| 106 11 17 4 4 4 81 1 1 1 80 17 15 15 16 16 97 98 16 14 12 14 86 4 14 11 11 14 1 1 98 97 84 16 14 19 19 11 6 1 6 6 1 5 5 5 1 5 106 105 105 91 106 19 83 105 56 45 106 33 77 77 58 50 40 20 20 20 20 105 61 60 86 82 86 5 5 5 82 82 86 81 33 82 34 34 81 81 86 82 37 81 37 37 82 82 106 104 104 11 105 5 5 5 5 3 3 5 5 4 2 2 3 3 3 4 4 4 4 4 4 4 4 4 4 4 4 4 3 4 2 2 1 2 4 4 4 3 3 3 3 3 3 3 3 3 2 3 3 3 29 4 29 5 4 3 3 3 3 3 3 3 1 1 1 1 2 2 2 2 3 3 2 2 3 99 56 105 1 106 41 106 25 106 106 106 41 106 25 106 105 105 105 5 5 5 5 5 5 5 2 3 3 99 11 11 11 11 11 99 2 4 4 4 4 4 4 4 106 1 58 106 55 1 45 45 1 103 106 106 2 106 106 106 103 106 106 104 105 2 106 105 106 106 106 102 102 103 103 103 6 6 6 106 38 7 7 7 7 7 7 7 7 106 106 106 106 3 106 1 1 1 1 1 104 106 89 86 6 89 82 88 82 89 58 106 36 106 3 4 4 106 149 100 1 148 53 53 1 105 80 101 10 10 99 88 43 42 44 38 43 10 11 11 11 1 11 98 99 98 35 99 25 21 21 21 20 21 21 25 22 4 22 25 82 99 81 81 77 38 37 7 7 7 7 7 38 29 38 60 54 25 6 5 6 5 22 60 99 99 7 2 2 99 98 98 99 10 1 89 99 99 43 99 106 27 27 27 27 29 4 29 29 4 1 1 1 1 1 1 25 29 1 1 1 1 25 29 27 27 29 29 28 4 28 27 1 27 2 27 4 27 2 1 1 27 2 27 1 27 1 27 1 27 1 27 2 27 1 27 2 1 1 27 2 1 1 27 2 27 1 27 2 1 1 27 2 2 27 3 3 3 28 21 27 26 26 26 26 26 26 26 26 26 27 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 35 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 1 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* COMMON Applications Kept Enhanced (CAKE) discipline * * Copyright (C) 2014-2018 Jonathan Morton <chromatix99@gmail.com> * Copyright (C) 2015-2018 Toke Høiland-Jørgensen <toke@toke.dk> * Copyright (C) 2014-2018 Dave Täht <dave.taht@gmail.com> * Copyright (C) 2015-2018 Sebastian Moeller <moeller0@gmx.de> * (C) 2015-2018 Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk> * Copyright (C) 2017-2018 Ryan Mounce <ryan@mounce.com.au> * * The CAKE Principles: * (or, how to have your cake and eat it too) * * This is a combination of several shaping, AQM and FQ techniques into one * easy-to-use package: * * - An overall bandwidth shaper, to move the bottleneck away from dumb CPE * equipment and bloated MACs. This operates in deficit mode (as in sch_fq), * eliminating the need for any sort of burst parameter (eg. token bucket * depth). Burst support is limited to that necessary to overcome scheduling * latency. * * - A Diffserv-aware priority queue, giving more priority to certain classes, * up to a specified fraction of bandwidth. Above that bandwidth threshold, * the priority is reduced to avoid starving other tins. * * - Each priority tin has a separate Flow Queue system, to isolate traffic * flows from each other. This prevents a burst on one flow from increasing * the delay to another. Flows are distributed to queues using a * set-associative hash function. * * - Each queue is actively managed by Cobalt, which is a combination of the * Codel and Blue AQM algorithms. This serves flows fairly, and signals * congestion early via ECN (if available) and/or packet drops, to keep * latency low. The codel parameters are auto-tuned based on the bandwidth * setting, as is necessary at low bandwidths. * * The configuration parameters are kept deliberately simple for ease of use. * Everything has sane defaults. Complete generality of configuration is *not* * a goal. * * The priority queue operates according to a weighted DRR scheme, combined with * a bandwidth tracker which reuses the shaper logic to detect which side of the * bandwidth sharing threshold the tin is operating. This determines whether a * priority-based weight (high) or a bandwidth-based weight (low) is used for * that tin in the current pass. * * This qdisc was inspired by Eric Dumazet's fq_codel code, which he kindly * granted us permission to leverage. */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/jhash.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/reciprocal_div.h> #include <net/netlink.h> #include <linux/if_vlan.h> #include <net/gso.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/tcp.h> #include <net/flow_dissector.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack_core.h> #endif #define CAKE_SET_WAYS (8) #define CAKE_MAX_TINS (8) #define CAKE_QUEUES (1024) #define CAKE_FLOW_MASK 63 #define CAKE_FLOW_NAT_FLAG 64 /* struct cobalt_params - contains codel and blue parameters * @interval: codel initial drop rate * @target: maximum persistent sojourn time & blue update rate * @mtu_time: serialisation delay of maximum-size packet * @p_inc: increment of blue drop probability (0.32 fxp) * @p_dec: decrement of blue drop probability (0.32 fxp) */ struct cobalt_params { u64 interval; u64 target; u64 mtu_time; u32 p_inc; u32 p_dec; }; /* struct cobalt_vars - contains codel and blue variables * @count: codel dropping frequency * @rec_inv_sqrt: reciprocal value of sqrt(count) >> 1 * @drop_next: time to drop next packet, or when we dropped last * @blue_timer: Blue time to next drop * @p_drop: BLUE drop probability (0.32 fxp) * @dropping: set if in dropping state * @ecn_marked: set if marked */ struct cobalt_vars { u32 count; u32 rec_inv_sqrt; ktime_t drop_next; ktime_t blue_timer; u32 p_drop; bool dropping; bool ecn_marked; }; enum { CAKE_SET_NONE = 0, CAKE_SET_SPARSE, CAKE_SET_SPARSE_WAIT, /* counted in SPARSE, actually in BULK */ CAKE_SET_BULK, CAKE_SET_DECAYING }; struct cake_flow { /* this stuff is all needed per-flow at dequeue time */ struct sk_buff *head; struct sk_buff *tail; struct list_head flowchain; s32 deficit; u32 dropped; struct cobalt_vars cvars; u16 srchost; /* index into cake_host table */ u16 dsthost; u8 set; }; /* please try to keep this structure <= 64 bytes */ struct cake_host { u32 srchost_tag; u32 dsthost_tag; u16 srchost_bulk_flow_count; u16 dsthost_bulk_flow_count; }; struct cake_heap_entry { u16 t:3, b:10; }; struct cake_tin_data { struct cake_flow flows[CAKE_QUEUES]; u32 backlogs[CAKE_QUEUES]; u32 tags[CAKE_QUEUES]; /* for set association */ u16 overflow_idx[CAKE_QUEUES]; struct cake_host hosts[CAKE_QUEUES]; /* for triple isolation */ u16 flow_quantum; struct cobalt_params cparams; u32 drop_overlimit; u16 bulk_flow_count; u16 sparse_flow_count; u16 decaying_flow_count; u16 unresponsive_flow_count; u32 max_skblen; struct list_head new_flows; struct list_head old_flows; struct list_head decaying_flows; /* time_next = time_this + ((len * rate_ns) >> rate_shft) */ ktime_t time_next_packet; u64 tin_rate_ns; u64 tin_rate_bps; u16 tin_rate_shft; u16 tin_quantum; s32 tin_deficit; u32 tin_backlog; u32 tin_dropped; u32 tin_ecn_mark; u32 packets; u64 bytes; u32 ack_drops; /* moving averages */ u64 avge_delay; u64 peak_delay; u64 base_delay; /* hash function stats */ u32 way_directs; u32 way_hits; u32 way_misses; u32 way_collisions; }; /* number of tins is small, so size of this struct doesn't matter much */ struct cake_sched_data { struct tcf_proto __rcu *filter_list; /* optional external classifier */ struct tcf_block *block; struct cake_tin_data *tins; struct cake_heap_entry overflow_heap[CAKE_QUEUES * CAKE_MAX_TINS]; u16 overflow_timeout; u16 tin_cnt; u8 tin_mode; u8 flow_mode; u8 ack_filter; u8 atm_mode; u32 fwmark_mask; u16 fwmark_shft; /* time_next = time_this + ((len * rate_ns) >> rate_shft) */ u16 rate_shft; ktime_t time_next_packet; ktime_t failsafe_next_packet; u64 rate_ns; u64 rate_bps; u16 rate_flags; s16 rate_overhead; u16 rate_mpu; u64 