = sg_mmap, .release = sg_release, .fasync = sg_fasync, }; static const struct class sg_sysfs_class = { .name = "scsi_generic" }; static int sg_sysfs_valid = 0; static Sg_device * sg_alloc(struct scsi_device *scsidp) { struct request_queue *q = scsidp->request_queue; Sg_device *sdp; unsigned long iflags; int error; u32 k; sdp = kzalloc(sizeof(Sg_device), GFP_KERNEL); if (!sdp) { sdev_printk(KERN_WARNING, scsidp, "%s: kmalloc Sg_device " "failure\n", __func__); return ERR_PTR(-ENOMEM); } idr_preload(GFP_KERNEL); write_lock_irqsave(&sg_index_lock, iflags); error = idr_alloc(&sg_index_idr, sdp, 0, SG_MAX_DEVS, GFP_NOWAIT); if (error < 0) { if (error == -ENOSPC) { sdev_printk(KERN_WARNING, scsidp, "Unable to attach sg device type=%d, minor number exceeds %d\n", scsidp->type, SG_MAX_DEVS - 1); error = -ENODEV; } else { sdev_printk(KERN_WARNING, scsidp, "%s: idr " "allocation Sg_device failure: %d\n", __func__, error); } goto out_unlock; } k = error; SCSI_LOG_TIMEOUT(3, sdev_printk(KERN_INFO, scsidp, "sg_alloc: dev=%d \n", k)); sprintf(sdp->name, "sg%d", k); sdp->device = scsidp; mutex_init(&sdp->open_rel_lock); INIT_LIST_HEAD(&sdp->sfds); init_waitqueue_head(&sdp->open_wait); atomic_set(&sdp->detaching, 0); rwlock_init(&sdp->sfd_lock); sdp->sg_tablesize = queue_max_segments(q); sdp->index = k; kref_init(&sdp->d_ref); error = 0; out_unlock: write_unlock_irqrestore(&sg_index_lock, iflags); idr_preload_end(); if (error) { kfree(sdp); return ERR_PTR(error); } return sdp; } static int sg_add_device(struct device *cl_dev) { struct scsi_device *scsidp = to_scsi_device(cl_dev->parent); Sg_device *sdp = NULL; struct cdev * cdev = NULL; int error; unsigned long iflags; if (!blk_get_queue(scsidp->request_queue)) { pr_warn("%s: get scsi_device queue failed\n", __func__); return -ENODEV; } error = -ENOMEM; cdev = cdev_alloc(); if (!cdev) { pr_warn("%s: cdev_alloc failed\n", __func__); goto out; } cdev->owner = THIS_MODULE; cdev->ops = &sg_fops; sdp = sg_alloc(scsidp); if (IS_ERR(sdp)) { pr_warn("%s: sg_alloc failed\n", __func__); error = PTR_ERR(sdp); goto out; } error = cdev_add(cdev, MKDEV(SCSI_GENERIC_MAJOR, sdp->index), 1); if (error) goto cdev_add_err; sdp->cdev = cdev; if (sg_sysfs_valid) { struct device *sg_class_member; sg_class_member = device_create(&sg_sysfs_class, cl_dev->parent, MKDEV(SCSI_GENERIC_MAJOR, sdp->index), sdp, "%s", sdp->name); if (IS_ERR(sg_class_member)) { pr_err("%s: device_create failed\n", __func__); error = PTR_ERR(sg_class_member); goto cdev_add_err; } error = sysfs_create_link(&scsidp->sdev_gendev.kobj, &sg_class_member->kobj, "generic"); if (error) pr_err("%s: unable to make symlink 'generic' back " "to sg%d\n", __func__, sdp->index); } else pr_warn("%s: sg_sys Invalid\n", __func__); sdev_printk(KERN_NOTICE, scsidp, "Attached scsi generic sg%d " "type %d\n", sdp->index, scsidp->type); dev_set_drvdata(cl_dev, sdp); return 0; cdev_add_err: write_lock_irqsave(&sg_index_lock, iflags); idr_remove(&sg_index_idr, sdp->index); write_unlock_irqrestore(&sg_index_lock, iflags); kfree(sdp); out: if (cdev) cdev_del(cdev); blk_put_queue(scsidp->request_queue); return error; } static void sg_device_destroy(struct kref *kref) { struct sg_device *sdp = container_of(kref, struct sg_device, d_ref); struct request_queue *q = sdp->device->request_queue; unsigned long flags; /* CAUTION! Note that the device can still be found via idr_find() * even though the refcount is 0. Therefore, do idr_remove() BEFORE * any other cleanup. */ blk_trace_remove(q); blk_put_queue(q); write_lock_irqsave(&sg_index_lock, flags); idr_remove(&sg_index_idr, sdp->index); write_unlock_irqrestore(&sg_index_lock, flags); SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_device_destroy\n")); kfree(sdp); } static void sg_remove_device(struct device *cl_dev) { struct scsi_device *scsidp = to_scsi_device(cl_dev->parent); Sg_device *sdp = dev_get_drvdata(cl_dev); unsigned long iflags; Sg_fd *sfp; int val; if (!sdp) return; /* want sdp->detaching non-zero as soon as possible */ val = atomic_inc_return(&sdp->detaching); if (val > 1) return; /* only want to do following once per device */ SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "%s\n", __func__)); read_lock_irqsave(&sdp->sfd_lock, iflags); list_for_each_entry(sfp, &sdp->sfds, sfd_siblings) { wake_up_interruptible_all(&sfp->read_wait); kill_fasync(&sfp->async_qp, SIGPOLL, POLL_HUP); } wake_up_interruptible_all(&sdp->open_wait); read_unlock_irqrestore(&sdp->sfd_lock, iflags); sysfs_remove_link(&scsidp->sdev_gendev.kobj, "generic"); device_destroy(&sg_sysfs_class, MKDEV(SCSI_GENERIC_MAJOR, sdp->index)); cdev_del(sdp->cdev); sdp->cdev = NULL; kref_put(&sdp->d_ref, sg_device_destroy); } module_param_named(scatter_elem_sz, scatter_elem_sz, int, S_IRUGO | S_IWUSR); module_param_named(def_reserved_size, def_reserved_size, int, S_IRUGO | S_IWUSR); module_param_named(allow_dio, sg_allow_dio, int, S_IRUGO | S_IWUSR); MODULE_AUTHOR("Douglas Gilbert"); MODULE_DESCRIPTION("SCSI generic (sg) driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(SG_VERSION_STR); MODULE_ALIAS_CHARDEV_MAJOR(SCSI_GENERIC_MAJOR); MODULE_PARM_DESC(scatter_elem_sz, "scatter gather element " "size (default: max(SG_SCATTER_SZ, PAGE_SIZE))"); MODULE_PARM_DESC(def_reserved_size, "size of buffer reserved for each fd"); MODULE_PARM_DESC(allow_dio, "allow direct I/O (default: 0 (disallow))"); #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> static const struct ctl_table sg_sysctls[] = { { .procname = "sg-big-buff", .data = &sg_big_buff, .maxlen = sizeof(int), .mode = 0444, .proc_handler = proc_dointvec, }, }; static struct ctl_table_header *hdr; static void register_sg_sysctls(void) { if (!hdr) hdr = register_sysctl("kernel", sg_sysctls); } static void unregister_sg_sysctls(void) { unregister_sysctl_table(hdr); } #else #define register_sg_sysctls() do { } while (0) #define unregister_sg_sysctls() do { } while (0) #endif /* CONFIG_SYSCTL */ static int __init init_sg(void) { int rc; if (scatter_elem_sz < PAGE_SIZE) { scatter_elem_sz = PAGE_SIZE; scatter_elem_sz_prev = scatter_elem_sz; } if (def_reserved_size >= 0) sg_big_buff = def_reserved_size; else def_reserved_size = sg_big_buff; rc = register_chrdev_region(MKDEV(SCSI_GENERIC_MAJOR, 0), SG_MAX_DEVS, "sg"); if (rc) return rc; rc = class_register(&sg_sysfs_class); if (rc) goto err_out; sg_sysfs_valid = 1; rc = scsi_register_interface(&sg_interface); if (0 == rc) { #ifdef CONFIG_SCSI_PROC_FS sg_proc_init(); #endif /* CONFIG_SCSI_PROC_FS */ return 0; } class_unregister(&sg_sysfs_class); register_sg_sysctls(); err_out: unregister_chrdev_region(MKDEV(SCSI_GENERIC_MAJOR, 0), SG_MAX_DEVS); return rc; } static void __exit exit_sg(void) { unregister_sg_sysctls(); #ifdef CONFIG_SCSI_PROC_FS remove_proc_subtree("scsi/sg", NULL); #endif /* CONFIG_SCSI_PROC_FS */ scsi_unregister_interface(&sg_interface); class_unregister(&sg_sysfs_class); sg_sysfs_valid = 0; unregister_chrdev_region(MKDEV(SCSI_GENERIC_MAJOR, 0), SG_MAX_DEVS); idr_destroy(&sg_index_idr); } static int sg_start_req(Sg_request *srp, unsigned char *cmd) { int res; struct request *rq; Sg_fd *sfp = srp->parentfp; sg_io_hdr_t *hp = &srp->header; int dxfer_len = (int) hp->dxfer_len; int dxfer_dir = hp->dxfer_direction; unsigned int iov_count = hp->iovec_count; Sg_scatter_hold *req_schp = &srp->data; Sg_scatter_hold *rsv_schp = &sfp->reserve; struct request_queue *q = sfp->parentdp->device->request_queue; struct rq_map_data *md, map_data; int rw = hp->dxfer_direction == SG_DXFER_TO_DEV ? ITER_SOURCE : ITER_DEST; struct scsi_cmnd *scmd; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp, "sg_start_req: dxfer_len=%d\n", dxfer_len)); /* * NOTE * * With scsi-mq enabled, there are a fixed number of preallocated * requests equal in number to shost->can_queue. If all of the * preallocated requests are already in use, then scsi_alloc_request() * will sleep until an active command completes, freeing up a request. * Although waiting in an asynchronous interface is less than ideal, we * do not want to use BLK_MQ_REQ_NOWAIT here because userspace might * not expect an EWOULDBLOCK from this condition. */ rq = scsi_alloc_request(q, hp->dxfer_direction == SG_DXFER_TO_DEV ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); if (IS_ERR(rq)) return PTR_ERR(rq); scmd = blk_mq_rq_to_pdu(rq); if (hp->cmd_len > sizeof(scmd->cmnd)) { blk_mq_free_request(rq); return -EINVAL; } memcpy(scmd->cmnd, cmd, hp->cmd_len); scmd->cmd_len = hp->cmd_len; srp->rq = rq; rq->end_io_data = srp; scmd->allowed = SG_DEFAULT_RETRIES; if ((dxfer_len <= 0) || (dxfer_dir == SG_DXFER_NONE)) return 0; if (sg_allow_dio && hp->flags & SG_FLAG_DIRECT_IO && dxfer_dir != SG_DXFER_UNKNOWN && !iov_count && blk_rq_aligned(q, (unsigned long)hp->dxferp, dxfer_len)) md = NULL; else md = &map_data; if (md) { mutex_lock(&sfp->f_mutex); if (dxfer_len <= rsv_schp->bufflen && !sfp->res_in_use) { sfp->res_in_use = 1; sg_link_reserve(sfp, srp, dxfer_len); } else if (hp->flags & SG_FLAG_MMAP_IO) { res = -EBUSY; /* sfp->res_in_use == 1 */ if (dxfer_len > rsv_schp->bufflen) res = -ENOMEM; mutex_unlock(&sfp->f_mutex); return res; } else { res = sg_build_indirect(req_schp, sfp, dxfer_len); if (res) { mutex_unlock(&sfp->f_mutex); return res; } } mutex_unlock(&sfp->f_mutex); md->pages = req_schp->pages; md->page_order = req_schp->page_order; md->nr_entries = req_schp->k_use_sg; md->offset = 0; md->null_mapped = hp->dxferp ? 0 : 1; if (dxfer_dir == SG_DXFER_TO_FROM_DEV) md->from_user = 1; else md->from_user = 0; } res = blk_rq_map_user_io(rq, md, hp->dxferp, hp->dxfer_len, GFP_ATOMIC, iov_count, iov_count, 1, rw); if (!res) { srp->bio = rq->bio; if (!md) { req_schp->dio_in_use = 1; hp->info |= SG_INFO_DIRECT_IO; } } return res; } static int sg_finish_rem_req(Sg_request *srp) { int ret = 0; Sg_fd *sfp = srp->parentfp; Sg_scatter_hold *req_schp = &srp->data; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp, "sg_finish_rem_req: res_used=%d\n", (int) srp->res_used)); if (srp->bio) ret = blk_rq_unmap_user(srp->bio); if (srp->rq) blk_mq_free_request(srp->rq); if (srp->res_used) sg_unlink_reserve(sfp, srp); else sg_remove_scat(sfp, req_schp); return ret; } static int sg_build_sgat(Sg_scatter_hold * schp, const Sg_fd * sfp, int tablesize) { int sg_bufflen = tablesize * sizeof(struct page *); gfp_t gfp_flags = GFP_ATOMIC | __GFP_NOWARN; schp->pages = kzalloc(sg_bufflen, gfp_flags); if (!schp->pages) return -ENOMEM; schp->sglist_len = sg_bufflen; return tablesize; /* number of scat_gath elements allocated */ } static int sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size) { int ret_sz = 0, i, k, rem_sz, num, mx_sc_elems; int sg_tablesize = sfp->parentdp->sg_tablesize; int blk_size = buff_size, order; gfp_t gfp_mask = GFP_ATOMIC | __GFP_COMP | __GFP_NOWARN | __GFP_ZERO; if (blk_size < 0) return -EFAULT; if (0 == blk_size) ++blk_size; /* don't know why */ /* round request up to next highest SG_SECTOR_SZ byte boundary */ blk_size = ALIGN(blk_size, SG_SECTOR_SZ); SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp, "sg_build_indirect: buff_size=%d, blk_size=%d\n", buff_size, blk_size)); /* N.B. ret_sz carried into this block ... */ mx_sc_elems = sg_build_sgat(schp, sfp, sg_tablesize); if (mx_sc_elems < 0) return mx_sc_elems; /* most likely -ENOMEM */ num = scatter_elem_sz; if (unlikely(num != scatter_elem_sz_prev)) { if (num < PAGE_SIZE) { scatter_elem_sz = PAGE_SIZE; scatter_elem_sz_prev = PAGE_SIZE; } else scatter_elem_sz_prev = num; } order = get_order(num); retry: ret_sz = 1 << (PAGE_SHIFT + order); for (k = 0, rem_sz = blk_size; rem_sz > 0 && k < mx_sc_elems; k++, rem_sz -= ret_sz) { num = (rem_sz > scatter_elem_sz_prev) ? scatter_elem_sz_prev : rem_sz; schp->pages[k] = alloc_pages(gfp_mask, order); if (!schp->pages[k]) goto out; if (num == scatter_elem_sz_prev) { if (unlikely(ret_sz > scatter_elem_sz_prev)) { scatter_elem_sz = ret_sz; scatter_elem_sz_prev = ret_sz; } } SCSI_LOG_TIMEOUT(5, sg_printk(KERN_INFO, sfp->parentdp, "sg_build_indirect: k=%d, num=%d, ret_sz=%d\n", k, num, ret_sz)); } /* end of for loop */ schp->page_order = order; schp->k_use_sg = k; SCSI_LOG_TIMEOUT(5, sg_printk(KERN_INFO, sfp->parentdp, "sg_build_indirect: k_use_sg=%d, rem_sz=%d\n", k, rem_sz)); schp->bufflen = blk_size; if (rem_sz > 0) /* must have failed */ return -ENOMEM; return 0; out: for (i = 0; i < k; i++) __free_pages(schp->pages[i], order); if (--order >= 0) goto retry; return -ENOMEM; } static void sg_remove_scat(Sg_fd * sfp, Sg_scatter_hold * schp) { SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp, "sg_remove_scat: k_use_sg=%d\n", schp->k_use_sg)); if (schp->pages && schp->sglist_len > 0) { if (!schp->dio_in_use) { int k; for (k = 0; k < schp->k_use_sg && schp->pages[k]; k++) { SCSI_LOG_TIMEOUT(5, sg_printk(KERN_INFO, sfp->parentdp, "sg_remove_scat: k=%d, pg=0x%p\n", k, schp->pages[k])); __free_pages(schp->pages[k], schp->page_order); } kfree(schp->pages); } } memset(schp, 0, sizeof (*schp)); } static int sg_read_oxfer(Sg_request * srp, char __user *outp, int num_read_xfer) { Sg_scatter_hold *schp = &srp->data; int k, num; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, srp->parentfp->parentdp, "sg_read_oxfer: num_read_xfer=%d\n", num_read_xfer)); if ((!outp) || (num_read_xfer <= 0)) return 0; num = 1 << (PAGE_SHIFT + schp->page_order); for (k = 0; k < schp->k_use_sg && schp->pages[k]; k++) { if (num > num_read_xfer) { if (copy_to_user(outp, page_address(schp->pages[k]), num_read_xfer)) return -EFAULT; break; } else { if (copy_to_user(outp, page_address(schp->pages[k]), num)) return -EFAULT; num_read_xfer -= num; if (num_read_xfer <= 0) break; outp += num; } } return 0; } static void sg_build_reserve(Sg_fd * sfp, int req_size) { Sg_scatter_hold *schp = &sfp->reserve; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp, "sg_build_reserve: req_size=%d\n", req_size)); do { if (req_size < PAGE_SIZE) req_size = PAGE_SIZE; if (0 == sg_build_indirect(schp, sfp, req_size)) return; else sg_remove_scat(sfp, schp); req_size >>= 1; /* divide by 2 */ } while (req_size > (PAGE_SIZE / 2)); } static void sg_link_reserve(Sg_fd * sfp, Sg_request * srp, int size) { Sg_scatter_hold *req_schp = &srp->data; Sg_scatter_hold *rsv_schp = &sfp->reserve; int k, num, rem; srp->res_used = 1; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sfp->parentdp, "sg_link_reserve: size=%d\n", size)); rem = size; num = 1 << (PAGE_SHIFT + rsv_schp->page_order); for (k = 0; k < rsv_schp->k_use_sg; k++) { if (rem <= num) { req_schp->k_use_sg = k + 1; req_schp->sglist_len = rsv_schp->sglist_len; req_schp->pages = rsv_schp->pages; req_schp->bufflen = size; req_schp->page_order = rsv_schp->page_order; break; } else rem -= num; } if (k >= rsv_schp->k_use_sg) SCSI_LOG_TIMEOUT(1, sg_printk(KERN_INFO, sfp->parentdp, "sg_link_reserve: BAD size\n")); } static void sg_unlink_reserve(Sg_fd * sfp, Sg_request * srp) { Sg_scatter_hold *req_schp = &srp->data; SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, srp->parentfp->parentdp, "sg_unlink_reserve: req->k_use_sg=%d\n", (int) req_schp->k_use_sg)); req_schp->k_use_sg = 0; req_schp->bufflen = 0; req_schp->pages = NULL; req_schp->page_order = 0; req_schp->sglist_len = 0; srp->res_used = 0; /* Called without mutex lock to avoid deadlock */ sfp->res_in_use = 0; } static Sg_request * sg_get_rq_mark(Sg_fd * sfp, int pack_id, bool *busy) { Sg_request *resp; unsigned long iflags; *busy = false; write_lock_irqsave(&sfp->rq_list_lock, iflags); list_for_each_entry(resp, &sfp->rq_list, entry) { /* look for requests that are not SG_IO owned */ if ((!resp->sg_io_owned) && ((-1 == pack_id) || (resp->header.pack_id == pack_id))) { switch (resp->done) { case 0: /* request active */ *busy = true; break; case 1: /* request done; response ready to return */ resp->done = 2; /* guard against other readers */ write_unlock_irqrestore(&sfp->rq_list_lock, iflags); return resp; case 2: /* response already being returned */ break; } } } write_unlock_irqrestore(&sfp->rq_list_lock, iflags); return NULL; } /* always adds to end of list */ static Sg_request * sg_add_request(Sg_fd * sfp) { int k; unsigned long iflags; Sg_request *rp = sfp->req_arr; write_lock_irqsave(&sfp->rq_list_lock, iflags); if (!list_empty(&sfp->rq_list)) { if (!sfp->cmd_q) goto out_unlock; for (k = 0; k < SG_MAX_QUEUE; ++k, ++rp) { if (!rp->parentfp) break; } if (k >= SG_MAX_QUEUE) goto out_unlock; } memset(rp, 0, sizeof (Sg_request)); rp->parentfp = sfp; rp->header.duration = jiffies_to_msecs(jiffies); list_add_tail(&rp->entry, &sfp->rq_list); write_unlock_irqrestore(&sfp->rq_list_lock, iflags); return rp; out_unlock: write_unlock_irqrestore(&sfp->rq_list_lock, iflags); return NULL; } /* Return of 1 for found; 0 for not found */ static int sg_remove_request(Sg_fd * sfp, Sg_request * srp) { unsigned long iflags; int res = 0; if (!sfp || !srp || list_empty(&sfp->rq_list)) return res; write_lock_irqsave(&sfp->rq_list_lock, iflags); if (!list_empty(&srp->entry)) { list_del(&srp->entry); srp->parentfp = NULL; res = 1; } write_unlock_irqrestore(&sfp->rq_list_lock, iflags); /* * If the device is detaching, wakeup any readers in case we just * removed the last response, which would leave nothing for them to * return other than -ENODEV. */ if (unlikely(atomic_read(&sfp->parentdp->detaching))) wake_up_interruptible_all(&sfp->read_wait); return res; } static Sg_fd * sg_add_sfp(Sg_device * sdp) { Sg_fd *sfp; unsigned long iflags; int bufflen; sfp = kzalloc(sizeof(*sfp), GFP_ATOMIC | __GFP_NOWARN); if (!sfp) return ERR_PTR(-ENOMEM); init_waitqueue_head(&sfp->read_wait); rwlock_init(&sfp->rq_list_lock); INIT_LIST_HEAD(&sfp->rq_list); kref_init(&sfp->f_ref); mutex_init(&sfp->f_mutex); sfp->timeout = SG_DEFAULT_TIMEOUT; sfp->timeout_user = SG_DEFAULT_TIMEOUT_USER; sfp->force_packid = SG_DEF_FORCE_PACK_ID; sfp->cmd_q = SG_DEF_COMMAND_Q; sfp->keep_orphan = SG_DEF_KEEP_ORPHAN; sfp->parentdp = sdp; write_lock_irqsave(&sdp->sfd_lock, iflags); if (atomic_read(&sdp->detaching)) { write_unlock_irqrestore(&sdp->sfd_lock, iflags); kfree(sfp); return ERR_PTR(-ENODEV); } list_add_tail(&sfp->sfd_siblings, &sdp->sfds); write_unlock_irqrestore(&sdp->sfd_lock, iflags); SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_add_sfp: sfp=0x%p\n", sfp)); if (unlikely(sg_big_buff != def_reserved_size)) sg_big_buff = def_reserved_size; bufflen = min_t(int, sg_big_buff, max_sectors_bytes(sdp->device->request_queue)); sg_build_reserve(sfp, bufflen); SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp, "sg_add_sfp: bufflen=%d, k_use_sg=%d\n", sfp->reserve.bufflen, sfp->reserve.k_use_sg)); kref_get(&sdp->d_ref); __module_get(THIS_MODULE); return sfp; } static void sg_remove_sfp_usercontext(struct work_struct *work) { struct sg_fd *sfp = container_of(work, struct sg_fd, ew.work); struct sg_device *sdp = sfp->parentdp; struct scsi_device *device = sdp->device; Sg_request *srp; unsigned long iflags; /* Cleanup any responses which were never read(). */ write_lock_irqsave(&sfp->rq_list_lock, iflags); while (!list_empty(&sfp->rq_list)) { srp = list_first_entry(&sfp->rq_list, Sg_request, entry); list_del(&srp->entry); write_unlock_irqrestore(&sfp->rq_list_lock, iflags); sg_finish_rem_req(srp); /* * sg_rq_end_io() uses srp->parentfp. Hence, only clear * srp->parentfp after blk_mq_free_request() has been called. */ srp->parentfp = NULL; write_lock_irqsave(&sfp->rq_list_lock, iflags); } write_unlock_irqrestore(&sfp->rq_list_lock, iflags); if (sfp->reserve.bufflen > 0) { SCSI_LOG_TIMEOUT(6, sg_printk(KERN_INFO, sdp, "sg_remove_sfp: bufflen=%d, k_use_sg=%d\n", (int) sfp->reserve.bufflen, (int) sfp->reserve.k_use_sg)); sg_remove_scat(sfp, &sfp->reserve); } SCSI_LOG_TIMEOUT(6, sg_printk(KERN_INFO, sdp, "sg_remove_sfp: sfp=0x%p\n", sfp)); kfree(sfp); kref_put(&sdp->d_ref, sg_device_destroy); scsi_device_put(device); module_put(THIS_MODULE); } static void sg_remove_sfp(struct kref *kref) { struct sg_fd *sfp = container_of(kref, struct sg_fd, f_ref); struct sg_device *sdp = sfp->parentdp; unsigned long iflags; write_lock_irqsave(&sdp->sfd_lock, iflags); list_del(&sfp->sfd_siblings); write_unlock_irqrestore(&sdp->sfd_lock, iflags); INIT_WORK(&sfp->ew.work, sg_remove_sfp_usercontext); schedule_work(&sfp->ew.work); } #ifdef CONFIG_SCSI_PROC_FS static int sg_idr_max_id(int id, void *p, void *data) { int *k = data; if (*k < id) *k = id; return 0; } static int sg_last_dev(void) { int k = -1; unsigned long iflags; read_lock_irqsave(&sg_index_lock, iflags); idr_for_each(&sg_index_idr, sg_idr_max_id, &k); read_unlock_irqrestore(&sg_index_lock, iflags); return k + 1; /* origin 1 */ } #endif /* must be called with sg_index_lock held */ static Sg_device *sg_lookup_dev(int dev) { return idr_find(&sg_index_idr, dev); } static Sg_device * sg_get_dev(int dev) { struct sg_device *sdp; unsigned long flags; read_lock_irqsave(&sg_index_lock, flags); sdp = sg_lookup_dev(dev); if (!sdp) sdp = ERR_PTR(-ENXIO); else if (atomic_read(&sdp->detaching)) { /* If sdp->detaching, then the refcount may already be 0, in * which case it would be a bug to do kref_get(). */ sdp = ERR_PTR(-ENODEV); } else kref_get(&sdp->d_ref); read_unlock_irqrestore(&sg_index_lock, flags); return sdp; } #ifdef CONFIG_SCSI_PROC_FS static int sg_proc_seq_show_int(struct seq_file *s, void *v); static int sg_proc_single_open_adio(struct inode *inode, struct file *file); static ssize_t sg_proc_write_adio(struct file *filp, const char __user *buffer, size_t count, loff_t *off); static const struct proc_ops adio_proc_ops = { .proc_open = sg_proc_single_open_adio, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_write = sg_proc_write_adio, .proc_release = single_release, }; static int sg_proc_single_open_dressz(struct inode *inode, struct file *file); static ssize_t sg_proc_write_dressz(struct file *filp, const char __user *buffer, size_t count, loff_t *off); static const struct proc_ops dressz_proc_ops = { .proc_open = sg_proc_single_open_dressz, .proc_read = seq_read, .proc_lseek = seq_lseek, .proc_write = sg_proc_write_dressz, .proc_release = single_release, }; static int sg_proc_seq_show_version(struct seq_file *s, void *v); static int sg_proc_seq_show_devhdr(struct seq_file *s, void *v); static int sg_proc_seq_show_dev(struct seq_file *s, void *v); static void * dev_seq_start(struct seq_file *s, loff_t *pos); static void * dev_seq_next(struct seq_file *s, void *v, loff_t *pos); static void dev_seq_stop(struct seq_file *s, void *v); static const struct seq_operations dev_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, .show = sg_proc_seq_show_dev, }; static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v); static const struct seq_operations devstrs_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, .show = sg_proc_seq_show_devstrs, }; static int sg_proc_seq_show_debug(struct seq_file *s, void *v); static const struct seq_operations debug_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, .show = sg_proc_seq_show_debug, }; static int sg_proc_init(void) { struct proc_dir_entry *p; p = proc_mkdir("scsi/sg", NULL); if (!p) return 1; proc_create("allow_dio", S_IRUGO | S_IWUSR, p, &adio_proc_ops); proc_create_seq("debug", S_IRUGO, p, &debug_seq_ops); proc_create("def_reserved_size", S_IRUGO | S_IWUSR, p, &dressz_proc_ops); proc_create_single("device_hdr", S_IRUGO, p, sg_proc_seq_show_devhdr); proc_create_seq("devices", S_IRUGO, p, &dev_seq_ops); proc_create_seq("device_strs", S_IRUGO, p, &devstrs_seq_ops); proc_create_single("version", S_IRUGO, p, sg_proc_seq_show_version); return 0; } static int sg_proc_seq_show_int(struct seq_file *s, void *v) { seq_printf(s, "%d\n", *((int *)s->private)); return 0; } static int sg_proc_single_open_adio(struct inode *inode, struct file *file) { return single_open(file, sg_proc_seq_show_int, &sg_allow_dio); } static ssize_t sg_proc_write_adio(struct file *filp, const char __user *buffer, size_t count, loff_t *off) { int err; unsigned long num; if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO)) return -EACCES; err = kstrtoul_from_user(buffer, count, 0, &num); if (err) return err; sg_allow_dio = num ? 1 : 0; return count; } static int sg_proc_single_open_dressz(struct inode *inode, struct file *file) { return single_open(file, sg_proc_seq_show_int, &sg_big_buff); } static ssize_t sg_proc_write_dressz(struct file *filp, const char __user *buffer, size_t count, loff_t *off) { int err; unsigned long k = ULONG_MAX; if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO)) return -EACCES; err = kstrtoul_from_user(buffer, count, 0, &k); if (err) return err; if (k <= 1048576) { /* limit "big buff" to 1 MB */ sg_big_buff = k; return count; } return -ERANGE; } static int sg_proc_seq_show_version(struct seq_file *s, void *v) { seq_printf(s, "%d\t%s [%s]\n", sg_version_num, SG_VERSION_STR, sg_version_date); return 0; } static int sg_proc_seq_show_devhdr(struct seq_file *s, void *v) { seq_puts(s, "host\tchan\tid\tlun\ttype\topens\tqdepth\tbusy\tonline\n"); return 0; } struct sg_proc_deviter { loff_t index; size_t max; }; static void * dev_seq_start(struct seq_file *s, loff_t *pos) { struct sg_proc_deviter * it = kmalloc(sizeof(*it), GFP_KERNEL); s->private = it; if (! it) return NULL; it->index = *pos; it->max = sg_last_dev(); if (it->index >= it->max) return NULL; return it; } static void * dev_seq_next(struct seq_file *s, void *v, loff_t *pos) { struct sg_proc_deviter * it = s->private; *pos = ++it->index; return (it->index < it->max) ? it : NULL; } static void dev_seq_stop(struct seq_file *s, void *v) { kfree(s->private); } static int sg_proc_seq_show_dev(struct seq_file *s, void *v) { struct sg_proc_deviter * it = (struct sg_proc_deviter *) v; Sg_device *sdp; struct scsi_device *scsidp; unsigned long iflags; read_lock_irqsave(&sg_index_lock, iflags); sdp = it ? sg_lookup_dev(it->index) : NULL; if ((NULL == sdp) || (NULL == sdp->device) || (atomic_read(&sdp->detaching))) seq_puts(s, "-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n"); else { scsidp = sdp->device; seq_printf(s, "%d\t%d\t%d\t%llu\t%d\t%d\t%d\t%d\t%d\n", scsidp->host->host_no, scsidp->channel, scsidp->id, scsidp->lun, (int) scsidp->type, 1, (int) scsidp->queue_depth, (int) scsi_device_busy(scsidp), (int) scsi_device_online(scsidp)); } read_unlock_irqrestore(&sg_index_lock, iflags); return 0; } static int sg_proc_seq_show_devstrs(struct seq_file *s, void *v) { struct sg_proc_deviter * it = (struct sg_proc_deviter *) v; Sg_device *sdp; struct scsi_device *scsidp; unsigned long iflags; read_lock_irqsave(&sg_index_lock, iflags); sdp = it ? sg_lookup_dev(it->index) : NULL; scsidp = sdp ? sdp->device : NULL; if (sdp && scsidp && (!atomic_read(&sdp->detaching))) seq_printf(s, "%8.8s\t%16.16s\t%4.4s\n", scsidp->vendor, scsidp->model, scsidp->rev); else seq_puts(s, "<no active device>\n"); read_unlock_irqrestore(&sg_index_lock, iflags); return 0; } /* must be called while holding sg_index_lock */ static void sg_proc_debug_helper(struct seq_file *s, Sg_device * sdp) { int k, new_interface, blen, usg; Sg_request *srp; Sg_fd *fp; const sg_io_hdr_t *hp; const char * cp; unsigned int ms; unsigned int duration; k = 0; list_for_each_entry(fp, &sdp->sfds, sfd_siblings) { k++; read_lock(&fp->rq_list_lock); /* irqs already disabled */ seq_printf(s, " FD(%d): timeout=%dms bufflen=%d " "(res)sgat=%d low_dma=%d\n", k, jiffies_to_msecs(fp->timeout), fp->reserve.bufflen, (int) fp->reserve.k_use_sg, 0); seq_printf(s, " cmd_q=%d f_packid=%d k_orphan=%d closed=0\n", (int) fp->cmd_q, (int) fp->force_packid, (int) fp->keep_orphan); list_for_each_entry(srp, &fp->rq_list, entry) { hp = &srp->header; new_interface = (hp->interface_id == '\0') ? 0 : 1; if (srp->res_used) { if (new_interface && (SG_FLAG_MMAP_IO & hp->flags)) cp = " mmap>> "; else cp = " rb>> "; } else { if (SG_INFO_DIRECT_IO_MASK & hp->info) cp = " dio>> "; else cp = " "; } seq_puts(s, cp); blen = srp->data.bufflen; usg = srp->data.k_use_sg; seq_puts(s, srp->done ? ((1 == srp->done) ? "rcv:" : "fin:") : "act:"); seq_printf(s, " id=%d blen=%d", srp->header.pack_id, blen); if (srp->done) seq_printf(s, " dur=%u", hp->duration); else { ms = jiffies_to_msecs(jiffies); duration = READ_ONCE(hp->duration); if (duration) duration = (ms > duration ? ms - duration : 0); seq_printf(s, " t_o/elap=%u/%u", (new_interface ? hp->timeout : jiffies_to_msecs(fp->timeout)), duration); } seq_printf(s, "ms sgat=%d op=0x%02x\n", usg, (int) srp->data.cmd_opcode); } if (list_empty(&fp->rq_list)) seq_puts(s, " No requests active\n"); read_unlock(&fp->rq_list_lock); } } static int sg_proc_seq_show_debug(struct seq_file *s, void *v) { struct sg_proc_deviter * it = (struct sg_proc_deviter *) v; Sg_device *sdp; unsigned long iflags; if (it && (0 == it->index)) seq_printf(s, "max_active_device=%d def_reserved_size=%d\n", (int)it->max, sg_big_buff); read_lock_irqsave(&sg_index_lock, iflags); sdp = it ? sg_lookup_dev(it->index) : NULL; if (NULL == sdp) goto skip; read_lock(&sdp->sfd_lock); if (!list_empty(&sdp->sfds)) { seq_printf(s, " >>> device=%s ", sdp->name); if (atomic_read(&sdp->detaching)) seq_puts(s, "detaching pending close "); else if (sdp->device) { struct scsi_device *scsidp = sdp->device; seq_printf(s, "%d:%d:%d:%llu em=%d", scsidp->host->host_no, scsidp->channel, scsidp->id, scsidp->lun, scsidp->host->hostt->emulated); } seq_printf(s, " sg_tablesize=%d excl=%d open_cnt=%d\n", sdp->sg_tablesize, sdp->exclude, sdp->open_cnt); sg_proc_debug_helper(s, sdp); } read_unlock(&sdp->sfd_lock); skip: read_unlock_irqrestore(&sg_index_lock, iflags); return 0; } #endif /* CONFIG_SCSI_PROC_FS */ module_init(init_sg); module_exit(exit_sg); |
| 7 7 7 7 7 2 7 1 7 7 2 1 1 1 5 7 1 7 7 3 2 7 7 7 7 7 7 7 7 7 2 7 7 7 7 7 7 1 1 1 1 1 1 2 7 2 5 7 2 7 7 7 7 | 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 | // SPDX-License-Identifier: GPL-2.0+ /* * hwmon driver for Aquacomputer devices (D5 Next, Farbwerk, Farbwerk 360, Octo, * Quadro, High Flow Next, Aquaero, Aquastream Ultimate, Leakshield, * High Flow USB/MPS Flow family) * * Aquacomputer devices send HID reports (with ID 0x01) every second to report * sensor values, except for devices that communicate through the * legacy way (currently, Poweradjust 3 and High Flow USB/MPS Flow family). * * Copyright 2021 Aleksa Savic <savicaleksa83@gmail.com> * Copyright 2022 Jack Doan <me@jackdoan.com> */ #include <linux/crc16.h> #include <linux/debugfs.h> #include <linux/delay.h> #include <linux/hid.h> #include <linux/hwmon.h> #include <linux/jiffies.h> #include <linux/ktime.h> #include <linux/module.h> #include <linux/seq_file.h> #include <linux/unaligned.h> #define USB_VENDOR_ID_AQUACOMPUTER 0x0c70 #define USB_PRODUCT_ID_AQUAERO 0xf001 #define USB_PRODUCT_ID_FARBWERK 0xf00a #define USB_PRODUCT_ID_QUADRO 0xf00d #define USB_PRODUCT_ID_D5NEXT 0xf00e #define USB_PRODUCT_ID_FARBWERK360 0xf010 #define USB_PRODUCT_ID_OCTO 0xf011 #define USB_PRODUCT_ID_HIGHFLOWNEXT 0xf012 #define USB_PRODUCT_ID_LEAKSHIELD 0xf014 #define USB_PRODUCT_ID_AQUASTREAMXT 0xf0b6 #define USB_PRODUCT_ID_AQUASTREAMULT 0xf00b #define USB_PRODUCT_ID_POWERADJUST3 0xf0bd #define USB_PRODUCT_ID_HIGHFLOW 0xf003 enum kinds { d5next, farbwerk, farbwerk360, octo, quadro, highflownext, aquaero, poweradjust3, aquastreamult, aquastreamxt, leakshield, highflow }; static const char *const aqc_device_names[] = { [d5next] = "d5next", [farbwerk] = "farbwerk", [farbwerk360] = "farbwerk360", [octo] = "octo", [quadro] = "quadro", [highflownext] = "highflownext", [leakshield] = "leakshield", [aquastreamxt] = "aquastreamxt", [aquaero] = "aquaero", [aquastreamult] = "aquastreamultimate", [poweradjust3] = "poweradjust3", [highflow] = "highflow" /* Covers MPS Flow devices */ }; #define DRIVER_NAME "aquacomputer_d5next" #define STATUS_REPORT_ID 0x01 #define STATUS_UPDATE_INTERVAL (2 * HZ) /* In seconds */ #define SERIAL_PART_OFFSET 2 #define CTRL_REPORT_ID 0x03 #define AQUAERO_CTRL_REPORT_ID 0x0b #define CTRL_REPORT_DELAY 200 /* ms */ /* The HID report that the official software always sends * after writing values, currently same for all devices */ #define SECONDARY_CTRL_REPORT_ID 0x02 #define SECONDARY_CTRL_REPORT_SIZE 0x0B static u8 secondary_ctrl_report[] = { 0x02, 0x00, 0x00, 0x00, 0x02, 0x00, 0x00, 0x00, 0x00, 0x34, 0xC6 }; /* Secondary HID report values for Aquaero */ #define AQUAERO_SECONDARY_CTRL_REPORT_ID 0x06 #define AQUAERO_SECONDARY_CTRL_REPORT_SIZE 0x07 static u8 aquaero_secondary_ctrl_report[] = { 0x06, 0x00, 0x02, 0x00, 0x00, 0x00, 0x00 }; /* Report IDs for legacy devices */ #define AQUASTREAMXT_STATUS_REPORT_ID 0x04 #define POWERADJUST3_STATUS_REPORT_ID 0x03 #define HIGHFLOW_STATUS_REPORT_ID 0x02 /* Data types for reading and writing control reports */ #define AQC_8 0 #define AQC_BE16 1 /* Info, sensor sizes and offsets for most Aquacomputer devices */ #define AQC_SERIAL_START 0x3 #define AQC_FIRMWARE_VERSION 0xD #define AQC_SENSOR_SIZE 0x02 #define AQC_SENSOR_NA 0x7FFF #define AQC_FAN_PERCENT_OFFSET 0x00 #define AQC_FAN_VOLTAGE_OFFSET 0x02 #define AQC_FAN_CURRENT_OFFSET 0x04 #define AQC_FAN_POWER_OFFSET 0x06 #define AQC_FAN_SPEED_OFFSET 0x08 /* Specs of the Aquaero fan controllers */ #define AQUAERO_SERIAL_START 0x07 #define AQUAERO_FIRMWARE_VERSION 0x0B #define AQUAERO_NUM_FANS 4 #define AQUAERO_NUM_SENSORS 8 #define AQUAERO_NUM_VIRTUAL_SENSORS 8 #define AQUAERO_NUM_CALC_VIRTUAL_SENSORS 4 #define AQUAERO_NUM_FLOW_SENSORS 2 #define AQUAERO_CTRL_REPORT_SIZE 0xa93 #define AQUAERO_CTRL_PRESET_ID 0x5c #define AQUAERO_CTRL_PRESET_SIZE 0x02 #define AQUAERO_CTRL_PRESET_START 0x55c /* Sensor report offsets for Aquaero fan controllers */ #define AQUAERO_SENSOR_START 0x65 #define AQUAERO_VIRTUAL_SENSOR_START 0x85 #define AQUAERO_CALC_VIRTUAL_SENSOR_START 0x95 #define AQUAERO_FLOW_SENSORS_START 0xF9 #define AQUAERO_FAN_VOLTAGE_OFFSET 0x04 #define AQUAERO_FAN_CURRENT_OFFSET 0x06 #define AQUAERO_FAN_POWER_OFFSET 0x08 #define AQUAERO_FAN_SPEED_OFFSET 0x00 static u16 aquaero_sensor_fan_offsets[] = { 0x167, 0x173, 0x17f, 0x18B }; /* Control report offsets for the Aquaero fan controllers */ #define AQUAERO_TEMP_CTRL_OFFSET 0xdb #define AQUAERO_FAN_CTRL_MIN_PWR_OFFSET 0x04 #define AQUAERO_FAN_CTRL_MAX_PWR_OFFSET 0x06 #define AQUAERO_FAN_CTRL_SRC_OFFSET 0x10 static u16 aquaero_ctrl_fan_offsets[] = { 0x20c, 0x220, 0x234, 0x248 }; /* Specs of the D5 Next pump */ #define D5NEXT_NUM_FANS 2 #define D5NEXT_NUM_SENSORS 1 #define D5NEXT_NUM_VIRTUAL_SENSORS 8 #define D5NEXT_CTRL_REPORT_SIZE 0x329 /* Sensor report offsets for the D5 Next pump */ #define D5NEXT_POWER_CYCLES 0x18 #define D5NEXT_COOLANT_TEMP 0x57 #define D5NEXT_PUMP_OFFSET 0x6c #define D5NEXT_FAN_OFFSET 0x5f #define D5NEXT_5V_VOLTAGE 0x39 #define D5NEXT_12V_VOLTAGE 0x37 #define D5NEXT_VIRTUAL_SENSORS_START 0x3f static u16 d5next_sensor_fan_offsets[] = { D5NEXT_PUMP_OFFSET, D5NEXT_FAN_OFFSET }; /* Control report offsets for the D5 Next pump */ #define D5NEXT_TEMP_CTRL_OFFSET 0x2D /* Temperature sensor offsets location */ static u16 d5next_ctrl_fan_offsets[] = { 0x97, 0x42 }; /* Pump and fan speed (from 0-100%) */ /* Specs of the Aquastream Ultimate pump */ /* Pump does not follow the standard structure, so only consider the fan */ #define AQUASTREAMULT_NUM_FANS 1 #define AQUASTREAMULT_NUM_SENSORS 2 /* Sensor report offsets for the Aquastream Ultimate pump */ #define AQUASTREAMULT_SENSOR_START 0x2D #define AQUASTREAMULT_PUMP_OFFSET 0x51 #define AQUASTREAMULT_PUMP_VOLTAGE 0x3D #define AQUASTREAMULT_PUMP_CURRENT 0x53 #define AQUASTREAMULT_PUMP_POWER 0x55 #define AQUASTREAMULT_FAN_OFFSET 0x41 #define AQUASTREAMULT_PRESSURE_OFFSET 0x57 #define AQUASTREAMULT_FLOW_SENSOR_OFFSET 0x37 #define AQUASTREAMULT_FAN_VOLTAGE_OFFSET 0x02 #define AQUASTREAMULT_FAN_CURRENT_OFFSET 0x00 #define AQUASTREAMULT_FAN_POWER_OFFSET 0x04 #define AQUASTREAMULT_FAN_SPEED_OFFSET 0x06 static u16 aquastreamult_sensor_fan_offsets[] = { AQUASTREAMULT_FAN_OFFSET }; /* Spec and sensor report offset for the Farbwerk RGB controller */ #define FARBWERK_NUM_SENSORS 4 #define FARBWERK_SENSOR_START 0x2f /* Specs of the Farbwerk 360 RGB controller */ #define FARBWERK360_NUM_SENSORS 4 #define FARBWERK360_NUM_VIRTUAL_SENSORS 16 #define FARBWERK360_CTRL_REPORT_SIZE 0x682 /* Sensor report offsets for the Farbwerk 360 */ #define FARBWERK360_SENSOR_START 0x32 #define FARBWERK360_VIRTUAL_SENSORS_START 0x3a /* Control report offsets for the Farbwerk 360 */ #define FARBWERK360_TEMP_CTRL_OFFSET 0x8 /* Specs of the Octo fan controller */ #define OCTO_NUM_FANS 8 #define OCTO_NUM_SENSORS 4 #define OCTO_NUM_VIRTUAL_SENSORS 16 #define OCTO_NUM_FLOW_SENSORS 1 #define OCTO_CTRL_REPORT_SIZE 0x65F /* Sensor report offsets for the Octo */ #define OCTO_POWER_CYCLES 0x18 #define OCTO_SENSOR_START 0x3D #define OCTO_VIRTUAL_SENSORS_START 0x45 #define OCTO_FLOW_SENSOR_OFFSET 0x7B static u16 octo_sensor_fan_offsets[] = { 0x7D, 0x8A, 0x97, 0xA4, 0xB1, 0xBE, 0xCB, 0xD8 }; /* Control report offsets for the Octo */ #define OCTO_TEMP_CTRL_OFFSET 0xA #define OCTO_FLOW_PULSES_CTRL_OFFSET 0x6 /* Fan speed offsets (0-100%) */ static u16 octo_ctrl_fan_offsets[] = { 0x5B, 0xB0, 0x105, 0x15A, 0x1AF, 0x204, 0x259, 0x2AE }; /* Specs of Quadro fan controller */ #define QUADRO_NUM_FANS 4 #define QUADRO_NUM_SENSORS 4 #define QUADRO_NUM_VIRTUAL_SENSORS 16 #define QUADRO_NUM_FLOW_SENSORS 1 #define QUADRO_CTRL_REPORT_SIZE 0x3c1 /* Sensor report offsets for the Quadro */ #define QUADRO_POWER_CYCLES 0x18 #define QUADRO_SENSOR_START 0x34 #define QUADRO_VIRTUAL_SENSORS_START 0x3c #define QUADRO_FLOW_SENSOR_OFFSET 0x6e static u16 quadro_sensor_fan_offsets[] = { 0x70, 0x7D, 0x8A, 0x97 }; /* Control report offsets for the Quadro */ #define QUADRO_TEMP_CTRL_OFFSET 0xA #define QUADRO_FLOW_PULSES_CTRL_OFFSET 0x6 static u16 quadro_ctrl_fan_offsets[] = { 0x37, 0x8c, 0xe1, 0x136 }; /* Fan speed offsets (0-100%) */ /* Specs of High Flow Next flow sensor */ #define HIGHFLOWNEXT_NUM_SENSORS 2 #define HIGHFLOWNEXT_NUM_FLOW_SENSORS 1 /* Sensor report offsets for the High Flow Next */ #define HIGHFLOWNEXT_SENSOR_START 85 #define HIGHFLOWNEXT_FLOW 81 #define HIGHFLOWNEXT_WATER_QUALITY 89 #define HIGHFLOWNEXT_POWER 91 #define HIGHFLOWNEXT_CONDUCTIVITY 95 #define HIGHFLOWNEXT_5V_VOLTAGE 97 #define HIGHFLOWNEXT_5V_VOLTAGE_USB 99 /* Specs of the Leakshield */ #define LEAKSHIELD_NUM_SENSORS 2 /* Sensor report offsets for Leakshield */ #define LEAKSHIELD_PRESSURE_ADJUSTED 285 #define LEAKSHIELD_TEMPERATURE_1 265 #define LEAKSHIELD_TEMPERATURE_2 287 #define LEAKSHIELD_PRESSURE_MIN 291 #define LEAKSHIELD_PRESSURE_TARGET 293 #define LEAKSHIELD_PRESSURE_MAX 295 #define LEAKSHIELD_PUMP_RPM_IN 101 #define LEAKSHIELD_FLOW_IN 111 #define LEAKSHIELD_RESERVOIR_VOLUME 313 #define LEAKSHIELD_RESERVOIR_FILLED 311 /* Specs of the Aquastream XT pump */ #define AQUASTREAMXT_SERIAL_START 0x3a #define AQUASTREAMXT_FIRMWARE_VERSION 0x32 #define AQUASTREAMXT_NUM_FANS 2 #define AQUASTREAMXT_NUM_SENSORS 3 #define AQUASTREAMXT_FAN_STOPPED 0x4 #define AQUASTREAMXT_PUMP_CONVERSION_CONST 45000000 #define AQUASTREAMXT_FAN_CONVERSION_CONST 5646000 #define AQUASTREAMXT_SENSOR_REPORT_SIZE 0x42 /* Sensor report offsets and info for Aquastream XT */ #define AQUASTREAMXT_SENSOR_START 0xd #define AQUASTREAMXT_FAN_VOLTAGE_OFFSET 0x7 #define AQUASTREAMXT_FAN_STATUS_OFFSET 0x1d #define AQUASTREAMXT_PUMP_VOLTAGE_OFFSET 0x9 #define AQUASTREAMXT_PUMP_CURR_OFFSET 0xb static u16 aquastreamxt_sensor_fan_offsets[] = { 0x13, 0x1b }; /* Specs of the Poweradjust 3 */ #define POWERADJUST3_NUM_SENSORS 1 #define POWERADJUST3_SENSOR_REPORT_SIZE 0x32 /* Sensor report offsets for the Poweradjust 3 */ #define POWERADJUST3_SENSOR_START 0x03 /* Specs of the High Flow USB */ #define HIGHFLOW_NUM_SENSORS 2 #define HIGHFLOW_NUM_FLOW_SENSORS 1 #define HIGHFLOW_SENSOR_REPORT_SIZE 0x76 /* Sensor report offsets for the High Flow USB */ #define HIGHFLOW_FIRMWARE_VERSION 0x3 #define HIGHFLOW_SERIAL_START 0x9 #define HIGHFLOW_FLOW_SENSOR_OFFSET 0x23 #define HIGHFLOW_SENSOR_START 0x2b /* Labels for D5 Next */ static const char *const label_d5next_temp[] = { "Coolant temp" }; static const char *const label_d5next_speeds[] = { "Pump speed", "Fan speed" }; static const char *const label_d5next_power[] = { "Pump power", "Fan power" }; static const char *const label_d5next_voltages[] = { "Pump voltage", "Fan voltage", "+5V voltage", "+12V voltage" }; static const char *const label_d5next_current[] = { "Pump current", "Fan current" }; /* Labels for Aquaero, Farbwerk, Farbwerk 360 and Octo and Quadro temperature sensors */ static const char *const label_temp_sensors[] = { "Sensor 1", "Sensor 2", "Sensor 3", "Sensor 4", "Sensor 5", "Sensor 6", "Sensor 7", "Sensor 8" }; static const char *const label_virtual_temp_sensors[] = { "Virtual sensor 1", "Virtual sensor 2", "Virtual sensor 3", "Virtual sensor 4", "Virtual sensor 5", "Virtual sensor 6", "Virtual sensor 7", "Virtual sensor 8", "Virtual sensor 9", "Virtual sensor 10", "Virtual sensor 11", "Virtual sensor 12", "Virtual sensor 13", "Virtual sensor 14", "Virtual sensor 15", "Virtual sensor 16", }; static const char *const label_aquaero_calc_temp_sensors[] = { "Calc. virtual sensor 1", "Calc. virtual sensor 2", "Calc. virtual sensor 3", "Calc. virtual sensor 4" }; static const char *const label_fan_power[] = { "Fan 1 power", "Fan 2 power", "Fan 3 power", "Fan 4 power", "Fan 5 power", "Fan 6 power", "Fan 7 power", "Fan 8 power" }; static const char *const label_fan_voltage[] = { "Fan 1 voltage", "Fan 2 voltage", "Fan 3 voltage", "Fan 4 voltage", "Fan 5 voltage", "Fan 6 voltage", "Fan 7 voltage", "Fan 8 voltage" }; static const char *const label_fan_current[] = { "Fan 1 current", "Fan 2 current", "Fan 3 current", "Fan 4 current", "Fan 5 current", "Fan 6 current", "Fan 7 current", "Fan 8 current" }; /* Labels for Octo fan speeds */ static const char *const label_octo_speeds[] = { "Fan 1 speed", "Fan 2 speed", "Fan 3 speed", "Fan 4 speed", "Fan 5 speed", "Fan 6 speed", "Fan 7 speed", "Fan 8 speed", "Flow speed [dL/h]", }; /* Labels for Quadro fan speeds */ static const char *const label_quadro_speeds[] = { "Fan 1 speed", "Fan 2 speed", "Fan 3 speed", "Fan 4 speed", "Flow speed [dL/h]" }; /* Labels for Aquaero fan speeds */ static const char *const label_aquaero_speeds[] = { "Fan 1 speed", "Fan 2 speed", "Fan 3 speed", "Fan 4 speed", "Flow sensor 1 [dL/h]", "Flow sensor 2 [dL/h]" }; /* Labels for High Flow Next */ static const char *const label_highflownext_temp_sensors[] = { "Coolant temp", "External sensor" }; static const char *const label_highflownext_fan_speed[] = { "Flow [dL/h]", "Water quality [%]", "Conductivity [nS/cm]", }; static const char *const label_highflownext_power[] = { "Dissipated power", }; static const char *const label_highflownext_voltage[] = { "+5V voltage", "+5V USB voltage" }; /* Labels for Leakshield */ static const char *const label_leakshield_temp_sensors[] = { "Temperature 1", "Temperature 2" }; static const char *const label_leakshield_fan_speed[] = { "Pressure [ubar]", "User-Provided Pump Speed", "User-Provided Flow [dL/h]", "Reservoir Volume [ml]", "Reservoir Filled [ml]", }; /* Labels for Aquastream XT */ static const char *const label_aquastreamxt_temp_sensors[] = { "Fan IC temp", "External sensor", "Coolant temp" }; /* Labels for Aquastream Ultimate */ static const char *const label_aquastreamult_temp[] = { "Coolant temp", "External temp" }; static const char *const label_aquastreamult_speeds[] = { "Fan speed", "Pump speed", "Pressure [mbar]", "Flow speed [dL/h]" }; static const char *const label_aquastreamult_power[] = { "Fan power", "Pump power" }; static const char *const label_aquastreamult_voltages[] = { "Fan voltage", "Pump voltage" }; static const char *const label_aquastreamult_current[] = { "Fan current", "Pump current" }; /* Labels for Poweradjust 3 */ static const char *const label_poweradjust3_temp_sensors[] = { "External sensor" }; /* Labels for Highflow */ static const char *const label_highflow_temp[] = { "External temp", "Internal temp" }; static const char *const label_highflow_speeds[] = { "Flow speed [dL/h]" }; struct aqc_fan_structure_offsets { u8 voltage; u8 curr; u8 power; u8 speed; }; /* Fan structure offsets for Aquaero */ static struct aqc_fan_structure_offsets aqc_aquaero_fan_structure = { .voltage = AQUAERO_FAN_VOLTAGE_OFFSET, .curr = AQUAERO_FAN_CURRENT_OFFSET, .power = AQUAERO_FAN_POWER_OFFSET, .speed = AQUAERO_FAN_SPEED_OFFSET }; /* Fan structure offsets for Aquastream Ultimate */ static struct aqc_fan_structure_offsets aqc_aquastreamult_fan_structure = { .voltage = AQUASTREAMULT_FAN_VOLTAGE_OFFSET, .curr = AQUASTREAMULT_FAN_CURRENT_OFFSET, .power = AQUASTREAMULT_FAN_POWER_OFFSET, .speed = AQUASTREAMULT_FAN_SPEED_OFFSET }; /* Fan structure offsets for all devices except those above */ static struct aqc_fan_structure_offsets aqc_general_fan_structure = { .voltage = AQC_FAN_VOLTAGE_OFFSET, .curr = AQC_FAN_CURRENT_OFFSET, .power = AQC_FAN_POWER_OFFSET, .speed = AQC_FAN_SPEED_OFFSET }; struct aqc_data { struct hid_device *hdev; struct device *hwmon_dev; struct dentry *debugfs; enum kinds kind; const char *name; int status_report_id; /* Used for legacy devices, report is stored in buffer */ int ctrl_report_id; int secondary_ctrl_report_id; int secondary_ctrl_report_size; u8 *secondary_ctrl_report; ktime_t last_ctrl_report_op; int ctrl_report_delay; /* Delay between two ctrl report operations, in ms */ int buffer_size; u8 *buffer; int checksum_start; int checksum_length; int checksum_offset; int num_fans; u16 *fan_sensor_offsets; u16 *fan_ctrl_offsets; int num_temp_sensors; int temp_sensor_start_offset; int num_virtual_temp_sensors; int virtual_temp_sensor_start_offset; int num_calc_virt_temp_sensors; int calc_virt_temp_sensor_start_offset; u16 temp_ctrl_offset; u16 power_cycle_count_offset; int num_flow_sensors; u8 flow_sensors_start_offset; u8 flow_pulses_ctrl_offset; struct aqc_fan_structure_offsets *fan_structure; /* General info, same across all devices */ u8 serial_number_start_offset; u32 serial_number[2]; u8 firmware_version_offset; u16 firmware_version; /* How many times the device was powered on, if available */ u32 power_cycles; /* Sensor values */ s32 temp_input[20]; /* Max 4 physical and 16 virtual or 8 physical and 12 virtual */ s32 speed_input[9]; u32 speed_input_min[1]; u32 speed_input_target[1]; u32 speed_input_max[1]; u32 power_input[8]; u16 voltage_input[8]; u16 current_input[8]; /* Label values */ const char *const *temp_label; const char *const *virtual_temp_label; const char *const *calc_virt_temp_label; /* For Aquaero */ const char *const *speed_label; const char *const *power_label; const char *const *voltage_label; const char *const *current_label; unsigned long updated; }; /* Converts from centi-percent */ static int aqc_percent_to_pwm(u16 val) { return DIV_ROUND_CLOSEST(val * 255, 100 * 100); } /* Converts to centi-percent */ static int aqc_pwm_to_percent(long val) { if (val < 0 || val > 255) return -EINVAL; return DIV_ROUND_CLOSEST(val * 100 * 100, 255); } /* Converts raw value for Aquastream XT pump speed to RPM */ static int aqc_aquastreamxt_convert_pump_rpm(u16 val) { if (val > 0) return DIV_ROUND_CLOSEST(AQUASTREAMXT_PUMP_CONVERSION_CONST, val); return 0; } /* Converts raw value for Aquastream XT fan speed to RPM */ static int aqc_aquastreamxt_convert_fan_rpm(u16 val) { if (val > 0) return DIV_ROUND_CLOSEST(AQUASTREAMXT_FAN_CONVERSION_CONST, val); return 0; } static void aqc_delay_ctrl_report(struct aqc_data *priv) { /* * If previous read or write is too close to this one, delay the current operation * to give the device enough time to process the previous one. */ if (priv->ctrl_report_delay) { s64 delta = ktime_ms_delta(ktime_get(), priv->last_ctrl_report_op); if (delta < priv->ctrl_report_delay) msleep(priv->ctrl_report_delay - delta); } } static int aqc_get_ctrl_data(struct aqc_data *priv) { int ret; aqc_delay_ctrl_report(priv); memset(priv->buffer, 0x00, priv->buffer_size); ret = hid_hw_raw_request(priv->hdev, priv->ctrl_report_id, priv->buffer, priv->buffer_size, HID_FEATURE_REPORT, HID_REQ_GET_REPORT); if (ret < 0) ret = -ENODATA; priv->last_ctrl_report_op = ktime_get(); return ret; } static int aqc_send_ctrl_data(struct aqc_data *priv) { int ret; u16 checksum; aqc_delay_ctrl_report(priv); /* Checksum is not needed for Aquaero */ if (priv->kind != aquaero) { /* Init and xorout value for CRC-16/USB is 0xffff */ checksum = crc16(0xffff, priv->buffer + priv->checksum_start, priv->checksum_length); checksum ^= 0xffff; /* Place the new checksum at the end of the report */ put_unaligned_be16(checksum, priv->buffer + priv->checksum_offset); } /* Send the patched up report back to the device */ ret = hid_hw_raw_request(priv->hdev, priv->ctrl_report_id, priv->buffer, priv->buffer_size, HID_FEATURE_REPORT, HID_REQ_SET_REPORT); if (ret < 0) goto record_access_and_ret; /* The official software sends this report after every change, so do it here as well */ ret = hid_hw_raw_request(priv->hdev, priv->secondary_ctrl_report_id, priv->secondary_ctrl_report, priv->secondary_ctrl_report_size, HID_FEATURE_REPORT, HID_REQ_SET_REPORT); record_access_and_ret: priv->last_ctrl_report_op = ktime_get(); return ret; } /* Refreshes the control buffer and stores value at offset in val */ static int aqc_get_ctrl_val(struct aqc_data *priv, int offset, long *val, int type) { int ret; ret = aqc_get_ctrl_data(priv); if (ret < 0) return ret; switch (type) { case AQC_BE16: *val = (s16)get_unaligned_be16(priv->buffer + offset); break; case AQC_8: *val = priv->buffer[offset]; break; default: ret = -EINVAL; } return ret; } static int aqc_set_ctrl_vals(struct aqc_data *priv, int *offsets, long *vals, int *types, int len) { int ret, i; ret = aqc_get_ctrl_data(priv); if (ret < 0) return ret; for (i = 0; i < len; i++) { switch (types[i]) { case AQC_BE16: put_unaligned_be16((s16)vals[i], priv->buffer + offsets[i]); break; case AQC_8: priv->buffer[offsets[i]] = (u8)vals[i]; break; default: return -EINVAL; } } return aqc_send_ctrl_data(priv); } static int aqc_set_ctrl_val(struct aqc_data *priv, int offset, long val, int type) { return aqc_set_ctrl_vals(priv, &offset, &val, &type, 1); } static umode_t aqc_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr, int channel) { const struct aqc_data *priv = data; switch (type) { case hwmon_temp: if (channel < priv->num_temp_sensors) { switch (attr) { case hwmon_temp_label: case hwmon_temp_input: return 0444; case hwmon_temp_offset: if (priv->temp_ctrl_offset != 0) return 0644; break; default: break; } } if (channel < priv->num_temp_sensors + priv->num_virtual_temp_sensors + priv->num_calc_virt_temp_sensors) switch (attr) { case hwmon_temp_label: case hwmon_temp_input: return 0444; default: break; } break; case hwmon_pwm: if (priv->fan_ctrl_offsets && channel < priv->num_fans) { switch (attr) { case hwmon_pwm_input: return 0644; default: break; } } break; case hwmon_fan: switch (attr) { case hwmon_fan_input: case hwmon_fan_label: switch (priv->kind) { case aquastreamult: /* * Special case to support pump RPM, fan RPM, * pressure and flow sensor */ if (channel < 4) return 0444; break; case highflownext: /* Special case to support flow sensor, water quality * and conductivity */ if (channel < 3) return 0444; break; case leakshield: /* Special case for Leakshield sensors */ if (channel < 5) return 0444; break; case aquaero: case octo: case quadro: case highflow: /* Special case to support flow sensors */ if (channel < priv->num_fans + priv->num_flow_sensors) return 0444; break; default: if (channel < priv->num_fans) return 0444; break; } break; case hwmon_fan_pulses: /* Special case for Quadro/Octo flow sensor */ if (channel == priv->num_fans) { switch (priv->kind) { case quadro: case octo: return 0644; default: break; } } break; case hwmon_fan_min: case hwmon_fan_max: case hwmon_fan_target: /* Special case for Leakshield pressure sensor */ if (priv->kind == leakshield && channel == 0) return 0444; break; default: break; } break; case hwmon_power: switch (priv->kind) { case aquastreamult: /* Special case to support pump and fan power */ if (channel < 2) return 0444; break; case highflownext: /* Special case to support one power sensor */ if (channel == 0) return 0444; break; case aquastreamxt: break; default: if (channel < priv->num_fans) return 0444; break; } break; case hwmon_curr: switch (priv->kind) { case aquastreamult: /* Special case to support pump and fan current */ if (channel < 2) return 0444; break; case aquastreamxt: /* Special case to support pump current */ if (channel == 0) return 0444; break; default: if (channel < priv->num_fans) return 0444; break; } break; case hwmon_in: switch (priv->kind) { case d5next: /* Special case to support +5V and +12V voltage sensors */ if (channel < priv->num_fans + 2) return 0444; break; case aquastreamult: case highflownext: /* Special case to support two voltage sensors */ if (channel < 2) return 0444; break; default: if (channel < priv->num_fans) return 0444; break; } break; default: break; } return 0; } /* Read device sensors by manually requesting the sensor report (legacy way) */ static int aqc_legacy_read(struct aqc_data *priv) { int ret, i, sensor_value; memset(priv->buffer, 0x00, priv->buffer_size); ret = hid_hw_raw_request(priv->hdev, priv->status_report_id, priv->buffer, priv->buffer_size, HID_FEATURE_REPORT, HID_REQ_GET_REPORT); if (ret < 0) return ret; /* Temperature sensor readings */ for (i = 0; i < priv->num_temp_sensors; i++) { sensor_value = get_unaligned_le16(priv->buffer + priv->temp_sensor_start_offset + i * AQC_SENSOR_SIZE); if (sensor_value == AQC_SENSOR_NA) priv->temp_input[i] = -ENODATA; else priv->temp_input[i] = sensor_value * 10; } /* Special-case sensor readings */ switch (priv->kind) { case aquastreamxt: /* Info provided with every report */ priv->serial_number[0] = get_unaligned_le16(priv->buffer + priv->serial_number_start_offset); priv->firmware_version = get_unaligned_le16(priv->buffer + priv->firmware_version_offset); /* Read pump speed in RPM */ sensor_value = get_unaligned_le16(priv->buffer + priv->fan_sensor_offsets[0]); priv->speed_input[0] = aqc_aquastreamxt_convert_pump_rpm(sensor_value); /* Read fan speed in RPM, if available */ sensor_value = get_unaligned_le16(priv->buffer + AQUASTREAMXT_FAN_STATUS_OFFSET); if (sensor_value == AQUASTREAMXT_FAN_STOPPED) { priv->speed_input[1] = 0; } else { sensor_value = get_unaligned_le16(priv->buffer + priv->fan_sensor_offsets[1]); priv->speed_input[1] = aqc_aquastreamxt_convert_fan_rpm(sensor_value); } /* Calculation derived from linear regression */ sensor_value = get_unaligned_le16(priv->buffer + AQUASTREAMXT_PUMP_CURR_OFFSET); priv->current_input[0] = DIV_ROUND_CLOSEST(sensor_value * 176, 100) - 52; sensor_value = get_unaligned_le16(priv->buffer + AQUASTREAMXT_PUMP_VOLTAGE_OFFSET); priv->voltage_input[0] = DIV_ROUND_CLOSEST(sensor_value * 1000, 61); sensor_value = get_unaligned_le16(priv->buffer + AQUASTREAMXT_FAN_VOLTAGE_OFFSET); priv->voltage_input[1] = DIV_ROUND_CLOSEST(sensor_value * 1000, 63); break; case highflow: /* Info provided with every report */ priv->serial_number[0] = get_unaligned_le16(priv->buffer + priv->serial_number_start_offset); priv->firmware_version = get_unaligned_le16(priv->buffer + priv->firmware_version_offset); /* Read flow speed */ priv->speed_input[0] = get_unaligned_le16(priv->buffer + priv->flow_sensors_start_offset); break; default: break; } priv->updated = jiffies; return 0; } static int aqc_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *val) { int ret; struct aqc_data *priv = dev_get_drvdata(dev); if (time_after(jiffies, priv->updated + STATUS_UPDATE_INTERVAL)) { if (priv->status_report_id != 0) { /* Legacy devices require manual reads */ ret = aqc_legacy_read(priv); if (ret < 0) return -ENODATA; } else { return -ENODATA; } } switch (type) { case hwmon_temp: switch (attr) { case hwmon_temp_input: if (priv->temp_input[channel] == -ENODATA) return -ENODATA; *val = priv->temp_input[channel]; break; case hwmon_temp_offset: ret = aqc_get_ctrl_val(priv, priv->temp_ctrl_offset + channel * AQC_SENSOR_SIZE, val, AQC_BE16); if (ret < 0) return ret; *val *= 10; break; default: break; } break; case hwmon_fan: switch (attr) { case hwmon_fan_input: if (priv->speed_input[channel] == -ENODATA) return -ENODATA; *val = priv->speed_input[channel]; break; case hwmon_fan_min: *val = priv->speed_input_min[channel]; break; case hwmon_fan_max: *val = priv->speed_input_max[channel]; break; case hwmon_fan_target: *val = priv->speed_input_target[channel]; break; case hwmon_fan_pulses: ret = aqc_get_ctrl_val(priv, priv->flow_pulses_ctrl_offset, val, AQC_BE16); if (ret < 0) return ret; break; default: break; } break; case hwmon_power: *val = priv->power_input[channel]; break; case hwmon_pwm: switch (priv->kind) { case aquaero: ret = aqc_get_ctrl_val(priv, AQUAERO_CTRL_PRESET_START + channel * AQUAERO_CTRL_PRESET_SIZE, val, AQC_BE16); if (ret < 0) return ret; *val = aqc_percent_to_pwm(*val); break; default: ret = aqc_get_ctrl_val(priv, priv->fan_ctrl_offsets[channel], val, AQC_BE16); if (ret < 0) return ret; *val = aqc_percent_to_pwm(*val); break; } break; case hwmon_in: *val = priv->voltage_input[channel]; break; case hwmon_curr: *val = priv->current_input[channel]; break; default: return -EOPNOTSUPP; } return 0; } static int aqc_read_string(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, const char **str) { struct aqc_data *priv = dev_get_drvdata(dev); /* Number of sensors that are not calculated */ int num_non_calc_sensors = priv->num_temp_sensors + priv->num_virtual_temp_sensors; switch (type) { case hwmon_temp: if (channel < priv->num_temp_sensors) { *str = priv->temp_label[channel]; } else { if (priv->kind == aquaero && channel >= num_non_calc_sensors) *str = priv->calc_virt_temp_label[channel - num_non_calc_sensors]; else *str = priv->virtual_temp_label[channel - priv->num_temp_sensors]; } break; case hwmon_fan: *str = priv->speed_label[channel]; break; case hwmon_power: *str = priv->power_label[channel]; break; case hwmon_in: *str = priv->voltage_label[channel]; break; case hwmon_curr: *str = priv->current_label[channel]; break; default: return -EOPNOTSUPP; } return 0; } static int aqc_write(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long val) { int ret, pwm_value; /* Arrays for setting multiple values at once in the control report */ int ctrl_values_offsets[4]; long ctrl_values[4]; int ctrl_values_types[4]; struct aqc_data *priv = dev_get_drvdata(dev); switch (type) { case hwmon_temp: switch (attr) { case hwmon_temp_offset: /* Limit temp offset to +/- 15K as in the official software */ val = clamp_val(val, -15000, 15000) / 10; ret = aqc_set_ctrl_val(priv, priv->temp_ctrl_offset + channel * AQC_SENSOR_SIZE, val, AQC_BE16); if (ret < 0) return ret; break; default: return -EOPNOTSUPP; } break; case hwmon_fan: switch (attr) { case hwmon_fan_pulses: val = clamp_val(val, 10, 1000); ret = aqc_set_ctrl_val(priv, priv->flow_pulses_ctrl_offset, val, AQC_BE16); if (ret < 0) return ret; break; default: break; } break; case hwmon_pwm: switch (attr) { case hwmon_pwm_input: pwm_value = aqc_pwm_to_percent(val); if (pwm_value < 0) return pwm_value; switch (priv->kind) { case aquaero: /* Write pwm value to preset corresponding to the channel */ ctrl_values_offsets[0] = AQUAERO_CTRL_PRESET_START + channel * AQUAERO_CTRL_PRESET_SIZE; ctrl_values[0] = pwm_value; ctrl_values_types[0] = AQC_BE16; /* Write preset number in fan control source */ ctrl_values_offsets[1] = priv->fan_ctrl_offsets[channel] + AQUAERO_FAN_CTRL_SRC_OFFSET; ctrl_values[1] = AQUAERO_CTRL_PRESET_ID + channel; ctrl_values_types[1] = AQC_BE16; /* Set minimum power to 0 to allow the fan to turn off */ ctrl_values_offsets[2] = priv->fan_ctrl_offsets[channel] + AQUAERO_FAN_CTRL_MIN_PWR_OFFSET; ctrl_values[2] = 0; ctrl_values_types[2] = AQC_BE16; /* Set maximum power to 255 to allow the fan to reach max speed */ ctrl_values_offsets[3] = priv->fan_ctrl_offsets[channel] + AQUAERO_FAN_CTRL_MAX_PWR_OFFSET; ctrl_values[3] = aqc_pwm_to_percent(255); ctrl_values_types[3] = AQC_BE16; ret = aqc_set_ctrl_vals(priv, ctrl_values_offsets, ctrl_values, ctrl_values_types, 4); if (ret < 0) return ret; break; default: ret = aqc_set_ctrl_val(priv, priv->fan_ctrl_offsets[channel], pwm_value, AQC_BE16); if (ret < 0) return ret; break; } break; default: break; } break; default: return -EOPNOTSUPP; } return 0; } static const struct hwmon_ops aqc_hwmon_ops = { .is_visible = aqc_is_visible, .read = aqc_read, .read_string = aqc_read_string, .write = aqc_write }; static const struct hwmon_channel_info * const aqc_info[] = { HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_LABEL | HWMON_T_OFFSET, HWMON_T_INPUT | HWMON_T_LABEL | HWMON_T_OFFSET, HWMON_T_INPUT | HWMON_T_LABEL | HWMON_T_OFFSET, HWMON_T_INPUT | HWMON_T_LABEL | HWMON_T_OFFSET, HWMON_T_INPUT | HWMON_T_LABEL | HWMON_T_OFFSET, HWMON_T_INPUT | HWMON_T_LABEL | HWMON_T_OFFSET, HWMON_T_INPUT | HWMON_T_LABEL | HWMON_T_OFFSET, HWMON_T_INPUT | HWMON_T_LABEL | HWMON_T_OFFSET, HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL, HWMON_T_INPUT | HWMON_T_LABEL), HWMON_CHANNEL_INFO(fan, HWMON_F_INPUT | HWMON_F_LABEL | HWMON_F_MIN | HWMON_F_MAX | HWMON_F_TARGET, HWMON_F_INPUT | HWMON_F_LABEL, HWMON_F_INPUT | HWMON_F_LABEL, HWMON_F_INPUT | HWMON_F_LABEL, HWMON_F_INPUT | HWMON_F_LABEL | HWMON_F_PULSES, HWMON_F_INPUT | HWMON_F_LABEL, HWMON_F_INPUT | HWMON_F_LABEL, HWMON_F_INPUT | HWMON_F_LABEL, HWMON_F_INPUT | HWMON_F_LABEL | HWMON_F_PULSES), HWMON_CHANNEL_INFO(power, HWMON_P_INPUT | HWMON_P_LABEL, HWMON_P_INPUT | HWMON_P_LABEL, HWMON_P_INPUT | HWMON_P_LABEL, HWMON_P_INPUT | HWMON_P_LABEL, HWMON_P_INPUT | HWMON_P_LABEL, HWMON_P_INPUT | HWMON_P_LABEL, HWMON_P_INPUT | HWMON_P_LABEL, HWMON_P_INPUT | HWMON_P_LABEL), HWMON_CHANNEL_INFO(pwm, HWMON_PWM_INPUT, HWMON_PWM_INPUT, HWMON_PWM_INPUT, HWMON_PWM_INPUT, HWMON_PWM_INPUT, HWMON_PWM_INPUT, HWMON_PWM_INPUT, HWMON_PWM_INPUT), HWMON_CHANNEL_INFO(in, HWMON_I_INPUT | HWMON_I_LABEL, HWMON_I_INPUT | HWMON_I_LABEL, HWMON_I_INPUT | HWMON_I_LABEL, HWMON_I_INPUT | HWMON_I_LABEL, HWMON_I_INPUT | HWMON_I_LABEL, HWMON_I_INPUT | HWMON_I_LABEL, HWMON_I_INPUT | HWMON_I_LABEL, HWMON_I_INPUT | HWMON_I_LABEL), HWMON_CHANNEL_INFO(curr, HWMON_C_INPUT | HWMON_C_LABEL, HWMON_C_INPUT | HWMON_C_LABEL, HWMON_C_INPUT | HWMON_C_LABEL, HWMON_C_INPUT | HWMON_C_LABEL, HWMON_C_INPUT | HWMON_C_LABEL, HWMON_C_INPUT | HWMON_C_LABEL, HWMON_C_INPUT | HWMON_C_LABEL, HWMON_C_INPUT | HWMON_C_LABEL), NULL }; static const struct hwmon_chip_info aqc_chip_info = { .ops = &aqc_hwmon_ops, .info = aqc_info, }; static int aqc_raw_event(struct hid_device *hdev, struct hid_report *report, u8 *data, int size) { int i, j, sensor_value; struct aqc_data *priv; if (report->id != STATUS_REPORT_ID) return 0; priv = hid_get_drvdata(hdev); /* Info provided with every report */ priv->serial_number[0] = get_unaligned_be16(data + priv->serial_number_start_offset); priv->serial_number[1] = get_unaligned_be16(data + priv->serial_number_start_offset + SERIAL_PART_OFFSET); priv->firmware_version = get_unaligned_be16(data + priv->firmware_version_offset); /* Physical temperature sensor readings */ for (i = 0; i < priv->num_temp_sensors; i++) { sensor_value = get_unaligned_be16(data + priv->temp_sensor_start_offset + i * AQC_SENSOR_SIZE); if (sensor_value == AQC_SENSOR_NA) priv->temp_input[i] = -ENODATA; else priv->temp_input[i] = sensor_value * 10; } /* Virtual temperature sensor readings */ for (j = 0; j < priv->num_virtual_temp_sensors; j++) { sensor_value = get_unaligned_be16(data + priv->virtual_temp_sensor_start_offset + j * AQC_SENSOR_SIZE); if (sensor_value == AQC_SENSOR_NA) priv->temp_input[i] = -ENODATA; else priv->temp_input[i] = sensor_value * 10; i++; } /* Fan speed and related readings */ for (i = 0; i < priv->num_fans; i++) { priv->speed_input[i] = get_unaligned_be16(data + priv->fan_sensor_offsets[i] + priv->fan_structure->speed); priv->power_input[i] = get_unaligned_be16(data + priv->fan_sensor_offsets[i] + priv->fan_structure->power) * 10000; priv->voltage_input[i] = get_unaligned_be16(data + priv->fan_sensor_offsets[i] + priv->fan_structure->voltage) * 10; priv->current_input[i] = get_unaligned_be16(data + priv->fan_sensor_offsets[i] + priv->fan_structure->curr); } /* Flow sensor readings */ for (j = 0; j < priv->num_flow_sensors; j++) { priv->speed_input[i] = get_unaligned_be16(data + priv->flow_sensors_start_offset + j * AQC_SENSOR_SIZE); i++; } if (priv->power_cycle_count_offset != 0) priv->power_cycles = get_unaligned_be32(data + priv->power_cycle_count_offset); /* Special-case sensor readings */ switch (priv->kind) { case aquaero: /* Read calculated virtual temp sensors */ i = priv->num_temp_sensors + priv->num_virtual_temp_sensors; for (j = 0; j < priv->num_calc_virt_temp_sensors; j++) { sensor_value = get_unaligned_be16(data + priv->calc_virt_temp_sensor_start_offset + j * AQC_SENSOR_SIZE); if (sensor_value == AQC_SENSOR_NA) priv->temp_input[i] = -ENODATA; else priv->temp_input[i] = sensor_value * 10; i++; } break; case aquastreamult: priv->speed_input[1] = get_unaligned_be16(data + AQUASTREAMULT_PUMP_OFFSET); priv->speed_input[2] = get_unaligned_be16(data + AQUASTREAMULT_PRESSURE_OFFSET); priv->speed_input[3] = get_unaligned_be16(data + AQUASTREAMULT_FLOW_SENSOR_OFFSET); priv->power_input[1] = get_unaligned_be16(data + AQUASTREAMULT_PUMP_POWER) * 10000; priv->voltage_input[1] = get_unaligned_be16(data + AQUASTREAMULT_PUMP_VOLTAGE) * 10; priv->current_input[1] = get_unaligned_be16(data + AQUASTREAMULT_PUMP_CURRENT); break; case d5next: priv->voltage_input[2] = get_unaligned_be16(data + D5NEXT_5V_VOLTAGE) * 10; priv->voltage_input[3] = get_unaligned_be16(data + D5NEXT_12V_VOLTAGE) * 10; break; case highflownext: /* If external temp sensor is not connected, its power reading is also N/A */ if (priv->temp_input[1] == -ENODATA) priv->power_input[0] = -ENODATA; else priv->power_input[0] = get_unaligned_be16(data + HIGHFLOWNEXT_POWER) * 1000000; priv->voltage_input[0] = get_unaligned_be16(data + HIGHFLOWNEXT_5V_VOLTAGE) * 10; priv->voltage_input[1] = get_unaligned_be16(data + HIGHFLOWNEXT_5V_VOLTAGE_USB) * 10; priv->speed_input[1] = get_unaligned_be16(data + HIGHFLOWNEXT_WATER_QUALITY); priv->speed_input[2] = get_unaligned_be16(data + HIGHFLOWNEXT_CONDUCTIVITY); break; case leakshield: priv->speed_input[0] = ((s16)get_unaligned_be16(data + LEAKSHIELD_PRESSURE_ADJUSTED)) * 100; priv->speed_input_min[0] = get_unaligned_be16(data + LEAKSHIELD_PRESSURE_MIN) * 100; priv->speed_input_target[0] = get_unaligned_be16(data + LEAKSHIELD_PRESSURE_TARGET) * 100; priv->speed_input_max[0] = get_unaligned_be16(data + LEAKSHIELD_PRESSURE_MAX) * 100; priv->speed_input[1] = get_unaligned_be16(data + LEAKSHIELD_PUMP_RPM_IN); if (priv->speed_input[1] == AQC_SENSOR_NA) priv->speed_input[1] = -ENODATA; priv->speed_input[2] = get_unaligned_be16(data + LEAKSHIELD_FLOW_IN); if (priv->speed_input[2] == AQC_SENSOR_NA) priv->speed_input[2] = -ENODATA; priv->speed_input[3] = get_unaligned_be16(data + LEAKSHIELD_RESERVOIR_VOLUME); priv->speed_input[4] = get_unaligned_be16(data + LEAKSHIELD_RESERVOIR_FILLED); /* Second temp sensor is not positioned after the first one, read it here */ priv->temp_input[1] = get_unaligned_be16(data + LEAKSHIELD_TEMPERATURE_2) * 10; break; default: break; } priv->updated = jiffies; return 0; } static int serial_number_show(struct seq_file *seqf, void *unused) { struct aqc_data *priv = seqf->private; seq_printf(seqf, "%05u-%05u\n", priv->serial_number[0], priv->serial_number[1]); return 0; } DEFINE_SHOW_ATTRIBUTE(serial_number); static int firmware_version_show(struct seq_file *seqf, void *unused) { struct aqc_data *priv = seqf->private; seq_printf(seqf, "%u\n", priv->firmware_version); return 0; } DEFINE_SHOW_ATTRIBUTE(firmware_version); static int power_cycles_show(struct seq_file *seqf, void *unused) { struct aqc_data *priv = seqf->private; seq_printf(seqf, "%u\n", priv->power_cycles); return 0; } DEFINE_SHOW_ATTRIBUTE(power_cycles); static void aqc_debugfs_init(struct aqc_data *priv) { char name[64]; scnprintf(name, sizeof(name), "%s_%s-%s", "aquacomputer", priv->name, dev_name(&priv->hdev->dev)); priv->debugfs = debugfs_create_dir(name, NULL); if (priv->serial_number_start_offset != 0) debugfs_create_file("serial_number", 0444, priv->debugfs, priv, &serial_number_fops); if (priv->firmware_version_offset != 0) debugfs_create_file("firmware_version", 0444, priv->debugfs, priv, &firmware_version_fops); if (priv->power_cycle_count_offset != 0) debugfs_create_file("power_cycles", 0444, priv->debugfs, priv, &power_cycles_fops); } static int aqc_probe(struct hid_device *hdev, const struct hid_device_id *id) { struct aqc_data *priv; int ret; priv = devm_kzalloc(&hdev->dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; priv->hdev = hdev; hid_set_drvdata(hdev, priv); priv->updated = jiffies - STATUS_UPDATE_INTERVAL; ret = hid_parse(hdev); if (ret) return ret; ret = hid_hw_start(hdev, HID_CONNECT_HIDRAW); if (ret) return ret; ret = hid_hw_open(hdev); if (ret) goto fail_and_stop; switch (hdev->product) { case USB_PRODUCT_ID_AQUAERO: /* * Aquaero presents itself as three HID devices under the same product ID: * "aquaero keyboard/mouse", "aquaero System Control" and "aquaero Device", * which is the one we want to communicate with. Unlike most other Aquacomputer * devices, Aquaero does not return meaningful data when explicitly requested * using GET_FEATURE_REPORT. * * The difference between "aquaero Device" and the other two is in the collections * they present. The two other devices have the type of the second element in * their respective collections set to 1, while the real device has it set to 0. */ if (hdev->collection[1].type != 0) { ret = -ENODEV; goto fail_and_close; } priv->kind = aquaero; priv->num_fans = AQUAERO_NUM_FANS; priv->fan_sensor_offsets = aquaero_sensor_fan_offsets; priv->fan_ctrl_offsets = aquaero_ctrl_fan_offsets; priv->num_temp_sensors = AQUAERO_NUM_SENSORS; priv->temp_sensor_start_offset = AQUAERO_SENSOR_START; priv->num_virtual_temp_sensors = AQUAERO_NUM_VIRTUAL_SENSORS; priv->virtual_temp_sensor_start_offset = AQUAERO_VIRTUAL_SENSOR_START; priv->num_calc_virt_temp_sensors = AQUAERO_NUM_CALC_VIRTUAL_SENSORS; priv->calc_virt_temp_sensor_start_offset = AQUAERO_CALC_VIRTUAL_SENSOR_START; priv->num_flow_sensors = AQUAERO_NUM_FLOW_SENSORS; priv->flow_sensors_start_offset = AQUAERO_FLOW_SENSORS_START; priv->buffer_size = AQUAERO_CTRL_REPORT_SIZE; priv->temp_ctrl_offset = AQUAERO_TEMP_CTRL_OFFSET; priv->ctrl_report_delay = CTRL_REPORT_DELAY; priv->temp_label = label_temp_sensors; priv->virtual_temp_label = label_virtual_temp_sensors; priv->calc_virt_temp_label = label_aquaero_calc_temp_sensors; priv->speed_label = label_aquaero_speeds; priv->power_label = label_fan_power; priv->voltage_label = label_fan_voltage; priv->current_label = label_fan_current; break; case USB_PRODUCT_ID_D5NEXT: priv->kind = d5next; priv->num_fans = D5NEXT_NUM_FANS; priv->fan_sensor_offsets = d5next_sensor_fan_offsets; priv->fan_ctrl_offsets = d5next_ctrl_fan_offsets; priv->num_temp_sensors = D5NEXT_NUM_SENSORS; priv->temp_sensor_start_offset = D5NEXT_COOLANT_TEMP; priv->num_virtual_temp_sensors = D5NEXT_NUM_VIRTUAL_SENSORS; priv->virtual_temp_sensor_start_offset = D5NEXT_VIRTUAL_SENSORS_START; priv->temp_ctrl_offset = D5NEXT_TEMP_CTRL_OFFSET; priv->buffer_size = D5NEXT_CTRL_REPORT_SIZE; priv->ctrl_report_delay = CTRL_REPORT_DELAY; priv->power_cycle_count_offset = D5NEXT_POWER_CYCLES; priv->temp_label = label_d5next_temp; priv->virtual_temp_label = label_virtual_temp_sensors; priv->speed_label = label_d5next_speeds; priv->power_label = label_d5next_power; priv->voltage_label = label_d5next_voltages; priv->current_label = label_d5next_current; break; case USB_PRODUCT_ID_FARBWERK: priv->kind = farbwerk; priv->num_fans = 0; priv->num_temp_sensors = FARBWERK_NUM_SENSORS; priv->temp_sensor_start_offset = FARBWERK_SENSOR_START; priv->temp_label = label_temp_sensors; break; case USB_PRODUCT_ID_FARBWERK360: priv->kind = farbwerk360; priv->num_fans = 0; priv->num_temp_sensors = FARBWERK360_NUM_SENSORS; priv->temp_sensor_start_offset = FARBWERK360_SENSOR_START; priv->num_virtual_temp_sensors = FARBWERK360_NUM_VIRTUAL_SENSORS; priv->virtual_temp_sensor_start_offset = FARBWERK360_VIRTUAL_SENSORS_START; priv->temp_ctrl_offset = FARBWERK360_TEMP_CTRL_OFFSET; priv->buffer_size = FARBWERK360_CTRL_REPORT_SIZE; priv->temp_label = label_temp_sensors; priv->virtual_temp_label = label_virtual_temp_sensors; break; case USB_PRODUCT_ID_OCTO: priv->kind = octo; priv->num_fans = OCTO_NUM_FANS; priv->fan_sensor_offsets = octo_sensor_fan_offsets; priv->fan_ctrl_offsets = octo_ctrl_fan_offsets; priv->num_temp_sensors = OCTO_NUM_SENSORS; priv->temp_sensor_start_offset = OCTO_SENSOR_START; priv->num_virtual_temp_sensors = OCTO_NUM_VIRTUAL_SENSORS; priv->virtual_temp_sensor_start_offset = OCTO_VIRTUAL_SENSORS_START; priv->num_flow_sensors = OCTO_NUM_FLOW_SENSORS; priv->flow_sensors_start_offset = OCTO_FLOW_SENSOR_OFFSET; priv->temp_ctrl_offset = OCTO_TEMP_CTRL_OFFSET; priv->buffer_size = OCTO_CTRL_REPORT_SIZE; priv->ctrl_report_delay = CTRL_REPORT_DELAY; priv->flow_pulses_ctrl_offset = OCTO_FLOW_PULSES_CTRL_OFFSET; priv->power_cycle_count_offset = OCTO_POWER_CYCLES; priv->temp_label = label_temp_sensors; priv->virtual_temp_label = label_virtual_temp_sensors; priv->speed_label = label_octo_speeds; priv->power_label = label_fan_power; priv->voltage_label = label_fan_voltage; priv->current_label = label_fan_current; break; case USB_PRODUCT_ID_QUADRO: priv->kind = quadro; priv->num_fans = QUADRO_NUM_FANS; priv->fan_sensor_offsets = quadro_sensor_fan_offsets; priv->fan_ctrl_offsets = quadro_ctrl_fan_offsets; priv->num_temp_sensors = QUADRO_NUM_SENSORS; priv->temp_sensor_start_offset = QUADRO_SENSOR_START; priv->num_virtual_temp_sensors = QUADRO_NUM_VIRTUAL_SENSORS; priv->virtual_temp_sensor_start_offset = QUADRO_VIRTUAL_SENSORS_START; priv->num_flow_sensors = QUADRO_NUM_FLOW_SENSORS; priv->flow_sensors_start_offset = QUADRO_FLOW_SENSOR_OFFSET; priv->temp_ctrl_offset = QUADRO_TEMP_CTRL_OFFSET; priv->buffer_size = QUADRO_CTRL_REPORT_SIZE; priv->ctrl_report_delay = CTRL_REPORT_DELAY; priv->flow_pulses_ctrl_offset = QUADRO_FLOW_PULSES_CTRL_OFFSET; priv->power_cycle_count_offset = QUADRO_POWER_CYCLES; priv->temp_label = label_temp_sensors; priv->virtual_temp_label = label_virtual_temp_sensors; priv->speed_label = label_quadro_speeds; priv->power_label = label_fan_power; priv->voltage_label = label_fan_voltage; priv->current_label = label_fan_current; break; case USB_PRODUCT_ID_HIGHFLOWNEXT: priv->kind = highflownext; priv->num_fans = 0; priv->num_temp_sensors = HIGHFLOWNEXT_NUM_SENSORS; priv->temp_sensor_start_offset = HIGHFLOWNEXT_SENSOR_START; priv->num_flow_sensors = HIGHFLOWNEXT_NUM_FLOW_SENSORS; priv->flow_sensors_start_offset = HIGHFLOWNEXT_FLOW; priv->power_cycle_count_offset = QUADRO_POWER_CYCLES; priv->temp_label = label_highflownext_temp_sensors; priv->speed_label = label_highflownext_fan_speed; priv->power_label = label_highflownext_power; priv->voltage_label = label_highflownext_voltage; break; case USB_PRODUCT_ID_LEAKSHIELD: /* * Choose the right Leakshield device, because * the other one acts as a keyboard */ if (hdev->type != 2) { ret = -ENODEV; goto fail_and_close; } priv->kind = leakshield; priv->num_fans = 0; priv->num_temp_sensors = LEAKSHIELD_NUM_SENSORS; priv->temp_sensor_start_offset = LEAKSHIELD_TEMPERATURE_1; priv->temp_label = label_leakshield_temp_sensors; priv->speed_label = label_leakshield_fan_speed; break; case USB_PRODUCT_ID_AQUASTREAMXT: priv->kind = aquastreamxt; priv->num_fans = AQUASTREAMXT_NUM_FANS; priv->fan_sensor_offsets = aquastreamxt_sensor_fan_offsets; priv->num_temp_sensors = AQUASTREAMXT_NUM_SENSORS; priv->temp_sensor_start_offset = AQUASTREAMXT_SENSOR_START; priv->buffer_size = AQUASTREAMXT_SENSOR_REPORT_SIZE; priv->temp_label = label_aquastreamxt_temp_sensors; priv->speed_label = label_d5next_speeds; priv->voltage_label = label_d5next_voltages; priv->current_label = label_d5next_current; break; case USB_PRODUCT_ID_AQUASTREAMULT: priv->kind = aquastreamult; priv->num_fans = AQUASTREAMULT_NUM_FANS; priv->fan_sensor_offsets = aquastreamult_sensor_fan_offsets; priv->num_temp_sensors = AQUASTREAMULT_NUM_SENSORS; priv->temp_sensor_start_offset = AQUASTREAMULT_SENSOR_START; priv->temp_label = label_aquastreamult_temp; priv->speed_label = label_aquastreamult_speeds; priv->power_label = label_aquastreamult_power; priv->voltage_label = label_aquastreamult_voltages; priv->current_label = label_aquastreamult_current; break; case USB_PRODUCT_ID_POWERADJUST3: priv->kind = poweradjust3; priv->num_fans = 0; priv->num_temp_sensors = POWERADJUST3_NUM_SENSORS; priv->temp_sensor_start_offset = POWERADJUST3_SENSOR_START; priv->buffer_size = POWERADJUST3_SENSOR_REPORT_SIZE; priv->temp_label = label_poweradjust3_temp_sensors; break; case USB_PRODUCT_ID_HIGHFLOW: priv->kind = highflow; priv->num_fans = 0; priv->num_temp_sensors = HIGHFLOW_NUM_SENSORS; priv->temp_sensor_start_offset = HIGHFLOW_SENSOR_START; priv->num_flow_sensors = HIGHFLOW_NUM_FLOW_SENSORS; priv->flow_sensors_start_offset = HIGHFLOW_FLOW_SENSOR_OFFSET; priv->buffer_size = HIGHFLOW_SENSOR_REPORT_SIZE; priv->temp_label = label_highflow_temp; priv->speed_label = label_highflow_speeds; break; default: break; } switch (priv->kind) { case aquaero: priv->serial_number_start_offset = AQUAERO_SERIAL_START; priv->firmware_version_offset = AQUAERO_FIRMWARE_VERSION; priv->fan_structure = &aqc_aquaero_fan_structure; priv->ctrl_report_id = AQUAERO_CTRL_REPORT_ID; priv->secondary_ctrl_report_id = AQUAERO_SECONDARY_CTRL_REPORT_ID; priv->secondary_ctrl_report_size = AQUAERO_SECONDARY_CTRL_REPORT_SIZE; priv->secondary_ctrl_report = aquaero_secondary_ctrl_report; break; case poweradjust3: priv->status_report_id = POWERADJUST3_STATUS_REPORT_ID; break; case aquastreamxt: priv->serial_number_start_offset = AQUASTREAMXT_SERIAL_START; priv->firmware_version_offset = AQUASTREAMXT_FIRMWARE_VERSION; priv->status_report_id = AQUASTREAMXT_STATUS_REPORT_ID; break; case highflow: priv->serial_number_start_offset = HIGHFLOW_SERIAL_START; priv->firmware_version_offset = HIGHFLOW_FIRMWARE_VERSION; priv->status_report_id = HIGHFLOW_STATUS_REPORT_ID; break; default: priv->serial_number_start_offset = AQC_SERIAL_START; priv->firmware_version_offset = AQC_FIRMWARE_VERSION; priv->ctrl_report_id = CTRL_REPORT_ID; priv->secondary_ctrl_report_id = SECONDARY_CTRL_REPORT_ID; priv->secondary_ctrl_report_size = SECONDARY_CTRL_REPORT_SIZE; priv->secondary_ctrl_report = secondary_ctrl_report; if (priv->kind == aquastreamult) priv->fan_structure = &aqc_aquastreamult_fan_structure; else priv->fan_structure = &aqc_general_fan_structure; break; } if (priv->buffer_size != 0) { priv->checksum_start = 0x01; priv->checksum_length = priv->buffer_size - 3; priv->checksum_offset = priv->buffer_size - 2; } priv->name = aqc_device_names[priv->kind]; priv->buffer = devm_kzalloc(&hdev->dev, priv->buffer_size, GFP_KERNEL); if (!priv->buffer) { ret = -ENOMEM; goto fail_and_close; } priv->hwmon_dev = hwmon_device_register_with_info(&hdev->dev, priv->name, priv, &aqc_chip_info, NULL); if (IS_ERR(priv->hwmon_dev)) { ret = PTR_ERR(priv->hwmon_dev); goto fail_and_close; } aqc_debugfs_init(priv); return 0; fail_and_close: hid_hw_close(hdev); fail_and_stop: hid_hw_stop(hdev); return ret; } static void aqc_remove(struct hid_device *hdev) { struct aqc_data *priv = hid_get_drvdata(hdev); debugfs_remove_recursive(priv->debugfs); hwmon_device_unregister(priv->hwmon_dev); hid_hw_close(hdev); hid_hw_stop(hdev); } static const struct hid_device_id aqc_table[] = { { HID_USB_DEVICE(USB_VENDOR_ID_AQUACOMPUTER, USB_PRODUCT_ID_AQUAERO) }, { HID_USB_DEVICE(USB_VENDOR_ID_AQUACOMPUTER, USB_PRODUCT_ID_D5NEXT) }, { HID_USB_DEVICE(USB_VENDOR_ID_AQUACOMPUTER, USB_PRODUCT_ID_FARBWERK) }, { HID_USB_DEVICE(USB_VENDOR_ID_AQUACOMPUTER, USB_PRODUCT_ID_FARBWERK360) }, { HID_USB_DEVICE(USB_VENDOR_ID_AQUACOMPUTER, USB_PRODUCT_ID_OCTO) }, { HID_USB_DEVICE(USB_VENDOR_ID_AQUACOMPUTER, USB_PRODUCT_ID_QUADRO) }, { HID_USB_DEVICE(USB_VENDOR_ID_AQUACOMPUTER, USB_PRODUCT_ID_HIGHFLOWNEXT) }, { HID_USB_DEVICE(USB_VENDOR_ID_AQUACOMPUTER, USB_PRODUCT_ID_LEAKSHIELD) }, { HID_USB_DEVICE(USB_VENDOR_ID_AQUACOMPUTER, USB_PRODUCT_ID_AQUASTREAMXT) }, { HID_USB_DEVICE(USB_VENDOR_ID_AQUACOMPUTER, USB_PRODUCT_ID_AQUASTREAMULT) }, { HID_USB_DEVICE(USB_VENDOR_ID_AQUACOMPUTER, USB_PRODUCT_ID_POWERADJUST3) }, { HID_USB_DEVICE(USB_VENDOR_ID_AQUACOMPUTER, USB_PRODUCT_ID_HIGHFLOW) }, { } }; MODULE_DEVICE_TABLE(hid, aqc_table); static struct hid_driver aqc_driver = { .name = DRIVER_NAME, .id_table = aqc_table, .probe = aqc_probe, .remove = aqc_remove, .raw_event = aqc_raw_event, }; static int __init aqc_init(void) { return hid_register_driver(&aqc_driver); } static void __exit aqc_exit(void) { hid_unregister_driver(&aqc_driver); } /* Request to initialize after the HID bus to ensure it's not being loaded before */ late_initcall(aqc_init); module_exit(aqc_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Aleksa Savic <savicaleksa83@gmail.com>"); MODULE_AUTHOR("Jack Doan <me@jackdoan.com>"); MODULE_DESCRIPTION("Hwmon driver for Aquacomputer devices"); |
| 356 356 356 353 357 357 19 19 371 324 370 372 372 371 371 371 34 32 32 32 130 131 29 29 29 130 378 371 371 371 376 19 19 19 19 19 19 233 233 24 234 24 233 234 233 233 234 234 273 270 3 273 272 2 271 271 268 13 259 259 271 12 14 248 249 24 224 23 23 23 224 246 246 8 120 232 234 11 148 148 148 123 123 56 146 148 24 24 24 24 24 24 24 24 24 24 24 30 24 24 24 24 34 34 34 30 11 11 11 411 372 373 373 373 28 28 9 9 9 9 9 28 28 28 28 28 273 255 273 174 272 273 5 272 273 273 273 272 273 272 273 273 273 273 232 234 232 94 250 94 252 234 234 232 234 234 234 234 233 233 234 233 234 233 234 233 233 25 25 24 24 24 24 24 24 24 23 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 131 130 128 131 131 29 131 370 367 338 369 371 315 367 371 370 234 234 233 234 233 233 232 234 158 234 234 190 189 188 189 189 121 158 158 158 158 67 151 190 5 119 120 120 4 4 120 120 120 5 120 120 39 109 109 107 119 120 120 120 120 5 372 141 372 131 436 438 438 438 424 438 273 425 326 424 19 19 19 13 19 19 2 19 9 9 9 320 321 317 318 | 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 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * All Rights Reserved. */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_log.h" #include "xfs_log_priv.h" #include "xfs_trace.h" #include "xfs_sysfs.h" #include "xfs_sb.h" #include "xfs_health.h" #include "xfs_zone_alloc.h" struct kmem_cache *xfs_log_ticket_cache; /* Local miscellaneous function prototypes */ STATIC struct xlog * xlog_alloc_log( struct xfs_mount *mp, struct xfs_buftarg *log_target, xfs_daddr_t blk_offset, int num_bblks); STATIC void xlog_dealloc_log( struct xlog *log); /* local state machine functions */ STATIC void xlog_state_done_syncing( struct xlog_in_core *iclog); STATIC void xlog_state_do_callback( struct xlog *log); STATIC int xlog_state_get_iclog_space( struct xlog *log, int len, struct xlog_in_core **iclog, struct xlog_ticket *ticket, int *logoffsetp); STATIC void xlog_sync( struct xlog *log, struct xlog_in_core *iclog, struct xlog_ticket *ticket); #if defined(DEBUG) STATIC void xlog_verify_iclog( struct xlog *log, struct xlog_in_core *iclog, int count); STATIC void xlog_verify_tail_lsn( struct xlog *log, struct xlog_in_core *iclog); #else #define xlog_verify_iclog(a,b,c) #define xlog_verify_tail_lsn(a,b) #endif STATIC int xlog_iclogs_empty( struct xlog *log); static int xfs_log_cover(struct xfs_mount *); /* * We need to make sure the buffer pointer returned is naturally aligned for the * biggest basic data type we put into it. We have already accounted for this * padding when sizing the buffer. * * However, this padding does not get written into the log, and hence we have to * track the space used by the log vectors separately to prevent log space hangs * due to inaccurate accounting (i.e. a leak) of the used log space through the * CIL context ticket. * * We also add space for the xlog_op_header that describes this region in the * log. This prepends the data region we return to the caller to copy their data * into, so do all the static initialisation of the ophdr now. Because the ophdr * is not 8 byte aligned, we have to be careful to ensure that we align the * start of the buffer such that the region we return to the call is 8 byte * aligned and packed against the tail of the ophdr. */ void * xlog_prepare_iovec( struct xfs_log_vec *lv, struct xfs_log_iovec **vecp, uint type) { struct xfs_log_iovec *vec = *vecp; struct xlog_op_header *oph; uint32_t len; void *buf; if (vec) { ASSERT(vec - lv->lv_iovecp < lv->lv_niovecs); vec++; } else { vec = &lv->lv_iovecp[0]; } len = lv->lv_buf_used + sizeof(struct xlog_op_header); if (!IS_ALIGNED(len, sizeof(uint64_t))) { lv->lv_buf_used = round_up(len, sizeof(uint64_t)) - sizeof(struct xlog_op_header); } vec->i_type = type; vec->i_addr = lv->lv_buf + lv->lv_buf_used; oph = vec->i_addr; oph->oh_clientid = XFS_TRANSACTION; oph->oh_res2 = 0; oph->oh_flags = 0; buf = vec->i_addr + sizeof(struct xlog_op_header); ASSERT(IS_ALIGNED((unsigned long)buf, sizeof(uint64_t))); *vecp = vec; return buf; } static inline void xlog_grant_sub_space( struct xlog_grant_head *head, int64_t bytes) { atomic64_sub(bytes, &head->grant); } static inline void xlog_grant_add_space( struct xlog_grant_head *head, int64_t bytes) { atomic64_add(bytes, &head->grant); } static void xlog_grant_head_init( struct xlog_grant_head *head) { atomic64_set(&head->grant, 0); INIT_LIST_HEAD(&head->waiters); spin_lock_init(&head->lock); } void xlog_grant_return_space( struct xlog *log, xfs_lsn_t old_head, xfs_lsn_t new_head) { int64_t diff = xlog_lsn_sub(log, new_head, old_head); xlog_grant_sub_space(&log->l_reserve_head, diff); xlog_grant_sub_space(&log->l_write_head, diff); } /* * Return the space in the log between the tail and the head. In the case where * we have overrun available reservation space, return 0. The memory barrier * pairs with the smp_wmb() in xlog_cil_ail_insert() to ensure that grant head * vs tail space updates are seen in the correct order and hence avoid * transients as space is transferred from the grant heads to the AIL on commit * completion. */ static uint64_t xlog_grant_space_left( struct xlog *log, struct xlog_grant_head *head) { int64_t free_bytes; smp_rmb(); /* paired with smp_wmb in xlog_cil_ail_insert() */ free_bytes = log->l_logsize - READ_ONCE(log->l_tail_space) - atomic64_read(&head->grant); if (free_bytes > 0) return free_bytes; return 0; } STATIC void xlog_grant_head_wake_all( struct xlog_grant_head *head) { struct xlog_ticket *tic; spin_lock(&head->lock); list_for_each_entry(tic, &head->waiters, t_queue) wake_up_process(tic->t_task); spin_unlock(&head->lock); } static inline int xlog_ticket_reservation( struct xlog *log, struct xlog_grant_head *head, struct xlog_ticket *tic) { if (head == &log->l_write_head) { ASSERT(tic->t_flags & XLOG_TIC_PERM_RESERV); return tic->t_unit_res; } if (tic->t_flags & XLOG_TIC_PERM_RESERV) return tic->t_unit_res * tic->t_cnt; return tic->t_unit_res; } STATIC bool xlog_grant_head_wake( struct xlog *log, struct xlog_grant_head *head, int *free_bytes) { struct xlog_ticket *tic; int need_bytes; list_for_each_entry(tic, &head->waiters, t_queue) { need_bytes = xlog_ticket_reservation(log, head, tic); if (*free_bytes < need_bytes) return false; *free_bytes -= need_bytes; trace_xfs_log_grant_wake_up(log, tic); wake_up_process(tic->t_task); } return true; } STATIC int xlog_grant_head_wait( struct xlog *log, struct xlog_grant_head *head, struct xlog_ticket *tic, int need_bytes) __releases(&head->lock) __acquires(&head->lock) { list_add_tail(&tic->t_queue, &head->waiters); do { if (xlog_is_shutdown(log)) goto shutdown; __set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock(&head->lock); XFS_STATS_INC(log->l_mp, xs_sleep_logspace); /* Push on the AIL to free up all the log space. */ xfs_ail_push_all(log->l_ailp); trace_xfs_log_grant_sleep(log, tic); schedule(); trace_xfs_log_grant_wake(log, tic); spin_lock(&head->lock); if (xlog_is_shutdown(log)) goto shutdown; } while (xlog_grant_space_left(log, head) < need_bytes); list_del_init(&tic->t_queue); return 0; shutdown: list_del_init(&tic->t_queue); return -EIO; } /* * Atomically get the log space required for a log ticket. * * Once a ticket gets put onto head->waiters, it will only return after the * needed reservation is satisfied. * * This function is structured so that it has a lock free fast path. This is * necessary because every new transaction reservation will come through this * path. Hence any lock will be globally hot if we take it unconditionally on * every pass. * * As tickets are only ever moved on and off head->waiters under head->lock, we * only need to take that lock if we are going to add the ticket to the queue * and sleep. We can avoid taking the lock if the ticket was never added to * head->waiters because the t_queue list head will be empty and we hold the * only reference to it so it can safely be checked unlocked. */ STATIC int xlog_grant_head_check( struct xlog *log, struct xlog_grant_head *head, struct xlog_ticket *tic, int *need_bytes) { int free_bytes; int error = 0; ASSERT(!xlog_in_recovery(log)); /* * If there are other waiters on the queue then give them a chance at * logspace before us. Wake up the first waiters, if we do not wake * up all the waiters then go to sleep waiting for more free space, * otherwise try to get some space for this transaction. */ *need_bytes = xlog_ticket_reservation(log, head, tic); free_bytes = xlog_grant_space_left(log, head); if (!list_empty_careful(&head->waiters)) { spin_lock(&head->lock); if (!xlog_grant_head_wake(log, head, &free_bytes) || free_bytes < *need_bytes) { error = xlog_grant_head_wait(log, head, tic, *need_bytes); } spin_unlock(&head->lock); } else if (free_bytes < *need_bytes) { spin_lock(&head->lock); error = xlog_grant_head_wait(log, head, tic, *need_bytes); spin_unlock(&head->lock); } return error; } bool xfs_log_writable( struct xfs_mount *mp) { /* * Do not write to the log on norecovery mounts, if the data or log * devices are read-only, or if the filesystem is shutdown. Read-only * mounts allow internal writes for log recovery and unmount purposes, * so don't restrict that case. */ if (xfs_has_norecovery(mp)) return false; if (xfs_readonly_buftarg(mp->m_ddev_targp)) return false; if (xfs_readonly_buftarg(mp->m_log->l_targ)) return false; if (xlog_is_shutdown(mp->m_log)) return false; return true; } /* * Replenish the byte reservation required by moving the grant write head. */ int xfs_log_regrant( struct xfs_mount *mp, struct xlog_ticket *tic) { struct xlog *log = mp->m_log; int need_bytes; int error = 0; if (xlog_is_shutdown(log)) return -EIO; XFS_STATS_INC(mp, xs_try_logspace); /* * This is a new transaction on the ticket, so we need to change the * transaction ID so that the next transaction has a different TID in * the log. Just add one to the existing tid so that we can see chains * of rolling transactions in the log easily. */ tic->t_tid++; tic->t_curr_res = tic->t_unit_res; if (tic->t_cnt > 0) return 0; trace_xfs_log_regrant(log, tic); error = xlog_grant_head_check(log, &log->l_write_head, tic, &need_bytes); if (error) goto out_error; xlog_grant_add_space(&log->l_write_head, need_bytes); trace_xfs_log_regrant_exit(log, tic); return 0; out_error: /* * If we are failing, make sure the ticket doesn't have any current * reservations. We don't want to add this back when the ticket/ * transaction gets cancelled. */ tic->t_curr_res = 0; tic->t_cnt = 0; /* ungrant will give back unit_res * t_cnt. */ return error; } /* * Reserve log space and return a ticket corresponding to the reservation. * * Each reservation is going to reserve extra space for a log record header. * When writes happen to the on-disk log, we don't subtract the length of the * log record header from any reservation. By wasting space in each * reservation, we prevent over allocation problems. */ int xfs_log_reserve( struct xfs_mount *mp, int unit_bytes, int cnt, struct xlog_ticket **ticp, bool permanent) { struct xlog *log = mp->m_log; struct xlog_ticket *tic; int need_bytes; int error = 0; if (xlog_is_shutdown(log)) return -EIO; XFS_STATS_INC(mp, xs_try_logspace); ASSERT(*ticp == NULL); tic = xlog_ticket_alloc(log, unit_bytes, cnt, permanent); *ticp = tic; trace_xfs_log_reserve(log, tic); error = xlog_grant_head_check(log, &log->l_reserve_head, tic, &need_bytes); if (error) goto out_error; xlog_grant_add_space(&log->l_reserve_head, need_bytes); xlog_grant_add_space(&log->l_write_head, need_bytes); trace_xfs_log_reserve_exit(log, tic); return 0; out_error: /* * If we are failing, make sure the ticket doesn't have any current * reservations. We don't want to add this back when the ticket/ * transaction gets cancelled. */ tic->t_curr_res = 0; tic->t_cnt = 0; /* ungrant will give back unit_res * t_cnt. */ return error; } /* * Run all the pending iclog callbacks and wake log force waiters and iclog * space waiters so they can process the newly set shutdown state. We really * don't care what order we process callbacks here because the log is shut down * and so state cannot change on disk anymore. However, we cannot wake waiters * until the callbacks have been processed because we may be in unmount and * we must ensure that all AIL operations the callbacks perform have completed * before we tear down the AIL. * * We avoid processing actively referenced iclogs so that we don't run callbacks * while the iclog owner might still be preparing the iclog for IO submssion. * These will be caught by xlog_state_iclog_release() and call this function * again to process any callbacks that may have been added to that iclog. */ static void xlog_state_shutdown_callbacks( struct xlog *log) { struct xlog_in_core *iclog; LIST_HEAD(cb_list); iclog = log->l_iclog; do { if (atomic_read(&iclog->ic_refcnt)) { /* Reference holder will re-run iclog callbacks. */ continue; } list_splice_init(&iclog->ic_callbacks, &cb_list); spin_unlock(&log->l_icloglock); xlog_cil_process_committed(&cb_list); spin_lock(&log->l_icloglock); wake_up_all(&iclog->ic_write_wait); wake_up_all(&iclog->ic_force_wait); } while ((iclog = iclog->ic_next) != log->l_iclog); wake_up_all(&log->l_flush_wait); } /* * Flush iclog to disk if this is the last reference to the given iclog and the * it is in the WANT_SYNC state. * * If XLOG_ICL_NEED_FUA is already set on the iclog, we need to ensure that the * log tail is updated correctly. NEED_FUA indicates that the iclog will be * written to stable storage, and implies that a commit record is contained * within the iclog. We need to ensure that the log tail does not move beyond * the tail that the first commit record in the iclog ordered against, otherwise * correct recovery of that checkpoint becomes dependent on future operations * performed on this iclog. * * Hence if NEED_FUA is set and the current iclog tail lsn is empty, write the * current tail into iclog. Once the iclog tail is set, future operations must * not modify it, otherwise they potentially violate ordering constraints for * the checkpoint commit that wrote the initial tail lsn value. The tail lsn in * the iclog will get zeroed on activation of the iclog after sync, so we * always capture the tail lsn on the iclog on the first NEED_FUA release * regardless of the number of active reference counts on this iclog. */ int xlog_state_release_iclog( struct xlog *log, struct xlog_in_core *iclog, struct xlog_ticket *ticket) { bool last_ref; lockdep_assert_held(&log->l_icloglock); trace_xlog_iclog_release(iclog, _RET_IP_); /* * Grabbing the current log tail needs to be atomic w.r.t. the writing * of the tail LSN into the iclog so we guarantee that the log tail does * not move between the first time we know that the iclog needs to be * made stable and when we eventually submit it. */ if ((iclog->ic_state == XLOG_STATE_WANT_SYNC || (iclog->ic_flags & XLOG_ICL_NEED_FUA)) && !iclog->ic_header->h_tail_lsn) { iclog->ic_header->h_tail_lsn = cpu_to_be64(atomic64_read(&log->l_tail_lsn)); } last_ref = atomic_dec_and_test(&iclog->ic_refcnt); if (xlog_is_shutdown(log)) { /* * If there are no more references to this iclog, process the * pending iclog callbacks that were waiting on the release of * this iclog. */ if (last_ref) xlog_state_shutdown_callbacks(log); return -EIO; } if (!last_ref) return 0; if (iclog->ic_state != XLOG_STATE_WANT_SYNC) { ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE); return 0; } iclog->ic_state = XLOG_STATE_SYNCING; xlog_verify_tail_lsn(log, iclog); trace_xlog_iclog_syncing(iclog, _RET_IP_); spin_unlock(&log->l_icloglock); xlog_sync(log, iclog, ticket); spin_lock(&log->l_icloglock); return 0; } /* * Mount a log filesystem * * mp - ubiquitous xfs mount point structure * log_target - buftarg of on-disk log device * blk_offset - Start block # where block size is 512 bytes (BBSIZE) * num_bblocks - Number of BBSIZE blocks in on-disk log * * Return error or zero. */ int xfs_log_mount( xfs_mount_t *mp, struct xfs_buftarg *log_target, xfs_daddr_t blk_offset, int num_bblks) { struct xlog *log; int error = 0; int min_logfsbs; if (!xfs_has_norecovery(mp)) { xfs_notice(mp, "Mounting V%d Filesystem %pU", XFS_SB_VERSION_NUM(&mp->m_sb), &mp->m_sb.sb_uuid); } else { xfs_notice(mp, "Mounting V%d filesystem %pU in no-recovery mode. Filesystem will be inconsistent.", XFS_SB_VERSION_NUM(&mp->m_sb), &mp->m_sb.sb_uuid); ASSERT(xfs_is_readonly(mp)); } log = xlog_alloc_log(mp, log_target, blk_offset, num_bblks); if (IS_ERR(log)) { error = PTR_ERR(log); goto out; } mp->m_log = log; /* * Now that we have set up the log and it's internal geometry * parameters, we can validate the given log space and drop a critical * message via syslog if the log size is too small. A log that is too * small can lead to unexpected situations in transaction log space * reservation stage. The superblock verifier has already validated all * the other log geometry constraints, so we don't have to check those * here. * * Note: For v4 filesystems, we can't just reject the mount if the * validation fails. This would mean that people would have to * downgrade their kernel just to remedy the situation as there is no * way to grow the log (short of black magic surgery with xfs_db). * * We can, however, reject mounts for V5 format filesystems, as the * mkfs binary being used to make the filesystem should never create a * filesystem with a log that is too small. */ min_logfsbs = xfs_log_calc_minimum_size(mp); if (mp->m_sb.sb_logblocks < min_logfsbs) { xfs_warn(mp, "Log size %d blocks too small, minimum size is %d blocks", mp->m_sb.sb_logblocks, min_logfsbs); /* * Log check errors are always fatal on v5; or whenever bad * metadata leads to a crash. */ if (xfs_has_crc(mp)) { xfs_crit(mp, "AAIEEE! Log failed size checks. Abort!"); ASSERT(0); error = -EINVAL; goto out_free_log; } xfs_crit(mp, "Log size out of supported range."); xfs_crit(mp, "Continuing onwards, but if log hangs are experienced then please report this message in the bug report."); } /* * Initialize the AIL now we have a log. */ error = xfs_trans_ail_init(mp); if (error) { xfs_warn(mp, "AIL initialisation failed: error %d", error); goto out_free_log; } log->l_ailp = mp->m_ail; /* * skip log recovery on a norecovery mount. pretend it all * just worked. */ if (!xfs_has_norecovery(mp)) { error = xlog_recover(log); if (error) { xfs_warn(mp, "log mount/recovery failed: error %d", error); xlog_recover_cancel(log); goto out_destroy_ail; } } error = xfs_sysfs_init(&log->l_kobj, &xfs_log_ktype, &mp->m_kobj, "log"); if (error) goto out_destroy_ail; /* Normal transactions can now occur */ clear_bit(XLOG_ACTIVE_RECOVERY, &log->l_opstate); /* * Now the log has been fully initialised and we know were our * space grant counters are, we can initialise the permanent ticket * needed for delayed logging to work. */ xlog_cil_init_post_recovery(log); return 0; out_destroy_ail: xfs_trans_ail_destroy(mp); out_free_log: xlog_dealloc_log(log); out: return error; } /* * Finish the recovery of the file system. This is separate from the * xfs_log_mount() call, because it depends on the code in xfs_mountfs() to read * in the root and real-time bitmap inodes between calling xfs_log_mount() and * here. * * If we finish recovery successfully, start the background log work. If we are * not doing recovery, then we have a RO filesystem and we don't need to start * it. */ int xfs_log_mount_finish( struct xfs_mount *mp) { struct xlog *log = mp->m_log; int error = 0; if (xfs_has_norecovery(mp)) { ASSERT(xfs_is_readonly(mp)); return 0; } /* * During the second phase of log recovery, we need iget and * iput to behave like they do for an active filesystem. * xfs_fs_drop_inode needs to be able to prevent the deletion * of inodes before we're done replaying log items on those * inodes. Turn it off immediately after recovery finishes * so that we don't leak the quota inodes if subsequent mount * activities fail. * * We let all inodes involved in redo item processing end up on * the LRU instead of being evicted immediately so that if we do * something to an unlinked inode, the irele won't cause * premature truncation and freeing of the inode, which results * in log recovery failure. We have to evict the unreferenced * lru inodes after clearing SB_ACTIVE because we don't * otherwise clean up the lru if there's a subsequent failure in * xfs_mountfs, which leads to us leaking the inodes if nothing * else (e.g. quotacheck) references the inodes before the * mount failure occurs. */ mp->m_super->s_flags |= SB_ACTIVE; xfs_log_work_queue(mp); if (xlog_recovery_needed(log)) error = xlog_recover_finish(log); mp->m_super->s_flags &= ~SB_ACTIVE; evict_inodes(mp->m_super); /* * Drain the buffer LRU after log recovery. This is required for v4 * filesystems to avoid leaving around buffers with NULL verifier ops, * but we do it unconditionally to make sure we're always in a clean * cache state after mount. * * Don't push in the error case because the AIL may have pending intents * that aren't removed until recovery is cancelled. */ if (xlog_recovery_needed(log)) { if (!error) { xfs_log_force(mp, XFS_LOG_SYNC); xfs_ail_push_all_sync(mp->m_ail); } xfs_notice(mp, "Ending recovery (logdev: %s)", mp->m_logname ? mp->m_logname : "internal"); } else { xfs_info(mp, "Ending clean mount"); } xfs_buftarg_drain(mp->m_ddev_targp); clear_bit(XLOG_RECOVERY_NEEDED, &log->l_opstate); /* Make sure the log is dead if we're returning failure. */ ASSERT(!error || xlog_is_shutdown(log)); return error; } /* * The mount has failed. Cancel the recovery if it hasn't completed and destroy * the log. */ void xfs_log_mount_cancel( struct xfs_mount *mp) { xlog_recover_cancel(mp->m_log); xfs_log_unmount(mp); } /* * Flush out the iclog to disk ensuring that device caches are flushed and * the iclog hits stable storage before any completion waiters are woken. */ static inline int xlog_force_iclog( struct xlog_in_core *iclog) { atomic_inc(&iclog->ic_refcnt); iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; if (iclog->ic_state == XLOG_STATE_ACTIVE) xlog_state_switch_iclogs(iclog->ic_log, iclog, 0); return xlog_state_release_iclog(iclog->ic_log, iclog, NULL); } /* * Cycle all the iclogbuf locks to make sure all log IO completion * is done before we tear down these buffers. */ static void xlog_wait_iclog_completion(struct xlog *log) { int i; struct xlog_in_core *iclog = log->l_iclog; for (i = 0; i < log->l_iclog_bufs; i++) { down(&iclog->ic_sema); up(&iclog->ic_sema); iclog = iclog->ic_next; } } /* * Wait for the iclog and all prior iclogs to be written disk as required by the * log force state machine. Waiting on ic_force_wait ensures iclog completions * have been ordered and callbacks run before we are woken here, hence * guaranteeing that all the iclogs up to this one are on stable storage. */ int xlog_wait_on_iclog( struct xlog_in_core *iclog) __releases(iclog->ic_log->l_icloglock) { struct xlog *log = iclog->ic_log; trace_xlog_iclog_wait_on(iclog, _RET_IP_); if (!xlog_is_shutdown(log) && iclog->ic_state != XLOG_STATE_ACTIVE && iclog->ic_state != XLOG_STATE_DIRTY) { XFS_STATS_INC(log->l_mp, xs_log_force_sleep); xlog_wait(&iclog->ic_force_wait, &log->l_icloglock); } else { spin_unlock(&log->l_icloglock); } if (xlog_is_shutdown(log)) return -EIO; return 0; } /* * Write out an unmount record using the ticket provided. We have to account for * the data space used in the unmount ticket as this write is not done from a * transaction context that has already done the accounting for us. */ static int xlog_write_unmount_record( struct xlog *log, struct xlog_ticket *ticket) { struct { struct xlog_op_header ophdr; struct xfs_unmount_log_format ulf; } unmount_rec = { .ophdr = { .oh_clientid = XFS_LOG, .oh_tid = cpu_to_be32(ticket->t_tid), .oh_flags = XLOG_UNMOUNT_TRANS, }, .ulf = { .magic = XLOG_UNMOUNT_TYPE, }, }; struct xfs_log_iovec reg = { .i_addr = &unmount_rec, .i_len = sizeof(unmount_rec), .i_type = XLOG_REG_TYPE_UNMOUNT, }; struct xfs_log_vec vec = { .lv_niovecs = 1, .lv_iovecp = ®, }; LIST_HEAD(lv_chain); list_add(&vec.lv_list, &lv_chain); BUILD_BUG_ON((sizeof(struct xlog_op_header) + sizeof(struct xfs_unmount_log_format)) != sizeof(unmount_rec)); /* account for space used by record data */ ticket->t_curr_res -= sizeof(unmount_rec); return xlog_write(log, NULL, &lv_chain, ticket, reg.i_len); } /* * Mark the filesystem clean by writing an unmount record to the head of the * log. */ static void xlog_unmount_write( struct xlog *log) { struct xfs_mount *mp = log->l_mp; struct xlog_in_core *iclog; struct xlog_ticket *tic = NULL; int error; error = xfs_log_reserve(mp, 600, 1, &tic, 0); if (error) goto out_err; error = xlog_write_unmount_record(log, tic); /* * At this point, we're umounting anyway, so there's no point in * transitioning log state to shutdown. Just continue... */ out_err: if (error) xfs_alert(mp, "%s: unmount record failed", __func__); spin_lock(&log->l_icloglock); iclog = log->l_iclog; error = xlog_force_iclog(iclog); xlog_wait_on_iclog(iclog); if (tic) { trace_xfs_log_umount_write(log, tic); xfs_log_ticket_ungrant(log, tic); } } static void xfs_log_unmount_verify_iclog( struct xlog *log) { struct xlog_in_core *iclog = log->l_iclog; do { ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE); ASSERT(iclog->ic_offset == 0); } while ((iclog = iclog->ic_next) != log->l_iclog); } /* * Unmount record used to have a string "Unmount filesystem--" in the * data section where the "Un" was really a magic number (XLOG_UNMOUNT_TYPE). * We just write the magic number now since that particular field isn't * currently architecture converted and "Unmount" is a bit foo. * As far as I know, there weren't any dependencies on the old behaviour. */ static void xfs_log_unmount_write( struct xfs_mount *mp) { struct xlog *log = mp->m_log; if (!xfs_log_writable(mp)) return; xfs_log_force(mp, XFS_LOG_SYNC); if (xlog_is_shutdown(log)) return; /* * If we think the summary counters are bad, avoid writing the unmount * record to force log recovery at next mount, after which the summary * counters will be recalculated. Refer to xlog_check_unmount_rec for * more details. */ if (xfs_fs_has_sickness(mp, XFS_SICK_FS_COUNTERS) || XFS_TEST_ERROR(mp, XFS_ERRTAG_FORCE_SUMMARY_RECALC)) { xfs_alert(mp, "%s: will fix summary counters at next mount", __func__); return; } xfs_log_unmount_verify_iclog(log); xlog_unmount_write(log); } /* * Empty the log for unmount/freeze. * * To do this, we first need to shut down the background log work so it is not * trying to cover the log as we clean up. We then need to unpin all objects in * the log so we can then flush them out. Once they have completed their IO and * run the callbacks removing themselves from the AIL, we can cover the log. */ int xfs_log_quiesce( struct xfs_mount *mp) { /* * Clear log incompat features since we're quiescing the log. Report * failures, though it's not fatal to have a higher log feature * protection level than the log contents actually require. */ if (xfs_clear_incompat_log_features(mp)) { int error; error = xfs_sync_sb(mp, false); if (error) xfs_warn(mp, "Failed to clear log incompat features on quiesce"); } cancel_delayed_work_sync(&mp->m_log->l_work); xfs_log_force(mp, XFS_LOG_SYNC); /* * The superblock buffer is uncached and while xfs_ail_push_all_sync() * will push it, xfs_buftarg_wait() will not wait for it. Further, * xfs_buf_iowait() cannot be used because it was pushed with the * XBF_ASYNC flag set, so we need to use a lock/unlock pair to wait for * the IO to complete. */ xfs_ail_push_all_sync(mp->m_ail); xfs_buftarg_wait(mp->m_ddev_targp); xfs_buf_lock(mp->m_sb_bp); xfs_buf_unlock(mp->m_sb_bp); return xfs_log_cover(mp); } void xfs_log_clean( struct xfs_mount *mp) { xfs_log_quiesce(mp); xfs_log_unmount_write(mp); } /* * Shut down and release the AIL and Log. * * During unmount, we need to ensure we flush all the dirty metadata objects * from the AIL so that the log is empty before we write the unmount record to * the log. Once this is done, we can tear down the AIL and the log. */ void xfs_log_unmount( struct xfs_mount *mp) { xfs_log_clean(mp); /* * If shutdown has come from iclog IO context, the log * cleaning will have been skipped and so we need to wait * for the iclog to complete shutdown processing before we * tear anything down. */ xlog_wait_iclog_completion(mp->m_log); xfs_buftarg_drain(mp->m_ddev_targp); xfs_trans_ail_destroy(mp); xfs_sysfs_del(&mp->m_log->l_kobj); xlog_dealloc_log(mp->m_log); } void xfs_log_item_init( struct xfs_mount *mp, struct xfs_log_item *item, int type, const struct xfs_item_ops *ops) { item->li_log = mp->m_log; item->li_ailp = mp->m_ail; item->li_type = type; item->li_ops = ops; item->li_lv = NULL; INIT_LIST_HEAD(&item->li_ail); INIT_LIST_HEAD(&item->li_cil); INIT_LIST_HEAD(&item->li_bio_list); INIT_LIST_HEAD(&item->li_trans); } /* * Wake up processes waiting for log space after we have moved the log tail. */ void xfs_log_space_wake( struct xfs_mount *mp) { struct xlog *log = mp->m_log; int free_bytes; if (xlog_is_shutdown(log)) return; if (!list_empty_careful(&log->l_write_head.waiters)) { ASSERT(!xlog_in_recovery(log)); spin_lock(&log->l_write_head.lock); free_bytes = xlog_grant_space_left(log, &log->l_write_head); xlog_grant_head_wake(log, &log->l_write_head, &free_bytes); spin_unlock(&log->l_write_head.lock); } if (!list_empty_careful(&log->l_reserve_head.waiters)) { ASSERT(!xlog_in_recovery(log)); spin_lock(&log->l_reserve_head.lock); free_bytes = xlog_grant_space_left(log, &log->l_reserve_head); xlog_grant_head_wake(log, &log->l_reserve_head, &free_bytes); spin_unlock(&log->l_reserve_head.lock); } } /* * Determine if we have a transaction that has gone to disk that needs to be * covered. To begin the transition to the idle state firstly the log needs to * be idle. That means the CIL, the AIL and the iclogs needs to be empty before * we start attempting to cover the log. * * Only if we are then in a state where covering is needed, the caller is * informed that dummy transactions are required to move the log into the idle * state. * * If there are any items in the AIl or CIL, then we do not want to attempt to * cover the log as we may be in a situation where there isn't log space * available to run a dummy transaction and this can lead to deadlocks when the * tail of the log is pinned by an item that is modified in the CIL. Hence * there's no point in running a dummy transaction at this point because we * can't start trying to idle the log until both the CIL and AIL are empty. */ static bool xfs_log_need_covered( struct xfs_mount *mp) { struct xlog *log = mp->m_log; bool needed = false; if (!xlog_cil_empty(log)) return false; spin_lock(&log->l_icloglock); switch (log->l_covered_state) { case XLOG_STATE_COVER_DONE: case XLOG_STATE_COVER_DONE2: case XLOG_STATE_COVER_IDLE: break; case XLOG_STATE_COVER_NEED: case XLOG_STATE_COVER_NEED2: if (xfs_ail_min_lsn(log->l_ailp)) break; if (!xlog_iclogs_empty(log)) break; needed = true; if (log->l_covered_state == XLOG_STATE_COVER_NEED) log->l_covered_state = XLOG_STATE_COVER_DONE; else log->l_covered_state = XLOG_STATE_COVER_DONE2; break; default: needed = true; break; } spin_unlock(&log->l_icloglock); return needed; } /* * Explicitly cover the log. This is similar to background log covering but * intended for usage in quiesce codepaths. The caller is responsible to ensure * the log is idle and suitable for covering. The CIL, iclog buffers and AIL * must all be empty. */ static int xfs_log_cover( struct xfs_mount *mp) { int error = 0; bool need_covered; ASSERT((xlog_cil_empty(mp->m_log) && xlog_iclogs_empty(mp->m_log) && !xfs_ail_min_lsn(mp->m_log->l_ailp)) || xlog_is_shutdown(mp->m_log)); if (!xfs_log_writable(mp)) return 0; /* * xfs_log_need_covered() is not idempotent because it progresses the * state machine if the log requires covering. Therefore, we must call * this function once and use the result until we've issued an sb sync. * Do so first to make that abundantly clear. * * Fall into the covering sequence if the log needs covering or the * mount has lazy superblock accounting to sync to disk. The sb sync * used for covering accumulates the in-core counters, so covering * handles this for us. */ need_covered = xfs_log_need_covered(mp); if (!need_covered && !xfs_has_lazysbcount(mp)) return 0; /* * To cover the log, commit the superblock twice (at most) in * independent checkpoints. The first serves as a reference for the * tail pointer. The sync transaction and AIL push empties the AIL and * updates the in-core tail to the LSN of the first checkpoint. The * second commit updates the on-disk tail with the in-core LSN, * covering the log. Push the AIL one more time to leave it empty, as * we found it. */ do { error = xfs_sync_sb(mp, true); if (error) break; xfs_ail_push_all_sync(mp->m_ail); } while (xfs_log_need_covered(mp)); return error; } static void xlog_ioend_work( struct work_struct *work) { struct xlog_in_core *iclog = container_of(work, struct xlog_in_core, ic_end_io_work); struct xlog *log = iclog->ic_log; int error; error = blk_status_to_errno(iclog->ic_bio.bi_status); #ifdef DEBUG /* treat writes with injected CRC errors as failed */ if (iclog->ic_fail_crc) error = -EIO; #endif /* * Race to shutdown the filesystem if we see an error. */ if (error || XFS_TEST_ERROR(log->l_mp, XFS_ERRTAG_IODONE_IOERR)) { xfs_alert(log->l_mp, "log I/O error %d", error); xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); } xlog_state_done_syncing(iclog); bio_uninit(&iclog->ic_bio); /* * Drop the lock to signal that we are done. Nothing references the * iclog after this, so an unmount waiting on this lock can now tear it * down safely. As such, it is unsafe to reference the iclog after the * unlock as we could race with it being freed. */ up(&iclog->ic_sema); } /* * Return size of each in-core log record buffer. * * All machines get 8 x 32kB buffers by default, unless tuned otherwise. * * If the filesystem blocksize is too large, we may need to choose a * larger size since the directory code currently logs entire blocks. */ STATIC void xlog_get_iclog_buffer_size( struct xfs_mount *mp, struct xlog *log) { if (mp->m_logbufs <= 0) mp->m_logbufs = XLOG_MAX_ICLOGS; if (mp->m_logbsize <= 0) mp->m_logbsize = XLOG_BIG_RECORD_BSIZE; log->l_iclog_bufs = mp->m_logbufs; log->l_iclog_size = mp->m_logbsize; /* * Combined size of the log record headers. The first 32k cycles * are stored directly in the xlog_rec_header, the rest in the * variable number of xlog_rec_ext_headers at its end. */ log->l_iclog_hsize = struct_size(log->l_iclog->ic_header, h_ext, DIV_ROUND_UP(mp->m_logbsize, XLOG_HEADER_CYCLE_SIZE) - 1); } void xfs_log_work_queue( struct xfs_mount *mp) { queue_delayed_work(mp->m_sync_workqueue, &mp->m_log->l_work, msecs_to_jiffies(xfs_syncd_centisecs * 10)); } /* * Clear the log incompat flags if we have the opportunity. * * This only happens if we're about to log the second dummy transaction as part * of covering the log. */ static inline void xlog_clear_incompat( struct xlog *log) { struct xfs_mount *mp = log->l_mp; if (!xfs_sb_has_incompat_log_feature(&mp->m_sb, XFS_SB_FEAT_INCOMPAT_LOG_ALL)) return; if (log->l_covered_state != XLOG_STATE_COVER_DONE2) return; xfs_clear_incompat_log_features(mp); } /* * Every sync period we need to unpin all items in the AIL and push them to * disk. If there is nothing dirty, then we might need to cover the log to * indicate that the filesystem is idle. */ static void xfs_log_worker( struct work_struct *work) { struct xlog *log = container_of(to_delayed_work(work), struct xlog, l_work); struct xfs_mount *mp = log->l_mp; /* dgc: errors ignored - not fatal and nowhere to report them */ if (xfs_fs_writable(mp, SB_FREEZE_WRITE) && xfs_log_need_covered(mp)) { /* * Dump a transaction into the log that contains no real change. * This is needed to stamp the current tail LSN into the log * during the covering operation. * * We cannot use an inode here for this - that will push dirty * state back up into the VFS and then periodic inode flushing * will prevent log covering from making progress. Hence we * synchronously log the superblock instead to ensure the * superblock is immediately unpinned and can be written back. */ xlog_clear_incompat(log); xfs_sync_sb(mp, true); } else xfs_log_force(mp, 0); /* start pushing all the metadata that is currently dirty */ xfs_ail_push_all(mp->m_ail); /* queue us up again */ xfs_log_work_queue(mp); } /* * This routine initializes some of the log structure for a given mount point. * Its primary purpose is to fill in enough, so recovery can occur. However, * some other stuff may be filled in too. */ STATIC struct xlog * xlog_alloc_log( struct xfs_mount *mp, struct xfs_buftarg *log_target, xfs_daddr_t blk_offset, int num_bblks) { struct xlog *log; struct xlog_in_core **iclogp; struct xlog_in_core *iclog, *prev_iclog = NULL; int i; int error = -ENOMEM; uint log2_size = 0; log = kzalloc(sizeof(struct xlog), GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!log) { xfs_warn(mp, "Log allocation failed: No memory!"); goto out; } log->l_mp = mp; log->l_targ = log_target; log->l_logsize = BBTOB(num_bblks); log->l_logBBstart = blk_offset; log->l_logBBsize = num_bblks; log->l_covered_state = XLOG_STATE_COVER_IDLE; set_bit(XLOG_ACTIVE_RECOVERY, &log->l_opstate); INIT_DELAYED_WORK(&log->l_work, xfs_log_worker); INIT_LIST_HEAD(&log->r_dfops); log->l_prev_block = -1; /* log->l_tail_lsn = 0x100000000LL; cycle = 1; current block = 0 */ xlog_assign_atomic_lsn(&log->l_tail_lsn, 1, 0); log->l_curr_cycle = 1; /* 0 is bad since this is initial value */ if (xfs_has_logv2(mp) && mp->m_sb.sb_logsunit > 1) log->l_iclog_roundoff = mp->m_sb.sb_logsunit; else log->l_iclog_roundoff = BBSIZE; xlog_grant_head_init(&log->l_reserve_head); xlog_grant_head_init(&log->l_write_head); error = -EFSCORRUPTED; if (xfs_has_sector(mp)) { log2_size = mp->m_sb.sb_logsectlog; if (log2_size < BBSHIFT) { xfs_warn(mp, "Log sector size too small (0x%x < 0x%x)", log2_size, BBSHIFT); goto out_free_log; } log2_size -= BBSHIFT; if (log2_size > mp->m_sectbb_log) { xfs_warn(mp, "Log sector size too large (0x%x > 0x%x)", log2_size, mp->m_sectbb_log); goto out_free_log; } /* for larger sector sizes, must have v2 or external log */ if (log2_size && log->l_logBBstart > 0 && !xfs_has_logv2(mp)) { xfs_warn(mp, "log sector size (0x%x) invalid for configuration.", log2_size); goto out_free_log; } } log->l_sectBBsize = 1 << log2_size; xlog_get_iclog_buffer_size(mp, log); spin_lock_init(&log->l_icloglock); init_waitqueue_head(&log->l_flush_wait); iclogp = &log->l_iclog; ASSERT(log->l_iclog_size >= 4096); for (i = 0; i < log->l_iclog_bufs; i++) { size_t bvec_size = howmany(log->l_iclog_size, PAGE_SIZE) * sizeof(struct bio_vec); iclog = kzalloc(sizeof(*iclog) + bvec_size, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!iclog) goto out_free_iclog; *iclogp = iclog; iclog->ic_prev = prev_iclog; prev_iclog = iclog; iclog->ic_header = kvzalloc(log->l_iclog_size, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!iclog->ic_header) goto out_free_iclog; iclog->ic_header->h_magicno = cpu_to_be32(XLOG_HEADER_MAGIC_NUM); iclog->ic_header->h_version = cpu_to_be32( xfs_has_logv2(log->l_mp) ? 2 : 1); iclog->ic_header->h_size = cpu_to_be32(log->l_iclog_size); iclog->ic_header->h_fmt = cpu_to_be32(XLOG_FMT); memcpy(&iclog->ic_header->h_fs_uuid, &mp->m_sb.sb_uuid, sizeof(iclog->ic_header->h_fs_uuid)); iclog->ic_datap = (void *)iclog->ic_header + log->l_iclog_hsize; iclog->ic_size = log->l_iclog_size - log->l_iclog_hsize; iclog->ic_state = XLOG_STATE_ACTIVE; iclog->ic_log = log; atomic_set(&iclog->ic_refcnt, 0); INIT_LIST_HEAD(&iclog->ic_callbacks); init_waitqueue_head(&iclog->ic_force_wait); init_waitqueue_head(&iclog->ic_write_wait); INIT_WORK(&iclog->ic_end_io_work, xlog_ioend_work); sema_init(&iclog->ic_sema, 1); iclogp = &iclog->ic_next; } *iclogp = log->l_iclog; /* complete ring */ log->l_iclog->ic_prev = prev_iclog; /* re-write 1st prev ptr */ log->l_ioend_workqueue = alloc_workqueue("xfs-log/%s", XFS_WQFLAGS(WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_PERCPU), 0, mp->m_super->s_id); if (!log->l_ioend_workqueue) goto out_free_iclog; error = xlog_cil_init(log); if (error) goto out_destroy_workqueue; return log; out_destroy_workqueue: destroy_workqueue(log->l_ioend_workqueue); out_free_iclog: for (iclog = log->l_iclog; iclog; iclog = prev_iclog) { prev_iclog = iclog->ic_next; kvfree(iclog->ic_header); kfree(iclog); if (prev_iclog == log->l_iclog) break; } out_free_log: kfree(log); out: return ERR_PTR(error); } /* xlog_alloc_log */ /* * Stamp cycle number in every block */ STATIC void xlog_pack_data( struct xlog *log, struct xlog_in_core *iclog, int roundoff) { struct xlog_rec_header *rhead = iclog->ic_header; __be32 cycle_lsn = CYCLE_LSN_DISK(rhead->h_lsn); char *dp = iclog->ic_datap; int i; for (i = 0; i < BTOBB(iclog->ic_offset + roundoff); i++) { *xlog_cycle_data(rhead, i) = *(__be32 *)dp; *(__be32 *)dp = cycle_lsn; dp += BBSIZE; } for (i = 0; i < (log->l_iclog_hsize >> BBSHIFT) - 1; i++) rhead->h_ext[i].xh_cycle = cycle_lsn; } /* * Calculate the checksum for a log buffer. * * This is a little more complicated than it should be because the various * headers and the actual data are non-contiguous. */ __le32 xlog_cksum( struct xlog *log, struct xlog_rec_header *rhead, char *dp, unsigned int hdrsize, unsigned int size) { uint32_t crc; /* first generate the crc for the record header ... */ crc = xfs_start_cksum_update((char *)rhead, hdrsize, offsetof(struct xlog_rec_header, h_crc)); /* ... then for additional cycle data for v2 logs ... */ if (xfs_has_logv2(log->l_mp)) { int xheads, i; xheads = DIV_ROUND_UP(size, XLOG_HEADER_CYCLE_SIZE) - 1; for (i = 0; i < xheads; i++) crc = crc32c(crc, &rhead->h_ext[i], XLOG_REC_EXT_SIZE); } /* ... and finally for the payload */ crc = crc32c(crc, dp, size); return xfs_end_cksum(crc); } static void xlog_bio_end_io( struct bio *bio) { struct xlog_in_core *iclog = bio->bi_private; queue_work(iclog->ic_log->l_ioend_workqueue, &iclog->ic_end_io_work); } STATIC void xlog_write_iclog( struct xlog *log, struct xlog_in_core *iclog, uint64_t bno, unsigned int count) { ASSERT(bno < log->l_logBBsize); trace_xlog_iclog_write(iclog, _RET_IP_); /* * We lock the iclogbufs here so that we can serialise against I/O * completion during unmount. We might be processing a shutdown * triggered during unmount, and that can occur asynchronously to the * unmount thread, and hence we need to ensure that completes before * tearing down the iclogbufs. Hence we need to hold the buffer lock * across the log IO to archieve that. */ down(&iclog->ic_sema); if (xlog_is_shutdown(log)) { /* * It would seem logical to return EIO here, but we rely on * the log state machine to propagate I/O errors instead of * doing it here. We kick of the state machine and unlock * the buffer manually, the code needs to be kept in sync * with the I/O completion path. */ goto sync; } /* * We use REQ_SYNC | REQ_IDLE here to tell the block layer the are more * IOs coming immediately after this one. This prevents the block layer * writeback throttle from throttling log writes behind background * metadata writeback and causing priority inversions. */ bio_init(&iclog->ic_bio, log->l_targ->bt_bdev, iclog->ic_bvec, howmany(count, PAGE_SIZE), REQ_OP_WRITE | REQ_META | REQ_SYNC | REQ_IDLE); iclog->ic_bio.bi_iter.bi_sector = log->l_logBBstart + bno; iclog->ic_bio.bi_end_io = xlog_bio_end_io; iclog->ic_bio.bi_private = iclog; if (iclog->ic_flags & XLOG_ICL_NEED_FLUSH) { iclog->ic_bio.bi_opf |= REQ_PREFLUSH; /* * For external log devices, we also need to flush the data * device cache first to ensure all metadata writeback covered * by the LSN in this iclog is on stable storage. This is slow, * but it *must* complete before we issue the external log IO. * * If the flush fails, we cannot conclude that past metadata * writeback from the log succeeded. Repeating the flush is * not possible, hence we must shut down with log IO error to * avoid shutdown re-entering this path and erroring out again. */ if (log->l_targ != log->l_mp->m_ddev_targp && blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev)) goto shutdown; } if (iclog->ic_flags & XLOG_ICL_NEED_FUA) iclog->ic_bio.bi_opf |= REQ_FUA; iclog->ic_flags &= ~(XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA); if (is_vmalloc_addr(iclog->ic_header)) { if (!bio_add_vmalloc(&iclog->ic_bio, iclog->ic_header, count)) goto shutdown; } else { bio_add_virt_nofail(&iclog->ic_bio, iclog->ic_header, count); } /* * If this log buffer would straddle the end of the log we will have * to split it up into two bios, so that we can continue at the start. */ if (bno + BTOBB(count) > log->l_logBBsize) { struct bio *split; split = bio_split(&iclog->ic_bio, log->l_logBBsize - bno, GFP_NOIO, &fs_bio_set); bio_chain(split, &iclog->ic_bio); submit_bio(split); /* restart at logical offset zero for the remainder */ iclog->ic_bio.bi_iter.bi_sector = log->l_logBBstart; } submit_bio(&iclog->ic_bio); return; shutdown: xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); sync: xlog_state_done_syncing(iclog); up(&iclog->ic_sema); } /* * We need to bump cycle number for the part of the iclog that is * written to the start of the log. Watch out for the header magic * number case, though. */ static void xlog_split_iclog( struct xlog *log, void *data, uint64_t bno, unsigned int count) { unsigned int split_offset = BBTOB(log->l_logBBsize - bno); unsigned int i; for (i = split_offset; i < count; i += BBSIZE) { uint32_t cycle = get_unaligned_be32(data + i); if (++cycle == XLOG_HEADER_MAGIC_NUM) cycle++; put_unaligned_be32(cycle, data + i); } } static int xlog_calc_iclog_size( struct xlog *log, struct xlog_in_core *iclog, uint32_t *roundoff) { uint32_t count_init, count; /* Add for LR header */ count_init = log->l_iclog_hsize + iclog->ic_offset; count = roundup(count_init, log->l_iclog_roundoff); *roundoff = count - count_init; ASSERT(count >= count_init); ASSERT(*roundoff < log->l_iclog_roundoff); return count; } /* * Flush out the in-core log (iclog) to the on-disk log in an asynchronous * fashion. Previously, we should have moved the current iclog * ptr in the log to point to the next available iclog. This allows further * write to continue while this code syncs out an iclog ready to go. * Before an in-core log can be written out, the data section must be scanned * to save away the 1st word of each BBSIZE block into the header. We replace * it with the current cycle count. Each BBSIZE block is tagged with the * cycle count because there in an implicit assumption that drives will * guarantee that entire 512 byte blocks get written at once. In other words, * we can't have part of a 512 byte block written and part not written. By * tagging each block, we will know which blocks are valid when recovering * after an unclean shutdown. * * This routine is single threaded on the iclog. No other thread can be in * this routine with the same iclog. Changing contents of iclog can there- * fore be done without grabbing the state machine lock. Updating the global * log will require grabbing the lock though. * * The entire log manager uses a logical block numbering scheme. Only * xlog_write_iclog knows about the fact that the log may not start with * block zero on a given device. */ STATIC void xlog_sync( struct xlog *log, struct xlog_in_core *iclog, struct xlog_ticket *ticket) { unsigned int count; /* byte count of bwrite */ unsigned int roundoff; /* roundoff to BB or stripe */ uint64_t bno; unsigned int size; ASSERT(atomic_read(&iclog->ic_refcnt) == 0); trace_xlog_iclog_sync(iclog, _RET_IP_); count = xlog_calc_iclog_size(log, iclog, &roundoff); /* * If we have a ticket, account for the roundoff via the ticket * reservation to avoid touching the hot grant heads needlessly. * Otherwise, we have to move grant heads directly. */ if (ticket) { ticket->t_curr_res -= roundoff; } else { xlog_grant_add_space(&log->l_reserve_head, roundoff); xlog_grant_add_space(&log->l_write_head, roundoff); } /* put cycle number in every block */ xlog_pack_data(log, iclog, roundoff); /* real byte length */ size = iclog->ic_offset; if (xfs_has_logv2(log->l_mp)) size += roundoff; iclog->ic_header->h_len = cpu_to_be32(size); XFS_STATS_INC(log->l_mp, xs_log_writes); XFS_STATS_ADD(log->l_mp, xs_log_blocks, BTOBB(count)); bno = BLOCK_LSN(be64_to_cpu(iclog->ic_header->h_lsn)); /* Do we need to split this write into 2 parts? */ if (bno + BTOBB(count) > log->l_logBBsize) xlog_split_iclog(log, iclog->ic_header, bno, count); /* calculcate the checksum */ iclog->ic_header->h_crc = xlog_cksum(log, iclog->ic_header, iclog->ic_datap, XLOG_REC_SIZE, size); /* * Intentionally corrupt the log record CRC based on the error injection * frequency, if defined. This facilitates testing log recovery in the * event of torn writes. Hence, set the IOABORT state to abort the log * write on I/O completion and shutdown the fs. The subsequent mount * detects the bad CRC and attempts to recover. */ #ifdef DEBUG if (XFS_TEST_ERROR(log->l_mp, XFS_ERRTAG_LOG_BAD_CRC)) { iclog->ic_header->h_crc &= cpu_to_le32(0xAAAAAAAA); iclog->ic_fail_crc = true; xfs_warn(log->l_mp, "Intentionally corrupted log record at LSN 0x%llx. Shutdown imminent.", be64_to_cpu(iclog->ic_header->h_lsn)); } #endif xlog_verify_iclog(log, iclog, count); xlog_write_iclog(log, iclog, bno, count); } /* * Deallocate a log structure */ STATIC void xlog_dealloc_log( struct xlog *log) { struct xlog_in_core *iclog, *next_iclog; int i; /* * Destroy the CIL after waiting for iclog IO completion because an * iclog EIO error will try to shut down the log, which accesses the * CIL to wake up the waiters. */ xlog_cil_destroy(log); iclog = log->l_iclog; for (i = 0; i < log->l_iclog_bufs; i++) { next_iclog = iclog->ic_next; kvfree(iclog->ic_header); kfree(iclog); iclog = next_iclog; } log->l_mp->m_log = NULL; destroy_workqueue(log->l_ioend_workqueue); kfree(log); } /* * Update counters atomically now that memcpy is done. */ static inline void xlog_state_finish_copy( struct xlog *log, struct xlog_in_core *iclog, int record_cnt, int copy_bytes) { lockdep_assert_held(&log->l_icloglock); be32_add_cpu(&iclog->ic_header->h_num_logops, record_cnt); iclog->ic_offset += copy_bytes; } /* * print out info relating to regions written which consume * the reservation */ void xlog_print_tic_res( struct xfs_mount *mp, struct xlog_ticket *ticket) { xfs_warn(mp, "ticket reservation summary:"); xfs_warn(mp, " unit res = %d bytes", ticket->t_unit_res); xfs_warn(mp, " current res = %d bytes", ticket->t_curr_res); xfs_warn(mp, " original count = %d", ticket->t_ocnt); xfs_warn(mp, " remaining count = %d", ticket->t_cnt); } /* * Print a summary of the transaction. */ void xlog_print_trans( struct xfs_trans *tp) { struct xfs_mount *mp = tp->t_mountp; struct xfs_log_item *lip; /* dump core transaction and ticket info */ xfs_warn(mp, "transaction summary:"); xfs_warn(mp, " log res = %d", tp->t_log_res); xfs_warn(mp, " log count = %d", tp->t_log_count); xfs_warn(mp, " flags = 0x%x", tp->t_flags); xlog_print_tic_res(mp, tp->t_ticket); /* dump each log item */ list_for_each_entry(lip, &tp->t_items, li_trans) { struct xfs_log_vec *lv = lip->li_lv; struct xfs_log_iovec *vec; int i; xfs_warn(mp, "log item: "); xfs_warn(mp, " type = 0x%x", lip->li_type); xfs_warn(mp, " flags = 0x%lx", lip->li_flags); if (!lv) continue; xfs_warn(mp, " niovecs = %d", lv->lv_niovecs); xfs_warn(mp, " alloc_size = %d", lv->lv_alloc_size); xfs_warn(mp, " bytes = %d", lv->lv_bytes); xfs_warn(mp, " buf used= %d", lv->lv_buf_used); /* dump each iovec for the log item */ vec = lv->lv_iovecp; for (i = 0; i < lv->lv_niovecs; i++) { int dumplen = min(vec->i_len, 32); xfs_warn(mp, " iovec[%d]", i); xfs_warn(mp, " type = 0x%x", vec->i_type); xfs_warn(mp, " len = %d", vec->i_len); xfs_warn(mp, " first %d bytes of iovec[%d]:", dumplen, i); xfs_hex_dump(vec->i_addr, dumplen); vec++; } } } static inline void xlog_write_iovec( struct xlog_in_core *iclog, uint32_t *log_offset, void *data, uint32_t write_len, int *bytes_left, uint32_t *record_cnt, uint32_t *data_cnt) { ASSERT(*log_offset < iclog->ic_log->l_iclog_size); ASSERT(*log_offset % sizeof(int32_t) == 0); ASSERT(write_len % sizeof(int32_t) == 0); memcpy(iclog->ic_datap + *log_offset, data, write_len); *log_offset += write_len; *bytes_left -= write_len; (*record_cnt)++; *data_cnt += write_len; } /* * Write log vectors into a single iclog which is guaranteed by the caller * to have enough space to write the entire log vector into. */ static void xlog_write_full( struct xfs_log_vec *lv, struct xlog_ticket *ticket, struct xlog_in_core *iclog, uint32_t *log_offset, uint32_t *len, uint32_t *record_cnt, uint32_t *data_cnt) { int index; ASSERT(*log_offset + *len <= iclog->ic_size || iclog->ic_state == XLOG_STATE_WANT_SYNC); /* * Ordered log vectors have no regions to write so this * loop will naturally skip them. */ for (index = 0; index < lv->lv_niovecs; index++) { struct xfs_log_iovec *reg = &lv->lv_iovecp[index]; struct xlog_op_header *ophdr = reg->i_addr; ophdr->oh_tid = cpu_to_be32(ticket->t_tid); xlog_write_iovec(iclog, log_offset, reg->i_addr, reg->i_len, len, record_cnt, data_cnt); } } static int xlog_write_get_more_iclog_space( struct xlog_ticket *ticket, struct xlog_in_core **iclogp, uint32_t *log_offset, uint32_t len, uint32_t *record_cnt, uint32_t *data_cnt) { struct xlog_in_core *iclog = *iclogp; struct xlog *log = iclog->ic_log; int error; spin_lock(&log->l_icloglock); ASSERT(iclog->ic_state == XLOG_STATE_WANT_SYNC); xlog_state_finish_copy(log, iclog, *record_cnt, *data_cnt); error = xlog_state_release_iclog(log, iclog, ticket); spin_unlock(&log->l_icloglock); if (error) return error; error = xlog_state_get_iclog_space(log, len, &iclog, ticket, log_offset); if (error) return error; *record_cnt = 0; *data_cnt = 0; *iclogp = iclog; return 0; } /* * Write log vectors into a single iclog which is smaller than the current chain * length. We write until we cannot fit a full record into the remaining space * and then stop. We return the log vector that is to be written that cannot * wholly fit in the iclog. */ static int xlog_write_partial( struct xfs_log_vec *lv, struct xlog_ticket *ticket, struct xlog_in_core **iclogp, uint32_t *log_offset, uint32_t *len, uint32_t *record_cnt, uint32_t *data_cnt) { struct xlog_in_core *iclog = *iclogp; struct xlog_op_header *ophdr; int index = 0; uint32_t rlen; int error; /* walk the logvec, copying until we run out of space in the iclog */ for (index = 0; index < lv->lv_niovecs; index++) { struct xfs_log_iovec *reg = &lv->lv_iovecp[index]; uint32_t reg_offset = 0; /* * The first region of a continuation must have a non-zero * length otherwise log recovery will just skip over it and * start recovering from the next opheader it finds. Because we * mark the next opheader as a continuation, recovery will then * incorrectly add the continuation to the previous region and * that breaks stuff. * * Hence if there isn't space for region data after the * opheader, then we need to start afresh with a new iclog. */ if (iclog->ic_size - *log_offset <= sizeof(struct xlog_op_header)) { error = xlog_write_get_more_iclog_space(ticket, &iclog, log_offset, *len, record_cnt, data_cnt); if (error) return error; } ophdr = reg->i_addr; rlen = min_t(uint32_t, reg->i_len, iclog->ic_size - *log_offset); ophdr->oh_tid = cpu_to_be32(ticket->t_tid); ophdr->oh_len = cpu_to_be32(rlen - sizeof(struct xlog_op_header)); if (rlen != reg->i_len) ophdr->oh_flags |= XLOG_CONTINUE_TRANS; xlog_write_iovec(iclog, log_offset, reg->i_addr, rlen, len, record_cnt, data_cnt); /* If we wrote the whole region, move to the next. */ if (rlen == reg->i_len) continue; /* * We now have a partially written iovec, but it can span * multiple iclogs so we loop here. First we release the iclog * we currently have, then we get a new iclog and add a new * opheader. Then we continue copying from where we were until * we either complete the iovec or fill the iclog. If we * complete the iovec, then we increment the index and go right * back to the top of the outer loop. if we fill the iclog, we * run the inner loop again. * * This is complicated by the tail of a region using all the * space in an iclog and hence requiring us to release the iclog * and get a new one before returning to the outer loop. We must * always guarantee that we exit this inner loop with at least * space for log transaction opheaders left in the current * iclog, hence we cannot just terminate the loop at the end * of the of the continuation. So we loop while there is no * space left in the current iclog, and check for the end of the * continuation after getting a new iclog. */ do { /* * Ensure we include the continuation opheader in the * space we need in the new iclog by adding that size * to the length we require. This continuation opheader * needs to be accounted to the ticket as the space it * consumes hasn't been accounted to the lv we are * writing. */ error = xlog_write_get_more_iclog_space(ticket, &iclog, log_offset, *len + sizeof(struct xlog_op_header), record_cnt, data_cnt); if (error) return error; ophdr = iclog->ic_datap + *log_offset; ophdr->oh_tid = cpu_to_be32(ticket->t_tid); ophdr->oh_clientid = XFS_TRANSACTION; ophdr->oh_res2 = 0; ophdr->oh_flags = XLOG_WAS_CONT_TRANS; ticket->t_curr_res -= sizeof(struct xlog_op_header); *log_offset += sizeof(struct xlog_op_header); *data_cnt += sizeof(struct xlog_op_header); /* * If rlen fits in the iclog, then end the region * continuation. Otherwise we're going around again. */ reg_offset += rlen; rlen = reg->i_len - reg_offset; if (rlen <= iclog->ic_size - *log_offset) ophdr->oh_flags |= XLOG_END_TRANS; else ophdr->oh_flags |= XLOG_CONTINUE_TRANS; rlen = min_t(uint32_t, rlen, iclog->ic_size - *log_offset); ophdr->oh_len = cpu_to_be32(rlen); xlog_write_iovec(iclog, log_offset, reg->i_addr + reg_offset, rlen, len, record_cnt, data_cnt); } while (ophdr->oh_flags & XLOG_CONTINUE_TRANS); } /* * No more iovecs remain in this logvec so return the next log vec to * the caller so it can go back to fast path copying. */ *iclogp = iclog; return 0; } /* * Write some region out to in-core log * * This will be called when writing externally provided regions or when * writing out a commit record for a given transaction. * * General algorithm: * 1. Find total length of this write. This may include adding to the * lengths passed in. * 2. Check whether we violate the tickets reservation. * 3. While writing to this iclog * A. Reserve as much space in this iclog as can get * B. If this is first write, save away start lsn * C. While writing this region: * 1. If first write of transaction, write start record * 2. Write log operation header (header per region) * 3. Find out if we can fit entire region into this iclog * 4. Potentially, verify destination memcpy ptr * 5. Memcpy (partial) region * 6. If partial copy, release iclog; otherwise, continue * copying more regions into current iclog * 4. Mark want sync bit (in simulation mode) * 5. Release iclog for potential flush to on-disk log. * * ERRORS: * 1. Panic if reservation is overrun. This should never happen since * reservation amounts are generated internal to the filesystem. * NOTES: * 1. Tickets are single threaded data structures. * 2. The XLOG_END_TRANS & XLOG_CONTINUE_TRANS flags are passed down to the * syncing routine. When a single log_write region needs to span * multiple in-core logs, the XLOG_CONTINUE_TRANS bit should be set * on all log operation writes which don't contain the end of the * region. The XLOG_END_TRANS bit is used for the in-core log * operation which contains the end of the continued log_write region. * 3. When xlog_state_get_iclog_space() grabs the rest of the current iclog, * we don't really know exactly how much space will be used. As a result, * we don't update ic_offset until the end when we know exactly how many * bytes have been written out. */ int xlog_write( struct xlog *log, struct xfs_cil_ctx *ctx, struct list_head *lv_chain, struct xlog_ticket *ticket, uint32_t len) { struct xlog_in_core *iclog = NULL; struct xfs_log_vec *lv; uint32_t record_cnt = 0; uint32_t data_cnt = 0; int error = 0; int log_offset; if (ticket->t_curr_res < 0) { xfs_alert_tag(log->l_mp, XFS_PTAG_LOGRES, "ctx ticket reservation ran out. Need to up reservation"); xlog_print_tic_res(log->l_mp, ticket); xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); } error = xlog_state_get_iclog_space(log, len, &iclog, ticket, &log_offset); if (error) return error; ASSERT(log_offset <= iclog->ic_size - 1); /* * If we have a context pointer, pass it the first iclog we are * writing to so it can record state needed for iclog write * ordering. */ if (ctx) xlog_cil_set_ctx_write_state(ctx, iclog); list_for_each_entry(lv, lv_chain, lv_list) { /* * If the entire log vec does not fit in the iclog, punt it to * the partial copy loop which can handle this case. */ if (lv->lv_niovecs && lv->lv_bytes > iclog->ic_size - log_offset) { error = xlog_write_partial(lv, ticket, &iclog, &log_offset, &len, &record_cnt, &data_cnt); if (error) { /* * We have no iclog to release, so just return * the error immediately. */ return error; } } else { xlog_write_full(lv, ticket, iclog, &log_offset, &len, &record_cnt, &data_cnt); } } ASSERT(len == 0); /* * We've already been guaranteed that the last writes will fit inside * the current iclog, and hence it will already have the space used by * those writes accounted to it. Hence we do not need to update the * iclog with the number of bytes written here. */ spin_lock(&log->l_icloglock); xlog_state_finish_copy(log, iclog, record_cnt, 0); error = xlog_state_release_iclog(log, iclog, ticket); spin_unlock(&log->l_icloglock); return error; } static void xlog_state_activate_iclog( struct xlog_in_core *iclog, int *iclogs_changed) { ASSERT(list_empty_careful(&iclog->ic_callbacks)); trace_xlog_iclog_activate(iclog, _RET_IP_); /* * If the number of ops in this iclog indicate it just contains the * dummy transaction, we can change state into IDLE (the second time * around). Otherwise we should change the state into NEED a dummy. * We don't need to cover the dummy. */ if (*iclogs_changed == 0 && iclog->ic_header->h_num_logops == cpu_to_be32(XLOG_COVER_OPS)) { *iclogs_changed = 1; } else { /* * We have two dirty iclogs so start over. This could also be * num of ops indicating this is not the dummy going out. */ *iclogs_changed = 2; } iclog->ic_state = XLOG_STATE_ACTIVE; iclog->ic_offset = 0; iclog->ic_header->h_num_logops = 0; memset(iclog->ic_header->h_cycle_data, 0, sizeof(iclog->ic_header->h_cycle_data)); iclog->ic_header->h_lsn = 0; iclog->ic_header->h_tail_lsn = 0; } /* * Loop through all iclogs and mark all iclogs currently marked DIRTY as * ACTIVE after iclog I/O has completed. */ static void xlog_state_activate_iclogs( struct xlog *log, int *iclogs_changed) { struct xlog_in_core *iclog = log->l_iclog; do { if (iclog->ic_state == XLOG_STATE_DIRTY) xlog_state_activate_iclog(iclog, iclogs_changed); /* * The ordering of marking iclogs ACTIVE must be maintained, so * an iclog doesn't become ACTIVE beyond one that is SYNCING. */ else if (iclog->ic_state != XLOG_STATE_ACTIVE) break; } while ((iclog = iclog->ic_next) != log->l_iclog); } static int xlog_covered_state( int prev_state, int iclogs_changed) { /* * We go to NEED for any non-covering writes. We go to NEED2 if we just * wrote the first covering record (DONE). We go to IDLE if we just * wrote the second covering record (DONE2) and remain in IDLE until a * non-covering write occurs. */ switch (prev_state) { case XLOG_STATE_COVER_IDLE: if (iclogs_changed == 1) return XLOG_STATE_COVER_IDLE; fallthrough; case XLOG_STATE_COVER_NEED: case XLOG_STATE_COVER_NEED2: break; case XLOG_STATE_COVER_DONE: if (iclogs_changed == 1) return XLOG_STATE_COVER_NEED2; break; case XLOG_STATE_COVER_DONE2: if (iclogs_changed == 1) return XLOG_STATE_COVER_IDLE; break; default: ASSERT(0); } return XLOG_STATE_COVER_NEED; } STATIC void xlog_state_clean_iclog( struct xlog *log, struct xlog_in_core *dirty_iclog) { int iclogs_changed = 0; trace_xlog_iclog_clean(dirty_iclog, _RET_IP_); dirty_iclog->ic_state = XLOG_STATE_DIRTY; xlog_state_activate_iclogs(log, &iclogs_changed); wake_up_all(&dirty_iclog->ic_force_wait); if (iclogs_changed) { log->l_covered_state = xlog_covered_state(log->l_covered_state, iclogs_changed); } } STATIC xfs_lsn_t xlog_get_lowest_lsn( struct xlog *log) { struct xlog_in_core *iclog = log->l_iclog; xfs_lsn_t lowest_lsn = 0, lsn; do { if (iclog->ic_state == XLOG_STATE_ACTIVE || iclog->ic_state == XLOG_STATE_DIRTY) continue; lsn = be64_to_cpu(iclog->ic_header->h_lsn); if ((lsn && !lowest_lsn) || XFS_LSN_CMP(lsn, lowest_lsn) < 0) lowest_lsn = lsn; } while ((iclog = iclog->ic_next) != log->l_iclog); return lowest_lsn; } /* * Return true if we need to stop processing, false to continue to the next * iclog. The caller will need to run callbacks if the iclog is returned in the * XLOG_STATE_CALLBACK state. */ static bool xlog_state_iodone_process_iclog( struct xlog *log, struct xlog_in_core *iclog) { xfs_lsn_t lowest_lsn; xfs_lsn_t header_lsn; switch (iclog->ic_state) { case XLOG_STATE_ACTIVE: case XLOG_STATE_DIRTY: /* * Skip all iclogs in the ACTIVE & DIRTY states: */ return false; case XLOG_STATE_DONE_SYNC: /* * Now that we have an iclog that is in the DONE_SYNC state, do * one more check here to see if we have chased our tail around. * If this is not the lowest lsn iclog, then we will leave it * for another completion to process. */ header_lsn = be64_to_cpu(iclog->ic_header->h_lsn); lowest_lsn = xlog_get_lowest_lsn(log); if (lowest_lsn && XFS_LSN_CMP(lowest_lsn, header_lsn) < 0) return false; /* * If there are no callbacks on this iclog, we can mark it clean * immediately and return. Otherwise we need to run the * callbacks. */ if (list_empty(&iclog->ic_callbacks)) { xlog_state_clean_iclog(log, iclog); return false; } trace_xlog_iclog_callback(iclog, _RET_IP_); iclog->ic_state = XLOG_STATE_CALLBACK; return false; default: /* * Can only perform callbacks in order. Since this iclog is not * in the DONE_SYNC state, we skip the rest and just try to * clean up. */ return true; } } /* * Loop over all the iclogs, running attached callbacks on them. Return true if * we ran any callbacks, indicating that we dropped the icloglock. We don't need * to handle transient shutdown state here at all because * xlog_state_shutdown_callbacks() will be run to do the necessary shutdown * cleanup of the callbacks. */ static bool xlog_state_do_iclog_callbacks( struct xlog *log) __releases(&log->l_icloglock) __acquires(&log->l_icloglock) { struct xlog_in_core *first_iclog = log->l_iclog; struct xlog_in_core *iclog = first_iclog; bool ran_callback = false; do { LIST_HEAD(cb_list); if (xlog_state_iodone_process_iclog(log, iclog)) break; if (iclog->ic_state != XLOG_STATE_CALLBACK) { iclog = iclog->ic_next; continue; } list_splice_init(&iclog->ic_callbacks, &cb_list); spin_unlock(&log->l_icloglock); trace_xlog_iclog_callbacks_start(iclog, _RET_IP_); xlog_cil_process_committed(&cb_list); trace_xlog_iclog_callbacks_done(iclog, _RET_IP_); ran_callback = true; spin_lock(&log->l_icloglock); xlog_state_clean_iclog(log, iclog); iclog = iclog->ic_next; } while (iclog != first_iclog); return ran_callback; } /* * Loop running iclog completion callbacks until there are no more iclogs in a * state that can run callbacks. */ STATIC void xlog_state_do_callback( struct xlog *log) { int flushcnt = 0; int repeats = 0; spin_lock(&log->l_icloglock); while (xlog_state_do_iclog_callbacks(log)) { if (xlog_is_shutdown(log)) break; if (++repeats > 5000) { flushcnt += repeats; repeats = 0; xfs_warn(log->l_mp, "%s: possible infinite loop (%d iterations)", __func__, flushcnt); } } if (log->l_iclog->ic_state == XLOG_STATE_ACTIVE) wake_up_all(&log->l_flush_wait); spin_unlock(&log->l_icloglock); } /* * Finish transitioning this iclog to the dirty state. * * Callbacks could take time, so they are done outside the scope of the * global state machine log lock. */ STATIC void xlog_state_done_syncing( struct xlog_in_core *iclog) { struct xlog *log = iclog->ic_log; spin_lock(&log->l_icloglock); ASSERT(atomic_read(&iclog->ic_refcnt) == 0); trace_xlog_iclog_sync_done(iclog, _RET_IP_); /* * If we got an error, either on the first buffer, or in the case of * split log writes, on the second, we shut down the file system and * no iclogs should ever be attempted to be written to disk again. */ if (!xlog_is_shutdown(log)) { ASSERT(iclog->ic_state == XLOG_STATE_SYNCING); iclog->ic_state = XLOG_STATE_DONE_SYNC; } /* * Someone could be sleeping prior to writing out the next * iclog buffer, we wake them all, one will get to do the * I/O, the others get to wait for the result. */ wake_up_all(&iclog->ic_write_wait); spin_unlock(&log->l_icloglock); xlog_state_do_callback(log); } /* * If the head of the in-core log ring is not (ACTIVE or DIRTY), then we must * sleep. We wait on the flush queue on the head iclog as that should be * the first iclog to complete flushing. Hence if all iclogs are syncing, * we will wait here and all new writes will sleep until a sync completes. * * The in-core logs are used in a circular fashion. They are not used * out-of-order even when an iclog past the head is free. * * return: * * log_offset where xlog_write() can start writing into the in-core * log's data space. * * in-core log pointer to which xlog_write() should write. * * boolean indicating this is a continued write to an in-core log. * If this is the last write, then the in-core log's offset field * needs to be incremented, depending on the amount of data which * is copied. */ STATIC int xlog_state_get_iclog_space( struct xlog *log, int len, struct xlog_in_core **iclogp, struct xlog_ticket *ticket, int *logoffsetp) { int log_offset; struct xlog_rec_header *head; struct xlog_in_core *iclog; restart: spin_lock(&log->l_icloglock); if (xlog_is_shutdown(log)) { spin_unlock(&log->l_icloglock); return -EIO; } iclog = log->l_iclog; if (iclog->ic_state != XLOG_STATE_ACTIVE) { XFS_STATS_INC(log->l_mp, xs_log_noiclogs); /* Wait for log writes to have flushed */ xlog_wait(&log->l_flush_wait, &log->l_icloglock); goto restart; } head = iclog->ic_header; atomic_inc(&iclog->ic_refcnt); /* prevents sync */ log_offset = iclog->ic_offset; trace_xlog_iclog_get_space(iclog, _RET_IP_); /* On the 1st write to an iclog, figure out lsn. This works * if iclogs marked XLOG_STATE_WANT_SYNC always write out what they are * committing to. If the offset is set, that's how many blocks * must be written. */ if (log_offset == 0) { ticket->t_curr_res -= log->l_iclog_hsize; head->h_cycle = cpu_to_be32(log->l_curr_cycle); head->h_lsn = cpu_to_be64( xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block)); ASSERT(log->l_curr_block >= 0); } /* If there is enough room to write everything, then do it. Otherwise, * claim the rest of the region and make sure the XLOG_STATE_WANT_SYNC * bit is on, so this will get flushed out. Don't update ic_offset * until you know exactly how many bytes get copied. Therefore, wait * until later to update ic_offset. * * xlog_write() algorithm assumes that at least 2 xlog_op_header's * can fit into remaining data section. */ if (iclog->ic_size - iclog->ic_offset < 2 * sizeof(struct xlog_op_header)) { int error = 0; xlog_state_switch_iclogs(log, iclog, iclog->ic_size); /* * If we are the only one writing to this iclog, sync it to * disk. We need to do an atomic compare and decrement here to * avoid racing with concurrent atomic_dec_and_lock() calls in * xlog_state_release_iclog() when there is more than one * reference to the iclog. */ if (!atomic_add_unless(&iclog->ic_refcnt, -1, 1)) error = xlog_state_release_iclog(log, iclog, ticket); spin_unlock(&log->l_icloglock); if (error) return error; goto restart; } /* Do we have enough room to write the full amount in the remainder * of this iclog? Or must we continue a write on the next iclog and * mark this iclog as completely taken? In the case where we switch * iclogs (to mark it taken), this particular iclog will release/sync * to disk in xlog_write(). */ if (len <= iclog->ic_size - iclog->ic_offset) iclog->ic_offset += len; else xlog_state_switch_iclogs(log, iclog, iclog->ic_size); *iclogp = iclog; ASSERT(iclog->ic_offset <= iclog->ic_size); spin_unlock(&log->l_icloglock); *logoffsetp = log_offset; return 0; } /* * The first cnt-1 times a ticket goes through here we don't need to move the * grant write head because the permanent reservation has reserved cnt times the * unit amount. Release part of current permanent unit reservation and reset * current reservation to be one units worth. Also move grant reservation head * forward. */ void xfs_log_ticket_regrant( struct xlog *log, struct xlog_ticket *ticket) { trace_xfs_log_ticket_regrant(log, ticket); if (ticket->t_cnt > 0) ticket->t_cnt--; xlog_grant_sub_space(&log->l_reserve_head, ticket->t_curr_res); xlog_grant_sub_space(&log->l_write_head, ticket->t_curr_res); ticket->t_curr_res = ticket->t_unit_res; trace_xfs_log_ticket_regrant_sub(log, ticket); /* just return if we still have some of the pre-reserved space */ if (!ticket->t_cnt) { xlog_grant_add_space(&log->l_reserve_head, ticket->t_unit_res); trace_xfs_log_ticket_regrant_exit(log, ticket); } xfs_log_ticket_put(ticket); } /* * Give back the space left from a reservation. * * All the information we need to make a correct determination of space left * is present. For non-permanent reservations, things are quite easy. The * count should have been decremented to zero. We only need to deal with the * space remaining in the current reservation part of the ticket. If the * ticket contains a permanent reservation, there may be left over space which * needs to be released. A count of N means that N-1 refills of the current * reservation can be done before we need to ask for more space. The first * one goes to fill up the first current reservation. Once we run out of * space, the count will stay at zero and the only space remaining will be * in the current reservation field. */ void xfs_log_ticket_ungrant( struct xlog *log, struct xlog_ticket *ticket) { int bytes; trace_xfs_log_ticket_ungrant(log, ticket); if (ticket->t_cnt > 0) ticket->t_cnt--; trace_xfs_log_ticket_ungrant_sub(log, ticket); /* * If this is a permanent reservation ticket, we may be able to free * up more space based on the remaining count. */ bytes = ticket->t_curr_res; if (ticket->t_cnt > 0) { ASSERT(ticket->t_flags & XLOG_TIC_PERM_RESERV); bytes += ticket->t_unit_res*ticket->t_cnt; } xlog_grant_sub_space(&log->l_reserve_head, bytes); xlog_grant_sub_space(&log->l_write_head, bytes); trace_xfs_log_ticket_ungrant_exit(log, ticket); xfs_log_space_wake(log->l_mp); xfs_log_ticket_put(ticket); } /* * This routine will mark the current iclog in the ring as WANT_SYNC and move * the current iclog pointer to the next iclog in the ring. */ void xlog_state_switch_iclogs( struct xlog *log, struct xlog_in_core *iclog, int eventual_size) { ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE); assert_spin_locked(&log->l_icloglock); trace_xlog_iclog_switch(iclog, _RET_IP_); if (!eventual_size) eventual_size = iclog->ic_offset; iclog->ic_state = XLOG_STATE_WANT_SYNC; iclog->ic_header->h_prev_block = cpu_to_be32(log->l_prev_block); log->l_prev_block = log->l_curr_block; log->l_prev_cycle = log->l_curr_cycle; /* roll log?: ic_offset changed later */ log->l_curr_block += BTOBB(eventual_size)+BTOBB(log->l_iclog_hsize); /* Round up to next log-sunit */ if (log->l_iclog_roundoff > BBSIZE) { uint32_t sunit_bb = BTOBB(log->l_iclog_roundoff); log->l_curr_block = roundup(log->l_curr_block, sunit_bb); } if (log->l_curr_block >= log->l_logBBsize) { /* * Rewind the current block before the cycle is bumped to make * sure that the combined LSN never transiently moves forward * when the log wraps to the next cycle. This is to support the * unlocked sample of these fields from xlog_valid_lsn(). Most * other cases should acquire l_icloglock. */ log->l_curr_block -= log->l_logBBsize; ASSERT(log->l_curr_block >= 0); smp_wmb(); log->l_curr_cycle++; if (log->l_curr_cycle == XLOG_HEADER_MAGIC_NUM) log->l_curr_cycle++; } ASSERT(iclog == log->l_iclog); log->l_iclog = iclog->ic_next; } /* * Force the iclog to disk and check if the iclog has been completed before * xlog_force_iclog() returns. This can happen on synchronous (e.g. * pmem) or fast async storage because we drop the icloglock to issue the IO. * If completion has already occurred, tell the caller so that it can avoid an * unnecessary wait on the iclog. */ static int xlog_force_and_check_iclog( struct xlog_in_core *iclog, bool *completed) { xfs_lsn_t lsn = be64_to_cpu(iclog->ic_header->h_lsn); int error; *completed = false; error = xlog_force_iclog(iclog); if (error) return error; /* * If the iclog has already been completed and reused the header LSN * will have been rewritten by completion */ if (be64_to_cpu(iclog->ic_header->h_lsn) != lsn) *completed = true; return 0; } /* * Write out all data in the in-core log as of this exact moment in time. * * Data may be written to the in-core log during this call. However, * we don't guarantee this data will be written out. A change from past * implementation means this routine will *not* write out zero length LRs. * * Basically, we try and perform an intelligent scan of the in-core logs. * If we determine there is no flushable data, we just return. There is no * flushable data if: * * 1. the current iclog is active and has no data; the previous iclog * is in the active or dirty state. * 2. the current iclog is dirty, and the previous iclog is in the * active or dirty state. * * We may sleep if: * * 1. the current iclog is not in the active nor dirty state. * 2. the current iclog dirty, and the previous iclog is not in the * active nor dirty state. * 3. the current iclog is active, and there is another thread writing * to this particular iclog. * 4. a) the current iclog is active and has no other writers * b) when we return from flushing out this iclog, it is still * not in the active nor dirty state. */ int xfs_log_force( struct xfs_mount *mp, uint flags) { struct xlog *log = mp->m_log; struct xlog_in_core *iclog; XFS_STATS_INC(mp, xs_log_force); trace_xfs_log_force(mp, 0, _RET_IP_); xlog_cil_force(log); spin_lock(&log->l_icloglock); if (xlog_is_shutdown(log)) goto out_error; iclog = log->l_iclog; trace_xlog_iclog_force(iclog, _RET_IP_); if (iclog->ic_state == XLOG_STATE_DIRTY || (iclog->ic_state == XLOG_STATE_ACTIVE && atomic_read(&iclog->ic_refcnt) == 0 && iclog->ic_offset == 0)) { /* * If the head is dirty or (active and empty), then we need to * look at the previous iclog. * * If the previous iclog is active or dirty we are done. There * is nothing to sync out. Otherwise, we attach ourselves to the * previous iclog and go to sleep. */ iclog = iclog->ic_prev; } else if (iclog->ic_state == XLOG_STATE_ACTIVE) { if (atomic_read(&iclog->ic_refcnt) == 0) { /* We have exclusive access to this iclog. */ bool completed; if (xlog_force_and_check_iclog(iclog, &completed)) goto out_error; if (completed) goto out_unlock; } else { /* * Someone else is still writing to this iclog, so we * need to ensure that when they release the iclog it * gets synced immediately as we may be waiting on it. */ xlog_state_switch_iclogs(log, iclog, 0); } } /* * The iclog we are about to wait on may contain the checkpoint pushed * by the above xlog_cil_force() call, but it may not have been pushed * to disk yet. Like the ACTIVE case above, we need to make sure caches * are flushed when this iclog is written. */ if (iclog->ic_state == XLOG_STATE_WANT_SYNC) iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; if (flags & XFS_LOG_SYNC) return xlog_wait_on_iclog(iclog); out_unlock: spin_unlock(&log->l_icloglock); return 0; out_error: spin_unlock(&log->l_icloglock); return -EIO; } /* * Force the log to a specific LSN. * * If an iclog with that lsn can be found: * If it is in the DIRTY state, just return. * If it is in the ACTIVE state, move the in-core log into the WANT_SYNC * state and go to sleep or return. * If it is in any other state, go to sleep or return. * * Synchronous forces are implemented with a wait queue. All callers trying * to force a given lsn to disk must wait on the queue attached to the * specific in-core log. When given in-core log finally completes its write * to disk, that thread will wake up all threads waiting on the queue. */ static int xlog_force_lsn( struct xlog *log, xfs_lsn_t lsn, uint flags, int *log_flushed, bool already_slept) { struct xlog_in_core *iclog; bool completed; spin_lock(&log->l_icloglock); if (xlog_is_shutdown(log)) goto out_error; iclog = log->l_iclog; while (be64_to_cpu(iclog->ic_header->h_lsn) != lsn) { trace_xlog_iclog_force_lsn(iclog, _RET_IP_); iclog = iclog->ic_next; if (iclog == log->l_iclog) goto out_unlock; } switch (iclog->ic_state) { case XLOG_STATE_ACTIVE: /* * We sleep here if we haven't already slept (e.g. this is the * first time we've looked at the correct iclog buf) and the * buffer before us is going to be sync'ed. The reason for this * is that if we are doing sync transactions here, by waiting * for the previous I/O to complete, we can allow a few more * transactions into this iclog before we close it down. * * Otherwise, we mark the buffer WANT_SYNC, and bump up the * refcnt so we can release the log (which drops the ref count). * The state switch keeps new transaction commits from using * this buffer. When the current commits finish writing into * the buffer, the refcount will drop to zero and the buffer * will go out then. */ if (!already_slept && (iclog->ic_prev->ic_state == XLOG_STATE_WANT_SYNC || iclog->ic_prev->ic_state == XLOG_STATE_SYNCING)) { xlog_wait(&iclog->ic_prev->ic_write_wait, &log->l_icloglock); return -EAGAIN; } if (xlog_force_and_check_iclog(iclog, &completed)) goto out_error; if (log_flushed) *log_flushed = 1; if (completed) goto out_unlock; break; case XLOG_STATE_WANT_SYNC: /* * This iclog may contain the checkpoint pushed by the * xlog_cil_force_seq() call, but there are other writers still * accessing it so it hasn't been pushed to disk yet. Like the * ACTIVE case above, we need to make sure caches are flushed * when this iclog is written. */ iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA; break; default: /* * The entire checkpoint was written by the CIL force and is on * its way to disk already. It will be stable when it * completes, so we don't need to manipulate caches here at all. * We just need to wait for completion if necessary. */ break; } if (flags & XFS_LOG_SYNC) return xlog_wait_on_iclog(iclog); out_unlock: spin_unlock(&log->l_icloglock); return 0; out_error: spin_unlock(&log->l_icloglock); return -EIO; } /* * Force the log to a specific checkpoint sequence. * * First force the CIL so that all the required changes have been flushed to the * iclogs. If the CIL force completed it will return a commit LSN that indicates * the iclog that needs to be flushed to stable storage. If the caller needs * a synchronous log force, we will wait on the iclog with the LSN returned by * xlog_cil_force_seq() to be completed. */ int xfs_log_force_seq( struct xfs_mount *mp, xfs_csn_t seq, uint flags, int *log_flushed) { struct xlog *log = mp->m_log; xfs_lsn_t lsn; int ret; ASSERT(seq != 0); XFS_STATS_INC(mp, xs_log_force); trace_xfs_log_force(mp, seq, _RET_IP_); lsn = xlog_cil_force_seq(log, seq); if (lsn == NULLCOMMITLSN) return 0; ret = xlog_force_lsn(log, lsn, flags, log_flushed, false); if (ret == -EAGAIN) { XFS_STATS_INC(mp, xs_log_force_sleep); ret = xlog_force_lsn(log, lsn, flags, log_flushed, true); } return ret; } /* * Free a used ticket when its refcount falls to zero. */ void xfs_log_ticket_put( struct xlog_ticket *ticket) { ASSERT(atomic_read(&ticket->t_ref) > 0); if (atomic_dec_and_test(&ticket->t_ref)) kmem_cache_free(xfs_log_ticket_cache, ticket); } struct xlog_ticket * xfs_log_ticket_get( struct xlog_ticket *ticket) { ASSERT(atomic_read(&ticket->t_ref) > 0); atomic_inc(&ticket->t_ref); return ticket; } /* * Figure out the total log space unit (in bytes) that would be * required for a log ticket. */ static int xlog_calc_unit_res( struct xlog *log, int unit_bytes, int *niclogs) { int iclog_space; uint num_headers; /* * Permanent reservations have up to 'cnt'-1 active log operations * in the log. A unit in this case is the amount of space for one * of these log operations. Normal reservations have a cnt of 1 * and their unit amount is the total amount of space required. * * The following lines of code account for non-transaction data * which occupy space in the on-disk log. * * Normal form of a transaction is: * <oph><trans-hdr><start-oph><reg1-oph><reg1><reg2-oph>...<commit-oph> * and then there are LR hdrs, split-recs and roundoff at end of syncs. * * We need to account for all the leadup data and trailer data * around the transaction data. * And then we need to account for the worst case in terms of using * more space. * The worst case will happen if: * - the placement of the transaction happens to be such that the * roundoff is at its maximum * - the transaction data is synced before the commit record is synced * i.e. <transaction-data><roundoff> | <commit-rec><roundoff> * Therefore the commit record is in its own Log Record. * This can happen as the commit record is called with its * own region to xlog_write(). * This then means that in the worst case, roundoff can happen for * the commit-rec as well. * The commit-rec is smaller than padding in this scenario and so it is * not added separately. */ /* for trans header */ unit_bytes += sizeof(struct xlog_op_header); unit_bytes += sizeof(struct xfs_trans_header); /* for start-rec */ unit_bytes += sizeof(struct xlog_op_header); /* * for LR headers - the space for data in an iclog is the size minus * the space used for the headers. If we use the iclog size, then we * undercalculate the number of headers required. * * Furthermore - the addition of op headers for split-recs might * increase the space required enough to require more log and op * headers, so take that into account too. * * IMPORTANT: This reservation makes the assumption that if this * transaction is the first in an iclog and hence has the LR headers * accounted to it, then the remaining space in the iclog is * exclusively for this transaction. i.e. if the transaction is larger * than the iclog, it will be the only thing in that iclog. * Fundamentally, this means we must pass the entire log vector to * xlog_write to guarantee this. */ iclog_space = log->l_iclog_size - log->l_iclog_hsize; num_headers = howmany(unit_bytes, iclog_space); /* for split-recs - ophdrs added when data split over LRs */ unit_bytes += sizeof(struct xlog_op_header) * num_headers; /* add extra header reservations if we overrun */ while (!num_headers || howmany(unit_bytes, iclog_space) > num_headers) { unit_bytes += sizeof(struct xlog_op_header); num_headers++; } unit_bytes += log->l_iclog_hsize * num_headers; /* for commit-rec LR header - note: padding will subsume the ophdr */ unit_bytes += log->l_iclog_hsize; /* roundoff padding for transaction data and one for commit record */ unit_bytes += 2 * log->l_iclog_roundoff; if (niclogs) *niclogs = num_headers; return unit_bytes; } int xfs_log_calc_unit_res( struct xfs_mount *mp, int unit_bytes) { return xlog_calc_unit_res(mp->m_log, unit_bytes, NULL); } /* * Allocate and initialise a new log ticket. */ struct xlog_ticket * xlog_ticket_alloc( struct xlog *log, int unit_bytes, int cnt, bool permanent) { struct xlog_ticket *tic; int unit_res; tic = kmem_cache_zalloc(xfs_log_ticket_cache, GFP_KERNEL | __GFP_NOFAIL); unit_res = xlog_calc_unit_res(log, unit_bytes, &tic->t_iclog_hdrs); atomic_set(&tic->t_ref, 1); tic->t_task = current; INIT_LIST_HEAD(&tic->t_queue); tic->t_unit_res = unit_res; tic->t_curr_res = unit_res; tic->t_cnt = cnt; tic->t_ocnt = cnt; tic->t_tid = get_random_u32(); if (permanent) tic->t_flags |= XLOG_TIC_PERM_RESERV; return tic; } #if defined(DEBUG) static void xlog_verify_dump_tail( struct xlog *log, struct xlog_in_core *iclog) { xfs_alert(log->l_mp, "ran out of log space tail 0x%llx/0x%llx, head lsn 0x%llx, head 0x%x/0x%x, prev head 0x%x/0x%x", iclog ? be64_to_cpu(iclog->ic_header->h_tail_lsn) : -1, atomic64_read(&log->l_tail_lsn), log->l_ailp->ail_head_lsn, log->l_curr_cycle, log->l_curr_block, log->l_prev_cycle, log->l_prev_block); xfs_alert(log->l_mp, "write grant 0x%llx, reserve grant 0x%llx, tail_space 0x%llx, size 0x%x, iclog flags 0x%x", atomic64_read(&log->l_write_head.grant), atomic64_read(&log->l_reserve_head.grant), log->l_tail_space, log->l_logsize, iclog ? iclog->ic_flags : -1); } /* Check if the new iclog will fit in the log. */ STATIC void xlog_verify_tail_lsn( struct xlog *log, struct xlog_in_core *iclog) { xfs_lsn_t tail_lsn = be64_to_cpu(iclog->ic_header->h_tail_lsn); int blocks; if (CYCLE_LSN(tail_lsn) == log->l_prev_cycle) { blocks = log->l_logBBsize - (log->l_prev_block - BLOCK_LSN(tail_lsn)); if (blocks < BTOBB(iclog->ic_offset) + BTOBB(log->l_iclog_hsize)) { xfs_emerg(log->l_mp, "%s: ran out of log space", __func__); xlog_verify_dump_tail(log, iclog); } return; } if (CYCLE_LSN(tail_lsn) + 1 != log->l_prev_cycle) { xfs_emerg(log->l_mp, "%s: head has wrapped tail.", __func__); xlog_verify_dump_tail(log, iclog); return; } if (BLOCK_LSN(tail_lsn) == log->l_prev_block) { xfs_emerg(log->l_mp, "%s: tail wrapped", __func__); xlog_verify_dump_tail(log, iclog); return; } blocks = BLOCK_LSN(tail_lsn) - log->l_prev_block; if (blocks < BTOBB(iclog->ic_offset) + 1) { xfs_emerg(log->l_mp, "%s: ran out of iclog space", __func__); xlog_verify_dump_tail(log, iclog); } } /* * Perform a number of checks on the iclog before writing to disk. * * 1. Make sure the iclogs are still circular * 2. Make sure we have a good magic number * 3. Make sure we don't have magic numbers in the data * 4. Check fields of each log operation header for: * A. Valid client identifier * B. tid ptr value falls in valid ptr space (user space code) * C. Length in log record header is correct according to the * individual operation headers within record. * 5. When a bwrite will occur within 5 blocks of the front of the physical * log, check the preceding blocks of the physical log to make sure all * the cycle numbers agree with the current cycle number. */ STATIC void xlog_verify_iclog( struct xlog *log, struct xlog_in_core *iclog, int count) { struct xlog_rec_header *rhead = iclog->ic_header; struct xlog_in_core *icptr; void *base_ptr, *ptr; ptrdiff_t field_offset; uint8_t clientid; int len, i, op_len; int idx; /* check validity of iclog pointers */ spin_lock(&log->l_icloglock); icptr = log->l_iclog; for (i = 0; i < log->l_iclog_bufs; i++, icptr = icptr->ic_next) ASSERT(icptr); if (icptr != log->l_iclog) xfs_emerg(log->l_mp, "%s: corrupt iclog ring", __func__); spin_unlock(&log->l_icloglock); /* check log magic numbers */ if (rhead->h_magicno != cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) xfs_emerg(log->l_mp, "%s: invalid magic num", __func__); base_ptr = ptr = rhead; for (ptr += BBSIZE; ptr < base_ptr + count; ptr += BBSIZE) { if (*(__be32 *)ptr == cpu_to_be32(XLOG_HEADER_MAGIC_NUM)) xfs_emerg(log->l_mp, "%s: unexpected magic num", __func__); } /* check fields */ len = be32_to_cpu(rhead->h_num_logops); base_ptr = ptr = iclog->ic_datap; for (i = 0; i < len; i++) { struct xlog_op_header *ophead = ptr; void *p = &ophead->oh_clientid; /* clientid is only 1 byte */ field_offset = p - base_ptr; if (field_offset & 0x1ff) { clientid = ophead->oh_clientid; } else { idx = BTOBBT((void *)&ophead->oh_clientid - iclog->ic_datap); clientid = xlog_get_client_id(*xlog_cycle_data(rhead, idx)); } if (clientid != XFS_TRANSACTION && clientid != XFS_LOG) { xfs_warn(log->l_mp, "%s: op %d invalid clientid %d op "PTR_FMT" offset 0x%lx", __func__, i, clientid, ophead, (unsigned long)field_offset); } /* check length */ p = &ophead->oh_len; field_offset = p - base_ptr; if (field_offset & 0x1ff) { op_len = be32_to_cpu(ophead->oh_len); } else { idx = BTOBBT((void *)&ophead->oh_len - iclog->ic_datap); op_len = be32_to_cpu(*xlog_cycle_data(rhead, idx)); } ptr += sizeof(struct xlog_op_header) + op_len; } } #endif /* * Perform a forced shutdown on the log. * * This can be called from low level log code to trigger a shutdown, or from the * high level mount shutdown code when the mount shuts down. * * Our main objectives here are to make sure that: * a. if the shutdown was not due to a log IO error, flush the logs to * disk. Anything modified after this is ignored. * b. the log gets atomically marked 'XLOG_IO_ERROR' for all interested * parties to find out. Nothing new gets queued after this is done. * c. Tasks sleeping on log reservations, pinned objects and * other resources get woken up. * d. The mount is also marked as shut down so that log triggered shutdowns * still behave the same as if they called xfs_forced_shutdown(). * * Return true if the shutdown cause was a log IO error and we actually shut the * log down. */ bool xlog_force_shutdown( struct xlog *log, uint32_t shutdown_flags) { bool log_error = (shutdown_flags & SHUTDOWN_LOG_IO_ERROR); if (!log) return false; /* * Ensure that there is only ever one log shutdown being processed. * If we allow the log force below on a second pass after shutting * down the log, we risk deadlocking the CIL push as it may require * locks on objects the current shutdown context holds (e.g. taking * buffer locks to abort buffers on last unpin of buf log items). */ if (test_and_set_bit(XLOG_SHUTDOWN_STARTED, &log->l_opstate)) return false; /* * Flush all the completed transactions to disk before marking the log * being shut down. We need to do this first as shutting down the log * before the force will prevent the log force from flushing the iclogs * to disk. * * When we are in recovery, there are no transactions to flush, and * we don't want to touch the log because we don't want to perturb the * current head/tail for future recovery attempts. Hence we need to * avoid a log force in this case. * * If we are shutting down due to a log IO error, then we must avoid * trying to write the log as that may just result in more IO errors and * an endless shutdown/force loop. */ if (!log_error && !xlog_in_recovery(log)) xfs_log_force(log->l_mp, XFS_LOG_SYNC); /* * Atomically set the shutdown state. If the shutdown state is already * set, there someone else is performing the shutdown and so we are done * here. This should never happen because we should only ever get called * once by the first shutdown caller. * * Much of the log state machine transitions assume that shutdown state * cannot change once they hold the log->l_icloglock. Hence we need to * hold that lock here, even though we use the atomic test_and_set_bit() * operation to set the shutdown state. */ spin_lock(&log->l_icloglock); if (test_and_set_bit(XLOG_IO_ERROR, &log->l_opstate)) { spin_unlock(&log->l_icloglock); ASSERT(0); return false; } spin_unlock(&log->l_icloglock); /* * If this log shutdown also sets the mount shutdown state, issue a * shutdown warning message. */ if (!xfs_set_shutdown(log->l_mp)) { xfs_alert_tag(log->l_mp, XFS_PTAG_SHUTDOWN_LOGERROR, "Filesystem has been shut down due to log error (0x%x).", shutdown_flags); xfs_alert(log->l_mp, "Please unmount the filesystem and rectify the problem(s)."); if (xfs_error_level >= XFS_ERRLEVEL_HIGH) xfs_stack_trace(); } /* * We don't want anybody waiting for log reservations after this. That * means we have to wake up everybody queued up on reserveq as well as * writeq. In addition, we make sure in xlog_{re}grant_log_space that * we don't enqueue anything once the SHUTDOWN flag is set, and this * action is protected by the grant locks. */ xlog_grant_head_wake_all(&log->l_reserve_head); xlog_grant_head_wake_all(&log->l_write_head); /* * Wake up everybody waiting on xfs_log_force. Wake the CIL push first * as if the log writes were completed. The abort handling in the log * item committed callback functions will do this again under lock to * avoid races. */ spin_lock(&log->l_cilp->xc_push_lock); wake_up_all(&log->l_cilp->xc_start_wait); wake_up_all(&log->l_cilp->xc_commit_wait); spin_unlock(&log->l_cilp->xc_push_lock); spin_lock(&log->l_icloglock); xlog_state_shutdown_callbacks(log); spin_unlock(&log->l_icloglock); wake_up_var(&log->l_opstate); if (IS_ENABLED(CONFIG_XFS_RT) && xfs_has_zoned(log->l_mp)) xfs_zoned_wake_all(log->l_mp); return log_error; } STATIC int xlog_iclogs_empty( struct xlog *log) { struct xlog_in_core *iclog = log->l_iclog; do { /* endianness does not matter here, zero is zero in * any language. */ if (iclog->ic_header->h_num_logops) return 0; iclog = iclog->ic_next; } while (iclog != log->l_iclog); return 1; } /* * Verify that an LSN stamped into a piece of metadata is valid. This is * intended for use in read verifiers on v5 superblocks. */ bool xfs_log_check_lsn( struct xfs_mount *mp, xfs_lsn_t lsn) { struct xlog *log = mp->m_log; bool valid; /* * norecovery mode skips mount-time log processing and unconditionally * resets the in-core LSN. We can't validate in this mode, but * modifications are not allowed anyways so just return true. */ if (xfs_has_norecovery(mp)) return true; /* * Some metadata LSNs are initialized to NULL (e.g., the agfl). This is * handled by recovery and thus safe to ignore here. */ if (lsn == NULLCOMMITLSN) return true; valid = xlog_valid_lsn(mp->m_log, lsn); /* warn the user about what's gone wrong before verifier failure */ if (!valid) { spin_lock(&log->l_icloglock); xfs_warn(mp, "Corruption warning: Metadata has LSN (%d:%d) ahead of current LSN (%d:%d). " "Please unmount and run xfs_repair (>= v4.3) to resolve.", CYCLE_LSN(lsn), BLOCK_LSN(lsn), log->l_curr_cycle, log->l_curr_block); spin_unlock(&log->l_icloglock); } return valid; } |
| 183 183 295 294 120 120 120 181 180 180 181 181 8 181 2 181 181 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 181 182 181 180 181 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 2 2 2 2 2 2 2 181 180 181 181 180 180 164 181 181 180 180 174 182 181 174 174 181 181 2 181 188 188 181 181 180 181 181 181 182 182 181 181 27 27 181 180 181 181 181 180 180 181 181 136 180 180 181 179 180 180 180 182 182 182 182 181 182 182 180 2 182 188 187 180 181 179 181 113 113 113 113 113 113 113 113 113 113 113 113 113 100 113 113 113 113 113 113 113 113 113 113 113 113 113 113 113 88 88 85 85 85 85 113 113 113 113 113 113 113 113 113 7 181 7 7 7 7 7 6 8 7 7 7 9 9 6 6 6 6 6 6 6 6 6 6 6 6 6 6 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015 Facebook. All rights reserved. */ #include <linux/kernel.h> #include <linux/sched/mm.h> #include "messages.h" #include "ctree.h" #include "disk-io.h" #include "locking.h" #include "free-space-tree.h" #include "transaction.h" #include "block-group.h" #include "fs.h" #include "accessors.h" #include "extent-tree.h" #include "root-tree.h" static int __add_block_group_free_space(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path); static struct btrfs_root *btrfs_free_space_root( struct btrfs_block_group *block_group) { struct btrfs_key key = { .objectid = BTRFS_FREE_SPACE_TREE_OBJECTID, .type = BTRFS_ROOT_ITEM_KEY, .offset = 0, }; if (btrfs_fs_incompat(block_group->fs_info, EXTENT_TREE_V2)) key.offset = block_group->global_root_id; return btrfs_global_root(block_group->fs_info, &key); } void btrfs_set_free_space_tree_thresholds(struct btrfs_block_group *cache) { u32 bitmap_range; size_t bitmap_size; u64 num_bitmaps, total_bitmap_size; if (WARN_ON(cache->length == 0)) btrfs_warn(cache->fs_info, "block group %llu length is zero", cache->start); /* * We convert to bitmaps when the disk space required for using extents * exceeds that required for using bitmaps. */ bitmap_range = cache->fs_info->sectorsize * BTRFS_FREE_SPACE_BITMAP_BITS; num_bitmaps = div_u64(cache->length + bitmap_range - 1, bitmap_range); bitmap_size = sizeof(struct btrfs_item) + BTRFS_FREE_SPACE_BITMAP_SIZE; total_bitmap_size = num_bitmaps * bitmap_size; cache->bitmap_high_thresh = div_u64(total_bitmap_size, sizeof(struct btrfs_item)); /* * We allow for a small buffer between the high threshold and low * threshold to avoid thrashing back and forth between the two formats. */ if (cache->bitmap_high_thresh > 100) cache->bitmap_low_thresh = cache->bitmap_high_thresh - 100; else cache->bitmap_low_thresh = 0; } static int add_new_free_space_info(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path) { struct btrfs_root *root = btrfs_free_space_root(block_group); struct btrfs_free_space_info *info; struct btrfs_key key; struct extent_buffer *leaf; int ret; key.objectid = block_group->start; key.type = BTRFS_FREE_SPACE_INFO_KEY; key.offset = block_group->length; ret = btrfs_insert_empty_item(trans, root, path, &key, sizeof(*info)); if (ret) return ret; leaf = path->nodes[0]; info = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_free_space_info); btrfs_set_free_space_extent_count(leaf, info, 0); btrfs_set_free_space_flags(leaf, info, 0); btrfs_release_path(path); return 0; } EXPORT_FOR_TESTS struct btrfs_free_space_info *btrfs_search_free_space_info( struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path, int cow) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_root *root = btrfs_free_space_root(block_group); struct btrfs_key key; int ret; key.objectid = block_group->start; key.type = BTRFS_FREE_SPACE_INFO_KEY; key.offset = block_group->length; ret = btrfs_search_slot(trans, root, &key, path, 0, cow); if (ret < 0) return ERR_PTR(ret); if (ret != 0) { btrfs_warn(fs_info, "missing free space info for %llu", block_group->start); DEBUG_WARN(); return ERR_PTR(-ENOENT); } return btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_free_space_info); } /* * btrfs_search_slot() but we're looking for the greatest key less than the * passed key. */ static int btrfs_search_prev_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_key *key, struct btrfs_path *p, int ins_len, int cow) { int ret; ret = btrfs_search_slot(trans, root, key, p, ins_len, cow); if (ret < 0) return ret; if (unlikely(ret == 0)) { DEBUG_WARN(); return -EIO; } if (unlikely(p->slots[0] == 0)) { DEBUG_WARN("no previous slot found"); return -EIO; } p->slots[0]--; return 0; } static inline u32 free_space_bitmap_size(const struct btrfs_fs_info *fs_info, u64 size) { return DIV_ROUND_UP(size >> fs_info->sectorsize_bits, BITS_PER_BYTE); } static unsigned long *alloc_bitmap(u32 bitmap_size) { unsigned long *ret; unsigned int nofs_flag; u32 bitmap_rounded_size = round_up(bitmap_size, sizeof(unsigned long)); /* * GFP_NOFS doesn't work with kvmalloc(), but we really can't recurse * into the filesystem here. All callers hold a transaction handle * open, so if a GFP_KERNEL allocation recurses into the filesystem * and triggers a transaction commit, we would deadlock. */ nofs_flag = memalloc_nofs_save(); ret = kvzalloc(bitmap_rounded_size, GFP_KERNEL); memalloc_nofs_restore(nofs_flag); return ret; } static void le_bitmap_set(unsigned long *map, unsigned int start, int len) { u8 *p = ((u8 *)map) + BIT_BYTE(start); const unsigned int size = start + len; int bits_to_set = BITS_PER_BYTE - (start % BITS_PER_BYTE); u8 mask_to_set = BITMAP_FIRST_BYTE_MASK(start); while (len - bits_to_set >= 0) { *p |= mask_to_set; len -= bits_to_set; bits_to_set = BITS_PER_BYTE; mask_to_set = ~0; p++; } if (len) { mask_to_set &= BITMAP_LAST_BYTE_MASK(size); *p |= mask_to_set; } } EXPORT_FOR_TESTS int btrfs_convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *root = btrfs_free_space_root(block_group); struct btrfs_free_space_info *info; struct btrfs_key key, found_key; struct extent_buffer *leaf; unsigned long *bitmap; char *bitmap_cursor; u64 start, end; u64 bitmap_range, i; u32 bitmap_size, flags, expected_extent_count; u32 extent_count = 0; int done = 0, nr; int ret; bitmap_size = free_space_bitmap_size(fs_info, block_group->length); bitmap = alloc_bitmap(bitmap_size); if (unlikely(!bitmap)) return 0; start = block_group->start; end = block_group->start + block_group->length; key.objectid = end - 1; key.type = (u8)-1; key.offset = (u64)-1; while (!done) { ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out; } leaf = path->nodes[0]; nr = 0; path->slots[0]++; while (path->slots[0] > 0) { btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1); if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) { ASSERT(found_key.objectid == block_group->start); ASSERT(found_key.offset == block_group->length); done = 1; break; } else if (found_key.type == BTRFS_FREE_SPACE_EXTENT_KEY) { u64 first, last; ASSERT(found_key.objectid >= start); ASSERT(found_key.objectid < end); ASSERT(found_key.objectid + found_key.offset <= end); first = div_u64(found_key.objectid - start, fs_info->sectorsize); last = div_u64(found_key.objectid + found_key.offset - start, fs_info->sectorsize); le_bitmap_set(bitmap, first, last - first); extent_count++; nr++; path->slots[0]--; } else { ASSERT(0); } } ret = btrfs_del_items(trans, root, path, path->slots[0], nr); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out; } btrfs_release_path(path); } info = btrfs_search_free_space_info(trans, block_group, path, 1); if (IS_ERR(info)) { ret = PTR_ERR(info); btrfs_abort_transaction(trans, ret); goto out; } leaf = path->nodes[0]; flags = btrfs_free_space_flags(leaf, info); flags |= BTRFS_FREE_SPACE_USING_BITMAPS; block_group->using_free_space_bitmaps = true; block_group->using_free_space_bitmaps_cached = true; btrfs_set_free_space_flags(leaf, info, flags); expected_extent_count = btrfs_free_space_extent_count(leaf, info); btrfs_release_path(path); if (unlikely(extent_count != expected_extent_count)) { btrfs_err(fs_info, "incorrect extent count for %llu; counted %u, expected %u", block_group->start, extent_count, expected_extent_count); ret = -EIO; btrfs_abort_transaction(trans, ret); goto out; } bitmap_cursor = (char *)bitmap; bitmap_range = fs_info->sectorsize * BTRFS_FREE_SPACE_BITMAP_BITS; i = start; while (i < end) { unsigned long ptr; u64 extent_size; u32 data_size; extent_size = min(end - i, bitmap_range); data_size = free_space_bitmap_size(fs_info, extent_size); key.objectid = i; key.type = BTRFS_FREE_SPACE_BITMAP_KEY; key.offset = extent_size; ret = btrfs_insert_empty_item(trans, root, path, &key, data_size); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out; } leaf = path->nodes[0]; ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); write_extent_buffer(leaf, bitmap_cursor, ptr, data_size); btrfs_release_path(path); i += extent_size; bitmap_cursor += data_size; } ret = 0; out: kvfree(bitmap); return ret; } EXPORT_FOR_TESTS int btrfs_convert_free_space_to_extents(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *root = btrfs_free_space_root(block_group); struct btrfs_free_space_info *info; struct btrfs_key key, found_key; struct extent_buffer *leaf; unsigned long *bitmap; u64 start, end; u32 bitmap_size, flags, expected_extent_count; unsigned long nrbits, start_bit, end_bit; u32 extent_count = 0; int done = 0, nr; int ret; bitmap_size = free_space_bitmap_size(fs_info, block_group->length); bitmap = alloc_bitmap(bitmap_size); if (unlikely(!bitmap)) return 0; start = block_group->start; end = block_group->start + block_group->length; key.objectid = end - 1; key.type = (u8)-1; key.offset = (u64)-1; while (!done) { ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out; } leaf = path->nodes[0]; nr = 0; path->slots[0]++; while (path->slots[0] > 0) { btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1); if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) { ASSERT(found_key.objectid == block_group->start); ASSERT(found_key.offset == block_group->length); done = 1; break; } else if (found_key.type == BTRFS_FREE_SPACE_BITMAP_KEY) { unsigned long ptr; char *bitmap_cursor; u32 bitmap_pos, data_size; ASSERT(found_key.objectid >= start); ASSERT(found_key.objectid < end); ASSERT(found_key.objectid + found_key.offset <= end); bitmap_pos = div_u64(found_key.objectid - start, fs_info->sectorsize * BITS_PER_BYTE); bitmap_cursor = ((char *)bitmap) + bitmap_pos; data_size = free_space_bitmap_size(fs_info, found_key.offset); path->slots[0]--; ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); read_extent_buffer(leaf, bitmap_cursor, ptr, data_size); nr++; } else { ASSERT(0); } } ret = btrfs_del_items(trans, root, path, path->slots[0], nr); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out; } btrfs_release_path(path); } info = btrfs_search_free_space_info(trans, block_group, path, 1); if (IS_ERR(info)) { ret = PTR_ERR(info); btrfs_abort_transaction(trans, ret); goto out; } leaf = path->nodes[0]; flags = btrfs_free_space_flags(leaf, info); flags &= ~BTRFS_FREE_SPACE_USING_BITMAPS; block_group->using_free_space_bitmaps = false; block_group->using_free_space_bitmaps_cached = true; btrfs_set_free_space_flags(leaf, info, flags); expected_extent_count = btrfs_free_space_extent_count(leaf, info); btrfs_release_path(path); nrbits = block_group->length >> fs_info->sectorsize_bits; start_bit = find_next_bit_le(bitmap, nrbits, 0); while (start_bit < nrbits) { end_bit = find_next_zero_bit_le(bitmap, nrbits, start_bit); ASSERT(start_bit < end_bit); key.objectid = start + start_bit * fs_info->sectorsize; key.type = BTRFS_FREE_SPACE_EXTENT_KEY; key.offset = (end_bit - start_bit) * fs_info->sectorsize; ret = btrfs_insert_empty_item(trans, root, path, &key, 0); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out; } btrfs_release_path(path); extent_count++; start_bit = find_next_bit_le(bitmap, nrbits, end_bit); } if (unlikely(extent_count != expected_extent_count)) { btrfs_err(fs_info, "incorrect extent count for %llu; counted %u, expected %u", block_group->start, extent_count, expected_extent_count); ret = -EIO; btrfs_abort_transaction(trans, ret); goto out; } ret = 0; out: kvfree(bitmap); return ret; } static int update_free_space_extent_count(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path, int new_extents) { struct btrfs_free_space_info *info; u32 flags; u32 extent_count; int ret = 0; if (new_extents == 0) return 0; info = btrfs_search_free_space_info(trans, block_group, path, 1); if (IS_ERR(info)) return PTR_ERR(info); flags = btrfs_free_space_flags(path->nodes[0], info); extent_count = btrfs_free_space_extent_count(path->nodes[0], info); extent_count += new_extents; btrfs_set_free_space_extent_count(path->nodes[0], info, extent_count); btrfs_release_path(path); if (!(flags & BTRFS_FREE_SPACE_USING_BITMAPS) && extent_count > block_group->bitmap_high_thresh) { ret = btrfs_convert_free_space_to_bitmaps(trans, block_group, path); } else if ((flags & BTRFS_FREE_SPACE_USING_BITMAPS) && extent_count < block_group->bitmap_low_thresh) { ret = btrfs_convert_free_space_to_extents(trans, block_group, path); } return ret; } EXPORT_FOR_TESTS bool btrfs_free_space_test_bit(struct btrfs_block_group *block_group, struct btrfs_path *path, u64 offset) { struct extent_buffer *leaf; struct btrfs_key key; u64 found_start, found_end; unsigned long ptr, i; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); ASSERT(key.type == BTRFS_FREE_SPACE_BITMAP_KEY); found_start = key.objectid; found_end = key.objectid + key.offset; ASSERT(offset >= found_start && offset < found_end); ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); i = div_u64(offset - found_start, block_group->fs_info->sectorsize); return extent_buffer_test_bit(leaf, ptr, i); } static void free_space_modify_bits(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path, u64 *start, u64 *size, bool set_bits) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct extent_buffer *leaf; struct btrfs_key key; u64 end = *start + *size; u64 found_start, found_end; unsigned long ptr, first, last; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); ASSERT(key.type == BTRFS_FREE_SPACE_BITMAP_KEY); found_start = key.objectid; found_end = key.objectid + key.offset; ASSERT(*start >= found_start && *start < found_end); ASSERT(end > found_start); if (end > found_end) end = found_end; ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); first = (*start - found_start) >> fs_info->sectorsize_bits; last = (end - found_start) >> fs_info->sectorsize_bits; if (set_bits) extent_buffer_bitmap_set(leaf, ptr, first, last - first); else extent_buffer_bitmap_clear(leaf, ptr, first, last - first); btrfs_mark_buffer_dirty(trans, leaf); *size -= end - *start; *start = end; } /* * We can't use btrfs_next_item() in modify_free_space_bitmap() because * btrfs_next_leaf() doesn't get the path for writing. We can forgo the fancy * tree walking in btrfs_next_leaf() anyways because we know exactly what we're * looking for. */ static int free_space_next_bitmap(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *p) { struct btrfs_key key; if (p->slots[0] + 1 < btrfs_header_nritems(p->nodes[0])) { p->slots[0]++; return 0; } btrfs_item_key_to_cpu(p->nodes[0], &key, p->slots[0]); btrfs_release_path(p); key.objectid += key.offset; key.type = (u8)-1; key.offset = (u64)-1; return btrfs_search_prev_slot(trans, root, &key, p, 0, 1); } /* * If remove is 1, then we are removing free space, thus clearing bits in the * bitmap. If remove is 0, then we are adding free space, thus setting bits in * the bitmap. */ static int modify_free_space_bitmap(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size, bool remove) { struct btrfs_root *root = btrfs_free_space_root(block_group); struct btrfs_key key; u64 end = start + size; u64 cur_start, cur_size; bool prev_bit_set = false; bool next_bit_set = false; int new_extents; int ret; /* * Read the bit for the block immediately before the extent of space if * that block is within the block group. */ if (start > block_group->start) { u64 prev_block = start - block_group->fs_info->sectorsize; key.objectid = prev_block; key.type = (u8)-1; key.offset = (u64)-1; ret = btrfs_search_prev_slot(trans, root, &key, path, 0, 1); if (ret) return ret; prev_bit_set = btrfs_free_space_test_bit(block_group, path, prev_block); /* The previous block may have been in the previous bitmap. */ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (start >= key.objectid + key.offset) { ret = free_space_next_bitmap(trans, root, path); if (ret) return ret; } } else { key.objectid = start; key.type = (u8)-1; key.offset = (u64)-1; ret = btrfs_search_prev_slot(trans, root, &key, path, 0, 1); if (ret) return ret; } /* * Iterate over all of the bitmaps overlapped by the extent of space, * clearing/setting bits as required. */ cur_start = start; cur_size = size; while (1) { free_space_modify_bits(trans, block_group, path, &cur_start, &cur_size, !remove); if (cur_size == 0) break; ret = free_space_next_bitmap(trans, root, path); if (ret) return ret; } /* * Read the bit for the block immediately after the extent of space if * that block is within the block group. */ if (end < block_group->start + block_group->length) { /* The next block may be in the next bitmap. */ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (end >= key.objectid + key.offset) { ret = free_space_next_bitmap(trans, root, path); if (ret) return ret; } next_bit_set = btrfs_free_space_test_bit(block_group, path, end); } if (remove) { new_extents = -1; if (prev_bit_set) { /* Leftover on the left. */ new_extents++; } if (next_bit_set) { /* Leftover on the right. */ new_extents++; } } else { new_extents = 1; if (prev_bit_set) { /* Merging with neighbor on the left. */ new_extents--; } if (next_bit_set) { /* Merging with neighbor on the right. */ new_extents--; } } btrfs_release_path(path); return update_free_space_extent_count(trans, block_group, path, new_extents); } static int remove_free_space_extent(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size) { struct btrfs_root *root = btrfs_free_space_root(block_group); struct btrfs_key key; u64 found_start, found_end; u64 end = start + size; int new_extents = -1; int ret; key.objectid = start; key.type = (u8)-1; key.offset = (u64)-1; ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1); if (ret) return ret; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); ASSERT(key.type == BTRFS_FREE_SPACE_EXTENT_KEY); found_start = key.objectid; found_end = key.objectid + key.offset; ASSERT(start >= found_start && end <= found_end); /* * Okay, now that we've found the free space extent which contains the * free space that we are removing, there are four cases: * * 1. We're using the whole extent: delete the key we found and * decrement the free space extent count. * 2. We are using part of the extent starting at the beginning: delete * the key we found and insert a new key representing the leftover at * the end. There is no net change in the number of extents. * 3. We are using part of the extent ending at the end: delete the key * we found and insert a new key representing the leftover at the * beginning. There is no net change in the number of extents. * 4. We are using part of the extent in the middle: delete the key we * found and insert two new keys representing the leftovers on each * side. Where we used to have one extent, we now have two, so increment * the extent count. We may need to convert the block group to bitmaps * as a result. */ /* Delete the existing key (cases 1-4). */ ret = btrfs_del_item(trans, root, path); if (ret) return ret; /* Add a key for leftovers at the beginning (cases 3 and 4). */ if (start > found_start) { key.objectid = found_start; key.type = BTRFS_FREE_SPACE_EXTENT_KEY; key.offset = start - found_start; btrfs_release_path(path); ret = btrfs_insert_empty_item(trans, root, path, &key, 0); if (ret) return ret; new_extents++; } /* Add a key for leftovers at the end (cases 2 and 4). */ if (end < found_end) { key.objectid = end; key.type = BTRFS_FREE_SPACE_EXTENT_KEY; key.offset = found_end - end; btrfs_release_path(path); ret = btrfs_insert_empty_item(trans, root, path, &key, 0); if (ret) return ret; new_extents++; } btrfs_release_path(path); return update_free_space_extent_count(trans, block_group, path, new_extents); } static int using_bitmaps(struct btrfs_block_group *bg, struct btrfs_path *path) { struct btrfs_free_space_info *info; u32 flags; if (bg->using_free_space_bitmaps_cached) return bg->using_free_space_bitmaps; info = btrfs_search_free_space_info(NULL, bg, path, 0); if (IS_ERR(info)) return PTR_ERR(info); flags = btrfs_free_space_flags(path->nodes[0], info); btrfs_release_path(path); bg->using_free_space_bitmaps = (flags & BTRFS_FREE_SPACE_USING_BITMAPS); bg->using_free_space_bitmaps_cached = true; return bg->using_free_space_bitmaps; } EXPORT_FOR_TESTS int __btrfs_remove_from_free_space_tree(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size) { int ret; ret = __add_block_group_free_space(trans, block_group, path); if (ret) return ret; ret = using_bitmaps(block_group, path); if (ret < 0) return ret; if (ret) return modify_free_space_bitmap(trans, block_group, path, start, size, true); return remove_free_space_extent(trans, block_group, path, start, size); } int btrfs_remove_from_free_space_tree(struct btrfs_trans_handle *trans, u64 start, u64 size) { struct btrfs_block_group *block_group; BTRFS_PATH_AUTO_FREE(path); int ret; if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE)) return 0; path = btrfs_alloc_path(); if (unlikely(!path)) { ret = -ENOMEM; btrfs_abort_transaction(trans, ret); return ret; } block_group = btrfs_lookup_block_group(trans->fs_info, start); if (unlikely(!block_group)) { DEBUG_WARN("no block group found for start=%llu", start); ret = -ENOENT; btrfs_abort_transaction(trans, ret); return ret; } mutex_lock(&block_group->free_space_lock); ret = __btrfs_remove_from_free_space_tree(trans, block_group, path, start, size); mutex_unlock(&block_group->free_space_lock); if (ret) btrfs_abort_transaction(trans, ret); btrfs_put_block_group(block_group); return ret; } static int add_free_space_extent(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size) { struct btrfs_root *root = btrfs_free_space_root(block_group); struct btrfs_key key, new_key; u64 found_start, found_end; u64 end = start + size; int new_extents = 1; int ret; /* * We are adding a new extent of free space, but we need to merge * extents. There are four cases here: * * 1. The new extent does not have any immediate neighbors to merge * with: add the new key and increment the free space extent count. We * may need to convert the block group to bitmaps as a result. * 2. The new extent has an immediate neighbor before it: remove the * previous key and insert a new key combining both of them. There is no * net change in the number of extents. * 3. The new extent has an immediate neighbor after it: remove the next * key and insert a new key combining both of them. There is no net * change in the number of extents. * 4. The new extent has immediate neighbors on both sides: remove both * of the keys and insert a new key combining all of them. Where we used * to have two extents, we now have one, so decrement the extent count. */ new_key.objectid = start; new_key.type = BTRFS_FREE_SPACE_EXTENT_KEY; new_key.offset = size; /* Search for a neighbor on the left. */ if (start == block_group->start) goto right; key.objectid = start - 1; key.type = (u8)-1; key.offset = (u64)-1; ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1); if (ret) return ret; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type != BTRFS_FREE_SPACE_EXTENT_KEY) { ASSERT(key.type == BTRFS_FREE_SPACE_INFO_KEY); btrfs_release_path(path); goto right; } found_start = key.objectid; found_end = key.objectid + key.offset; ASSERT(found_start >= block_group->start && found_end > block_group->start); ASSERT(found_start < start && found_end <= start); /* * Delete the neighbor on the left and absorb it into the new key (cases * 2 and 4). */ if (found_end == start) { ret = btrfs_del_item(trans, root, path); if (ret) return ret; new_key.objectid = found_start; new_key.offset += key.offset; new_extents--; } btrfs_release_path(path); right: /* Search for a neighbor on the right. */ if (end == block_group->start + block_group->length) goto insert; key.objectid = end; key.type = (u8)-1; key.offset = (u64)-1; ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1); if (ret) return ret; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type != BTRFS_FREE_SPACE_EXTENT_KEY) { ASSERT(key.type == BTRFS_FREE_SPACE_INFO_KEY); btrfs_release_path(path); goto insert; } found_start = key.objectid; found_end = key.objectid + key.offset; ASSERT(found_start >= block_group->start && found_end > block_group->start); ASSERT((found_start < start && found_end <= start) || (found_start >= end && found_end > end)); /* * Delete the neighbor on the right and absorb it into the new key * (cases 3 and 4). */ if (found_start == end) { ret = btrfs_del_item(trans, root, path); if (ret) return ret; new_key.offset += key.offset; new_extents--; } btrfs_release_path(path); insert: /* Insert the new key (cases 1-4). */ ret = btrfs_insert_empty_item(trans, root, path, &new_key, 0); if (ret) return ret; btrfs_release_path(path); return update_free_space_extent_count(trans, block_group, path, new_extents); } EXPORT_FOR_TESTS int __btrfs_add_to_free_space_tree(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path, u64 start, u64 size) { int ret; ret = __add_block_group_free_space(trans, block_group, path); if (ret) return ret; ret = using_bitmaps(block_group, path); if (ret < 0) return ret; if (ret) return modify_free_space_bitmap(trans, block_group, path, start, size, false); return add_free_space_extent(trans, block_group, path, start, size); } int btrfs_add_to_free_space_tree(struct btrfs_trans_handle *trans, u64 start, u64 size) { struct btrfs_block_group *block_group; BTRFS_PATH_AUTO_FREE(path); int ret; if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE)) return 0; path = btrfs_alloc_path(); if (unlikely(!path)) { ret = -ENOMEM; btrfs_abort_transaction(trans, ret); return ret; } block_group = btrfs_lookup_block_group(trans->fs_info, start); if (unlikely(!block_group)) { DEBUG_WARN("no block group found for start=%llu", start); ret = -ENOENT; btrfs_abort_transaction(trans, ret); return ret; } mutex_lock(&block_group->free_space_lock); ret = __btrfs_add_to_free_space_tree(trans, block_group, path, start, size); mutex_unlock(&block_group->free_space_lock); if (ret) btrfs_abort_transaction(trans, ret); btrfs_put_block_group(block_group); return ret; } /* * Populate the free space tree by walking the extent tree. Operations on the * extent tree that happen as a result of writes to the free space tree will go * through the normal add/remove hooks. */ static int populate_free_space_tree(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group) { struct btrfs_root *extent_root; BTRFS_PATH_AUTO_FREE(path); BTRFS_PATH_AUTO_FREE(path2); struct btrfs_key key; u64 start, end; int ret; path = btrfs_alloc_path(); if (!path) return -ENOMEM; path2 = btrfs_alloc_path(); if (!path2) return -ENOMEM; path->reada = READA_FORWARD; ret = add_new_free_space_info(trans, block_group, path2); if (ret) return ret; mutex_lock(&block_group->free_space_lock); /* * Iterate through all of the extent and metadata items in this block * group, adding the free space between them and the free space at the * end. Note that EXTENT_ITEM and METADATA_ITEM are less than * BLOCK_GROUP_ITEM, so an extent may precede the block group that it's * contained in. */ key.objectid = block_group->start; key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = 0; extent_root = btrfs_extent_root(trans->fs_info, key.objectid); ret = btrfs_search_slot_for_read(extent_root, &key, path, 1, 0); if (ret < 0) goto out_locked; /* * If ret is 1 (no key found), it means this is an empty block group, * without any extents allocated from it and there's no block group * item (key BTRFS_BLOCK_GROUP_ITEM_KEY) located in the extent tree * because we are using the block group tree feature (so block group * items are stored in the block group tree) or this is a new block * group created in the current transaction and its block group item * was not yet inserted in the extent tree (that happens in * btrfs_create_pending_block_groups() -> insert_block_group_item()). * It also means there are no extents allocated for block groups with a * start offset beyond this block group's end offset (this is the last, * highest, block group). */ start = block_group->start; end = block_group->start + block_group->length; while (ret == 0) { btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type == BTRFS_EXTENT_ITEM_KEY || key.type == BTRFS_METADATA_ITEM_KEY) { if (key.objectid >= end) break; if (start < key.objectid) { ret = __btrfs_add_to_free_space_tree(trans, block_group, path2, start, key.objectid - start); if (ret) goto out_locked; } start = key.objectid; if (key.type == BTRFS_METADATA_ITEM_KEY) start += trans->fs_info->nodesize; else start += key.offset; } else if (key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) { if (key.objectid != block_group->start) break; } ret = btrfs_next_item(extent_root, path); if (ret < 0) goto out_locked; } if (start < end) { ret = __btrfs_add_to_free_space_tree(trans, block_group, path2, start, end - start); if (ret) goto out_locked; } ret = 0; out_locked: mutex_unlock(&block_group->free_space_lock); return ret; } int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info) { struct btrfs_trans_handle *trans; struct btrfs_root *tree_root = fs_info->tree_root; struct btrfs_root *free_space_root; struct btrfs_block_group *block_group; struct rb_node *node; int ret; trans = btrfs_start_transaction(tree_root, 0); if (IS_ERR(trans)) return PTR_ERR(trans); set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); free_space_root = btrfs_create_tree(trans, BTRFS_FREE_SPACE_TREE_OBJECTID); if (IS_ERR(free_space_root)) { ret = PTR_ERR(free_space_root); btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); goto out_clear; } ret = btrfs_global_root_insert(free_space_root); if (unlikely(ret)) { btrfs_put_root(free_space_root); btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); goto out_clear; } node = rb_first_cached(&fs_info->block_group_cache_tree); while (node) { block_group = rb_entry(node, struct btrfs_block_group, cache_node); ret = populate_free_space_tree(trans, block_group); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); goto out_clear; } node = rb_next(node); } btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE); btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); ret = btrfs_commit_transaction(trans); /* * Now that we've committed the transaction any reading of our commit * root will be safe, so we can cache from the free space tree now. */ clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); return ret; out_clear: clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); return ret; } static int clear_free_space_tree(struct btrfs_trans_handle *trans, struct btrfs_root *root) { BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; struct rb_node *node; int nr; int ret; path = btrfs_alloc_path(); if (!path) return -ENOMEM; key.objectid = 0; key.type = 0; key.offset = 0; while (1) { ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret < 0) return ret; nr = btrfs_header_nritems(path->nodes[0]); if (!nr) break; path->slots[0] = 0; ret = btrfs_del_items(trans, root, path, 0, nr); if (ret) return ret; btrfs_release_path(path); } node = rb_first_cached(&trans->fs_info->block_group_cache_tree); while (node) { struct btrfs_block_group *bg; bg = rb_entry(node, struct btrfs_block_group, cache_node); clear_bit(BLOCK_GROUP_FLAG_FREE_SPACE_ADDED, &bg->runtime_flags); node = rb_next(node); cond_resched(); } return 0; } int btrfs_delete_free_space_tree(struct btrfs_fs_info *fs_info) { struct btrfs_trans_handle *trans; struct btrfs_root *tree_root = fs_info->tree_root; struct btrfs_key key = { .objectid = BTRFS_FREE_SPACE_TREE_OBJECTID, .type = BTRFS_ROOT_ITEM_KEY, .offset = 0, }; struct btrfs_root *free_space_root = btrfs_global_root(fs_info, &key); int ret; trans = btrfs_start_transaction(tree_root, 0); if (IS_ERR(trans)) return PTR_ERR(trans); btrfs_clear_fs_compat_ro(fs_info, FREE_SPACE_TREE); btrfs_clear_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); ret = clear_free_space_tree(trans, free_space_root); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret; } ret = btrfs_del_root(trans, &free_space_root->root_key); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret; } btrfs_global_root_delete(free_space_root); spin_lock(&fs_info->trans_lock); list_del(&free_space_root->dirty_list); spin_unlock(&fs_info->trans_lock); btrfs_tree_lock(free_space_root->node); btrfs_clear_buffer_dirty(trans, free_space_root->node); btrfs_tree_unlock(free_space_root->node); ret = btrfs_free_tree_block(trans, btrfs_root_id(free_space_root), free_space_root->node, 0, 1); btrfs_put_root(free_space_root); if (unlikely(ret < 0)) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret; } return btrfs_commit_transaction(trans); } int btrfs_rebuild_free_space_tree(struct btrfs_fs_info *fs_info) { struct btrfs_trans_handle *trans; struct btrfs_key key = { .objectid = BTRFS_FREE_SPACE_TREE_OBJECTID, .type = BTRFS_ROOT_ITEM_KEY, .offset = 0, }; struct btrfs_root *free_space_root = btrfs_global_root(fs_info, &key); struct rb_node *node; int ret; trans = btrfs_start_transaction(free_space_root, 1); if (IS_ERR(trans)) return PTR_ERR(trans); set_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); set_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); ret = clear_free_space_tree(trans, free_space_root); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret; } node = rb_first_cached(&fs_info->block_group_cache_tree); while (node) { struct btrfs_block_group *block_group; block_group = rb_entry(node, struct btrfs_block_group, cache_node); if (test_bit(BLOCK_GROUP_FLAG_FREE_SPACE_ADDED, &block_group->runtime_flags)) goto next; ret = populate_free_space_tree(trans, block_group); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); return ret; } next: if (btrfs_should_end_transaction(trans)) { btrfs_end_transaction(trans); trans = btrfs_start_transaction(free_space_root, 1); if (IS_ERR(trans)) return PTR_ERR(trans); } node = rb_next(node); } btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE); btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID); clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags); ret = btrfs_commit_transaction(trans); clear_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags); return ret; } static int __add_block_group_free_space(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path) { bool own_path = false; int ret; if (!test_and_clear_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags)) return 0; /* * While rebuilding the free space tree we may allocate new metadata * block groups while modifying the free space tree. * * Because during the rebuild (at btrfs_rebuild_free_space_tree()) we * can use multiple transactions, every time btrfs_end_transaction() is * called at btrfs_rebuild_free_space_tree() we finish the creation of * new block groups by calling btrfs_create_pending_block_groups(), and * that in turn calls us, through add_block_group_free_space(), to add * a free space info item and a free space extent item for the block * group. * * Then later btrfs_rebuild_free_space_tree() may find such new block * groups and processes them with populate_free_space_tree(), which can * fail with EEXIST since there are already items for the block group in * the free space tree. Notice that we say "may find" because a new * block group may be added to the block groups rbtree in a node before * or after the block group currently being processed by the rebuild * process. So signal the rebuild process to skip such new block groups * if it finds them. */ set_bit(BLOCK_GROUP_FLAG_FREE_SPACE_ADDED, &block_group->runtime_flags); if (!path) { path = btrfs_alloc_path(); if (unlikely(!path)) { btrfs_abort_transaction(trans, -ENOMEM); return -ENOMEM; } own_path = true; } ret = add_new_free_space_info(trans, block_group, path); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); goto out; } ret = __btrfs_add_to_free_space_tree(trans, block_group, path, block_group->start, block_group->length); if (ret) btrfs_abort_transaction(trans, ret); out: if (own_path) btrfs_free_path(path); return ret; } int btrfs_add_block_group_free_space(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group) { int ret; if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE)) return 0; mutex_lock(&block_group->free_space_lock); ret = __add_block_group_free_space(trans, block_group, NULL); mutex_unlock(&block_group->free_space_lock); return ret; } int btrfs_remove_block_group_free_space(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group) { struct btrfs_root *root = btrfs_free_space_root(block_group); BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key, found_key; struct extent_buffer *leaf; u64 start, end; int done = 0, nr; int ret; if (!btrfs_fs_compat_ro(trans->fs_info, FREE_SPACE_TREE)) return 0; if (test_bit(BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, &block_group->runtime_flags)) { /* We never added this block group to the free space tree. */ return 0; } path = btrfs_alloc_path(); if (unlikely(!path)) { ret = -ENOMEM; btrfs_abort_transaction(trans, ret); return ret; } start = block_group->start; end = block_group->start + block_group->length; key.objectid = end - 1; key.type = (u8)-1; key.offset = (u64)-1; while (!done) { ret = btrfs_search_prev_slot(trans, root, &key, path, -1, 1); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); return ret; } leaf = path->nodes[0]; nr = 0; path->slots[0]++; while (path->slots[0] > 0) { btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0] - 1); if (found_key.type == BTRFS_FREE_SPACE_INFO_KEY) { ASSERT(found_key.objectid == block_group->start); ASSERT(found_key.offset == block_group->length); done = 1; nr++; path->slots[0]--; break; } else if (found_key.type == BTRFS_FREE_SPACE_EXTENT_KEY || found_key.type == BTRFS_FREE_SPACE_BITMAP_KEY) { ASSERT(found_key.objectid >= start); ASSERT(found_key.objectid < end); ASSERT(found_key.objectid + found_key.offset <= end); nr++; path->slots[0]--; } else { ASSERT(0); } } ret = btrfs_del_items(trans, root, path, path->slots[0], nr); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); return ret; } btrfs_release_path(path); } ret = 0; return ret; } static int load_free_space_bitmaps(struct btrfs_caching_control *caching_ctl, struct btrfs_path *path, u32 expected_extent_count) { struct btrfs_block_group *block_group; struct btrfs_fs_info *fs_info; struct btrfs_root *root; struct btrfs_key key; bool prev_bit_set = false; /* Initialize to silence GCC. */ u64 extent_start = 0; u64 end, offset; u64 total_found = 0; u32 extent_count = 0; int ret; block_group = caching_ctl->block_group; fs_info = block_group->fs_info; root = btrfs_free_space_root(block_group); end = block_group->start + block_group->length; while (1) { ret = btrfs_next_item(root, path); if (ret < 0) return ret; if (ret) break; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type == BTRFS_FREE_SPACE_INFO_KEY) break; ASSERT(key.type == BTRFS_FREE_SPACE_BITMAP_KEY); ASSERT(key.objectid < end && key.objectid + key.offset <= end); offset = key.objectid; while (offset < key.objectid + key.offset) { bool bit_set; bit_set = btrfs_free_space_test_bit(block_group, path, offset); if (!prev_bit_set && bit_set) { extent_start = offset; } else if (prev_bit_set && !bit_set) { u64 space_added; ret = btrfs_add_new_free_space(block_group, extent_start, offset, &space_added); if (ret) return ret; total_found += space_added; if (total_found > CACHING_CTL_WAKE_UP) { total_found = 0; wake_up(&caching_ctl->wait); } extent_count++; } prev_bit_set = bit_set; offset += fs_info->sectorsize; } } if (prev_bit_set) { ret = btrfs_add_new_free_space(block_group, extent_start, end, NULL); if (ret) return ret; extent_count++; } if (unlikely(extent_count != expected_extent_count)) { btrfs_err(fs_info, "incorrect extent count for %llu; counted %u, expected %u", block_group->start, extent_count, expected_extent_count); DEBUG_WARN(); return -EIO; } return 0; } static int load_free_space_extents(struct btrfs_caching_control *caching_ctl, struct btrfs_path *path, u32 expected_extent_count) { struct btrfs_block_group *block_group; struct btrfs_fs_info *fs_info; struct btrfs_root *root; struct btrfs_key key; u64 end; u64 total_found = 0; u32 extent_count = 0; int ret; block_group = caching_ctl->block_group; fs_info = block_group->fs_info; root = btrfs_free_space_root(block_group); end = block_group->start + block_group->length; while (1) { u64 space_added; ret = btrfs_next_item(root, path); if (ret < 0) return ret; if (ret) break; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.type == BTRFS_FREE_SPACE_INFO_KEY) break; ASSERT(key.type == BTRFS_FREE_SPACE_EXTENT_KEY); ASSERT(key.objectid < end && key.objectid + key.offset <= end); ret = btrfs_add_new_free_space(block_group, key.objectid, key.objectid + key.offset, &space_added); if (ret) return ret; total_found += space_added; if (total_found > CACHING_CTL_WAKE_UP) { total_found = 0; wake_up(&caching_ctl->wait); } extent_count++; } if (unlikely(extent_count != expected_extent_count)) { btrfs_err(fs_info, "incorrect extent count for %llu; counted %u, expected %u", block_group->start, extent_count, expected_extent_count); DEBUG_WARN(); return -EIO; } return 0; } int btrfs_load_free_space_tree(struct btrfs_caching_control *caching_ctl) { struct btrfs_block_group *block_group; struct btrfs_free_space_info *info; BTRFS_PATH_AUTO_FREE(path); u32 extent_count, flags; block_group = caching_ctl->block_group; path = btrfs_alloc_path(); if (!path) return -ENOMEM; /* * Just like caching_thread() doesn't want to deadlock on the extent * tree, we don't want to deadlock on the free space tree. */ path->skip_locking = true; path->search_commit_root = true; path->reada = READA_FORWARD; info = btrfs_search_free_space_info(NULL, block_group, path, 0); if (IS_ERR(info)) return PTR_ERR(info); extent_count = btrfs_free_space_extent_count(path->nodes[0], info); flags = btrfs_free_space_flags(path->nodes[0], info); /* * We left path pointing to the free space info item, so now * load_free_space_foo can just iterate through the free space tree from * there. */ if (flags & BTRFS_FREE_SPACE_USING_BITMAPS) return load_free_space_bitmaps(caching_ctl, path, extent_count); else return load_free_space_extents(caching_ctl, path, extent_count); } |