interval; u64 target; /* resource tracking */ u32 buffer_used; u32 buffer_max_used; u32 buffer_limit; u32 buffer_config_limit; /* indices for dequeue */ u16 cur_tin; u16 cur_flow; struct qdisc_watchdog watchdog; const u8 *tin_index; const u8 *tin_order; /* bandwidth capacity estimate */ ktime_t last_packet_time; ktime_t avg_window_begin; u64 avg_packet_interval; u64 avg_window_bytes; u64 avg_peak_bandwidth; ktime_t last_reconfig_time; /* packet length stats */ u32 avg_netoff; u16 max_netlen; u16 max_adjlen; u16 min_netlen; u16 min_adjlen; }; enum { CAKE_FLAG_OVERHEAD = BIT(0), CAKE_FLAG_AUTORATE_INGRESS = BIT(1), CAKE_FLAG_INGRESS = BIT(2), CAKE_FLAG_WASH = BIT(3), CAKE_FLAG_SPLIT_GSO = BIT(4) }; /* COBALT operates the Codel and BLUE algorithms in parallel, in order to * obtain the best features of each. Codel is excellent on flows which * respond to congestion signals in a TCP-like way. BLUE is more effective on * unresponsive flows. */ struct cobalt_skb_cb { ktime_t enqueue_time; u32 adjusted_len; }; static u64 us_to_ns(u64 us) { return us * NSEC_PER_USEC; } static struct cobalt_skb_cb *get_cobalt_cb(const struct sk_buff *skb) { qdisc_cb_private_validate(skb, sizeof(struct cobalt_skb_cb)); return (struct cobalt_skb_cb *)qdisc_skb_cb(skb)->data; } static ktime_t cobalt_get_enqueue_time(const struct sk_buff *skb) { return get_cobalt_cb(skb)->enqueue_time; } static void cobalt_set_enqueue_time(struct sk_buff *skb, ktime_t now) { get_cobalt_cb(skb)->enqueue_time = now; } static u16 quantum_div[CAKE_QUEUES + 1] = {0}; /* Diffserv lookup tables */ static const u8 precedence[] = { 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 5, 6, 6, 6, 6, 6, 6, 6, 6, 7, 7, 7, 7, 7, 7, 7, 7, }; static const u8 diffserv8[] = { 2, 0, 1, 2, 4, 2, 2, 2, 1, 2, 1, 2, 1, 2, 1, 2, 5, 2, 4, 2, 4, 2, 4, 2, 3, 2, 3, 2, 3, 2, 3, 2, 6, 2, 3, 2, 3, 2, 3, 2, 6, 2, 2, 2, 6, 2, 6, 2, 7, 2, 2, 2, 2, 2, 2, 2, 7, 2, 2, 2, 2, 2, 2, 2, }; static const u8 diffserv4[] = { 0, 1, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 2, 0, 3, 0, 2, 0, 2, 0, 2, 0, 3, 0, 0, 0, 3, 0, 3, 0, 3, 0, 0, 0, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, }; static const u8 diffserv3[] = { 0, 1, 0, 0, 2, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2, 0, 2, 0, 2, 0, 0, 0, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, }; static const u8 besteffort[] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, }; /* tin priority order for stats dumping */ static const u8 normal_order[] = {0, 1, 2, 3, 4, 5, 6, 7}; static const u8 bulk_order[] = {1, 0, 2, 3}; /* There is a big difference in timing between the accurate values placed in the * cache and the approximations given by a single Newton step for small count * values, particularly when stepping from count 1 to 2 or vice versa. Hence, * these values are calculated using eight Newton steps, using the * implementation below. Above 16, a single Newton step gives sufficient * accuracy in either direction, given the precision stored. * * The magnitude of the error when stepping up to count 2 is such as to give the * value that *should* have been produced at count 4. */ #define REC_INV_SQRT_CACHE (16) static const u32 inv_sqrt_cache[REC_INV_SQRT_CACHE] = { ~0, ~0, 3037000500, 2479700525, 2147483647, 1920767767, 1753413056, 1623345051, 1518500250, 1431655765, 1358187914, 1294981364, 1239850263, 1191209601, 1147878294, 1108955788 }; /* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2) * * Here, invsqrt is a fixed point number (< 1.0), 32bit mantissa, aka Q0.32 */ static void cobalt_newton_step(struct cobalt_vars *vars) { u32 invsqrt, invsqrt2; u64 val; invsqrt = vars->rec_inv_sqrt; invsqrt2 = ((u64)invsqrt * invsqrt) >> 32; val = (3LL << 32) - ((u64)vars->count * invsqrt2); val >>= 2; /* avoid overflow in following multiply */ val = (val * invsqrt) >> (32 - 2 + 1); vars->rec_inv_sqrt = val; } static void cobalt_invsqrt(struct cobalt_vars *vars) { if (vars->count < REC_INV_SQRT_CACHE) vars->rec_inv_sqrt = inv_sqrt_cache[vars->count]; else cobalt_newton_step(vars); } static void cobalt_vars_init(struct cobalt_vars *vars) { memset(vars, 0, sizeof(*vars)); } /* CoDel control_law is t + interval/sqrt(count) * We maintain in rec_inv_sqrt the reciprocal value of sqrt(count) to avoid * both sqrt() and divide operation. */ static ktime_t cobalt_control(ktime_t t, u64 interval, u32 rec_inv_sqrt) { return ktime_add_ns(t, reciprocal_scale(interval, rec_inv_sqrt)); } /* Call this when a packet had to be dropped due to queue overflow. Returns * true if the BLUE state was quiescent before but active after this call. */ static bool cobalt_queue_full(struct cobalt_vars *vars, struct cobalt_params *p, ktime_t now) { bool up = false; if (ktime_to_ns(ktime_sub(now, vars->blue_timer)) > p->target) { up = !vars->p_drop; vars->p_drop += p->p_inc; if (vars->p_drop < p->p_inc) vars->p_drop = ~0; vars->blue_timer = now; } vars->dropping = true; vars->drop_next = now; if (!vars->count) vars->count = 1; return up; } /* Call this when the queue was serviced but turned out to be empty. Returns * true if the BLUE state was active before but quiescent after this call. */ static bool cobalt_queue_empty(struct cobalt_vars *vars, struct cobalt_params *p, ktime_t now) { bool down = false; if (vars->p_drop && ktime_to_ns(ktime_sub(now, vars->blue_timer)) > p->target) { if (vars->p_drop < p->p_dec) vars->p_drop = 0; else vars->p_drop -= p->p_dec; vars->blue_timer = now; down = !vars->p_drop; } vars->dropping = false; if (vars->count && ktime_to_ns(ktime_sub(now, vars->drop_next)) >= 0) { vars->count--; cobalt_invsqrt(vars); vars->drop_next = cobalt_control(vars->drop_next, p->interval, vars->rec_inv_sqrt); } return down; } /* Call this with a freshly dequeued packet for possible congestion marking. * Returns true as an instruction to drop the packet, false for delivery. */ static bool cobalt_should_drop(struct cobalt_vars *vars, struct cobalt_params *p, ktime_t now, struct sk_buff *skb, u32 bulk_flows) { bool next_due, over_target, drop = false; ktime_t schedule; u64 sojourn; /* The 'schedule' variable records, in its sign, whether 'now' is before or * after 'drop_next'. This allows 'drop_next' to be updated before the next * scheduling decision is actually branched, without destroying that * information. Similarly, the first 'schedule' value calculated is preserved * in the boolean 'next_due'. * * As for 'drop_next', we take advantage of the fact that 'interval' is both * the delay between first exceeding 'target' and the first signalling event, * *and* the scaling factor for the signalling frequency. It's therefore very * natural to use a single mechanism for both purposes, and eliminates a * significant amount of reference Codel's spaghetti code. To help with this, * both the '0' and '1' entries in the invsqrt cache are 0xFFFFFFFF, as close * as possible to 1.0 in fixed-point. */ sojourn = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb))); schedule = ktime_sub(now, vars->drop_next); over_target = sojourn > p->target && sojourn > p->mtu_time * bulk_flows * 2 && sojourn > p->mtu_time * 4; next_due = vars->count && ktime_to_ns(schedule) >= 0; vars->ecn_marked = false; if (over_target) { if (!vars->dropping) { vars->dropping = true; vars->drop_next = cobalt_control(now, p->interval, vars->rec_inv_sqrt); } if (!vars->count) vars->count = 1; } else if (vars->dropping) { vars->dropping = false; } if (next_due && vars->dropping) { /* Use ECN mark if possible, otherwise drop */ drop = !