| 29 29 27 29 29 29 29 124 126 126 126 125 126 150 150 126 17 17 10 19 19 19 18 19 19 19 18 18 5 10 10 10 10 10 8 10 10 9 9 4 3 9 9 9 7 5 4 4 3 3 3 3 3 3 3 8 8 8 8 24 24 23 26 26 26 14 26 15 15 18 9 17 17 29 88 51 51 50 51 54 54 54 8 17 17 2 2 2 2 17 1 10 10 4 4 8 8 8 9 9 9 9 5 9 21 21 10 10 27 27 27 27 27 22 21 9 2 16 16 2 2 2 16 23 23 23 10 10 10 23 23 23 23 23 34 34 34 34 34 34 34 34 14 24 24 24 24 3 23 24 11 34 34 2 34 26 9 9 43 42 26 19 19 18 19 25 25 25 3 3 34 34 33 3 2 33 34 2 1 1 1 1 1 1 1 1 1 1 53 34 34 37 14 37 37 14 16 16 14 13 1 1 30 30 29 29 29 29 54 54 28 29 28 28 54 11 4 4 4 4 54 54 50 29 13 54 8 47 53 6 6 6 30 29 10 10 29 29 29 29 29 29 29 29 29 28 29 29 29 29 29 16 16 16 2 16 16 15 2 16 29 28 29 9 3 3 8 2 29 29 29 29 29 29 29 29 15 29 2 2 2 28 28 28 28 10 10 10 10 10 10 10 9 10 10 10 2 10 10 10 9 10 29 28 4 12 4 4 29 29 29 28 29 9 28 28 28 8 9 8 8 28 28 29 52 52 52 29 29 29 29 29 1 29 29 8 52 29 52 28 28 51 3 3 3 3 3 3 32 35 35 24 17 5 2 20 20 20 21 31 31 31 31 31 8 8 78 61 61 59 35 35 19 2 26 38 16 34 32 32 31 31 14 30 31 31 31 31 31 29 29 29 29 28 23 38 52 22 46 41 12 6 6 1 1 1 6 5 1 6 1 6 5 2 3 3 3 4 6 5 6 6 2 6 6 6 6 6 4 2 2 2 2 2 2 4 25 25 25 25 10 25 16 25 295 294 294 25 25 25 294 25 25 1 4 4 2 4 5 5 1 1 4 4 21 22 4 18 17 17 17 17 6 12 1 1 12 12 12 4 4 4 3 12 12 10 8 7 2 7 15 9 4 1 4 3 17 21 1 1 1 1 1 1 1 8 8 8 8 8 8 8 50 49 49 6 65 66 4 66 4 66 20 51 8 64 50 50 20 20 20 20 20 20 66 65 50 50 3 50 3 8 9 9 8 7 8 8 6 6 6 4 3 1 1 2 4 5 2 6 5 5 8 8 67 68 1 67 1 1 68 48 49 48 47 9 47 47 47 87 87 47 47 47 47 47 47 68 68 3 3 26 26 2 21 6 20 13 13 7 7 20 123 39 39 121 24 123 18 37 37 13 13 13 14 14 9 26 26 26 26 26 1 24 62 12 11 12 12 26 25 21 21 12 2 10 8 12 26 20 20 20 20 26 25 26 26 26 5 26 26 26 26 95 95 40 41 94 68 67 61 68 68 46 46 45 46 46 46 46 39 39 39 26 26 48 3 47 49 3 48 292 294 289 293 51 1 51 1 51 50 51 6 51 16 45 293 25 47 293 65 37 65 25 65 10 1 1 11 11 10 10 10 11 1 11 11 3 130 128 1 1 1 1 1 1 8 9 6 3 3 1 1 1 3 11 11 2 2 2 2 2 3 1 1 78 78 78 78 77 78 78 78 78 78 48 31 77 69 78 48 69 43 78 69 29 29 29 29 14 15 15 29 25 29 17 17 17 17 17 17 9 9 9 9 9 9 15 15 14 5 10 9 9 9 9 9 9 2 2 2 1 1 10 14 23 1 1 25 25 25 1 1 24 23 23 5 24 24 23 2 2 23 24 25 | 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 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 | // SPDX-License-Identifier: GPL-2.0 /* Multipath TCP * * Copyright (c) 2017 - 2019, Intel Corporation. */ #define pr_fmt(fmt) "MPTCP: " fmt #include <linux/kernel.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/sched/signal.h> #include <linux/atomic.h> #include <net/aligned_data.h> #include <net/rps.h> #include <net/sock.h> #include <net/inet_common.h> #include <net/inet_hashtables.h> #include <net/protocol.h> #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/transp_v6.h> #endif #include <net/mptcp.h> #include <net/hotdata.h> #include <net/xfrm.h> #include <asm/ioctls.h> #include "protocol.h" #include "mib.h" #define CREATE_TRACE_POINTS #include <trace/events/mptcp.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) struct mptcp6_sock { struct mptcp_sock msk; struct ipv6_pinfo np; }; #endif enum { MPTCP_CMSG_TS = BIT(0), MPTCP_CMSG_INQ = BIT(1), }; static struct percpu_counter mptcp_sockets_allocated ____cacheline_aligned_in_smp; static void __mptcp_destroy_sock(struct sock *sk); static void mptcp_check_send_data_fin(struct sock *sk); DEFINE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; static struct net_device *mptcp_napi_dev; /* Returns end sequence number of the receiver's advertised window */ static u64 mptcp_wnd_end(const struct mptcp_sock *msk) { return READ_ONCE(msk->wnd_end); } static const struct proto_ops *mptcp_fallback_tcp_ops(const struct sock *sk) { unsigned short family = READ_ONCE(sk->sk_family); #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (family == AF_INET6) return &inet6_stream_ops; #endif WARN_ON_ONCE(family != AF_INET); return &inet_stream_ops; } bool __mptcp_try_fallback(struct mptcp_sock *msk, int fb_mib) { struct net *net = sock_net((struct sock *)msk); if (__mptcp_check_fallback(msk)) return true; /* The caller possibly is not holding the msk socket lock, but * in the fallback case only the current subflow is touching * the OoO queue. */ if (!RB_EMPTY_ROOT(&msk->out_of_order_queue)) return false; spin_lock_bh(&msk->fallback_lock); if (!msk->allow_infinite_fallback) { spin_unlock_bh(&msk->fallback_lock); return false; } msk->allow_subflows = false; set_bit(MPTCP_FALLBACK_DONE, &msk->flags); __MPTCP_INC_STATS(net, fb_mib); spin_unlock_bh(&msk->fallback_lock); return true; } static int __mptcp_socket_create(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; struct socket *ssock; int err; err = mptcp_subflow_create_socket(sk, sk->sk_family, &ssock); if (err) return err; msk->scaling_ratio = tcp_sk(ssock->sk)->scaling_ratio; WRITE_ONCE(msk->first, ssock->sk); subflow = mptcp_subflow_ctx(ssock->sk); list_add(&subflow->node, &msk->conn_list); sock_hold(ssock->sk); subflow->request_mptcp = 1; subflow->subflow_id = msk->subflow_id++; /* This is the first subflow, always with id 0 */ WRITE_ONCE(subflow->local_id, 0); mptcp_sock_graft(msk->first, sk->sk_socket); iput(SOCK_INODE(ssock)); return 0; } /* If the MPC handshake is not started, returns the first subflow, * eventually allocating it. */ struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; int ret; if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) return ERR_PTR(-EINVAL); if (!msk->first) { ret = __mptcp_socket_create(msk); if (ret) return ERR_PTR(ret); } return msk->first; } static void mptcp_drop(struct sock *sk, struct sk_buff *skb) { sk_drops_skbadd(sk, skb); __kfree_skb(skb); } static bool __mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta) { int limit = READ_ONCE(sk->sk_rcvbuf); if (unlikely(MPTCP_SKB_CB(to)->cant_coalesce) || MPTCP_SKB_CB(from)->offset || ((to->len + from->len) > (limit >> 3)) || !skb_try_coalesce(to, from, fragstolen, delta)) return false; pr_debug("colesced seq %llx into %llx new len %d new end seq %llx\n", MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq, to->len, MPTCP_SKB_CB(from)->end_seq); MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq; return true; } static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, struct sk_buff *from) { bool fragstolen; int delta; if (!__mptcp_try_coalesce(sk, to, from, &fragstolen, &delta)) return false; /* note the fwd memory can reach a negative value after accounting * for the delta, but the later skb free will restore a non * negative one */ atomic_add(delta, &sk->sk_rmem_alloc); sk_mem_charge(sk, delta); kfree_skb_partial(from, fragstolen); return true; } static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to, struct sk_buff *from) { if (MPTCP_SKB_CB(from)->map_seq != MPTCP_SKB_CB(to)->end_seq) return false; return mptcp_try_coalesce((struct sock *)msk, to, from); } /* "inspired" by tcp_rcvbuf_grow(), main difference: * - mptcp does not maintain a msk-level window clamp * - returns true when the receive buffer is actually updated */ static bool mptcp_rcvbuf_grow(struct sock *sk, u32 newval) { struct mptcp_sock *msk = mptcp_sk(sk); const struct net *net = sock_net(sk); u32 rcvwin, rcvbuf, cap, oldval; u64 grow; oldval = msk->rcvq_space.space; msk->rcvq_space.space = newval; if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) || (sk->sk_userlocks & SOCK_RCVBUF_LOCK)) return false; /* DRS is always one RTT late. */ rcvwin = newval << 1; /* slow start: allow the sender to double its rate. */ grow = (u64)rcvwin * (newval - oldval); do_div(grow, oldval); rcvwin += grow << 1; if (!RB_EMPTY_ROOT(&msk->out_of_order_queue)) rcvwin += MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq - msk->ack_seq; cap = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]); rcvbuf = min_t(u32, mptcp_space_from_win(sk, rcvwin), cap); if (rcvbuf > sk->sk_rcvbuf) { WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); return true; } return false; } /* "inspired" by tcp_data_queue_ofo(), main differences: * - use mptcp seqs * - don't cope with sacks */ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb) { struct sock *sk = (struct sock *)msk; struct rb_node **p, *parent; u64 seq, end_seq, max_seq; struct sk_buff *skb1; seq = MPTCP_SKB_CB(skb)->map_seq; end_seq = MPTCP_SKB_CB(skb)->end_seq; max_seq = atomic64_read(&msk->rcv_wnd_sent); pr_debug("msk=%p seq=%llx limit=%llx empty=%d\n", msk, seq, max_seq, RB_EMPTY_ROOT(&msk->out_of_order_queue)); if (after64(end_seq, max_seq)) { /* out of window */ mptcp_drop(sk, skb); pr_debug("oow by %lld, rcv_wnd_sent %llu\n", (unsigned long long)end_seq - (unsigned long)max_seq, (unsigned long long)atomic64_read(&msk->rcv_wnd_sent)); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_NODSSWINDOW); return; } p = &msk->out_of_order_queue.rb_node; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUE); if (RB_EMPTY_ROOT(&msk->out_of_order_queue)) { rb_link_node(&skb->rbnode, NULL, p); rb_insert_color(&skb->rbnode, &msk->out_of_order_queue); msk->ooo_last_skb = skb; goto end; } /* with 2 subflows, adding at end of ooo queue is quite likely * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. */ if (mptcp_ooo_try_coalesce(msk, msk->ooo_last_skb, skb)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL); return; } /* Can avoid an rbtree lookup if we are adding skb after ooo_last_skb */ if (!before64(seq, MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL); parent = &msk->ooo_last_skb->rbnode; p = &parent->rb_right; goto insert; } /* Find place to insert this segment. Handle overlaps on the way. */ parent = NULL; while (*p) { parent = *p; skb1 = rb_to_skb(parent); if (before64(seq, MPTCP_SKB_CB(skb1)->map_seq)) { p = &parent->rb_left; continue; } if (before64(seq, MPTCP_SKB_CB(skb1)->end_seq)) { if (!after64(end_seq, MPTCP_SKB_CB(skb1)->end_seq)) { /* All the bits are present. Drop. */ mptcp_drop(sk, skb); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); return; } if (after64(seq, MPTCP_SKB_CB(skb1)->map_seq)) { /* partial overlap: * | skb | * | skb1 | * continue traversing */ } else { /* skb's seq == skb1's seq and skb covers skb1. * Replace skb1 with skb. */ rb_replace_node(&skb1->rbnode, &skb->rbnode, &msk->out_of_order_queue); mptcp_drop(sk, skb1); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); goto merge_right; } } else if (mptcp_ooo_try_coalesce(msk, skb1, skb)) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE); return; } p = &parent->rb_right; } insert: /* Insert segment into RB tree. */ rb_link_node(&skb->rbnode, parent, p); rb_insert_color(&skb->rbnode, &msk->out_of_order_queue); merge_right: /* Remove other segments covered by skb. */ while ((skb1 = skb_rb_next(skb)) != NULL) { if (before64(end_seq, MPTCP_SKB_CB(skb1)->end_seq)) break; rb_erase(&skb1->rbnode, &msk->out_of_order_queue); mptcp_drop(sk, skb1); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); } /* If there is no skb after us, we are the last_skb ! */ if (!skb1) msk->ooo_last_skb = skb; end: skb_condense(skb); skb_set_owner_r(skb, sk); /* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */ if (sk->sk_socket) mptcp_rcvbuf_grow(sk, msk->rcvq_space.space); } static void mptcp_init_skb(struct sock *ssk, struct sk_buff *skb, int offset, int copy_len) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); bool has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; /* the skb map_seq accounts for the skb offset: * mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq * value */ MPTCP_SKB_CB(skb)->map_seq = mptcp_subflow_get_mapped_dsn(subflow); MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + copy_len; MPTCP_SKB_CB(skb)->offset = offset; MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp; MPTCP_SKB_CB(skb)->cant_coalesce = 0; __skb_unlink(skb, &ssk->sk_receive_queue); skb_ext_reset(skb); skb_dst_drop(skb); } static bool __mptcp_move_skb(struct sock *sk, struct sk_buff *skb) { u64 copy_len = MPTCP_SKB_CB(skb)->end_seq - MPTCP_SKB_CB(skb)->map_seq; struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *tail; mptcp_borrow_fwdmem(sk, skb); if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) { /* in sequence */ msk->bytes_received += copy_len; WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len); tail = skb_peek_tail(&sk->sk_receive_queue); if (tail && mptcp_try_coalesce(sk, tail, skb)) return true; skb_set_owner_r(skb, sk); __skb_queue_tail(&sk->sk_receive_queue, skb); return true; } else if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) { mptcp_data_queue_ofo(msk, skb); return false; } /* old data, keep it simple and drop the whole pkt, sender * will retransmit as needed, if needed. */ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); mptcp_drop(sk, skb); return false; } static void mptcp_stop_rtx_timer(struct sock *sk) { sk_stop_timer(sk, &sk->mptcp_retransmit_timer); mptcp_sk(sk)->timer_ival = 0; } static void mptcp_close_wake_up(struct sock *sk) { if (sock_flag(sk, SOCK_DEAD)) return; sk->sk_state_change(sk); if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == TCP_CLOSE) sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP); else sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); } static void mptcp_shutdown_subflows(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow; slow = lock_sock_fast(ssk); tcp_shutdown(ssk, SEND_SHUTDOWN); unlock_sock_fast(ssk, slow); } } /* called under the msk socket lock */ static bool mptcp_pending_data_fin_ack(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); return ((1 << sk->sk_state) & (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) && msk->write_seq == READ_ONCE(msk->snd_una); } static void mptcp_check_data_fin_ack(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); /* Look for an acknowledged DATA_FIN */ if (mptcp_pending_data_fin_ack(sk)) { WRITE_ONCE(msk->snd_data_fin_enable, 0); switch (sk->sk_state) { case TCP_FIN_WAIT1: mptcp_set_state(sk, TCP_FIN_WAIT2); break; case TCP_CLOSING: case TCP_LAST_ACK: mptcp_shutdown_subflows(msk); mptcp_set_state(sk, TCP_CLOSE); break; } mptcp_close_wake_up(sk); } } /* can be called with no lock acquired */ static bool mptcp_pending_data_fin(struct sock *sk, u64 *seq) { struct mptcp_sock *msk = mptcp_sk(sk); if (READ_ONCE(msk->rcv_data_fin) && ((1 << inet_sk_state_load(sk)) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2))) { u64 rcv_data_fin_seq = READ_ONCE(msk->rcv_data_fin_seq); if (READ_ONCE(msk->ack_seq) == rcv_data_fin_seq) { if (seq) *seq = rcv_data_fin_seq; return true; } } return false; } static void mptcp_set_datafin_timeout(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); u32 retransmits; retransmits = min_t(u32, icsk->icsk_retransmits, ilog2(TCP_RTO_MAX / TCP_RTO_MIN)); mptcp_sk(sk)->timer_ival = TCP_RTO_MIN << retransmits; } static void __mptcp_set_timeout(struct sock *sk, long tout) { mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN; } static long mptcp_timeout_from_subflow(const struct mptcp_subflow_context *subflow) { const struct sock *ssk = mptcp_subflow_tcp_sock(subflow); return inet_csk(ssk)->icsk_pending && !subflow->stale_count ? tcp_timeout_expires(ssk) - jiffies : 0; } static void mptcp_set_timeout(struct sock *sk) { struct mptcp_subflow_context *subflow; long tout = 0; mptcp_for_each_subflow(mptcp_sk(sk), subflow) tout = max(tout, mptcp_timeout_from_subflow(subflow)); __mptcp_set_timeout(sk, tout); } static inline bool tcp_can_send_ack(const struct sock *ssk) { return !((1 << inet_sk_state_load(ssk)) & (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN)); } void __mptcp_subflow_send_ack(struct sock *ssk) { if (tcp_can_send_ack(ssk)) tcp_send_ack(ssk); } static void mptcp_subflow_send_ack(struct sock *ssk) { bool slow; slow = lock_sock_fast(ssk); __mptcp_subflow_send_ack(ssk); unlock_sock_fast(ssk, slow); } static void mptcp_send_ack(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; mptcp_for_each_subflow(msk, subflow) mptcp_subflow_send_ack(mptcp_subflow_tcp_sock(subflow)); } static void mptcp_subflow_cleanup_rbuf(struct sock *ssk, int copied) { bool slow; slow = lock_sock_fast(ssk); if (tcp_can_send_ack(ssk)) tcp_cleanup_rbuf(ssk, copied); unlock_sock_fast(ssk, slow); } static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty) { const struct inet_connection_sock *icsk = inet_csk(ssk); u8 ack_pending = READ_ONCE(icsk->icsk_ack.pending); const struct tcp_sock *tp = tcp_sk(ssk); return (ack_pending & ICSK_ACK_SCHED) && ((READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->rcv_wup) > READ_ONCE(icsk->icsk_ack.rcv_mss)) || (rx_empty && ack_pending & (ICSK_ACK_PUSHED2 | ICSK_ACK_PUSHED))); } static void mptcp_cleanup_rbuf(struct mptcp_sock *msk, int copied) { int old_space = READ_ONCE(msk->old_wspace); struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; int space = __mptcp_space(sk); bool cleanup, rx_empty; cleanup = (space > 0) && (space >= (old_space << 1)) && copied; rx_empty = !sk_rmem_alloc_get(sk) && copied; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (cleanup || mptcp_subflow_could_cleanup(ssk, rx_empty)) mptcp_subflow_cleanup_rbuf(ssk, copied); } } static void mptcp_check_data_fin(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); u64 rcv_data_fin_seq; /* Need to ack a DATA_FIN received from a peer while this side * of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2. * msk->rcv_data_fin was set when parsing the incoming options * at the subflow level and the msk lock was not held, so this * is the first opportunity to act on the DATA_FIN and change * the msk state. * * If we are caught up to the sequence number of the incoming * DATA_FIN, send the DATA_ACK now and do state transition. If * not caught up, do nothing and let the recv code send DATA_ACK * when catching up. */ if (mptcp_pending_data_fin(sk, &rcv_data_fin_seq)) { WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1); WRITE_ONCE(msk->rcv_data_fin, 0); WRITE_ONCE(sk->sk_shutdown, sk->sk_shutdown | RCV_SHUTDOWN); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ switch (sk->sk_state) { case TCP_ESTABLISHED: mptcp_set_state(sk, TCP_CLOSE_WAIT); break; case TCP_FIN_WAIT1: mptcp_set_state(sk, TCP_CLOSING); break; case TCP_FIN_WAIT2: mptcp_shutdown_subflows(msk); mptcp_set_state(sk, TCP_CLOSE); break; default: /* Other states not expected */ WARN_ON_ONCE(1); break; } if (!__mptcp_check_fallback(msk)) mptcp_send_ack(msk); mptcp_close_wake_up(sk); } } static void mptcp_dss_corruption(struct mptcp_sock *msk, struct sock *ssk) { if (!mptcp_try_fallback(ssk, MPTCP_MIB_DSSCORRUPTIONFALLBACK)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSCORRUPTIONRESET); mptcp_subflow_reset(ssk); } } static void __mptcp_add_backlog(struct sock *sk, struct mptcp_subflow_context *subflow, struct sk_buff *skb) { struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *tail = NULL; struct sock *ssk = skb->sk; bool fragstolen; int delta; if (unlikely(sk->sk_state == TCP_CLOSE)) { kfree_skb_reason(skb, SKB_DROP_REASON_SOCKET_CLOSE); return; } /* Try to coalesce with the last skb in our backlog */ if (!list_empty(&msk->backlog_list)) tail = list_last_entry(&msk->backlog_list, struct sk_buff, list); if (tail && MPTCP_SKB_CB(skb)->map_seq == MPTCP_SKB_CB(tail)->end_seq && ssk == tail->sk && __mptcp_try_coalesce(sk, tail, skb, &fragstolen, &delta)) { skb->truesize -= delta; kfree_skb_partial(skb, fragstolen); __mptcp_subflow_lend_fwdmem(subflow, delta); goto account; } list_add_tail(&skb->list, &msk->backlog_list); mptcp_subflow_lend_fwdmem(subflow, skb); delta = skb->truesize; account: WRITE_ONCE(msk->backlog_len, msk->backlog_len + delta); /* Possibly not accept()ed yet, keep track of memory not CG * accounted, mptcp_graft_subflows() will handle it. */ if (!mem_cgroup_from_sk(ssk)) msk->backlog_unaccounted += delta; } static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, struct sock *ssk, bool own_msk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = (struct sock *)msk; bool more_data_avail; struct tcp_sock *tp; bool ret = false; pr_debug("msk=%p ssk=%p\n", msk, ssk); tp = tcp_sk(ssk); do { u32 map_remaining, offset; u32 seq = tp->copied_seq; struct sk_buff *skb; bool fin; /* try to move as much data as available */ map_remaining = subflow->map_data_len - mptcp_subflow_get_map_offset(subflow); skb = skb_peek(&ssk->sk_receive_queue); if (unlikely(!skb)) break; if (__mptcp_check_fallback(msk)) { /* Under fallback skbs have no MPTCP extension and TCP could * collapse them between the dummy map creation and the * current dequeue. Be sure to adjust the map size. */ map_remaining = skb->len; subflow->map_data_len = skb->len; } offset = seq - TCP_SKB_CB(skb)->seq; fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; if (fin) seq++; if (offset < skb->len) { size_t len = skb->len - offset; mptcp_init_skb(ssk, skb, offset, len); if (own_msk && sk_rmem_alloc_get(sk) < sk->sk_rcvbuf) { mptcp_subflow_lend_fwdmem(subflow, skb); ret |= __mptcp_move_skb(sk, skb); } else { __mptcp_add_backlog(sk, subflow, skb); } seq += len; if (unlikely(map_remaining < len)) { DEBUG_NET_WARN_ON_ONCE(1); mptcp_dss_corruption(msk, ssk); } } else { if (unlikely(!fin)) { DEBUG_NET_WARN_ON_ONCE(1); mptcp_dss_corruption(msk, ssk); } sk_eat_skb(ssk, skb); } WRITE_ONCE(tp->copied_seq, seq); more_data_avail = mptcp_subflow_data_available(ssk); } while (more_data_avail); if (ret) msk->last_data_recv = tcp_jiffies32; return ret; } static bool __mptcp_ofo_queue(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; struct sk_buff *skb, *tail; bool moved = false; struct rb_node *p; u64 end_seq; p = rb_first(&msk->out_of_order_queue); pr_debug("msk=%p empty=%d\n", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue)); while (p) { skb = rb_to_skb(p); if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) break; p = rb_next(p); rb_erase(&skb->rbnode, &msk->out_of_order_queue); if (unlikely(!after64(MPTCP_SKB_CB(skb)->end_seq, msk->ack_seq))) { mptcp_drop(sk, skb); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); continue; } end_seq = MPTCP_SKB_CB(skb)->end_seq; tail = skb_peek_tail(&sk->sk_receive_queue); if (!tail || !mptcp_ooo_try_coalesce(msk, tail, skb)) { int delta = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq; /* skip overlapping data, if any */ pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d\n", MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq, delta); MPTCP_SKB_CB(skb)->offset += delta; MPTCP_SKB_CB(skb)->map_seq += delta; __skb_queue_tail(&sk->sk_receive_queue, skb); } msk->bytes_received += end_seq - msk->ack_seq; WRITE_ONCE(msk->ack_seq, end_seq); moved = true; } return moved; } static bool __mptcp_subflow_error_report(struct sock *sk, struct sock *ssk) { int err = sock_error(ssk); int ssk_state; if (!err) return false; /* only propagate errors on fallen-back sockets or * on MPC connect */ if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(mptcp_sk(sk))) return false; /* We need to propagate only transition to CLOSE state. * Orphaned socket will see such state change via * subflow_sched_work_if_closed() and that path will properly * destroy the msk as needed. */ ssk_state = inet_sk_state_load(ssk); if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) mptcp_set_state(sk, ssk_state); WRITE_ONCE(sk->sk_err, -err); /* This barrier is coupled with smp_rmb() in mptcp_poll() */ smp_wmb(); sk_error_report(sk); return true; } void __mptcp_error_report(struct sock *sk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); mptcp_for_each_subflow(msk, subflow) if (__mptcp_subflow_error_report(sk, mptcp_subflow_tcp_sock(subflow))) break; } /* In most cases we will be able to lock the mptcp socket. If its already * owned, we need to defer to the work queue to avoid ABBA deadlock. */ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; bool moved; moved = __mptcp_move_skbs_from_subflow(msk, ssk, true); __mptcp_ofo_queue(msk); if (unlikely(ssk->sk_err)) __mptcp_subflow_error_report(sk, ssk); /* If the moves have caught up with the DATA_FIN sequence number * it's time to ack the DATA_FIN and change socket state, but * this is not a good place to change state. Let the workqueue * do it. */ if (mptcp_pending_data_fin(sk, NULL)) mptcp_schedule_work(sk); return moved; } void mptcp_data_ready(struct sock *sk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(sk); /* The peer can send data while we are shutting down this * subflow at subflow destruction time, but we must avoid enqueuing * more data to the msk receive queue */ if (unlikely(subflow->closing)) return; mptcp_data_lock(sk); if (!sock_owned_by_user(sk)) { /* Wake-up the reader only for in-sequence data */ if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk)) sk->sk_data_ready(sk); } else { __mptcp_move_skbs_from_subflow(msk, ssk, false); } mptcp_data_unlock(sk); } static void mptcp_subflow_joined(struct mptcp_sock *msk, struct sock *ssk) { mptcp_subflow_ctx(ssk)->map_seq = READ_ONCE(msk->ack_seq); msk->allow_infinite_fallback = false; mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC); } static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; if (sk->sk_state != TCP_ESTABLISHED) return false; spin_lock_bh(&msk->fallback_lock); if (!msk->allow_subflows) { spin_unlock_bh(&msk->fallback_lock); return false; } mptcp_subflow_joined(msk, ssk); spin_unlock_bh(&msk->fallback_lock); mptcp_subflow_ctx(ssk)->subflow_id = msk->subflow_id++; mptcp_sockopt_sync_locked(msk, ssk); mptcp_stop_tout_timer(sk); __mptcp_propagate_sndbuf(sk, ssk); return true; } static void __mptcp_flush_join_list(struct sock *sk, struct list_head *join_list) { struct mptcp_subflow_context *tmp, *subflow; struct mptcp_sock *msk = mptcp_sk(sk); list_for_each_entry_safe(subflow, tmp, join_list, node) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast(ssk); list_move_tail(&subflow->node, &msk->conn_list); if (!__mptcp_finish_join(msk, ssk)) mptcp_subflow_reset(ssk); unlock_sock_fast(ssk, slow); } } static bool mptcp_rtx_timer_pending(struct sock *sk) { return timer_pending(&sk->mptcp_retransmit_timer); } static void mptcp_reset_rtx_timer(struct sock *sk) { unsigned long tout; /* prevent rescheduling on close */ if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE)) return; tout = mptcp_sk(sk)->timer_ival; sk_reset_timer(sk, &sk->mptcp_retransmit_timer, jiffies + tout); } bool mptcp_schedule_work(struct sock *sk) { if (inet_sk_state_load(sk) == TCP_CLOSE) return false; /* Get a reference on this socket, mptcp_worker() will release it. * As mptcp_worker() might complete before us, we can not avoid * a sock_hold()/sock_put() if schedule_work() returns false. */ sock_hold(sk); if (schedule_work(&mptcp_sk(sk)->work)) return true; sock_put(sk); return false; } static bool mptcp_skb_can_collapse_to(u64 write_seq, const struct sk_buff *skb, const struct mptcp_ext *mpext) { if (!tcp_skb_can_collapse_to(skb)) return false; /* can collapse only if MPTCP level sequence is in order and this * mapping has not been xmitted yet */ return mpext && mpext->data_seq + mpext->data_len == write_seq && !mpext->frozen; } /* we can append data to the given data frag if: * - there is space available in the backing page_frag * - the data frag tail matches the current page_frag free offset * - the data frag end sequence number matches the current write seq */ static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk, const struct page_frag *pfrag, const struct mptcp_data_frag *df) { return df && pfrag->page == df->page && pfrag->size - pfrag->offset > 0 && pfrag->offset == (df->offset + df->data_len) && df->data_seq + df->data_len == msk->write_seq; } static void dfrag_uncharge(struct sock *sk, int len) { sk_mem_uncharge(sk, len); sk_wmem_queued_add(sk, -len); } static void dfrag_clear(struct sock *sk, struct mptcp_data_frag *dfrag) { int len = dfrag->data_len + dfrag->overhead; list_del(&dfrag->list); dfrag_uncharge(sk, len); put_page(dfrag->page); } /* called under both the msk socket lock and the data lock */ static void __mptcp_clean_una(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_data_frag *dtmp, *dfrag; u64 snd_una; snd_una = msk->snd_una; list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) { if (after64(dfrag->data_seq + dfrag->data_len, snd_una)) break; if (unlikely(dfrag == msk->first_pending)) { /* in recovery mode can see ack after the current snd head */ if (WARN_ON_ONCE(!msk->recovery)) break; msk->first_pending = mptcp_send_next(sk); } dfrag_clear(sk, dfrag); } dfrag = mptcp_rtx_head(sk); if (dfrag && after64(snd_una, dfrag->data_seq)) { u64 delta = snd_una - dfrag->data_seq; /* prevent wrap around in recovery mode */ if (unlikely(delta > dfrag->already_sent)) { if (WARN_ON_ONCE(!msk->recovery)) goto out; if (WARN_ON_ONCE(delta > dfrag->data_len)) goto out; dfrag->already_sent += delta - dfrag->already_sent; } dfrag->data_seq += delta; dfrag->offset += delta; dfrag->data_len -= delta; dfrag->already_sent -= delta; dfrag_uncharge(sk, delta); } /* all retransmitted data acked, recovery completed */ if (unlikely(msk->recovery) && after64(msk->snd_una, msk->recovery_snd_nxt)) msk->recovery = false; out: if (snd_una == msk->snd_nxt && snd_una == msk->write_seq) { if (mptcp_rtx_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) mptcp_stop_rtx_timer(sk); } else { mptcp_reset_rtx_timer(sk); } if (mptcp_pending_data_fin_ack(sk)) mptcp_schedule_work(sk); } static void __mptcp_clean_una_wakeup(struct sock *sk) { lockdep_assert_held_once(&sk->sk_lock.slock); __mptcp_clean_una(sk); mptcp_write_space(sk); } static void mptcp_clean_una_wakeup(struct sock *sk) { mptcp_data_lock(sk); __mptcp_clean_una_wakeup(sk); mptcp_data_unlock(sk); } static void mptcp_enter_memory_pressure(struct sock *sk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); bool first = true; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (first && !ssk->sk_bypass_prot_mem) { tcp_enter_memory_pressure(ssk); first = false; } sk_stream_moderate_sndbuf(ssk); } __mptcp_sync_sndbuf(sk); } /* ensure we get enough memory for the frag hdr, beyond some minimal amount of * data */ static bool mptcp_page_frag_refill(struct sock *sk, struct page_frag *pfrag) { if (likely(skb_page_frag_refill(32U + sizeof(struct mptcp_data_frag), pfrag, sk->sk_allocation))) return true; mptcp_enter_memory_pressure(sk); return false; } static struct mptcp_data_frag * mptcp_carve_data_frag(const struct mptcp_sock *msk, struct page_frag *pfrag, int orig_offset) { int offset = ALIGN(orig_offset, sizeof(long)); struct mptcp_data_frag *dfrag; dfrag = (struct mptcp_data_frag *)(page_to_virt(pfrag->page) + offset); dfrag->data_len = 0; dfrag->data_seq = msk->write_seq; dfrag->overhead = offset - orig_offset + sizeof(struct mptcp_data_frag); dfrag->offset = offset + sizeof(struct mptcp_data_frag); dfrag->already_sent = 0; dfrag->page = pfrag->page; return dfrag; } struct mptcp_sendmsg_info { int mss_now; int size_goal; u16 limit; u16 sent; unsigned int flags; bool data_lock_held; }; static int mptcp_check_allowed_size(const struct mptcp_sock *msk, struct sock *ssk, u64 data_seq, int avail_size) { u64 window_end = mptcp_wnd_end(msk); u64 mptcp_snd_wnd; if (__mptcp_check_fallback(msk)) return avail_size; mptcp_snd_wnd = window_end - data_seq; avail_size = min_t(unsigned int, mptcp_snd_wnd, avail_size); if (unlikely(tcp_sk(ssk)->snd_wnd < mptcp_snd_wnd)) { tcp_sk(ssk)->snd_wnd = min_t(u64, U32_MAX, mptcp_snd_wnd); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_SNDWNDSHARED); } return avail_size; } static bool __mptcp_add_ext(struct sk_buff *skb, gfp_t gfp) { struct skb_ext *mpext = __skb_ext_alloc(gfp); if (!mpext) return false; __skb_ext_set(skb, SKB_EXT_MPTCP, mpext); return true; } static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp) { struct sk_buff *skb; skb = alloc_skb_fclone(MAX_TCP_HEADER, gfp); if (likely(skb)) { if (likely(__mptcp_add_ext(skb, gfp))) { skb_reserve(skb, MAX_TCP_HEADER); skb->ip_summed = CHECKSUM_PARTIAL; INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); return skb; } __kfree_skb(skb); } else { mptcp_enter_memory_pressure(sk); } return NULL; } static struct sk_buff *__mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp) { struct sk_buff *skb; skb = __mptcp_do_alloc_tx_skb(sk, gfp); if (!skb) return NULL; if (likely(sk_wmem_schedule(ssk, skb->truesize))) { tcp_skb_entail(ssk, skb); return skb; } tcp_skb_tsorted_anchor_cleanup(skb); kfree_skb(skb); return NULL; } static struct sk_buff *mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, bool data_lock_held) { gfp_t gfp = data_lock_held ? GFP_ATOMIC : sk->sk_allocation; return __mptcp_alloc_tx_skb(sk, ssk, gfp); } /* note: this always recompute the csum on the whole skb, even * if we just appended a single frag. More status info needed */ static void mptcp_update_data_checksum(struct sk_buff *skb, int added) { struct mptcp_ext *mpext = mptcp_get_ext(skb); __wsum csum = ~csum_unfold(mpext->csum); int offset = skb->len - added; mpext->csum = csum_fold(csum_block_add(csum, skb_checksum(skb, offset, added, 0), offset)); } static void mptcp_update_infinite_map(struct mptcp_sock *msk, struct sock *ssk, struct mptcp_ext *mpext) { if (!mpext) return; mpext->infinite_map = 1; mpext->data_len = 0; if (!mptcp_try_fallback(ssk, MPTCP_MIB_INFINITEMAPTX)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_FALLBACKFAILED); mptcp_subflow_reset(ssk); return; } mptcp_subflow_ctx(ssk)->send_infinite_map = 0; } #define MPTCP_MAX_GSO_SIZE (GSO_LEGACY_MAX_SIZE - (MAX_TCP_HEADER + 1)) static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, struct mptcp_data_frag *dfrag, struct mptcp_sendmsg_info *info) { u64 data_seq = dfrag->data_seq + info->sent; int offset = dfrag->offset + info->sent; struct mptcp_sock *msk = mptcp_sk(sk); bool zero_window_probe = false; struct mptcp_ext *mpext = NULL; bool can_coalesce = false; bool reuse_skb = true; struct sk_buff *skb; size_t copy; int i; pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u\n", msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent); if (WARN_ON_ONCE(info->sent > info->limit || info->limit > dfrag->data_len)) return 0; if (unlikely(!__tcp_can_send(ssk))) return -EAGAIN; /* compute send limit */ if (unlikely(ssk->sk_gso_max_size > MPTCP_MAX_GSO_SIZE)) ssk->sk_gso_max_size = MPTCP_MAX_GSO_SIZE; info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags); copy = info->size_goal; skb = tcp_write_queue_tail(ssk); if (skb && copy > skb->len) { /* Limit the write to the size available in the * current skb, if any, so that we create at most a new skb. * Explicitly tells TCP internals to avoid collapsing on later * queue management operation, to avoid breaking the ext <-> * SSN association set here */ mpext = mptcp_get_ext(skb); if (!mptcp_skb_can_collapse_to(data_seq, skb, mpext)) { TCP_SKB_CB(skb)->eor = 1; tcp_mark_push(tcp_sk(ssk), skb); goto alloc_skb; } i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, dfrag->page, offset); if (!can_coalesce && i >= READ_ONCE(net_hotdata.sysctl_max_skb_frags)) { tcp_mark_push(tcp_sk(ssk), skb); goto alloc_skb; } copy -= skb->len; } else { alloc_skb: skb = mptcp_alloc_tx_skb(sk, ssk, info->data_lock_held); if (!skb) return -ENOMEM; i = skb_shinfo(skb)->nr_frags; reuse_skb = false; mpext = mptcp_get_ext(skb); } /* Zero window and all data acked? Probe. */ copy = mptcp_check_allowed_size(msk, ssk, data_seq, copy); if (copy == 0) { u64 snd_una = READ_ONCE(msk->snd_una); /* No need for zero probe if there are any data pending * either at the msk or ssk level; skb is the current write * queue tail and can be empty at this point. */ if (snd_una != msk->snd_nxt || skb->len || skb != tcp_send_head(ssk)) { tcp_remove_empty_skb(ssk); return 0; } zero_window_probe = true; data_seq = snd_una - 1; copy = 1; } copy = min_t(size_t, copy, info->limit - info->sent); if (!sk_wmem_schedule(ssk, copy)) { tcp_remove_empty_skb(ssk); return -ENOMEM; } if (can_coalesce) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { get_page(dfrag->page); skb_fill_page_desc(skb, i, dfrag->page, offset, copy); } skb->len += copy; skb->data_len += copy; skb->truesize += copy; sk_wmem_queued_add(ssk, copy); sk_mem_charge(ssk, copy); WRITE_ONCE(tcp_sk(ssk)->write_seq, tcp_sk(ssk)->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); /* on skb reuse we just need to update the DSS len */ if (reuse_skb) { TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; mpext->data_len += copy; goto out; } memset(mpext, 0, sizeof(*mpext)); mpext->data_seq = data_seq; mpext->subflow_seq = mptcp_subflow_ctx(ssk)->rel_write_seq; mpext->data_len = copy; mpext->use_map = 1; mpext->dsn64 = 1; pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d\n", mpext->data_seq, mpext->subflow_seq, mpext->data_len, mpext->dsn64); if (zero_window_probe) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_WINPROBE); mptcp_subflow_ctx(ssk)->rel_write_seq += copy; mpext->frozen = 1; if (READ_ONCE(msk->csum_enabled)) mptcp_update_data_checksum(skb, copy); tcp_push_pending_frames(ssk); return 0; } out: if (READ_ONCE(msk->csum_enabled)) mptcp_update_data_checksum(skb, copy); if (mptcp_subflow_ctx(ssk)->send_infinite_map) mptcp_update_infinite_map(msk, ssk, mpext); trace_mptcp_sendmsg_frag(mpext); mptcp_subflow_ctx(ssk)->rel_write_seq += copy; return copy; } #define MPTCP_SEND_BURST_SIZE ((1 << 16) - \ sizeof(struct tcphdr) - \ MAX_TCP_OPTION_SPACE - \ sizeof(struct ipv6hdr) - \ sizeof(struct frag_hdr)) struct subflow_send_info { struct sock *ssk; u64 linger_time; }; void mptcp_subflow_set_active(struct mptcp_subflow_context *subflow) { if (!subflow->stale) return; subflow->stale = 0; MPTCP_INC_STATS(sock_net(mptcp_subflow_tcp_sock(subflow)), MPTCP_MIB_SUBFLOWRECOVER); } bool mptcp_subflow_active(struct mptcp_subflow_context *subflow) { if (unlikely(subflow->stale)) { u32 rcv_tstamp = READ_ONCE(tcp_sk(mptcp_subflow_tcp_sock(subflow))->rcv_tstamp); if (subflow->stale_rcv_tstamp == rcv_tstamp) return false; mptcp_subflow_set_active(subflow); } return __mptcp_subflow_active(subflow); } #define SSK_MODE_ACTIVE 0 #define SSK_MODE_BACKUP 1 #define SSK_MODE_MAX 2 /* implement the mptcp packet scheduler; * returns the subflow that will transmit the next DSS * additionally updates the rtx timeout */ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) { struct subflow_send_info send_info[SSK_MODE_MAX]; struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; u32 pace, burst, wmem; int i, nr_active = 0; struct sock *ssk; u64 linger_time; long tout = 0; /* pick the subflow with the lower wmem/wspace ratio */ for (i = 0; i < SSK_MODE_MAX; ++i) { send_info[i].ssk = NULL; send_info[i].linger_time = -1; } mptcp_for_each_subflow(msk, subflow) { bool backup = subflow->backup || subflow->request_bkup; trace_mptcp_subflow_get_send(subflow); ssk = mptcp_subflow_tcp_sock(subflow); if (!mptcp_subflow_active(subflow)) continue; tout = max(tout, mptcp_timeout_from_subflow(subflow)); nr_active += !backup; pace = subflow->avg_pacing_rate; if (unlikely(!pace)) { /* init pacing rate from socket */ subflow->avg_pacing_rate = READ_ONCE(ssk->sk_pacing_rate); pace = subflow->avg_pacing_rate; if (!pace) continue; } linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace); if (linger_time < send_info[backup].linger_time) { send_info[backup].ssk = ssk; send_info[backup].linger_time = linger_time; } } __mptcp_set_timeout(sk, tout); /* pick the best backup if no other subflow is active */ if (!nr_active) send_info[SSK_MODE_ACTIVE].ssk = send_info[SSK_MODE_BACKUP].ssk; /* According to the blest algorithm, to avoid HoL blocking for the * faster flow, we need to: * - estimate the faster flow linger time * - use the above to estimate the amount of byte transferred * by the faster flow * - check that the amount of queued data is greater than the above, * otherwise do not use the picked, slower, subflow * We select the subflow with the shorter estimated time to flush * the queued mem, which basically ensure the above. We just need * to check that subflow has a non empty cwin. */ ssk = send_info[SSK_MODE_ACTIVE].ssk; if (!ssk || !sk_stream_memory_free(ssk)) return NULL; burst = min_t(int, MPTCP_SEND_BURST_SIZE, mptcp_wnd_end(msk) - msk->snd_nxt); wmem = READ_ONCE(ssk->sk_wmem_queued); if (!burst) return ssk; subflow = mptcp_subflow_ctx(ssk); subflow->avg_pacing_rate = div_u64((u64)subflow->avg_pacing_rate * wmem + READ_ONCE(ssk->sk_pacing_rate) * burst, burst + wmem); msk->snd_burst = burst; return ssk; } static void mptcp_push_release(struct sock *ssk, struct mptcp_sendmsg_info *info) { tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle, info->size_goal); release_sock(ssk); } static void mptcp_update_post_push(struct mptcp_sock *msk, struct mptcp_data_frag *dfrag, u32 sent) { u64 snd_nxt_new = dfrag->data_seq; dfrag->already_sent += sent; msk->snd_burst -= sent; snd_nxt_new += dfrag->already_sent; /* snd_nxt_new can be smaller than snd_nxt in case mptcp * is recovering after a failover. In that event, this re-sends * old segments. * * Thus compute snd_nxt_new candidate based on * the dfrag->data_seq that was sent and the data * that has been handed to the subflow for transmission * and skip update in case it was old dfrag. */ if (likely(after64(snd_nxt_new, msk->snd_nxt))) { msk->bytes_sent += snd_nxt_new - msk->snd_nxt; WRITE_ONCE(msk->snd_nxt, snd_nxt_new); } } void mptcp_check_and_set_pending(struct sock *sk) { if (mptcp_send_head(sk)) { mptcp_data_lock(sk); mptcp_sk(sk)->cb_flags |= BIT(MPTCP_PUSH_PENDING); mptcp_data_unlock(sk); } } static int __subflow_push_pending(struct sock *sk, struct sock *ssk, struct mptcp_sendmsg_info *info) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_data_frag *dfrag; int len, copied = 0, err = 0; while ((dfrag = mptcp_send_head(sk))) { info->sent = dfrag->already_sent; info->limit = dfrag->data_len; len = dfrag->data_len - dfrag->already_sent; while (len > 0) { int ret = 0; ret = mptcp_sendmsg_frag(sk, ssk, dfrag, info); if (ret <= 0) { err = copied ? : ret; goto out; } info->sent += ret; copied += ret; len -= ret; mptcp_update_post_push(msk, dfrag, ret); } msk->first_pending = mptcp_send_next(sk); if (msk->snd_burst <= 0 || !sk_stream_memory_free(ssk) || !mptcp_subflow_active(mptcp_subflow_ctx(ssk))) { err = copied; goto out; } mptcp_set_timeout(sk); } err = copied; out: if (err > 0) msk->last_data_sent = tcp_jiffies32; return err; } void __mptcp_push_pending(struct sock *sk, unsigned int flags) { struct sock *prev_ssk = NULL, *ssk = NULL; struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_sendmsg_info info = { .flags = flags, }; bool copied = false; int push_count = 1; while (mptcp_send_head(sk) && (push_count > 0)) { struct mptcp_subflow_context *subflow; int ret = 0; if (mptcp_sched_get_send(msk)) break; push_count = 0; mptcp_for_each_subflow(msk, subflow) { if (READ_ONCE(subflow->scheduled)) { mptcp_subflow_set_scheduled(subflow, false); prev_ssk = ssk; ssk = mptcp_subflow_tcp_sock(subflow); if (ssk != prev_ssk) { /* First check. If the ssk has changed since * the last round, release prev_ssk */ if (prev_ssk) mptcp_push_release(prev_ssk, &info); /* Need to lock the new subflow only if different * from the previous one, otherwise we are still * helding the relevant lock */ lock_sock(ssk); } push_count++; ret = __subflow_push_pending(sk, ssk, &info); if (ret <= 0) { if (ret != -EAGAIN || (1 << ssk->sk_state) & (TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSE)) push_count--; continue; } copied = true; } } } /* at this point we held the socket lock for the last subflow we used */ if (ssk) mptcp_push_release(ssk, &info); /* Avoid scheduling the rtx timer if no data has been pushed; the timer * will be updated on positive acks by __mptcp_cleanup_una(). */ if (copied) { if (!mptcp_rtx_timer_pending(sk)) mptcp_reset_rtx_timer(sk); mptcp_check_send_data_fin(sk); } } static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk, bool first) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_sendmsg_info info = { .data_lock_held = true, }; bool keep_pushing = true; struct sock *xmit_ssk; int copied = 0; info.flags = 0; while (mptcp_send_head(sk) && keep_pushing) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); int ret = 0; /* check for a different subflow usage only after * spooling the first chunk of data */ if (first) { mptcp_subflow_set_scheduled(subflow, false); ret = __subflow_push_pending(sk, ssk, &info); first = false; if (ret <= 0) break; copied += ret; continue; } if (mptcp_sched_get_send(msk)) goto out; if (READ_ONCE(subflow->scheduled)) { mptcp_subflow_set_scheduled(subflow, false); ret = __subflow_push_pending(sk, ssk, &info); if (ret <= 0) keep_pushing = false; copied += ret; } mptcp_for_each_subflow(msk, subflow) { if (READ_ONCE(subflow->scheduled)) { xmit_ssk = mptcp_subflow_tcp_sock(subflow); if (xmit_ssk != ssk) { mptcp_subflow_delegate(subflow, MPTCP_DELEGATE_SEND); keep_pushing = false; } } } } out: /* __mptcp_alloc_tx_skb could have released some wmem and we are * not going to flush it via release_sock() */ if (copied) { tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); if (!mptcp_rtx_timer_pending(sk)) mptcp_reset_rtx_timer(sk); if (msk->snd_data_fin_enable && msk->snd_nxt + 1 == msk->write_seq) mptcp_schedule_work(sk); } } static int mptcp_disconnect(struct sock *sk, int flags); static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, size_t len, int *copied_syn) { unsigned int saved_flags = msg->msg_flags; struct mptcp_sock *msk = mptcp_sk(sk); struct sock *ssk; int ret; /* on flags based fastopen the mptcp is supposed to create the * first subflow right now. Otherwise we are in the defer_connect * path, and the first subflow must be already present. * Since the defer_connect flag is cleared after the first succsful * fastopen attempt, no need to check for additional subflow status. */ if (msg->msg_flags & MSG_FASTOPEN) { ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) return PTR_ERR(ssk); } if (!msk->first) return -EINVAL; ssk = msk->first; lock_sock(ssk); msg->msg_flags |= MSG_DONTWAIT; msk->fastopening = 1; ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL); msk->fastopening = 0; msg->msg_flags = saved_flags; release_sock(ssk); /* do the blocking bits of inet_stream_connect outside the ssk socket lock */ if (ret == -EINPROGRESS && !(msg->msg_flags & MSG_DONTWAIT)) { ret = __inet_stream_connect(sk->sk_socket, msg->msg_name, msg->msg_namelen, msg->msg_flags, 1); /* Keep the same behaviour of plain TCP: zero the copied bytes in * case of any error, except timeout or signal */ if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR) *copied_syn = 0; } else if (ret && ret != -EINPROGRESS) { /* The disconnect() op called by tcp_sendmsg_fastopen()/ * __inet_stream_connect() can fail, due to looking check, * see mptcp_disconnect(). * Attempt it again outside the problematic scope. */ if (!mptcp_disconnect(sk, 0)) { sk->sk_disconnects++; sk->sk_socket->state = SS_UNCONNECTED; } } inet_clear_bit(DEFER_CONNECT, sk); return ret; } static int do_copy_data_nocache(struct sock *sk, int copy, struct iov_iter *from, char *to) { if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) { if (!copy_from_iter_full_nocache(to, copy, from)) return -EFAULT; } else if (!copy_from_iter_full(to, copy, from)) { return -EFAULT; } return 0; } /* open-code sk_stream_memory_free() plus sent limit computation to * avoid indirect calls in fast-path. * Called under the msk socket lock, so we can avoid a bunch of ONCE * annotations. */ static u32 mptcp_send_limit(const struct sock *sk) { const struct mptcp_sock *msk = mptcp_sk(sk); u32 limit, not_sent; if (sk->sk_wmem_queued >= READ_ONCE(sk->sk_sndbuf)) return 0; limit = mptcp_notsent_lowat(sk); if (limit == UINT_MAX) return UINT_MAX; not_sent = msk->write_seq - msk->snd_nxt; if (not_sent >= limit) return 0; return limit - not_sent; } static void mptcp_rps_record_subflows(const struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; if (!rfs_is_needed()) return; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); sock_rps_record_flow(ssk); } } static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct mptcp_sock *msk = mptcp_sk(sk); struct page_frag *pfrag; size_t copied = 0; int ret = 0; long timeo; /* silently ignore everything else */ msg->msg_flags &= MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_FASTOPEN; lock_sock(sk); mptcp_rps_record_subflows(msk); if (unlikely(inet_test_bit(DEFER_CONNECT, sk) || msg->msg_flags & MSG_FASTOPEN)) { int copied_syn = 0; ret = mptcp_sendmsg_fastopen(sk, msg, len, &copied_syn); copied += copied_syn; if (ret == -EINPROGRESS && copied_syn > 0) goto out; else if (ret) goto do_error; } timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) { ret = sk_stream_wait_connect(sk, &timeo); if (ret) goto do_error; } ret = -EPIPE; if (unlikely(sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))) goto do_error; pfrag = sk_page_frag(sk); while (msg_data_left(msg)) { int total_ts, frag_truesize = 0; struct mptcp_data_frag *dfrag; bool dfrag_collapsed; size_t psize, offset; u32 copy_limit; /* ensure fitting the notsent_lowat() constraint */ copy_limit = mptcp_send_limit(sk); if (!copy_limit) goto wait_for_memory; /* reuse tail pfrag, if possible, or carve a new one from the * page allocator */ dfrag = mptcp_pending_tail(sk); dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag); if (!dfrag_collapsed) { if (!mptcp_page_frag_refill(sk, pfrag)) goto wait_for_memory; dfrag = mptcp_carve_data_frag(msk, pfrag, pfrag->offset); frag_truesize = dfrag->overhead; } /* we do not bound vs wspace, to allow a single packet. * memory accounting will prevent execessive memory usage * anyway */ offset = dfrag->offset + dfrag->data_len; psize = pfrag->size - offset; psize = min_t(size_t, psize, msg_data_left(msg)); psize = min_t(size_t, psize, copy_limit); total_ts = psize + frag_truesize; if (!sk_wmem_schedule(sk, total_ts)) goto wait_for_memory; ret = do_copy_data_nocache(sk, psize, &msg->msg_iter, page_address(dfrag->page) + offset); if (ret) goto do_error; /* data successfully copied into the write queue */ sk_forward_alloc_add(sk, -total_ts); copied += psize; dfrag->data_len += psize; frag_truesize += psize; pfrag->offset += frag_truesize; WRITE_ONCE(msk->write_seq, msk->write_seq + psize); /* charge data on mptcp pending queue to the msk socket * Note: we charge such data both to sk and ssk */ sk_wmem_queued_add(sk, frag_truesize); if (!dfrag_collapsed) { get_page(dfrag->page); list_add_tail(&dfrag->list, &msk->rtx_queue); if (!msk->first_pending) msk->first_pending = dfrag; } pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d\n", msk, dfrag->data_seq, dfrag->data_len, dfrag->already_sent, !dfrag_collapsed); continue; wait_for_memory: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); __mptcp_push_pending(sk, msg->msg_flags); ret = sk_stream_wait_memory(sk, &timeo); if (ret) goto do_error; } if (copied) __mptcp_push_pending(sk, msg->msg_flags); out: release_sock(sk); return copied; do_error: if (copied) goto out; copied = sk_stream_error(sk, msg->msg_flags, ret); goto out; } static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied); static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg, size_t len, int flags, int copied_total, struct scm_timestamping_internal *tss, int *cmsg_flags) { struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *skb, *tmp; int total_data_len = 0; int copied = 0; skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) { u32 delta, offset = MPTCP_SKB_CB(skb)->offset; u32 data_len = skb->len - offset; u32 count; int err; if (flags & MSG_PEEK) { /* skip already peeked skbs */ if (total_data_len + data_len <= copied_total) { total_data_len += data_len; continue; } /* skip the already peeked data in the current skb */ delta = copied_total - total_data_len; offset += delta; data_len -= delta; } count = min_t(size_t, len - copied, data_len); if (!(flags & MSG_TRUNC)) { err = skb_copy_datagram_msg(skb, offset, msg, count); if (unlikely(err < 0)) { if (!copied) return err; break; } } if (MPTCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); *cmsg_flags |= MPTCP_CMSG_TS; } copied += count; if (!(flags & MSG_PEEK)) { msk->bytes_consumed += count; if (count < data_len) { MPTCP_SKB_CB(skb)->offset += count; MPTCP_SKB_CB(skb)->map_seq += count; break; } /* avoid the indirect call, we know the destructor is sock_rfree */ skb->destructor = NULL; skb->sk = NULL; atomic_sub(skb->truesize, &sk->sk_rmem_alloc); sk_mem_uncharge(sk, skb->truesize); __skb_unlink(skb, &sk->sk_receive_queue); skb_attempt_defer_free(skb); } if (copied >= len) break; } mptcp_rcv_space_adjust(msk, copied); return copied; } /* receive buffer autotuning. See tcp_rcv_space_adjust for more information. * * Only difference: Use highest rtt estimate of the subflows in use. */ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) { struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; u8 scaling_ratio = U8_MAX; u32 time, advmss = 1; u64 rtt_us, mstamp; msk_owned_by_me(msk); if (copied <= 0) return; if (!msk->rcvspace_init) mptcp_rcv_space_init(msk, msk->first); msk->rcvq_space.copied += copied; mstamp = div_u64(tcp_clock_ns(), NSEC_PER_USEC); time = tcp_stamp_us_delta(mstamp, msk->rcvq_space.time); rtt_us = msk->rcvq_space.rtt_us; if (rtt_us && time < (rtt_us >> 3)) return; rtt_us = 0; mptcp_for_each_subflow(msk, subflow) { const struct tcp_sock *tp; u64 sf_rtt_us; u32 sf_advmss; tp = tcp_sk(mptcp_subflow_tcp_sock(subflow)); sf_rtt_us = READ_ONCE(tp->rcv_rtt_est.rtt_us); sf_advmss = READ_ONCE(tp->advmss); rtt_us = max(sf_rtt_us, rtt_us); advmss = max(sf_advmss, advmss); scaling_ratio = min(tp->scaling_ratio, scaling_ratio); } msk->rcvq_space.rtt_us = rtt_us; msk->scaling_ratio = scaling_ratio; if (time < (rtt_us >> 3) || rtt_us == 0) return; if (msk->rcvq_space.copied <= msk->rcvq_space.space) goto new_measure; if (mptcp_rcvbuf_grow(sk, msk->rcvq_space.copied)) { /* Make subflows follow along. If we do not do this, we * get drops at subflow level if skbs can't be moved to * the mptcp rx queue fast enough (announced rcv_win can * exceed ssk->sk_rcvbuf). */ mptcp_for_each_subflow(msk, subflow) { struct sock *ssk; bool slow; ssk = mptcp_subflow_tcp_sock(subflow); slow = lock_sock_fast(ssk); /* subflows can be added before tcp_init_transfer() */ if (tcp_sk(ssk)->rcvq_space.space) tcp_rcvbuf_grow(ssk, msk->rcvq_space.copied); unlock_sock_fast(ssk, slow); } } new_measure: msk->rcvq_space.copied = 0; msk->rcvq_space.time = mstamp; } static bool __mptcp_move_skbs(struct sock *sk, struct list_head *skbs, u32 *delta) { struct sk_buff *skb = list_first_entry(skbs, struct sk_buff, list); struct mptcp_sock *msk = mptcp_sk(sk); bool moved = false; *delta = 0; while (1) { /* If the msk recvbuf is full stop, don't drop */ if (sk_rmem_alloc_get(sk) > sk->sk_rcvbuf) break; prefetch(skb->next); list_del(&skb->list); *delta += skb->truesize; moved |= __mptcp_move_skb(sk, skb); if (list_empty(skbs)) break; skb = list_first_entry(skbs, struct sk_buff, list); } __mptcp_ofo_queue(msk); if (moved) mptcp_check_data_fin((struct sock *)msk); return moved; } static bool mptcp_can_spool_backlog(struct sock *sk, struct list_head *skbs) { struct mptcp_sock *msk = mptcp_sk(sk); /* After CG initialization, subflows should never add skb before * gaining the CG themself. */ DEBUG_NET_WARN_ON_ONCE(msk->backlog_unaccounted && sk->sk_socket && mem_cgroup_from_sk(sk)); /* Don't spool the backlog if the rcvbuf is full. */ if (list_empty(&msk->backlog_list) || sk_rmem_alloc_get(sk) > sk->sk_rcvbuf) return false; INIT_LIST_HEAD(skbs); list_splice_init(&msk->backlog_list, skbs); return true; } static void mptcp_backlog_spooled(struct sock *sk, u32 moved, struct list_head *skbs) { struct mptcp_sock *msk = mptcp_sk(sk); WRITE_ONCE(msk->backlog_len, msk->backlog_len - moved); list_splice(skbs, &msk->backlog_list); } static bool mptcp_move_skbs(struct sock *sk) { struct list_head skbs; bool enqueued = false; u32 moved; mptcp_data_lock(sk); while (mptcp_can_spool_backlog(sk, &skbs)) { mptcp_data_unlock(sk); enqueued |= __mptcp_move_skbs(sk, &skbs, &moved); mptcp_data_lock(sk); mptcp_backlog_spooled(sk, moved, &skbs); } mptcp_data_unlock(sk); return enqueued; } static unsigned int mptcp_inq_hint(const struct sock *sk) { const struct mptcp_sock *msk = mptcp_sk(sk); const struct sk_buff *skb; skb = skb_peek(&sk->sk_receive_queue); if (skb) { u64 hint_val = READ_ONCE(msk->ack_seq) - MPTCP_SKB_CB(skb)->map_seq; if (hint_val >= INT_MAX) return INT_MAX; return (unsigned int)hint_val; } if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN)) return 1; return 0; } static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct mptcp_sock *msk = mptcp_sk(sk); struct scm_timestamping_internal tss; int copied = 0, cmsg_flags = 0; int target; long timeo; /* MSG_ERRQUEUE is really a no-op till we support IP_RECVERR */ if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); lock_sock(sk); if (unlikely(sk->sk_state == TCP_LISTEN)) { copied = -ENOTCONN; goto out_err; } mptcp_rps_record_subflows(msk); timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); len = min_t(size_t, len, INT_MAX); target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); if (unlikely(msk->recvmsg_inq)) cmsg_flags = MPTCP_CMSG_INQ; while (copied < len) { int err, bytes_read; bytes_read = __mptcp_recvmsg_mskq(sk, msg, len - copied, flags, copied, &tss, &cmsg_flags); if (unlikely(bytes_read < 0)) { if (!copied) copied = bytes_read; goto out_err; } copied += bytes_read; if (!list_empty(&msk->backlog_list) && mptcp_move_skbs(sk)) continue; /* only the MPTCP socket status is relevant here. The exit * conditions mirror closely tcp_recvmsg() */ if (copied >= target) break; if (copied) { if (sk->sk_err || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || !timeo || signal_pending(current)) break; } else { if (sk->sk_err) { copied = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_state == TCP_CLOSE) { copied = -ENOTCONN; break; } if (!timeo) { copied = -EAGAIN; break; } if (signal_pending(current)) { copied = sock_intr_errno(timeo); break; } } pr_debug("block timeout %ld\n", timeo); mptcp_cleanup_rbuf(msk, copied); err = sk_wait_data(sk, &timeo, NULL); if (err < 0) { err = copied ? : err; goto out_err; } } mptcp_cleanup_rbuf(msk, copied); out_err: if (cmsg_flags && copied >= 0) { if (cmsg_flags & MPTCP_CMSG_TS) tcp_recv_timestamp(msg, sk, &tss); if (cmsg_flags & MPTCP_CMSG_INQ) { unsigned int inq = mptcp_inq_hint(sk); put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq); } } pr_debug("msk=%p rx queue empty=%d copied=%d\n", msk, skb_queue_empty(&sk->sk_receive_queue), copied); release_sock(sk); return copied; } static void mptcp_retransmit_timer(struct timer_list *t) { struct sock *sk = timer_container_of(sk, t, mptcp_retransmit_timer); struct mptcp_sock *msk = mptcp_sk(sk); bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { /* we need a process context to retransmit */ if (!test_and_set_bit(MPTCP_WORK_RTX, &msk->flags)) mptcp_schedule_work(sk); } else { /* delegate our work to tcp_release_cb() */ __set_bit(MPTCP_RETRANSMIT, &msk->cb_flags); } bh_unlock_sock(sk); sock_put(sk); } static void mptcp_tout_timer(struct timer_list *t) { struct inet_connection_sock *icsk = timer_container_of(icsk, t, mptcp_tout_timer); struct sock *sk = &icsk->icsk_inet.sk; mptcp_schedule_work(sk); sock_put(sk); } /* Find an idle subflow. Return NULL if there is unacked data at tcp * level. * * A backup subflow is returned only if that is the only kind available. */ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk) { struct sock *backup = NULL, *pick = NULL; struct mptcp_subflow_context *subflow; int min_stale_count = INT_MAX; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (!__mptcp_subflow_active(subflow)) continue; /* still data outstanding at TCP level? skip this */ if (!tcp_rtx_and_write_queues_empty(ssk)) { mptcp_pm_subflow_chk_stale(msk, ssk); min_stale_count = min_t(int, min_stale_count, subflow->stale_count); continue; } if (subflow->backup || subflow->request_bkup) { if (!backup) backup = ssk; continue; } if (!pick) pick = ssk; } if (pick) return pick; /* use backup only if there are no progresses anywhere */ return min_stale_count > 1 ? backup : NULL; } bool __mptcp_retransmit_pending_data(struct sock *sk) { struct mptcp_data_frag *cur, *rtx_head; struct mptcp_sock *msk = mptcp_sk(sk); if (__mptcp_check_fallback(msk)) return false; /* the closing socket has some data untransmitted and/or unacked: * some data in the mptcp rtx queue has not really xmitted yet. * keep it simple and re-inject the whole mptcp level rtx queue */ mptcp_data_lock(sk); __mptcp_clean_una_wakeup(sk); rtx_head = mptcp_rtx_head(sk); if (!rtx_head) { mptcp_data_unlock(sk); return false; } msk->recovery_snd_nxt = msk->snd_nxt; msk->recovery = true; mptcp_data_unlock(sk); msk->first_pending = rtx_head; msk->snd_burst = 0; /* be sure to clear the "sent status" on all re-injected fragments */ list_for_each_entry(cur, &msk->rtx_queue, list) { if (!cur->already_sent) break; cur->already_sent = 0; } return true; } /* flags for __mptcp_close_ssk() */ #define MPTCP_CF_PUSH BIT(1) /* be sure to send a reset only if the caller asked for it, also * clean completely the subflow status when the subflow reaches * TCP_CLOSE state */ static void __mptcp_subflow_disconnect(struct sock *ssk, struct mptcp_subflow_context *subflow, bool fastclosing) { if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || fastclosing) { /* The MPTCP code never wait on the subflow sockets, TCP-level * disconnect should never fail */ WARN_ON_ONCE(tcp_disconnect(ssk, 0)); mptcp_subflow_ctx_reset(subflow); } else { tcp_shutdown(ssk, SEND_SHUTDOWN); } } /* subflow sockets can be either outgoing (connect) or incoming * (accept). * * Outgoing subflows use in-kernel sockets. * Incoming subflows do not have their own 'struct socket' allocated, * so we need to use tcp_close() after detaching them from the mptcp * parent socket. */ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow, unsigned int flags) { struct mptcp_sock *msk = mptcp_sk(sk); bool dispose_it, need_push = false; int fwd_remaining; /* Do not pass RX data to the msk, even if the subflow socket is not * going to be freed (i.e. even for the first subflow on graceful * subflow close. */ lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); subflow->closing = 1; /* Borrow the fwd allocated page left-over; fwd memory for the subflow * could be negative at this point, but will be reach zero soon - when * the data allocated using such fragment will be freed. */ if (subflow->lent_mem_frag) { fwd_remaining = PAGE_SIZE - subflow->lent_mem_frag; sk_forward_alloc_add(sk, fwd_remaining); sk_forward_alloc_add(ssk, -fwd_remaining); subflow->lent_mem_frag = 0; } /* If the first subflow moved to a close state before accept, e.g. due * to an incoming reset or listener shutdown, the subflow socket is * already deleted by inet_child_forget() and the mptcp socket can't * survive too. */ if (msk->in_accept_queue && msk->first == ssk && (sock_flag(sk, SOCK_DEAD) || sock_flag(ssk, SOCK_DEAD))) { /* ensure later check in mptcp_worker() will dispose the msk */ sock_set_flag(sk, SOCK_DEAD); mptcp_set_close_tout(sk, tcp_jiffies32 - (mptcp_close_timeout(sk) + 1)); mptcp_subflow_drop_ctx(ssk); goto out_release; } dispose_it = msk->free_first || ssk != msk->first; if (dispose_it) list_del(&subflow->node); if (subflow->send_fastclose && ssk->sk_state != TCP_CLOSE) tcp_set_state(ssk, TCP_CLOSE); need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { __mptcp_subflow_disconnect(ssk, subflow, msk->fastclosing); release_sock(ssk); goto out; } subflow->disposable = 1; /* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops * the ssk has been already destroyed, we just need to release the * reference owned by msk; */ if (!inet_csk(ssk)->icsk_ulp_ops) { WARN_ON_ONCE(!sock_flag(ssk, SOCK_DEAD)); kfree_rcu(subflow, rcu); } else { /* otherwise tcp will dispose of the ssk and subflow ctx */ __tcp_close(ssk, 0); /* close acquired an extra ref */ __sock_put(ssk); } out_release: __mptcp_subflow_error_report(sk, ssk); release_sock(ssk); sock_put(ssk); if (ssk == msk->first) WRITE_ONCE(msk->first, NULL); out: __mptcp_sync_sndbuf(sk); if (need_push) __mptcp_push_pending(sk, 0); /* Catch every 'all subflows closed' scenario, including peers silently * closing them, e.g. due to timeout. * For established sockets, allow an additional timeout before closing, * as the protocol can still create more subflows. */ if (list_is_singular(&msk->conn_list) && msk->first && inet_sk_state_load(msk->first) == TCP_CLOSE) { if (sk->sk_state != TCP_ESTABLISHED || msk->in_accept_queue || sock_flag(sk, SOCK_DEAD)) { mptcp_set_state(sk, TCP_CLOSE); mptcp_close_wake_up(sk); } else { mptcp_start_tout_timer(sk); } } } void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow) { struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *skb; /* The first subflow can already be closed and still in the list */ if (subflow->close_event_done) return; subflow->close_event_done = true; if (sk->sk_state == TCP_ESTABLISHED) mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL); /* Remove any reference from the backlog to this ssk; backlog skbs consume * space in the msk receive queue, no need to touch sk->sk_rmem_alloc */ list_for_each_entry(skb, &msk->backlog_list, list) { if (skb->sk != ssk) continue; atomic_sub(skb->truesize, &skb->sk->sk_rmem_alloc); skb->sk = NULL; } /* subflow aborted before reaching the fully_established status * attempt the creation of the next subflow */ mptcp_pm_subflow_check_next(mptcp_sk(sk), subflow); __mptcp_close_ssk(sk, ssk, subflow, MPTCP_CF_PUSH); } static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu) { return 0; } static void __mptcp_close_subflow(struct sock *sk) { struct mptcp_subflow_context *subflow, *tmp; struct mptcp_sock *msk = mptcp_sk(sk); might_sleep(); mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); int ssk_state = inet_sk_state_load(ssk); if (ssk_state != TCP_CLOSE && (ssk_state != TCP_CLOSE_WAIT || inet_sk_state_load(sk) != TCP_ESTABLISHED || __mptcp_check_fallback(msk))) continue; /* 'subflow_data_ready' will re-sched once rx queue is empty */ if (!skb_queue_empty_lockless(&ssk->sk_receive_queue)) continue; mptcp_close_ssk(sk, ssk, subflow); } } static bool mptcp_close_tout_expired(const struct sock *sk) { if (!inet_csk(sk)->icsk_mtup.probe_timestamp || sk->sk_state == TCP_CLOSE) return false; return time_after32(tcp_jiffies32, inet_csk(sk)->icsk_mtup.probe_timestamp + mptcp_close_timeout(sk)); } static void mptcp_check_fastclose(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow, *tmp; struct sock *sk = (struct sock *)msk; if (likely(!READ_ONCE(msk->rcv_fastclose))) return; mptcp_token_destroy(msk); mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); bool slow; slow = lock_sock_fast(tcp_sk); if (tcp_sk->sk_state != TCP_CLOSE) { mptcp_send_active_reset_reason(tcp_sk); tcp_set_state(tcp_sk, TCP_CLOSE); } unlock_sock_fast(tcp_sk, slow); } /* Mirror the tcp_reset() error propagation */ switch (sk->sk_state) { case TCP_SYN_SENT: WRITE_ONCE(sk->sk_err, ECONNREFUSED); break; case TCP_CLOSE_WAIT: WRITE_ONCE(sk->sk_err, EPIPE); break; case TCP_CLOSE: return; default: WRITE_ONCE(sk->sk_err, ECONNRESET); } mptcp_set_state(sk, TCP_CLOSE); WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); smp_mb__before_atomic(); /* SHUTDOWN must be visible first */ set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags); /* the calling mptcp_worker will properly destroy the socket */ if (sock_flag(sk, SOCK_DEAD)) return; sk->sk_state_change(sk); sk_error_report(sk); } static void __mptcp_retrans(struct sock *sk) { struct mptcp_sendmsg_info info = { .data_lock_held = true, }; struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_subflow_context *subflow; struct mptcp_data_frag *dfrag; struct sock *ssk; int ret, err; u16 len = 0; mptcp_clean_una_wakeup(sk); /* first check ssk: need to kick "stale" logic */ err = mptcp_sched_get_retrans(msk); dfrag = mptcp_rtx_head(sk); if (!dfrag) { if (mptcp_data_fin_enabled(msk)) { struct inet_connection_sock *icsk = inet_csk(sk); WRITE_ONCE(icsk->icsk_retransmits, icsk->icsk_retransmits + 1); mptcp_set_datafin_timeout(sk); mptcp_send_ack(msk); goto reset_timer; } if (!mptcp_send_head(sk)) goto clear_scheduled; goto reset_timer; } if (err) goto reset_timer; mptcp_for_each_subflow(msk, subflow) { if (READ_ONCE(subflow->scheduled)) { u16 copied = 0; mptcp_subflow_set_scheduled(subflow, false); ssk = mptcp_subflow_tcp_sock(subflow); lock_sock(ssk); /* limit retransmission to the bytes already sent on some subflows */ info.sent = 0; info.limit = READ_ONCE(msk->csum_enabled) ? dfrag->data_len : dfrag->already_sent; /* * make the whole retrans decision, xmit, disallow * fallback atomic, note that we can't retrans even * when an infinite fallback is in progress, i.e. new * subflows are disallowed. */ spin_lock_bh(&msk->fallback_lock); if (__mptcp_check_fallback(msk) || !msk->allow_subflows) { spin_unlock_bh(&msk->fallback_lock); release_sock(ssk); goto clear_scheduled; } while (info.sent < info.limit) { ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info); if (ret <= 0) break; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS); copied += ret; info.sent += ret; } if (copied) { len = max(copied, len); tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); msk->allow_infinite_fallback = false; } spin_unlock_bh(&msk->fallback_lock); release_sock(ssk); } } msk->bytes_retrans += len; dfrag->already_sent = max(dfrag->already_sent, len); reset_timer: mptcp_check_and_set_pending(sk); if (!mptcp_rtx_timer_pending(sk)) mptcp_reset_rtx_timer(sk); clear_scheduled: /* If no rtx data was available or in case of fallback, there * could be left-over scheduled subflows; clear them all * or later xmit could use bad ones */ mptcp_for_each_subflow(msk, subflow) if (READ_ONCE(subflow->scheduled)) mptcp_subflow_set_scheduled(subflow, false); } /* schedule the timeout timer for the relevant event: either close timeout * or mp_fail timeout. The close timeout takes precedence on the mp_fail one */ void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout) { struct sock *sk = (struct sock *)msk; unsigned long timeout, close_timeout; if (!fail_tout && !inet_csk(sk)->icsk_mtup.probe_timestamp) return; close_timeout = (unsigned long)inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + mptcp_close_timeout(sk); /* the close timeout takes precedence on the fail one, and here at least one of * them is active */ timeout = inet_csk(sk)->icsk_mtup.probe_timestamp ? close_timeout : fail_tout; sk_reset_timer(sk, &inet_csk(sk)->mptcp_tout_timer, timeout); } static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) { struct sock *ssk = msk->first; bool slow; if (!ssk) return; pr_debug("MP_FAIL doesn't respond, reset the subflow\n"); slow = lock_sock_fast(ssk); mptcp_subflow_reset(ssk); WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0); unlock_sock_fast(ssk, slow); } static void mptcp_backlog_purge(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *tmp, *skb; LIST_HEAD(backlog); mptcp_data_lock(sk); list_splice_init(&msk->backlog_list, &backlog); msk->backlog_len = 0; mptcp_data_unlock(sk); list_for_each_entry_safe(skb, tmp, &backlog, list) { mptcp_borrow_fwdmem(sk, skb); kfree_skb_reason(skb, SKB_DROP_REASON_SOCKET_CLOSE); } sk_mem_reclaim(sk); } static void mptcp_do_fastclose(struct sock *sk) { struct mptcp_subflow_context *subflow, *tmp; struct mptcp_sock *msk = mptcp_sk(sk); mptcp_set_state(sk, TCP_CLOSE); mptcp_backlog_purge(sk); msk->fastclosing = 1; /* Explicitly send the fastclose reset as need */ if (__mptcp_check_fallback(msk)) return; mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); lock_sock(ssk); /* Some subflow socket states don't allow/need a reset.*/ if ((1 << ssk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) goto unlock; subflow->send_fastclose = 1; /* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0 * issue in __tcp_select_window(), see tcp_disconnect(). */ inet_csk(ssk)->icsk_ack.rcv_mss = TCP_MIN_MSS; tcp_send_active_reset(ssk, ssk->sk_allocation, SK_RST_REASON_TCP_ABORT_ON_CLOSE); unlock: release_sock(ssk); } } static void mptcp_worker(struct work_struct *work) { struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work); struct sock *sk = (struct sock *)msk; unsigned long fail_tout; int state; lock_sock(sk); state = sk->sk_state; if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN))) goto unlock; mptcp_check_fastclose(msk); mptcp_pm_worker(msk); mptcp_check_send_data_fin(sk); mptcp_check_data_fin_ack(sk); mptcp_check_data_fin(sk); if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) __mptcp_close_subflow(sk); if (mptcp_close_tout_expired(sk)) { struct mptcp_subflow_context *subflow, *tmp; mptcp_do_fastclose(sk); mptcp_for_each_subflow_safe(msk, subflow, tmp) __mptcp_close_ssk(sk, subflow->tcp_sock, subflow, 0); mptcp_close_wake_up(sk); } if (sock_flag(sk, SOCK_DEAD) && sk->sk_state == TCP_CLOSE) { __mptcp_destroy_sock(sk); goto unlock; } if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) __mptcp_retrans(sk); fail_tout = msk->first ? READ_ONCE(mptcp_subflow_ctx(msk->first)->fail_tout) : 0; if (fail_tout && time_after(jiffies, fail_tout)) mptcp_mp_fail_no_response(msk); unlock: release_sock(sk); sock_put(sk); } static void __mptcp_init_sock(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); INIT_LIST_HEAD(&msk->conn_list); INIT_LIST_HEAD(&msk->join_list); INIT_LIST_HEAD(&msk->rtx_queue); INIT_LIST_HEAD(&msk->backlog_list); INIT_WORK(&msk->work, mptcp_worker); msk->out_of_order_queue = RB_ROOT; msk->first_pending = NULL; msk->timer_ival = TCP_RTO_MIN; msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO; msk->backlog_len = 0; WRITE_ONCE(msk->first, NULL); inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); msk->allow_infinite_fallback = true; msk->allow_subflows = true; msk->recovery = false; msk->subflow_id = 1; msk->last_data_sent = tcp_jiffies32; msk->last_data_recv = tcp_jiffies32; msk->last_ack_recv = tcp_jiffies32; mptcp_pm_data_init(msk); spin_lock_init(&msk->fallback_lock); /* re-use the csk retrans timer for MPTCP-level retrans */ timer_setup(&sk->mptcp_retransmit_timer, mptcp_retransmit_timer, 0); timer_setup(&msk->sk.mptcp_tout_timer, mptcp_tout_timer, 0); } static void mptcp_ca_reset(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_assign_congestion_control(sk); strscpy(mptcp_sk(sk)->ca_name, icsk->icsk_ca_ops->name, sizeof(mptcp_sk(sk)->ca_name)); /* no need to keep a reference to the ops, the name will suffice */ tcp_cleanup_congestion_control(sk); icsk->icsk_ca_ops = NULL; } static int mptcp_init_sock(struct sock *sk) { struct net *net = sock_net(sk); int ret; __mptcp_init_sock(sk); if (!mptcp_is_enabled(net)) return -ENOPROTOOPT; if (unlikely(!net->mib.mptcp_statistics) && !mptcp_mib_alloc(net)) return -ENOMEM; rcu_read_lock(); ret = mptcp_init_sched(mptcp_sk(sk), mptcp_sched_find(mptcp_get_scheduler(net))); rcu_read_unlock(); if (ret) return ret; set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags); /* fetch the ca name; do it outside __mptcp_init_sock(), so that clone will * propagate the correct value */ mptcp_ca_reset(sk); sk_sockets_allocated_inc(sk); sk->sk_rcvbuf = READ_ONCE(net->ipv4.sysctl_tcp_rmem[1]); sk->sk_sndbuf = READ_ONCE(net->ipv4.sysctl_tcp_wmem[1]); return 0; } static void __mptcp_clear_xmit(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_data_frag *dtmp, *dfrag; msk->first_pending = NULL; list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) dfrag_clear(sk, dfrag); } void mptcp_cancel_work(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); if (cancel_work_sync(&msk->work)) __sock_put(sk); } void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how) { lock_sock(ssk); switch (ssk->sk_state) { case TCP_LISTEN: if (!(how & RCV_SHUTDOWN)) break; fallthrough; case TCP_SYN_SENT: WARN_ON_ONCE(tcp_disconnect(ssk, O_NONBLOCK)); break; default: if (__mptcp_check_fallback(mptcp_sk(sk))) { pr_debug("Fallback\n"); ssk->sk_shutdown |= how; tcp_shutdown(ssk, how); /* simulate the data_fin ack reception to let the state * machine move forward */ WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt); mptcp_schedule_work(sk); } else { pr_debug("Sending DATA_FIN on subflow %p\n", ssk); tcp_send_ack(ssk); if (!mptcp_rtx_timer_pending(sk)) mptcp_reset_rtx_timer(sk); } break; } release_sock(ssk); } void mptcp_set_state(struct sock *sk, int state) { int oldstate = sk->sk_state; switch (state) { case TCP_ESTABLISHED: if (oldstate != TCP_ESTABLISHED) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB); break; case TCP_CLOSE_WAIT: /* Unlike TCP, MPTCP sk would not have the TCP_SYN_RECV state: * MPTCP "accepted" sockets will be created later on. So no * transition from TCP_SYN_RECV to TCP_CLOSE_WAIT. */ break; default: if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT) MPTCP_DEC_STATS(sock_net(sk), MPTCP_MIB_CURRESTAB); } inet_sk_state_store(sk, state); } static const unsigned char new_state[16] = { /* current state: new state: action: */ [0 /* (Invalid) */] = TCP_CLOSE, [TCP_ESTABLISHED] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, [TCP_SYN_SENT] = TCP_CLOSE, [TCP_SYN_RECV] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, [TCP_FIN_WAIT1] = TCP_FIN_WAIT1, [TCP_FIN_WAIT2] = TCP_FIN_WAIT2, [TCP_TIME_WAIT] = TCP_CLOSE, /* should not happen ! */ [TCP_CLOSE] = TCP_CLOSE, [TCP_CLOSE_WAIT] = TCP_LAST_ACK | TCP_ACTION_FIN, [TCP_LAST_ACK] = TCP_LAST_ACK, [TCP_LISTEN] = TCP_CLOSE, [TCP_CLOSING] = TCP_CLOSING, [TCP_NEW_SYN_RECV] = TCP_CLOSE, /* should not happen ! */ }; static int mptcp_close_state(struct sock *sk) { int next = (int)new_state[sk->sk_state]; int ns = next & TCP_STATE_MASK; mptcp_set_state(sk, ns); return next & TCP_ACTION_FIN; } static void mptcp_check_send_data_fin(struct sock *sk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu\n", msk, msk->snd_data_fin_enable, !!mptcp_send_head(sk), msk->snd_nxt, msk->write_seq); /* we still need to enqueue subflows or not really shutting down, * skip this */ if (!msk->snd_data_fin_enable || msk->snd_nxt + 1 != msk->write_seq || mptcp_send_head(sk)) return; WRITE_ONCE(msk->snd_nxt, msk->write_seq); mptcp_for_each_subflow(msk, subflow) { struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow); mptcp_subflow_shutdown(sk, tcp_sk, SEND_SHUTDOWN); } } static void __mptcp_wr_shutdown(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d\n", msk, msk->snd_data_fin_enable, sk->sk_shutdown, sk->sk_state, !!mptcp_send_head(sk)); /* will be ignored by fallback sockets */ WRITE_ONCE(msk->write_seq, msk->write_seq + 1); WRITE_ONCE(msk->snd_data_fin_enable, 1); mptcp_check_send_data_fin(sk); } static void __mptcp_destroy_sock(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); pr_debug("msk=%p\n", msk); might_sleep(); mptcp_stop_rtx_timer(sk); sk_stop_timer(sk, &inet_csk(sk)->mptcp_tout_timer); msk->pm.status = 0; mptcp_release_sched(msk); sk->sk_prot->destroy(sk); sk_stream_kill_queues(sk); xfrm_sk_free_policy(sk); sock_put(sk); } void __mptcp_unaccepted_force_close(struct sock *sk) { sock_set_flag(sk, SOCK_DEAD); mptcp_do_fastclose(sk); __mptcp_destroy_sock(sk); } static __poll_t mptcp_check_readable(struct sock *sk) { return mptcp_epollin_ready(sk) ? EPOLLIN | EPOLLRDNORM : 0; } static void mptcp_check_listen_stop(struct sock *sk) { struct sock *ssk; if (inet_sk_state_load(sk) != TCP_LISTEN) return; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); ssk = mptcp_sk(sk)->first; if (WARN_ON_ONCE(!ssk || inet_sk_state_load(ssk) != TCP_LISTEN)) return; lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); tcp_set_state(ssk, TCP_CLOSE); mptcp_subflow_queue_clean(sk, ssk); inet_csk_listen_stop(ssk); mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); release_sock(ssk); } bool __mptcp_close(struct sock *sk, long timeout) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); bool do_cancel_work = false; int subflows_alive = 0; WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) { mptcp_check_listen_stop(sk); mptcp_set_state(sk, TCP_CLOSE); goto cleanup; } if (mptcp_data_avail(msk) || timeout < 0) { /* If the msk has read data, or the caller explicitly ask it, * do the MPTCP equivalent of TCP reset, aka MPTCP fastclose */ mptcp_do_fastclose(sk); timeout = 0; } else if (mptcp_close_state(sk)) { __mptcp_wr_shutdown(sk); } sk_stream_wait_close(sk, timeout); cleanup: /* orphan all the subflows */ mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast_nested(ssk); subflows_alive += ssk->sk_state != TCP_CLOSE; /* since the close timeout takes precedence on the fail one, * cancel the latter */ if (ssk == msk->first) subflow->fail_tout = 0; /* detach from the parent socket, but allow data_ready to * push incoming data into the mptcp stack, to properly ack it */ ssk->sk_socket = NULL; ssk->sk_wq = NULL; unlock_sock_fast(ssk, slow); } sock_orphan(sk); /* all the subflows are closed, only timeout can change the msk * state, let's not keep resources busy for no reasons */ if (subflows_alive == 0) mptcp_set_state(sk, TCP_CLOSE); sock_hold(sk); pr_debug("msk=%p state=%d\n", sk, sk->sk_state); mptcp_pm_connection_closed(msk); if (sk->sk_state == TCP_CLOSE) { __mptcp_destroy_sock(sk); do_cancel_work = true; } else { mptcp_start_tout_timer(sk); } return do_cancel_work; } static void mptcp_close(struct sock *sk, long timeout) { bool do_cancel_work; lock_sock(sk); do_cancel_work = __mptcp_close(sk, timeout); release_sock(sk); if (do_cancel_work) mptcp_cancel_work(sk); sock_put(sk); } static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) const struct ipv6_pinfo *ssk6 = inet6_sk(ssk); struct ipv6_pinfo *msk6 = inet6_sk(msk); msk->sk_v6_daddr = ssk->sk_v6_daddr; msk->sk_v6_rcv_saddr = ssk->sk_v6_rcv_saddr; if (msk6 && ssk6) { msk6->saddr = ssk6->saddr; msk6->flow_label = ssk6->flow_label; } #endif inet_sk(msk)->inet_num = inet_sk(ssk)->inet_num; inet_sk(msk)->inet_dport = inet_sk(ssk)->inet_dport; inet_sk(msk)->inet_sport = inet_sk(ssk)->inet_sport; inet_sk(msk)->inet_daddr = inet_sk(ssk)->inet_daddr; inet_sk(msk)->inet_saddr = inet_sk(ssk)->inet_saddr; inet_sk(msk)->inet_rcv_saddr = inet_sk(ssk)->inet_rcv_saddr; } static void mptcp_destroy_common(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow, *tmp; struct sock *sk = (struct sock *)msk; __mptcp_clear_xmit(sk); mptcp_backlog_purge(sk); /* join list will be eventually flushed (with rst) at sock lock release time */ mptcp_for_each_subflow_safe(msk, subflow, tmp) __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, 0); __skb_queue_purge(&sk->sk_receive_queue); skb_rbtree_purge(&msk->out_of_order_queue); /* move all the rx fwd alloc into the sk_mem_reclaim_final in * inet_sock_destruct() will dispose it */ mptcp_token_destroy(msk); mptcp_pm_destroy(msk); } static int mptcp_disconnect(struct sock *sk, int flags) { struct mptcp_sock *msk = mptcp_sk(sk); /* We are on the fastopen error path. We can't call straight into the * subflows cleanup code due to lock nesting (we are already under * msk->firstsocket lock). */ if (msk->fastopening) return -EBUSY; mptcp_check_listen_stop(sk); mptcp_set_state(sk, TCP_CLOSE); mptcp_stop_rtx_timer(sk); mptcp_stop_tout_timer(sk); mptcp_pm_connection_closed(msk); /* msk->subflow is still intact, the following will not free the first * subflow */ mptcp_do_fastclose(sk); mptcp_destroy_common(msk); /* The first subflow is already in TCP_CLOSE status, the following * can't overlap with a fallback anymore */ spin_lock_bh(&msk->fallback_lock); msk->allow_subflows = true; msk->allow_infinite_fallback = true; WRITE_ONCE(msk->flags, 0); spin_unlock_bh(&msk->fallback_lock); msk->cb_flags = 0; msk->recovery = false; WRITE_ONCE(msk->can_ack, false); WRITE_ONCE(msk->fully_established, false); WRITE_ONCE(msk->rcv_data_fin, false); WRITE_ONCE(msk->snd_data_fin_enable, false); WRITE_ONCE(msk->rcv_fastclose, false); WRITE_ONCE(msk->use_64bit_ack, false); WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); mptcp_pm_data_reset(msk); mptcp_ca_reset(sk); msk->bytes_consumed = 0; msk->bytes_acked = 0; msk->bytes_received = 0; msk->bytes_sent = 0; msk->bytes_retrans = 0; msk->rcvspace_init = 0; msk->fastclosing = 0; /* for fallback's sake */ WRITE_ONCE(msk->ack_seq, 0); WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); return 0; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) { struct mptcp6_sock *msk6 = container_of(mptcp_sk(sk), struct mptcp6_sock, msk); return &msk6->np; } static void mptcp_copy_ip6_options(struct sock *newsk, const struct sock *sk) { const struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_txoptions *opt; struct ipv6_pinfo *newnp; newnp = inet6_sk(newsk); rcu_read_lock(); opt = rcu_dereference(np->opt); if (opt) { opt = ipv6_dup_options(newsk, opt); if (!opt) net_warn_ratelimited("%s: Failed to copy ip6 options\n", __func__); } RCU_INIT_POINTER(newnp->opt, opt); rcu_read_unlock(); } #endif static void mptcp_copy_ip_options(struct sock *newsk, const struct sock *sk) { struct ip_options_rcu *inet_opt, *newopt = NULL; const struct inet_sock *inet = inet_sk(sk); struct inet_sock *newinet; newinet = inet_sk(newsk); rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt) { newopt = sock_kmemdup(newsk, inet_opt, sizeof(*inet_opt) + inet_opt->opt.optlen, GFP_ATOMIC); if (!newopt) net_warn_ratelimited("%s: Failed to copy ip options\n", __func__); } RCU_INIT_POINTER(newinet->inet_opt, newopt); rcu_read_unlock(); } struct sock *mptcp_sk_clone_init(const struct sock *sk, const struct mptcp_options_received *mp_opt, struct sock *ssk, struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); struct sock *nsk = sk_clone_lock(sk, GFP_ATOMIC); struct mptcp_subflow_context *subflow; struct mptcp_sock *msk; if (!nsk) return NULL; #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (nsk->sk_family == AF_INET6) inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk); #endif __mptcp_init_sock(nsk); #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (nsk->sk_family == AF_INET6) mptcp_copy_ip6_options(nsk, sk); else #endif mptcp_copy_ip_options(nsk, sk); msk = mptcp_sk(nsk); WRITE_ONCE(msk->local_key, subflow_req->local_key); WRITE_ONCE(msk->token, subflow_req->token); msk->in_accept_queue = 1; WRITE_ONCE(msk->fully_established, false); if (mp_opt->suboptions & OPTION_MPTCP_CSUMREQD) WRITE_ONCE(msk->csum_enabled, true); WRITE_ONCE(msk->write_seq, subflow_req->idsn + 1); WRITE_ONCE(msk->snd_nxt, msk->write_seq); WRITE_ONCE(msk->snd_una, msk->write_seq); WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq; mptcp_init_sched(msk, mptcp_sk(sk)->sched); /* passive msk is created after the first/MPC subflow */ msk->subflow_id = 2; sock_reset_flag(nsk, SOCK_RCU_FREE); security_inet_csk_clone(nsk, req); /* this can't race with mptcp_close(), as the msk is * not yet exposted to user-space */ mptcp_set_state(nsk, TCP_ESTABLISHED); /* The msk maintain a ref to each subflow in the connections list */ WRITE_ONCE(msk->first, ssk); subflow = mptcp_subflow_ctx(ssk); list_add(&subflow->node, &msk->conn_list); sock_hold(ssk); /* new mpc subflow takes ownership of the newly * created mptcp socket */ mptcp_token_accept(subflow_req, msk); /* set msk addresses early to ensure mptcp_pm_get_local_id() * uses the correct data */ mptcp_copy_inaddrs(nsk, ssk); __mptcp_propagate_sndbuf(nsk, ssk); mptcp_rcv_space_init(msk, ssk); if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK) __mptcp_subflow_fully_established(msk, subflow, mp_opt); bh_unlock_sock(nsk); /* note: the newly allocated socket refcount is 2 now */ return nsk; } void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk) { const struct tcp_sock *tp = tcp_sk(ssk); msk->rcvspace_init = 1; msk->rcvq_space.copied = 0; msk->rcvq_space.rtt_us = 0; msk->rcvq_space.time = tp->tcp_mstamp; /* initial rcv_space offering made to peer */ msk->rcvq_space.space = min_t(u32, tp->rcv_wnd, TCP_INIT_CWND * tp->advmss); if (msk->rcvq_space.space == 0) msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT; } static void mptcp_destroy(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); /* allow the following to close even the initial subflow */ msk->free_first = 1; mptcp_destroy_common(msk); sk_sockets_allocated_dec(sk); } void __mptcp_data_acked(struct sock *sk) { if (!sock_owned_by_user(sk)) __mptcp_clean_una(sk); else __set_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->cb_flags); } void __mptcp_check_push(struct sock *sk, struct sock *ssk) { if (!sock_owned_by_user(sk)) __mptcp_subflow_push_pending(sk, ssk, false); else __set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags); } #define MPTCP_FLAGS_PROCESS_CTX_NEED (BIT(MPTCP_PUSH_PENDING) | \ BIT(MPTCP_RETRANSMIT) | \ BIT(MPTCP_FLUSH_JOIN_LIST)) /* processes deferred events and flush wmem */ static void mptcp_release_cb(struct sock *sk) __must_hold(&sk->sk_lock.slock) { struct mptcp_sock *msk = mptcp_sk(sk); for (;;) { unsigned long flags = (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED); struct list_head join_list, skbs; bool spool_bl; u32 moved; spool_bl = mptcp_can_spool_backlog(sk, &skbs); if (!flags && !spool_bl) break; INIT_LIST_HEAD(&join_list); list_splice_init(&msk->join_list, &join_list); /* the following actions acquire the subflow socket lock * * 1) can't be invoked in atomic scope * 2) must avoid ABBA deadlock with msk socket spinlock: the RX * datapath acquires the msk socket spinlock while helding * the subflow socket lock */ msk->cb_flags &= ~flags; spin_unlock_bh(&sk->sk_lock.slock); if (flags & BIT(MPTCP_FLUSH_JOIN_LIST)) __mptcp_flush_join_list(sk, &join_list); if (flags & BIT(MPTCP_PUSH_PENDING)) __mptcp_push_pending(sk, 0); if (flags & BIT(MPTCP_RETRANSMIT)) __mptcp_retrans(sk); if (spool_bl && __mptcp_move_skbs(sk, &skbs, &moved)) { /* notify ack seq update */ mptcp_cleanup_rbuf(msk, 0); sk->sk_data_ready(sk); } cond_resched(); spin_lock_bh(&sk->sk_lock.slock); if (spool_bl) mptcp_backlog_spooled(sk, moved, &skbs); } if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags)) __mptcp_clean_una_wakeup(sk); if (unlikely(msk->cb_flags)) { /* be sure to sync the msk state before taking actions * depending on sk_state (MPTCP_ERROR_REPORT) * On sk release avoid actions depending on the first subflow */ if (__test_and_clear_bit(MPTCP_SYNC_STATE, &msk->cb_flags) && msk->first) __mptcp_sync_state(sk, msk->pending_state); if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags)) __mptcp_error_report(sk); if (__test_and_clear_bit(MPTCP_SYNC_SNDBUF, &msk->cb_flags)) __mptcp_sync_sndbuf(sk); } } /* MP_JOIN client subflow must wait for 4th ack before sending any data: * TCP can't schedule delack timer before the subflow is fully established. * MPTCP uses the delack timer to do 3rd ack retransmissions */ static void schedule_3rdack_retransmission(struct sock *ssk) { struct inet_connection_sock *icsk = inet_csk(ssk); struct tcp_sock *tp = tcp_sk(ssk); unsigned long timeout; if (READ_ONCE(mptcp_subflow_ctx(ssk)->fully_established)) return; /* reschedule with a timeout above RTT, as we must look only for drop */ if (tp->srtt_us) timeout = usecs_to_jiffies(tp->srtt_us >> (3 - 1)); else timeout = TCP_TIMEOUT_INIT; timeout += jiffies; WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER); smp_store_release(&icsk->icsk_ack.pending, icsk->icsk_ack.pending | ICSK_ACK_SCHED | ICSK_ACK_TIMER); sk_reset_timer(ssk, &icsk->icsk_delack_timer, timeout); } void mptcp_subflow_process_delegated(struct sock *ssk, long status) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = subflow->conn; if (status & BIT(MPTCP_DELEGATE_SEND)) { mptcp_data_lock(sk); if (!sock_owned_by_user(sk)) __mptcp_subflow_push_pending(sk, ssk, true); else __set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); } if (status & BIT(MPTCP_DELEGATE_SNDBUF)) { mptcp_data_lock(sk); if (!sock_owned_by_user(sk)) __mptcp_sync_sndbuf(sk); else __set_bit(MPTCP_SYNC_SNDBUF, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); } if (status & BIT(MPTCP_DELEGATE_ACK)) schedule_3rdack_retransmission(ssk); } static int mptcp_hash(struct sock *sk) { /* should never be called, * we hash the TCP subflows not the MPTCP socket */ WARN_ON_ONCE(1); return 0; } static void mptcp_unhash(struct sock *sk) { /* called from sk_common_release(), but nothing to do here */ } static int mptcp_get_port(struct sock *sk, unsigned short snum) { struct mptcp_sock *msk = mptcp_sk(sk); pr_debug("msk=%p, ssk=%p\n", msk, msk->first); if (WARN_ON_ONCE(!msk->first)) return -EINVAL; return inet_csk_get_port(msk->first, snum); } void mptcp_finish_connect(struct sock *ssk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk; struct sock *sk; subflow = mptcp_subflow_ctx(ssk); sk = subflow->conn; msk = mptcp_sk(sk); pr_debug("msk=%p, token=%u\n", sk, subflow->token); subflow->map_seq = subflow->iasn; subflow->map_subflow_seq = 1; /* the socket is not connected yet, no msk/subflow ops can access/race * accessing the field below */ WRITE_ONCE(msk->local_key, subflow->local_key); mptcp_pm_new_connection(msk, ssk, 0); } void mptcp_sock_graft(struct sock *sk, struct socket *parent) { write_lock_bh(&sk->sk_callback_lock); rcu_assign_pointer(sk->sk_wq, &parent->wq); sk_set_socket(sk, parent); write_unlock_bh(&sk->sk_callback_lock); } /* Can be called without holding the msk socket lock; use the callback lock * to avoid {READ_,WRITE_}ONCE annotations on sk_socket. */ static void mptcp_sock_check_graft(struct sock *sk, struct sock *ssk) { struct socket *sock; write_lock_bh(&sk->sk_callback_lock); sock = sk->sk_socket; write_unlock_bh(&sk->sk_callback_lock); if (sock) { mptcp_sock_graft(ssk, sock); __mptcp_inherit_cgrp_data(sk, ssk); __mptcp_inherit_memcg(sk, ssk, GFP_ATOMIC); } } bool mptcp_finish_join(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); struct sock *parent = (void *)msk; bool ret = true; pr_debug("msk=%p, subflow=%p\n", msk, subflow); /* mptcp socket already closing? */ if (!mptcp_is_fully_established(parent)) { subflow->reset_reason = MPTCP_RST_EMPTCP; return false; } /* Active subflow, already present inside the conn_list; is grafted * either by __mptcp_subflow_connect() or accept. */ if (!list_empty(&subflow->node)) { spin_lock_bh(&msk->fallback_lock); if (!msk->allow_subflows) { spin_unlock_bh(&msk->fallback_lock); return false; } mptcp_subflow_joined(msk, ssk); spin_unlock_bh(&msk->fallback_lock); mptcp_propagate_sndbuf(parent, ssk); return true; } if (!mptcp_pm_allow_new_subflow(msk)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_JOINREJECTED); goto err_prohibited; } /* If we can't acquire msk socket lock here, let the release callback * handle it */ mptcp_data_lock(parent); if (!sock_owned_by_user(parent)) { ret = __mptcp_finish_join(msk, ssk); if (ret) { sock_hold(ssk); list_add_tail(&subflow->node, &msk->conn_list); mptcp_sock_check_graft(parent, ssk); } } else { sock_hold(ssk); list_add_tail(&subflow->node, &msk->join_list); __set_bit(MPTCP_FLUSH_JOIN_LIST, &msk->cb_flags); /* In case of later failures, __mptcp_flush_join_list() will * properly orphan the ssk via mptcp_close_ssk(). */ mptcp_sock_check_graft(parent, ssk); } mptcp_data_unlock(parent); if (!ret) { err_prohibited: subflow->reset_reason = MPTCP_RST_EPROHIBIT; return false; } return true; } static void mptcp_shutdown(struct sock *sk, int how) { pr_debug("sk=%p, how=%d\n", sk, how); if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk)) __mptcp_wr_shutdown(sk); } static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v) { const struct sock *sk = (void *)msk; u64 delta; if (sk->sk_state == TCP_LISTEN) return -EINVAL; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) return 0; delta = msk->write_seq - v; if (__mptcp_check_fallback(msk) && msk->first) { struct tcp_sock *tp = tcp_sk(msk->first); /* the first subflow is disconnected after close - see * __mptcp_close_ssk(). tcp_disconnect() moves the write_seq * so ignore that status, too. */ if (!((1 << msk->first->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))) delta += READ_ONCE(tp->write_seq) - tp->snd_una; } if (delta > INT_MAX) delta = INT_MAX; return (int)delta; } static int mptcp_ioctl(struct sock *sk, int cmd, int *karg) { struct mptcp_sock *msk = mptcp_sk(sk); bool slow; switch (cmd) { case SIOCINQ: if (sk->sk_state == TCP_LISTEN) return -EINVAL; lock_sock(sk); if (mptcp_move_skbs(sk)) mptcp_cleanup_rbuf(msk, 0); *karg = mptcp_inq_hint(sk); release_sock(sk); break; case SIOCOUTQ: slow = lock_sock_fast(sk); *karg = mptcp_ioctl_outq(msk, READ_ONCE(msk->snd_una)); unlock_sock_fast(sk, slow); break; case SIOCOUTQNSD: slow = lock_sock_fast(sk); *karg = mptcp_ioctl_outq(msk, msk->snd_nxt); unlock_sock_fast(sk, slow); break; default: return -ENOIOCTLCMD; } return 0; } static int mptcp_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); int err = -EINVAL; struct sock *ssk; ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) return PTR_ERR(ssk); mptcp_set_state(sk, TCP_SYN_SENT); subflow = mptcp_subflow_ctx(ssk); #ifdef CONFIG_TCP_MD5SIG /* no MPTCP if MD5SIG is enabled on this socket or we may run out of * TCP option space. */ if (rcu_access_pointer(tcp_sk(ssk)->md5sig_info)) mptcp_early_fallback(msk, subflow, MPTCP_MIB_MD5SIGFALLBACK); #endif if (subflow->request_mptcp) { if (mptcp_active_should_disable(sk)) mptcp_early_fallback(msk, subflow, MPTCP_MIB_MPCAPABLEACTIVEDISABLED); else if (mptcp_token_new_connect(ssk) < 0) mptcp_early_fallback(msk, subflow, MPTCP_MIB_TOKENFALLBACKINIT); } WRITE_ONCE(msk->write_seq, subflow->idsn); WRITE_ONCE(msk->snd_nxt, subflow->idsn); WRITE_ONCE(msk->snd_una, subflow->idsn); if (likely(!__mptcp_check_fallback(msk))) MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVE); /* if reaching here via the fastopen/sendmsg path, the caller already * acquired the subflow socket lock, too. */ if (!msk->fastopening) lock_sock(ssk); /* the following mirrors closely a very small chunk of code from * __inet_stream_connect() */ if (ssk->sk_state != TCP_CLOSE) goto out; if (BPF_CGROUP_PRE_CONNECT_ENABLED(ssk)) { err = ssk->sk_prot->pre_connect(ssk, uaddr, addr_len); if (err) goto out; } err = ssk->sk_prot->connect(ssk, uaddr, addr_len); if (err < 0) goto out; inet_assign_bit(DEFER_CONNECT, sk, inet_test_bit(DEFER_CONNECT, ssk)); out: if (!msk->fastopening) release_sock(ssk); /* on successful connect, the msk state will be moved to established by * subflow_finish_connect() */ if (unlikely(err)) { /* avoid leaving a dangling token in an unconnected socket */ mptcp_token_destroy(msk); mptcp_set_state(sk, TCP_CLOSE); return err; } mptcp_copy_inaddrs(sk, ssk); return 0; } static struct proto mptcp_prot = { .name = "MPTCP", .owner = THIS_MODULE, .init = mptcp_init_sock, .connect = mptcp_connect, .disconnect = mptcp_disconnect, .close = mptcp_close, .setsockopt = mptcp_setsockopt, .getsockopt = mptcp_getsockopt, .shutdown = mptcp_shutdown, .destroy = mptcp_destroy, .sendmsg = mptcp_sendmsg, .ioctl = mptcp_ioctl, .recvmsg = mptcp_recvmsg, .release_cb = mptcp_release_cb, .hash = mptcp_hash, .unhash = mptcp_unhash, .get_port = mptcp_get_port, .stream_memory_free = mptcp_stream_memory_free, .sockets_allocated = &mptcp_sockets_allocated, .memory_allocated = &net_aligned_data.tcp_memory_allocated, .per_cpu_fw_alloc = &tcp_memory_per_cpu_fw_alloc, .memory_pressure = &tcp_memory_pressure, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .sysctl_mem = sysctl_tcp_mem, .obj_size = sizeof(struct mptcp_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, .no_autobind = true, }; static int mptcp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { struct mptcp_sock *msk = mptcp_sk(sock->sk); struct sock *ssk, *sk = sock->sk; int err = -EINVAL; lock_sock(sk); ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) { err = PTR_ERR(ssk); goto unlock; } if (sk->sk_family == AF_INET) err = inet_bind_sk(ssk, uaddr, addr_len); #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (sk->sk_family == AF_INET6) err = inet6_bind_sk(ssk, uaddr, addr_len); #endif if (!err) mptcp_copy_inaddrs(sk, ssk); unlock: release_sock(sk); return err; } static int mptcp_listen(struct socket *sock, int backlog) { struct mptcp_sock *msk = mptcp_sk(sock->sk); struct sock *sk = sock->sk; struct sock *ssk; int err; pr_debug("msk=%p\n", msk); lock_sock(sk); err = -EINVAL; if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) goto unlock; ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) { err = PTR_ERR(ssk); goto unlock; } mptcp_set_state(sk, TCP_LISTEN); sock_set_flag(sk, SOCK_RCU_FREE); lock_sock(ssk); err = __inet_listen_sk(ssk, backlog); release_sock(ssk); mptcp_set_state(sk, inet_sk_state_load(ssk)); if (!err) { sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); mptcp_copy_inaddrs(sk, ssk); mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CREATED); } unlock: release_sock(sk); return err; } static void mptcp_graft_subflows(struct sock *sk) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); if (mem_cgroup_sockets_enabled) { LIST_HEAD(join_list); /* Subflows joining after __inet_accept() will get the * mem CG properly initialized at mptcp_finish_join() time, * but subflows pending in join_list need explicit * initialization before flushing `backlog_unaccounted` * or MPTCP can later unexpectedly observe unaccounted memory. */ mptcp_data_lock(sk); list_splice_init(&msk->join_list, &join_list); mptcp_data_unlock(sk); __mptcp_flush_join_list(sk, &join_list); } mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); lock_sock(ssk); /* Set ssk->sk_socket of accept()ed flows to mptcp socket. * This is needed so NOSPACE flag can be set from tcp stack. */ if (!ssk->sk_socket) mptcp_sock_graft(ssk, sk->sk_socket); if (!mem_cgroup_sk_enabled(sk)) goto unlock; __mptcp_inherit_cgrp_data(sk, ssk); __mptcp_inherit_memcg(sk, ssk, GFP_KERNEL); unlock: release_sock(ssk); } if (mem_cgroup_sk_enabled(sk)) { gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL; int amt; /* Account the backlog memory; prior accept() is aware of * fwd and rmem only. */ mptcp_data_lock(sk); amt = sk_mem_pages(sk->sk_forward_alloc + msk->backlog_unaccounted + atomic_read(&sk->sk_rmem_alloc)) - sk_mem_pages(sk->sk_forward_alloc + atomic_read(&sk->sk_rmem_alloc)); msk->backlog_unaccounted = 0; mptcp_data_unlock(sk); if (amt) mem_cgroup_sk_charge(sk, amt, gfp); } } static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { struct mptcp_sock *msk = mptcp_sk(sock->sk); struct sock *ssk, *newsk; pr_debug("msk=%p\n", msk); /* Buggy applications can call accept on socket states other then LISTEN * but no need to allocate the first subflow just to error out. */ ssk = READ_ONCE(msk->first); if (!ssk) return -EINVAL; pr_debug("ssk=%p, listener=%p\n", ssk, mptcp_subflow_ctx(ssk)); newsk = inet_csk_accept(ssk, arg); if (!newsk) return arg->err; pr_debug("newsk=%p, subflow is mptcp=%d\n", newsk, sk_is_mptcp(newsk)); if (sk_is_mptcp(newsk)) { struct mptcp_subflow_context *subflow; struct sock *new_mptcp_sock; subflow = mptcp_subflow_ctx(newsk); new_mptcp_sock = subflow->conn; /* is_mptcp should be false if subflow->conn is missing, see * subflow_syn_recv_sock() */ if (WARN_ON_ONCE(!new_mptcp_sock)) { tcp_sk(newsk)->is_mptcp = 0; goto tcpfallback; } newsk = new_mptcp_sock; MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEPASSIVEACK); newsk->sk_kern_sock = arg->kern; lock_sock(newsk); __inet_accept(sock, newsock, newsk); set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags); msk = mptcp_sk(newsk); msk->in_accept_queue = 0; mptcp_graft_subflows(newsk); mptcp_rps_record_subflows(msk); /* Do late cleanup for the first subflow as necessary. Also * deal with bad peers not doing a complete shutdown. */ if (unlikely(inet_sk_state_load(msk->first) == TCP_CLOSE)) { if (unlikely(list_is_singular(&msk->conn_list))) mptcp_set_state(newsk, TCP_CLOSE); mptcp_close_ssk(newsk, msk->first, mptcp_subflow_ctx(msk->first)); } } else { tcpfallback: newsk->sk_kern_sock = arg->kern; lock_sock(newsk); __inet_accept(sock, newsock, newsk); /* we are being invoked after accepting a non-mp-capable * flow: sk is a tcp_sk, not an mptcp one. * * Hand the socket over to tcp so all further socket ops * bypass mptcp. */ WRITE_ONCE(newsock->sk->sk_socket->ops, mptcp_fallback_tcp_ops(newsock->sk)); } release_sock(newsk); return 0; } static __poll_t mptcp_check_writeable(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; if (__mptcp_stream_is_writeable(sk, 1)) return EPOLLOUT | EPOLLWRNORM; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); smp_mb__after_atomic(); /* NOSPACE is changed by mptcp_write_space() */ if (__mptcp_stream_is_writeable(sk, 1)) return EPOLLOUT | EPOLLWRNORM; return 0; } static __poll_t mptcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait) { struct sock *sk = sock->sk; struct mptcp_sock *msk; __poll_t mask = 0; u8 shutdown; int state; msk = mptcp_sk(sk); sock_poll_wait(file, sock, wait); state = inet_sk_state_load(sk); pr_debug("msk=%p state=%d flags=%lx\n", msk, state, msk->flags); if (state == TCP_LISTEN) { struct sock *ssk = READ_ONCE(msk->first); if (WARN_ON_ONCE(!ssk)) return 0; return inet_csk_listen_poll(ssk); } shutdown = READ_ONCE(sk->sk_shutdown); if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) mask |= EPOLLHUP; if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) { mask |= mptcp_check_readable(sk); if (shutdown & SEND_SHUTDOWN) mask |= EPOLLOUT | EPOLLWRNORM; else mask |= mptcp_check_writeable(msk); } else if (state == TCP_SYN_SENT && inet_test_bit(DEFER_CONNECT, sk)) { /* cf tcp_poll() note about TFO */ mask |= EPOLLOUT | EPOLLWRNORM; } /* This barrier is coupled with smp_wmb() in __mptcp_error_report() */ smp_rmb(); if (READ_ONCE(sk->sk_err)) mask |= EPOLLERR; return mask; } static const struct proto_ops mptcp_stream_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, .bind = mptcp_bind, .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = mptcp_stream_accept, .getname = inet_getname, .poll = mptcp_poll, .ioctl = inet_ioctl, .gettstamp = sock_gettstamp, .listen = mptcp_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .set_rcvlowat = mptcp_set_rcvlowat, }; static struct inet_protosw mptcp_protosw = { .type = SOCK_STREAM, .protocol = IPPROTO_MPTCP, .prot = &mptcp_prot, .ops = &mptcp_stream_ops, .flags = INET_PROTOSW_ICSK, }; static int mptcp_napi_poll(struct napi_struct *napi, int budget) { struct mptcp_delegated_action *delegated; struct mptcp_subflow_context *subflow; int work_done = 0; delegated = container_of(napi, struct mptcp_delegated_action, napi); while ((subflow = mptcp_subflow_delegated_next(delegated)) != NULL) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bh_lock_sock_nested(ssk); if (!sock_owned_by_user(ssk)) { mptcp_subflow_process_delegated(ssk, xchg(&subflow->delegated_status, 0)); } else { /* tcp_release_cb_override already processed * the action or will do at next release_sock(). * In both case must dequeue the subflow here - on the same * CPU that scheduled it. */ smp_wmb(); clear_bit(MPTCP_DELEGATE_SCHEDULED, &subflow->delegated_status); } bh_unlock_sock(ssk); sock_put(ssk); if (++work_done == budget) return budget; } /* always provide a 0 'work_done' argument, so that napi_complete_done * will not try accessing the NULL napi->dev ptr */ napi_complete_done(napi, 0); return work_done; } void __init mptcp_proto_init(void) { struct mptcp_delegated_action *delegated; int cpu; mptcp_prot.h.hashinfo = tcp_prot.h.hashinfo; if (percpu_counter_init(&mptcp_sockets_allocated, 0, GFP_KERNEL)) panic("Failed to allocate MPTCP pcpu counter\n"); mptcp_napi_dev = alloc_netdev_dummy(0); if (!mptcp_napi_dev) panic("Failed to allocate MPTCP dummy netdev\n"); for_each_possible_cpu(cpu) { delegated = per_cpu_ptr(&mptcp_delegated_actions, cpu); INIT_LIST_HEAD(&delegated->head); netif_napi_add_tx(mptcp_napi_dev, &delegated->napi, mptcp_napi_poll); napi_enable(&delegated->napi); } mptcp_subflow_init(); mptcp_pm_init(); mptcp_sched_init(); mptcp_token_init(); if (proto_register(&mptcp_prot, 1) != 0) panic("Failed to register MPTCP proto.\n"); inet_register_protosw(&mptcp_protosw); BUILD_BUG_ON(sizeof(struct mptcp_skb_cb) > sizeof_field(struct sk_buff, cb)); } #if IS_ENABLED(CONFIG_MPTCP_IPV6) static const struct proto_ops mptcp_v6_stream_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, .bind = mptcp_bind, .connect = inet_stream_connect, .socketpair = sock_no_socketpair, .accept = mptcp_stream_accept, .getname = inet6_getname, .poll = mptcp_poll, .ioctl = inet6_ioctl, .gettstamp = sock_gettstamp, .listen = mptcp_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet6_sendmsg, .recvmsg = inet6_recvmsg, .mmap = sock_no_mmap, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif .set_rcvlowat = mptcp_set_rcvlowat, }; static struct proto mptcp_v6_prot; static struct inet_protosw mptcp_v6_protosw = { .type = SOCK_STREAM, .protocol = IPPROTO_MPTCP, .prot = &mptcp_v6_prot, .ops = &mptcp_v6_stream_ops, .flags = INET_PROTOSW_ICSK, }; int __init mptcp_proto_v6_init(void) { int err; mptcp_v6_prot = mptcp_prot; strscpy(mptcp_v6_prot.name, "MPTCPv6", sizeof(mptcp_v6_prot.name)); mptcp_v6_prot.slab = NULL; mptcp_v6_prot.obj_size = sizeof(struct mptcp6_sock); mptcp_v6_prot.ipv6_pinfo_offset = offsetof(struct mptcp6_sock, np); err = proto_register(&mptcp_v6_prot, 1); if (err) return err; err = inet6_register_protosw(&mptcp_v6_protosw); if (err) proto_unregister(&mptcp_v6_prot); return err; } #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* drivers/net/ifb.c: The purpose of this driver is to provide a device that allows for sharing of resources: 1) qdiscs/policies that are per device as opposed to system wide. ifb allows for a device which can be redirected to thus providing an impression of sharing. 2) Allows for queueing incoming traffic for shaping instead of dropping. The original concept is based on what is known as the IMQ driver initially written by Martin Devera, later rewritten by Patrick McHardy and then maintained by Andre Correa. You need the tc action mirror or redirect to feed this device packets. Authors: Jamal Hadi Salim (2005) */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/ethtool.h> #include <linux/etherdevice.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/moduleparam.h> #include <linux/netfilter_netdev.h> #include <net/pkt_sched.h> #include <net/net_namespace.h> #define TX_Q_LIMIT 32 struct ifb_q_stats { u64 packets; u64 bytes; struct u64_stats_sync sync; }; struct ifb_q_private { struct net_device *dev; struct tasklet_struct ifb_tasklet; int tasklet_pending; int txqnum; struct sk_buff_head rq; struct sk_buff_head tq; struct ifb_q_stats rx_stats; struct ifb_q_stats tx_stats; } ____cacheline_aligned_in_smp; struct ifb_dev_private { struct ifb_q_private *tx_private; }; /* For ethtools stats. */ struct ifb_q_stats_desc { char desc[ETH_GSTRING_LEN]; size_t offset; }; #define IFB_Q_STAT(m) offsetof(struct ifb_q_stats, m) static const struct ifb_q_stats_desc ifb_q_stats_desc[] = { { "packets", IFB_Q_STAT(packets) }, { "bytes", IFB_Q_STAT(bytes) }, }; #define IFB_Q_STATS_LEN ARRAY_SIZE(ifb_q_stats_desc) static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev); static int ifb_open(struct net_device *dev); static int ifb_close(struct net_device *dev); static void ifb_update_q_stats(struct ifb_q_stats *stats, int len) { u64_stats_update_begin(&stats->sync); stats->packets++; stats->bytes += len; u64_stats_update_end(&stats->sync); } static void ifb_ri_tasklet(struct tasklet_struct *t) { struct ifb_q_private *txp = from_tasklet(txp, t, ifb_tasklet); struct netdev_queue *txq; struct sk_buff *skb; txq = netdev_get_tx_queue(txp->dev, txp->txqnum); skb = skb_peek(&txp->tq); if (!skb) { if (!__netif_tx_trylock(txq)) goto resched; skb_queue_splice_tail_init(&txp->rq, &txp->tq); __netif_tx_unlock(txq); } while ((skb = __skb_dequeue(&txp->tq)) != NULL) { /* Skip tc and netfilter to prevent redirection loop. */ skb->redirected = 0; #ifdef CONFIG_NET_CLS_ACT skb->tc_skip_classify = 1; #endif nf_skip_egress(skb, true); ifb_update_q_stats(&txp->tx_stats, skb->len); rcu_read_lock(); skb->dev = dev_get_by_index_rcu(dev_net(txp->dev), skb->skb_iif); if (!skb->dev) { rcu_read_unlock(); dev_kfree_skb(skb); txp->dev->stats.tx_dropped++; if (skb_queue_len(&txp->tq) != 0) goto resched; break; } rcu_read_unlock(); skb->skb_iif = txp->dev->ifindex; if (!skb->from_ingress) { dev_queue_xmit(skb); } else { skb_pull_rcsum(skb, skb->mac_len); netif_receive_skb(skb); } } if (__netif_tx_trylock(txq)) { skb = skb_peek(&txp->rq); if (!skb) { txp->tasklet_pending = 0; if (netif_tx_queue_stopped(txq)) netif_tx_wake_queue(txq); } else { __netif_tx_unlock(txq); goto resched; } __netif_tx_unlock(txq); } else { resched: txp->tasklet_pending = 1; tasklet_schedule(&txp->ifb_tasklet); } } static void ifb_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct ifb_dev_private *dp = netdev_priv(dev); struct ifb_q_private *txp = dp->tx_private; unsigned int start; u64 packets, bytes; int i; for (i = 0; i < dev->num_tx_queues; i++,txp++) { do { start = u64_stats_fetch_begin(&txp->rx_stats.sync); packets = txp->rx_stats.packets; bytes = txp->rx_stats.bytes; } while (u64_stats_fetch_retry(&txp->rx_stats.sync, start)); stats->rx_packets += packets; stats->rx_bytes += bytes; do { start = u64_stats_fetch_begin(&txp->tx_stats.sync); packets = txp->tx_stats.packets; bytes = txp->tx_stats.bytes; } while (u64_stats_fetch_retry(&txp->tx_stats.sync, start)); stats->tx_packets += packets; stats->tx_bytes += bytes; } stats->rx_dropped = dev->stats.rx_dropped; stats->tx_dropped = dev->stats.tx_dropped; } static int ifb_dev_init(struct net_device *dev) { struct ifb_dev_private *dp = netdev_priv(dev); struct ifb_q_private *txp; int i; txp = kcalloc(dev->num_tx_queues, sizeof(*txp), GFP_KERNEL); if (!txp) return -ENOMEM; dp->tx_private = txp; for (i = 0; i < dev->num_tx_queues; i++,txp++) { txp->txqnum = i; txp->dev = dev; __skb_queue_head_init(&txp->rq); __skb_queue_head_init(&txp->tq); u64_stats_init(&txp->rx_stats.sync); u64_stats_init(&txp->tx_stats.sync); tasklet_setup(&txp->ifb_tasklet, ifb_ri_tasklet); netif_tx_start_queue(netdev_get_tx_queue(dev, i)); } return 0; } static void ifb_get_strings(struct net_device *dev, u32 stringset, u8 *buf) { u8 *p = buf; int i, j; switch (stringset) { case ETH_SS_STATS: for (i = 0; i < dev->real_num_rx_queues; i++) for (j = 0; j < IFB_Q_STATS_LEN; j++) ethtool_sprintf(&p, "rx_queue_%u_%.18s", i, ifb_q_stats_desc[j].desc); for (i = 0; i < dev->real_num_tx_queues; i++) for (j = 0; j < IFB_Q_STATS_LEN; j++) ethtool_sprintf(&p, "tx_queue_%u_%.18s", i, ifb_q_stats_desc[j].desc); break; } } static int ifb_get_sset_count(struct net_device *dev, int sset) { switch (sset) { case ETH_SS_STATS: return IFB_Q_STATS_LEN * (dev->real_num_rx_queues + dev->real_num_tx_queues); default: return -EOPNOTSUPP; } } static void ifb_fill_stats_data(u64 **data, struct ifb_q_stats *q_stats) { void *stats_base = (void *)q_stats; unsigned int start; size_t offset; int j; do { start = u64_stats_fetch_begin(&q_stats->sync); for (j = 0; j < IFB_Q_STATS_LEN; j++) { offset = ifb_q_stats_desc[j].offset; (*data)[j] = *(u64 *)(stats_base + offset); } } while (u64_stats_fetch_retry(&q_stats->sync, start)); *data += IFB_Q_STATS_LEN; } static void ifb_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { struct ifb_dev_private *dp = netdev_priv(dev); struct ifb_q_private *txp; int i; for (i = 0; i < dev->real_num_rx_queues; i++) { txp = dp->tx_private + i; ifb_fill_stats_data(&data, &txp->rx_stats); } for (i = 0; i < dev->real_num_tx_queues; i++) { txp = dp->tx_private + i; ifb_fill_stats_data(&data, &txp->tx_stats); } } static const struct net_device_ops ifb_netdev_ops = { .ndo_open = ifb_open, .ndo_stop = ifb_close, .ndo_get_stats64 = ifb_stats64, .ndo_start_xmit = ifb_xmit, .ndo_validate_addr = eth_validate_addr, .ndo_init = ifb_dev_init, }; static const struct ethtool_ops ifb_ethtool_ops = { .get_strings = ifb_get_strings, .get_sset_count = ifb_get_sset_count, .get_ethtool_stats = ifb_get_ethtool_stats, }; #define IFB_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_FRAGLIST | \ NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL | \ NETIF_F_HIGHDMA | NETIF_F_HW_VLAN_CTAG_TX | \ NETIF_F_HW_VLAN_STAG_TX) static void ifb_dev_free(struct net_device *dev) { struct ifb_dev_private *dp = netdev_priv(dev); struct ifb_q_private *txp = dp->tx_private; int i; for (i = 0; i < dev->num_tx_queues; i++,txp++) { tasklet_kill(&txp->ifb_tasklet); __skb_queue_purge(&txp->rq); __skb_queue_purge(&txp->tq); } kfree(dp->tx_private); } static void ifb_setup(struct net_device *dev) { /* Initialize the device structure. */ dev->netdev_ops = &ifb_netdev_ops; dev->ethtool_ops = &ifb_ethtool_ops; /* Fill in device structure with ethernet-generic values. */ ether_setup(dev); dev->tx_queue_len = TX_Q_LIMIT; dev->features |= IFB_FEATURES; dev->hw_features |= dev->features; dev->hw_enc_features |= dev->features; dev->vlan_features |= IFB_FEATURES & ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); dev->flags |= IFF_NOARP; dev->flags &= ~IFF_MULTICAST; dev->priv_flags &= ~IFF_TX_SKB_SHARING; netif_keep_dst(dev); eth_hw_addr_random(dev); dev->needs_free_netdev = true; dev->priv_destructor = ifb_dev_free; dev->min_mtu = 0; dev->max_mtu = 0; netif_set_tso_max_size(dev, GSO_MAX_SIZE); } static netdev_tx_t ifb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ifb_dev_private *dp = netdev_priv(dev); struct ifb_q_private *txp = dp->tx_private + skb_get_queue_mapping(skb); ifb_update_q_stats(&txp->rx_stats, skb->len); if (!skb->redirected || !skb->skb_iif) { dev_kfree_skb(skb); dev->stats.rx_dropped++; return NETDEV_TX_OK; } if (skb_queue_len(&txp->rq) >= dev->tx_queue_len) netif_tx_stop_queue(netdev_get_tx_queue(dev, txp->txqnum)); __skb_queue_tail(&txp->rq, skb); if (!txp->tasklet_pending) { txp->tasklet_pending = 1; tasklet_schedule(&txp->ifb_tasklet); } return NETDEV_TX_OK; } static int ifb_close(struct net_device *dev) { netif_tx_stop_all_queues(dev); return 0; } static int ifb_open(struct net_device *dev) { netif_tx_start_all_queues(dev); return 0; } static int ifb_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } return 0; } static struct rtnl_link_ops ifb_link_ops __read_mostly = { .kind = "ifb", .priv_size = sizeof(struct ifb_dev_private), .setup = ifb_setup, .validate = ifb_validate, }; /* Number of ifb devices to be set up by this module. * Note that these legacy devices have one queue. * Prefer something like : ip link add ifb10 numtxqueues 8 type ifb */ static int numifbs = 2; module_param(numifbs, int, 0); MODULE_PARM_DESC(numifbs, "Number of ifb devices"); static int __init ifb_init_one(int index) { struct net_device *dev_ifb; int err; dev_ifb = alloc_netdev(sizeof(struct ifb_dev_private), "ifb%d", NET_NAME_UNKNOWN, ifb_setup); if (!dev_ifb) return -ENOMEM; dev_ifb->rtnl_link_ops = &ifb_link_ops; err = register_netdevice(dev_ifb); if (err < 0) goto err; return 0; err: free_netdev(dev_ifb); return err; } static int __init ifb_init_module(void) { int i, err; err = rtnl_link_register(&ifb_link_ops); if (err < 0) return err; rtnl_net_lock(&init_net); for (i = 0; i < numifbs && !err; i++) { err = ifb_init_one(i); cond_resched(); } rtnl_net_unlock(&init_net); if (err) rtnl_link_unregister(&ifb_link_ops); return err; } static void __exit ifb_cleanup_module(void) { rtnl_link_unregister(&ifb_link_ops); } module_init(ifb_init_module); module_exit(ifb_cleanup_module); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Intermediate Functional Block (ifb) netdevice driver for sharing of resources and ingress packet queuing"); MODULE_AUTHOR("Jamal Hadi Salim"); MODULE_ALIAS_RTNL_LINK("ifb"); |
| 16 16 16 9 9 8 3 8 5 7 1 6 16 8 2 7 1 6 8 2 5 4 4 2 2 2 2 2 6 12 12 12 12 13 12 13 5 13 13 13 2 18 18 17 16 15 14 11 14 14 8 4 3 1 3 6 12 1 11 11 11 11 6 8 18 10 9 8 8 4 6 5 5 5 5 6 10 1 1 5 5 5 3 1 2 2 1 2 2 1 5 2 2 13 12 12 29 29 29 29 28 28 28 27 26 5 4 2 26 5 1 26 19 13 6 5 4 26 20 25 14 2 13 4 2 13 19 3 3 8 25 17 12 25 5 25 20 2 18 25 10 25 24 25 20 1 20 13 20 5 21 23 29 15 6 6 5 5 3 1 3 2 2 2 2 2 2 1 2 2 1 2 1 2 5 43 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* L2TPv3 IP encapsulation support for IPv6 * * Copyright (c) 2012 Katalix Systems Ltd */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/icmp.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/random.h> #include <linux/socket.h> #include <linux/l2tp.h> #include <linux/in.h> #include <linux/in6.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/udp.h> #include <net/inet_common.h> #include <net/tcp_states.h> #include <net/protocol.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/transp_v6.h> #include <net/addrconf.h> #include <net/ip6_route.h> #include "l2tp_core.h" /* per-net private data for this module */ static unsigned int l2tp_ip6_net_id; struct l2tp_ip6_net { rwlock_t l2tp_ip6_lock; struct hlist_head l2tp_ip6_table; struct hlist_head l2tp_ip6_bind_table; }; struct l2tp_ip6_sock { /* inet_sock has to be the first member of l2tp_ip6_sock */ struct inet_sock inet; u32 conn_id; u32 peer_conn_id; struct ipv6_pinfo inet6; }; static struct l2tp_ip6_sock *l2tp_ip6_sk(const struct sock *sk) { return (struct l2tp_ip6_sock *)sk; } static struct l2tp_ip6_net *l2tp_ip6_pernet(const struct net *net) { return net_generic(net, l2tp_ip6_net_id); } static struct sock *__l2tp_ip6_bind_lookup(const struct net *net, const struct in6_addr *laddr, const struct in6_addr *raddr, int dif, u32 tunnel_id) { struct l2tp_ip6_net *pn = l2tp_ip6_pernet(net); struct sock *sk; sk_for_each_bound(sk, &pn->l2tp_ip6_bind_table) { const struct in6_addr *sk_laddr = inet6_rcv_saddr(sk); const struct in6_addr *sk_raddr = &sk->sk_v6_daddr; const struct l2tp_ip6_sock *l2tp = l2tp_ip6_sk(sk); int bound_dev_if; if (!net_eq(sock_net(sk), net)) continue; bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); if (bound_dev_if && dif && bound_dev_if != dif) continue; if (sk_laddr && !ipv6_addr_any(sk_laddr) && !ipv6_addr_any(laddr) && !ipv6_addr_equal(sk_laddr, laddr)) continue; if (!ipv6_addr_any(sk_raddr) && raddr && !ipv6_addr_any(raddr) && !ipv6_addr_equal(sk_raddr, raddr)) continue; if (l2tp->conn_id != tunnel_id) continue; goto found; } sk = NULL; found: return sk; } /* When processing receive frames, there are two cases to * consider. Data frames consist of a non-zero session-id and an * optional cookie. Control frames consist of a regular L2TP header * preceded by 32-bits of zeros. * * L2TPv3 Session Header Over IP * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Cookie (optional, maximum 64 bits)... * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * L2TPv3 Control Message Header Over IP * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | (32 bits of zeros) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |T|L|x|x|S|x|x|x|x|x|x|x| Ver | Length | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Control Connection ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Ns | Nr | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * All control frames are passed to userspace. */ static int l2tp_ip6_recv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); struct l2tp_ip6_net *pn; struct sock *sk; u32 session_id; u32 tunnel_id; unsigned char *ptr, *optr; struct l2tp_session *session; struct l2tp_tunnel *tunnel = NULL; struct ipv6hdr *iph; pn = l2tp_ip6_pernet(net); if (!pskb_may_pull(skb, 4)) goto discard; /* Point to L2TP header */ optr = skb->data; ptr = skb->data; session_id = ntohl(*((__be32 *)ptr)); ptr += 4; /* RFC3931: L2TP/IP packets have the first 4 bytes containing * the session_id. If it is 0, the packet is a L2TP control * frame and the session_id value can be discarded. */ if (session_id == 0) { __skb_pull(skb, 4); goto pass_up; } /* Ok, this is a data packet. Lookup the session. */ session = l2tp_v3_session_get(net, NULL, session_id); if (!session) goto discard; tunnel = session->tunnel; if (!tunnel) goto discard_sess; if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) goto discard_sess; l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_put(session); return 0; pass_up: /* Get the tunnel_id from the L2TP header */ if (!pskb_may_pull(skb, 12)) goto discard; if ((skb->data[0] & 0xc0) != 0xc0) goto discard; tunnel_id = ntohl(*(__be32 *)&skb->data[4]); iph = ipv6_hdr(skb); read_lock_bh(&pn->l2tp_ip6_lock); sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, &iph->saddr, inet6_iif(skb), tunnel_id); if (!sk) { read_unlock_bh(&pn->l2tp_ip6_lock); goto discard; } sock_hold(sk); read_unlock_bh(&pn->l2tp_ip6_lock); if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_put; nf_reset_ct(skb); return sk_receive_skb(sk, skb, 1); discard_sess: l2tp_session_put(session); goto discard; discard_put: sock_put(sk); discard: kfree_skb(skb); return 0; } static int l2tp_ip6_hash(struct sock *sk) { struct l2tp_ip6_net *pn = l2tp_ip6_pernet(sock_net(sk)); if (sk_unhashed(sk)) { write_lock_bh(&pn->l2tp_ip6_lock); sk_add_node(sk, &pn->l2tp_ip6_table); write_unlock_bh(&pn->l2tp_ip6_lock); } return 0; } static void l2tp_ip6_unhash(struct sock *sk) { struct l2tp_ip6_net *pn = l2tp_ip6_pernet(sock_net(sk)); if (sk_unhashed(sk)) return; write_lock_bh(&pn->l2tp_ip6_lock); sk_del_node_init(sk); write_unlock_bh(&pn->l2tp_ip6_lock); } static int l2tp_ip6_open(struct sock *sk) { /* Prevent autobind. We don't have ports. */ inet_sk(sk)->inet_num = IPPROTO_L2TP; l2tp_ip6_hash(sk); return 0; } static void l2tp_ip6_close(struct sock *sk, long timeout) { struct l2tp_ip6_net *pn = l2tp_ip6_pernet(sock_net(sk)); write_lock_bh(&pn->l2tp_ip6_lock); hlist_del_init(&sk->sk_bind_node); sk_del_node_init(sk); write_unlock_bh(&pn->l2tp_ip6_lock); sk_common_release(sk); } static void l2tp_ip6_destroy_sock(struct sock *sk) { struct l2tp_tunnel *tunnel; lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) { l2tp_tunnel_delete(tunnel); l2tp_tunnel_put(tunnel); } } static int l2tp_ip6_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_l2tpip6 *addr = (struct sockaddr_l2tpip6 *)uaddr; struct net *net = sock_net(sk); struct l2tp_ip6_net *pn; __be32 v4addr = 0; int bound_dev_if; int addr_type; int err; pn = l2tp_ip6_pernet(net); if (addr->l2tp_family != AF_INET6) return -EINVAL; if (addr_len < sizeof(*addr)) return -EINVAL; addr_type = ipv6_addr_type(&addr->l2tp_addr); /* l2tp_ip6 sockets are IPv6 only */ if (addr_type == IPV6_ADDR_MAPPED) return -EADDRNOTAVAIL; /* L2TP is point-point, not multicast */ if (addr_type & IPV6_ADDR_MULTICAST) return -EADDRNOTAVAIL; lock_sock(sk); err = -EINVAL; if (!sock_flag(sk, SOCK_ZAPPED)) goto out_unlock; if (sk->sk_state != TCP_CLOSE) goto out_unlock; bound_dev_if = sk->sk_bound_dev_if; /* Check if the address belongs to the host. */ rcu_read_lock(); if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; if (addr_type & IPV6_ADDR_LINKLOCAL) { if (addr->l2tp_scope_id) bound_dev_if = addr->l2tp_scope_id; /* Binding to link-local address requires an * interface. */ if (!bound_dev_if) goto out_unlock_rcu; err = -ENODEV; dev = dev_get_by_index_rcu(sock_net(sk), bound_dev_if); if (!dev) goto out_unlock_rcu; } /* ipv4 addr of the socket is invalid. Only the * unspecified and mapped address have a v4 equivalent. */ v4addr = LOOPBACK4_IPV6; err = -EADDRNOTAVAIL; if (!ipv6_chk_addr(sock_net(sk), &addr->l2tp_addr, dev, 0)) goto out_unlock_rcu; } rcu_read_unlock(); write_lock_bh(&pn->l2tp_ip6_lock); if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, NULL, bound_dev_if, addr->l2tp_conn_id)) { write_unlock_bh(&pn->l2tp_ip6_lock); err = -EADDRINUSE; goto out_unlock; } inet->inet_saddr = v4addr; inet->inet_rcv_saddr = v4addr; sk->sk_bound_dev_if = bound_dev_if; sk->sk_v6_rcv_saddr = addr->l2tp_addr; np->saddr = addr->l2tp_addr; l2tp_ip6_sk(sk)->conn_id = addr->l2tp_conn_id; sk_add_bind_node(sk, &pn->l2tp_ip6_bind_table); sk_del_node_init(sk); write_unlock_bh(&pn->l2tp_ip6_lock); sock_reset_flag(sk, SOCK_ZAPPED); release_sock(sk); return 0; out_unlock_rcu: rcu_read_unlock(); out_unlock: release_sock(sk); return err; } static int l2tp_ip6_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)uaddr; struct sockaddr_in6 *usin = (struct sockaddr_in6 *)uaddr; struct in6_addr *daddr; int addr_type; int rc; struct l2tp_ip6_net *pn; if (addr_len < sizeof(*lsa)) return -EINVAL; if (usin->sin6_family != AF_INET6) return -EINVAL; addr_type = ipv6_addr_type(&usin->sin6_addr); if (addr_type & IPV6_ADDR_MULTICAST) return -EINVAL; if (addr_type & IPV6_ADDR_MAPPED) { daddr = &usin->sin6_addr; if (ipv4_is_multicast(daddr->s6_addr32[3])) return -EINVAL; } lock_sock(sk); /* Must bind first - autobinding does not work */ if (sock_flag(sk, SOCK_ZAPPED)) { rc = -EINVAL; goto out_sk; } rc = __ip6_datagram_connect(sk, uaddr, addr_len); if (rc < 0) goto out_sk; l2tp_ip6_sk(sk)->peer_conn_id = lsa->l2tp_conn_id; pn = l2tp_ip6_pernet(sock_net(sk)); write_lock_bh(&pn->l2tp_ip6_lock); hlist_del_init(&sk->sk_bind_node); sk_add_bind_node(sk, &pn->l2tp_ip6_bind_table); write_unlock_bh(&pn->l2tp_ip6_lock); out_sk: release_sock(sk); return rc; } static int l2tp_ip6_disconnect(struct sock *sk, int flags) { if (sock_flag(sk, SOCK_ZAPPED)) return 0; return __udp_disconnect(sk, flags); } static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)uaddr; struct sock *sk = sock->sk; struct ipv6_pinfo *np = inet6_sk(sk); struct l2tp_ip6_sock *lsk = l2tp_ip6_sk(sk); lsa->l2tp_family = AF_INET6; lsa->l2tp_flowinfo = 0; lsa->l2tp_scope_id = 0; lsa->l2tp_unused = 0; if (peer) { if (!lsk->peer_conn_id) return -ENOTCONN; lsa->l2tp_conn_id = lsk->peer_conn_id; lsa->l2tp_addr = sk->sk_v6_daddr; if (inet6_test_bit(SNDFLOW, sk)) lsa->l2tp_flowinfo = np->flow_label; } else { if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) lsa->l2tp_addr = np->saddr; else lsa->l2tp_addr = sk->sk_v6_rcv_saddr; lsa->l2tp_conn_id = lsk->conn_id; } if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL) lsa->l2tp_scope_id = READ_ONCE(sk->sk_bound_dev_if); return sizeof(*lsa); } static int l2tp_ip6_backlog_recv(struct sock *sk, struct sk_buff *skb) { int rc; /* Charge it to the socket, dropping if the queue is full. */ rc = sock_queue_rcv_skb(sk, skb); if (rc < 0) goto drop; return 0; drop: IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS); kfree_skb(skb); return -1; } static int l2tp_ip6_push_pending_frames(struct sock *sk) { struct sk_buff *skb; __be32 *transhdr = NULL; int err = 0; skb = skb_peek(&sk->sk_write_queue); if (!skb) goto out; transhdr = (__be32 *)skb_transport_header(skb); *transhdr = 0; err = ip6_push_pending_frames(sk); out: return err; } /* Userspace will call sendmsg() on the tunnel socket to send L2TP * control frames. */ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions opt_space; DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_txoptions *opt_to_free = NULL; struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; struct dst_entry *dst = NULL; struct flowi6 fl6; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; int transhdrlen = 4; /* zero session-id */ int ulen; int err; /* Rough check on arithmetic overflow, * better check is made in ip6_append_data(). */ if (len > INT_MAX - transhdrlen) return -EMSGSIZE; /* Mirror BSD error message compatibility */ if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; /* Get and verify the address */ memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_mark = READ_ONCE(sk->sk_mark); fl6.flowi6_uid = sk_uid(sk); ipcm6_init_sk(&ipc6, sk); if (lsa) { if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (lsa->l2tp_family && lsa->l2tp_family != AF_INET6) return -EAFNOSUPPORT; daddr = &lsa->l2tp_addr; if (inet6_test_bit(SNDFLOW, sk)) { fl6.flowlabel = lsa->l2tp_flowinfo & IPV6_FLOWINFO_MASK; if (fl6.flowlabel & IPV6_FLOWLABEL_MASK) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } } /* Otherwise it will be difficult to maintain * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && lsa->l2tp_scope_id && ipv6_addr_type(daddr) & IPV6_ADDR_LINKLOCAL) fl6.flowi6_oif = lsa->l2tp_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; } if (fl6.flowi6_oif == 0) fl6.flowi6_oif = READ_ONCE(sk->sk_bound_dev_if); if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); ipc6.opt = opt; err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6); if (err < 0) { fl6_sock_release(flowlabel); return err; } if ((fl6.flowlabel & IPV6_FLOWLABEL_MASK) && !flowlabel) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } if (!(opt->opt_nflen | opt->opt_flen)) opt = NULL; } if (!opt) { opt = txopt_get(np); opt_to_free = opt; } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); ipc6.opt = opt; fl6.flowi6_proto = sk->sk_protocol; if (!ipv6_addr_any(daddr)) fl6.daddr = *daddr; else fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) fl6.saddr = np->saddr; final_p = fl6_update_dst(&fl6, opt, &final); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = READ_ONCE(np->mcast_oif); else if (!fl6.flowi6_oif) fl6.flowi6_oif = READ_ONCE(np->ucast_oif); security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6)); fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; } if (ipc6.hlimit < 0) ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); if (msg->msg_flags & MSG_CONFIRM) goto do_confirm; back_from_confirm: lock_sock(sk); ulen = len + (skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0); err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen, transhdrlen, &ipc6, &fl6, dst_rt6_info(dst), msg->msg_flags); if (err) ip6_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) err = l2tp_ip6_push_pending_frames(sk); release_sock(sk); done: dst_release(dst); out: fl6_sock_release(flowlabel); txopt_put(opt_to_free); return err < 0 ? err : len; do_confirm: if (msg->msg_flags & MSG_PROBE) dst_confirm_neigh(dst, &fl6.daddr); if (!(msg->msg_flags & MSG_PROBE) || len) goto back_from_confirm; err = 0; goto done; } static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name); size_t copied = 0; int err = -EOPNOTSUPP; struct sk_buff *skb; if (flags & MSG_OOB) goto out; if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, &err); if (!skb) goto out; copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto done; sock_recv_timestamp(msg, sk, skb); /* Copy the address. */ if (lsa) { lsa->l2tp_family = AF_INET6; lsa->l2tp_unused = 0; lsa->l2tp_addr = ipv6_hdr(skb)->saddr; lsa->l2tp_flowinfo = 0; lsa->l2tp_scope_id = 0; lsa->l2tp_conn_id = 0; if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL) lsa->l2tp_scope_id = inet6_iif(skb); *addr_len = sizeof(*lsa); } if (np->rxopt.all) ip6_datagram_recv_ctl(sk, msg, skb); if (flags & MSG_TRUNC) copied = skb->len; done: skb_free_datagram(sk, skb); out: return err ? err : copied; } static struct proto l2tp_ip6_prot = { .name = "L2TP/IPv6", .owner = THIS_MODULE, .init = l2tp_ip6_open, .close = l2tp_ip6_close, .bind = l2tp_ip6_bind, .connect = l2tp_ip6_connect, .disconnect = l2tp_ip6_disconnect, .ioctl = l2tp_ioctl, .destroy = l2tp_ip6_destroy_sock, .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .sendmsg = l2tp_ip6_sendmsg, .recvmsg = l2tp_ip6_recvmsg, .backlog_rcv = l2tp_ip6_backlog_recv, .hash = l2tp_ip6_hash, .unhash = l2tp_ip6_unhash, .obj_size = sizeof(struct l2tp_ip6_sock), .ipv6_pinfo_offset = offsetof(struct l2tp_ip6_sock, inet6), }; static const struct proto_ops l2tp_ip6_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, .connect = inet_dgram_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = l2tp_ip6_getname, .poll = datagram_poll, .ioctl = inet6_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = inet_shutdown, .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif }; static struct inet_protosw l2tp_ip6_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_L2TP, .prot = &l2tp_ip6_prot, .ops = &l2tp_ip6_ops, }; static struct inet6_protocol l2tp_ip6_protocol __read_mostly = { .handler = l2tp_ip6_recv, }; static __net_init int l2tp_ip6_init_net(struct net *net) { struct l2tp_ip6_net *pn = net_generic(net, l2tp_ip6_net_id); rwlock_init(&pn->l2tp_ip6_lock); INIT_HLIST_HEAD(&pn->l2tp_ip6_table); INIT_HLIST_HEAD(&pn->l2tp_ip6_bind_table); return 0; } static __net_exit void l2tp_ip6_exit_net(struct net *net) { struct l2tp_ip6_net *pn = l2tp_ip6_pernet(net); write_lock_bh(&pn->l2tp_ip6_lock); WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip6_table) != 0); WARN_ON_ONCE(hlist_count_nodes(&pn->l2tp_ip6_bind_table) != 0); write_unlock_bh(&pn->l2tp_ip6_lock); } static struct pernet_operations l2tp_ip6_net_ops = { .init = l2tp_ip6_init_net, .exit = l2tp_ip6_exit_net, .id = &l2tp_ip6_net_id, .size = sizeof(struct l2tp_ip6_net), }; static int __init l2tp_ip6_init(void) { int err; pr_info("L2TP IP encapsulation support for IPv6 (L2TPv3)\n"); err = register_pernet_device(&l2tp_ip6_net_ops); if (err) goto out; err = proto_register(&l2tp_ip6_prot, 1); if (err != 0) goto out1; err = inet6_add_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP); if (err) goto out2; inet6_register_protosw(&l2tp_ip6_protosw); return 0; out2: proto_unregister(&l2tp_ip6_prot); out1: unregister_pernet_device(&l2tp_ip6_net_ops); out: return err; } static void __exit l2tp_ip6_exit(void) { inet6_unregister_protosw(&l2tp_ip6_protosw); inet6_del_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP); proto_unregister(&l2tp_ip6_prot); unregister_pernet_device(&l2tp_ip6_net_ops); } module_init(l2tp_ip6_init); module_exit(l2tp_ip6_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Chris Elston <celston@katalix.com>"); MODULE_DESCRIPTION("L2TP IP encapsulation for IPv6"); MODULE_VERSION("1.0"); /* Use the values of SOCK_DGRAM (2) as type and IPPROTO_L2TP (115) as protocol, * because __stringify doesn't like enums */ MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 115, 2); MODULE_ALIAS_NET_PF_PROTO(PF_INET6, 115); |
| 13 13 13 13 11 13 12 12 13 12 12 13 13 2 2 13 11 11 10 1 6 10 8 10 5 9 8 7 6 3 10 6 3 5 5 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <net/xdp_sock_drv.h> #include "netlink.h" #include "common.h" struct channels_req_info { struct ethnl_req_info base; }; struct channels_reply_data { struct ethnl_reply_data base; struct ethtool_channels channels; }; #define CHANNELS_REPDATA(__reply_base) \ container_of(__reply_base, struct channels_reply_data, base) const struct nla_policy ethnl_channels_get_policy[] = { [ETHTOOL_A_CHANNELS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), }; static int channels_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct channels_reply_data *data = CHANNELS_REPDATA(reply_base); struct net_device *dev = reply_base->dev; int ret; if (!dev->ethtool_ops->get_channels) return -EOPNOTSUPP; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; dev->ethtool_ops->get_channels(dev, &data->channels); ethnl_ops_complete(dev); return 0; } static int channels_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { return nla_total_size(sizeof(u32)) + /* _CHANNELS_RX_MAX */ nla_total_size(sizeof(u32)) + /* _CHANNELS_TX_MAX */ nla_total_size(sizeof(u32)) + /* _CHANNELS_OTHER_MAX */ nla_total_size(sizeof(u32)) + /* _CHANNELS_COMBINED_MAX */ nla_total_size(sizeof(u32)) + /* _CHANNELS_RX_COUNT */ nla_total_size(sizeof(u32)) + /* _CHANNELS_TX_COUNT */ nla_total_size(sizeof(u32)) + /* _CHANNELS_OTHER_COUNT */ nla_total_size(sizeof(u32)); /* _CHANNELS_COMBINED_COUNT */ } static int channels_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct channels_reply_data *data = CHANNELS_REPDATA(reply_base); const struct ethtool_channels *channels = &data->channels; if ((channels->max_rx && (nla_put_u32(skb, ETHTOOL_A_CHANNELS_RX_MAX, channels->max_rx) || nla_put_u32(skb, ETHTOOL_A_CHANNELS_RX_COUNT, channels->rx_count))) || (channels->max_tx && (nla_put_u32(skb, ETHTOOL_A_CHANNELS_TX_MAX, channels->max_tx) || nla_put_u32(skb, ETHTOOL_A_CHANNELS_TX_COUNT, channels->tx_count))) || (channels->max_other && (nla_put_u32(skb, ETHTOOL_A_CHANNELS_OTHER_MAX, channels->max_other) || nla_put_u32(skb, ETHTOOL_A_CHANNELS_OTHER_COUNT, channels->other_count))) || (channels->max_combined && (nla_put_u32(skb, ETHTOOL_A_CHANNELS_COMBINED_MAX, channels->max_combined) || nla_put_u32(skb, ETHTOOL_A_CHANNELS_COMBINED_COUNT, channels->combined_count)))) return -EMSGSIZE; return 0; } /* CHANNELS_SET */ const struct nla_policy ethnl_channels_set_policy[] = { [ETHTOOL_A_CHANNELS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_CHANNELS_RX_COUNT] = { .type = NLA_U32 }, [ETHTOOL_A_CHANNELS_TX_COUNT] = { .type = NLA_U32 }, [ETHTOOL_A_CHANNELS_OTHER_COUNT] = { .type = NLA_U32 }, [ETHTOOL_A_CHANNELS_COMBINED_COUNT] = { .type = NLA_U32 }, }; static int ethnl_set_channels_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; return ops->get_channels && ops->set_channels ? 1 : -EOPNOTSUPP; } static int ethnl_set_channels(struct ethnl_req_info *req_info, struct genl_info *info) { unsigned int from_channel, old_total, i; bool mod = false, mod_combined = false; struct net_device *dev = req_info->dev; struct ethtool_channels channels = {}; struct nlattr **tb = info->attrs; u32 err_attr; int ret; dev->ethtool_ops->get_channels(dev, &channels); old_total = channels.combined_count + max(channels.rx_count, channels.tx_count); ethnl_update_u32(&channels.rx_count, tb[ETHTOOL_A_CHANNELS_RX_COUNT], &mod); ethnl_update_u32(&channels.tx_count, tb[ETHTOOL_A_CHANNELS_TX_COUNT], &mod); ethnl_update_u32(&channels.other_count, tb[ETHTOOL_A_CHANNELS_OTHER_COUNT], &mod); ethnl_update_u32(&channels.combined_count, tb[ETHTOOL_A_CHANNELS_COMBINED_COUNT], &mod_combined); mod |= mod_combined; if (!mod) return 0; /* ensure new channel counts are within limits */ if (channels.rx_count > channels.max_rx) err_attr = ETHTOOL_A_CHANNELS_RX_COUNT; else if (channels.tx_count > channels.max_tx) err_attr = ETHTOOL_A_CHANNELS_TX_COUNT; else if (channels.other_count > channels.max_other) err_attr = ETHTOOL_A_CHANNELS_OTHER_COUNT; else if (channels.combined_count > channels.max_combined) err_attr = ETHTOOL_A_CHANNELS_COMBINED_COUNT; else err_attr = 0; if (err_attr) { NL_SET_ERR_MSG_ATTR(info->extack, tb[err_attr], "requested channel count exceeds maximum"); return -EINVAL; } /* ensure there is at least one RX and one TX channel */ if (!channels.combined_count && !channels.rx_count) err_attr = ETHTOOL_A_CHANNELS_RX_COUNT; else if (!channels.combined_count && !channels.tx_count) err_attr = ETHTOOL_A_CHANNELS_TX_COUNT; else err_attr = 0; if (err_attr) { if (mod_combined) err_attr = ETHTOOL_A_CHANNELS_COMBINED_COUNT; NL_SET_ERR_MSG_ATTR(info->extack, tb[err_attr], "requested channel counts would result in no RX or TX channel being configured"); return -EINVAL; } ret = ethtool_check_max_channel(dev, channels, info); if (ret) return ret; /* Disabling channels, query zero-copy AF_XDP sockets */ from_channel = channels.combined_count + min(channels.rx_count, channels.tx_count); for (i = from_channel; i < old_total; i++) if (xsk_get_pool_from_qid(dev, i)) { GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing zerocopy AF_XDP sockets"); return -EINVAL; } ret = dev->ethtool_ops->set_channels(dev, &channels); return ret < 0 ? ret : 1; } const struct ethnl_request_ops ethnl_channels_request_ops = { .request_cmd = ETHTOOL_MSG_CHANNELS_GET, .reply_cmd = ETHTOOL_MSG_CHANNELS_GET_REPLY, .hdr_attr = ETHTOOL_A_CHANNELS_HEADER, .req_info_size = sizeof(struct channels_req_info), .reply_data_size = sizeof(struct channels_reply_data), .prepare_data = channels_prepare_data, .reply_size = channels_reply_size, .fill_reply = channels_fill_reply, .set_validate = ethnl_set_channels_validate, .set = ethnl_set_channels, .set_ntf_cmd = ETHTOOL_MSG_CHANNELS_NTF, }; |
| 2 2 2 2 2 2 2 2 1 1 1 1 1 2 55 54 56 15 15 7 55 2 2 56 58 58 3 3 3 2 58 56 58 44 58 1 57 58 57 57 20 58 57 58 19 8 1 8 8 8 5 8 1 8 56 58 24 24 24 65 65 64 65 65 64 64 19 51 51 50 51 1 51 51 51 48 48 48 50 50 49 49 4 4 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ALSA sequencer Memory Manager * Copyright (c) 1998 by Frank van de Pol <fvdpol@coil.demon.nl> * Jaroslav Kysela <perex@perex.cz> * 2000 by Takashi Iwai <tiwai@suse.de> */ #include <linux/init.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/mm.h> #include <sound/core.h> #include <sound/seq_kernel.h> #include "seq_memory.h" #include "seq_queue.h" #include "seq_info.h" #include "seq_lock.h" static inline int snd_seq_pool_available(struct snd_seq_pool *pool) { return pool->total_elements - atomic_read(&pool->counter); } static inline int snd_seq_output_ok(struct snd_seq_pool *pool) { return snd_seq_pool_available(pool) >= pool->room; } /* * Variable length event: * The event like sysex uses variable length type. * The external data may be stored in three different formats. * 1) kernel space * This is the normal case. * ext.data.len = length * ext.data.ptr = buffer pointer * 2) user space * When an event is generated via read(), the external data is * kept in user space until expanded. * ext.data.len = length | SNDRV_SEQ_EXT_USRPTR * ext.data.ptr = userspace pointer * 3) chained cells * When the variable length event is enqueued (in prioq or fifo), * the external data is decomposed to several cells. * ext.data.len = length | SNDRV_SEQ_EXT_CHAINED * ext.data.ptr = the additiona cell head * -> cell.next -> cell.next -> .. */ /* * exported: * call dump function to expand external data. */ static int get_var_len(const struct snd_seq_event *event) { if ((event->flags & SNDRV_SEQ_EVENT_LENGTH_MASK) != SNDRV_SEQ_EVENT_LENGTH_VARIABLE) return -EINVAL; return event->data.ext.len & ~SNDRV_SEQ_EXT_MASK; } static int dump_var_event(const struct snd_seq_event *event, snd_seq_dump_func_t func, void *private_data, int offset, int maxlen) { int len, err; struct snd_seq_event_cell *cell; len = get_var_len(event); if (len <= 0) return len; if (len <= offset) return 0; if (maxlen && len > offset + maxlen) len = offset + maxlen; if (event->data.ext.len & SNDRV_SEQ_EXT_USRPTR) { char buf[32]; char __user *curptr = (char __force __user *)event->data.ext.ptr; curptr += offset; len -= offset; while (len > 0) { int size = sizeof(buf); if (len < size) size = len; if (copy_from_user(buf, curptr, size)) return -EFAULT; err = func(private_data, buf, size); if (err < 0) return err; curptr += size; len -= size; } return 0; } if (!(event->data.ext.len & SNDRV_SEQ_EXT_CHAINED)) return func(private_data, event->data.ext.ptr + offset, len - offset); cell = (struct snd_seq_event_cell *)event->data.ext.ptr; for (; len > 0 && cell; cell = cell->next) { int size = sizeof(struct snd_seq_event); char *curptr = (char *)&cell->event; if (offset >= size) { offset -= size; len -= size; continue; } if (len < size) size = len; err = func(private_data, curptr + offset, size - offset); if (err < 0) return err; offset = 0; len -= size; } return 0; } int snd_seq_dump_var_event(const struct snd_seq_event *event, snd_seq_dump_func_t func, void *private_data) { return dump_var_event(event, func, private_data, 0, 0); } EXPORT_SYMBOL(snd_seq_dump_var_event); /* * exported: * expand the variable length event to linear buffer space. */ static int seq_copy_in_kernel(void *ptr, void *src, int size) { char **bufptr = ptr; memcpy(*bufptr, src, size); *bufptr += size; return 0; } static int seq_copy_in_user(void *ptr, void *src, int size) { char __user **bufptr = ptr; if (copy_to_user(*bufptr, src, size)) return -EFAULT; *bufptr += size; return 0; } static int expand_var_event(const struct snd_seq_event *event, int offset, int size, char *buf, bool in_kernel) { if (event->data.ext.len & SNDRV_SEQ_EXT_USRPTR) { if (! in_kernel) return -EINVAL; if (copy_from_user(buf, (char __force __user *)event->data.ext.ptr + offset, size)) return -EFAULT; return 0; } return dump_var_event(event, in_kernel ? seq_copy_in_kernel : seq_copy_in_user, &buf, offset, size); } int snd_seq_expand_var_event(const struct snd_seq_event *event, int count, char *buf, int in_kernel, int size_aligned) { int len, newlen, err; len = get_var_len(event); if (len < 0) return len; newlen = len; if (size_aligned > 0) newlen = roundup(len, size_aligned); if (count < newlen) return -EAGAIN; err = expand_var_event(event, 0, len, buf, in_kernel); if (err < 0) return err; if (len != newlen) { if (in_kernel) memset(buf + len, 0, newlen - len); else if (clear_user((__force void __user *)buf + len, newlen - len)) return -EFAULT; } return newlen; } EXPORT_SYMBOL(snd_seq_expand_var_event); int snd_seq_expand_var_event_at(const struct snd_seq_event *event, int count, char *buf, int offset) { int len, err; len = get_var_len(event); if (len < 0) return len; if (len <= offset) return 0; len -= offset; if (len > count) len = count; err = expand_var_event(event, offset, count, buf, true); if (err < 0) return err; return len; } EXPORT_SYMBOL_GPL(snd_seq_expand_var_event_at); /* * release this cell, free extended data if available */ static inline void free_cell(struct snd_seq_pool *pool, struct snd_seq_event_cell *cell) { cell->next = pool->free; pool->free = cell; atomic_dec(&pool->counter); } void snd_seq_cell_free(struct snd_seq_event_cell * cell) { struct snd_seq_pool *pool; if (snd_BUG_ON(!cell)) return; pool = cell->pool; if (snd_BUG_ON(!pool)) return; guard(spinlock_irqsave)(&pool->lock); free_cell(pool, cell); if (snd_seq_ev_is_variable(&cell->event)) { if (cell->event.data.ext.len & SNDRV_SEQ_EXT_CHAINED) { struct snd_seq_event_cell *curp, *nextptr; curp = cell->event.data.ext.ptr; for (; curp; curp = nextptr) { nextptr = curp->next; curp->next = pool->free; free_cell(pool, curp); } } } if (waitqueue_active(&pool->output_sleep)) { /* has enough space now? */ if (snd_seq_output_ok(pool)) wake_up(&pool->output_sleep); } } /* * allocate an event cell. */ static int snd_seq_cell_alloc(struct snd_seq_pool *pool, struct snd_seq_event_cell **cellp, int nonblock, struct file *file, struct mutex *mutexp) { struct snd_seq_event_cell *cell; unsigned long flags; int err = -EAGAIN; wait_queue_entry_t wait; if (pool == NULL) return -EINVAL; *cellp = NULL; init_waitqueue_entry(&wait, current); spin_lock_irqsave(&pool->lock, flags); if (pool->ptr == NULL) { /* not initialized */ pr_debug("ALSA: seq: pool is not initialized\n"); err = -EINVAL; goto __error; } while (pool->free == NULL && ! nonblock && ! pool->closing) { set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&pool->output_sleep, &wait); spin_unlock_irqrestore(&pool->lock, flags); if (mutexp) mutex_unlock(mutexp); schedule(); if (mutexp) mutex_lock(mutexp); spin_lock_irqsave(&pool->lock, flags); remove_wait_queue(&pool->output_sleep, &wait); /* interrupted? */ if (signal_pending(current)) { err = -ERESTARTSYS; goto __error; } } if (pool->closing) { /* closing.. */ err = -ENOMEM; goto __error; } cell = pool->free; if (cell) { int used; pool->free = cell->next; atomic_inc(&pool->counter); used = atomic_read(&pool->counter); if (pool->max_used < used) pool->max_used = used; pool->event_alloc_success++; /* clear cell pointers */ cell->next = NULL; err = 0; } else pool->event_alloc_failures++; *cellp = cell; __error: spin_unlock_irqrestore(&pool->lock, flags); return err; } /* * duplicate the event to a cell. * if the event has external data, the data is decomposed to additional * cells. */ int snd_seq_event_dup(struct snd_seq_pool *pool, struct snd_seq_event *event, struct snd_seq_event_cell **cellp, int nonblock, struct file *file, struct mutex *mutexp) { int ncells, err; unsigned int extlen; struct snd_seq_event_cell *cell; int size; *cellp = NULL; ncells = 0; extlen = 0; if (snd_seq_ev_is_variable(event)) { extlen = event->data.ext.len & ~SNDRV_SEQ_EXT_MASK; ncells = DIV_ROUND_UP(extlen, sizeof(struct snd_seq_event)); } if (ncells >= pool->total_elements) return -ENOMEM; err = snd_seq_cell_alloc(pool, &cell, nonblock, file, mutexp); if (err < 0) return err; /* copy the event */ size = snd_seq_event_packet_size(event); memcpy(&cell->ump, event, size); #if IS_ENABLED(CONFIG_SND_SEQ_UMP) if (size < sizeof(cell->event)) cell->ump.raw.extra = 0; #endif /* decompose */ if (snd_seq_ev_is_variable(event)) { int len = extlen; int is_chained = event->data.ext.len & SNDRV_SEQ_EXT_CHAINED; int is_usrptr = event->data.ext.len & SNDRV_SEQ_EXT_USRPTR; struct snd_seq_event_cell *src, *tmp, *tail; char *buf; cell->event.data.ext.len = extlen | SNDRV_SEQ_EXT_CHAINED; cell->event.data.ext.ptr = NULL; src = (struct snd_seq_event_cell *)event->data.ext.ptr; buf = (char *)event->data.ext.ptr; tail = NULL; while (ncells-- > 0) { size = sizeof(struct snd_seq_event); if (len < size) size = len; err = snd_seq_cell_alloc(pool, &tmp, nonblock, file, mutexp); if (err < 0) goto __error; if (cell->event.data.ext.ptr == NULL) cell->event.data.ext.ptr = tmp; if (tail) tail->next = tmp; tail = tmp; /* copy chunk */ if (is_chained && src) { tmp->event = src->event; src = src->next; } else if (is_usrptr) { if (copy_from_user(&tmp->event, (char __force __user *)buf, size)) { err = -EFAULT; goto __error; } } else { memcpy(&tmp->event, buf, size); } buf += size; len -= size; } } *cellp = cell; return 0; __error: snd_seq_cell_free(cell); return err; } /* poll wait */ int snd_seq_pool_poll_wait(struct snd_seq_pool *pool, struct file *file, poll_table *wait) { poll_wait(file, &pool->output_sleep, wait); guard(spinlock_irq)(&pool->lock); return snd_seq_output_ok(pool); } /* allocate room specified number of events */ int snd_seq_pool_init(struct snd_seq_pool *pool) { int cell; struct snd_seq_event_cell *cellptr; if (snd_BUG_ON(!pool)) return -EINVAL; cellptr = kvmalloc_array(pool->size, sizeof(struct snd_seq_event_cell), GFP_KERNEL); if (!cellptr) return -ENOMEM; /* add new cells to the free cell list */ guard(spinlock_irq)(&pool->lock); if (pool->ptr) { kvfree(cellptr); return 0; } pool->ptr = cellptr; pool->free = NULL; for (cell = 0; cell < pool->size; cell++) { cellptr = pool->ptr + cell; cellptr->pool = pool; cellptr->next = pool->free; pool->free = cellptr; } pool->room = (pool->size + 1) / 2; /* init statistics */ pool->max_used = 0; pool->total_elements = pool->size; return 0; } /* refuse the further insertion to the pool */ void snd_seq_pool_mark_closing(struct snd_seq_pool *pool) { if (snd_BUG_ON(!pool)) return; guard(spinlock_irqsave)(&pool->lock); pool->closing = 1; } /* remove events */ int snd_seq_pool_done(struct snd_seq_pool *pool) { struct snd_seq_event_cell *ptr; if (snd_BUG_ON(!pool)) return -EINVAL; /* wait for closing all threads */ if (waitqueue_active(&pool->output_sleep)) wake_up(&pool->output_sleep); while (atomic_read(&pool->counter) > 0) schedule_timeout_uninterruptible(1); /* release all resources */ scoped_guard(spinlock_irq, &pool->lock) { ptr = pool->ptr; pool->ptr = NULL; pool->free = NULL; pool->total_elements = 0; } kvfree(ptr); guard(spinlock_irq)(&pool->lock); pool->closing = 0; return 0; } /* init new memory pool */ struct snd_seq_pool *snd_seq_pool_new(int poolsize) { struct snd_seq_pool *pool; /* create pool block */ pool = kzalloc(sizeof(*pool), GFP_KERNEL); if (!pool) return NULL; spin_lock_init(&pool->lock); pool->ptr = NULL; pool->free = NULL; pool->total_elements = 0; atomic_set(&pool->counter, 0); pool->closing = 0; init_waitqueue_head(&pool->output_sleep); pool->size = poolsize; /* init statistics */ pool->max_used = 0; return pool; } /* remove memory pool */ int snd_seq_pool_delete(struct snd_seq_pool **ppool) { struct snd_seq_pool *pool = *ppool; *ppool = NULL; if (pool == NULL) return 0; snd_seq_pool_mark_closing(pool); snd_seq_pool_done(pool); kfree(pool); return 0; } /* exported to seq_clientmgr.c */ void snd_seq_info_pool(struct snd_info_buffer *buffer, struct snd_seq_pool *pool, char *space) { if (pool == NULL) return; snd_iprintf(buffer, "%sPool size : %d\n", space, pool->total_elements); snd_iprintf(buffer, "%sCells in use : %d\n", space, atomic_read(&pool->counter)); snd_iprintf(buffer, "%sPeak cells in use : %d\n", space, pool->max_used); snd_iprintf(buffer, "%sAlloc success : %d\n", space, pool->event_alloc_success); snd_iprintf(buffer, "%sAlloc failures : %d\n", space, pool->event_alloc_failures); } |
| 9 9 9 9 9 9 9 9 9 4 3 9 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Scatterlist Cryptographic API. * * Procfs information. * * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> * Copyright (c) 2005 Herbert Xu <herbert@gondor.apana.org.au> */ #include <linux/atomic.h> #include <linux/init.h> #include <linux/crypto.h> #include <linux/fips.h> #include <linux/module.h> /* for module_name() */ #include <linux/rwsem.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include "internal.h" static void *c_start(struct seq_file *m, loff_t *pos) { down_read(&crypto_alg_sem); return seq_list_start(&crypto_alg_list, *pos); } static void *c_next(struct seq_file *m, void *p, loff_t *pos) { return seq_list_next(p, &crypto_alg_list, pos); } static void c_stop(struct seq_file *m, void *p) { up_read(&crypto_alg_sem); } static int c_show(struct seq_file *m, void *p) { struct crypto_alg *alg = list_entry(p, struct crypto_alg, cra_list); seq_printf(m, "name : %s\n", alg->cra_name); seq_printf(m, "driver : %s\n", alg->cra_driver_name); seq_printf(m, "module : %s\n", module_name(alg->cra_module)); seq_printf(m, "priority : %d\n", alg->cra_priority); seq_printf(m, "refcnt : %u\n", refcount_read(&alg->cra_refcnt)); seq_printf(m, "selftest : %s\n", (alg->cra_flags & CRYPTO_ALG_TESTED) ? "passed" : "unknown"); seq_printf(m, "internal : %s\n", str_yes_no(alg->cra_flags & CRYPTO_ALG_INTERNAL)); if (fips_enabled) seq_printf(m, "fips : %s\n", str_no_yes(alg->cra_flags & CRYPTO_ALG_FIPS_INTERNAL)); if (alg->cra_flags & CRYPTO_ALG_LARVAL) { seq_printf(m, "type : larval\n"); seq_printf(m, "flags : 0x%x\n", alg->cra_flags); goto out; } if (alg->cra_type && alg->cra_type->show) { alg->cra_type->show(m, alg); goto out; } switch (alg->cra_flags & CRYPTO_ALG_TYPE_MASK) { case CRYPTO_ALG_TYPE_CIPHER: seq_printf(m, "type : cipher\n"); seq_printf(m, "blocksize : %u\n", alg->cra_blocksize); seq_printf(m, "min keysize : %u\n", alg->cra_cipher.cia_min_keysize); seq_printf(m, "max keysize : %u\n", alg->cra_cipher.cia_max_keysize); break; default: seq_printf(m, "type : unknown\n"); break; } out: seq_putc(m, '\n'); return 0; } static const struct seq_operations crypto_seq_ops = { .start = c_start, .next = c_next, .stop = c_stop, .show = c_show }; void __init crypto_init_proc(void) { proc_create_seq("crypto", 0, NULL, &crypto_seq_ops); } void __exit crypto_exit_proc(void) { remove_proc_entry("crypto", NULL); } |