(vars->ecn_marked = INET_ECN_set_ce(skb)); vars->count++; if (!vars->count) vars->count--; cobalt_invsqrt(vars); vars->drop_next = cobalt_control(vars->drop_next, p->interval, vars->rec_inv_sqrt); schedule = ktime_sub(now, vars->drop_next); } else { while (next_due) { vars->count--; cobalt_invsqrt(vars); vars->drop_next = cobalt_control(vars->drop_next, p->interval, vars->rec_inv_sqrt); schedule = ktime_sub(now, vars->drop_next); next_due = vars->count && ktime_to_ns(schedule) >= 0; } } /* Simple BLUE implementation. Lack of ECN is deliberate. */ if (vars->p_drop) drop |= (get_random_u32() < vars->p_drop); /* Overload the drop_next field as an activity timeout */ if (!vars->count) vars->drop_next = ktime_add_ns(now, p->interval); else if (ktime_to_ns(schedule) > 0 && !drop) vars->drop_next = now; return drop; } static bool cake_update_flowkeys(struct flow_keys *keys, const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) struct nf_conntrack_tuple tuple = {}; bool rev = !skb->_nfct, upd = false; __be32 ip; if (skb_protocol(skb, true) != htons(ETH_P_IP)) return false; if (!nf_ct_get_tuple_skb(&tuple, skb)) return false; ip = rev ? tuple.dst.u3.ip : tuple.src.u3.ip; if (ip != keys->addrs.v4addrs.src) { keys->addrs.v4addrs.src = ip; upd = true; } ip = rev ? tuple.src.u3.ip : tuple.dst.u3.ip; if (ip != keys->addrs.v4addrs.dst) { keys->addrs.v4addrs.dst = ip; upd = true; } if (keys->ports.ports) { __be16 port; port = rev ? tuple.dst.u.all : tuple.src.u.all; if (port != keys->ports.src) { keys->ports.src = port; upd = true; } port = rev ? tuple.src.u.all : tuple.dst.u.all; if (port != keys->ports.dst) { port = keys->ports.dst; upd = true; } } return upd; #else return false; #endif } /* Cake has several subtle multiple bit settings. In these cases you * would be matching triple isolate mode as well. */ static bool cake_dsrc(int flow_mode) { return (flow_mode & CAKE_FLOW_DUAL_SRC) == CAKE_FLOW_DUAL_SRC; } static bool cake_ddst(int flow_mode) { return (flow_mode & CAKE_FLOW_DUAL_DST) == CAKE_FLOW_DUAL_DST; } static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, int flow_mode, u16 flow_override, u16 host_override) { bool hash_flows = (!flow_override && !!(flow_mode & CAKE_FLOW_FLOWS)); bool hash_hosts = (!host_override && !!(flow_mode & CAKE_FLOW_HOSTS)); bool nat_enabled = !!(flow_mode & CAKE_FLOW_NAT_FLAG); u32 flow_hash = 0, srchost_hash = 0, dsthost_hash = 0; u16 reduced_hash, srchost_idx, dsthost_idx; struct flow_keys keys, host_keys; bool use_skbhash = skb->l4_hash; if (unlikely(flow_mode == CAKE_FLOW_NONE)) return 0; /* If both overrides are set, or we can use the SKB hash and nat mode is * disabled, we can skip packet dissection entirely. If nat mode is * enabled there's another check below after doing the conntrack lookup. */ if ((!hash_flows || (use_skbhash && !nat_enabled)) && !hash_hosts) goto skip_hash; skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); /* Don't use the SKB hash if we change the lookup keys from conntrack */ if (nat_enabled && cake_update_flowkeys(&keys, skb)) use_skbhash = false; /* If we can still use the SKB hash and don't need the host hash, we can * skip the rest of the hashing procedure */ if (use_skbhash && !hash_hosts) goto skip_hash; /* flow_hash_from_keys() sorts the addresses by value, so we have * to preserve their order in a separate data structure to treat * src and dst host addresses as independently selectable. */ host_keys = keys; host_keys.ports.ports = 0; host_keys.basic.ip_proto = 0; host_keys.keyid.keyid = 0; host_keys.tags.flow_label = 0; switch (host_keys.control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: host_keys.addrs.v4addrs.src = 0; dsthost_hash = flow_hash_from_keys(&host_keys); host_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; host_keys.addrs.v4addrs.dst = 0; srchost_hash = flow_hash_from_keys(&host_keys); break; case FLOW_DISSECTOR_KEY_IPV6_ADDRS: memset(&host_keys.addrs.v6addrs.src, 0, sizeof(host_keys.addrs.v6addrs.src)); dsthost_hash = flow_hash_from_keys(&host_keys); host_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; memset(&host_keys.addrs.v6addrs.dst, 0, sizeof(host_keys.addrs.v6addrs.dst)); srchost_hash = flow_hash_from_keys(&host_keys); break; default: dsthost_hash = 0; srchost_hash = 0; } /* This *must* be after the above switch, since as a * side-effect it sorts the src and dst addresses. */ if (hash_flows && !use_skbhash) flow_hash = flow_hash_from_keys(&keys); skip_hash: if (flow_override) flow_hash = flow_override - 1; else if (use_skbhash && (flow_mode & CAKE_FLOW_FLOWS)) flow_hash = skb->hash; if (host_override) { dsthost_hash = host_override - 1; srchost_hash = host_override - 1; } if (!(flow_mode & CAKE_FLOW_FLOWS)) { if (flow_mode & CAKE_FLOW_SRC_IP) flow_hash ^= srchost_hash; if (flow_mode & CAKE_FLOW_DST_IP) flow_hash ^= dsthost_hash; } reduced_hash = flow_hash % CAKE_QUEUES; /* set-associative hashing */ /* fast path if no hash collision (direct lookup succeeds) */ if (likely(q->tags[reduced_hash] == flow_hash && q->flows[reduced_hash].set)) { q->way_directs++; } else { u32 inner_hash = reduced_hash % CAKE_SET_WAYS; u32 outer_hash = reduced_hash - inner_hash; bool allocate_src = false; bool allocate_dst = false; u32 i, k; /* check if any active queue in the set is reserved for * this flow. */ for (i = 0, k = inner_hash; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (q->tags[outer_hash + k] == flow_hash) { if (i) q->way_hits++; if (!q->flows[outer_hash + k].set) { /* need to increment host refcnts */ allocate_src = cake_dsrc(flow_mode); allocate_dst = cake_ddst(flow_mode); } goto found; } } /* no queue is reserved for this flow, look for an * empty one. */ for (i = 0; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (!q->flows[outer_hash + k].set) { q->way_misses++; allocate_src = cake_dsrc(flow_mode); allocate_dst = cake_ddst(flow_mode); goto found; } } /* With no empty queues, default to the original * queue, accept the collision, update the host tags. */ q->way_collisions++; allocate_src = cake_dsrc(flow_mode); allocate_dst = cake_ddst(flow_mode); if (q->flows[outer_hash + k].set == CAKE_SET_BULK) { if (allocate_src) q->hosts[q->flows[reduced_hash].srchost].srchost_bulk_flow_count--; if (allocate_dst) q->hosts[q->flows[reduced_hash].dsthost].dsthost_bulk_flow_count--; } found: /* reserve queue for future packets in same flow */ reduced_hash = outer_hash + k; q->tags[reduced_hash] = flow_hash; if (allocate_src) { srchost_idx = srchost_hash % CAKE_QUEUES; inner_hash = srchost_idx % CAKE_SET_WAYS; outer_hash = srchost_idx - inner_hash; for (i = 0, k = inner_hash; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (q->hosts[outer_hash + k].srchost_tag == srchost_hash) goto found_src; } for (i = 0; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (!q->hosts[outer_hash + k].srchost_bulk_flow_count) break; } q->hosts[outer_hash + k].srchost_tag = srchost_hash; found_src: srchost_idx = outer_hash + k; if (q->flows[reduced_hash].set == CAKE_SET_BULK) q->hosts[srchost_idx].srchost_bulk_flow_count++; q->flows[reduced_hash].srchost = srchost_idx; } if (allocate_dst) { dsthost_idx = dsthost_hash % CAKE_QUEUES; inner_hash = dsthost_idx % CAKE_SET_WAYS; outer_hash = dsthost_idx - inner_hash; for (i = 0, k = inner_hash; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (q->hosts[outer_hash + k].dsthost_tag == dsthost_hash) goto found_dst; } for (i = 0; i < CAKE_SET_WAYS; i++, k = (k + 1) % CAKE_SET_WAYS) { if (!q->hosts[outer_hash + k].dsthost_bulk_flow_count) break; } q->hosts[outer_hash + k].dsthost_tag = dsthost_hash; found_dst: dsthost_idx = outer_hash + k; if (q->flows[reduced_hash].set == CAKE_SET_BULK) q->hosts[dsthost_idx].dsthost_bulk_flow_count++; q->flows[reduced_hash].dsthost = dsthost_idx; } } return reduced_hash; } /* helper functions : might be changed when/if skb use a standard list_head */ /* remove one skb from head of slot queue */ static struct sk_buff *dequeue_head(struct cake_flow *flow) { struct sk_buff *skb = flow->head; if (skb) { flow->head = skb->next; skb_mark_not_on_list(skb); } return skb; } /* add skb to flow queue (tail add) */ static void flow_queue_add(struct cake_flow *flow, struct sk_buff *skb) { if (!flow->head) flow->head = skb; else flow->tail->next = skb; flow->tail = skb; skb->next = NULL; } static struct iphdr *cake_get_iphdr(const struct sk_buff *skb, struct ipv6hdr *buf) { unsigned int offset = skb_network_offset(skb); struct iphdr *iph; iph = skb_header_pointer(skb, offset, sizeof(struct iphdr), buf); if (!iph) return NULL; if (iph->version == 4 && iph->protocol == IPPROTO_IPV6) return skb_header_pointer(skb, offset + iph->ihl * 4, sizeof(struct ipv6hdr), buf); else if (iph->version == 4) return iph; else if (iph->version == 6) return skb_header_pointer(skb, offset, sizeof(struct ipv6hdr), buf); return NULL; } static struct tcphdr *cake_get_tcphdr(const struct sk_buff *skb, void *buf, unsigned int bufsize) { unsigned int offset = skb_network_offset(skb); const struct ipv6hdr *ipv6h; const struct tcphdr *tcph; const struct iphdr *iph; struct ipv6hdr _ipv6h; struct tcphdr _tcph; ipv6h = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); if (!ipv6h) return NULL; if (ipv6h->version == 4) { iph = (struct iphdr *)ipv6h; offset += iph->ihl * 4; /* special-case 6in4 tunnelling, as that is a common way to get * v6 connectivity in the home */ if (iph->protocol == IPPROTO_IPV6) { ipv6h = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h); if (!ipv6h || ipv6h->nexthdr != IPPROTO_TCP) return NULL; offset += sizeof(struct ipv6hdr); } else if (iph->protocol != IPPROTO_TCP) { return NULL; } } else if (ipv6h->version == 6) { if (ipv6h->nexthdr != IPPROTO_TCP) return NULL; offset += sizeof(struct ipv6hdr); } else { return NULL; } tcph = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (!tcph || tcph->doff < 5) return NULL; return skb_header_pointer(skb, offset, min(__tcp_hdrlen(tcph), bufsize), buf); } static const void *cake_get_tcpopt(const struct tcphdr *tcph, int code, int *oplen) { /* inspired by tcp_parse_options in tcp_input.c */ int length = __tcp_hdrlen(tcph) - sizeof(struct tcphdr); const u8 *ptr = (const u8 *)(tcph + 1); while (length > 0) { int opcode = *ptr++; int opsize; if (opcode == TCPOPT_EOL) break; if (opcode == TCPOPT_NOP) { length--; continue; } if (length < 2) break; opsize = *ptr++; if (opsize < 2 || opsize > length) break; if (opcode == code) { *oplen = opsize; return ptr; } ptr += opsize - 2; length -= opsize; } return NULL; } /* Compare two SACK sequences. A sequence is considered greater if it SACKs more * bytes than the other. In the case where both sequences ACKs bytes that the * other doesn't, A is considered greater. DSACKs in A also makes A be * considered greater. * * @return -1, 0 or 1 as normal compare functions */ static int cake_tcph_sack_compare(const struct tcphdr *tcph_a, const struct tcphdr *tcph_b) { const struct tcp_sack_block_wire *sack_a, *sack_b; u32 ack_seq_a = ntohl(tcph_a->ack_seq); u32 bytes_a = 0, bytes_b = 0; int oplen_a, oplen_b; bool first = true; sack_a = cake_get_tcpopt(tcph_a, TCPOPT_SACK, &oplen_a); sack_b = cake_get_tcpopt(tcph_b, TCPOPT_SACK, &oplen_b); /* pointers point to option contents */ oplen_a -= TCPOLEN_SACK_BASE; oplen_b -= TCPOLEN_SACK_BASE; if (sack_a && oplen_a >= sizeof(*sack_a) && (!sack_b || oplen_b < sizeof(*sack_b))) return -1; else if (sack_b && oplen_b >= sizeof(*sack_b) && (!sack_a || oplen_a < sizeof(*sack_a))) return 1; else if ((!sack_a || oplen_a < sizeof(*sack_a)) && (!sack_b || oplen_b < sizeof(*sack_b))) return 0; while (oplen_a >= sizeof(*sack_a)) { const struct tcp_sack_block_wire *sack_tmp = sack_b; u32 start_a = get_unaligned_be32(&sack_a->start_seq); u32 end_a = get_unaligned_be32(&sack_a->end_seq); int oplen_tmp = oplen_b; bool found = false; /* DSACK; always considered greater to prevent dropping */ if (before(start_a, ack_seq_a)) return -1; bytes_a += end_a - start_a; while (oplen_tmp >= sizeof(*sack_tmp)) { u32 start_b = get_unaligned_be32(&sack_tmp->start_seq); u32 end_b = get_unaligned_be32(&sack_tmp->end_seq); /* first time through we count the total size */ if (first) bytes_b += end_b - start_b; if (!after(start_b, start_a) && !before(end_b, end_a)) { found = true; if (!first) break; } oplen_tmp -= sizeof(*sack_tmp); sack_tmp++; } if (!found) return -1; oplen_a -= sizeof(*sack_a); sack_a++; first = false; } /* If we made it this far, all ranges SACKed by A are covered by B, so * either the SACKs are equal, or B SACKs more bytes. */ return bytes_b > bytes_a ? 1 : 0; } static void cake_tcph_get_tstamp(const struct tcphdr *tcph, u32 *tsval, u32 *tsecr) { const u8 *ptr; int opsize; ptr = cake_get_tcpopt(tcph, TCPOPT_TIMESTAMP, &opsize); if (ptr && opsize == TCPOLEN_TIMESTAMP) { *tsval = get_unaligned_be32(ptr); *tsecr = get_unaligned_be32(ptr + 4); } } static bool cake_tcph_may_drop(const struct tcphdr *tcph, u32 tstamp_new, u32 tsecr_new) { /* inspired by tcp_parse_options in tcp_input.c */ int length = __tcp_hdrlen(tcph) - sizeof(struct tcphdr); const u8 *ptr = (const u8 *)(tcph + 1); u32 tstamp, tsecr; /* 3 reserved flags must be unset to avoid future breakage * ACK must be set * ECE/CWR are handled separately * All other flags URG/PSH/RST/SYN/FIN must be unset * 0x0FFF0000 = all TCP flags (confirm ACK=1, others zero) * 0x00C00000 = CWR/ECE (handled separately) * 0x0F3F0000 = 0x0FFF0000 & ~0x00C00000 */ if (((tcp_flag_word(tcph) & cpu_to_be32(0x0F3F0000)) != TCP_FLAG_ACK)) return false; while (length > 0) { int opcode = *ptr++; int opsize; if (opcode == TCPOPT_EOL) break; if (opcode == TCPOPT_NOP) { length--; continue; } if (length < 2) break; opsize = *ptr++; if (opsize < 2 || opsize > length) break; switch (opcode) { case TCPOPT_MD5SIG: /* doesn't influence state */ break; case TCPOPT_SACK: /* stricter checking performed later */ if (opsize % 8 != 2) return false; break; case TCPOPT_TIMESTAMP: /* only drop timestamps lower than new */ if (opsize != TCPOLEN_TIMESTAMP) return false; tstamp = get_unaligned_be32(ptr); tsecr = get_unaligned_be32(ptr + 4); if (after(tstamp, tstamp_new) || after(tsecr, tsecr_new)) return false; break; case TCPOPT_MSS: /* these should only be set on SYN */ case TCPOPT_WINDOW: case TCPOPT_SACK_PERM: case TCPOPT_FASTOPEN: case TCPOPT_EXP: default: /* don't drop if any unknown options are present */ return false; } ptr += opsize - 2; length -= opsize; } return true; } static struct sk_buff *cake_ack_filter(struct cake_sched_data *q, struct cake_flow *flow) { bool aggressive = q->ack_filter == CAKE_ACK_AGGRESSIVE; struct sk_buff *elig_ack = NULL, *elig_ack_prev = NULL; struct sk_buff *skb_check, *skb_prev = NULL; const struct ipv6hdr *ipv6h, *ipv6h_check; unsigned char _tcph[64], _tcph_check[64]; const struct tcphdr *tcph, *tcph_check; const struct iphdr *iph, *iph_check; struct ipv6hdr _iph, _iph_check; const struct sk_buff *skb; int seglen, num_found = 0; u32 tstamp = 0, tsecr = 0; __be32 elig_flags = 0; int sack_comp; /* no other possible ACKs to filter */ if (flow->head == flow->tail) return NULL; skb = flow->tail; tcph = cake_get_tcphdr(skb, _tcph, sizeof(_tcph)); iph = cake_get_iphdr(skb, &_iph); if (!tcph) return NULL; cake_tcph_get_tstamp(tcph, &tstamp, &tsecr); /* the 'triggering' packet need only have the ACK flag set. * also check that SYN is not set, as there won't be any previous ACKs. */ if ((tcp_flag_word(tcph) & (TCP_FLAG_ACK | TCP_FLAG_SYN)) != TCP_FLAG_ACK) return NULL; /* the 'triggering' ACK is at the tail of the queue, we have already * returned if it is the only packet in the flow. loop through the rest * of the queue looking for pure ACKs with the same 5-tuple as the * triggering one. */ for (skb_check = flow->head; skb_check && skb_check != skb; skb_prev = skb_check, skb_check = skb_check->next) { iph_check = cake_get_iphdr(skb_check, &_iph_check); tcph_check = cake_get_tcphdr(skb_check, &_tcph_check, sizeof(_tcph_check)); /* only TCP packets with matching 5-tuple are eligible, and only * drop safe headers */ if (!tcph_check || iph->version != iph_check->version || tcph_check->source != tcph->source || tcph_check->dest != tcph->dest) continue; if (iph_check->version == 4) { if (iph_check->saddr != iph->saddr || iph_check->daddr != iph->daddr) continue; seglen = iph_totlen(skb, iph_check) - (4 * iph_check->ihl); } else if (iph_check->version == 6) { ipv6h = (struct ipv6hdr *)iph; ipv6h_check = (struct ipv6hdr *)iph_check; if (ipv6_addr_cmp(&ipv6h_check->saddr, &ipv6h->saddr) || ipv6_addr_cmp(&ipv6h_check->daddr, &ipv6h->daddr)) continue; seglen = ntohs(ipv6h_check->payload_len); } else { WARN_ON(1); /* shouldn't happen */ continue; } /* If the ECE/CWR flags changed from the previous eligible * packet in the same flow, we should no longer be dropping that * previous packet as this would lose information. */ if (elig_ack && (tcp_flag_word(tcph_check) & (TCP_FLAG_ECE | TCP_FLAG_CWR)) != elig_flags) { elig_ack = NULL; elig_ack_prev = NULL; num_found--; } /* Check TCP options and flags, don't drop ACKs with segment * data, and don't drop ACKs with a higher cumulative ACK * counter than the triggering packet. Check ACK seqno here to * avoid parsing SACK options of packets we are going to exclude * anyway. */ if (!cake_tcph_may_drop(tcph_check, tstamp, tsecr) || (seglen - __tcp_hdrlen(tcph_check)) != 0 || after(ntohl(tcph_check->ack_seq), ntohl(tcph->ack_seq))) continue; /* Check SACK options. The triggering packet must SACK more data * than the ACK under consideration, or SACK the same range but * have a larger cumulative ACK counter. The latter is a * pathological case, but is contained in the following check * anyway, just to be safe. */ sack_comp = cake_tcph_sack_compare(tcph_check, tcph); if (sack_comp < 0 || (ntohl(tcph_check->ack_seq) == ntohl(tcph->ack_seq) && sack_comp == 0)) continue; /* At this point we have found an eligible pure ACK to drop; if * we are in aggressive mode, we are done. Otherwise, keep * searching unless this is the second eligible ACK we * found. * * Since we want to drop ACK closest to the head of the queue, * save the first eligible ACK we find, even if we need to loop * again. */ if (!elig_ack) { elig_ack = skb_check; elig_ack_prev = skb_prev; elig_flags = (tcp_flag_word(tcph_check) & (TCP_FLAG_ECE | TCP_FLAG_CWR)); } if (num_found++ > 0) goto found; } /* We made it through the queue without finding two eligible ACKs . If * we found a single eligible ACK we can drop it in aggressive mode if * we can guarantee that this does not interfere with ECN flag * information. We ensure this by dropping it only if the enqueued * packet is consecutive with the eligible ACK, and their flags match. */ if (elig_ack && aggressive && elig_ack->next == skb && (elig_flags == (tcp_flag_word(tcph) & (TCP_FLAG_ECE | TCP_FLAG_CWR)))) goto found; return NULL; found: if (elig_ack_prev) elig_ack_prev->next = elig_ack->next; else flow->head = elig_ack->next; skb_mark_not_on_list(elig_ack); return elig_ack; } static u64 cake_ewma(u64 avg, u64 sample, u32 shift) { avg -= avg >> shift; avg += sample >> shift; return avg; } static u32 cake_calc_overhead(struct cake_sched_data *q, u32 len, u32 off) { if (q->rate_flags & CAKE_FLAG_OVERHEAD) len -= off; if (q->max_netlen < len) q->max_netlen = len; if (q->min_netlen > len) q->min_netlen = len; len += q->rate_overhead; if (len < q->rate_mpu) len = q->rate_mpu; if (q->atm_mode == CAKE_ATM_ATM) { len += 47; len /= 48; len *= 53; } else if (q->atm_mode == CAKE_ATM_PTM) { /* Add one byte per 64 bytes or part thereof. * This is conservative and easier to calculate than the * precise value. */ len += (len + 63) / 64; } if (q->max_adjlen < len) q->max_adjlen = len; if (q->min_adjlen > len) q->min_adjlen = len; return len; } static u32 cake_overhead(struct cake_sched_data *q, const struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); unsigned int hdr_len, last_len = 0; u32 off = skb_network_offset(skb); u32 len = qdisc_pkt_len(skb); u16 segs = 1; q->avg_netoff = cake_ewma(q->avg_netoff, off << 16, 8); if (!shinfo->gso_size) return cake_calc_overhead(q, len, off); /* borrowed from qdisc_pkt_len_init() */ hdr_len = skb_transport_offset(skb); /* + transport layer */ if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { const struct tcphdr *th; struct tcphdr _tcphdr; th = skb_header_pointer(skb, hdr_len, sizeof(_tcphdr), &_tcphdr); if (likely(th)) hdr_len += __tcp_hdrlen(th); } else { struct udphdr _udphdr; if (skb_header_pointer(skb, hdr_len, sizeof(_udphdr), &_udphdr)) hdr_len += sizeof(struct udphdr); } if (unlikely(shinfo->gso_type & SKB_GSO_DODGY)) segs = DIV_ROUND_UP(skb->len - hdr_len, shinfo->gso_size); else segs = shinfo->gso_segs; len = shinfo->gso_size + hdr_len; last_len = skb->len - shinfo->gso_size * (segs - 1); return (cake_calc_overhead(q, len, off) * (segs - 1) + cake_calc_overhead(q, last_len, off)); } static void cake_heap_swap(struct cake_sched_data *q, u16 i, u16 j) { struct cake_heap_entry ii = q->overflow_heap[i]; struct cake_heap_entry jj = q->overflow_heap[j]; q->overflow_heap[i] = jj; q->overflow_heap[j] = ii; q->tins[ii.t].overflow_idx[ii.b] = j; q->tins[jj.t].overflow_idx[jj.b] = i; } static u32 cake_heap_get_backlog(const struct cake_sched_data *q, u16 i) { struct cake_heap_entry ii = q->overflow_heap[i]; return q->tins[ii.t].backlogs[ii.b]; } static void cake_heapify(struct cake_sched_data *q, u16 i) { static const u32 a = CAKE_MAX_TINS * CAKE_QUEUES; u32 mb = cake_heap_get_backlog(q, i); u32 m = i; while (m < a) { u32 l = m + m + 1; u32 r = l + 1; if (l < a) { u32 lb = cake_heap_get_backlog(q, l); if (lb > mb) { m = l; mb = lb; } } if (r < a) { u32 rb = cake_heap_get_backlog(q, r); if (rb > mb) { m = r; mb = rb; } } if (m != i) { cake_heap_swap(q, i, m); i = m; } else { break; } } } static void cake_heapify_up(struct cake_sched_data *q, u16 i) { while (i > 0 && i < CAKE_MAX_TINS * CAKE_QUEUES) { u16 p = (i - 1) >> 1; u32 ib = cake_heap_get_backlog(q, i); u32 pb = cake_heap_get_backlog(q, p); if (ib > pb) { cake_heap_swap(q, i, p); i = p; } else { break; } } } static int cake_advance_shaper(struct cake_sched_data *q, struct cake_tin_data *b, struct sk_buff *skb, ktime_t now, bool drop) { u32 len = get_cobalt_cb(skb)->adjusted_len; /* charge packet bandwidth to this tin * and to the global shaper. */ if (q->rate_ns) { u64 tin_dur = (len * b->tin_rate_ns) >> b->tin_rate_shft; u64 global_dur = (len * q->rate_ns) >> q->rate_shft; u64 failsafe_dur = global_dur + (global_dur >> 1); if (ktime_before(b->time_next_packet, now)) b->time_next_packet = ktime_add_ns(b->time_next_packet, tin_dur); else if (ktime_before(b->time_next_packet, ktime_add_ns(now, tin_dur))) b->time_next_packet = ktime_add_ns(now, tin_dur); q->time_next_packet = ktime_add_ns(q->time_next_packet, global_dur); if (!drop) q->failsafe_next_packet = \ ktime_add_ns(q->failsafe_next_packet, failsafe_dur); } return len; } static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) { struct cake_sched_data *q = qdisc_priv(sch); ktime_t now = ktime_get(); u32 idx = 0, tin = 0, len; struct cake_heap_entry qq; struct cake_tin_data *b; struct cake_flow *flow; struct sk_buff *skb; if (!q->overflow_timeout) { int i; /* Build fresh max-heap */ for (i = CAKE_MAX_TINS * CAKE_QUEUES / 2 - 1; i >= 0; i--) cake_heapify(q, i); } q->overflow_timeout = 65535; /* select longest queue for pruning */ qq = q->overflow_heap[0]; tin = qq.t; idx = qq.b; b = &q->tins[tin]; flow = &b->flows[idx]; skb = dequeue_head(flow); if (unlikely(!skb)) { /* heap has gone wrong, rebuild it next time */ q->overflow_timeout = 0; return idx + (tin << 16); } if (cobalt_queue_full(&flow->cvars, &b->cparams, now)) b->unresponsive_flow_count++; len = qdisc_pkt_len(skb); q->buffer_used -= skb->truesize; b->backlogs[idx] -= len; b->tin_backlog -= len; sch->qstats.backlog -= len; flow->dropped++; b->tin_dropped++; sch->qstats.drops++; if (q->rate_flags & CAKE_FLAG_INGRESS) cake_advance_shaper(q, b, skb, now, true); __qdisc_drop(skb, to_free); sch->q.qlen--; qdisc_tree_reduce_backlog(sch, 1, len); cake_heapify(q, 0); return idx + (tin << 16); } static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash) { const int offset = skb_network_offset(skb); u16 *buf, buf_; u8 dscp; switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); if (unlikely(!buf)) return 0; /* ToS is in the second byte of iphdr */ dscp = ipv4_get_dsfield((struct iphdr *)buf) >> 2; if (wash && dscp) { const int wlen = offset + sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen) || skb_try_make_writable(skb, wlen)) return 0; ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0); } return dscp; case htons(ETH_P_IPV6): buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); if (unlikely(!buf)) return 0; /* Traffic class is in the first and second bytes of ipv6hdr */ dscp = ipv6_get_dsfield((struct ipv6hdr *)buf) >> 2; if (wash && dscp) { const int wlen = offset + sizeof(struct ipv6hdr); if (!pskb_may_pull(skb, wlen) || skb_try_make_writable(skb, wlen)) return 0; ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0); } return dscp; case htons(ETH_P_ARP): return 0x38; /* CS7 - Net Control */ default: /* If there is no Diffserv field, treat as best-effort */ return 0; } } static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, struct sk_buff *skb) { struct cake_sched_data *q = qdisc_priv(sch); u32 tin, mark; bool wash; u8 dscp; /* Tin selection: Default to diffserv-based selection, allow overriding * using firewall marks or skb->priority. Call DSCP parsing early if * wash is enabled, otherwise defer to below to skip unneeded parsing. */ mark = (skb->mark & q->fwmark_mask) >> q->fwmark_shft; wash = !!(q->rate_flags & CAKE_FLAG_WASH); if (wash) dscp = cake_handle_diffserv(skb, wash); if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT) tin = 0; else if (mark && mark <= q->tin_cnt) tin = q->tin_order[mark - 1]; else if (TC_H_MAJ(skb->priority) == sch->handle && TC_H_MIN(skb->priority) > 0 && TC_H_MIN(skb->priority) <= q->tin_cnt) tin = q->tin_order[TC_H_MIN(skb->priority) - 1]; else { if (!wash) dscp = cake_handle_diffserv(skb, wash); tin = q->tin_index[dscp]; if (unlikely(tin >= q->tin_cnt)) tin = 0; } return &q->tins[tin]; } static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data **t, struct sk_buff *skb, int flow_mode, int *qerr) { struct cake_sched_data *q = qdisc_priv(sch); struct tcf_proto *filter; struct tcf_result res; u16 flow = 0, host = 0; int result; filter = rcu_dereference_bh(q->filter_list); if (!filter) goto hash; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; result = tcf_classify(skb, NULL, filter, &res, false); if (result >= 0) { #ifdef CONFIG_NET_CLS_ACT switch (result) { case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; fallthrough; case TC_ACT_SHOT: return 0; } #endif if (TC_H_MIN(res.classid) <= CAKE_QUEUES) flow = TC_H_MIN(res.classid); if (TC_H_MAJ(res.classid) <= (CAKE_QUEUES << 16)) host = TC_H_MAJ(res.classid) >> 16; } hash: *t = cake_select_tin(sch, skb); return cake_hash(*t, skb, flow_mode, flow, host) + 1; } static void cake_reconfigure(struct Qdisc *sch); static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct cake_sched_data *q = qdisc_priv(sch); int len = qdisc_pkt_len(skb); int ret; struct sk_buff *ack = NULL; ktime_t now = ktime_get(); struct cake_tin_data *b; struct cake_flow *flow; u32 idx; /* choose flow to insert into */ idx = cake_classify(sch, &b, skb, q->flow_mode, &ret); if (idx == 0) { if (ret & __NET_XMIT_BYPASS) qdisc_qstats_drop(sch); __qdisc_drop(skb, to_free); return ret; } idx--; flow = &b->flows[idx]; /* ensure shaper state isn't stale */ if (!b->tin_backlog) { if (ktime_before(b->time_next_packet, now)) b->time_next_packet = now; if (!sch->q.qlen) { if (ktime_before(q->time_next_packet, now)) { q->failsafe_next_packet = now; q->time_next_packet = now; } else if (ktime_after(q->time_next_packet, now) && ktime_after(q->failsafe_next_packet, now)) { u64 next = \ min(ktime_to_ns(q->time_next_packet), ktime_to_ns( q->failsafe_next_packet)); sch->qstats.overlimits++; qdisc_watchdog_schedule_ns(&q->watchdog, next); } } } if (unlikely(len > b->max_skblen)) b->max_skblen = len; if (skb_is_gso(skb) && q->rate_flags & CAKE_FLAG_SPLIT_GSO) { struct sk_buff *segs, *nskb; netdev_features_t features = netif_skb_features(skb); unsigned int slen = 0, numsegs = 0; segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) return qdisc_drop(skb, sch, to_free); skb_list_walk_safe(segs, segs, nskb) { skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; cobalt_set_enqueue_time(segs, now); get_cobalt_cb(segs)->adjusted_len = cake_overhead(q, segs); flow_queue_add(flow, segs); sch->q.qlen++; numsegs++; slen += segs->len; q->buffer_used += segs->truesize; b->packets++; } /* stats */ b->bytes += slen; b->backlogs[idx] += slen; b->tin_backlog += slen; sch->qstats.backlog += slen; q->avg_window_bytes += slen; qdisc_tree_reduce_backlog(sch, 1-numsegs, len-slen); consume_skb(skb); } else { /* not splitting */ cobalt_set_enqueue_time(skb, now); get_cobalt_cb(skb)->adjusted_len = cake_overhead(q, skb); flow_queue_add(flow, skb); if (q->ack_filter) ack = cake_ack_filter(q, flow); if (ack) { b->ack_drops++; sch->qstats.drops++; b->bytes += qdisc_pkt_len(ack); len -= qdisc_pkt_len(ack); q->buffer_used += skb->truesize - ack->truesize; if (q->rate_flags & CAKE_FLAG_INGRESS) cake_advance_shaper(q, b, ack, now, true); qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(ack)); consume_skb(ack); } else { sch->q.qlen++; q->buffer_used += skb->truesize; } /* stats */ b->packets++; b->bytes += len; b->backlogs[idx] += len; b->tin_backlog += len; sch->qstats.backlog += len; q->avg_window_bytes += len; } if (q->overflow_timeout) cake_heapify_up(q, b->overflow_idx[idx]); /* incoming bandwidth capacity estimate */ if (q->rate_flags & CAKE_FLAG_AUTORATE_INGRESS) { u64 packet_interval = \ ktime_to_ns(ktime_sub(now, q->last_packet_time)); if (packet_interval > NSEC_PER_SEC) packet_interval = NSEC_PER_SEC; /* filter out short-term bursts, eg. wifi aggregation */ q->avg_packet_interval = \ cake_ewma(q->avg_packet_interval, packet_interval, (packet_interval > q->avg_packet_interval ? 