| 1 10 3 3 20 23 22 7 3 3 2 | 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* L2TP internal definitions. * * Copyright (c) 2008,2009 Katalix Systems Ltd */ #include <linux/refcount.h> #ifndef _L2TP_CORE_H_ #define _L2TP_CORE_H_ #include <net/dst.h> #include <net/sock.h> #ifdef CONFIG_XFRM #include <net/xfrm.h> #endif /* Random numbers used for internal consistency checks of tunnel and session structures */ #define L2TP_SESSION_MAGIC 0x0C04EB7D struct sk_buff; struct l2tp_stats { atomic_long_t tx_packets; atomic_long_t tx_bytes; atomic_long_t tx_errors; atomic_long_t rx_packets; atomic_long_t rx_bytes; atomic_long_t rx_seq_discards; atomic_long_t rx_oos_packets; atomic_long_t rx_errors; atomic_long_t rx_cookie_discards; atomic_long_t rx_invalid; }; struct l2tp_tunnel; /* L2TP session configuration */ struct l2tp_session_cfg { enum l2tp_pwtype pw_type; unsigned int recv_seq:1; /* expect receive packets with sequence numbers? */ unsigned int send_seq:1; /* send packets with sequence numbers? */ unsigned int lns_mode:1; /* behave as LNS? * LAC enables sequence numbers under LNS control. */ u16 l2specific_type; /* Layer 2 specific type */ u8 cookie[8]; /* optional cookie */ int cookie_len; /* 0, 4 or 8 bytes */ u8 peer_cookie[8]; /* peer's cookie */ int peer_cookie_len; /* 0, 4 or 8 bytes */ int reorder_timeout; /* configured reorder timeout (in jiffies) */ char *ifname; }; struct l2tp_session_coll_list { spinlock_t lock; /* for access to list */ struct list_head list; refcount_t ref_count; }; /* Represents a session (pseudowire) instance. * Tracks runtime state including cookies, dataplane packet sequencing, and IO statistics. * Is linked into a per-tunnel session list and a per-net ("global") IDR tree. */ #define L2TP_SESSION_NAME_MAX 32 struct l2tp_session { int magic; /* should be L2TP_SESSION_MAGIC */ long dead; struct rcu_head rcu; struct l2tp_tunnel *tunnel; /* back pointer to tunnel context */ u32 session_id; u32 peer_session_id; u8 cookie[8]; int cookie_len; u8 peer_cookie[8]; int peer_cookie_len; u16 l2specific_type; u16 hdr_len; u32 nr; /* session NR state (receive) */ u32 ns; /* session NR state (send) */ struct sk_buff_head reorder_q; /* receive reorder queue */ u32 nr_max; /* max NR. Depends on tunnel */ u32 nr_window_size; /* NR window size */ u32 nr_oos; /* NR of last OOS packet */ int nr_oos_count; /* for OOS recovery */ int nr_oos_count_max; struct list_head list; /* per-tunnel list node */ refcount_t ref_count; struct hlist_node hlist; /* per-net session hlist */ unsigned long hlist_key; /* key for session hlist */ struct l2tp_session_coll_list *coll_list; /* session collision list */ struct list_head clist; /* for coll_list */ char name[L2TP_SESSION_NAME_MAX]; /* for logging */ char ifname[IFNAMSIZ]; unsigned int recv_seq:1; /* expect receive packets with sequence numbers? */ unsigned int send_seq:1; /* send packets with sequence numbers? */ unsigned int lns_mode:1; /* behave as LNS? * LAC enables sequence numbers under LNS control. */ int reorder_timeout; /* configured reorder timeout (in jiffies) */ int reorder_skip; /* set if skip to next nr */ enum l2tp_pwtype pwtype; struct l2tp_stats stats; struct work_struct del_work; /* Session receive handler for data packets. * Each pseudowire implementation should implement this callback in order to * handle incoming packets. Packets are passed to the pseudowire handler after * reordering, if data sequence numbers are enabled for the session. */ void (*recv_skb)(struct l2tp_session *session, struct sk_buff *skb, int data_len); /* Session close handler. * Each pseudowire implementation may implement this callback in order to carry * out pseudowire-specific shutdown actions. * The callback is called by core after unlisting the session and purging its * reorder queue. */ void (*session_close)(struct l2tp_session *session); /* Session show handler. * Pseudowire-specific implementation of debugfs session rendering. * The callback is called by l2tp_debugfs.c after rendering core session * information. */ void (*show)(struct seq_file *m, void *priv); u8 priv[]; /* private data */ }; /* L2TP tunnel configuration */ struct l2tp_tunnel_cfg { enum l2tp_encap_type encap; /* Used only for kernel-created sockets */ struct in_addr local_ip; struct in_addr peer_ip; #if IS_ENABLED(CONFIG_IPV6) struct in6_addr *local_ip6; struct in6_addr *peer_ip6; #endif u16 local_udp_port; u16 peer_udp_port; unsigned int use_udp_checksums:1, udp6_zero_tx_checksums:1, udp6_zero_rx_checksums:1; }; /* Represents a tunnel instance. * Tracks runtime state including IO statistics. * Holds the tunnel socket (either passed from userspace or directly created by the kernel). * Maintains a list of sessions belonging to the tunnel instance. * Is linked into a per-net list of tunnels. */ #define L2TP_TUNNEL_NAME_MAX 20 struct l2tp_tunnel { unsigned long dead; struct rcu_head rcu; spinlock_t list_lock; /* write-protection for session_list */ bool acpt_newsess; /* indicates whether this tunnel accepts * new sessions. Protected by list_lock. */ struct list_head session_list; /* list of sessions */ u32 tunnel_id; u32 peer_tunnel_id; int version; /* 2=>L2TPv2, 3=>L2TPv3 */ char name[L2TP_TUNNEL_NAME_MAX]; /* for logging */ enum l2tp_encap_type encap; struct l2tp_stats stats; struct net *l2tp_net; /* the net we belong to */ refcount_t ref_count; struct sock *sock; /* parent socket */ int fd; /* parent fd, if tunnel socket was created * by userspace */ struct work_struct del_work; }; /* Pseudowire ops callbacks for use with the l2tp genetlink interface */ struct l2tp_nl_cmd_ops { /* The pseudowire session create callback is responsible for creating a session * instance for a specific pseudowire type. * It must call l2tp_session_create and l2tp_session_register to register the * session instance, as well as carry out any pseudowire-specific initialisation. * It must return >= 0 on success, or an appropriate negative errno value on failure. */ int (*session_create)(struct net *net, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg); /* The pseudowire session delete callback is responsible for initiating the deletion * of a session instance. * It must call l2tp_session_delete, as well as carry out any pseudowire-specific * teardown actions. */ void (*session_delete)(struct l2tp_session *session); }; static inline void *l2tp_session_priv(struct l2tp_session *session) { return &session->priv[0]; } /* Tunnel and session refcounts */ void l2tp_tunnel_put(struct l2tp_tunnel *tunnel); void l2tp_session_put(struct l2tp_session *session); /* Tunnel and session lookup. * These functions take a reference on the instances they return, so * the caller must ensure that the reference is dropped appropriately. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id); struct l2tp_tunnel *l2tp_tunnel_get_next(const struct net *net, unsigned long *key); struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id); struct l2tp_session *l2tp_v2_session_get(const struct net *net, u16 tunnel_id, u16 session_id); struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, int pver, u32 tunnel_id, u32 session_id); struct l2tp_session *l2tp_session_get_next(const struct net *net, struct sock *sk, int pver, u32 tunnel_id, unsigned long *key); struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, const char *ifname); /* Tunnel and session lifetime management. * Creation of a new instance is a two-step process: create, then register. * Destruction is triggered using the *_delete functions, and completes asynchronously. */ int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp); int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, struct l2tp_tunnel_cfg *cfg); void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel); struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg); int l2tp_session_register(struct l2tp_session *session, struct l2tp_tunnel *tunnel); void l2tp_session_delete(struct l2tp_session *session); /* Receive path helpers. If data sequencing is enabled for the session these * functions handle queuing and reordering prior to passing packets to the * pseudowire code to be passed to userspace. */ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, int length); int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb); /* Transmit path helpers for sending packets over the tunnel socket. */ void l2tp_session_set_header_len(struct l2tp_session *session, int version, enum l2tp_encap_type encap); int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb); /* Pseudowire management. * Pseudowires should register with l2tp core on module init, and unregister * on module exit. */ int l2tp_nl_register_ops(enum l2tp_pwtype pw_type, const struct l2tp_nl_cmd_ops *ops); void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type); /* IOCTL helper for IP encap modules. */ int l2tp_ioctl(struct sock *sk, int cmd, int *karg); struct l2tp_tunnel *l2tp_sk_to_tunnel(const struct sock *sk); static inline int l2tp_get_l2specific_len(struct l2tp_session *session) { switch (session->l2specific_type) { case L2TP_L2SPECTYPE_DEFAULT: return 4; case L2TP_L2SPECTYPE_NONE: default: return 0; } } static inline u32 l2tp_tunnel_dst_mtu(const struct l2tp_tunnel *tunnel) { struct dst_entry *dst; u32 mtu; dst = sk_dst_get(tunnel->sock); if (!dst) return 0; mtu = dst_mtu(dst); dst_release(dst); return mtu; } #ifdef CONFIG_XFRM static inline bool l2tp_tunnel_uses_xfrm(const struct l2tp_tunnel *tunnel) { struct sock *sk = tunnel->sock; return sk && (rcu_access_pointer(sk->sk_policy[0]) || rcu_access_pointer(sk->sk_policy[1])); } #else static inline bool l2tp_tunnel_uses_xfrm(const struct l2tp_tunnel *tunnel) { return false; } #endif static inline int l2tp_v3_ensure_opt_in_linear(struct l2tp_session *session, struct sk_buff *skb, unsigned char **ptr, unsigned char **optr) { int opt_len = session->peer_cookie_len + l2tp_get_l2specific_len(session); if (opt_len > 0) { int off = *ptr - *optr; if (!pskb_may_pull(skb, off + opt_len)) return -1; if (skb->data != *optr) { *optr = skb->data; *ptr = skb->data + off; } } return 0; } #define MODULE_ALIAS_L2TP_PWTYPE(type) \ MODULE_ALIAS("net-l2tp-type-" __stringify(type)) #endif /* _L2TP_CORE_H_ */ |
| 169 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BLK_STAT_H #define BLK_STAT_H #include <linux/kernel.h> #include <linux/blkdev.h> #include <linux/ktime.h> #include <linux/rcupdate.h> #include <linux/timer.h> /** * struct blk_stat_callback - Block statistics callback. * * A &struct blk_stat_callback is associated with a &struct request_queue. While * @timer is active, that queue's request completion latencies are sorted into * buckets by @bucket_fn and added to a per-cpu buffer, @cpu_stat. When the * timer fires, @cpu_stat is flushed to @stat and @timer_fn is invoked. */ struct blk_stat_callback { /* * @list: RCU list of callbacks for a &struct request_queue. */ struct list_head list; /** * @timer: Timer for the next callback invocation. */ struct timer_list timer; /** * @cpu_stat: Per-cpu statistics buckets. */ struct blk_rq_stat __percpu *cpu_stat; /** * @bucket_fn: Given a request, returns which statistics bucket it * should be accounted under. Return -1 for no bucket for this * request. */ int (*bucket_fn)(const struct request *); /** * @buckets: Number of statistics buckets. */ unsigned int buckets; /** * @stat: Array of statistics buckets. */ struct blk_rq_stat *stat; /** * @fn: Callback function. */ void (*timer_fn)(struct blk_stat_callback *); /** * @data: Private pointer for the user. */ void *data; struct rcu_head rcu; }; struct blk_queue_stats *blk_alloc_queue_stats(void); void blk_free_queue_stats(struct blk_queue_stats *); void blk_stat_add(struct request *rq, u64 now); /* record time/size info in request but not add a callback */ void blk_stat_enable_accounting(struct request_queue *q); void blk_stat_disable_accounting(struct request_queue *q); /** * blk_stat_alloc_callback() - Allocate a block statistics callback. * @timer_fn: Timer callback function. * @bucket_fn: Bucket callback function. * @buckets: Number of statistics buckets. * @data: Value for the @data field of the &struct blk_stat_callback. * * See &struct blk_stat_callback for details on the callback functions. * * Return: &struct blk_stat_callback on success or NULL on ENOMEM. */ struct blk_stat_callback * blk_stat_alloc_callback(void (*timer_fn)(struct blk_stat_callback *), int (*bucket_fn)(const struct request *), unsigned int buckets, void *data); /** * blk_stat_add_callback() - Add a block statistics callback to be run on a * request queue. * @q: The request queue. * @cb: The callback. * * Note that a single &struct blk_stat_callback can only be added to a single * &struct request_queue. */ void blk_stat_add_callback(struct request_queue *q, struct blk_stat_callback *cb); /** * blk_stat_remove_callback() - Remove a block statistics callback from a * request queue. * @q: The request queue. * @cb: The callback. * * When this returns, the callback is not running on any CPUs and will not be * called again unless readded. */ void blk_stat_remove_callback(struct request_queue *q, struct blk_stat_callback *cb); /** * blk_stat_free_callback() - Free a block statistics callback. * @cb: The callback. * * @cb may be NULL, in which case this does nothing. If it is not NULL, @cb must * not be associated with a request queue. I.e., if it was previously added with * blk_stat_add_callback(), it must also have been removed since then with * blk_stat_remove_callback(). */ void blk_stat_free_callback(struct blk_stat_callback *cb); /** * blk_stat_is_active() - Check if a block statistics callback is currently * gathering statistics. * @cb: The callback. */ static inline bool blk_stat_is_active(struct blk_stat_callback *cb) { return timer_pending(&cb->timer); } /** * blk_stat_activate_nsecs() - Gather block statistics during a time window in * nanoseconds. * @cb: The callback. * @nsecs: Number of nanoseconds to gather statistics for. * * The timer callback will be called when the window expires. */ static inline void blk_stat_activate_nsecs(struct blk_stat_callback *cb, u64 nsecs) { mod_timer(&cb->timer, jiffies + nsecs_to_jiffies(nsecs)); } static inline void blk_stat_deactivate(struct blk_stat_callback *cb) { timer_delete_sync(&cb->timer); } /** * blk_stat_activate_msecs() - Gather block statistics during a time window in * milliseconds. * @cb: The callback. * @msecs: Number of milliseconds to gather statistics for. * * The timer callback will be called when the window expires. */ static inline void blk_stat_activate_msecs(struct blk_stat_callback *cb, unsigned int msecs) { mod_timer(&cb->timer, jiffies + msecs_to_jiffies(msecs)); } void blk_rq_stat_add(struct blk_rq_stat *, u64); void blk_rq_stat_sum(struct blk_rq_stat *, struct blk_rq_stat *); void blk_rq_stat_init(struct blk_rq_stat *); #endif |
| 22 22 22 22 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fence-chain: chain fences together in a timeline * * Copyright (C) 2018 Advanced Micro Devices, Inc. * Authors: * Christian König <christian.koenig@amd.com> */ #include <linux/dma-fence-chain.h> static bool dma_fence_chain_enable_signaling(struct dma_fence *fence); /** * dma_fence_chain_get_prev - use RCU to get a reference to the previous fence * @chain: chain node to get the previous node from * * Use dma_fence_get_rcu_safe to get a reference to the previous fence of the * chain node. */ static struct dma_fence *dma_fence_chain_get_prev(struct dma_fence_chain *chain) { struct dma_fence *prev; rcu_read_lock(); prev = dma_fence_get_rcu_safe(&chain->prev); rcu_read_unlock(); return prev; } /** * dma_fence_chain_walk - chain walking function * @fence: current chain node * * Walk the chain to the next node. Returns the next fence or NULL if we are at * the end of the chain. Garbage collects chain nodes which are already * signaled. */ struct dma_fence *dma_fence_chain_walk(struct dma_fence *fence) { struct dma_fence_chain *chain, *prev_chain; struct dma_fence *prev, *replacement, *tmp; chain = to_dma_fence_chain(fence); if (!chain) { dma_fence_put(fence); return NULL; } while ((prev = dma_fence_chain_get_prev(chain))) { prev_chain = to_dma_fence_chain(prev); if (prev_chain) { if (!dma_fence_is_signaled(prev_chain->fence)) break; replacement = dma_fence_chain_get_prev(prev_chain); } else { if (!dma_fence_is_signaled(prev)) break; replacement = NULL; } tmp = unrcu_pointer(cmpxchg(&chain->prev, RCU_INITIALIZER(prev), RCU_INITIALIZER(replacement))); if (tmp == prev) dma_fence_put(tmp); else dma_fence_put(replacement); dma_fence_put(prev); } dma_fence_put(fence); return prev; } EXPORT_SYMBOL(dma_fence_chain_walk); /** * dma_fence_chain_find_seqno - find fence chain node by seqno * @pfence: pointer to the chain node where to start * @seqno: the sequence number to search for * * Advance the fence pointer to the chain node which will signal this sequence * number. If no sequence number is provided then this is a no-op. * * Returns EINVAL if the fence is not a chain node or the sequence number has * not yet advanced far enough. */ int dma_fence_chain_find_seqno(struct dma_fence **pfence, uint64_t seqno) { struct dma_fence_chain *chain; if (!seqno) return 0; chain = to_dma_fence_chain(*pfence); if (!chain || chain->base.seqno < seqno) return -EINVAL; dma_fence_chain_for_each(*pfence, &chain->base) { if ((*pfence)->context != chain->base.context || to_dma_fence_chain(*pfence)->prev_seqno < seqno) break; } dma_fence_put(&chain->base); return 0; } EXPORT_SYMBOL(dma_fence_chain_find_seqno); static const char *dma_fence_chain_get_driver_name(struct dma_fence *fence) { return "dma_fence_chain"; } static const char *dma_fence_chain_get_timeline_name(struct dma_fence *fence) { return "unbound"; } static void dma_fence_chain_irq_work(struct irq_work *work) { struct dma_fence_chain *chain; chain = container_of(work, typeof(*chain), work); /* Try to rearm the callback */ if (!dma_fence_chain_enable_signaling(&chain->base)) /* Ok, we are done. No more unsignaled fences left */ dma_fence_signal(&chain->base); dma_fence_put(&chain->base); } static void dma_fence_chain_cb(struct dma_fence *f, struct dma_fence_cb *cb) { struct dma_fence_chain *chain; chain = container_of(cb, typeof(*chain), cb); init_irq_work(&chain->work, dma_fence_chain_irq_work); irq_work_queue(&chain->work); dma_fence_put(f); } static bool dma_fence_chain_enable_signaling(struct dma_fence *fence) { struct dma_fence_chain *head = to_dma_fence_chain(fence); dma_fence_get(&head->base); dma_fence_chain_for_each(fence, &head->base) { struct dma_fence *f = dma_fence_chain_contained(fence); dma_fence_get(f); if (!dma_fence_add_callback(f, &head->cb, dma_fence_chain_cb)) { dma_fence_put(fence); return true; } dma_fence_put(f); } dma_fence_put(&head->base); return false; } static bool dma_fence_chain_signaled(struct dma_fence *fence) { dma_fence_chain_for_each(fence, fence) { struct dma_fence *f = dma_fence_chain_contained(fence); if (!dma_fence_is_signaled(f)) { dma_fence_put(fence); return false; } } return true; } static void dma_fence_chain_release(struct dma_fence *fence) { struct dma_fence_chain *chain = to_dma_fence_chain(fence); struct dma_fence *prev; /* Manually unlink the chain as much as possible to avoid recursion * and potential stack overflow. */ while ((prev = rcu_dereference_protected(chain->prev, true))) { struct dma_fence_chain *prev_chain; if (kref_read(&prev->refcount) > 1) break; prev_chain = to_dma_fence_chain(prev); if (!prev_chain) break; /* No need for atomic operations since we hold the last * reference to prev_chain. */ chain->prev = prev_chain->prev; RCU_INIT_POINTER(prev_chain->prev, NULL); dma_fence_put(prev); } dma_fence_put(prev); dma_fence_put(chain->fence); dma_fence_free(fence); } static void dma_fence_chain_set_deadline(struct dma_fence *fence, ktime_t deadline) { dma_fence_chain_for_each(fence, fence) { struct dma_fence *f = dma_fence_chain_contained(fence); dma_fence_set_deadline(f, deadline); } } const struct dma_fence_ops dma_fence_chain_ops = { .get_driver_name = dma_fence_chain_get_driver_name, .get_timeline_name = dma_fence_chain_get_timeline_name, .enable_signaling = dma_fence_chain_enable_signaling, .signaled = dma_fence_chain_signaled, .release = dma_fence_chain_release, .set_deadline = dma_fence_chain_set_deadline, }; EXPORT_SYMBOL(dma_fence_chain_ops); /** * dma_fence_chain_init - initialize a fence chain * @chain: the chain node to initialize * @prev: the previous fence * @fence: the current fence * @seqno: the sequence number to use for the fence chain * * Initialize a new chain node and either start a new chain or add the node to * the existing chain of the previous fence. */ void dma_fence_chain_init(struct dma_fence_chain *chain, struct dma_fence *prev, struct dma_fence *fence, uint64_t seqno) { struct dma_fence_chain *prev_chain = to_dma_fence_chain(prev); uint64_t context; spin_lock_init(&chain->lock); rcu_assign_pointer(chain->prev, prev); chain->fence = fence; chain->prev_seqno = 0; /* Try to reuse the context of the previous chain node. */ if (prev_chain && __dma_fence_is_later(prev, seqno, prev->seqno)) { context = prev->context; chain->prev_seqno = prev->seqno; } else { context = dma_fence_context_alloc(1); /* Make sure that we always have a valid sequence number. */ if (prev_chain) seqno = max(prev->seqno, seqno); } dma_fence_init64(&chain->base, &dma_fence_chain_ops, &chain->lock, context, seqno); /* * Chaining dma_fence_chain container together is only allowed through * the prev fence and not through the contained fence. * * The correct way of handling this is to flatten out the fence * structure into a dma_fence_array by the caller instead. */ WARN_ON(dma_fence_is_chain(fence)); } EXPORT_SYMBOL(dma_fence_chain_init); |
| 11 11 7 7 7 7 7 7 6 1 7 7 7 7 4 11 11 11 11 7 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later // // Special handling for implicit feedback mode // #include <linux/init.h> #include <linux/usb.h> #include <linux/usb/audio.h> #include <linux/usb/audio-v2.h> #include <sound/core.h> #include <sound/pcm.h> #include <sound/pcm_params.h> #include "usbaudio.h" #include "card.h" #include "helper.h" #include "pcm.h" #include "implicit.h" enum { IMPLICIT_FB_NONE, IMPLICIT_FB_GENERIC, IMPLICIT_FB_FIXED, IMPLICIT_FB_BOTH, /* generic playback + capture (for BOSS) */ }; struct snd_usb_implicit_fb_match { unsigned int id; unsigned int iface_class; unsigned int ep_num; unsigned int iface; int type; }; #define IMPLICIT_FB_GENERIC_DEV(vend, prod) \ { .id = USB_ID(vend, prod), .type = IMPLICIT_FB_GENERIC } #define IMPLICIT_FB_FIXED_DEV(vend, prod, ep, ifnum) \ { .id = USB_ID(vend, prod), .type = IMPLICIT_FB_FIXED, .ep_num = (ep),\ .iface = (ifnum) } #define IMPLICIT_FB_BOTH_DEV(vend, prod, ep, ifnum) \ { .id = USB_ID(vend, prod), .type = IMPLICIT_FB_BOTH, .ep_num = (ep),\ .iface = (ifnum) } #define IMPLICIT_FB_SKIP_DEV(vend, prod) \ { .id = USB_ID(vend, prod), .type = IMPLICIT_FB_NONE } /* Implicit feedback quirk table for playback */ static const struct snd_usb_implicit_fb_match playback_implicit_fb_quirks[] = { /* Fixed EP */ /* FIXME: check the availability of generic matching */ IMPLICIT_FB_FIXED_DEV(0x0763, 0x2030, 0x81, 3), /* M-Audio Fast Track C400 */ IMPLICIT_FB_FIXED_DEV(0x0763, 0x2031, 0x81, 3), /* M-Audio Fast Track C600 */ IMPLICIT_FB_FIXED_DEV(0x0763, 0x2080, 0x81, 2), /* M-Audio FastTrack Ultra */ IMPLICIT_FB_FIXED_DEV(0x0763, 0x2081, 0x81, 2), /* M-Audio FastTrack Ultra */ IMPLICIT_FB_FIXED_DEV(0x2466, 0x8010, 0x81, 2), /* Fractal Audio Axe-Fx III */ IMPLICIT_FB_FIXED_DEV(0x31e9, 0x0001, 0x81, 2), /* Solid State Logic SSL2 */ IMPLICIT_FB_FIXED_DEV(0x31e9, 0x0002, 0x81, 2), /* Solid State Logic SSL2+ */ IMPLICIT_FB_FIXED_DEV(0x0499, 0x172f, 0x81, 2), /* Steinberg UR22C */ IMPLICIT_FB_FIXED_DEV(0x0d9a, 0x00df, 0x81, 2), /* RTX6001 */ IMPLICIT_FB_FIXED_DEV(0x19f7, 0x000a, 0x84, 3), /* RODE AI-1 */ IMPLICIT_FB_FIXED_DEV(0x22f0, 0x0006, 0x81, 3), /* Allen&Heath Qu-16 */ IMPLICIT_FB_FIXED_DEV(0x1686, 0xf029, 0x82, 2), /* Zoom UAC-2 */ IMPLICIT_FB_FIXED_DEV(0x2466, 0x8003, 0x86, 2), /* Fractal Audio Axe-Fx II */ IMPLICIT_FB_FIXED_DEV(0x0499, 0x172a, 0x86, 2), /* Yamaha MODX */ /* Special matching */ { .id = USB_ID(0x07fd, 0x0004), .iface_class = USB_CLASS_AUDIO, .type = IMPLICIT_FB_NONE }, /* MicroBook IIc */ /* ep = 0x84, ifnum = 0 */ { .id = USB_ID(0x07fd, 0x0004), .iface_class = USB_CLASS_VENDOR_SPEC, .type = IMPLICIT_FB_FIXED, .ep_num = 0x84, .iface = 0 }, /* MOTU MicroBook II */ {} /* terminator */ }; /* Implicit feedback quirk table for capture: only FIXED type */ static const struct snd_usb_implicit_fb_match capture_implicit_fb_quirks[] = { {} /* terminator */ }; /* set up sync EP information on the audioformat */ static int add_implicit_fb_sync_ep(struct snd_usb_audio *chip, struct audioformat *fmt, int ep, int ep_idx, int ifnum, const struct usb_host_interface *alts) { struct usb_interface *iface; if (!alts) { iface = usb_ifnum_to_if(chip->dev, ifnum); if (!iface || iface->num_altsetting < 2) return 0; alts = &iface->altsetting[1]; } fmt->sync_ep = ep; fmt->sync_iface = ifnum; fmt->sync_altsetting = alts->desc.bAlternateSetting; fmt->sync_ep_idx = ep_idx; fmt->implicit_fb = 1; usb_audio_dbg(chip, "%d:%d: added %s implicit_fb sync_ep %x, iface %d:%d\n", fmt->iface, fmt->altsetting, (ep & USB_DIR_IN) ? "playback" : "capture", fmt->sync_ep, fmt->sync_iface, fmt->sync_altsetting); return 1; } /* Check whether the given UAC2 iface:altset points to an implicit fb source */ static int add_generic_uac2_implicit_fb(struct snd_usb_audio *chip, struct audioformat *fmt, unsigned int ifnum, unsigned int altsetting) { struct usb_host_interface *alts; struct usb_endpoint_descriptor *epd; alts = snd_usb_get_host_interface(chip, ifnum, altsetting); if (!alts) return 0; if (alts->desc.bInterfaceClass != USB_CLASS_AUDIO || alts->desc.bInterfaceSubClass != USB_SUBCLASS_AUDIOSTREAMING || alts->desc.bInterfaceProtocol != UAC_VERSION_2 || alts->desc.bNumEndpoints < 1) return 0; epd = get_endpoint(alts, 0); if (!usb_endpoint_is_isoc_in(epd) || (epd->bmAttributes & USB_ENDPOINT_USAGE_MASK) != USB_ENDPOINT_USAGE_IMPLICIT_FB) return 0; return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress, 0, ifnum, alts); } static bool roland_sanity_check_iface(struct usb_host_interface *alts) { if (alts->desc.bInterfaceClass != USB_CLASS_VENDOR_SPEC || (alts->desc.bInterfaceSubClass != 2 && alts->desc.bInterfaceProtocol != 2) || alts->desc.bNumEndpoints < 1) return false; return true; } /* Like the UAC2 case above, but specific to Roland with vendor class and hack */ static int add_roland_implicit_fb(struct snd_usb_audio *chip, struct audioformat *fmt, struct usb_host_interface *alts) { struct usb_endpoint_descriptor *epd; if (!roland_sanity_check_iface(alts)) return 0; /* only when both streams are with ASYNC type */ epd = get_endpoint(alts, 0); if (!usb_endpoint_is_isoc_out(epd) || (epd->bmAttributes & USB_ENDPOINT_SYNCTYPE) != USB_ENDPOINT_SYNC_ASYNC) return 0; /* check capture EP */ alts = snd_usb_get_host_interface(chip, alts->desc.bInterfaceNumber + 1, alts->desc.bAlternateSetting); if (!alts || !roland_sanity_check_iface(alts)) return 0; epd = get_endpoint(alts, 0); if (!usb_endpoint_is_isoc_in(epd) || (epd->bmAttributes & USB_ENDPOINT_SYNCTYPE) != USB_ENDPOINT_SYNC_ASYNC) return 0; chip->quirk_flags |= QUIRK_FLAG_PLAYBACK_FIRST; return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress, 0, alts->desc.bInterfaceNumber, alts); } /* capture quirk for Roland device; always full-duplex */ static int add_roland_capture_quirk(struct snd_usb_audio *chip, struct audioformat *fmt, struct usb_host_interface *alts) { struct usb_endpoint_descriptor *epd; if (!roland_sanity_check_iface(alts)) return 0; epd = get_endpoint(alts, 0); if (!usb_endpoint_is_isoc_in(epd) || (epd->bmAttributes & USB_ENDPOINT_SYNCTYPE) != USB_ENDPOINT_SYNC_ASYNC) return 0; alts = snd_usb_get_host_interface(chip, alts->desc.bInterfaceNumber - 1, alts->desc.bAlternateSetting); if (!alts || !roland_sanity_check_iface(alts)) return 0; epd = get_endpoint(alts, 0); if (!usb_endpoint_is_isoc_out(epd)) return 0; return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress, 0, alts->desc.bInterfaceNumber, alts); } /* Playback and capture EPs on Pioneer devices share the same iface/altset * for the implicit feedback operation */ static bool is_pioneer_implicit_fb(struct snd_usb_audio *chip, struct usb_host_interface *alts) { struct usb_endpoint_descriptor *epd; if (USB_ID_VENDOR(chip->usb_id) != 0x2b73 && USB_ID_VENDOR(chip->usb_id) != 0x08e4) return false; if (alts->desc.bInterfaceClass != USB_CLASS_VENDOR_SPEC) return false; if (alts->desc.bNumEndpoints != 2) return false; epd = get_endpoint(alts, 0); if (!usb_endpoint_is_isoc_out(epd) || (epd->bmAttributes & USB_ENDPOINT_SYNCTYPE) != USB_ENDPOINT_SYNC_ASYNC) return false; epd = get_endpoint(alts, 1); if (!usb_endpoint_is_isoc_in(epd) || (epd->bmAttributes & USB_ENDPOINT_SYNCTYPE) != USB_ENDPOINT_SYNC_ASYNC || ((epd->bmAttributes & USB_ENDPOINT_USAGE_MASK) != USB_ENDPOINT_USAGE_DATA && (epd->bmAttributes & USB_ENDPOINT_USAGE_MASK) != USB_ENDPOINT_USAGE_IMPLICIT_FB)) return false; return true; } static int __add_generic_implicit_fb(struct snd_usb_audio *chip, struct audioformat *fmt, int iface, int altset) { struct usb_host_interface *alts; struct usb_endpoint_descriptor *epd; alts = snd_usb_get_host_interface(chip, iface, altset); if (!alts) return 0; if ((alts->desc.bInterfaceClass != USB_CLASS_VENDOR_SPEC && alts->desc.bInterfaceClass != USB_CLASS_AUDIO) || alts->desc.bNumEndpoints < 1) return 0; epd = get_endpoint(alts, 0); if (!usb_endpoint_is_isoc_in(epd) || (epd->bmAttributes & USB_ENDPOINT_SYNCTYPE) != USB_ENDPOINT_SYNC_ASYNC) return 0; return add_implicit_fb_sync_ep(chip, fmt, epd->bEndpointAddress, 0, iface, alts); } /* More generic quirk: look for the sync EP next to the data EP */ static int add_generic_implicit_fb(struct snd_usb_audio *chip, struct audioformat *fmt, struct usb_host_interface *alts) { if ((fmt->ep_attr & USB_ENDPOINT_SYNCTYPE) != USB_ENDPOINT_SYNC_ASYNC) return 0; if (__add_generic_implicit_fb(chip, fmt, alts->desc.bInterfaceNumber + 1, alts->desc.bAlternateSetting)) return 1; return __add_generic_implicit_fb(chip, fmt, alts->desc.bInterfaceNumber - 1, alts->desc.bAlternateSetting); } static const struct snd_usb_implicit_fb_match * find_implicit_fb_entry(struct snd_usb_audio *chip, const struct snd_usb_implicit_fb_match *match, const struct usb_host_interface *alts) { for (; match->id; match++) if (match->id == chip->usb_id && (!match->iface_class || (alts->desc.bInterfaceClass == match->iface_class))) return match; return NULL; } /* Setup an implicit feedback endpoint from a quirk. Returns 0 if no quirk * applies. Returns 1 if a quirk was found. */ static int audioformat_implicit_fb_quirk(struct snd_usb_audio *chip, struct audioformat *fmt, struct usb_host_interface *alts) { const struct snd_usb_implicit_fb_match *p; unsigned int attr = fmt->ep_attr & USB_ENDPOINT_SYNCTYPE; p = find_implicit_fb_entry(chip, playback_implicit_fb_quirks, alts); if (p) { switch (p->type) { case IMPLICIT_FB_GENERIC: return add_generic_implicit_fb(chip, fmt, alts); case IMPLICIT_FB_NONE: return 0; /* No quirk */ case IMPLICIT_FB_FIXED: return add_implicit_fb_sync_ep(chip, fmt, p->ep_num, 0, p->iface, NULL); } } /* Special handling for devices with capture quirks */ p = find_implicit_fb_entry(chip, capture_implicit_fb_quirks, alts); if (p) { switch (p->type) { case IMPLICIT_FB_FIXED: return 0; /* no quirk */ case IMPLICIT_FB_BOTH: chip->quirk_flags |= QUIRK_FLAG_PLAYBACK_FIRST; return add_generic_implicit_fb(chip, fmt, alts); } } /* Generic UAC2 implicit feedback */ if (attr == USB_ENDPOINT_SYNC_ASYNC && alts->desc.bInterfaceClass == USB_CLASS_AUDIO && alts->desc.bInterfaceProtocol == UAC_VERSION_2 && alts->desc.bNumEndpoints == 1) { if (add_generic_uac2_implicit_fb(chip, fmt, alts->desc.bInterfaceNumber + 1, alts->desc.bAlternateSetting)) return 1; } /* Roland/BOSS implicit feedback with vendor spec class */ if (USB_ID_VENDOR(chip->usb_id) == 0x0582) { if (add_roland_implicit_fb(chip, fmt, alts) > 0) return 1; } /* Pioneer devices with vendor spec class */ if (is_pioneer_implicit_fb(chip, alts)) { chip->quirk_flags |= QUIRK_FLAG_PLAYBACK_FIRST; return add_implicit_fb_sync_ep(chip, fmt, get_endpoint(alts, 1)->bEndpointAddress, 1, alts->desc.bInterfaceNumber, alts); } /* Try the generic implicit fb if available */ if (chip->generic_implicit_fb || (chip->quirk_flags & QUIRK_FLAG_GENERIC_IMPLICIT_FB)) return add_generic_implicit_fb(chip, fmt, alts); /* No quirk */ return 0; } /* same for capture, but only handling FIXED entry */ static int audioformat_capture_quirk(struct snd_usb_audio *chip, struct audioformat *fmt, struct usb_host_interface *alts) { const struct snd_usb_implicit_fb_match *p; p = find_implicit_fb_entry(chip, capture_implicit_fb_quirks, alts); if (p && (p->type == IMPLICIT_FB_FIXED || p->type == IMPLICIT_FB_BOTH)) return add_implicit_fb_sync_ep(chip, fmt, p->ep_num, 0, p->iface, NULL); /* Roland/BOSS need full-duplex streams */ if (USB_ID_VENDOR(chip->usb_id) == 0x0582) { if (add_roland_capture_quirk(chip, fmt, alts) > 0) return 1; } if (is_pioneer_implicit_fb(chip, alts)) return 1; /* skip the quirk, also don't handle generic sync EP */ return 0; } /* * Parse altset and set up implicit feedback endpoint on the audioformat */ int snd_usb_parse_implicit_fb_quirk(struct snd_usb_audio *chip, struct audioformat *fmt, struct usb_host_interface *alts) { if (chip->quirk_flags & QUIRK_FLAG_SKIP_IMPLICIT_FB) return 0; if (fmt->endpoint & USB_DIR_IN) return audioformat_capture_quirk(chip, fmt, alts); else return audioformat_implicit_fb_quirk(chip, fmt, alts); } /* * Return the score of matching two audioformats. * Veto the audioformat if: * - It has no channels for some reason. * - Requested PCM format is not supported. * - Requested sample rate is not supported. */ static int match_endpoint_audioformats(struct snd_usb_substream *subs, const struct audioformat *fp, int rate, int channels, snd_pcm_format_t pcm_format) { int i, score; if (fp->channels < 1) return 0; if (!(fp->formats & pcm_format_to_bits(pcm_format))) return 0; if (fp->rates & SNDRV_PCM_RATE_CONTINUOUS) { if (rate < fp->rate_min || rate > fp->rate_max) return 0; } else { for (i = 0; i < fp->nr_rates; i++) { if (fp->rate_table[i] == rate) break; } if (i >= fp->nr_rates) return 0; } score = 1; if (fp->channels == channels) score++; return score; } static struct snd_usb_substream * find_matching_substream(struct snd_usb_audio *chip, int stream, int ep_num, int fmt_type) { struct snd_usb_stream *as; struct snd_usb_substream *subs; list_for_each_entry(as, &chip->pcm_list, list) { subs = &as->substream[stream]; if (as->fmt_type == fmt_type && subs->ep_num == ep_num) return subs; } return NULL; } /* * Return the audioformat that is suitable for the implicit fb */ const struct audioformat * snd_usb_find_implicit_fb_sync_format(struct snd_usb_audio *chip, const struct audioformat *target, const struct snd_pcm_hw_params *params, int stream, bool *fixed_rate) { struct snd_usb_substream *subs; const struct audioformat *fp, *sync_fmt = NULL; int score, high_score; /* Use the original audioformat as fallback for the shared altset */ if (target->iface == target->sync_iface && target->altsetting == target->sync_altsetting) sync_fmt = target; subs = find_matching_substream(chip, stream, target->sync_ep, target->fmt_type); if (!subs) goto end; high_score = 0; list_for_each_entry(fp, &subs->fmt_list, list) { score = match_endpoint_audioformats(subs, fp, params_rate(params), params_channels(params), params_format(params)); if (score > high_score) { sync_fmt = fp; high_score = score; } } end: if (fixed_rate) *fixed_rate = snd_usb_pcm_has_fixed_rate(subs); return sync_fmt; } |
| 2 | 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 | // SPDX-License-Identifier: GPL-2.0-only /*************************************************************************** * Copyright (C) 2010-2012 by Bruno Prémont <bonbons@linux-vserver.org> * * * * Based on Logitech G13 driver (v0.4) * * Copyright (C) 2009 by Rick L. Vinyard, Jr. <rvinyard@cs.nmsu.edu> * * * ***************************************************************************/ #include <linux/hid.h> #include <linux/hid-debug.h> #include <linux/input.h> #include "hid-ids.h" #include <linux/fb.h> #include <linux/vmalloc.h> #include <linux/backlight.h> #include <linux/lcd.h> #include <linux/leds.h> #include <linux/seq_file.h> #include <linux/debugfs.h> #include <linux/completion.h> #include <linux/uaccess.h> #include <linux/module.h> #include <media/rc-core.h> #include "hid-picolcd.h" int picolcd_raw_cir(struct picolcd_data *data, struct hid_report *report, u8 *raw_data, int size) { unsigned long flags; int i, w, sz; struct ir_raw_event rawir = {}; /* ignore if rc_dev is NULL or status is shunned */ spin_lock_irqsave(&data->lock, flags); if (!data->rc_dev || (data->status & PICOLCD_CIR_SHUN)) { spin_unlock_irqrestore(&data->lock, flags); return 1; } spin_unlock_irqrestore(&data->lock, flags); /* PicoLCD USB packets contain 16-bit intervals in network order, * with value negated for pulse. Intervals are in microseconds. * * Note: some userspace LIRC code for PicoLCD says negated values * for space - is it a matter of IR chip? (pulse for my TSOP2236) * * In addition, the first interval seems to be around 15000 + base * interval for non-first report of IR data - thus the quirk below * to get RC_CODE to understand Sony and JVC remotes I have at hand */ sz = size > 0 ? min((int)raw_data[0], size-1) : 0; for (i = 0; i+1 < sz; i += 2) { w = (raw_data[i] << 8) | (raw_data[i+1]); rawir.pulse = !!(w & 0x8000); rawir.duration = rawir.pulse ? (65536 - w) : w; /* Quirk!! - see above */ if (i == 0 && rawir.duration > 15000) rawir.duration -= 15000; ir_raw_event_store(data->rc_dev, &rawir); } ir_raw_event_handle(data->rc_dev); return 1; } static int picolcd_cir_open(struct rc_dev *dev) { struct picolcd_data *data = dev->priv; unsigned long flags; spin_lock_irqsave(&data->lock, flags); data->status &= ~PICOLCD_CIR_SHUN; spin_unlock_irqrestore(&data->lock, flags); return 0; } static void picolcd_cir_close(struct rc_dev *dev) { struct picolcd_data *data = dev->priv; unsigned long flags; spin_lock_irqsave(&data->lock, flags); data->status |= PICOLCD_CIR_SHUN; spin_unlock_irqrestore(&data->lock, flags); } /* initialize CIR input device */ int picolcd_init_cir(struct picolcd_data *data, struct hid_report *report) { struct rc_dev *rdev; int ret = 0; rdev = rc_allocate_device(RC_DRIVER_IR_RAW); if (!rdev) return -ENOMEM; rdev->priv = data; rdev->allowed_protocols = RC_PROTO_BIT_ALL_IR_DECODER; rdev->open = picolcd_cir_open; rdev->close = picolcd_cir_close; rdev->device_name = data->hdev->name; rdev->input_phys = data->hdev->phys; rdev->input_id.bustype = data->hdev->bus; rdev->input_id.vendor = data->hdev->vendor; rdev->input_id.product = data->hdev->product; rdev->input_id.version = data->hdev->version; rdev->dev.parent = &data->hdev->dev; rdev->driver_name = PICOLCD_NAME; rdev->map_name = RC_MAP_RC6_MCE; rdev->timeout = MS_TO_US(100); rdev->rx_resolution = 1; ret = rc_register_device(rdev); if (ret) goto err; data->rc_dev = rdev; return 0; err: rc_free_device(rdev); return ret; } void picolcd_exit_cir(struct picolcd_data *data) { struct rc_dev *rdev = data->rc_dev; data->rc_dev = NULL; rc_unregister_device(rdev); } |
| 22 18 14 6 15 13 13 11 14 4 3 4 32 45 48 36 13 11 11 13 2 2 1 1 1 1 1 1459 12 1452 260 13 1226 114 6 3 3 19 19 487 483 10 10 4 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Generic nexthop implementation * * Copyright (c) 2017-19 Cumulus Networks * Copyright (c) 2017-19 David Ahern <dsa@cumulusnetworks.com> */ #ifndef __LINUX_NEXTHOP_H #define __LINUX_NEXTHOP_H #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/route.h> #include <linux/types.h> #include <net/ip_fib.h> #include <net/ip6_fib.h> #include <net/netlink.h> #define NEXTHOP_VALID_USER_FLAGS RTNH_F_ONLINK struct nexthop; struct nh_config { u32 nh_id; u8 nh_family; u8 nh_protocol; u8 nh_blackhole; u8 nh_fdb; u32 nh_flags; int nh_ifindex; struct net_device *dev; union { __be32 ipv4; struct in6_addr ipv6; } gw; struct nlattr *nh_grp; u16 nh_grp_type; u16 nh_grp_res_num_buckets; unsigned long nh_grp_res_idle_timer; unsigned long nh_grp_res_unbalanced_timer; bool nh_grp_res_has_num_buckets; bool nh_grp_res_has_idle_timer; bool nh_grp_res_has_unbalanced_timer; bool nh_hw_stats; struct nlattr *nh_encap; u16 nh_encap_type; u32 nlflags; struct nl_info nlinfo; }; struct nh_info { struct hlist_node dev_hash; /* entry on netns devhash */ struct nexthop *nh_parent; u8 family; bool reject_nh; bool fdb_nh; union { struct fib_nh_common fib_nhc; struct fib_nh fib_nh; struct fib6_nh fib6_nh; }; }; struct nh_res_bucket { struct nh_grp_entry __rcu *nh_entry; atomic_long_t used_time; unsigned long migrated_time; bool occupied; u8 nh_flags; }; struct nh_res_table { struct net *net; u32 nhg_id; struct delayed_work upkeep_dw; /* List of NHGEs that have too few buckets ("uw" for underweight). * Reclaimed buckets will be given to entries in this list. */ struct list_head uw_nh_entries; unsigned long unbalanced_since; u32 idle_timer; u32 unbalanced_timer; u16 num_nh_buckets; struct nh_res_bucket nh_buckets[] __counted_by(num_nh_buckets); }; struct nh_grp_entry_stats { u64_stats_t packets; struct u64_stats_sync syncp; }; struct nh_grp_entry { struct nexthop *nh; struct nh_grp_entry_stats __percpu *stats; u16 weight; union { struct { atomic_t upper_bound; } hthr; struct { /* Member on uw_nh_entries. */ struct list_head uw_nh_entry; u16 count_buckets; u16 wants_buckets; } res; }; struct list_head nh_list; struct nexthop *nh_parent; /* nexthop of group with this entry */ u64 packets_hw; }; struct nh_group { struct nh_group *spare; /* spare group for removals */ u16 num_nh; bool is_multipath; bool hash_threshold; bool resilient; bool fdb_nh; bool has_v4; bool hw_stats; struct nh_res_table __rcu *res_table; struct nh_grp_entry nh_entries[] __counted_by(num_nh); }; struct nexthop { struct rb_node rb_node; /* entry on netns rbtree */ struct list_head fi_list; /* v4 entries using nh */ struct list_head f6i_list; /* v6 entries using nh */ struct list_head fdb_list; /* fdb entries using this nh */ struct list_head grp_list; /* nh group entries using this nh */ struct net *net; u32 id; u8 protocol; /* app managing this nh */ u8 nh_flags; bool is_group; bool dead; spinlock_t lock; /* protect dead and f6i_list */ refcount_t refcnt; struct rcu_head rcu; union { struct nh_info __rcu *nh_info; struct nh_group __rcu *nh_grp; }; }; enum nexthop_event_type { NEXTHOP_EVENT_DEL, NEXTHOP_EVENT_REPLACE, NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE, NEXTHOP_EVENT_BUCKET_REPLACE, NEXTHOP_EVENT_HW_STATS_REPORT_DELTA, }; enum nh_notifier_info_type { NH_NOTIFIER_INFO_TYPE_SINGLE, NH_NOTIFIER_INFO_TYPE_GRP, NH_NOTIFIER_INFO_TYPE_RES_TABLE, NH_NOTIFIER_INFO_TYPE_RES_BUCKET, NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS, }; struct nh_notifier_single_info { struct net_device *dev; u8 gw_family; union { __be32 ipv4; struct in6_addr ipv6; }; u32 id; u8 is_reject:1, is_fdb:1, has_encap:1; }; struct nh_notifier_grp_entry_info { u16 weight; struct nh_notifier_single_info nh; }; struct nh_notifier_grp_info { u16 num_nh; bool is_fdb; bool hw_stats; struct nh_notifier_grp_entry_info nh_entries[] __counted_by(num_nh); }; struct nh_notifier_res_bucket_info { u16 bucket_index; unsigned int idle_timer_ms; bool force; struct nh_notifier_single_info old_nh; struct nh_notifier_single_info new_nh; }; struct nh_notifier_res_table_info { u16 num_nh_buckets; bool hw_stats; struct nh_notifier_single_info nhs[] __counted_by(num_nh_buckets); }; struct nh_notifier_grp_hw_stats_entry_info { u32 id; u64 packets; }; struct nh_notifier_grp_hw_stats_info { u16 num_nh; bool hw_stats_used; struct nh_notifier_grp_hw_stats_entry_info stats[] __counted_by(num_nh); }; struct nh_notifier_info { struct net *net; struct netlink_ext_ack *extack; u32 id; enum nh_notifier_info_type type; union { struct nh_notifier_single_info *nh; struct nh_notifier_grp_info *nh_grp; struct nh_notifier_res_table_info *nh_res_table; struct nh_notifier_res_bucket_info *nh_res_bucket; struct nh_notifier_grp_hw_stats_info *nh_grp_hw_stats; }; }; int register_nexthop_notifier(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); int __unregister_nexthop_notifier(struct net *net, struct notifier_block *nb); int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb); void nexthop_set_hw_flags(struct net *net, u32 id, bool offload, bool trap); void nexthop_bucket_set_hw_flags(struct net *net, u32 id, u16 bucket_index, bool offload, bool trap); void nexthop_res_grp_activity_update(struct net *net, u32 id, u16 num_buckets, unsigned long *activity); void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info, unsigned int nh_idx, u64 delta_packets); /* caller is holding rcu or rtnl; no reference taken to nexthop */ struct nexthop *nexthop_find_by_id(struct net *net, u32 id); void nexthop_free_rcu(struct rcu_head *head); static inline bool nexthop_get(struct nexthop *nh) { return refcount_inc_not_zero(&nh->refcnt); } static inline void nexthop_put(struct nexthop *nh) { if (refcount_dec_and_test(&nh->refcnt)) call_rcu_hurry(&nh->rcu, nexthop_free_rcu); } static inline bool nexthop_cmp(const struct nexthop *nh1, const struct nexthop *nh2) { return nh1 == nh2; } static inline bool nexthop_is_fdb(const struct nexthop *nh) { if (nh->is_group) { const struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); return nh_grp->fdb_nh; } else { const struct nh_info *nhi; nhi = rcu_dereference_rtnl(nh->nh_info); return nhi->fdb_nh; } } static inline bool nexthop_has_v4(const struct nexthop *nh) { if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); return nh_grp->has_v4; } return false; } static inline bool nexthop_is_multipath(const struct nexthop *nh) { if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); return nh_grp->is_multipath; } return false; } struct nexthop *nexthop_select_path(struct nexthop *nh, int hash); static inline unsigned int nexthop_num_path(const struct nexthop *nh) { unsigned int rc = 1; if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); if (nh_grp->is_multipath) rc = nh_grp->num_nh; } return rc; } static inline struct nexthop *nexthop_mpath_select(const struct nh_group *nhg, int nhsel) { /* for_nexthops macros in fib_semantics.c grabs a pointer to * the nexthop before checking nhsel */ if (nhsel >= nhg->num_nh) return NULL; return nhg->nh_entries[nhsel].nh; } static inline int nexthop_mpath_fill_node(struct sk_buff *skb, struct nexthop *nh, u8 rt_family) { struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp); int i; for (i = 0; i < nhg->num_nh; i++) { struct nexthop *nhe = nhg->nh_entries[i].nh; struct nh_info *nhi = rcu_dereference_rtnl(nhe->nh_info); struct fib_nh_common *nhc = &nhi->fib_nhc; int weight = nhg->nh_entries[i].weight; if (fib_add_nexthop(skb, nhc, weight, rt_family, 0) < 0) return -EMSGSIZE; } return 0; } /* called with rcu lock */ static inline bool nexthop_is_blackhole(const struct nexthop *nh) { const struct nh_info *nhi; if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); if (nh_grp->num_nh > 1) return false; nh = nh_grp->nh_entries[0].nh; } nhi = rcu_dereference_rtnl(nh->nh_info); return nhi->reject_nh; } static inline void nexthop_path_fib_result(struct fib_result *res, int hash) { struct nh_info *nhi; struct nexthop *nh; nh = nexthop_select_path(res->fi->nh, hash); nhi = rcu_dereference(nh->nh_info); res->nhc = &nhi->fib_nhc; } /* called with rcu read lock or rtnl held */ static inline struct fib_nh_common *nexthop_fib_nhc(struct nexthop *nh, int nhsel) { struct nh_info *nhi; BUILD_BUG_ON(offsetof(struct fib_nh, nh_common) != 0); BUILD_BUG_ON(offsetof(struct fib6_nh, nh_common) != 0); if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); if (nh_grp->is_multipath) { nh = nexthop_mpath_select(nh_grp, nhsel); if (!nh) return NULL; } } nhi = rcu_dereference_rtnl(nh->nh_info); return &nhi->fib_nhc; } /* called from fib_table_lookup with rcu_lock */ static inline struct fib_nh_common *nexthop_get_nhc_lookup(const struct nexthop *nh, int fib_flags, const struct flowi4 *flp, int *nhsel) { struct nh_info *nhi; if (nh->is_group) { struct nh_group *nhg = rcu_dereference(nh->nh_grp); int i; for (i = 0; i < nhg->num_nh; i++) { struct nexthop *nhe = nhg->nh_entries[i].nh; nhi = rcu_dereference(nhe->nh_info); if (fib_lookup_good_nhc(&nhi->fib_nhc, fib_flags, flp)) { *nhsel = i; return &nhi->fib_nhc; } } } else { nhi = rcu_dereference(nh->nh_info); if (fib_lookup_good_nhc(&nhi->fib_nhc, fib_flags, flp)) { *nhsel = 0; return &nhi->fib_nhc; } } return NULL; } static inline bool nexthop_uses_dev(const struct nexthop *nh, const struct net_device *dev) { struct nh_info *nhi; if (nh->is_group) { struct nh_group *nhg = rcu_dereference(nh->nh_grp); int i; for (i = 0; i < nhg->num_nh; i++) { struct nexthop *nhe = nhg->nh_entries[i].nh; nhi = rcu_dereference(nhe->nh_info); if (nhc_l3mdev_matches_dev(&nhi->fib_nhc, dev)) return true; } } else { nhi = rcu_dereference(nh->nh_info); if (nhc_l3mdev_matches_dev(&nhi->fib_nhc, dev)) return true; } return false; } static inline unsigned int fib_info_num_path(const struct fib_info *fi) { if (unlikely(fi->nh)) return nexthop_num_path(fi->nh); return fi->fib_nhs; } int fib_check_nexthop(struct nexthop *nh, u8 scope, struct netlink_ext_ack *extack); static inline struct fib_nh_common *fib_info_nhc(struct fib_info *fi, int nhsel) { if (unlikely(fi->nh)) return nexthop_fib_nhc(fi->nh, nhsel); return &fi->fib_nh[nhsel].nh_common; } /* only used when fib_nh is built into fib_info */ static inline struct fib_nh *fib_info_nh(struct fib_info *fi, int nhsel) { WARN_ON(fi->nh); return &fi->fib_nh[nhsel]; } /* * IPv6 variants */ int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, struct netlink_ext_ack *extack); /* Caller should either hold rcu_read_lock(), or RTNL. */ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) { struct nh_info *nhi; if (nh->is_group) { struct nh_group *nh_grp; nh_grp = rcu_dereference_rtnl(nh->nh_grp); nh = nexthop_mpath_select(nh_grp, 0); if (!nh) return NULL; } nhi = rcu_dereference_rtnl(nh->nh_info); if (nhi->family == AF_INET6) return &nhi->fib6_nh; return NULL; } static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i) { struct fib6_nh *fib6_nh; fib6_nh = f6i->nh ? nexthop_fib6_nh(f6i->nh) : f6i->fib6_nh; return fib6_nh->fib_nh_dev; } static inline void nexthop_path_fib6_result(struct fib6_result *res, int hash) { struct nexthop *nh = res->f6i->nh; struct nh_info *nhi; nh = nexthop_select_path(nh, hash); nhi = rcu_dereference_rtnl(nh->nh_info); if (nhi->reject_nh) { res->fib6_type = RTN_BLACKHOLE; res->fib6_flags |= RTF_REJECT; res->nh = nexthop_fib6_nh(nh); } else { res->nh = &nhi->fib6_nh; } } int nexthop_for_each_fib6_nh(struct nexthop *nh, int (*cb)(struct fib6_nh *nh, void *arg), void *arg); static inline int nexthop_get_family(struct nexthop *nh) { struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info); return nhi->family; } static inline struct fib_nh_common *nexthop_fdb_nhc(struct nexthop *nh) { struct nh_info *nhi = rcu_dereference_rtnl(nh->nh_info); return &nhi->fib_nhc; } static inline struct fib_nh_common *nexthop_path_fdb_result(struct nexthop *nh, int hash) { struct nh_info *nhi; struct nexthop *nhp; nhp = nexthop_select_path(nh, hash); if (unlikely(!nhp)) return NULL; nhi = rcu_dereference(nhp->nh_info); return &nhi->fib_nhc; } #endif |
| 20 19 19 19 19 20 19 18 2 19 19 18 20 1 1 20 18 20 3 16 1 1 5 2 1 19 17 20 20 1 20 17 18 20 20 20 20 20 20 19 1 1 20 20 20 2 2 2 2 2 1 1 1 24 21 24 22 23 23 23 3 1 2 2 2 2 1 20 19 19 19 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 3 3 3 3 3 3 3 3 3 3 1 3 3 24 26 26 13 26 26 26 13 5 2 2 2 2 2 2 2 2 2 26 26 26 26 26 26 1 1 1 26 26 1 24 26 26 2 2 2 2 2 24 1 24 26 3 3 3 3 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Scanning implementation * * Copyright 2003, Jouni Malinen <jkmaline@cc.hut.fi> * Copyright 2004, Instant802 Networks, Inc. * Copyright 2005, Devicescape Software, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2013-2015 Intel Mobile Communications GmbH * Copyright 2016-2017 Intel Deutschland GmbH * Copyright (C) 2018-2025 Intel Corporation */ #include <linux/if_arp.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <net/sch_generic.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/random.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "mesh.h" #define IEEE80211_PROBE_DELAY (HZ / 33) #define IEEE80211_CHANNEL_TIME (HZ / 33) #define IEEE80211_PASSIVE_CHANNEL_TIME (HZ / 9) void ieee80211_rx_bss_put(struct ieee80211_local *local, struct ieee80211_bss *bss) { if (!bss) return; cfg80211_put_bss(local->hw.wiphy, container_of((void *)bss, struct cfg80211_bss, priv)); } static bool is_uapsd_supported(struct ieee802_11_elems *elems) { u8 qos_info; if (elems->wmm_info && elems->wmm_info_len == 7 && elems->wmm_info[5] == 1) qos_info = elems->wmm_info[6]; else if (elems->wmm_param && elems->wmm_param_len == 24 && elems->wmm_param[5] == 1) qos_info = elems->wmm_param[6]; else /* no valid wmm information or parameter element found */ return false; return qos_info & IEEE80211_WMM_IE_AP_QOSINFO_UAPSD; } struct inform_bss_update_data { struct ieee80211_rx_status *rx_status; bool beacon; }; void ieee80211_inform_bss(struct wiphy *wiphy, struct cfg80211_bss *cbss, const struct cfg80211_bss_ies *ies, void *data) { struct ieee80211_local *local = wiphy_priv(wiphy); struct inform_bss_update_data *update_data = data; struct ieee80211_bss *bss = (void *)cbss->priv; struct ieee80211_rx_status *rx_status; struct ieee802_11_elems *elems; int clen, srlen; /* This happens while joining an IBSS */ if (!update_data) return; elems = ieee802_11_parse_elems(ies->data, ies->len, update_data->beacon ? IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON : IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_RESP, NULL); if (!elems) return; rx_status = update_data->rx_status; if (update_data->beacon) bss->device_ts_beacon = rx_status->device_timestamp; else bss->device_ts_presp = rx_status->device_timestamp; if (elems->parse_error) { if (update_data->beacon) bss->corrupt_data |= IEEE80211_BSS_CORRUPT_BEACON; else bss->corrupt_data |= IEEE80211_BSS_CORRUPT_PROBE_RESP; } else { if (update_data->beacon) bss->corrupt_data &= ~IEEE80211_BSS_CORRUPT_BEACON; else bss->corrupt_data &= ~IEEE80211_BSS_CORRUPT_PROBE_RESP; } /* save the ERP value so that it is available at association time */ if (elems->erp_info && (!elems->parse_error || !(bss->valid_data & IEEE80211_BSS_VALID_ERP))) { bss->erp_value = elems->erp_info[0]; bss->has_erp_value = true; if (!elems->parse_error) bss->valid_data |= IEEE80211_BSS_VALID_ERP; } /* replace old supported rates if we get new values */ if (!elems->parse_error || !(bss->valid_data & IEEE80211_BSS_VALID_RATES)) { srlen = 0; if (elems->supp_rates) { clen = IEEE80211_MAX_SUPP_RATES; if (clen > elems->supp_rates_len) clen = elems->supp_rates_len; memcpy(bss->supp_rates, elems->supp_rates, clen); srlen += clen; } if (elems->ext_supp_rates) { clen = IEEE80211_MAX_SUPP_RATES - srlen; if (clen > elems->ext_supp_rates_len) clen = elems->ext_supp_rates_len; memcpy(bss->supp_rates + srlen, elems->ext_supp_rates, clen); srlen += clen; } if (srlen) { bss->supp_rates_len = srlen; if (!elems->parse_error) bss->valid_data |= IEEE80211_BSS_VALID_RATES; } } if (!elems->parse_error || !(bss->valid_data & IEEE80211_BSS_VALID_WMM)) { bss->wmm_used = elems->wmm_param || elems->wmm_info; bss->uapsd_supported = is_uapsd_supported(elems); if (!elems->parse_error) bss->valid_data |= IEEE80211_BSS_VALID_WMM; } if (update_data->beacon) { struct ieee80211_supported_band *sband = local->hw.wiphy->bands[rx_status->band]; if (!(rx_status->encoding == RX_ENC_HT) && !(rx_status->encoding == RX_ENC_VHT)) bss->beacon_rate = &sband->bitrates[rx_status->rate_idx]; } if (elems->vht_cap_elem) bss->vht_cap_info = le32_to_cpu(elems->vht_cap_elem->vht_cap_info); else bss->vht_cap_info = 0; kfree(elems); } struct ieee80211_bss * ieee80211_bss_info_update(struct ieee80211_local *local, struct ieee80211_rx_status *rx_status, struct ieee80211_mgmt *mgmt, size_t len, struct ieee80211_channel *channel) { bool beacon = ieee80211_is_beacon(mgmt->frame_control) || ieee80211_is_s1g_beacon(mgmt->frame_control); struct cfg80211_bss *cbss; struct inform_bss_update_data update_data = { .rx_status = rx_status, .beacon = beacon, }; struct cfg80211_inform_bss bss_meta = { .boottime_ns = rx_status->boottime_ns, .drv_data = (void *)&update_data, }; bool signal_valid; struct ieee80211_sub_if_data *scan_sdata; if (rx_status->flag & RX_FLAG_NO_SIGNAL_VAL) bss_meta.signal = 0; /* invalid signal indication */ else if (ieee80211_hw_check(&local->hw, SIGNAL_DBM)) bss_meta.signal = rx_status->signal * 100; else if (ieee80211_hw_check(&local->hw, SIGNAL_UNSPEC)) bss_meta.signal = (rx_status->signal * 100) / local->hw.max_signal; bss_meta.chan = channel; rcu_read_lock(); scan_sdata = rcu_dereference(local->scan_sdata); if (scan_sdata && scan_sdata->vif.type == NL80211_IFTYPE_STATION && scan_sdata->vif.cfg.assoc && ieee80211_have_rx_timestamp(rx_status)) { struct ieee80211_bss_conf *link_conf = NULL; /* for an MLO connection, set the TSF data only in case we have * an indication on which of the links the frame was received */ if (ieee80211_vif_is_mld(&scan_sdata->vif)) { if (rx_status->link_valid) { s8 link_id = rx_status->link_id; link_conf = rcu_dereference(scan_sdata->vif.link_conf[link_id]); } } else { link_conf = &scan_sdata->vif.bss_conf; } if (link_conf) { bss_meta.parent_tsf = ieee80211_calculate_rx_timestamp(local, rx_status, len + FCS_LEN, 24); ether_addr_copy(bss_meta.parent_bssid, link_conf->bssid); } } rcu_read_unlock(); cbss = cfg80211_inform_bss_frame_data(local->hw.wiphy, &bss_meta, mgmt, len, GFP_ATOMIC); if (!cbss) return NULL; /* In case the signal is invalid update the status */ signal_valid = channel == cbss->channel; if (!signal_valid) rx_status->flag |= RX_FLAG_NO_SIGNAL_VAL; return (void *)cbss->priv; } static bool ieee80211_scan_accept_presp(struct ieee80211_sub_if_data *sdata, struct ieee80211_channel *channel, u32 scan_flags, const u8 *da) { struct ieee80211_link_data *link_sdata; u8 link_id; if (!sdata) return false; /* accept broadcast on 6 GHz and for OCE */ if (is_broadcast_ether_addr(da) && (channel->band == NL80211_BAND_6GHZ || scan_flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP)) return true; if (scan_flags & NL80211_SCAN_FLAG_RANDOM_ADDR) return true; if (ether_addr_equal(da, sdata->vif.addr)) return true; for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { link_sdata = rcu_dereference(sdata->link[link_id]); if (!link_sdata) continue; if (ether_addr_equal(da, link_sdata->conf->addr)) return true; } return false; } void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) { struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); struct ieee80211_mgmt *mgmt = (void *)skb->data; struct ieee80211_bss *bss; struct ieee80211_channel *channel; struct ieee80211_ext *ext; size_t min_hdr_len = offsetof(struct ieee80211_mgmt, u.probe_resp.variable); if (!ieee80211_is_probe_resp(mgmt->frame_control) && !ieee80211_is_beacon(mgmt->frame_control) && !ieee80211_is_s1g_beacon(mgmt->frame_control)) return; if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { ext = (struct ieee80211_ext *)mgmt; min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_beacon.variable) + ieee80211_s1g_optional_len(ext->frame_control); } if (skb->len < min_hdr_len) return; if (test_and_clear_bit(SCAN_BEACON_WAIT, &local->scanning)) { /* * we were passive scanning because of radar/no-IR, but * the beacon/proberesp rx gives us an opportunity to upgrade * to active scan */ set_bit(SCAN_BEACON_DONE, &local->scanning); wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, 0); } channel = ieee80211_get_channel_khz(local->hw.wiphy, ieee80211_rx_status_to_khz(rx_status)); if (!channel || channel->flags & IEEE80211_CHAN_DISABLED) return; if (ieee80211_is_probe_resp(mgmt->frame_control)) { struct ieee80211_sub_if_data *sdata1, *sdata2; struct cfg80211_scan_request *scan_req; struct cfg80211_sched_scan_request *sched_scan_req; u32 scan_req_flags = 0, sched_scan_req_flags = 0; sdata1 = rcu_dereference(local->scan_sdata); sdata2 = rcu_dereference(local->sched_scan_sdata); if (likely(!sdata1 && !sdata2)) return; scan_req = rcu_dereference(local->scan_req); sched_scan_req = rcu_dereference(local->sched_scan_req); if (scan_req) scan_req_flags = scan_req->flags; if (sched_scan_req) sched_scan_req_flags = sched_scan_req->flags; /* ignore ProbeResp to foreign address or non-bcast (OCE) * unless scanning with randomised address */ if (!ieee80211_scan_accept_presp(sdata1, channel, scan_req_flags, mgmt->da) && !ieee80211_scan_accept_presp(sdata2, channel, sched_scan_req_flags, mgmt->da)) return; } else { /* Beacons are expected only with broadcast address */ if (!is_broadcast_ether_addr(mgmt->da)) return; } /* Do not update the BSS table in case of only monitor interfaces */ if (local->open_count == local->monitors) return; bss = ieee80211_bss_info_update(local, rx_status, mgmt, skb->len, channel); if (bss) ieee80211_rx_bss_put(local, bss); } static void ieee80211_prepare_scan_chandef(struct cfg80211_chan_def *chandef) { memset(chandef, 0, sizeof(*chandef)); chandef->width = NL80211_CHAN_WIDTH_20_NOHT; } /* return false if no more work */ static bool ieee80211_prep_hw_scan(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; struct cfg80211_scan_request *req; struct cfg80211_chan_def chandef; u8 bands_used = 0; int i, ielen; u32 *n_chans; u32 flags = 0; req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->hw.wiphy->mtx)); if (test_bit(SCAN_HW_CANCELLED, &local->scanning)) return false; if (ieee80211_hw_check(&local->hw, SINGLE_SCAN_ON_ALL_BANDS)) { local->hw_scan_req->req.n_channels = req->n_channels; for (i = 0; i < req->n_channels; i++) { local->hw_scan_req->req.channels[i] = req->channels[i]; bands_used |= BIT(req->channels[i]->band); } } else { do { if (local->hw_scan_band == NUM_NL80211_BANDS) return false; n_chans = &local->hw_scan_req->req.n_channels; *n_chans = 0; for (i = 0; i < req->n_channels; i++) { if (req->channels[i]->band != local->hw_scan_band) continue; local->hw_scan_req->req.channels[(*n_chans)++] = req->channels[i]; bands_used |= BIT(req->channels[i]->band); } local->hw_scan_band++; } while (!*n_chans); } ieee80211_prepare_scan_chandef(&chandef); if (req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT) flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT; ielen = ieee80211_build_preq_ies(sdata, (u8 *)local->hw_scan_req->req.ie, local->hw_scan_ies_bufsize, &local->hw_scan_req->ies, req->ie, req->ie_len, bands_used, req->rates, &chandef, flags); if (ielen < 0) return false; local->hw_scan_req->req.ie_len = ielen; local->hw_scan_req->req.no_cck = req->no_cck; ether_addr_copy(local->hw_scan_req->req.mac_addr, req->mac_addr); ether_addr_copy(local->hw_scan_req->req.mac_addr_mask, req->mac_addr_mask); ether_addr_copy(local->hw_scan_req->req.bssid, req->bssid); return true; } static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) { struct ieee80211_local *local = hw_to_local(hw); bool hw_scan = test_bit(SCAN_HW_SCANNING, &local->scanning); bool was_scanning = local->scanning; struct cfg80211_scan_request *scan_req; struct ieee80211_sub_if_data *scan_sdata; struct ieee80211_sub_if_data *sdata; lockdep_assert_wiphy(local->hw.wiphy); /* * It's ok to abort a not-yet-running scan (that * we have one at all will be verified by checking * local->scan_req next), but not to complete it * successfully. */ if (WARN_ON(!local->scanning && !aborted)) aborted = true; if (WARN_ON(!local->scan_req)) return; scan_sdata = rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->hw.wiphy->mtx)); if (hw_scan && !aborted && !ieee80211_hw_check(&local->hw, SINGLE_SCAN_ON_ALL_BANDS) && ieee80211_prep_hw_scan(scan_sdata)) { int rc; rc = drv_hw_scan(local, rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->hw.wiphy->mtx)), local->hw_scan_req); if (rc == 0) return; /* HW scan failed and is going to be reported as aborted, * so clear old scan info. */ memset(&local->scan_info, 0, sizeof(local->scan_info)); aborted = true; } kfree(local->hw_scan_req); local->hw_scan_req = NULL; scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->hw.wiphy->mtx)); RCU_INIT_POINTER(local->scan_req, NULL); RCU_INIT_POINTER(local->scan_sdata, NULL); local->scanning = 0; local->scan_chandef.chan = NULL; synchronize_rcu(); if (scan_req != local->int_scan_req) { local->scan_info.aborted = aborted; cfg80211_scan_done(scan_req, &local->scan_info); } /* Set power back to normal operating levels. */ ieee80211_hw_conf_chan(local); if (!hw_scan && was_scanning) { ieee80211_configure_filter(local); drv_sw_scan_complete(local, scan_sdata); ieee80211_offchannel_return(local); } ieee80211_recalc_idle(local); ieee80211_mlme_notify_scan_completed(local); ieee80211_ibss_notify_scan_completed(local); /* Requeue all the work that might have been ignored while * the scan was in progress; if there was none this will * just be a no-op for the particular interface. */ list_for_each_entry(sdata, &local->interfaces, list) { if (ieee80211_sdata_running(sdata)) wiphy_work_queue(sdata->local->hw.wiphy, &sdata->work); } if (was_scanning) ieee80211_start_next_roc(local); } void ieee80211_scan_completed(struct ieee80211_hw *hw, struct cfg80211_scan_info *info) { struct ieee80211_local *local = hw_to_local(hw); trace_api_scan_completed(local, info->aborted); set_bit(SCAN_COMPLETED, &local->scanning); if (info->aborted) set_bit(SCAN_ABORTED, &local->scanning); memcpy(&local->scan_info, info, sizeof(*info)); wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, 0); } EXPORT_SYMBOL(ieee80211_scan_completed); static int ieee80211_start_sw_scan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { /* Software scan is not supported in multi-channel cases */ if (!local->emulate_chanctx) return -EOPNOTSUPP; /* * Hardware/driver doesn't support hw_scan, so use software * scanning instead. First send a nullfunc frame with power save * bit on so that AP will buffer the frames for us while we are not * listening, then send probe requests to each channel and wait for * the responses. After all channels are scanned, tune back to the * original channel and send a nullfunc frame with power save bit * off to trigger the AP to send us all the buffered frames. * * Note that while local->sw_scanning is true everything else but * nullfunc frames and probe requests will be dropped in * ieee80211_tx_h_check_assoc(). */ drv_sw_scan_start(local, sdata, local->scan_addr); local->leave_oper_channel_time = jiffies; local->next_scan_state = SCAN_DECISION; local->scan_channel_idx = 0; ieee80211_offchannel_stop_vifs(local); /* ensure nullfunc is transmitted before leaving operating channel */ ieee80211_flush_queues(local, NULL, false); ieee80211_configure_filter(local); /* We need to set power level at maximum rate for scanning. */ ieee80211_hw_conf_chan(local); wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, 0); return 0; } static bool __ieee80211_can_leave_ch(struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req) { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *sdata_iter; unsigned int link_id; lockdep_assert_wiphy(local->hw.wiphy); if (!ieee80211_is_radar_required(local, req)) return true; if (!regulatory_pre_cac_allowed(local->hw.wiphy)) return false; list_for_each_entry(sdata_iter, &local->interfaces, list) { for_each_valid_link(&sdata_iter->wdev, link_id) if (sdata_iter->wdev.links[link_id].cac_started) return false; } return true; } static bool ieee80211_can_scan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req) { if (!__ieee80211_can_leave_ch(sdata, req)) return false; if (!list_empty(&local->roc_list)) return false; if (sdata->vif.type == NL80211_IFTYPE_STATION && sdata->u.mgd.flags & IEEE80211_STA_CONNECTION_POLL) return false; return true; } void ieee80211_run_deferred_scan(struct ieee80211_local *local) { struct cfg80211_scan_request *req; lockdep_assert_wiphy(local->hw.wiphy); if (!local->scan_req || local->scanning) return; req = wiphy_dereference(local->hw.wiphy, local->scan_req); if (!ieee80211_can_scan(local, rcu_dereference_protected( local->scan_sdata, lockdep_is_held(&local->hw.wiphy->mtx)), req)) return; wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, round_jiffies_relative(0)); } static void ieee80211_send_scan_probe_req(struct ieee80211_sub_if_data *sdata, const u8 *src, const u8 *dst, const u8 *ssid, size_t ssid_len, const u8 *ie, size_t ie_len, u32 ratemask, u32 flags, u32 tx_flags, struct ieee80211_channel *channel) { struct sk_buff *skb; skb = ieee80211_build_probe_req(sdata, src, dst, ratemask, channel, ssid, ssid_len, ie, ie_len, flags); if (skb) { if (flags & IEEE80211_PROBE_FLAG_RANDOM_SN) { struct ieee80211_hdr *hdr = (void *)skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); u16 sn = get_random_u16(); info->control.flags |= IEEE80211_TX_CTRL_NO_SEQNO; hdr->seq_ctrl = cpu_to_le16(IEEE80211_SN_TO_SEQ(sn)); } IEEE80211_SKB_CB(skb)->flags |= tx_flags; IEEE80211_SKB_CB(skb)->control.flags |= IEEE80211_TX_CTRL_DONT_USE_RATE_MASK; ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band); } } static void ieee80211_scan_state_send_probe(struct ieee80211_local *local, unsigned long *next_delay) { int i; struct ieee80211_sub_if_data *sdata; struct cfg80211_scan_request *scan_req; enum nl80211_band band = local->hw.conf.chandef.chan->band; u32 flags = 0, tx_flags; scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->hw.wiphy->mtx)); tx_flags = IEEE80211_TX_INTFL_OFFCHAN_TX_OK; if (scan_req->no_cck) tx_flags |= IEEE80211_TX_CTL_NO_CCK_RATE; if (scan_req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT) flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT; if (scan_req->flags & NL80211_SCAN_FLAG_RANDOM_SN) flags |= IEEE80211_PROBE_FLAG_RANDOM_SN; sdata = rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->hw.wiphy->mtx)); for (i = 0; i < scan_req->n_ssids; i++) ieee80211_send_scan_probe_req( sdata, local->scan_addr, scan_req->bssid, scan_req->ssids[i].ssid, scan_req->ssids[i].ssid_len, scan_req->ie, scan_req->ie_len, scan_req->rates[band], flags, tx_flags, local->hw.conf.chandef.chan); /* * After sending probe requests, wait for probe responses * on the channel. */ *next_delay = msecs_to_jiffies(scan_req->duration) > IEEE80211_PROBE_DELAY + IEEE80211_CHANNEL_TIME ? msecs_to_jiffies(scan_req->duration) - IEEE80211_PROBE_DELAY : IEEE80211_CHANNEL_TIME; local->next_scan_state = SCAN_DECISION; } static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req) { struct ieee80211_local *local = sdata->local; bool hw_scan = local->ops->hw_scan; int rc; lockdep_assert_wiphy(local->hw.wiphy); if (local->scan_req) return -EBUSY; /* For an MLO connection, if a link ID was specified, validate that it * is indeed active. */ if (ieee80211_vif_is_mld(&sdata->vif) && req->tsf_report_link_id >= 0 && !(sdata->vif.active_links & BIT(req->tsf_report_link_id))) return -EINVAL; if (!__ieee80211_can_leave_ch(sdata, req)) return -EBUSY; if (!ieee80211_can_scan(local, sdata, req)) { /* wait for the work to finish/time out */ rcu_assign_pointer(local->scan_req, req); rcu_assign_pointer(local->scan_sdata, sdata); return 0; } again: if (hw_scan) { u8 *ies; local->hw_scan_ies_bufsize = local->scan_ies_len + req->ie_len; if (ieee80211_hw_check(&local->hw, SINGLE_SCAN_ON_ALL_BANDS)) { int i, n_bands = 0; u8 bands_counted = 0; for (i = 0; i < req->n_channels; i++) { if (bands_counted & BIT(req->channels[i]->band)) continue; bands_counted |= BIT(req->channels[i]->band); n_bands++; } local->hw_scan_ies_bufsize *= n_bands; } local->hw_scan_req = kmalloc(struct_size(local->hw_scan_req, req.channels, req->n_channels) + local->hw_scan_ies_bufsize, GFP_KERNEL); if (!local->hw_scan_req) return -ENOMEM; local->hw_scan_req->req.ssids = req->ssids; local->hw_scan_req->req.n_ssids = req->n_ssids; /* None of the channels are actually set * up but let UBSAN know the boundaries. */ local->hw_scan_req->req.n_channels = req->n_channels; ies = (u8 *)local->hw_scan_req + sizeof(*local->hw_scan_req) + req->n_channels * sizeof(req->channels[0]); local->hw_scan_req->req.ie = ies; local->hw_scan_req->req.flags = req->flags; eth_broadcast_addr(local->hw_scan_req->req.bssid); local->hw_scan_req->req.duration = req->duration; local->hw_scan_req->req.duration_mandatory = req->duration_mandatory; local->hw_scan_req->req.tsf_report_link_id = req->tsf_report_link_id; local->hw_scan_band = 0; local->hw_scan_req->req.n_6ghz_params = req->n_6ghz_params; local->hw_scan_req->req.scan_6ghz_params = req->scan_6ghz_params; local->hw_scan_req->req.scan_6ghz = req->scan_6ghz; local->hw_scan_req->req.first_part = req->first_part; /* * After allocating local->hw_scan_req, we must * go through until ieee80211_prep_hw_scan(), so * anything that might be changed here and leave * this function early must not go after this * allocation. */ } rcu_assign_pointer(local->scan_req, req); rcu_assign_pointer(local->scan_sdata, sdata); if (req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) get_random_mask_addr(local->scan_addr, req->mac_addr, req->mac_addr_mask); else memcpy(local->scan_addr, sdata->vif.addr, ETH_ALEN); if (hw_scan) { __set_bit(SCAN_HW_SCANNING, &local->scanning); } else if ((req->n_channels == 1) && (req->channels[0] == local->hw.conf.chandef.chan)) { /* * If we are scanning only on the operating channel * then we do not need to stop normal activities */ unsigned long next_delay; __set_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning); ieee80211_recalc_idle(local); /* Notify driver scan is starting, keep order of operations * same as normal software scan, in case that matters. */ drv_sw_scan_start(local, sdata, local->scan_addr); ieee80211_configure_filter(local); /* accept probe-responses */ /* We need to ensure power level is at max for scanning. */ ieee80211_hw_conf_chan(local); if ((req->channels[0]->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) || !req->n_ssids) { next_delay = IEEE80211_PASSIVE_CHANNEL_TIME; if (req->n_ssids) set_bit(SCAN_BEACON_WAIT, &local->scanning); } else { ieee80211_scan_state_send_probe(local, &next_delay); next_delay = IEEE80211_CHANNEL_TIME; } /* Now, just wait a bit and we are all done! */ wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, next_delay); return 0; } else { /* Do normal software scan */ __set_bit(SCAN_SW_SCANNING, &local->scanning); } ieee80211_recalc_idle(local); if (hw_scan) { WARN_ON(!ieee80211_prep_hw_scan(sdata)); rc = drv_hw_scan(local, sdata, local->hw_scan_req); } else { rc = ieee80211_start_sw_scan(local, sdata); } if (rc) { kfree(local->hw_scan_req); local->hw_scan_req = NULL; local->scanning = 0; ieee80211_recalc_idle(local); local->scan_req = NULL; RCU_INIT_POINTER(local->scan_sdata, NULL); } if (hw_scan && rc == 1) { /* * we can't fall back to software for P2P-GO * as it must update NoA etc. */ if (ieee80211_vif_type_p2p(&sdata->vif) == NL80211_IFTYPE_P2P_GO) return -EOPNOTSUPP; hw_scan = false; goto again; } return rc; } static unsigned long ieee80211_scan_get_channel_time(struct ieee80211_channel *chan) { /* * TODO: channel switching also consumes quite some time, * add that delay as well to get a better estimation */ if (chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) return IEEE80211_PASSIVE_CHANNEL_TIME; return IEEE80211_PROBE_DELAY + IEEE80211_CHANNEL_TIME; } static void ieee80211_scan_state_decision(struct ieee80211_local *local, unsigned long *next_delay) { bool associated = false; bool tx_empty = true; bool bad_latency; struct ieee80211_sub_if_data *sdata; struct ieee80211_channel *next_chan; enum mac80211_scan_state next_scan_state; struct cfg80211_scan_request *scan_req; lockdep_assert_wiphy(local->hw.wiphy); /* * check if at least one STA interface is associated, * check if at least one STA interface has pending tx frames * and grab the lowest used beacon interval */ list_for_each_entry(sdata, &local->interfaces, list) { if (!ieee80211_sdata_running(sdata)) continue; if (sdata->vif.type == NL80211_IFTYPE_STATION) { if (sdata->u.mgd.associated) { associated = true; if (!qdisc_all_tx_empty(sdata->dev)) { tx_empty = false; break; } } } } scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->hw.wiphy->mtx)); next_chan = scan_req->channels[local->scan_channel_idx]; /* * we're currently scanning a different channel, let's * see if we can scan another channel without interfering * with the current traffic situation. * * Keep good latency, do not stay off-channel more than 125 ms. */ bad_latency = time_after(jiffies + ieee80211_scan_get_channel_time(next_chan), local->leave_oper_channel_time + HZ / 8); if (associated && !tx_empty) { if (scan_req->flags & NL80211_SCAN_FLAG_LOW_PRIORITY) next_scan_state = SCAN_ABORT; else next_scan_state = SCAN_SUSPEND; } else if (associated && bad_latency) { next_scan_state = SCAN_SUSPEND; } else { next_scan_state = SCAN_SET_CHANNEL; } local->next_scan_state = next_scan_state; *next_delay = 0; } static void ieee80211_scan_state_set_channel(struct ieee80211_local *local, unsigned long *next_delay) { int skip; struct ieee80211_channel *chan; struct cfg80211_scan_request *scan_req; scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->hw.wiphy->mtx)); skip = 0; chan = scan_req->channels[local->scan_channel_idx]; local->scan_chandef.chan = chan; local->scan_chandef.center_freq1 = chan->center_freq; local->scan_chandef.freq1_offset = chan->freq_offset; local->scan_chandef.center_freq2 = 0; /* For S1G, only scan the 1MHz primaries. */ if (chan->band == NL80211_BAND_S1GHZ) { local->scan_chandef.width = NL80211_CHAN_WIDTH_1; local->scan_chandef.s1g_primary_2mhz = false; goto set_channel; } /* * If scanning on oper channel, use whatever channel-type * is currently in use. */ if (chan == local->hw.conf.chandef.chan) local->scan_chandef = local->hw.conf.chandef; else local->scan_chandef.width = NL80211_CHAN_WIDTH_20_NOHT; set_channel: if (ieee80211_hw_conf_chan(local)) skip = 1; /* advance state machine to next channel/band */ local->scan_channel_idx++; if (skip) { /* if we skip this channel return to the decision state */ local->next_scan_state = SCAN_DECISION; return; } /* * Probe delay is used to update the NAV, cf. 11.1.3.2.2 * (which unfortunately doesn't say _why_ step a) is done, * but it waits for the probe delay or until a frame is * received - and the received frame would update the NAV). * For now, we do not support waiting until a frame is * received. * * In any case, it is not necessary for a passive scan. */ if ((chan->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_RADAR)) || !scan_req->n_ssids) { *next_delay = max(msecs_to_jiffies(scan_req->duration), IEEE80211_PASSIVE_CHANNEL_TIME); local->next_scan_state = SCAN_DECISION; if (scan_req->n_ssids) set_bit(SCAN_BEACON_WAIT, &local->scanning); return; } /* active scan, send probes */ *next_delay = IEEE80211_PROBE_DELAY; local->next_scan_state = SCAN_SEND_PROBE; } static void ieee80211_scan_state_suspend(struct ieee80211_local *local, unsigned long *next_delay) { /* switch back to the operating channel */ local->scan_chandef.chan = NULL; ieee80211_hw_conf_chan(local); /* disable PS */ ieee80211_offchannel_return(local); *next_delay = HZ / 5; /* afterwards, resume scan & go to next channel */ local->next_scan_state = SCAN_RESUME; } static void ieee80211_scan_state_resume(struct ieee80211_local *local, unsigned long *next_delay) { ieee80211_offchannel_stop_vifs(local); if (local->ops->flush) { ieee80211_flush_queues(local, NULL, false); *next_delay = 0; } else *next_delay = HZ / 10; /* remember when we left the operating channel */ local->leave_oper_channel_time = jiffies; /* advance to the next channel to be scanned */ local->next_scan_state = SCAN_SET_CHANNEL; } void ieee80211_scan_work(struct wiphy *wiphy, struct wiphy_work *work) { struct ieee80211_local *local = container_of(work, struct ieee80211_local, scan_work.work); struct ieee80211_sub_if_data *sdata; struct cfg80211_scan_request *scan_req; unsigned long next_delay = 0; bool aborted; lockdep_assert_wiphy(local->hw.wiphy); if (!ieee80211_can_run_worker(local)) { aborted = true; goto out_complete; } sdata = rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->hw.wiphy->mtx)); scan_req = rcu_dereference_protected(local->scan_req, lockdep_is_held(&local->hw.wiphy->mtx)); /* When scanning on-channel, the first-callback means completed. */ if (test_bit(SCAN_ONCHANNEL_SCANNING, &local->scanning)) { aborted = test_and_clear_bit(SCAN_ABORTED, &local->scanning); goto out_complete; } if (test_and_clear_bit(SCAN_COMPLETED, &local->scanning)) { aborted = test_and_clear_bit(SCAN_ABORTED, &local->scanning); goto out_complete; } if (!sdata || !scan_req) return; if (!local->scanning) { int rc; RCU_INIT_POINTER(local->scan_req, NULL); RCU_INIT_POINTER(local->scan_sdata, NULL); rc = __ieee80211_start_scan(sdata, scan_req); if (!rc) return; /* need to complete scan in cfg80211 */ rcu_assign_pointer(local->scan_req, scan_req); aborted = true; goto out_complete; } clear_bit(SCAN_BEACON_WAIT, &local->scanning); /* * as long as no delay is required advance immediately * without scheduling a new work */ do { if (!ieee80211_sdata_running(sdata)) { aborted = true; goto out_complete; } if (test_and_clear_bit(SCAN_BEACON_DONE, &local->scanning) && local->next_scan_state == SCAN_DECISION) local->next_scan_state = SCAN_SEND_PROBE; switch (local->next_scan_state) { case SCAN_DECISION: /* if no more bands/channels left, complete scan */ if (local->scan_channel_idx >= scan_req->n_channels) { aborted = false; goto out_complete; } ieee80211_scan_state_decision(local, &next_delay); break; case SCAN_SET_CHANNEL: ieee80211_scan_state_set_channel(local, &next_delay); break; case SCAN_SEND_PROBE: ieee80211_scan_state_send_probe(local, &next_delay); break; case SCAN_SUSPEND: ieee80211_scan_state_suspend(local, &next_delay); break; case SCAN_RESUME: ieee80211_scan_state_resume(local, &next_delay); break; case SCAN_ABORT: aborted = true; goto out_complete; } } while (next_delay == 0); wiphy_delayed_work_queue(local->hw.wiphy, &local->scan_work, next_delay); return; out_complete: __ieee80211_scan_completed(&local->hw, aborted); } int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req) { lockdep_assert_wiphy(sdata->local->hw.wiphy); return __ieee80211_start_scan(sdata, req); } int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata, const u8 *ssid, u8 ssid_len, struct ieee80211_channel **channels, unsigned int n_channels) { struct ieee80211_local *local = sdata->local; int i, n_ch = 0; enum nl80211_band band; lockdep_assert_wiphy(local->hw.wiphy); /* busy scanning */ if (local->scan_req) return -EBUSY; /* fill internal scan request */ if (!channels) { int max_n; for (band = 0; band < NUM_NL80211_BANDS; band++) { if (!local->hw.wiphy->bands[band] || band == NL80211_BAND_6GHZ || band == NL80211_BAND_S1GHZ) continue; max_n = local->hw.wiphy->bands[band]->n_channels; for (i = 0; i < max_n; i++) { struct ieee80211_channel *tmp_ch = &local->hw.wiphy->bands[band]->channels[i]; if (tmp_ch->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_DISABLED) || !cfg80211_wdev_channel_allowed(&sdata->wdev, tmp_ch)) continue; local->int_scan_req->channels[n_ch] = tmp_ch; n_ch++; } } if (WARN_ON_ONCE(n_ch == 0)) return -EINVAL; local->int_scan_req->n_channels = n_ch; } else { for (i = 0; i < n_channels; i++) { if (channels[i]->flags & (IEEE80211_CHAN_NO_IR | IEEE80211_CHAN_DISABLED) || !cfg80211_wdev_channel_allowed(&sdata->wdev, channels[i])) continue; local->int_scan_req->channels[n_ch] = channels[i]; n_ch++; } if (n_ch == 0) return -EINVAL; local->int_scan_req->n_channels = n_ch; } local->int_scan_req->ssids = &local->scan_ssid; local->int_scan_req->n_ssids = 1; memcpy(local->int_scan_req->ssids[0].ssid, ssid, IEEE80211_MAX_SSID_LEN); local->int_scan_req->ssids[0].ssid_len = ssid_len; return __ieee80211_start_scan(sdata, sdata->local->int_scan_req); } void ieee80211_scan_cancel(struct ieee80211_local *local) { /* ensure a new scan cannot be queued */ lockdep_assert_wiphy(local->hw.wiphy); /* * We are canceling software scan, or deferred scan that was not * yet really started (see __ieee80211_start_scan ). * * Regarding hardware scan: * - we can not call __ieee80211_scan_completed() as when * SCAN_HW_SCANNING bit is set this function change * local->hw_scan_req to operate on 5G band, what race with * driver which can use local->hw_scan_req * * - we can not cancel scan_work since driver can schedule it * by ieee80211_scan_completed(..., true) to finish scan * * Hence we only call the cancel_hw_scan() callback, but the low-level * driver is still responsible for calling ieee80211_scan_completed() * after the scan was completed/aborted. */ if (!local->scan_req) return; /* * We have a scan running and the driver already reported completion, * but the worker hasn't run yet or is stuck on the mutex - mark it as * cancelled. */ if (test_bit(SCAN_HW_SCANNING, &local->scanning) && test_bit(SCAN_COMPLETED, &local->scanning)) { set_bit(SCAN_HW_CANCELLED, &local->scanning); return; } if (test_bit(SCAN_HW_SCANNING, &local->scanning)) { /* * Make sure that __ieee80211_scan_completed doesn't trigger a * scan on another band. */ set_bit(SCAN_HW_CANCELLED, &local->scanning); if (local->ops->cancel_hw_scan) drv_cancel_hw_scan(local, rcu_dereference_protected(local->scan_sdata, lockdep_is_held(&local->hw.wiphy->mtx))); return; } wiphy_delayed_work_cancel(local->hw.wiphy, &local->scan_work); /* and clean up */ memset(&local->scan_info, 0, sizeof(local->scan_info)); __ieee80211_scan_completed(&local->hw, true); } int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, struct cfg80211_sched_scan_request *req) { struct ieee80211_local *local = sdata->local; struct ieee80211_scan_ies sched_scan_ies = {}; struct cfg80211_chan_def chandef; int ret, i, iebufsz, num_bands = 0; u32 rate_masks[NUM_NL80211_BANDS] = {}; u8 bands_used = 0; u8 *ie; u32 flags = 0; lockdep_assert_wiphy(local->hw.wiphy); iebufsz = local->scan_ies_len + req->ie_len; if (!local->ops->sched_scan_start) return -EOPNOTSUPP; for (i = 0; i < NUM_NL80211_BANDS; i++) { if (local->hw.wiphy->bands[i]) { bands_used |= BIT(i); rate_masks[i] = (u32) -1; num_bands++; } } if (req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT) flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT; ie = kcalloc(iebufsz, num_bands, GFP_KERNEL); if (!ie) { ret = -ENOMEM; goto out; } ieee80211_prepare_scan_chandef(&chandef); ret = ieee80211_build_preq_ies(sdata, ie, num_bands * iebufsz, &sched_scan_ies, req->ie, req->ie_len, bands_used, rate_masks, &chandef, flags); if (ret < 0) goto error; ret = drv_sched_scan_start(local, sdata, req, &sched_scan_ies); if (ret == 0) { rcu_assign_pointer(local->sched_scan_sdata, sdata); rcu_assign_pointer(local->sched_scan_req, req); } error: kfree(ie); out: if (ret) { /* Clean in case of failure after HW restart or upon resume. */ RCU_INIT_POINTER(local->sched_scan_sdata, NULL); RCU_INIT_POINTER(local->sched_scan_req, NULL); } return ret; } int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, struct cfg80211_sched_scan_request *req) { struct ieee80211_local *local = sdata->local; lockdep_assert_wiphy(local->hw.wiphy); if (rcu_access_pointer(local->sched_scan_sdata)) return -EBUSY; return __ieee80211_request_sched_scan_start(sdata, req); } int ieee80211_request_sched_scan_stop(struct ieee80211_local *local) { struct ieee80211_sub_if_data *sched_scan_sdata; int ret = -ENOENT; lockdep_assert_wiphy(local->hw.wiphy); if (!local->ops->sched_scan_stop) return -EOPNOTSUPP; /* We don't want to restart sched scan anymore. */ RCU_INIT_POINTER(local->sched_scan_req, NULL); sched_scan_sdata = rcu_dereference_protected(local->sched_scan_sdata, lockdep_is_held(&local->hw.wiphy->mtx)); if (sched_scan_sdata) { ret = drv_sched_scan_stop(local, sched_scan_sdata); if (!ret) RCU_INIT_POINTER(local->sched_scan_sdata, NULL); } return ret; } void ieee80211_sched_scan_results(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); trace_api_sched_scan_results(local); cfg80211_sched_scan_results(hw->wiphy, 0); } EXPORT_SYMBOL(ieee80211_sched_scan_results); void ieee80211_sched_scan_end(struct ieee80211_local *local) { lockdep_assert_wiphy(local->hw.wiphy); if (!rcu_access_pointer(local->sched_scan_sdata)) return; RCU_INIT_POINTER(local->sched_scan_sdata, NULL); /* If sched scan was aborted by the driver. */ RCU_INIT_POINTER(local->sched_scan_req, NULL); cfg80211_sched_scan_stopped_locked(local->hw.wiphy, 0); } void ieee80211_sched_scan_stopped_work(struct wiphy *wiphy, struct wiphy_work *work) { struct ieee80211_local *local = container_of(work, struct ieee80211_local, sched_scan_stopped_work); ieee80211_sched_scan_end(local); } void ieee80211_sched_scan_stopped(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); trace_api_sched_scan_stopped(local); /* * this shouldn't really happen, so for simplicity * simply ignore it, and let mac80211 reconfigure * the sched scan later on. */ if (local->in_reconfig) return; wiphy_work_queue(hw->wiphy, &local->sched_scan_stopped_work); } EXPORT_SYMBOL(ieee80211_sched_scan_stopped); |
| 159 152 154 152 151 153 19 18 1 19 154 151 5 148 285 3 285 160 285 1538 165 164 1487 227 288 1538 165 11 2 165 3 1539 3 3 180 180 179 179 181 181 180 181 181 179 180 180 180 179 179 181 180 181 181 179 181 181 180 180 181 179 181 180 181 180 181 181 181 179 180 180 181 180 180 181 181 180 3 154 5 5 154 152 153 154 153 153 152 152 20 20 20 154 154 153 2 2 2 2 2 2 2 167 166 155 16 167 166 167 167 167 167 166 166 167 167 132 167 152 153 152 166 162 163 167 163 151 16 163 23 155 154 155 146 9 155 160 1 158 2 156 1 167 162 156 23 166 1 158 145 12 157 157 158 158 16 16 16 25 25 11 20 19 2 1 2 1 4 4 25 38 38 36 35 18 18 30 12 12 8 8 8 8 3 8 6 5 6 10 18 14 86 85 85 8 6 3 31 31 26 22 5 2 3 1 2 84 5 4 4 4 4 5 15 46 30 46 15 46 45 2 46 46 46 46 46 45 46 46 46 46 46 46 46 46 46 46 46 1 1 1 45 45 1 44 2 44 3 43 3 42 1 42 10 41 2 40 40 3 2 39 4 3 3 36 1 69 55 68 14 11 11 3 2 13 10 61 67 22 25 24 3 24 25 2 99 1 1 1 99 88 4 87 12 98 35 35 35 35 34 138 125 98 98 87 11 85 1 85 2 84 17 84 14 84 2 84 10 83 3 84 11 84 6 83 4 82 2 2 82 4 3 3 2 1 79 2 79 8 76 11 77 2 77 8 77 2 77 3 77 1 77 2 77 5 76 5 77 1 77 3 77 5 76 5 77 5 77 4 73 3 73 3 73 6 73 3 73 13 70 1 1 78 79 79 64 15 216 224 225 225 225 224 224 225 224 225 224 225 225 224 225 225 225 223 225 224 223 223 225 224 224 224 224 224 222 224 224 224 224 223 224 224 223 223 224 224 224 223 224 224 223 223 223 224 224 2 1 1 1 1 2 2 2 1 2 16 11 10 10 16 16 16 16 16 16 9 16 16 16 16 4 16 16 16 16 10 9 16 9 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Bridge netlink control interface * * Authors: * Stephen Hemminger <shemminger@osdl.org> */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/etherdevice.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> #include <uapi/linux/if_bridge.h> #include "br_private.h" #include "br_private_stp.h" #include "br_private_cfm.h" #include "br_private_tunnel.h" #include "br_private_mcast_eht.h" static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg, u32 filter_mask) { struct net_bridge_vlan *v; u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; u16 flags, pvid; int num_vlans = 0; if (!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) return 0; pvid = br_get_pvid(vg); /* Count number of vlan infos */ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { flags = 0; /* only a context, bridge vlan not activated */ if (!br_vlan_should_use(v)) continue; if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { vid_range_end = v->vid; continue; } else { if ((vid_range_end - vid_range_start) > 0) num_vlans += 2; else num_vlans += 1; } initvars: vid_range_start = v->vid; vid_range_end = v->vid; vid_range_flags = flags; } if (vid_range_start != 0) { if ((vid_range_end - vid_range_start) > 0) num_vlans += 2; else num_vlans += 1; } return num_vlans; } static int br_get_num_vlan_infos(struct net_bridge_vlan_group *vg, u32 filter_mask) { int num_vlans; if (!vg) return 0; if (filter_mask & RTEXT_FILTER_BRVLAN) return vg->num_vlans; rcu_read_lock(); num_vlans = __get_num_vlan_infos(vg, filter_mask); rcu_read_unlock(); return num_vlans; } static size_t br_get_link_af_size_filtered(const struct net_device *dev, u32 filter_mask) { struct net_bridge_vlan_group *vg = NULL; struct net_bridge_port *p = NULL; struct net_bridge *br = NULL; u32 num_cfm_peer_mep_infos; u32 num_cfm_mep_infos; size_t vinfo_sz = 0; int num_vlan_infos; rcu_read_lock(); if (netif_is_bridge_port(dev)) { p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); } else if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group_rcu(br); } num_vlan_infos = br_get_num_vlan_infos(vg, filter_mask); rcu_read_unlock(); if (p && (p->flags & BR_VLAN_TUNNEL)) vinfo_sz += br_get_vlan_tunnel_info_size(vg); /* Each VLAN is returned in bridge_vlan_info along with flags */ vinfo_sz += num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info)); if (p && vg && (filter_mask & RTEXT_FILTER_MST)) vinfo_sz += br_mst_info_size(vg); if (!(filter_mask & RTEXT_FILTER_CFM_STATUS)) return vinfo_sz; if (!br) return vinfo_sz; /* CFM status info must be added */ br_cfm_mep_count(br, &num_cfm_mep_infos); br_cfm_peer_mep_count(br, &num_cfm_peer_mep_infos); vinfo_sz += nla_total_size(0); /* IFLA_BRIDGE_CFM */ /* For each status struct the MEP instance (u32) is added */ /* MEP instance (u32) + br_cfm_mep_status */ vinfo_sz += num_cfm_mep_infos * /*IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE */ (nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN */ + nla_total_size(sizeof(u32))); /* MEP instance (u32) + br_cfm_cc_peer_status */ vinfo_sz += num_cfm_peer_mep_infos * /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE */ (nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE */ + nla_total_size(sizeof(u8)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE */ + nla_total_size(sizeof(u8)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN */ + nla_total_size(sizeof(u32))); return vinfo_sz; } static inline size_t br_port_info_size(void) { return nla_total_size(1) /* IFLA_BRPORT_STATE */ + nla_total_size(2) /* IFLA_BRPORT_PRIORITY */ + nla_total_size(4) /* IFLA_BRPORT_COST */ + nla_total_size(1) /* IFLA_BRPORT_MODE */ + nla_total_size(1) /* IFLA_BRPORT_GUARD */ + nla_total_size(1) /* IFLA_BRPORT_PROTECT */ + nla_total_size(1) /* IFLA_BRPORT_FAST_LEAVE */ + nla_total_size(1) /* IFLA_BRPORT_MCAST_TO_UCAST */ + nla_total_size(1) /* IFLA_BRPORT_LEARNING */ + nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_MCAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_BCAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */ + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */ + nla_total_size(1) /* IFLA_BRPORT_ISOLATED */ + nla_total_size(1) /* IFLA_BRPORT_LOCKED */ + nla_total_size(1) /* IFLA_BRPORT_MAB */ + nla_total_size(1) /* IFLA_BRPORT_NEIGH_VLAN_SUPPRESS */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_COST */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_NO */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_TOPOLOGY_CHANGE_ACK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_CONFIG_PENDING */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_MESSAGE_AGE_TIMER */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_FORWARD_DELAY_TIMER */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_N_GROUPS */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_MAX_GROUPS */ #endif + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_RING_OPEN */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_IN_OPEN */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_EHT_HOSTS_CNT */ + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_BACKUP_NHID */ + 0; } static inline size_t br_nlmsg_size(struct net_device *dev, u32 filter_mask) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + nla_total_size(4) /* IFLA_MASTER */ + nla_total_size(4) /* IFLA_MTU */ + nla_total_size(4) /* IFLA_LINK */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(br_port_info_size()) /* IFLA_PROTINFO */ + nla_total_size(br_get_link_af_size_filtered(dev, filter_mask)) /* IFLA_AF_SPEC */ + nla_total_size(4); /* IFLA_BRPORT_BACKUP_PORT */ } static int br_port_fill_attrs(struct sk_buff *skb, const struct net_bridge_port *p) { u8 mode = !!(p->flags & BR_HAIRPIN_MODE); struct net_bridge_port *backup_p; u64 timerval; if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) || nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) || nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) || nla_put_u8(skb, IFLA_BRPORT_MODE, mode) || nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)) || nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(p->flags & BR_ROOT_BLOCK)) || nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(p->flags & BR_MULTICAST_FAST_LEAVE)) || nla_put_u8(skb, IFLA_BRPORT_MCAST_TO_UCAST, !!(p->flags & BR_MULTICAST_TO_UNICAST)) || nla_put_u8(skb, IFLA_BRPORT_LEARNING, !!(p->flags & BR_LEARNING)) || nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_MCAST_FLOOD, !!(p->flags & BR_MCAST_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_BCAST_FLOOD, !!(p->flags & BR_BCAST_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI, !!(p->flags & BR_PROXYARP_WIFI)) || nla_put(skb, IFLA_BRPORT_ROOT_ID, sizeof(struct ifla_bridge_id), &p->designated_root) || nla_put(skb, IFLA_BRPORT_BRIDGE_ID, sizeof(struct ifla_bridge_id), &p->designated_bridge) || nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_PORT, p->designated_port) || nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_COST, p->designated_cost) || nla_put_u16(skb, IFLA_BRPORT_ID, p->port_id) || nla_put_u16(skb, IFLA_BRPORT_NO, p->port_no) || nla_put_u8(skb, IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, p->topology_change_ack) || nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending) || nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(p->flags & BR_VLAN_TUNNEL)) || nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask) || nla_put_u8(skb, IFLA_BRPORT_NEIGH_SUPPRESS, !!(p->flags & BR_NEIGH_SUPPRESS)) || nla_put_u8(skb, IFLA_BRPORT_MRP_RING_OPEN, !!(p->flags & BR_MRP_LOST_CONT)) || nla_put_u8(skb, IFLA_BRPORT_MRP_IN_OPEN, !!(p->flags & BR_MRP_LOST_IN_CONT)) || nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(p->flags & BR_ISOLATED)) || nla_put_u8(skb, IFLA_BRPORT_LOCKED, !!(p->flags & BR_PORT_LOCKED)) || nla_put_u8(skb, IFLA_BRPORT_MAB, !!(p->flags & BR_PORT_MAB)) || nla_put_u8(skb, IFLA_BRPORT_NEIGH_VLAN_SUPPRESS, !!(p->flags & BR_NEIGH_VLAN_SUPPRESS))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_MESSAGE_AGE_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; timerval = br_timer_value(&p->forward_delay_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_FORWARD_DELAY_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; timerval = br_timer_value(&p->hold_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_HOLD_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BRPORT_MULTICAST_ROUTER, p->multicast_ctx.multicast_router) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, p->multicast_eht_hosts_limit) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, p->multicast_eht_hosts_cnt) || nla_put_u32(skb, IFLA_BRPORT_MCAST_N_GROUPS, br_multicast_ngroups_get(&p->multicast_ctx)) || nla_put_u32(skb, IFLA_BRPORT_MCAST_MAX_GROUPS, br_multicast_ngroups_get_max(&p->multicast_ctx))) return -EMSGSIZE; #endif /* we might be called only with br->lock */ rcu_read_lock(); backup_p = rcu_dereference(p->backup_port); if (backup_p) nla_put_u32(skb, IFLA_BRPORT_BACKUP_PORT, backup_p->dev->ifindex); rcu_read_unlock(); if (p->backup_nhid && nla_put_u32(skb, IFLA_BRPORT_BACKUP_NHID, p->backup_nhid)) return -EMSGSIZE; return 0; } static int br_fill_ifvlaninfo_range(struct sk_buff *skb, u16 vid_start, u16 vid_end, u16 flags) { struct bridge_vlan_info vinfo; if ((vid_end - vid_start) > 0) { /* add range to skb */ vinfo.vid = vid_start; vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_BEGIN; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; vinfo.vid = vid_end; vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_END; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } else { vinfo.vid = vid_start; vinfo.flags = flags; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb, struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *v; u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; u16 flags, pvid; int err = 0; /* Pack IFLA_BRIDGE_VLAN_INFO's for every vlan * and mark vlan info with begin and end flags * if vlaninfo represents a range */ pvid = br_get_pvid(vg); list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { flags = 0; if (!br_vlan_should_use(v)) continue; if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { vid_range_end = v->vid; continue; } else { err = br_fill_ifvlaninfo_range(skb, vid_range_start, vid_range_end, vid_range_flags); if (err) return err; } initvars: vid_range_start = v->vid; vid_range_end = v->vid; vid_range_flags = flags; } if (vid_range_start != 0) { /* Call it once more to send any left over vlans */ err = br_fill_ifvlaninfo_range(skb, vid_range_start, vid_range_end, vid_range_flags); if (err) return err; } return 0; } static int br_fill_ifvlaninfo(struct sk_buff *skb, struct net_bridge_vlan_group *vg) { struct bridge_vlan_info vinfo; struct net_bridge_vlan *v; u16 pvid; pvid = br_get_pvid(vg); list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { if (!br_vlan_should_use(v)) continue; vinfo.vid = v->vid; vinfo.flags = 0; if (v->vid == pvid) vinfo.flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } /* * Create one netlink message for one interface * Contains port and master info as well as carrier and bridge state. */ static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *port, u32 pid, u32 seq, int event, unsigned int flags, u32 filter_mask, const struct net_device *dev, bool getlink) { u8 operstate = netif_running(dev) ? READ_ONCE(dev->operstate) : IF_OPER_DOWN; struct nlattr *af = NULL; struct net_bridge *br; struct ifinfomsg *hdr; struct nlmsghdr *nlh; if (port) br = port->br; else br = netdev_priv(dev); br_debug(br, "br_fill_ifinfo event %d port %s master %s\n", event, dev->name, br->dev->name); nlh = nlmsg_put(skb, pid, seq, event, sizeof(*hdr), flags); if (nlh == NULL) return -EMSGSIZE; hdr = nlmsg_data(nlh); hdr->ifi_family = AF_BRIDGE; hdr->__ifi_pad = 0; hdr->ifi_type = dev->type; hdr->ifi_index = dev->ifindex; hdr->ifi_flags = netif_get_flags(dev); hdr->ifi_change = 0; if (nla_put_string(skb, IFLA_IFNAME, dev->name) || nla_put_u32(skb, IFLA_MASTER, br->dev->ifindex) || nla_put_u32(skb, IFLA_MTU, dev->mtu) || nla_put_u8(skb, IFLA_OPERSTATE, operstate) || (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || (dev->ifindex != dev_get_iflink(dev) && nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev)))) goto nla_put_failure; if (event == RTM_NEWLINK && port) { struct nlattr *nest; nest = nla_nest_start(skb, IFLA_PROTINFO); if (nest == NULL || br_port_fill_attrs(skb, port) < 0) goto nla_put_failure; nla_nest_end(skb, nest); } if (filter_mask & (RTEXT_FILTER_BRVLAN | RTEXT_FILTER_BRVLAN_COMPRESSED | RTEXT_FILTER_MRP | RTEXT_FILTER_CFM_CONFIG | RTEXT_FILTER_CFM_STATUS | RTEXT_FILTER_MST)) { af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!af) goto nla_put_failure; } /* Check if the VID information is requested */ if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { struct net_bridge_vlan_group *vg; int err; /* RCU needed because of the VLAN locking rules (rcu || rtnl) */ rcu_read_lock(); if (port) vg = nbp_vlan_group_rcu(port); else vg = br_vlan_group_rcu(br); if (!vg || !vg->num_vlans) { rcu_read_unlock(); goto done; } if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) err = br_fill_ifvlaninfo_compressed(skb, vg); else err = br_fill_ifvlaninfo(skb, vg); if (port && (port->flags & BR_VLAN_TUNNEL)) err = br_fill_vlan_tunnel_info(skb, vg); rcu_read_unlock(); if (err) goto nla_put_failure; } if (filter_mask & RTEXT_FILTER_MRP) { int err; if (!br_mrp_enabled(br) || port) goto done; rcu_read_lock(); err = br_mrp_fill_info(skb, br); rcu_read_unlock(); if (err) goto nla_put_failure; } if (filter_mask & (RTEXT_FILTER_CFM_CONFIG | RTEXT_FILTER_CFM_STATUS)) { struct nlattr *cfm_nest = NULL; int err; if (!br_cfm_created(br) || port) goto done; cfm_nest = nla_nest_start(skb, IFLA_BRIDGE_CFM); if (!cfm_nest) goto nla_put_failure; if (filter_mask & RTEXT_FILTER_CFM_CONFIG) { rcu_read_lock(); err = br_cfm_config_fill_info(skb, br); rcu_read_unlock(); if (err) goto nla_put_failure; } if (filter_mask & RTEXT_FILTER_CFM_STATUS) { rcu_read_lock(); err = br_cfm_status_fill_info(skb, br, getlink); rcu_read_unlock(); if (err) goto nla_put_failure; } nla_nest_end(skb, cfm_nest); } if ((filter_mask & RTEXT_FILTER_MST) && br_opt_get(br, BROPT_MST_ENABLED) && port) { const struct net_bridge_vlan_group *vg = nbp_vlan_group(port); struct nlattr *mst_nest; int err; if (!vg || !vg->num_vlans) goto done; mst_nest = nla_nest_start(skb, IFLA_BRIDGE_MST); if (!mst_nest) goto nla_put_failure; err = br_mst_fill_info(skb, vg); if (err) goto nla_put_failure; nla_nest_end(skb, mst_nest); } done: if (af) { if (nlmsg_get_pos(skb) - (void *)af > nla_attr_size(0)) nla_nest_end(skb, af); else nla_nest_cancel(skb, af); } nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } void br_info_notify(int event, const struct net_bridge *br, const struct net_bridge_port *port, u32 filter) { struct net_device *dev; struct sk_buff *skb; int err = -ENOBUFS; struct net *net; u16 port_no = 0; if (WARN_ON(!port && !br)) return; if (port) { dev = port->dev; br = port->br; port_no = port->port_no; } else { dev = br->dev; } net = dev_net(dev); br_debug(br, "port %u(%s) event %d\n", port_no, dev->name, event); skb = nlmsg_new(br_nlmsg_size(dev, filter), GFP_ATOMIC); if (skb == NULL) goto errout; err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev, false); if (err < 0) { /* -EMSGSIZE implies BUG in br_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_LINK, err); } /* Notify listeners of a change in bridge or port information */ void br_ifinfo_notify(int event, const struct net_bridge *br, const struct net_bridge_port *port) { u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED; br_info_notify(event, br, port, filter); } /* * Dump information about all ports, in response to GETLINK */ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags) { struct net_bridge_port *port = br_port_get_rtnl(dev); if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN) && !(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) && !(filter_mask & RTEXT_FILTER_MRP) && !(filter_mask & RTEXT_FILTER_CFM_CONFIG) && !(filter_mask & RTEXT_FILTER_CFM_STATUS)) return 0; return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags, filter_mask, dev, true); } static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, int cmd, struct bridge_vlan_info *vinfo, bool *changed, struct netlink_ext_ack *extack) { bool curr_change; int err = 0; switch (cmd) { case RTM_SETLINK: if (p) { /* if the MASTER flag is set this will act on the global * per-VLAN entry as well */ err = nbp_vlan_add(p, vinfo->vid, vinfo->flags, &curr_change, extack); } else { vinfo->flags |= BRIDGE_VLAN_INFO_BRENTRY; err = br_vlan_add(br, vinfo->vid, vinfo->flags, &curr_change, extack); } if (curr_change) *changed = true; break; case RTM_DELLINK: if (p) { if (!nbp_vlan_delete(p, vinfo->vid)) *changed = true; if ((vinfo->flags & BRIDGE_VLAN_INFO_MASTER) && !br_vlan_delete(p->br, vinfo->vid)) *changed = true; } else if (!br_vlan_delete(br, vinfo->vid)) { *changed = true; } break; } return err; } int br_process_vlan_info(struct net_bridge *br, struct net_bridge_port *p, int cmd, struct bridge_vlan_info *vinfo_curr, struct bridge_vlan_info **vinfo_last, bool *changed, struct netlink_ext_ack *extack) { int err, rtm_cmd; if (!br_vlan_valid_id(vinfo_curr->vid, extack)) return -EINVAL; /* needed for vlan-only NEWVLAN/DELVLAN notifications */ rtm_cmd = br_afspec_cmd_to_rtm(cmd); if (vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { if (!br_vlan_valid_range(vinfo_curr, *vinfo_last, extack)) return -EINVAL; *vinfo_last = vinfo_curr; return 0; } if (*vinfo_last) { struct bridge_vlan_info tmp_vinfo; int v, v_change_start = 0; if (!br_vlan_valid_range(vinfo_curr, *vinfo_last, extack)) return -EINVAL; memcpy(&tmp_vinfo, *vinfo_last, sizeof(struct bridge_vlan_info)); for (v = (*vinfo_last)->vid; v <= vinfo_curr->vid; v++) { bool curr_change = false; tmp_vinfo.vid = v; err = br_vlan_info(br, p, cmd, &tmp_vinfo, &curr_change, extack); if (err) break; if (curr_change) { *changed = curr_change; if (!v_change_start) v_change_start = v; } else { /* nothing to notify yet */ if (!v_change_start) continue; br_vlan_notify(br, p, v_change_start, v - 1, rtm_cmd); v_change_start = 0; } cond_resched(); } /* v_change_start is set only if the last/whole range changed */ if (v_change_start) br_vlan_notify(br, p, v_change_start, v - 1, rtm_cmd); *vinfo_last = NULL; return err; } err = br_vlan_info(br, p, cmd, vinfo_curr, changed, extack); if (*changed) br_vlan_notify(br, p, vinfo_curr->vid, 0, rtm_cmd); return err; } static int br_afspec(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *af_spec, int cmd, bool *changed, struct netlink_ext_ack *extack) { struct bridge_vlan_info *vinfo_curr = NULL; struct bridge_vlan_info *vinfo_last = NULL; struct nlattr *attr; struct vtunnel_info tinfo_last = {}; struct vtunnel_info tinfo_curr = {}; int err = 0, rem; nla_for_each_nested(attr, af_spec, rem) { err = 0; switch (nla_type(attr)) { case IFLA_BRIDGE_VLAN_TUNNEL_INFO: if (!p || !(p->flags & BR_VLAN_TUNNEL)) return -EINVAL; err = br_parse_vlan_tunnel_info(attr, &tinfo_curr); if (err) return err; err = br_process_vlan_tunnel_info(br, p, cmd, &tinfo_curr, &tinfo_last, changed); if (err) return err; break; case IFLA_BRIDGE_VLAN_INFO: if (nla_len(attr) != sizeof(struct bridge_vlan_info)) return -EINVAL; vinfo_curr = nla_data(attr); err = br_process_vlan_info(br, p, cmd, vinfo_curr, &vinfo_last, changed, extack); if (err) return err; break; case IFLA_BRIDGE_MRP: err = br_mrp_parse(br, p, attr, cmd, extack); if (err) return err; break; case IFLA_BRIDGE_CFM: err = br_cfm_parse(br, p, attr, cmd, extack); if (err) return err; break; case IFLA_BRIDGE_MST: if (!p) { NL_SET_ERR_MSG(extack, "MST states can only be set on bridge ports"); return -EINVAL; } if (cmd != RTM_SETLINK) { NL_SET_ERR_MSG(extack, "MST states can only be set through RTM_SETLINK"); return -EINVAL; } err = br_mst_process(p, attr, extack); if (err) return err; break; } } return err; } static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_UNSPEC] = { .strict_start_type = IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT + 1 }, [IFLA_BRPORT_STATE] = { .type = NLA_U8 }, [IFLA_BRPORT_COST] = { .type = NLA_U32 }, [IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 }, [IFLA_BRPORT_MODE] = { .type = NLA_U8 }, [IFLA_BRPORT_GUARD] = { .type = NLA_U8 }, [IFLA_BRPORT_PROTECT] = { .type = NLA_U8 }, [IFLA_BRPORT_FAST_LEAVE]= { .type = NLA_U8 }, [IFLA_BRPORT_LEARNING] = { .type = NLA_U8 }, [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 }, [IFLA_BRPORT_MULTICAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BRPORT_MCAST_TO_UCAST] = { .type = NLA_U8 }, [IFLA_BRPORT_MCAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_BCAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_VLAN_TUNNEL] = { .type = NLA_U8 }, [IFLA_BRPORT_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 }, [IFLA_BRPORT_ISOLATED] = { .type = NLA_U8 }, [IFLA_BRPORT_LOCKED] = { .type = NLA_U8 }, [IFLA_BRPORT_MAB] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_N_GROUPS] = { .type = NLA_REJECT }, [IFLA_BRPORT_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, [IFLA_BRPORT_NEIGH_VLAN_SUPPRESS] = NLA_POLICY_MAX(NLA_U8, 1), [IFLA_BRPORT_BACKUP_NHID] = { .type = NLA_U32 }, }; /* Change the state of the port and notify spanning tree */ static int br_set_port_state(struct net_bridge_port *p, u8 state) { if (state > BR_STATE_BLOCKING) return -EINVAL; /* if kernel STP is running, don't allow changes */ if (p->br->stp_enabled == BR_KERNEL_STP) return -EBUSY; /* if device is not up, change is not allowed * if link is not present, only allowable state is disabled */ if (!netif_running(p->dev) || (!netif_oper_up(p->dev) && state != BR_STATE_DISABLED)) return -ENETDOWN; br_set_state(p, state); br_port_state_selection(p->br); return 0; } /* Set/clear or port flags based on attribute */ static void br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[], int attrtype, unsigned long mask) { if (!tb[attrtype]) return; if (nla_get_u8(tb[attrtype])) p->flags |= mask; else p->flags &= ~mask; } /* Process bridge protocol info on port */ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], struct netlink_ext_ack *extack) { unsigned long old_flags, changed_mask; bool br_vlan_tunnel_old; int err; old_flags = p->flags; br_vlan_tunnel_old = (old_flags & BR_VLAN_TUNNEL) ? true : false; br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE); br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD); br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE, BR_MULTICAST_FAST_LEAVE); br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK); br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD); br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_TO_UCAST, BR_MULTICAST_TO_UNICAST); br_set_port_flag(p, tb, IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD); br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); br_set_port_flag(p, tb, IFLA_BRPORT_VLAN_TUNNEL, BR_VLAN_TUNNEL); br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, BR_NEIGH_SUPPRESS); br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED); br_set_port_flag(p, tb, IFLA_BRPORT_LOCKED, BR_PORT_LOCKED); br_set_port_flag(p, tb, IFLA_BRPORT_MAB, BR_PORT_MAB); br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_VLAN_SUPPRESS, BR_NEIGH_VLAN_SUPPRESS); if ((p->flags & BR_PORT_MAB) && (!(p->flags & BR_PORT_LOCKED) || !(p->flags & BR_LEARNING))) { NL_SET_ERR_MSG(extack, "Bridge port must be locked and have learning enabled when MAB is enabled"); p->flags = old_flags; return -EINVAL; } else if (!(p->flags & BR_PORT_MAB) && (old_flags & BR_PORT_MAB)) { struct net_bridge_fdb_flush_desc desc = { .flags = BIT(BR_FDB_LOCKED), .flags_mask = BIT(BR_FDB_LOCKED), .port_ifindex = p->dev->ifindex, }; br_fdb_flush(p->br, &desc); } changed_mask = old_flags ^ p->flags; err = br_switchdev_set_port_flag(p, p->flags, changed_mask, extack); if (err) { p->flags = old_flags; return err; } if (br_vlan_tunnel_old && !(p->flags & BR_VLAN_TUNNEL)) nbp_vlan_tunnel_info_flush(p); br_port_flags_change(p, changed_mask); if (tb[IFLA_BRPORT_COST]) { err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST])); if (err) return err; } if (tb[IFLA_BRPORT_PRIORITY]) { err = br_stp_set_port_priority(p, nla_get_u16(tb[IFLA_BRPORT_PRIORITY])); if (err) return err; } if (tb[IFLA_BRPORT_STATE]) { err = br_set_port_state(p, nla_get_u8(tb[IFLA_BRPORT_STATE])); if (err) return err; } if (tb[IFLA_BRPORT_FLUSH]) br_fdb_delete_by_port(p->br, p, 0, 0); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (tb[IFLA_BRPORT_MULTICAST_ROUTER]) { u8 mcast_router = nla_get_u8(tb[IFLA_BRPORT_MULTICAST_ROUTER]); err = br_multicast_set_port_router(&p->multicast_ctx, mcast_router); if (err) return err; } if (tb[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT]) { u32 hlimit; hlimit = nla_get_u32(tb[IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT]); err = br_multicast_eht_set_hosts_limit(p, hlimit); if (err) return err; } if (tb[IFLA_BRPORT_MCAST_MAX_GROUPS]) { u32 max_groups; max_groups = nla_get_u32(tb[IFLA_BRPORT_MCAST_MAX_GROUPS]); br_multicast_ngroups_set_max(&p->multicast_ctx, max_groups); } #endif if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) { u16 fwd_mask = nla_get_u16(tb[IFLA_BRPORT_GROUP_FWD_MASK]); if (fwd_mask & BR_GROUPFWD_MACPAUSE) return -EINVAL; p->group_fwd_mask = fwd_mask; } if (tb[IFLA_BRPORT_BACKUP_PORT]) { struct net_device *backup_dev = NULL; u32 backup_ifindex; backup_ifindex = nla_get_u32(tb[IFLA_BRPORT_BACKUP_PORT]); if (backup_ifindex) { backup_dev = __dev_get_by_index(dev_net(p->dev), backup_ifindex); if (!backup_dev) return -ENOENT; } err = nbp_backup_change(p, backup_dev); if (err) return err; } if (tb[IFLA_BRPORT_BACKUP_NHID]) { u32 backup_nhid = nla_get_u32(tb[IFLA_BRPORT_BACKUP_NHID]); WRITE_ONCE(p->backup_nhid, backup_nhid); } return 0; } /* Change state and parameters on port. */ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, struct netlink_ext_ack *extack) { struct net_bridge *br = (struct net_bridge *)netdev_priv(dev); struct nlattr *tb[IFLA_BRPORT_MAX + 1]; struct net_bridge_port *p; struct nlattr *protinfo; struct nlattr *afspec; bool changed = false; int err = 0; protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO); afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (!protinfo && !afspec) return 0; p = br_port_get_rtnl(dev); /* We want to accept dev as bridge itself if the AF_SPEC * is set to see if someone is setting vlan info on the bridge */ if (!p && !afspec) return -EINVAL; if (p && protinfo) { if (protinfo->nla_type & NLA_F_NESTED) { err = nla_parse_nested_deprecated(tb, IFLA_BRPORT_MAX, protinfo, br_port_policy, NULL); if (err) return err; spin_lock_bh(&p->br->lock); err = br_setport(p, tb, extack); spin_unlock_bh(&p->br->lock); } else { /* Binary compatibility with old RSTP */ if (nla_len(protinfo) < sizeof(u8)) return -EINVAL; spin_lock_bh(&p->br->lock); err = br_set_port_state(p, nla_get_u8(protinfo)); spin_unlock_bh(&p->br->lock); } if (err) goto out; changed = true; } if (afspec) err = br_afspec(br, p, afspec, RTM_SETLINK, &changed, extack); if (changed) br_ifinfo_notify(RTM_NEWLINK, br, p); out: return err; } /* Delete port information */ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) { struct net_bridge *br = (struct net_bridge *)netdev_priv(dev); struct net_bridge_port *p; struct nlattr *afspec; bool changed = false; int err = 0; afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (!afspec) return 0; p = br_port_get_rtnl(dev); /* We want to accept dev as bridge itself as well */ if (!p && !netif_is_bridge_master(dev)) return -EINVAL; err = br_afspec(br, p, afspec, RTM_DELLINK, &changed, NULL); if (changed) /* Send RTM_NEWLINK because userspace * expects RTM_NEWLINK for vlan dels */ br_ifinfo_notify(RTM_NEWLINK, br, p); return err; } static int br_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (!data) return 0; #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (data[IFLA_BR_VLAN_PROTOCOL] && !eth_type_vlan(nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL]))) return -EPROTONOSUPPORT; if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); if (defpvid >= VLAN_VID_MASK) return -EINVAL; } #endif return 0; } static int br_port_slave_changelink(struct net_device *brdev, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(brdev); int ret; if (!data) return 0; spin_lock_bh(&br->lock); ret = br_setport(br_port_get_rtnl(dev), data, extack); spin_unlock_bh(&br->lock); return ret; } static int br_port_fill_slave_info(struct sk_buff *skb, const struct net_device *brdev, const struct net_device *dev) { return br_port_fill_attrs(skb, br_port_get_rtnl(dev)); } static size_t br_port_get_slave_size(const struct net_device *brdev, const struct net_device *dev) { return br_port_info_size(); } static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_UNSPEC] = { .strict_start_type = IFLA_BR_FDB_N_LEARNED }, [IFLA_BR_FORWARD_DELAY] = { .type = NLA_U32 }, [IFLA_BR_HELLO_TIME] = { .type = NLA_U32 }, [IFLA_BR_MAX_AGE] = { .type = NLA_U32 }, [IFLA_BR_AGEING_TIME] = { .type = NLA_U32 }, [IFLA_BR_STP_STATE] = { .type = NLA_U32 }, [IFLA_BR_PRIORITY] = { .type = NLA_U16 }, [IFLA_BR_VLAN_FILTERING] = { .type = NLA_U8 }, [IFLA_BR_VLAN_PROTOCOL] = { .type = NLA_U16 }, [IFLA_BR_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BR_GROUP_ADDR] = { .type = NLA_BINARY, .len = ETH_ALEN }, [IFLA_BR_MCAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_SNOOPING] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERY_USE_IFADDR] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERIER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_HASH_ELASTICITY] = { .type = NLA_U32 }, [IFLA_BR_MCAST_HASH_MAX] = { .type = NLA_U32 }, [IFLA_BR_MCAST_LAST_MEMBER_CNT] = { .type = NLA_U32 }, [IFLA_BR_MCAST_STARTUP_QUERY_CNT] = { .type = NLA_U32 }, [IFLA_BR_MCAST_LAST_MEMBER_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_MEMBERSHIP_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERIER_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERY_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERY_RESPONSE_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_STARTUP_QUERY_INTVL] = { .type = NLA_U64 }, [IFLA_BR_NF_CALL_IPTABLES] = { .type = NLA_U8 }, [IFLA_BR_NF_CALL_IP6TABLES] = { .type = NLA_U8 }, [IFLA_BR_NF_CALL_ARPTABLES] = { .type = NLA_U8 }, [IFLA_BR_VLAN_DEFAULT_PVID] = { .type = NLA_U16 }, [IFLA_BR_VLAN_STATS_ENABLED] = { .type = NLA_U8 }, [IFLA_BR_MCAST_STATS_ENABLED] = { .type = NLA_U8 }, [IFLA_BR_MCAST_IGMP_VERSION] = { .type = NLA_U8 }, [IFLA_BR_MCAST_MLD_VERSION] = { .type = NLA_U8 }, [IFLA_BR_VLAN_STATS_PER_PORT] = { .type = NLA_U8 }, [IFLA_BR_MULTI_BOOLOPT] = NLA_POLICY_EXACT_LEN(sizeof(struct br_boolopt_multi)), [IFLA_BR_FDB_N_LEARNED] = { .type = NLA_REJECT }, [IFLA_BR_FDB_MAX_LEARNED] = { .type = NLA_U32 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(brdev); int err; if (!data) return 0; if (data[IFLA_BR_FORWARD_DELAY]) { err = br_set_forward_delay(br, nla_get_u32(data[IFLA_BR_FORWARD_DELAY])); if (err) return err; } if (data[IFLA_BR_HELLO_TIME]) { err = br_set_hello_time(br, nla_get_u32(data[IFLA_BR_HELLO_TIME])); if (err) return err; } if (data[IFLA_BR_MAX_AGE]) { err = br_set_max_age(br, nla_get_u32(data[IFLA_BR_MAX_AGE])); if (err) return err; } if (data[IFLA_BR_AGEING_TIME]) { err = br_set_ageing_time(br, nla_get_u32(data[IFLA_BR_AGEING_TIME])); if (err) return err; } if (data[IFLA_BR_STP_STATE]) { u32 stp_enabled = nla_get_u32(data[IFLA_BR_STP_STATE]); err = br_stp_set_enabled(br, stp_enabled, extack); if (err) return err; } if (data[IFLA_BR_PRIORITY]) { u32 priority = nla_get_u16(data[IFLA_BR_PRIORITY]); br_stp_set_bridge_priority(br, priority); } if (data[IFLA_BR_VLAN_FILTERING]) { u8 vlan_filter = nla_get_u8(data[IFLA_BR_VLAN_FILTERING]); err = br_vlan_filter_toggle(br, vlan_filter, extack); if (err) return err; } #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (data[IFLA_BR_VLAN_PROTOCOL]) { __be16 vlan_proto = nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL]); err = __br_vlan_set_proto(br, vlan_proto, extack); if (err) return err; } if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); err = __br_vlan_set_default_pvid(br, defpvid, extack); if (err) return err; } if (data[IFLA_BR_VLAN_STATS_ENABLED]) { __u8 vlan_stats = nla_get_u8(data[IFLA_BR_VLAN_STATS_ENABLED]); err = br_vlan_set_stats(br, vlan_stats); if (err) return err; } if (data[IFLA_BR_VLAN_STATS_PER_PORT]) { __u8 per_port = nla_get_u8(data[IFLA_BR_VLAN_STATS_PER_PORT]); err = br_vlan_set_stats_per_port(br, per_port); if (err) return err; } #endif if (data[IFLA_BR_GROUP_FWD_MASK]) { u16 fwd_mask = nla_get_u16(data[IFLA_BR_GROUP_FWD_MASK]); if (fwd_mask & BR_GROUPFWD_RESTRICTED) return -EINVAL; br->group_fwd_mask = fwd_mask; } if (data[IFLA_BR_GROUP_ADDR]) { u8 new_addr[ETH_ALEN]; if (nla_len(data[IFLA_BR_GROUP_ADDR]) != ETH_ALEN) return -EINVAL; memcpy(new_addr, nla_data(data[IFLA_BR_GROUP_ADDR]), ETH_ALEN); if (!is_link_local_ether_addr(new_addr)) return -EINVAL; if (new_addr[5] == 1 || /* 802.3x Pause address */ new_addr[5] == 2 || /* 802.3ad Slow protocols */ new_addr[5] == 3) /* 802.1X PAE address */ return -EINVAL; spin_lock_bh(&br->lock); memcpy(br->group_addr, new_addr, sizeof(br->group_addr)); spin_unlock_bh(&br->lock); br_opt_toggle(br, BROPT_GROUP_ADDR_SET, true); br_recalculate_fwd_mask(br); } if (data[IFLA_BR_FDB_FLUSH]) { struct net_bridge_fdb_flush_desc desc = { .flags_mask = BIT(BR_FDB_STATIC) }; br_fdb_flush(br, &desc); } #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (data[IFLA_BR_MCAST_ROUTER]) { u8 multicast_router = nla_get_u8(data[IFLA_BR_MCAST_ROUTER]); err = br_multicast_set_router(&br->multicast_ctx, multicast_router); if (err) return err; } if (data[IFLA_BR_MCAST_SNOOPING]) { u8 mcast_snooping = nla_get_u8(data[IFLA_BR_MCAST_SNOOPING]); err = br_multicast_toggle(br, mcast_snooping, extack); if (err) return err; } if (data[IFLA_BR_MCAST_QUERY_USE_IFADDR]) { u8 val; val = nla_get_u8(data[IFLA_BR_MCAST_QUERY_USE_IFADDR]); br_opt_toggle(br, BROPT_MULTICAST_QUERY_USE_IFADDR, !!val); } if (data[IFLA_BR_MCAST_QUERIER]) { u8 mcast_querier = nla_get_u8(data[IFLA_BR_MCAST_QUERIER]); err = br_multicast_set_querier(&br->multicast_ctx, mcast_querier); if (err) return err; } if (data[IFLA_BR_MCAST_HASH_ELASTICITY]) br_warn(br, "the hash_elasticity option has been deprecated and is always %u\n", RHT_ELASTICITY); if (data[IFLA_BR_MCAST_HASH_MAX]) br->hash_max = nla_get_u32(data[IFLA_BR_MCAST_HASH_MAX]); if (data[IFLA_BR_MCAST_LAST_MEMBER_CNT]) { u32 val = nla_get_u32(data[IFLA_BR_MCAST_LAST_MEMBER_CNT]); br->multicast_ctx.multicast_last_member_count = val; } if (data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]) { u32 val = nla_get_u32(data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]); br->multicast_ctx.multicast_startup_query_count = val; } if (data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]); br->multicast_ctx.multicast_last_member_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]); br->multicast_ctx.multicast_membership_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_QUERIER_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERIER_INTVL]); br->multicast_ctx.multicast_querier_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_QUERY_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_INTVL]); br_multicast_set_query_intvl(&br->multicast_ctx, val); } if (data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]); br->multicast_ctx.multicast_query_response_interval = clock_t_to_jiffies(val); } if (data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]); br_multicast_set_startup_query_intvl(&br->multicast_ctx, val); } if (data[IFLA_BR_MCAST_STATS_ENABLED]) { __u8 mcast_stats; mcast_stats = nla_get_u8(data[IFLA_BR_MCAST_STATS_ENABLED]); br_opt_toggle(br, BROPT_MULTICAST_STATS_ENABLED, !!mcast_stats); } if (data[IFLA_BR_MCAST_IGMP_VERSION]) { __u8 igmp_version; igmp_version = nla_get_u8(data[IFLA_BR_MCAST_IGMP_VERSION]); err = br_multicast_set_igmp_version(&br->multicast_ctx, igmp_version); if (err) return err; } #if IS_ENABLED(CONFIG_IPV6) if (data[IFLA_BR_MCAST_MLD_VERSION]) { __u8 mld_version; mld_version = nla_get_u8(data[IFLA_BR_MCAST_MLD_VERSION]); err = br_multicast_set_mld_version(&br->multicast_ctx, mld_version); if (err) return err; } #endif #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (data[IFLA_BR_NF_CALL_IPTABLES]) { u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IPTABLES]); br_opt_toggle(br, BROPT_NF_CALL_IPTABLES, !!val); } if (data[IFLA_BR_NF_CALL_IP6TABLES]) { u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IP6TABLES]); br_opt_toggle(br, BROPT_NF_CALL_IP6TABLES, !!val); } if (data[IFLA_BR_NF_CALL_ARPTABLES]) { u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_ARPTABLES]); br_opt_toggle(br, BROPT_NF_CALL_ARPTABLES, !!val); } #endif if (data[IFLA_BR_MULTI_BOOLOPT]) { struct br_boolopt_multi *bm; bm = nla_data(data[IFLA_BR_MULTI_BOOLOPT]); err = br_boolopt_multi_toggle(br, bm, extack); if (err) return err; } if (data[IFLA_BR_FDB_MAX_LEARNED]) { u32 val = nla_get_u32(data[IFLA_BR_FDB_MAX_LEARNED]); WRITE_ONCE(br->fdb_max_learned, val); } return 0; } static int br_dev_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(dev); struct nlattr **data = params->data; struct nlattr **tb = params->tb; int err; err = register_netdevice(dev); if (err) return err; if (tb[IFLA_ADDRESS]) { spin_lock_bh(&br->lock); br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); spin_unlock_bh(&br->lock); } err = br_changelink(dev, tb, data, extack); if (err) br_dev_delete(dev, NULL); return err; } static size_t br_get_size(const struct net_device *brdev) { return nla_total_size(sizeof(u32)) + /* IFLA_BR_FORWARD_DELAY */ nla_total_size(sizeof(u32)) + /* IFLA_BR_HELLO_TIME */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MAX_AGE */ nla_total_size(sizeof(u32)) + /* IFLA_BR_AGEING_TIME */ nla_total_size(sizeof(u32)) + /* IFLA_BR_STP_STATE */ nla_total_size(sizeof(u16)) + /* IFLA_BR_PRIORITY */ nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_FILTERING */ #ifdef CONFIG_BRIDGE_VLAN_FILTERING nla_total_size(sizeof(__be16)) + /* IFLA_BR_VLAN_PROTOCOL */ nla_total_size(sizeof(u16)) + /* IFLA_BR_VLAN_DEFAULT_PVID */ nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_STATS_ENABLED */ nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_STATS_PER_PORT */ #endif nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */ nla_total_size(sizeof(u16)) + /* IFLA_BR_ROOT_PORT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_ROOT_PATH_COST */ nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE */ nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE_DETECTED */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_HELLO_TIMER */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_TCN_TIMER */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_GC_TIMER */ nla_total_size(ETH_ALEN) + /* IFLA_BR_GROUP_ADDR */ nla_total_size(sizeof(u32)) + /* IFLA_BR_FDB_N_LEARNED */ nla_total_size(sizeof(u32)) + /* IFLA_BR_FDB_MAX_LEARNED */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_STATS_ENABLED */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_LAST_MEMBER_CNT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_STARTUP_QUERY_CNT */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_LAST_MEMBER_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_MEMBERSHIP_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERIER_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_RESPONSE_INTVL */ nla_total_size_64bit(sizeof(u64)) + /* IFLA_BR_MCAST_STARTUP_QUERY_INTVL */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_IGMP_VERSION */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_MLD_VERSION */ br_multicast_querier_state_size() + /* IFLA_BR_MCAST_QUERIER_STATE */ #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IPTABLES */ nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IP6TABLES */ nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_ARPTABLES */ #endif nla_total_size(sizeof(struct br_boolopt_multi)) + /* IFLA_BR_MULTI_BOOLOPT */ 0; } static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) { struct net_bridge *br = netdev_priv(brdev); u32 forward_delay = jiffies_to_clock_t(br->forward_delay); u32 hello_time = jiffies_to_clock_t(br->hello_time); u32 age_time = jiffies_to_clock_t(br->max_age); u32 ageing_time = jiffies_to_clock_t(br->ageing_time); u32 stp_enabled = br->stp_enabled; u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; u8 vlan_enabled = br_vlan_enabled(br->dev); struct br_boolopt_multi bm; u64 clockval; clockval = br_timer_value(&br->hello_timer); if (nla_put_u64_64bit(skb, IFLA_BR_HELLO_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = br_timer_value(&br->tcn_timer); if (nla_put_u64_64bit(skb, IFLA_BR_TCN_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = br_timer_value(&br->topology_change_timer); if (nla_put_u64_64bit(skb, IFLA_BR_TOPOLOGY_CHANGE_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = br_timer_value(&br->gc_work.timer); if (nla_put_u64_64bit(skb, IFLA_BR_GC_TIMER, clockval, IFLA_BR_PAD)) return -EMSGSIZE; br_boolopt_multi_get(br, &bm); if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || nla_put_u32(skb, IFLA_BR_MAX_AGE, age_time) || nla_put_u32(skb, IFLA_BR_AGEING_TIME, ageing_time) || nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) || nla_put_u16(skb, IFLA_BR_PRIORITY, priority) || nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled) || nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, br->group_fwd_mask) || nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(struct ifla_bridge_id), &br->bridge_id) || nla_put(skb, IFLA_BR_ROOT_ID, sizeof(struct ifla_bridge_id), &br->designated_root) || nla_put_u16(skb, IFLA_BR_ROOT_PORT, br->root_port) || nla_put_u32(skb, IFLA_BR_ROOT_PATH_COST, br->root_path_cost) || nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE, br->topology_change) || nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE_DETECTED, br->topology_change_detected) || nla_put(skb, IFLA_BR_GROUP_ADDR, ETH_ALEN, br->group_addr) || nla_put(skb, IFLA_BR_MULTI_BOOLOPT, sizeof(bm), &bm) || nla_put_u32(skb, IFLA_BR_FDB_N_LEARNED, atomic_read(&br->fdb_n_learned)) || nla_put_u32(skb, IFLA_BR_FDB_MAX_LEARNED, br->fdb_max_learned)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (nla_put_be16(skb, IFLA_BR_VLAN_PROTOCOL, br->vlan_proto) || nla_put_u16(skb, IFLA_BR_VLAN_DEFAULT_PVID, br->default_pvid) || nla_put_u8(skb, IFLA_BR_VLAN_STATS_ENABLED, br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) || nla_put_u8(skb, IFLA_BR_VLAN_STATS_PER_PORT, br_opt_get(br, BROPT_VLAN_STATS_PER_PORT))) return -EMSGSIZE; #endif #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_ctx.multicast_router) || nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, br_opt_get(br, BROPT_MULTICAST_ENABLED)) || nla_put_u8(skb, IFLA_BR_MCAST_QUERY_USE_IFADDR, br_opt_get(br, BROPT_MULTICAST_QUERY_USE_IFADDR)) || nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_ctx.multicast_querier) || nla_put_u8(skb, IFLA_BR_MCAST_STATS_ENABLED, br_opt_get(br, BROPT_MULTICAST_STATS_ENABLED)) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY, RHT_ELASTICITY) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max) || nla_put_u32(skb, IFLA_BR_MCAST_LAST_MEMBER_CNT, br->multicast_ctx.multicast_last_member_count) || nla_put_u32(skb, IFLA_BR_MCAST_STARTUP_QUERY_CNT, br->multicast_ctx.multicast_startup_query_count) || nla_put_u8(skb, IFLA_BR_MCAST_IGMP_VERSION, br->multicast_ctx.multicast_igmp_version) || br_multicast_dump_querier_state(skb, &br->multicast_ctx, IFLA_BR_MCAST_QUERIER_STATE)) return -EMSGSIZE; #if IS_ENABLED(CONFIG_IPV6) if (nla_put_u8(skb, IFLA_BR_MCAST_MLD_VERSION, br->multicast_ctx.multicast_mld_version)) return -EMSGSIZE; #endif clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_last_member_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_LAST_MEMBER_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_membership_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_MEMBERSHIP_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_querier_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERIER_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_query_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERY_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_query_response_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_startup_query_interval); if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_STARTUP_QUERY_INTVL, clockval, IFLA_BR_PAD)) return -EMSGSIZE; #endif #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_u8(skb, IFLA_BR_NF_CALL_IPTABLES, br_opt_get(br, BROPT_NF_CALL_IPTABLES) ? 1 : 0) || nla_put_u8(skb, IFLA_BR_NF_CALL_IP6TABLES, br_opt_get(br, BROPT_NF_CALL_IP6TABLES) ? 1 : 0) || nla_put_u8(skb, IFLA_BR_NF_CALL_ARPTABLES, br_opt_get(br, BROPT_NF_CALL_ARPTABLES) ? 1 : 0)) return -EMSGSIZE; #endif return 0; } static size_t br_get_linkxstats_size(const struct net_device *dev, int attr) { struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge *br; int numvls = 0; switch (attr) { case IFLA_STATS_LINK_XSTATS: br = netdev_priv(dev); vg = br_vlan_group(br); break; case IFLA_STATS_LINK_XSTATS_SLAVE: p = br_port_get_rtnl(dev); if (!p) return 0; vg = nbp_vlan_group(p); break; default: return 0; } if (vg) { /* we need to count all, even placeholder entries */ list_for_each_entry(v, &vg->vlan_list, vlist) numvls++; } return numvls * nla_total_size(sizeof(struct bridge_vlan_xstats)) + nla_total_size_64bit(sizeof(struct br_mcast_stats)) + (p ? nla_total_size_64bit(sizeof(p->stp_xstats)) : 0) + nla_total_size(0); } static int br_fill_linkxstats(struct sk_buff *skb, const struct net_device *dev, int *prividx, int attr) { struct nlattr *nla __maybe_unused; struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; struct net_bridge_vlan *v; struct net_bridge *br; struct nlattr *nest; int vl_idx = 0; switch (attr) { case IFLA_STATS_LINK_XSTATS: br = netdev_priv(dev); vg = br_vlan_group(br); break; case IFLA_STATS_LINK_XSTATS_SLAVE: p = br_port_get_rtnl(dev); if (!p) return 0; br = p->br; vg = nbp_vlan_group(p); break; default: return -EINVAL; } nest = nla_nest_start_noflag(skb, LINK_XSTATS_TYPE_BRIDGE); if (!nest) return -EMSGSIZE; if (vg) { u16 pvid; pvid = br_get_pvid(vg); list_for_each_entry(v, &vg->vlan_list, vlist) { struct bridge_vlan_xstats vxi; struct pcpu_sw_netstats stats; if (++vl_idx < *prividx) continue; memset(&vxi, 0, sizeof(vxi)); vxi.vid = v->vid; vxi.flags = v->flags; if (v->vid == pvid) vxi.flags |= BRIDGE_VLAN_INFO_PVID; br_vlan_get_stats(v, &stats); vxi.rx_bytes = u64_stats_read(&stats.rx_bytes); vxi.rx_packets = u64_stats_read(&stats.rx_packets); vxi.tx_bytes = u64_stats_read(&stats.tx_bytes); vxi.tx_packets = u64_stats_read(&stats.tx_packets); if (nla_put(skb, BRIDGE_XSTATS_VLAN, sizeof(vxi), &vxi)) goto nla_put_failure; } } #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (++vl_idx >= *prividx) { nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_MCAST, sizeof(struct br_mcast_stats), BRIDGE_XSTATS_PAD); if (!nla) goto nla_put_failure; br_multicast_get_stats(br, p, nla_data(nla)); } #endif if (p) { nla = nla_reserve_64bit(skb, BRIDGE_XSTATS_STP, sizeof(p->stp_xstats), BRIDGE_XSTATS_PAD); if (!nla) goto nla_put_failure; spin_lock_bh(&br->lock); memcpy(nla_data(nla), &p->stp_xstats, sizeof(p->stp_xstats)); spin_unlock_bh(&br->lock); } nla_nest_end(skb, nest); *prividx = 0; return 0; nla_put_failure: nla_nest_end(skb, nest); *prividx = vl_idx; return -EMSGSIZE; } static struct rtnl_af_ops br_af_ops __read_mostly = { .family = AF_BRIDGE, .get_link_af_size = br_get_link_af_size_filtered, }; struct rtnl_link_ops br_link_ops __read_mostly = { .kind = "bridge", .priv_size = sizeof(struct net_bridge), .setup = br_dev_setup, .maxtype = IFLA_BR_MAX, .policy = br_policy, .validate = br_validate, .newlink = br_dev_newlink, .changelink = br_changelink, .dellink = br_dev_delete, .get_size = br_get_size, .fill_info = br_fill_info, .fill_linkxstats = br_fill_linkxstats, .get_linkxstats_size = br_get_linkxstats_size, .slave_maxtype = IFLA_BRPORT_MAX, .slave_policy = br_port_policy, .slave_changelink = br_port_slave_changelink, .get_slave_size = br_port_get_slave_size, .fill_slave_info = br_port_fill_slave_info, }; int __init br_netlink_init(void) { int err; err = br_vlan_rtnl_init(); if (err) goto out; err = rtnl_af_register(&br_af_ops); if (err) goto out_vlan; err = rtnl_link_register(&br_link_ops); if (err) goto out_af; return 0; out_af: rtnl_af_unregister(&br_af_ops); out_vlan: br_vlan_rtnl_uninit(); out: return err; } void br_netlink_fini(void) { br_vlan_rtnl_uninit(); rtnl_af_unregister(&br_af_ops); rtnl_link_unregister(&br_link_ops); } |
| 10 10 10 7 5 10 8 5 3 3 3 8 3 3 3 3 3 24 24 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* Helper handling for netfilter. */ /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> * (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org> * (C) 2006-2012 Patrick McHardy <kaber@trash.net> */ #include <linux/types.h> #include <linux/netfilter.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/stddef.h> #include <linux/random.h> #include <linux/err.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/rculist.h> #include <linux/rtnetlink.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_log.h> #include <net/ip.h> static DEFINE_MUTEX(nf_ct_helper_mutex); struct hlist_head *nf_ct_helper_hash __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_helper_hash); unsigned int nf_ct_helper_hsize __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_helper_hsize); static unsigned int nf_ct_helper_count __read_mostly; static DEFINE_MUTEX(nf_ct_nat_helpers_mutex); static struct list_head nf_ct_nat_helpers __read_mostly; /* Stupid hash, but collision free for the default registrations of the * helpers currently in the kernel. */ static unsigned int helper_hash(const struct nf_conntrack_tuple *tuple) { return (((tuple->src.l3num << 8) | tuple->dst.protonum) ^ (__force __u16)tuple->src.u.all) % nf_ct_helper_hsize; } struct nf_conntrack_helper * __nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum) { struct nf_conntrack_helper *h; unsigned int i; for (i = 0; i < nf_ct_helper_hsize; i++) { hlist_for_each_entry_rcu(h, &nf_ct_helper_hash[i], hnode) { if (strcmp(h->name, name)) continue; if (h->tuple.src.l3num != NFPROTO_UNSPEC && h->tuple.src.l3num != l3num) continue; if (h->tuple.dst.protonum == protonum) return h; } } return NULL; } EXPORT_SYMBOL_GPL(__nf_conntrack_helper_find); struct nf_conntrack_helper * nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum) { struct nf_conntrack_helper *h; rcu_read_lock(); h = __nf_conntrack_helper_find(name, l3num, protonum); #ifdef CONFIG_MODULES if (h == NULL) { rcu_read_unlock(); if (request_module("nfct-helper-%s", name) == 0) { rcu_read_lock(); h = __nf_conntrack_helper_find(name, l3num, protonum); } else { return h; } } #endif if (h != NULL && !try_module_get(h->me)) h = NULL; if (h != NULL && !refcount_inc_not_zero(&h->refcnt)) { module_put(h->me); h = NULL; } rcu_read_unlock(); return h; } EXPORT_SYMBOL_GPL(nf_conntrack_helper_try_module_get); void nf_conntrack_helper_put(struct nf_conntrack_helper *helper) { refcount_dec(&helper->refcnt); module_put(helper->me); } EXPORT_SYMBOL_GPL(nf_conntrack_helper_put); static struct nf_conntrack_nat_helper * nf_conntrack_nat_helper_find(const char *mod_name) { struct nf_conntrack_nat_helper *cur; bool found = false; list_for_each_entry_rcu(cur, &nf_ct_nat_helpers, list) { if (!strcmp(cur->mod_name, mod_name)) { found = true; break; } } return found ? cur : NULL; } int nf_nat_helper_try_module_get(const char *name, u16 l3num, u8 protonum) { struct nf_conntrack_helper *h; struct nf_conntrack_nat_helper *nat; char mod_name[NF_CT_HELPER_NAME_LEN]; int ret = 0; rcu_read_lock(); h = __nf_conntrack_helper_find(name, l3num, protonum); if (!h) { rcu_read_unlock(); return -ENOENT; } nat = nf_conntrack_nat_helper_find(h->nat_mod_name); if (!nat) { snprintf(mod_name, sizeof(mod_name), "%s", h->nat_mod_name); rcu_read_unlock(); request_module("%s", mod_name); rcu_read_lock(); nat = nf_conntrack_nat_helper_find(mod_name); if (!nat) { rcu_read_unlock(); return -ENOENT; } } if (!try_module_get(nat->module)) ret = -ENOENT; rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(nf_nat_helper_try_module_get); void nf_nat_helper_put(struct nf_conntrack_helper *helper) { struct nf_conntrack_nat_helper *nat; nat = nf_conntrack_nat_helper_find(helper->nat_mod_name); if (WARN_ON_ONCE(!nat)) return; module_put(nat->module); } EXPORT_SYMBOL_GPL(nf_nat_helper_put); struct nf_conn_help * nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp) { struct nf_conn_help *help; help = nf_ct_ext_add(ct, NF_CT_EXT_HELPER, gfp); if (help) INIT_HLIST_HEAD(&help->expectations); else pr_debug("failed to add helper extension area"); return help; } EXPORT_SYMBOL_GPL(nf_ct_helper_ext_add); int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, gfp_t flags) { struct nf_conntrack_helper *helper = NULL; struct nf_conn_help *help; /* We already got a helper explicitly attached (e.g. nft_ct) */ if (test_bit(IPS_HELPER_BIT, &ct->status)) return 0; if (WARN_ON_ONCE(!tmpl)) return 0; help = nfct_help(tmpl); if (help != NULL) { helper = rcu_dereference(help->helper); set_bit(IPS_HELPER_BIT, &ct->status); } help = nfct_help(ct); if (helper == NULL) { if (help) RCU_INIT_POINTER(help->helper, NULL); return 0; } if (help == NULL) { help = nf_ct_helper_ext_add(ct, flags); if (help == NULL) return -ENOMEM; } else { /* We only allow helper re-assignment of the same sort since * we cannot reallocate the helper extension area. */ struct nf_conntrack_helper *tmp = rcu_dereference(help->helper); if (tmp && tmp->help != helper->help) { RCU_INIT_POINTER(help->helper, NULL); return 0; } } rcu_assign_pointer(help->helper, helper); return 0; } EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper); /* appropriate ct lock protecting must be taken by caller */ static int unhelp(struct nf_conn *ct, void *me) { struct nf_conn_help *help = nfct_help(ct); if (help && rcu_dereference_raw(help->helper) == me) { nf_conntrack_event(IPCT_HELPER, ct); RCU_INIT_POINTER(help->helper, NULL); } /* We are not intended to delete this conntrack. */ return 0; } void nf_ct_helper_destroy(struct nf_conn *ct) { struct nf_conn_help *help = nfct_help(ct); struct nf_conntrack_helper *helper; if (help) { rcu_read_lock(); helper = rcu_dereference(help->helper); if (helper && helper->destroy) helper->destroy(ct); rcu_read_unlock(); } } static LIST_HEAD(nf_ct_helper_expectfn_list); void nf_ct_helper_expectfn_register(struct nf_ct_helper_expectfn *n) { spin_lock_bh(&nf_conntrack_expect_lock); list_add_rcu(&n->head, &nf_ct_helper_expectfn_list); spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_register); void nf_ct_helper_expectfn_unregister(struct nf_ct_helper_expectfn *n) { spin_lock_bh(&nf_conntrack_expect_lock); list_del_rcu(&n->head); spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_unregister); /* Caller should hold the rcu lock */ struct nf_ct_helper_expectfn * nf_ct_helper_expectfn_find_by_name(const char *name) { struct nf_ct_helper_expectfn *cur; bool found = false; list_for_each_entry_rcu(cur, &nf_ct_helper_expectfn_list, head) { if (!strcmp(cur->name, name)) { found = true; break; } } return found ? cur : NULL; } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_name); /* Caller should hold the rcu lock */ struct nf_ct_helper_expectfn * nf_ct_helper_expectfn_find_by_symbol(const void *symbol) { struct nf_ct_helper_expectfn *cur; bool found = false; list_for_each_entry_rcu(cur, &nf_ct_helper_expectfn_list, head) { if (cur->expectfn == symbol) { found = true; break; } } return found ? cur : NULL; } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_symbol); __printf(3, 4) void nf_ct_helper_log(struct sk_buff *skb, const struct nf_conn *ct, const char *fmt, ...) { const struct nf_conn_help *help; const struct nf_conntrack_helper *helper; struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; /* Called from the helper function, this call never fails */ help = nfct_help(ct); /* rcu_read_lock()ed by nf_hook_thresh */ helper = rcu_dereference(help->helper); nf_log_packet(nf_ct_net(ct), nf_ct_l3num(ct), 0, skb, NULL, NULL, NULL, "nf_ct_%s: dropping packet: %pV ", helper->name, &vaf); va_end(args); } EXPORT_SYMBOL_GPL(nf_ct_helper_log); int nf_conntrack_helper_register(struct nf_conntrack_helper *me) { struct nf_conntrack_tuple_mask mask = { .src.u.all = htons(0xFFFF) }; unsigned int h = helper_hash(&me->tuple); struct nf_conntrack_helper *cur; int ret = 0, i; BUG_ON(me->expect_policy == NULL); BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES); BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1); if (!nf_ct_helper_hash) return -ENOENT; if (me->expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT) return -EINVAL; mutex_lock(&nf_ct_helper_mutex); for (i = 0; i < nf_ct_helper_hsize; i++) { hlist_for_each_entry(cur, &nf_ct_helper_hash[i], hnode) { if (!strcmp(cur->name, me->name) && (cur->tuple.src.l3num == NFPROTO_UNSPEC || cur->tuple.src.l3num == me->tuple.src.l3num) && cur->tuple.dst.protonum == me->tuple.dst.protonum) { ret = -EBUSY; goto out; } } } /* avoid unpredictable behaviour for auto_assign_helper */ if (!(me->flags & NF_CT_HELPER_F_USERSPACE)) { hlist_for_each_entry(cur, &nf_ct_helper_hash[h], hnode) { if (nf_ct_tuple_src_mask_cmp(&cur->tuple, &me->tuple, &mask)) { ret = -EBUSY; goto out; } } } refcount_set(&me->refcnt, 1); hlist_add_head_rcu(&me->hnode, &nf_ct_helper_hash[h]); nf_ct_helper_count++; out: mutex_unlock(&nf_ct_helper_mutex); return ret; } EXPORT_SYMBOL_GPL(nf_conntrack_helper_register); static bool expect_iter_me(struct nf_conntrack_expect *exp, void *data) { struct nf_conn_help *help = nfct_help(exp->master); const struct nf_conntrack_helper *me = data; const struct nf_conntrack_helper *this; if (exp->helper == me) return true; this = rcu_dereference_protected(help->helper, lockdep_is_held(&nf_conntrack_expect_lock)); return this == me; } void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) { mutex_lock(&nf_ct_helper_mutex); hlist_del_rcu(&me->hnode); nf_ct_helper_count--; mutex_unlock(&nf_ct_helper_mutex); /* Make sure every nothing is still using the helper unless its a * connection in the hash. */ synchronize_rcu(); nf_ct_expect_iterate_destroy(expect_iter_me, NULL); nf_ct_iterate_destroy(unhelp, me); } EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister); void nf_ct_helper_init(struct nf_conntrack_helper *helper, u16 l3num, u16 protonum, const char *name, u16 default_port, u16 spec_port, u32 id, const struct nf_conntrack_expect_policy *exp_pol, u32 expect_class_max, int (*help)(struct sk_buff *skb, unsigned int protoff, struct nf_conn *ct, enum ip_conntrack_info ctinfo), int (*from_nlattr)(struct nlattr *attr, struct nf_conn *ct), struct module *module) { helper->tuple.src.l3num = l3num; helper->tuple.dst.protonum = protonum; helper->tuple.src.u.all = htons(spec_port); helper->expect_policy = exp_pol; helper->expect_class_max = expect_class_max; helper->help = help; helper->from_nlattr = from_nlattr; helper->me = module; snprintf(helper->nat_mod_name, sizeof(helper->nat_mod_name), NF_NAT_HELPER_PREFIX "%s", name); if (spec_port == default_port) snprintf(helper->name, sizeof(helper->name), "%s", name); else snprintf(helper->name, sizeof(helper->name), "%s-%u", name, id); } EXPORT_SYMBOL_GPL(nf_ct_helper_init); int nf_conntrack_helpers_register(struct nf_conntrack_helper *helper, unsigned int n) { unsigned int i; int err = 0; for (i = 0; i < n; i++) { err = nf_conntrack_helper_register(&helper[i]); if (err < 0) goto err; } return err; err: if (i > 0) nf_conntrack_helpers_unregister(helper, i); return err; } EXPORT_SYMBOL_GPL(nf_conntrack_helpers_register); void nf_conntrack_helpers_unregister(struct nf_conntrack_helper *helper, unsigned int n) { while (n-- > 0) nf_conntrack_helper_unregister(&helper[n]); } EXPORT_SYMBOL_GPL(nf_conntrack_helpers_unregister); void nf_nat_helper_register(struct nf_conntrack_nat_helper *nat) { mutex_lock(&nf_ct_nat_helpers_mutex); list_add_rcu(&nat->list, &nf_ct_nat_helpers); mutex_unlock(&nf_ct_nat_helpers_mutex); } EXPORT_SYMBOL_GPL(nf_nat_helper_register); void nf_nat_helper_unregister(struct nf_conntrack_nat_helper *nat) { mutex_lock(&nf_ct_nat_helpers_mutex); list_del_rcu(&nat->list); mutex_unlock(&nf_ct_nat_helpers_mutex); } EXPORT_SYMBOL_GPL(nf_nat_helper_unregister); int nf_conntrack_helper_init(void) { nf_ct_helper_hsize = 1; /* gets rounded up to use one page */ nf_ct_helper_hash = nf_ct_alloc_hashtable(&nf_ct_helper_hsize, 0); if (!nf_ct_helper_hash) return -ENOMEM; INIT_LIST_HEAD(&nf_ct_nat_helpers); return 0; } void nf_conntrack_helper_fini(void) { kvfree(nf_ct_helper_hash); nf_ct_helper_hash = NULL; } |
| 2 134 133 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2014 Christoph Hellwig. */ #include "xfs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_bmap.h" #include "xfs_iomap.h" #include "xfs_pnfs.h" /* * Ensure that we do not have any outstanding pNFS layouts that can be used by * clients to directly read from or write to this inode. This must be called * before every operation that can remove blocks from the extent map. * Additionally we call it during the write operation, where aren't concerned * about exposing unallocated blocks but just want to provide basic * synchronization between a local writer and pNFS clients. mmap writes would * also benefit from this sort of synchronization, but due to the tricky locking * rules in the page fault path we don't bother. */ int xfs_break_leased_layouts( struct inode *inode, uint *iolock, bool *did_unlock) { struct xfs_inode *ip = XFS_I(inode); int error; while ((error = break_layout(inode, false)) == -EWOULDBLOCK) { xfs_iunlock(ip, *iolock); *did_unlock = true; error = break_layout(inode, true); *iolock &= ~XFS_IOLOCK_SHARED; *iolock |= XFS_IOLOCK_EXCL; xfs_ilock(ip, *iolock); } return error; } /* * Get a unique ID including its location so that the client can identify * the exported device. */ int xfs_fs_get_uuid( struct super_block *sb, u8 *buf, u32 *len, u64 *offset) { struct xfs_mount *mp = XFS_M(sb); if (*len < sizeof(uuid_t)) return -EINVAL; memcpy(buf, &mp->m_sb.sb_uuid, sizeof(uuid_t)); *len = sizeof(uuid_t); *offset = offsetof(struct xfs_dsb, sb_uuid); return 0; } /* * We cannot use file based VFS helpers such as file_modified() to update * inode state as we modify the data/metadata in the inode here. Hence we have * to open code the timestamp updates and SUID/SGID stripping. We also need * to set the inode prealloc flag to ensure that the extents we allocate are not * removed if the inode is reclaimed from memory before xfs_fs_block_commit() * is from the client to indicate that data has been written and the file size * can be extended. */ static int xfs_fs_map_update_inode( struct xfs_inode *ip) { struct xfs_trans *tp; int error; error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_writeid, 0, 0, 0, &tp); if (error) return error; xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); VFS_I(ip)->i_mode &= ~S_ISUID; if (VFS_I(ip)->i_mode & S_IXGRP) VFS_I(ip)->i_mode &= ~S_ISGID; xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); ip->i_diflags |= XFS_DIFLAG_PREALLOC; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); return xfs_trans_commit(tp); } /* * Get a layout for the pNFS client. */ int xfs_fs_map_blocks( struct inode *inode, loff_t offset, u64 length, struct iomap *iomap, bool write, u32 *device_generation) { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; struct xfs_bmbt_irec imap; xfs_fileoff_t offset_fsb, end_fsb; loff_t limit; int bmapi_flags = XFS_BMAPI_ENTIRE; int nimaps = 1; uint lock_flags; int error = 0; u64 seq; if (xfs_is_shutdown(mp)) return -EIO; /* * We can't export inodes residing on the realtime device. The realtime * device doesn't have a UUID to identify it, so the client has no way * to find it. */ if (XFS_IS_REALTIME_INODE(ip)) return -ENXIO; /* * The pNFS block layout spec actually supports reflink like * functionality, but the Linux pNFS server doesn't implement it yet. */ if (xfs_is_reflink_inode(ip)) return -ENXIO; /* * Lock out any other I/O before we flush and invalidate the pagecache, * and then hand out a layout to the remote system. This is very * similar to direct I/O, except that the synchronization is much more * complicated. See the comment near xfs_break_leased_layouts * for a detailed explanation. */ xfs_ilock(ip, XFS_IOLOCK_EXCL); error = -EINVAL; limit = mp->m_super->s_maxbytes; if (!write) limit = max(limit, round_up(i_size_read(inode), inode->i_sb->s_blocksize)); if (offset > limit) goto out_unlock; if (offset > limit - length) length = limit - offset; error = filemap_write_and_wait(inode->i_mapping); if (error) goto out_unlock; error = invalidate_inode_pages2(inode->i_mapping); if (WARN_ON_ONCE(error)) goto out_unlock; end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length); offset_fsb = XFS_B_TO_FSBT(mp, offset); lock_flags = xfs_ilock_data_map_shared(ip); error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, &nimaps, bmapi_flags); seq = xfs_iomap_inode_sequence(ip, 0); ASSERT(!nimaps || imap.br_startblock != DELAYSTARTBLOCK); if (!error && write && (!nimaps || imap.br_startblock == HOLESTARTBLOCK)) { if (offset + length > XFS_ISIZE(ip)) end_fsb = xfs_iomap_eof_align_last_fsb(ip, end_fsb); else if (nimaps && imap.br_startblock == HOLESTARTBLOCK) end_fsb = min(end_fsb, imap.br_startoff + imap.br_blockcount); xfs_iunlock(ip, lock_flags); error = xfs_iomap_write_direct(ip, offset_fsb, end_fsb - offset_fsb, 0, &imap, &seq); if (error) goto out_unlock; /* * Ensure the next transaction is committed synchronously so * that the blocks allocated and handed out to the client are * guaranteed to be present even after a server crash. */ error = xfs_fs_map_update_inode(ip); if (!error) error = xfs_log_force_inode(ip); if (error) goto out_unlock; } else { xfs_iunlock(ip, lock_flags); } xfs_iunlock(ip, XFS_IOLOCK_EXCL); error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0, 0, seq); *device_generation = mp->m_generation; return error; out_unlock: xfs_iunlock(ip, XFS_IOLOCK_EXCL); return error; } /* * Ensure the size update falls into a valid allocated block. */ static int xfs_pnfs_validate_isize( struct xfs_inode *ip, xfs_off_t isize) { struct xfs_bmbt_irec imap; int nimaps = 1; int error = 0; xfs_ilock(ip, XFS_ILOCK_SHARED); error = xfs_bmapi_read(ip, XFS_B_TO_FSBT(ip->i_mount, isize - 1), 1, &imap, &nimaps, 0); xfs_iunlock(ip, XFS_ILOCK_SHARED); if (error) return error; if (imap.br_startblock == HOLESTARTBLOCK || imap.br_startblock == DELAYSTARTBLOCK || imap.br_state == XFS_EXT_UNWRITTEN) return -EIO; return 0; } /* * Make sure the blocks described by maps are stable on disk. This includes * converting any unwritten extents, flushing the disk cache and updating the * time stamps. * * Note that we rely on the caller to always send us a timestamp update so that * we always commit a transaction here. If that stops being true we will have * to manually flush the cache here similar to what the fsync code path does * for datasyncs on files that have no dirty metadata. */ int xfs_fs_commit_blocks( struct inode *inode, struct iomap *maps, int nr_maps, struct iattr *iattr) { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; bool update_isize = false; int error, i; loff_t size; ASSERT(iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME)); xfs_ilock(ip, XFS_IOLOCK_EXCL); size = i_size_read(inode); if ((iattr->ia_valid & ATTR_SIZE) && iattr->ia_size > size) { update_isize = true; size = iattr->ia_size; } for (i = 0; i < nr_maps; i++) { u64 start, length, end; start = maps[i].offset; if (start > size) continue; end = start + maps[i].length; if (end > size) end = size; length = end - start; if (!length) continue; /* * Make sure reads through the pagecache see the new data. */ error = invalidate_inode_pages2_range(inode->i_mapping, start >> PAGE_SHIFT, (end - 1) >> PAGE_SHIFT); WARN_ON_ONCE(error); error = xfs_iomap_write_unwritten(ip, start, length, false); if (error) goto out_drop_iolock; } if (update_isize) { error = xfs_pnfs_validate_isize(ip, size); if (error) goto out_drop_iolock; } error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp); if (error) goto out_drop_iolock; xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); ASSERT(!(iattr->ia_valid & (ATTR_UID | ATTR_GID))); setattr_copy(&nop_mnt_idmap, inode, iattr); if (update_isize) { i_size_write(inode, iattr->ia_size); ip->i_disk_size = iattr->ia_size; } xfs_trans_set_sync(tp); error = xfs_trans_commit(tp); out_drop_iolock: xfs_iunlock(ip, XFS_IOLOCK_EXCL); return error; } |
| 1 1 8 8 7 1 1 1 7 7 7 7 7 7 8 7 1 7 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * xt_LED.c - netfilter target to make LEDs blink upon packet matches * * Copyright (C) 2008 Adam Nielsen <a.nielsen@shikadi.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter/x_tables.h> #include <linux/slab.h> #include <linux/leds.h> #include <linux/mutex.h> #include <linux/netfilter/xt_LED.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Adam Nielsen <a.nielsen@shikadi.net>"); MODULE_DESCRIPTION("Xtables: trigger LED devices on packet match"); MODULE_ALIAS("ipt_LED"); MODULE_ALIAS("ip6t_LED"); static LIST_HEAD(xt_led_triggers); static DEFINE_MUTEX(xt_led_mutex); /* * This is declared in here (the kernel module) only, to avoid having these * dependencies in userspace code. This is what xt_led_info.internal_data * points to. */ struct xt_led_info_internal { struct list_head list; int refcnt; char *trigger_id; struct led_trigger netfilter_led_trigger; struct timer_list timer; }; #define XT_LED_BLINK_DELAY 50 /* ms */ static unsigned int led_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_led_info *ledinfo = par->targinfo; struct xt_led_info_internal *ledinternal = ledinfo->internal_data; /* * If "always blink" is enabled, and there's still some time until the * LED will switch off, briefly switch it off now. */ if ((ledinfo->delay > 0) && ledinfo->always_blink && timer_pending(&ledinternal->timer)) led_trigger_blink_oneshot(&ledinternal->netfilter_led_trigger, XT_LED_BLINK_DELAY, XT_LED_BLINK_DELAY, 1); else led_trigger_event(&ledinternal->netfilter_led_trigger, LED_FULL); /* If there's a positive delay, start/update the timer */ if (ledinfo->delay > 0) { mod_timer(&ledinternal->timer, jiffies + msecs_to_jiffies(ledinfo->delay)); /* Otherwise if there was no delay given, blink as fast as possible */ } else if (ledinfo->delay == 0) { led_trigger_event(&ledinternal->netfilter_led_trigger, LED_OFF); } /* else the delay is negative, which means switch on and stay on */ return XT_CONTINUE; } static void led_timeout_callback(struct timer_list *t) { struct xt_led_info_internal *ledinternal = timer_container_of(ledinternal, t, timer); led_trigger_event(&ledinternal->netfilter_led_trigger, LED_OFF); } static struct xt_led_info_internal *led_trigger_lookup(const char *name) { struct xt_led_info_internal *ledinternal; list_for_each_entry(ledinternal, &xt_led_triggers, list) { if (!strcmp(name, ledinternal->netfilter_led_trigger.name)) { return ledinternal; } } return NULL; } static int led_tg_check(const struct xt_tgchk_param *par) { struct xt_led_info *ledinfo = par->targinfo; struct xt_led_info_internal *ledinternal; int err; /* Bail out if empty string or not a string at all. */ if (ledinfo->id[0] == '\0' || !memchr(ledinfo->id, '\0', sizeof(ledinfo->id))) return -EINVAL; mutex_lock(&xt_led_mutex); ledinternal = led_trigger_lookup(ledinfo->id); if (ledinternal) { ledinternal->refcnt++; goto out; } err = -ENOMEM; ledinternal = kzalloc(sizeof(struct xt_led_info_internal), GFP_KERNEL); if (!ledinternal) goto exit_mutex_only; ledinternal->trigger_id = kstrdup(ledinfo->id, GFP_KERNEL); if (!ledinternal->trigger_id) goto exit_internal_alloc; ledinternal->refcnt = 1; ledinternal->netfilter_led_trigger.name = ledinternal->trigger_id; err = led_trigger_register(&ledinternal->netfilter_led_trigger); if (err) { pr_info_ratelimited("Trigger name is already in use.\n"); goto exit_alloc; } /* Since the letinternal timer can be shared between multiple targets, * always set it up, even if the current target does not need it */ timer_setup(&ledinternal->timer, led_timeout_callback, 0); list_add_tail(&ledinternal->list, &xt_led_triggers); out: mutex_unlock(&xt_led_mutex); ledinfo->internal_data = ledinternal; return 0; exit_alloc: kfree(ledinternal->trigger_id); exit_internal_alloc: kfree(ledinternal); exit_mutex_only: mutex_unlock(&xt_led_mutex); return err; } static void led_tg_destroy(const struct xt_tgdtor_param *par) { const struct xt_led_info *ledinfo = par->targinfo; struct xt_led_info_internal *ledinternal = ledinfo->internal_data; mutex_lock(&xt_led_mutex); if (--ledinternal->refcnt) { mutex_unlock(&xt_led_mutex); return; } list_del(&ledinternal->list); timer_shutdown_sync(&ledinternal->timer); led_trigger_unregister(&ledinternal->netfilter_led_trigger); mutex_unlock(&xt_led_mutex); kfree(ledinternal->trigger_id); kfree(ledinternal); } static struct xt_target led_tg_reg[] __read_mostly = { { .name = "LED", .revision = 0, .family = NFPROTO_IPV4, .target = led_tg, .targetsize = sizeof(struct xt_led_info), .usersize = offsetof(struct xt_led_info, internal_data), .checkentry = led_tg_check, .destroy = led_tg_destroy, .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "LED", .revision = 0, .family = NFPROTO_IPV6, .target = led_tg, .targetsize = sizeof(struct xt_led_info), .usersize = offsetof(struct xt_led_info, internal_data), .checkentry = led_tg_check, .destroy = led_tg_destroy, .me = THIS_MODULE, }, #endif }; static int __init led_tg_init(void) { return xt_register_targets(led_tg_reg, ARRAY_SIZE(led_tg_reg)); } static void __exit led_tg_exit(void) { xt_unregister_targets(led_tg_reg, ARRAY_SIZE(led_tg_reg)); } module_init(led_tg_init); module_exit(led_tg_exit); |
| 1 1 1 1 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Force feedback support for Zeroplus based devices * * Copyright (c) 2005, 2006 Anssi Hannula <anssi.hannula@gmail.com> */ /* */ #include <linux/hid.h> #include <linux/input.h> #include <linux/slab.h> #include <linux/module.h> #include "hid-ids.h" #ifdef CONFIG_ZEROPLUS_FF struct zpff_device { struct hid_report *report; }; static int zpff_play(struct input_dev *dev, void *data, struct ff_effect *effect) { struct hid_device *hid = input_get_drvdata(dev); struct zpff_device *zpff = data; int left, right; /* * The following is specified the other way around in the Zeroplus * datasheet but the order below is correct for the XFX Executioner; * however it is possible that the XFX Executioner is an exception */ left = effect->u.rumble.strong_magnitude; right = effect->u.rumble.weak_magnitude; dbg_hid("called with 0x%04x 0x%04x\n", left, right); left = left * 0x7f / 0xffff; right = right * 0x7f / 0xffff; zpff->report->field[2]->value[0] = left; zpff->report->field[3]->value[0] = right; dbg_hid("running with 0x%02x 0x%02x\n", left, right); hid_hw_request(hid, zpff->report, HID_REQ_SET_REPORT); return 0; } static int zpff_init(struct hid_device *hid) { struct zpff_device *zpff; struct hid_report *report; struct hid_input *hidinput; struct input_dev *dev; int i, error; if (list_empty(&hid->inputs)) { hid_err(hid, "no inputs found\n"); return -ENODEV; } hidinput = list_entry(hid->inputs.next, struct hid_input, list); dev = hidinput->input; for (i = 0; i < 4; i++) { report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, i, 1); if (!report) return -ENODEV; } zpff = kzalloc(sizeof(struct zpff_device), GFP_KERNEL); if (!zpff) return -ENOMEM; set_bit(FF_RUMBLE, dev->ffbit); error = input_ff_create_memless(dev, zpff, zpff_play); if (error) { kfree(zpff); return error; } zpff->report = report; zpff->report->field[0]->value[0] = 0x00; zpff->report->field[1]->value[0] = 0x02; zpff->report->field[2]->value[0] = 0x00; zpff->report->field[3]->value[0] = 0x00; hid_hw_request(hid, zpff->report, HID_REQ_SET_REPORT); hid_info(hid, "force feedback for Zeroplus based devices by Anssi Hannula <anssi.hannula@gmail.com>\n"); return 0; } #else static inline int zpff_init(struct hid_device *hid) { return 0; } #endif static int zp_probe(struct hid_device *hdev, const struct hid_device_id *id) { int ret; ret = hid_parse(hdev); if (ret) { hid_err(hdev, "parse failed\n"); goto err; } ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT & ~HID_CONNECT_FF); if (ret) { hid_err(hdev, "hw start failed\n"); goto err; } zpff_init(hdev); return 0; err: return ret; } static const struct hid_device_id zp_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ZEROPLUS, 0x0005) }, { HID_USB_DEVICE(USB_VENDOR_ID_ZEROPLUS, 0x0030) }, { } }; MODULE_DEVICE_TABLE(hid, zp_devices); static struct hid_driver zp_driver = { .name = "zeroplus", .id_table = zp_devices, .probe = zp_probe, }; module_hid_driver(zp_driver); MODULE_DESCRIPTION("Force feedback support for Zeroplus based devices"); MODULE_LICENSE("GPL"); |
| 2 2 2 8 1 8 8 8 8 8 1 1 8 7 7 7 2 15 15 15 15 15 15 | 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 | /* * Route Plug-In * Copyright (c) 2000 by Abramo Bagnara <abramo@alsa-project.org> * * * This library is free software; you can redistribute it and/or modify * it under the terms of the GNU Library General Public License as * published by the Free Software Foundation; either version 2 of * the License, or (at your option) any later version. * * This program 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 Library General Public License for more details. * * You should have received a copy of the GNU Library General Public * License along with this library; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA * */ #include <linux/time.h> #include <sound/core.h> #include <sound/pcm.h> #include "pcm_plugin.h" static void zero_areas(struct snd_pcm_plugin_channel *dvp, int ndsts, snd_pcm_uframes_t frames, snd_pcm_format_t format) { int dst = 0; for (; dst < ndsts; ++dst) { if (dvp->wanted) snd_pcm_area_silence(&dvp->area, 0, frames, format); dvp->enabled = 0; dvp++; } } static inline void copy_area(const struct snd_pcm_plugin_channel *src_channel, struct snd_pcm_plugin_channel *dst_channel, snd_pcm_uframes_t frames, snd_pcm_format_t format) { dst_channel->enabled = 1; snd_pcm_area_copy(&src_channel->area, 0, &dst_channel->area, 0, frames, format); } static snd_pcm_sframes_t route_transfer(struct snd_pcm_plugin *plugin, const struct snd_pcm_plugin_channel *src_channels, struct snd_pcm_plugin_channel *dst_channels, snd_pcm_uframes_t frames) { int nsrcs, ndsts, dst; struct snd_pcm_plugin_channel *dvp; snd_pcm_format_t format; if (snd_BUG_ON(!plugin || !src_channels || !dst_channels)) return -ENXIO; if (frames == 0) return 0; if (frames > dst_channels[0].frames) frames = dst_channels[0].frames; nsrcs = plugin->src_format.channels; ndsts = plugin->dst_format.channels; format = plugin->dst_format.format; dvp = dst_channels; if (nsrcs <= 1) { /* expand to all channels */ for (dst = 0; dst < ndsts; ++dst) { copy_area(src_channels, dvp, frames, format); dvp++; } return frames; } for (dst = 0; dst < ndsts && dst < nsrcs; ++dst) { copy_area(src_channels, dvp, frames, format); dvp++; src_channels++; } if (dst < ndsts) zero_areas(dvp, ndsts - dst, frames, format); return frames; } int snd_pcm_plugin_build_route(struct snd_pcm_substream *plug, struct snd_pcm_plugin_format *src_format, struct snd_pcm_plugin_format *dst_format, struct snd_pcm_plugin **r_plugin) { struct snd_pcm_plugin *plugin; int err; if (snd_BUG_ON(!r_plugin)) return -ENXIO; *r_plugin = NULL; if (snd_BUG_ON(src_format->rate != dst_format->rate)) return -ENXIO; if (snd_BUG_ON(src_format->format != dst_format->format)) return -ENXIO; err = snd_pcm_plugin_build(plug, "route conversion", src_format, dst_format, 0, &plugin); if (err < 0) return err; plugin->transfer = route_transfer; *r_plugin = plugin; return 0; } |
| 241 252 12 243 243 243 243 12 35 35 35 35 35 35 12 35 34 35 340 361 354 130 503 277 150 145 237 128 90 128 128 300 36 33 27 23 4 22 37 23 23 23 408 403 398 279 281 28 400 406 315 306 304 295 8 7 300 1 298 298 297 299 297 297 307 28 28 27 28 5 20 1 19 9 9 9 8 5 5 4 3 4 8 2 1 1 36 34 34 32 32 30 31 28 27 20 4 1 326 326 256 135 2 325 326 325 326 4 3 4 3 4 2 4 2 3 326 17 16 14 3 1 17 13 12 114 114 114 114 113 112 107 3 100 107 106 11 12 11 11 10 7 100 66 100 100 100 6 80 76 79 79 79 80 4 5 73 73 73 72 72 2 71 25 54 54 59 30 30 24 1 30 26 26 26 8 24 61 2 61 61 60 61 41 24 19 259 3 275 278 52 8 270 44 15 270 12 271 2 260 246 270 26 10 24 226 225 139 223 224 223 223 8 3 8 8 8 6 8 6 6 3 2 7 53 1 53 52 53 13 8 243 240 229 240 241 241 15 241 11 11 2 239 217 216 238 6 236 236 236 235 235 1 235 214 225 267 234 234 244 238 239 238 240 240 243 1 278 279 267 230 262 7 4 3 2 2 2 227 9 226 4 221 82 47 41 242 17 14 247 63 7 7 7 29 2 27 1 1 27 15 15 1 26 19 12 19 19 19 19 12 7 19 1 18 2 19 7 19 13 7 2 6 5 1 6 6 6 26 28 2 1 9 8 8 9 5 9 6 3 2 2 3 2 2 1 55 35 54 11 7 4 10 9 10 9 1 44 16 23 28 22 16 33 9 9 19 7 12 36 22 23 8 23 23 17 17 17 49 4 8 11 8 3 44 23 23 29 15 21 20 22 14 21 5 27 4 8 6 5 9 8 6 8 5 3 48 10 6 2 6 6 6 5 55 60 57 57 59 58 57 57 56 57 9 56 43 2 41 53 54 30 30 6 4 6 2 4 3 6 6 4 6 2 4 3 14 13 9 4 14 8 2 6 5 2 5 2 3 2 8 4 2 16 5 5 11 10 9 5 4 3 4 2 4 3 4 2 9 8 8 7 2 6 2 4 4 6 2 1 11 10 10 8 3 7 3 4 5 7 3 2 2 3 3 3 2 1 1 9 9 5 1 8 2 4 2 2 4 2 3 1 3 3 2 3 2 6 4 3 1 3 2 2 2 2 3 2 1 2 2 2 3 2 1 1 6 2 2 4 3 3 2 5 1 3 3 2 2 2 2 3 3 2 1 1 1 8 7 6 2 1 5 1 3 3 5 2 1 2 2 1 4 3 2 10 2 2 8 6 6 1 7 3 7 2 1 3 1 1 1 7 5 4 3 3 17 16 15 14 3 4 13 9 3 10 11 1 1 1 16 9 9 9 2 1 8 4 3 4 5 2 1 1 14 12 11 3 2 10 3 5 7 5 2 1 1 11 10 9 2 3 8 5 3 6 5 3 2 2 4 4 3 2 1 1 1 1 1 1 2 14 13 12 5 2 1 2 1 2 14 7 4 3 3 3 2 3 1 3 3 2 3 1 3 2 1 2 1 2 2 1 1 1 4 4 4 2 3 8 8 8 3 8 8 1 7 3 3 5 7 1 1 3 2 2 1 2 10 11 10 10 2 1 9 4 4 5 9 3 2 11 10 9 10 5 5 5 11 10 9 24 23 22 6 2 16 5 2 2 4 5 1 1 16 16 12 11 4 11 9 1 5 4 3 3 2 1 1 1 7 7 5 3 3 7 14 13 12 11 2 2 10 2 8 9 9 10 7 5 7 6 6 4 5 1 13 12 11 7 11 10 10 2 11 5 5 3 2 4 4 4 4 3 2 1 2 9 8 2 1 6 4 2 2 2 2 3 9 9 8 3 3 3 5 3 2 3 3 3 3 2 530 105 530 429 393 397 426 32 4 5 5 2 9 3 60 16 4 5 9 11 3 3 1 10 6 3 6 1 8 2 10 3 7 17 9 14 11 4 8 6 2 1 4 8 3 11 11 6 11 24 16 5 2 14 7 13 5 4 9 10 423 36 35 30 33 39 37 39 3 2 3 34 35 35 25 25 35 35 35 35 27 27 26 26 26 22 28 16 10 15 2 1 1 16 157 157 157 157 60 61 1 1 60 2 29 35 30 30 7 7 7 5 5 2 5 5 14 14 14 4 11 10 11 10 4 14 14 14 10 7 13 13 8 8 12 13 2 2 2 14 14 14 10 10 10 1 1 14 9 7 6 14 5 3 3 3 3 3 2 3 3 5 4 3 2 1 1 1 1 1 4 2 1 1 3 2 2 2 2 2 3 2 1 1 17 14 13 13 13 18 18 13 1 7 12 12 3 3 3 3 1 1 1 16 15 15 11 1 10 10 17 3 16 15 8 13 9 4 2 5 1 5 2 1 2 4 1 4 3 11 17 6 4 2 2 2 6 4 2 2 1 5 2 3 2 5 5 1 1 1 4 3 3 3 1 3 2 2 2 2 7 9 9 2 7 7 2 9 9 9 7 9 17 16 15 12 3 3 11 15 15 10 9 6 4 2 11 11 11 14 5 5 5 3 3 5 1 1 1 5 4 4 3 2 1 3 2 3 5 4 4 3 2 2 4 2 4 3 2 2 4 3 3 3 2 1 3 2 3 6 5 5 4 2 1 1 1 3 4 3 3 3 3 5 4 4 3 2 3 3 3 8 1 1 7 6 7 5 2 6 4 6 1 5 2 1 1 2 2 2 13 1 1 12 11 12 10 8 11 1 10 3 2 2 2 1 1 7 6 6 4 2 2 3 1 2 2 1 1 1 1 1 1 1 1 1 6 5 1 5 5 2 1 4 2 2 2 1 1 1 1 2 2 2 1 2 2 3 3 1 3 2 9 8 7 3 7 6 6 2 6 1 5 8 7 6 2 1 5 4 3 1 2 2 8 4 3 3 3 1 4 3 2 1 2 2 2 2 1 2 2 5 4 4 3 2 4 2 4 6 6 6 4 1 3 5 3 5 5 4 4 4 2 1 1 1 1 5 5 5 4 3 2 2 2 1 1 1 2 5 4 4 3 2 4 2 4 3 3 3 3 1 3 2 3 6 4 4 3 2 4 2 4 5 4 4 4 4 4 5 4 4 3 3 2 1 2 2 1 1 5 5 5 4 3 2 4 4 4 7 6 6 4 3 4 2 4 5 5 5 3 2 4 2 3 5 4 4 3 2 3 2 3 5 4 4 3 2 3 2 3 244 8 7 7 2 1 5 3 2 2 1 4 8 8 6 6 1 5 4 2 1 2 3 8 321 339 21 337 321 314 312 5 2 3 3 4 16 17 6 1 5 17 73 5 5 5 3 4 6 3 8 4 1 5 2 2 13 3 7 2 6 2 9 3 8 4 3 2 5 6 5 5 5 3 6 5 5 2 5 7 5 5 244 8 8 309 146 309 268 309 60 267 267 268 267 268 1 1 1 1 267 310 60 34 34 34 1 34 31 31 10 2 1 10 1 9 9 292 308 292 4 29 1 2 29 1 286 308 297 299 308 30 10 22 30 3 33 33 32 33 33 3 2 1 1 31 2 30 33 33 26 26 26 26 3 25 1 25 2 25 1 25 3 25 14 5 5 23 290 292 291 36 28 28 14 36 36 36 36 36 265 52 52 49 46 5 4 16 16 13 13 3 3 2 1 2 1 7 14 14 14 14 10 10 8 8 2 6 26 26 26 7 25 17 20 19 17 14 4 72 73 72 13 73 73 73 3 72 64 73 146 88 63 62 63 62 145 147 147 147 146 1 1 147 147 145 164 164 3 11 11 11 7 6 6 2 6 4 9 3 7 2 89 89 89 7 89 89 90 10 87 309 309 157 119 119 119 117 116 279 35 9 26 26 4 26 26 25 3 3 1 26 2 2 2 2 2 35 34 35 35 34 35 35 12 133 133 133 | 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 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001-2003 Intel Corp. * Copyright (c) 2001-2002 Nokia, Inc. * Copyright (c) 2001 La Monte H.P. Yarroll * * This file is part of the SCTP kernel implementation * * These functions interface with the sockets layer to implement the * SCTP Extensions for the Sockets API. * * Note that the descriptions from the specification are USER level * functions--this file is the functions which populate the struct proto * for SCTP which is the BOTTOM of the sockets interface. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Narasimha Budihal <narsi@refcode.org> * Karl Knutson <karl@athena.chicago.il.us> * Jon Grimm <jgrimm@us.ibm.com> * Xingang Guo <xingang.guo@intel.com> * Daisy Chang <daisyc@us.ibm.com> * Sridhar Samudrala <samudrala@us.ibm.com> * Inaky Perez-Gonzalez <inaky.gonzalez@intel.com> * Ardelle Fan <ardelle.fan@intel.com> * Ryan Layer <rmlayer@us.ibm.com> * Anup Pemmaiah <pemmaiah@cc.usu.edu> * Kevin Gao <kevin.gao@intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/kernel.h> #include <linux/wait.h> #include <linux/time.h> #include <linux/sched/signal.h> #include <linux/ip.h> #include <linux/capability.h> #include <linux/fcntl.h> #include <linux/poll.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/compat.h> #include <linux/rhashtable.h> #include <net/ip.h> #include <net/icmp.h> #include <net/route.h> #include <net/ipv6.h> #include <net/inet_common.h> #include <net/busy_poll.h> #include <trace/events/sock.h> #include <linux/socket.h> /* for sa_family_t */ #include <linux/export.h> #include <net/sock.h> #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> #include <net/rps.h> /* Forward declarations for internal helper functions. */ static bool sctp_writeable(const struct sock *sk); static void sctp_wfree(struct sk_buff *skb); static int sctp_wait_for_sndbuf(struct sctp_association *asoc, struct sctp_transport *transport, long *timeo_p, size_t msg_len); static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p); static int sctp_wait_for_connect(struct sctp_association *, long *timeo_p); static int sctp_wait_for_accept(struct sock *sk, long timeo); static void sctp_wait_for_close(struct sock *sk, long timeo); static void sctp_destruct_sock(struct sock *sk); static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt, union sctp_addr *addr, int len); static int sctp_bindx_add(struct sock *, struct sockaddr *, int); static int sctp_bindx_rem(struct sock *, struct sockaddr *, int); static int sctp_send_asconf_add_ip(struct sock *, struct sockaddr *, int); static int sctp_send_asconf_del_ip(struct sock *, struct sockaddr *, int); static int sctp_send_asconf(struct sctp_association *asoc, struct sctp_chunk *chunk); static int sctp_do_bind(struct sock *, union sctp_addr *, int); static int sctp_autobind(struct sock *sk); static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, struct sctp_association *assoc, enum sctp_socket_type type); static unsigned long sctp_memory_pressure; static atomic_long_t sctp_memory_allocated; static DEFINE_PER_CPU(int, sctp_memory_per_cpu_fw_alloc); struct percpu_counter sctp_sockets_allocated; static void sctp_enter_memory_pressure(struct sock *sk) { WRITE_ONCE(sctp_memory_pressure, 1); } /* Get the sndbuf space available at the time on the association. */ static inline int sctp_wspace(struct sctp_association *asoc) { struct sock *sk = asoc->base.sk; return asoc->ep->sndbuf_policy ? sk->sk_sndbuf - asoc->sndbuf_used : sk_stream_wspace(sk); } /* Increment the used sndbuf space count of the corresponding association by * the size of the outgoing data chunk. * Also, set the skb destructor for sndbuf accounting later. * * Since it is always 1-1 between chunk and skb, and also a new skb is always * allocated for chunk bundling in sctp_packet_transmit(), we can use the * destructor in the data chunk skb for the purpose of the sndbuf space * tracking. */ static inline void sctp_set_owner_w(struct sctp_chunk *chunk) { struct sctp_association *asoc = chunk->asoc; struct sock *sk = asoc->base.sk; /* The sndbuf space is tracked per association. */ sctp_association_hold(asoc); if (chunk->shkey) sctp_auth_shkey_hold(chunk->shkey); skb_set_owner_w(chunk->skb, sk); chunk->skb->destructor = sctp_wfree; /* Save the chunk pointer in skb for sctp_wfree to use later. */ skb_shinfo(chunk->skb)->destructor_arg = chunk; refcount_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc); asoc->sndbuf_used += chunk->skb->truesize + sizeof(struct sctp_chunk); sk_wmem_queued_add(sk, chunk->skb->truesize + sizeof(struct sctp_chunk)); sk_mem_charge(sk, chunk->skb->truesize); } static void sctp_clear_owner_w(struct sctp_chunk *chunk) { skb_orphan(chunk->skb); } #define traverse_and_process() \ do { \ msg = chunk->msg; \ if (msg == prev_msg) \ continue; \ list_for_each_entry(c, &msg->chunks, frag_list) { \ if ((clear && asoc->base.sk == c->skb->sk) || \ (!clear && asoc->base.sk != c->skb->sk)) \ cb(c); \ } \ prev_msg = msg; \ } while (0) static void sctp_for_each_tx_datachunk(struct sctp_association *asoc, bool clear, void (*cb)(struct sctp_chunk *)) { struct sctp_datamsg *msg, *prev_msg = NULL; struct sctp_outq *q = &asoc->outqueue; struct sctp_chunk *chunk, *c; struct sctp_transport *t; list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) list_for_each_entry(chunk, &t->transmitted, transmitted_list) traverse_and_process(); list_for_each_entry(chunk, &q->retransmit, transmitted_list) traverse_and_process(); list_for_each_entry(chunk, &q->sacked, transmitted_list) traverse_and_process(); list_for_each_entry(chunk, &q->abandoned, transmitted_list) traverse_and_process(); list_for_each_entry(chunk, &q->out_chunk_list, list) traverse_and_process(); } static void sctp_for_each_rx_skb(struct sctp_association *asoc, struct sock *sk, void (*cb)(struct sk_buff *, struct sock *)) { struct sk_buff *skb, *tmp; sctp_skb_for_each(skb, &asoc->ulpq.lobby, tmp) cb(skb, sk); sctp_skb_for_each(skb, &asoc->ulpq.reasm, tmp) cb(skb, sk); sctp_skb_for_each(skb, &asoc->ulpq.reasm_uo, tmp) cb(skb, sk); } /* Verify that this is a valid address. */ static inline int sctp_verify_addr(struct sock *sk, union sctp_addr *addr, int len) { struct sctp_af *af; /* Verify basic sockaddr. */ af = sctp_sockaddr_af(sctp_sk(sk), addr, len); if (!af) return -EINVAL; /* Is this a valid SCTP address? */ if (!af->addr_valid(addr, sctp_sk(sk), NULL)) return -EINVAL; if (!sctp_sk(sk)->pf->send_verify(sctp_sk(sk), (addr))) return -EINVAL; return 0; } /* Look up the association by its id. If this is not a UDP-style * socket, the ID field is always ignored. */ struct sctp_association *sctp_id2assoc(struct sock *sk, sctp_assoc_t id) { struct sctp_association *asoc = NULL; /* If this is not a UDP-style socket, assoc id should be ignored. */ if (!sctp_style(sk, UDP)) { /* Return NULL if the socket state is not ESTABLISHED. It * could be a TCP-style listening socket or a socket which * hasn't yet called connect() to establish an association. */ if (!sctp_sstate(sk, ESTABLISHED) && !sctp_sstate(sk, CLOSING)) return NULL; /* Get the first and the only association from the list. */ if (!list_empty(&sctp_sk(sk)->ep->asocs)) asoc = list_entry(sctp_sk(sk)->ep->asocs.next, struct sctp_association, asocs); return asoc; } /* Otherwise this is a UDP-style socket. */ if (id <= SCTP_ALL_ASSOC) return NULL; spin_lock_bh(&sctp_assocs_id_lock); asoc = (struct sctp_association *)idr_find(&sctp_assocs_id, (int)id); if (asoc && (asoc->base.sk != sk || asoc->base.dead)) asoc = NULL; spin_unlock_bh(&sctp_assocs_id_lock); return asoc; } /* Look up the transport from an address and an assoc id. If both address and * id are specified, the associations matching the address and the id should be * the same. */ static struct sctp_transport *sctp_addr_id2transport(struct sock *sk, struct sockaddr_storage *addr, sctp_assoc_t id) { struct sctp_association *addr_asoc = NULL, *id_asoc = NULL; struct sctp_af *af = sctp_get_af_specific(addr->ss_family); union sctp_addr *laddr = (union sctp_addr *)addr; struct sctp_transport *transport; if (!af || sctp_verify_addr(sk, laddr, af->sockaddr_len)) return NULL; addr_asoc = sctp_endpoint_lookup_assoc(sctp_sk(sk)->ep, laddr, &transport); if (!addr_asoc) return NULL; id_asoc = sctp_id2assoc(sk, id); if (id_asoc && (id_asoc != addr_asoc)) return NULL; sctp_get_pf_specific(sk->sk_family)->addr_to_user(sctp_sk(sk), (union sctp_addr *)addr); return transport; } /* API 3.1.2 bind() - UDP Style Syntax * The syntax of bind() is, * * ret = bind(int sd, struct sockaddr *addr, int addrlen); * * sd - the socket descriptor returned by socket(). * addr - the address structure (struct sockaddr_in or struct * sockaddr_in6 [RFC 2553]), * addr_len - the size of the address structure. */ static int sctp_bind(struct sock *sk, struct sockaddr_unsized *addr, int addr_len) { int retval = 0; lock_sock(sk); pr_debug("%s: sk:%p, addr:%p, addr_len:%d\n", __func__, sk, addr, addr_len); /* Disallow binding twice. */ if (!sctp_sk(sk)->ep->base.bind_addr.port) retval = sctp_do_bind(sk, (union sctp_addr *)addr, addr_len); else retval = -EINVAL; release_sock(sk); return retval; } static int sctp_get_port_local(struct sock *, union sctp_addr *); /* Verify this is a valid sockaddr. */ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt, union sctp_addr *addr, int len) { struct sctp_af *af; /* Check minimum size. */ if (len < sizeof (struct sockaddr)) return NULL; if (!opt->pf->af_supported(addr->sa.sa_family, opt)) return NULL; if (addr->sa.sa_family == AF_INET6) { if (len < SIN6_LEN_RFC2133) return NULL; /* V4 mapped address are really of AF_INET family */ if (ipv6_addr_v4mapped(&addr->v6.sin6_addr) && !opt->pf->af_supported(AF_INET, opt)) return NULL; } /* If we get this far, af is valid. */ af = sctp_get_af_specific(addr->sa.sa_family); if (len < af->sockaddr_len) return NULL; return af; } static void sctp_auto_asconf_init(struct sctp_sock *sp) { struct net *net = sock_net(&sp->inet.sk); if (net->sctp.default_auto_asconf) { spin_lock_bh(&net->sctp.addr_wq_lock); list_add_tail(&sp->auto_asconf_list, &net->sctp.auto_asconf_splist); spin_unlock_bh(&net->sctp.addr_wq_lock); sp->do_auto_asconf = 1; } } /* Bind a local address either to an endpoint or to an association. */ static int sctp_do_bind(struct sock *sk, union sctp_addr *addr, int len) { struct net *net = sock_net(sk); struct sctp_sock *sp = sctp_sk(sk); struct sctp_endpoint *ep = sp->ep; struct sctp_bind_addr *bp = &ep->base.bind_addr; struct sctp_af *af; unsigned short snum; int ret = 0; /* Common sockaddr verification. */ af = sctp_sockaddr_af(sp, addr, len); if (!af) { pr_debug("%s: sk:%p, newaddr:%p, len:%d EINVAL\n", __func__, sk, addr, len); return -EINVAL; } snum = ntohs(addr->v4.sin_port); pr_debug("%s: sk:%p, new addr:%pISc, port:%d, new port:%d, len:%d\n", __func__, sk, &addr->sa, bp->port, snum, len); /* PF specific bind() address verification. */ if (!sp->pf->bind_verify(sp, addr)) return -EADDRNOTAVAIL; /* We must either be unbound, or bind to the same port. * It's OK to allow 0 ports if we are already bound. * We'll just inhert an already bound port in this case */ if (bp->port) { if (!snum) snum = bp->port; else if (snum != bp->port) { pr_debug("%s: new port %d doesn't match existing port " "%d\n", __func__, snum, bp->port); return -EINVAL; } } if (snum && inet_port_requires_bind_service(net, snum) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) return -EACCES; /* See if the address matches any of the addresses we may have * already bound before checking against other endpoints. */ if (sctp_bind_addr_match(bp, addr, sp)) return -EINVAL; /* Make sure we are allowed to bind here. * The function sctp_get_port_local() does duplicate address * detection. */ addr->v4.sin_port = htons(snum); if (sctp_get_port_local(sk, addr)) return -EADDRINUSE; /* Refresh ephemeral port. */ if (!bp->port) { bp->port = inet_sk(sk)->inet_num; sctp_auto_asconf_init(sp); } /* Add the address to the bind address list. * Use GFP_ATOMIC since BHs will be disabled. */ ret = sctp_add_bind_addr(bp, addr, af->sockaddr_len, SCTP_ADDR_SRC, GFP_ATOMIC); if (ret) { sctp_put_port(sk); return ret; } /* Copy back into socket for getsockname() use. */ inet_sk(sk)->inet_sport = htons(inet_sk(sk)->inet_num); sp->pf->to_sk_saddr(addr, sk); return ret; } /* ADDIP Section 4.1.1 Congestion Control of ASCONF Chunks * * R1) One and only one ASCONF Chunk MAY be in transit and unacknowledged * at any one time. If a sender, after sending an ASCONF chunk, decides * it needs to transfer another ASCONF Chunk, it MUST wait until the * ASCONF-ACK Chunk returns from the previous ASCONF Chunk before sending a * subsequent ASCONF. Note this restriction binds each side, so at any * time two ASCONF may be in-transit on any given association (one sent * from each endpoint). */ static int sctp_send_asconf(struct sctp_association *asoc, struct sctp_chunk *chunk) { int retval = 0; /* If there is an outstanding ASCONF chunk, queue it for later * transmission. */ if (asoc->addip_last_asconf) { list_add_tail(&chunk->list, &asoc->addip_chunk_list); goto out; } /* Hold the chunk until an ASCONF_ACK is received. */ sctp_chunk_hold(chunk); retval = sctp_primitive_ASCONF(asoc->base.net, asoc, chunk); if (retval) sctp_chunk_free(chunk); else asoc->addip_last_asconf = chunk; out: return retval; } /* Add a list of addresses as bind addresses to local endpoint or * association. * * Basically run through each address specified in the addrs/addrcnt * array/length pair, determine if it is IPv6 or IPv4 and call * sctp_do_bind() on it. * * If any of them fails, then the operation will be reversed and the * ones that were added will be removed. * * Only sctp_setsockopt_bindx() is supposed to call this function. */ static int sctp_bindx_add(struct sock *sk, struct sockaddr *addrs, int addrcnt) { int cnt; int retval = 0; void *addr_buf; struct sockaddr *sa_addr; struct sctp_af *af; pr_debug("%s: sk:%p, addrs:%p, addrcnt:%d\n", __func__, sk, addrs, addrcnt); addr_buf = addrs; for (cnt = 0; cnt < addrcnt; cnt++) { /* The list may contain either IPv4 or IPv6 address; * determine the address length for walking thru the list. */ sa_addr = addr_buf; af = sctp_get_af_specific(sa_addr->sa_family); if (!af) { retval = -EINVAL; goto err_bindx_add; } retval = sctp_do_bind(sk, (union sctp_addr *)sa_addr, af->sockaddr_len); addr_buf += af->sockaddr_len; err_bindx_add: if (retval < 0) { /* Failed. Cleanup the ones that have been added */ if (cnt > 0) sctp_bindx_rem(sk, addrs, cnt); return retval; } } return retval; } /* Send an ASCONF chunk with Add IP address parameters to all the peers of the * associations that are part of the endpoint indicating that a list of local * addresses are added to the endpoint. * * If any of the addresses is already in the bind address list of the * association, we do not send the chunk for that association. But it will not * affect other associations. * * Only sctp_setsockopt_bindx() is supposed to call this function. */ static int sctp_send_asconf_add_ip(struct sock *sk, struct sockaddr *addrs, int addrcnt) { struct sctp_sock *sp; struct sctp_endpoint *ep; struct sctp_association *asoc; struct sctp_bind_addr *bp; struct sctp_chunk *chunk; struct sctp_sockaddr_entry *laddr; union sctp_addr *addr; union sctp_addr saveaddr; void *addr_buf; struct sctp_af *af; struct list_head *p; int i; int retval = 0; sp = sctp_sk(sk); ep = sp->ep; if (!ep->asconf_enable) return retval; pr_debug("%s: sk:%p, addrs:%p, addrcnt:%d\n", __func__, sk, addrs, addrcnt); list_for_each_entry(asoc, &ep->asocs, asocs) { if (!asoc->peer.asconf_capable) continue; if (asoc->peer.addip_disabled_mask & SCTP_PARAM_ADD_IP) continue; if (!sctp_state(asoc, ESTABLISHED)) continue; /* Check if any address in the packed array of addresses is * in the bind address list of the association. If so, * do not send the asconf chunk to its peer, but continue with * other associations. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { addr = addr_buf; af = sctp_get_af_specific(addr->v4.sin_family); if (!af) { retval = -EINVAL; goto out; } if (sctp_assoc_lookup_laddr(asoc, addr)) break; addr_buf += af->sockaddr_len; } if (i < addrcnt) continue; /* Use the first valid address in bind addr list of * association as Address Parameter of ASCONF CHUNK. */ bp = &asoc->base.bind_addr; p = bp->address_list.next; laddr = list_entry(p, struct sctp_sockaddr_entry, list); chunk = sctp_make_asconf_update_ip(asoc, &laddr->a, addrs, addrcnt, SCTP_PARAM_ADD_IP); if (!chunk) { retval = -ENOMEM; goto out; } /* Add the new addresses to the bind address list with * use_as_src set to 0. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { addr = addr_buf; af = sctp_get_af_specific(addr->v4.sin_family); memcpy(&saveaddr, addr, af->sockaddr_len); retval = sctp_add_bind_addr(bp, &saveaddr, sizeof(saveaddr), SCTP_ADDR_NEW, GFP_ATOMIC); addr_buf += af->sockaddr_len; } if (asoc->src_out_of_asoc_ok) { struct sctp_transport *trans; list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { trans->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380)); trans->ssthresh = asoc->peer.i.a_rwnd; trans->rto = asoc->rto_initial; sctp_max_rto(asoc, trans); trans->rtt = trans->srtt = trans->rttvar = 0; /* Clear the source and route cache */ sctp_transport_route(trans, NULL, sctp_sk(asoc->base.sk)); } } retval = sctp_send_asconf(asoc, chunk); } out: return retval; } /* Remove a list of addresses from bind addresses list. Do not remove the * last address. * * Basically run through each address specified in the addrs/addrcnt * array/length pair, determine if it is IPv6 or IPv4 and call * sctp_del_bind() on it. * * If any of them fails, then the operation will be reversed and the * ones that were removed will be added back. * * At least one address has to be left; if only one address is * available, the operation will return -EBUSY. * * Only sctp_setsockopt_bindx() is supposed to call this function. */ static int sctp_bindx_rem(struct sock *sk, struct sockaddr *addrs, int addrcnt) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_endpoint *ep = sp->ep; int cnt; struct sctp_bind_addr *bp = &ep->base.bind_addr; int retval = 0; void *addr_buf; union sctp_addr *sa_addr; struct sctp_af *af; pr_debug("%s: sk:%p, addrs:%p, addrcnt:%d\n", __func__, sk, addrs, addrcnt); addr_buf = addrs; for (cnt = 0; cnt < addrcnt; cnt++) { /* If the bind address list is empty or if there is only one * bind address, there is nothing more to be removed (we need * at least one address here). */ if (list_empty(&bp->address_list) || (sctp_list_single_entry(&bp->address_list))) { retval = -EBUSY; goto err_bindx_rem; } sa_addr = addr_buf; af = sctp_get_af_specific(sa_addr->sa.sa_family); if (!af) { retval = -EINVAL; goto err_bindx_rem; } if (!af->addr_valid(sa_addr, sp, NULL)) { retval = -EADDRNOTAVAIL; goto err_bindx_rem; } if (sa_addr->v4.sin_port && sa_addr->v4.sin_port != htons(bp->port)) { retval = -EINVAL; goto err_bindx_rem; } if (!sa_addr->v4.sin_port) sa_addr->v4.sin_port = htons(bp->port); /* FIXME - There is probably a need to check if sk->sk_saddr and * sk->sk_rcv_addr are currently set to one of the addresses to * be removed. This is something which needs to be looked into * when we are fixing the outstanding issues with multi-homing * socket routing and failover schemes. Refer to comments in * sctp_do_bind(). -daisy */ retval = sctp_del_bind_addr(bp, sa_addr); addr_buf += af->sockaddr_len; err_bindx_rem: if (retval < 0) { /* Failed. Add the ones that has been removed back */ if (cnt > 0) sctp_bindx_add(sk, addrs, cnt); return retval; } } return retval; } /* Send an ASCONF chunk with Delete IP address parameters to all the peers of * the associations that are part of the endpoint indicating that a list of * local addresses are removed from the endpoint. * * If any of the addresses is already in the bind address list of the * association, we do not send the chunk for that association. But it will not * affect other associations. * * Only sctp_setsockopt_bindx() is supposed to call this function. */ static int sctp_send_asconf_del_ip(struct sock *sk, struct sockaddr *addrs, int addrcnt) { struct sctp_sock *sp; struct sctp_endpoint *ep; struct sctp_association *asoc; struct sctp_transport *transport; struct sctp_bind_addr *bp; struct sctp_chunk *chunk; union sctp_addr *laddr; void *addr_buf; struct sctp_af *af; struct sctp_sockaddr_entry *saddr; int i; int retval = 0; int stored = 0; chunk = NULL; sp = sctp_sk(sk); ep = sp->ep; if (!ep->asconf_enable) return retval; pr_debug("%s: sk:%p, addrs:%p, addrcnt:%d\n", __func__, sk, addrs, addrcnt); list_for_each_entry(asoc, &ep->asocs, asocs) { if (!asoc->peer.asconf_capable) continue; if (asoc->peer.addip_disabled_mask & SCTP_PARAM_DEL_IP) continue; if (!sctp_state(asoc, ESTABLISHED)) continue; /* Check if any address in the packed array of addresses is * not present in the bind address list of the association. * If so, do not send the asconf chunk to its peer, but * continue with other associations. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { laddr = addr_buf; af = sctp_get_af_specific(laddr->v4.sin_family); if (!af) { retval = -EINVAL; goto out; } if (!sctp_assoc_lookup_laddr(asoc, laddr)) break; addr_buf += af->sockaddr_len; } if (i < addrcnt) continue; /* Find one address in the association's bind address list * that is not in the packed array of addresses. This is to * make sure that we do not delete all the addresses in the * association. */ bp = &asoc->base.bind_addr; laddr = sctp_find_unmatch_addr(bp, (union sctp_addr *)addrs, addrcnt, sp); if ((laddr == NULL) && (addrcnt == 1)) { if (asoc->asconf_addr_del_pending) continue; asoc->asconf_addr_del_pending = kzalloc(sizeof(union sctp_addr), GFP_ATOMIC); if (asoc->asconf_addr_del_pending == NULL) { retval = -ENOMEM; goto out; } asoc->asconf_addr_del_pending->sa.sa_family = addrs->sa_family; asoc->asconf_addr_del_pending->v4.sin_port = htons(bp->port); if (addrs->sa_family == AF_INET) { struct sockaddr_in *sin; sin = (struct sockaddr_in *)addrs; asoc->asconf_addr_del_pending->v4.sin_addr.s_addr = sin->sin_addr.s_addr; } else if (addrs->sa_family == AF_INET6) { struct sockaddr_in6 *sin6; sin6 = (struct sockaddr_in6 *)addrs; asoc->asconf_addr_del_pending->v6.sin6_addr = sin6->sin6_addr; } pr_debug("%s: keep the last address asoc:%p %pISc at %p\n", __func__, asoc, &asoc->asconf_addr_del_pending->sa, asoc->asconf_addr_del_pending); asoc->src_out_of_asoc_ok = 1; stored = 1; goto skip_mkasconf; } if (laddr == NULL) return -EINVAL; /* We do not need RCU protection throughout this loop * because this is done under a socket lock from the * setsockopt call. */ chunk = sctp_make_asconf_update_ip(asoc, laddr, addrs, addrcnt, SCTP_PARAM_DEL_IP); if (!chunk) { retval = -ENOMEM; goto out; } skip_mkasconf: /* Reset use_as_src flag for the addresses in the bind address * list that are to be deleted. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { laddr = addr_buf; af = sctp_get_af_specific(laddr->v4.sin_family); list_for_each_entry(saddr, &bp->address_list, list) { if (sctp_cmp_addr_exact(&saddr->a, laddr)) saddr->state = SCTP_ADDR_DEL; } addr_buf += af->sockaddr_len; } /* Update the route and saddr entries for all the transports * as some of the addresses in the bind address list are * about to be deleted and cannot be used as source addresses. */ list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { sctp_transport_route(transport, NULL, sctp_sk(asoc->base.sk)); } if (stored) /* We don't need to transmit ASCONF */ continue; retval = sctp_send_asconf(asoc, chunk); } out: return retval; } /* set addr events to assocs in the endpoint. ep and addr_wq must be locked */ int sctp_asconf_mgmt(struct sctp_sock *sp, struct sctp_sockaddr_entry *addrw) { struct sock *sk = sctp_opt2sk(sp); union sctp_addr *addr; struct sctp_af *af; /* It is safe to write port space in caller. */ addr = &addrw->a; addr->v4.sin_port = htons(sp->ep->base.bind_addr.port); af = sctp_get_af_specific(addr->sa.sa_family); if (!af) return -EINVAL; if (sctp_verify_addr(sk, addr, af->sockaddr_len)) return -EINVAL; if (addrw->state == SCTP_ADDR_NEW) return sctp_send_asconf_add_ip(sk, (struct sockaddr *)addr, 1); else return sctp_send_asconf_del_ip(sk, (struct sockaddr *)addr, 1); } /* Helper for tunneling sctp_bindx() requests through sctp_setsockopt() * * API 8.1 * int sctp_bindx(int sd, struct sockaddr *addrs, int addrcnt, * int flags); * * If sd is an IPv4 socket, the addresses passed must be IPv4 addresses. * If the sd is an IPv6 socket, the addresses passed can either be IPv4 * or IPv6 addresses. * * A single address may be specified as INADDR_ANY or IN6ADDR_ANY, see * Section 3.1.2 for this usage. * * addrs is a pointer to an array of one or more socket addresses. Each * address is contained in its appropriate structure (i.e. struct * sockaddr_in or struct sockaddr_in6) the family of the address type * must be used to distinguish the address length (note that this * representation is termed a "packed array" of addresses). The caller * specifies the number of addresses in the array with addrcnt. * * On success, sctp_bindx() returns 0. On failure, sctp_bindx() returns * -1, and sets errno to the appropriate error code. * * For SCTP, the port given in each socket address must be the same, or * sctp_bindx() will fail, setting errno to EINVAL. * * The flags parameter is formed from the bitwise OR of zero or more of * the following currently defined flags: * * SCTP_BINDX_ADD_ADDR * * SCTP_BINDX_REM_ADDR * * SCTP_BINDX_ADD_ADDR directs SCTP to add the given addresses to the * association, and SCTP_BINDX_REM_ADDR directs SCTP to remove the given * addresses from the association. The two flags are mutually exclusive; * if both are given, sctp_bindx() will fail with EINVAL. A caller may * not remove all addresses from an association; sctp_bindx() will * reject such an attempt with EINVAL. * * An application can use sctp_bindx(SCTP_BINDX_ADD_ADDR) to associate * additional addresses with an endpoint after calling bind(). Or use * sctp_bindx(SCTP_BINDX_REM_ADDR) to remove some addresses a listening * socket is associated with so that no new association accepted will be * associated with those addresses. If the endpoint supports dynamic * address a SCTP_BINDX_REM_ADDR or SCTP_BINDX_ADD_ADDR may cause a * endpoint to send the appropriate message to the peer to change the * peers address lists. * * Adding and removing addresses from a connected association is * optional functionality. Implementations that do not support this * functionality should return EOPNOTSUPP. * * Basically do nothing but copying the addresses from user to kernel * land and invoking either sctp_bindx_add() or sctp_bindx_rem() on the sk. * This is used for tunneling the sctp_bindx() request through sctp_setsockopt() * from userspace. * * On exit there is no need to do sockfd_put(), sys_setsockopt() does * it. * * sk The sk of the socket * addrs The pointer to the addresses * addrssize Size of the addrs buffer * op Operation to perform (add or remove, see the flags of * sctp_bindx) * * Returns 0 if ok, <0 errno code on error. */ static int sctp_setsockopt_bindx(struct sock *sk, struct sockaddr *addrs, int addrs_size, int op) { int err; int addrcnt = 0; int walk_size = 0; struct sockaddr *sa_addr; void *addr_buf = addrs; struct sctp_af *af; pr_debug("%s: sk:%p addrs:%p addrs_size:%d opt:%d\n", __func__, sk, addr_buf, addrs_size, op); if (unlikely(addrs_size <= 0)) return -EINVAL; /* Walk through the addrs buffer and count the number of addresses. */ while (walk_size < addrs_size) { if (walk_size + sizeof(sa_family_t) > addrs_size) return -EINVAL; sa_addr = addr_buf; af = sctp_get_af_specific(sa_addr->sa_family); /* If the address family is not supported or if this address * causes the address buffer to overflow return EINVAL. */ if (!af || (walk_size + af->sockaddr_len) > addrs_size) return -EINVAL; addrcnt++; addr_buf += af->sockaddr_len; walk_size += af->sockaddr_len; } /* Do the work. */ switch (op) { case SCTP_BINDX_ADD_ADDR: /* Allow security module to validate bindx addresses. */ err = security_sctp_bind_connect(sk, SCTP_SOCKOPT_BINDX_ADD, addrs, addrs_size); if (err) return err; err = sctp_bindx_add(sk, addrs, addrcnt); if (err) return err; return sctp_send_asconf_add_ip(sk, addrs, addrcnt); case SCTP_BINDX_REM_ADDR: err = sctp_bindx_rem(sk, addrs, addrcnt); if (err) return err; return sctp_send_asconf_del_ip(sk, addrs, addrcnt); default: return -EINVAL; } } static int sctp_bind_add(struct sock *sk, struct sockaddr_unsized *addrs, int addrlen) { int err; lock_sock(sk); err = sctp_setsockopt_bindx(sk, (struct sockaddr *)addrs, addrlen, SCTP_BINDX_ADD_ADDR); release_sock(sk); return err; } static int sctp_connect_new_asoc(struct sctp_endpoint *ep, const union sctp_addr *daddr, const struct sctp_initmsg *init, struct sctp_transport **tp) { struct sctp_association *asoc; struct sock *sk = ep->base.sk; struct net *net = sock_net(sk); enum sctp_scope scope; int err; if (sctp_endpoint_is_peeled_off(ep, daddr)) return -EADDRNOTAVAIL; if (!ep->base.bind_addr.port) { if (sctp_autobind(sk)) return -EAGAIN; } else { if (inet_port_requires_bind_service(net, ep->base.bind_addr.port) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) return -EACCES; } scope = sctp_scope(daddr); asoc = sctp_association_new(ep, sk, scope, GFP_KERNEL); if (!asoc) return -ENOMEM; err = sctp_assoc_set_bind_addr_from_ep(asoc, scope, GFP_KERNEL); if (err < 0) goto free; *tp = sctp_assoc_add_peer(asoc, daddr, GFP_KERNEL, SCTP_UNKNOWN); if (!*tp) { err = -ENOMEM; goto free; } if (!init) return 0; if (init->sinit_num_ostreams) { __u16 outcnt = init->sinit_num_ostreams; asoc->c.sinit_num_ostreams = outcnt; /* outcnt has been changed, need to re-init stream */ err = sctp_stream_init(&asoc->stream, outcnt, 0, GFP_KERNEL); if (err) goto free; } if (init->sinit_max_instreams) asoc->c.sinit_max_instreams = init->sinit_max_instreams; if (init->sinit_max_attempts) asoc->max_init_attempts = init->sinit_max_attempts; if (init->sinit_max_init_timeo) asoc->max_init_timeo = msecs_to_jiffies(init->sinit_max_init_timeo); return 0; free: sctp_association_free(asoc); return err; } static int sctp_connect_add_peer(struct sctp_association *asoc, union sctp_addr *daddr, int addr_len) { struct sctp_endpoint *ep = asoc->ep; struct sctp_association *old; struct sctp_transport *t; int err; err = sctp_verify_addr(ep->base.sk, daddr, addr_len); if (err) return err; old = sctp_endpoint_lookup_assoc(ep, daddr, &t); if (old && old != asoc) return old->state >= SCTP_STATE_ESTABLISHED ? -EISCONN : -EALREADY; if (sctp_endpoint_is_peeled_off(ep, daddr)) return -EADDRNOTAVAIL; t = sctp_assoc_add_peer(asoc, daddr, GFP_KERNEL, SCTP_UNKNOWN); if (!t) return -ENOMEM; return 0; } /* __sctp_connect(struct sock* sk, struct sockaddr *kaddrs, int addrs_size) * * Common routine for handling connect() and sctp_connectx(). * Connect will come in with just a single address. */ static int __sctp_connect(struct sock *sk, struct sockaddr *kaddrs, int addrs_size, int flags, sctp_assoc_t *assoc_id) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_endpoint *ep = sp->ep; struct sctp_transport *transport; struct sctp_association *asoc; void *addr_buf = kaddrs; union sctp_addr *daddr; struct sctp_af *af; int walk_size, err; long timeo; if (sctp_sstate(sk, ESTABLISHED) || sctp_sstate(sk, CLOSING) || (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING))) return -EISCONN; daddr = addr_buf; af = sctp_get_af_specific(daddr->sa.sa_family); if (!af || af->sockaddr_len > addrs_size) return -EINVAL; err = sctp_verify_addr(sk, daddr, af->sockaddr_len); if (err) return err; asoc = sctp_endpoint_lookup_assoc(ep, daddr, &transport); if (asoc) return asoc->state >= SCTP_STATE_ESTABLISHED ? -EISCONN : -EALREADY; err = sctp_connect_new_asoc(ep, daddr, NULL, &transport); if (err) return err; asoc = transport->asoc; addr_buf += af->sockaddr_len; walk_size = af->sockaddr_len; while (walk_size < addrs_size) { err = -EINVAL; if (walk_size + sizeof(sa_family_t) > addrs_size) goto out_free; daddr = addr_buf; af = sctp_get_af_specific(daddr->sa.sa_family); if (!af || af->sockaddr_len + walk_size > addrs_size) goto out_free; if (asoc->peer.port != ntohs(daddr->v4.sin_port)) goto out_free; err = sctp_connect_add_peer(asoc, daddr, af->sockaddr_len); if (err) goto out_free; addr_buf += af->sockaddr_len; walk_size += af->sockaddr_len; } /* In case the user of sctp_connectx() wants an association * id back, assign one now. */ if (assoc_id) { err = sctp_assoc_set_id(asoc, GFP_KERNEL); if (err < 0) goto out_free; } err = sctp_primitive_ASSOCIATE(sock_net(sk), asoc, NULL); if (err < 0) goto out_free; /* Initialize sk's dport and daddr for getpeername() */ inet_sk(sk)->inet_dport = htons(asoc->peer.port); sp->pf->to_sk_daddr(daddr, sk); sk->sk_err = 0; if (assoc_id) *assoc_id = asoc->assoc_id; timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); return sctp_wait_for_connect(asoc, &timeo); out_free: pr_debug("%s: took out_free path with asoc:%p kaddrs:%p err:%d\n", __func__, asoc, kaddrs, err); sctp_association_free(asoc); return err; } /* Helper for tunneling sctp_connectx() requests through sctp_setsockopt() * * API 8.9 * int sctp_connectx(int sd, struct sockaddr *addrs, int addrcnt, * sctp_assoc_t *asoc); * * If sd is an IPv4 socket, the addresses passed must be IPv4 addresses. * If the sd is an IPv6 socket, the addresses passed can either be IPv4 * or IPv6 addresses. * * A single address may be specified as INADDR_ANY or IN6ADDR_ANY, see * Section 3.1.2 for this usage. * * addrs is a pointer to an array of one or more socket addresses. Each * address is contained in its appropriate structure (i.e. struct * sockaddr_in or struct sockaddr_in6) the family of the address type * must be used to distengish the address length (note that this * representation is termed a "packed array" of addresses). The caller * specifies the number of addresses in the array with addrcnt. * * On success, sctp_connectx() returns 0. It also sets the assoc_id to * the association id of the new association. On failure, sctp_connectx() * returns -1, and sets errno to the appropriate error code. The assoc_id * is not touched by the kernel. * * For SCTP, the port given in each socket address must be the same, or * sctp_connectx() will fail, setting errno to EINVAL. * * An application can use sctp_connectx to initiate an association with * an endpoint that is multi-homed. Much like sctp_bindx() this call * allows a caller to specify multiple addresses at which a peer can be * reached. The way the SCTP stack uses the list of addresses to set up * the association is implementation dependent. This function only * specifies that the stack will try to make use of all the addresses in * the list when needed. * * Note that the list of addresses passed in is only used for setting up * the association. It does not necessarily equal the set of addresses * the peer uses for the resulting association. If the caller wants to * find out the set of peer addresses, it must use sctp_getpaddrs() to * retrieve them after the association has been set up. * * Basically do nothing but copying the addresses from user to kernel * land and invoking either sctp_connectx(). This is used for tunneling * the sctp_connectx() request through sctp_setsockopt() from userspace. * * On exit there is no need to do sockfd_put(), sys_setsockopt() does * it. * * sk The sk of the socket * addrs The pointer to the addresses * addrssize Size of the addrs buffer * * Returns >=0 if ok, <0 errno code on error. */ static int __sctp_setsockopt_connectx(struct sock *sk, struct sockaddr *kaddrs, int addrs_size, sctp_assoc_t *assoc_id) { int err = 0, flags = 0; pr_debug("%s: sk:%p addrs:%p addrs_size:%d\n", __func__, sk, kaddrs, addrs_size); /* make sure the 1st addr's sa_family is accessible later */ if (unlikely(addrs_size < sizeof(sa_family_t))) return -EINVAL; /* Allow security module to validate connectx addresses. */ err = security_sctp_bind_connect(sk, SCTP_SOCKOPT_CONNECTX, (struct sockaddr *)kaddrs, addrs_size); if (err) return err; /* in-kernel sockets don't generally have a file allocated to them * if all they do is call sock_create_kern(). */ if (sk->sk_socket->file) flags = sk->sk_socket->file->f_flags; return __sctp_connect(sk, kaddrs, addrs_size, flags, assoc_id); } /* * This is an older interface. It's kept for backward compatibility * to the option that doesn't provide association id. */ static int sctp_setsockopt_connectx_old(struct sock *sk, struct sockaddr *kaddrs, int addrs_size) { return __sctp_setsockopt_connectx(sk, kaddrs, addrs_size, NULL); } /* * New interface for the API. The since the API is done with a socket * option, to make it simple we feed back the association id is as a return * indication to the call. Error is always negative and association id is * always positive. */ static int sctp_setsockopt_connectx(struct sock *sk, struct sockaddr *kaddrs, int addrs_size) { sctp_assoc_t assoc_id = 0; int err = 0; err = __sctp_setsockopt_connectx(sk, kaddrs, addrs_size, &assoc_id); if (err) return err; else return assoc_id; } /* * New (hopefully final) interface for the API. * We use the sctp_getaddrs_old structure so that use-space library * can avoid any unnecessary allocations. The only different part * is that we store the actual length of the address buffer into the * addrs_num structure member. That way we can re-use the existing * code. */ #ifdef CONFIG_COMPAT struct compat_sctp_getaddrs_old { sctp_assoc_t assoc_id; s32 addr_num; compat_uptr_t addrs; /* struct sockaddr * */ }; #endif static int sctp_getsockopt_connectx3(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_getaddrs_old param; sctp_assoc_t assoc_id = 0; struct sockaddr *kaddrs; int err = 0; #ifdef CONFIG_COMPAT if (in_compat_syscall()) { struct compat_sctp_getaddrs_old param32; if (len < sizeof(param32)) return -EINVAL; if (copy_from_user(¶m32, optval, sizeof(param32))) return -EFAULT; param.assoc_id = param32.assoc_id; param.addr_num = param32.addr_num; param.addrs = compat_ptr(param32.addrs); } else #endif { if (len < sizeof(param)) return -EINVAL; if (copy_from_user(¶m, optval, sizeof(param))) return -EFAULT; } kaddrs = memdup_user(param.addrs, param.addr_num); if (IS_ERR(kaddrs)) return PTR_ERR(kaddrs); err = __sctp_setsockopt_connectx(sk, kaddrs, param.addr_num, &assoc_id); kfree(kaddrs); if (err == 0 || err == -EINPROGRESS) { if (copy_to_user(optval, &assoc_id, sizeof(assoc_id))) return -EFAULT; if (put_user(sizeof(assoc_id), optlen)) return -EFAULT; } return err; } /* API 3.1.4 close() - UDP Style Syntax * Applications use close() to perform graceful shutdown (as described in * Section 10.1 of [SCTP]) on ALL the associations currently represented * by a UDP-style socket. * * The syntax is * * ret = close(int sd); * * sd - the socket descriptor of the associations to be closed. * * To gracefully shutdown a specific association represented by the * UDP-style socket, an application should use the sendmsg() call, * passing no user data, but including the appropriate flag in the * ancillary data (see Section xxxx). * * If sd in the close() call is a branched-off socket representing only * one association, the shutdown is performed on that association only. * * 4.1.6 close() - TCP Style Syntax * * Applications use close() to gracefully close down an association. * * The syntax is: * * int close(int sd); * * sd - the socket descriptor of the association to be closed. * * After an application calls close() on a socket descriptor, no further * socket operations will succeed on that descriptor. * * API 7.1.4 SO_LINGER * * An application using the TCP-style socket can use this option to * perform the SCTP ABORT primitive. The linger option structure is: * * struct linger { * int l_onoff; // option on/off * int l_linger; // linger time * }; * * To enable the option, set l_onoff to 1. If the l_linger value is set * to 0, calling close() is the same as the ABORT primitive. If the * value is set to a negative value, the setsockopt() call will return * an error. If the value is set to a positive value linger_time, the * close() can be blocked for at most linger_time ms. If the graceful * shutdown phase does not finish during this period, close() will * return but the graceful shutdown phase continues in the system. */ static void sctp_close(struct sock *sk, long timeout) { struct net *net = sock_net(sk); struct sctp_endpoint *ep; struct sctp_association *asoc; struct list_head *pos, *temp; unsigned int data_was_unread; pr_debug("%s: sk:%p, timeout:%ld\n", __func__, sk, timeout); lock_sock_nested(sk, SINGLE_DEPTH_NESTING); sk->sk_shutdown = SHUTDOWN_MASK; inet_sk_set_state(sk, SCTP_SS_CLOSING); ep = sctp_sk(sk)->ep; /* Clean up any skbs sitting on the receive queue. */ data_was_unread = sctp_queue_purge_ulpevents(&sk->sk_receive_queue); data_was_unread += sctp_queue_purge_ulpevents(&sctp_sk(sk)->pd_lobby); /* Walk all associations on an endpoint. */ list_for_each_safe(pos, temp, &ep->asocs) { asoc = list_entry(pos, struct sctp_association, asocs); if (sctp_style(sk, TCP)) { /* A closed association can still be in the list if * it belongs to a TCP-style listening socket that is * not yet accepted. If so, free it. If not, send an * ABORT or SHUTDOWN based on the linger options. */ if (sctp_state(asoc, CLOSED)) { sctp_association_free(asoc); continue; } } if (data_was_unread || !skb_queue_empty(&asoc->ulpq.lobby) || !skb_queue_empty(&asoc->ulpq.reasm) || !skb_queue_empty(&asoc->ulpq.reasm_uo) || (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime)) { struct sctp_chunk *chunk; chunk = sctp_make_abort_user(asoc, NULL, 0); sctp_primitive_ABORT(net, asoc, chunk); } else sctp_primitive_SHUTDOWN(net, asoc, NULL); } /* On a TCP-style socket, block for at most linger_time if set. */ if (sctp_style(sk, TCP) && timeout) sctp_wait_for_close(sk, timeout); /* This will run the backlog queue. */ release_sock(sk); /* Supposedly, no process has access to the socket, but * the net layers still may. * Also, sctp_destroy_sock() needs to be called with addr_wq_lock * held and that should be grabbed before socket lock. */ spin_lock_bh(&net->sctp.addr_wq_lock); bh_lock_sock_nested(sk); /* Hold the sock, since sk_common_release() will put sock_put() * and we have just a little more cleanup. */ sock_hold(sk); sk_common_release(sk); bh_unlock_sock(sk); spin_unlock_bh(&net->sctp.addr_wq_lock); sock_put(sk); } /* Handle EPIPE error. */ static int sctp_error(struct sock *sk, int flags, int err) { if (err == -EPIPE) err = sock_error(sk) ? : -EPIPE; if (err == -EPIPE && !(flags & MSG_NOSIGNAL)) send_sig(SIGPIPE, current, 0); return err; } /* API 3.1.3 sendmsg() - UDP Style Syntax * * An application uses sendmsg() and recvmsg() calls to transmit data to * and receive data from its peer. * * ssize_t sendmsg(int socket, const struct msghdr *message, * int flags); * * socket - the socket descriptor of the endpoint. * message - pointer to the msghdr structure which contains a single * user message and possibly some ancillary data. * * See Section 5 for complete description of the data * structures. * * flags - flags sent or received with the user message, see Section * 5 for complete description of the flags. * * Note: This function could use a rewrite especially when explicit * connect support comes in. */ /* BUG: We do not implement the equivalent of sk_stream_wait_memory(). */ static int sctp_msghdr_parse(const struct msghdr *msg, struct sctp_cmsgs *cmsgs); static int sctp_sendmsg_parse(struct sock *sk, struct sctp_cmsgs *cmsgs, struct sctp_sndrcvinfo *srinfo, const struct msghdr *msg, size_t msg_len) { __u16 sflags; int err; if (sctp_sstate(sk, LISTENING) && sctp_style(sk, TCP)) return -EPIPE; if (msg_len > sk->sk_sndbuf) return -EMSGSIZE; memset(cmsgs, 0, sizeof(*cmsgs)); err = sctp_msghdr_parse(msg, cmsgs); if (err) { pr_debug("%s: msghdr parse err:%x\n", __func__, err); return err; } memset(srinfo, 0, sizeof(*srinfo)); if (cmsgs->srinfo) { srinfo->sinfo_stream = cmsgs->srinfo->sinfo_stream; srinfo->sinfo_flags = cmsgs->srinfo->sinfo_flags; srinfo->sinfo_ppid = cmsgs->srinfo->sinfo_ppid; srinfo->sinfo_context = cmsgs->srinfo->sinfo_context; srinfo->sinfo_assoc_id = cmsgs->srinfo->sinfo_assoc_id; srinfo->sinfo_timetolive = cmsgs->srinfo->sinfo_timetolive; } if (cmsgs->sinfo) { srinfo->sinfo_stream = cmsgs->sinfo->snd_sid; srinfo->sinfo_flags = cmsgs->sinfo->snd_flags; srinfo->sinfo_ppid = cmsgs->sinfo->snd_ppid; srinfo->sinfo_context = cmsgs->sinfo->snd_context; srinfo->sinfo_assoc_id = cmsgs->sinfo->snd_assoc_id; } if (cmsgs->prinfo) { srinfo->sinfo_timetolive = cmsgs->prinfo->pr_value; SCTP_PR_SET_POLICY(srinfo->sinfo_flags, cmsgs->prinfo->pr_policy); } sflags = srinfo->sinfo_flags; if (!sflags && msg_len) return 0; if (sctp_style(sk, TCP) && (sflags & (SCTP_EOF | SCTP_ABORT))) return -EINVAL; if (((sflags & SCTP_EOF) && msg_len > 0) || (!(sflags & (SCTP_EOF | SCTP_ABORT)) && msg_len == 0)) return -EINVAL; if ((sflags & SCTP_ADDR_OVER) && !msg->msg_name) return -EINVAL; return 0; } static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags, struct sctp_cmsgs *cmsgs, union sctp_addr *daddr, struct sctp_transport **tp) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_association *asoc; struct cmsghdr *cmsg; __be32 flowinfo = 0; struct sctp_af *af; int err; *tp = NULL; if (sflags & (SCTP_EOF | SCTP_ABORT)) return -EINVAL; if (sctp_style(sk, TCP) && (sctp_sstate(sk, ESTABLISHED) || sctp_sstate(sk, CLOSING))) return -EADDRNOTAVAIL; /* Label connection socket for first association 1-to-many * style for client sequence socket()->sendmsg(). This * needs to be done before sctp_assoc_add_peer() as that will * set up the initial packet that needs to account for any * security ip options (CIPSO/CALIPSO) added to the packet. */ af = sctp_get_af_specific(daddr->sa.sa_family); if (!af) return -EINVAL; err = security_sctp_bind_connect(sk, SCTP_SENDMSG_CONNECT, (struct sockaddr *)daddr, af->sockaddr_len); if (err < 0) return err; err = sctp_connect_new_asoc(ep, daddr, cmsgs->init, tp); if (err) return err; asoc = (*tp)->asoc; if (!cmsgs->addrs_msg) return 0; if (daddr->sa.sa_family == AF_INET6) flowinfo = daddr->v6.sin6_flowinfo; /* sendv addr list parse */ for_each_cmsghdr(cmsg, cmsgs->addrs_msg) { union sctp_addr _daddr; int dlen; if (cmsg->cmsg_level != IPPROTO_SCTP || (cmsg->cmsg_type != SCTP_DSTADDRV4 && cmsg->cmsg_type != SCTP_DSTADDRV6)) continue; daddr = &_daddr; memset(daddr, 0, sizeof(*daddr)); dlen = cmsg->cmsg_len - sizeof(struct cmsghdr); if (cmsg->cmsg_type == SCTP_DSTADDRV4) { if (dlen < sizeof(struct in_addr)) { err = -EINVAL; goto free; } dlen = sizeof(struct in_addr); daddr->v4.sin_family = AF_INET; daddr->v4.sin_port = htons(asoc->peer.port); memcpy(&daddr->v4.sin_addr, CMSG_DATA(cmsg), dlen); } else { if (dlen < sizeof(struct in6_addr)) { err = -EINVAL; goto free; } dlen = sizeof(struct in6_addr); daddr->v6.sin6_flowinfo = flowinfo; daddr->v6.sin6_family = AF_INET6; daddr->v6.sin6_port = htons(asoc->peer.port); memcpy(&daddr->v6.sin6_addr, CMSG_DATA(cmsg), dlen); } err = sctp_connect_add_peer(asoc, daddr, sizeof(*daddr)); if (err) goto free; } return 0; free: sctp_association_free(asoc); return err; } static int sctp_sendmsg_check_sflags(struct sctp_association *asoc, __u16 sflags, struct msghdr *msg, size_t msg_len) { struct sock *sk = asoc->base.sk; struct net *net = sock_net(sk); if (sctp_state(asoc, CLOSED) && sctp_style(sk, TCP)) return -EPIPE; if ((sflags & SCTP_SENDALL) && sctp_style(sk, UDP) && !sctp_state(asoc, ESTABLISHED)) return 0; if (sflags & SCTP_EOF) { pr_debug("%s: shutting down association:%p\n", __func__, asoc); sctp_primitive_SHUTDOWN(net, asoc, NULL); return 0; } if (sflags & SCTP_ABORT) { struct sctp_chunk *chunk; chunk = sctp_make_abort_user(asoc, msg, msg_len); if (!chunk) return -ENOMEM; pr_debug("%s: aborting association:%p\n", __func__, asoc); sctp_primitive_ABORT(net, asoc, chunk); iov_iter_revert(&msg->msg_iter, msg_len); return 0; } return 1; } static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, struct msghdr *msg, size_t msg_len, struct sctp_transport *transport, struct sctp_sndrcvinfo *sinfo) { struct sock *sk = asoc->base.sk; struct sctp_sock *sp = sctp_sk(sk); struct net *net = sock_net(sk); struct sctp_datamsg *datamsg; bool wait_connect = false; struct sctp_chunk *chunk; long timeo; int err; if (sinfo->sinfo_stream >= asoc->stream.outcnt) { err = -EINVAL; goto err; } if (unlikely(!SCTP_SO(&asoc->stream, sinfo->sinfo_stream)->ext)) { err = sctp_stream_init_ext(&asoc->stream, sinfo->sinfo_stream); if (err) goto err; } if (sp->disable_fragments && msg_len > asoc->frag_point) { err = -EMSGSIZE; goto err; } if (asoc->pmtu_pending) { if (sp->param_flags & SPP_PMTUD_ENABLE) sctp_assoc_sync_pmtu(asoc); asoc->pmtu_pending = 0; } if (sctp_wspace(asoc) < (int)msg_len) sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc)); if (sctp_wspace(asoc) <= 0 || !sk_wmem_schedule(sk, msg_len)) { timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); err = sctp_wait_for_sndbuf(asoc, transport, &timeo, msg_len); if (err) goto err; if (unlikely(sinfo->sinfo_stream >= asoc->stream.outcnt)) { err = -EINVAL; goto err; } } if (sctp_state(asoc, CLOSED)) { err = sctp_primitive_ASSOCIATE(net, asoc, NULL); if (err) goto err; if (asoc->ep->intl_enable) { timeo = sock_sndtimeo(sk, 0); err = sctp_wait_for_connect(asoc, &timeo); if (err) { err = -ESRCH; goto err; } } else { wait_connect = true; } pr_debug("%s: we associated primitively\n", __func__); } datamsg = sctp_datamsg_from_user(asoc, sinfo, &msg->msg_iter); if (IS_ERR(datamsg)) { err = PTR_ERR(datamsg); goto err; } asoc->force_delay = !!(msg->msg_flags & MSG_MORE); list_for_each_entry(chunk, &datamsg->chunks, frag_list) { sctp_chunk_hold(chunk); sctp_set_owner_w(chunk); chunk->transport = transport; } err = sctp_primitive_SEND(net, asoc, datamsg); if (err) { sctp_datamsg_free(datamsg); goto err; } pr_debug("%s: we sent primitively\n", __func__); sctp_datamsg_put(datamsg); if (unlikely(wait_connect)) { timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); sctp_wait_for_connect(asoc, &timeo); } err = msg_len; err: return err; } static union sctp_addr *sctp_sendmsg_get_daddr(struct sock *sk, const struct msghdr *msg, struct sctp_cmsgs *cmsgs) { union sctp_addr *daddr = NULL; int err; if (!sctp_style(sk, UDP_HIGH_BANDWIDTH) && msg->msg_name) { int len = msg->msg_namelen; if (len > sizeof(*daddr)) len = sizeof(*daddr); daddr = (union sctp_addr *)msg->msg_name; err = sctp_verify_addr(sk, daddr, len); if (err) return ERR_PTR(err); } return daddr; } static void sctp_sendmsg_update_sinfo(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, struct sctp_cmsgs *cmsgs) { if (!cmsgs->srinfo && !cmsgs->sinfo) { sinfo->sinfo_stream = asoc->default_stream; sinfo->sinfo_ppid = asoc->default_ppid; sinfo->sinfo_context = asoc->default_context; sinfo->sinfo_assoc_id = sctp_assoc2id(asoc); if (!cmsgs->prinfo) sinfo->sinfo_flags = asoc->default_flags; } if (!cmsgs->srinfo && !cmsgs->prinfo) sinfo->sinfo_timetolive = asoc->default_timetolive; if (cmsgs->authinfo) { /* Reuse sinfo_tsn to indicate that authinfo was set and * sinfo_ssn to save the keyid on tx path. */ sinfo->sinfo_tsn = 1; sinfo->sinfo_ssn = cmsgs->authinfo->auth_keynumber; } } static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_transport *transport = NULL; struct sctp_sndrcvinfo _sinfo, *sinfo; struct sctp_association *asoc, *tmp; struct sctp_cmsgs cmsgs; union sctp_addr *daddr; bool new = false; __u16 sflags; int err; /* Parse and get snd_info */ err = sctp_sendmsg_parse(sk, &cmsgs, &_sinfo, msg, msg_len); if (err) goto out; sinfo = &_sinfo; sflags = sinfo->sinfo_flags; /* Get daddr from msg */ daddr = sctp_sendmsg_get_daddr(sk, msg, &cmsgs); if (IS_ERR(daddr)) { err = PTR_ERR(daddr); goto out; } lock_sock(sk); /* SCTP_SENDALL process */ if ((sflags & SCTP_SENDALL) && sctp_style(sk, UDP)) { list_for_each_entry_safe(asoc, tmp, &ep->asocs, asocs) { err = sctp_sendmsg_check_sflags(asoc, sflags, msg, msg_len); if (err == 0) continue; if (err < 0) goto out_unlock; sctp_sendmsg_update_sinfo(asoc, sinfo, &cmsgs); err = sctp_sendmsg_to_asoc(asoc, msg, msg_len, NULL, sinfo); if (err < 0) goto out_unlock; iov_iter_revert(&msg->msg_iter, err); } goto out_unlock; } /* Get and check or create asoc */ if (daddr) { asoc = sctp_endpoint_lookup_assoc(ep, daddr, &transport); if (asoc) { err = sctp_sendmsg_check_sflags(asoc, sflags, msg, msg_len); if (err <= 0) goto out_unlock; } else { err = sctp_sendmsg_new_asoc(sk, sflags, &cmsgs, daddr, &transport); if (err) goto out_unlock; asoc = transport->asoc; new = true; } if (!sctp_style(sk, TCP) && !(sflags & SCTP_ADDR_OVER)) transport = NULL; } else { asoc = sctp_id2assoc(sk, sinfo->sinfo_assoc_id); if (!asoc) { err = -EPIPE; goto out_unlock; } err = sctp_sendmsg_check_sflags(asoc, sflags, msg, msg_len); if (err <= 0) goto out_unlock; } /* Update snd_info with the asoc */ sctp_sendmsg_update_sinfo(asoc, sinfo, &cmsgs); /* Send msg to the asoc */ err = sctp_sendmsg_to_asoc(asoc, msg, msg_len, transport, sinfo); if (err < 0 && err != -ESRCH && new) sctp_association_free(asoc); out_unlock: release_sock(sk); out: return sctp_error(sk, msg->msg_flags, err); } /* This is an extended version of skb_pull() that removes the data from the * start of a skb even when data is spread across the list of skb's in the * frag_list. len specifies the total amount of data that needs to be removed. * when 'len' bytes could be removed from the skb, it returns 0. * If 'len' exceeds the total skb length, it returns the no. of bytes that * could not be removed. */ static int sctp_skb_pull(struct sk_buff *skb, int len) { struct sk_buff *list; int skb_len = skb_headlen(skb); int rlen; if (len <= skb_len) { __skb_pull(skb, len); return 0; } len -= skb_len; __skb_pull(skb, skb_len); skb_walk_frags(skb, list) { rlen = sctp_skb_pull(list, len); skb->len -= (len-rlen); skb->data_len -= (len-rlen); if (!rlen) return 0; len = rlen; } return len; } /* API 3.1.3 recvmsg() - UDP Style Syntax * * ssize_t recvmsg(int socket, struct msghdr *message, * int flags); * * socket - the socket descriptor of the endpoint. * message - pointer to the msghdr structure which contains a single * user message and possibly some ancillary data. * * See Section 5 for complete description of the data * structures. * * flags - flags sent or received with the user message, see Section * 5 for complete description of the flags. */ static int sctp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { struct sctp_ulpevent *event = NULL; struct sctp_sock *sp = sctp_sk(sk); struct sk_buff *skb, *head_skb; int copied; int err = 0; int skb_len; pr_debug("%s: sk:%p, msghdr:%p, len:%zd, flags:0x%x, addr_len:%p)\n", __func__, sk, msg, len, flags, addr_len); if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue)) sk_busy_loop(sk, flags & MSG_DONTWAIT); lock_sock(sk); if (sctp_style(sk, TCP) && !sctp_sstate(sk, ESTABLISHED) && !sctp_sstate(sk, CLOSING) && !sctp_sstate(sk, CLOSED)) { err = -ENOTCONN; goto out; } skb = sctp_skb_recv_datagram(sk, flags, &err); if (!skb) goto out; /* Get the total length of the skb including any skb's in the * frag_list. */ skb_len = skb->len; copied = skb_len; if (copied > len) copied = len; err = skb_copy_datagram_msg(skb, 0, msg, copied); event = sctp_skb2event(skb); if (err) goto out_free; if (event->chunk && event->chunk->head_skb) head_skb = event->chunk->head_skb; else head_skb = skb; sock_recv_cmsgs(msg, sk, head_skb); if (sctp_ulpevent_is_notification(event)) { msg->msg_flags |= MSG_NOTIFICATION; sp->pf->event_msgname(event, msg->msg_name, addr_len); } else { sp->pf->skb_msgname(head_skb, msg->msg_name, addr_len); } /* Check if we allow SCTP_NXTINFO. */ if (sp->recvnxtinfo) sctp_ulpevent_read_nxtinfo(event, msg, sk); /* Check if we allow SCTP_RCVINFO. */ if (sp->recvrcvinfo) sctp_ulpevent_read_rcvinfo(event, msg); /* Check if we allow SCTP_SNDRCVINFO. */ if (sctp_ulpevent_type_enabled(sp->subscribe, SCTP_DATA_IO_EVENT)) sctp_ulpevent_read_sndrcvinfo(event, msg); err = copied; /* If skb's length exceeds the user's buffer, update the skb and * push it back to the receive_queue so that the next call to * recvmsg() will return the remaining data. Don't set MSG_EOR. */ if (skb_len > copied) { msg->msg_flags &= ~MSG_EOR; if (flags & MSG_PEEK) goto out_free; sctp_skb_pull(skb, copied); skb_queue_head(&sk->sk_receive_queue, skb); /* When only partial message is copied to the user, increase * rwnd by that amount. If all the data in the skb is read, * rwnd is updated when the event is freed. */ if (!sctp_ulpevent_is_notification(event)) sctp_assoc_rwnd_increase(event->asoc, copied); goto out; } else if ((event->msg_flags & MSG_NOTIFICATION) || (event->msg_flags & MSG_EOR)) msg->msg_flags |= MSG_EOR; else msg->msg_flags &= ~MSG_EOR; out_free: if (flags & MSG_PEEK) { /* Release the skb reference acquired after peeking the skb in * sctp_skb_recv_datagram(). */ kfree_skb(skb); } else { /* Free the event which includes releasing the reference to * the owner of the skb, freeing the skb and updating the * rwnd. */ sctp_ulpevent_free(event); } out: release_sock(sk); return err; } /* 7.1.12 Enable/Disable message fragmentation (SCTP_DISABLE_FRAGMENTS) * * This option is a on/off flag. If enabled no SCTP message * fragmentation will be performed. Instead if a message being sent * exceeds the current PMTU size, the message will NOT be sent and * instead a error will be indicated to the user. */ static int sctp_setsockopt_disable_fragments(struct sock *sk, int *val, unsigned int optlen) { if (optlen < sizeof(int)) return -EINVAL; sctp_sk(sk)->disable_fragments = (*val == 0) ? 0 : 1; return 0; } static int sctp_setsockopt_events(struct sock *sk, __u8 *sn_type, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; int i; if (optlen > sizeof(struct sctp_event_subscribe)) return -EINVAL; for (i = 0; i < optlen; i++) sctp_ulpevent_type_set(&sp->subscribe, SCTP_SN_TYPE_BASE + i, sn_type[i]); list_for_each_entry(asoc, &sp->ep->asocs, asocs) asoc->subscribe = sctp_sk(sk)->subscribe; /* At the time when a user app subscribes to SCTP_SENDER_DRY_EVENT, * if there is no data to be sent or retransmit, the stack will * immediately send up this notification. */ if (sctp_ulpevent_type_enabled(sp->subscribe, SCTP_SENDER_DRY_EVENT)) { struct sctp_ulpevent *event; aso |