2 : 8)); q->last_packet_time = now; if (packet_interval > q->avg_packet_interval) { u64 window_interval = \ ktime_to_ns(ktime_sub(now, q->avg_window_begin)); u64 b = q->avg_window_bytes * (u64)NSEC_PER_SEC; b = div64_u64(b, window_interval); q->avg_peak_bandwidth = cake_ewma(q->avg_peak_bandwidth, b, b > q->avg_peak_bandwidth ? 2 : 8); q->avg_window_bytes = 0; q->avg_window_begin = now; if (ktime_after(now, ktime_add_ms(q->last_reconfig_time, 250))) { q->rate_bps = (q->avg_peak_bandwidth * 15) >> 4; cake_reconfigure(sch); } } } else { q->avg_window_bytes = 0; q->last_packet_time = now; } /* flowchain */ if (!flow->set || flow->set == CAKE_SET_DECAYING) { struct cake_host *srchost = &b->hosts[flow->srchost]; struct cake_host *dsthost = &b->hosts[flow->dsthost]; u16 host_load = 1; if (!flow->set) { list_add_tail(&flow->flowchain, &b->new_flows); } else { b->decaying_flow_count--; list_move_tail(&flow->flowchain, &b->new_flows); } flow->set = CAKE_SET_SPARSE; b->sparse_flow_count++; if (cake_dsrc(q->flow_mode)) host_load = max(host_load, srchost->srchost_bulk_flow_count); if (cake_ddst(q->flow_mode)) host_load = max(host_load, dsthost->dsthost_bulk_flow_count); flow->deficit = (b->flow_quantum * quantum_div[host_load]) >> 16; } else if (flow->set == CAKE_SET_SPARSE_WAIT) { struct cake_host *srchost = &b->hosts[flow->srchost]; struct cake_host *dsthost = &b->hosts[flow->dsthost]; /* this flow was empty, accounted as a sparse flow, but actually * in the bulk rotation. */ flow->set = CAKE_SET_BULK; b->sparse_flow_count--; b->bulk_flow_count++; if (cake_dsrc(q->flow_mode)) srchost->srchost_bulk_flow_count++; if (cake_ddst(q->flow_mode)) dsthost->dsthost_bulk_flow_count++; } if (q->buffer_used > q->buffer_max_used) q->buffer_max_used = q->buffer_used; if (q->buffer_used > q->buffer_limit) { u32 dropped = 0; while (q->buffer_used > q->buffer_limit) { dropped++; cake_drop(sch, to_free); } b->drop_overlimit += dropped; } return NET_XMIT_SUCCESS; } static struct sk_buff *cake_dequeue_one(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); struct cake_tin_data *b = &q->tins[q->cur_tin]; struct cake_flow *flow = &b->flows[q->cur_flow]; struct sk_buff *skb = NULL; u32 len; if (flow->head) { skb = dequeue_head(flow); len = qdisc_pkt_len(skb); b->backlogs[q->cur_flow] -= len; b->tin_backlog -= len; sch->qstats.backlog -= len; q->buffer_used -= skb->truesize; sch->q.qlen--; if (q->overflow_timeout) cake_heapify(q, b->overflow_idx[q->cur_flow]); } return skb; } /* Discard leftover packets from a tin no longer in use. */ static void cake_clear_tin(struct Qdisc *sch, u16 tin) { struct cake_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; q->cur_tin = tin; for (q->cur_flow = 0; q->cur_flow < CAKE_QUEUES; q->cur_flow++) while (!!(skb = cake_dequeue_one(sch))) kfree_skb(skb); } static struct sk_buff *cake_dequeue(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); struct cake_tin_data *b = &q->tins[q->cur_tin]; struct cake_host *srchost, *dsthost; ktime_t now = ktime_get(); struct cake_flow *flow; struct list_head *head; bool first_flow = true; struct sk_buff *skb; u16 host_load; u64 delay; u32 len; begin: if (!sch->q.qlen) return NULL; /* global hard shaper */ if (ktime_after(q->time_next_packet, now) && ktime_after(q->failsafe_next_packet, now)) { u64 next = min(ktime_to_ns(q->time_next_packet), ktime_to_ns(q->failsafe_next_packet)); sch->qstats.overlimits++; qdisc_watchdog_schedule_ns(&q->watchdog, next); return NULL; } /* Choose a class to work on. */ if (!q->rate_ns) { /* In unlimited mode, can't rely on shaper timings, just balance * with DRR */ bool wrapped = false, empty = true; while (b->tin_deficit < 0 || !(b->sparse_flow_count + b->bulk_flow_count)) { if (b->tin_deficit <= 0) b->tin_deficit += b->tin_quantum; if (b->sparse_flow_count + b->bulk_flow_count) empty = false; q->cur_tin++; b++; if (q->cur_tin >= q->tin_cnt) { q->cur_tin = 0; b = q->tins; if (wrapped) { /* It's possible for q->qlen to be * nonzero when we actually have no * packets anywhere. */ if (empty) return NULL; } else { wrapped = true; } } } } else { /* In shaped mode, choose: * - Highest-priority tin with queue and meeting schedule, or * - The earliest-scheduled tin with queue. */ ktime_t best_time = KTIME_MAX; int tin, best_tin = 0; for (tin = 0; tin < q->tin_cnt; tin++) { b = q->tins + tin; if ((b->sparse_flow_count + b->bulk_flow_count) > 0) { ktime_t time_to_pkt = \ ktime_sub(b->time_next_packet, now); if (ktime_to_ns(time_to_pkt) <= 0 || ktime_compare(time_to_pkt, best_time) <= 0) { best_time = time_to_pkt; best_tin = tin; } } } q->cur_tin = best_tin; b = q->tins + best_tin; /* No point in going further if no packets to deliver. */ if (unlikely(!(b->sparse_flow_count + b->bulk_flow_count))) return NULL; } retry: /* service this class */ head = &b->decaying_flows; if (!first_flow || list_empty(head)) { head = &b->new_flows; if (list_empty(head)) { head = &b->old_flows; if (unlikely(list_empty(head))) { head = &b->decaying_flows; if (unlikely(list_empty(head))) goto begin; } } } flow = list_first_entry(head, struct cake_flow, flowchain); q->cur_flow = flow - b->flows; first_flow = false; /* triple isolation (modified DRR++) */ srchost = &b->hosts[flow->srchost]; dsthost = &b->hosts[flow->dsthost]; host_load = 1; /* flow isolation (DRR++) */ if (flow->deficit <= 0) { /* Keep all flows with deficits out of the sparse and decaying * rotations. No non-empty flow can go into the decaying * rotation, so they can't get deficits */ if (flow->set == CAKE_SET_SPARSE) { if (flow->head) { b->sparse_flow_count--; b->bulk_flow_count++; if (cake_dsrc(q->flow_mode)) srchost->srchost_bulk_flow_count++; if (cake_ddst(q->flow_mode)) dsthost->dsthost_bulk_flow_count++; flow->set = CAKE_SET_BULK; } else { /* we've moved it to the bulk rotation for * correct deficit accounting but we still want * to count it as a sparse flow, not a bulk one. */ flow->set = CAKE_SET_SPARSE_WAIT; } } if (cake_dsrc(q->flow_mode)) host_load = max(host_load, srchost->srchost_bulk_flow_count); if (cake_ddst(q->flow_mode)) host_load = max(host_load, dsthost->dsthost_bulk_flow_count); WARN_ON(host_load > CAKE_QUEUES); /* The get_random_u16() is a way to apply dithering to avoid * accumulating roundoff errors */ flow->deficit += (b->flow_quantum * quantum_div[host_load] + get_random_u16()) >> 16; list_move_tail(&flow->flowchain, &b->old_flows); goto retry; } /* Retrieve a packet via the AQM */ while (1) { skb = cake_dequeue_one(sch); if (!skb) { /* this queue was actually empty */ if (cobalt_queue_empty(&flow->cvars, &b->cparams, now)) b->unresponsive_flow_count--; if (flow->cvars.p_drop || flow->cvars.count || ktime_before(now, flow->cvars.drop_next)) { /* keep in the flowchain until the state has * decayed to rest */ list_move_tail(&flow->flowchain, &b->decaying_flows); if (flow->set == CAKE_SET_BULK) { b->bulk_flow_count--; if (cake_dsrc(q->flow_mode)) srchost->srchost_bulk_flow_count--; if (cake_ddst(q->flow_mode)) dsthost->dsthost_bulk_flow_count--; b->decaying_flow_count++; } else if (flow->set == CAKE_SET_SPARSE || flow->set == CAKE_SET_SPARSE_WAIT) { b->sparse_flow_count--; b->decaying_flow_count++; } flow->set = CAKE_SET_DECAYING; } else { /* remove empty queue from the flowchain */ list_del_init(&flow->flowchain); if (flow->set == CAKE_SET_SPARSE || flow->set == CAKE_SET_SPARSE_WAIT) b->sparse_flow_count--; else if (flow->set == CAKE_SET_BULK) { b->bulk_flow_count--; if (cake_dsrc(q->flow_mode)) srchost->srchost_bulk_flow_count--; if (cake_ddst(q->flow_mode)) dsthost->dsthost_bulk_flow_count--; } else b->decaying_flow_count--; flow->set = CAKE_SET_NONE; } goto begin; } /* Last packet in queue may be marked, shouldn't be dropped */ if (!cobalt_should_drop(&flow->cvars, &b->cparams, now, skb, (b->bulk_flow_count * !!(q->rate_flags & CAKE_FLAG_INGRESS))) || !flow->head) break; /* drop this packet, get another one */ if (q->rate_flags & CAKE_FLAG_INGRESS) { len = cake_advance_shaper(q, b, skb, now, true); flow->deficit -= len; b->tin_deficit -= len; } flow->dropped++; b->tin_dropped++; qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb)); qdisc_qstats_drop(sch); kfree_skb(skb); if (q->rate_flags & CAKE_FLAG_INGRESS) goto retry; } b->tin_ecn_mark += !!flow->cvars.ecn_marked; qdisc_bstats_update(sch, skb); /* collect delay stats */ delay = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb))); b->avge_delay = cake_ewma(b->avge_delay, delay, 8); b->peak_delay = cake_ewma(b->peak_delay, delay, delay > b->peak_delay ? 2 : 8); b->base_delay = cake_ewma(b->base_delay, delay, delay < b->base_delay ? 2 : 8); len = cake_advance_shaper(q, b, skb, now, false); flow->deficit -= len; b->tin_deficit -= len; if (ktime_after(q->time_next_packet, now) && sch->q.qlen) { u64 next = min(ktime_to_ns(q->time_next_packet), ktime_to_ns(q->failsafe_next_packet)); qdisc_watchdog_schedule_ns(&q->watchdog, next); } else if (!sch->q.qlen) { int i; for (i = 0; i < q->tin_cnt; i++) { if (q->tins[i].decaying_flow_count) { ktime_t next = \ ktime_add_ns(now, q->tins[i].cparams.target); qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next)); break; } } } if (q->overflow_timeout) q->overflow_timeout--; return skb; } static void cake_reset(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); u32 c; if (!q->tins) return; for (c = 0; c < CAKE_MAX_TINS; c++) cake_clear_tin(sch, c); } static const struct nla_policy cake_policy[TCA_CAKE_MAX + 1] = { [TCA_CAKE_BASE_RATE64] = { .type = NLA_U64 }, [TCA_CAKE_DIFFSERV_MODE] = { .type = NLA_U32 }, [TCA_CAKE_ATM] = { .type = NLA_U32 }, [TCA_CAKE_FLOW_MODE] = { .type = NLA_U32 }, [TCA_CAKE_OVERHEAD] = { .type = NLA_S32 }, [TCA_CAKE_RTT] = { .type = NLA_U32 }, [TCA_CAKE_TARGET] = { .type = NLA_U32 }, [TCA_CAKE_AUTORATE] = { .type = NLA_U32 }, [TCA_CAKE_MEMORY] = { .type = NLA_U32 }, [TCA_CAKE_NAT] = { .type = NLA_U32 }, [TCA_CAKE_RAW] = { .type = NLA_U32 }, [TCA_CAKE_WASH] = { .type = NLA_U32 }, [TCA_CAKE_MPU] = { .type = NLA_U32 }, [TCA_CAKE_INGRESS] = { .type = NLA_U32 }, [TCA_CAKE_ACK_FILTER] = { .type = NLA_U32 }, [TCA_CAKE_SPLIT_GSO] = { .type = NLA_U32 }, [TCA_CAKE_FWMARK] = { .type = NLA_U32 }, }; static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, u64 target_ns, u64 rtt_est_ns) { /* convert byte-rate into time-per-byte * so it will always unwedge in reasonable time. */ static const u64 MIN_RATE = 64; u32 byte_target = mtu; u64 byte_target_ns; u8 rate_shft = 0; u64 rate_ns = 0; b->flow_quantum = 1514; if (rate) { b->flow_quantum = max(min(rate >> 12, 1514ULL), 300ULL); rate_shft = 34; rate_ns = ((u64)NSEC_PER_SEC) << rate_shft; rate_ns = div64_u64(rate_ns, max(MIN_RATE, rate)); while (!!(rate_ns >> 34)) { rate_ns >>= 1; rate_shft--; } } /* else unlimited, ie. zero delay */ b->tin_rate_bps = rate; b->tin_rate_ns = rate_ns; b->tin_rate_shft = rate_shft; byte_target_ns = (byte_target * rate_ns) >> rate_shft; b->cparams.target = max((byte_target_ns * 3) / 2, target_ns); b->cparams.interval = max(rtt_est_ns + b->cparams.target - target_ns, b->cparams.target * 2); b->cparams.mtu_time = byte_target_ns; b->cparams.p_inc = 1 << 24; /* 1/256 */ b->cparams.p_dec = 1 << 20; /* 1/4096 */ } static int cake_config_besteffort(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); struct cake_tin_data *b = &q->tins[0]; u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; q->tin_cnt = 1; q->tin_index = besteffort; q->tin_order = normal_order; cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); b->tin_quantum = 65535; return 0; } static int cake_config_precedence(struct Qdisc *sch) { /* convert high-level (user visible) parameters into internal format */ struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; u32 quantum = 256; u32 i; q->tin_cnt = 8; q->tin_index = precedence; q->tin_order = normal_order; for (i = 0; i < q->tin_cnt; i++) { struct cake_tin_data *b = &q->tins[i]; cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); b->tin_quantum = max_t(u16, 1U, quantum); /* calculate next class's parameters */ rate *= 7; rate >>= 3; quantum *= 7; quantum >>= 3; } return 0; } /* List of known Diffserv codepoints: * * Default Forwarding (DF/CS0) - Best Effort * Max Throughput (TOS2) * Min Delay (TOS4) * LLT "La" (TOS5) * Assured Forwarding 1 (AF1x) - x3 * Assured Forwarding 2 (AF2x) - x3 * Assured Forwarding 3 (AF3x) - x3 * Assured Forwarding 4 (AF4x) - x3 * Precedence Class 1 (CS1) * Precedence Class 2 (CS2) * Precedence Class 3 (CS3) * Precedence Class 4 (CS4) * Precedence Class 5 (CS5) * Precedence Class 6 (CS6) * Precedence Class 7 (CS7) * Voice Admit (VA) * Expedited Forwarding (EF) * Lower Effort (LE) * * Total 26 codepoints. */ /* List of traffic classes in RFC 4594, updated by RFC 8622: * (roughly descending order of contended priority) * (roughly ascending order of uncontended throughput) * * Network Control (CS6,CS7) - routing traffic * Telephony (EF,VA) - aka. VoIP streams * Signalling (CS5) - VoIP setup * Multimedia Conferencing (AF4x) - aka. video calls * Realtime Interactive (CS4) - eg. games * Multimedia Streaming (AF3x) - eg. YouTube, NetFlix, Twitch * Broadcast Video (CS3) * Low-Latency Data (AF2x,TOS4) - eg. database * Ops, Admin, Management (CS2) - eg. ssh * Standard Service (DF & unrecognised codepoints) * High-Throughput Data (AF1x,TOS2) - eg. web traffic * Low-Priority Data (LE,CS1) - eg. BitTorrent * * Total 12 traffic classes. */ static int cake_config_diffserv8(struct Qdisc *sch) { /* Pruned list of traffic classes for typical applications: * * Network Control (CS6, CS7) * Minimum Latency (EF, VA, CS5, CS4) * Interactive Shell (CS2) * Low Latency Transactions (AF2x, TOS4) * Video Streaming (AF4x, AF3x, CS3) * Bog Standard (DF etc.) * High Throughput (AF1x, TOS2, CS1) * Background Traffic (LE) * * Total 8 traffic classes. */ struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; u32 quantum = 256; u32 i; q->tin_cnt = 8; /* codepoint to class mapping */ q->tin_index = diffserv8; q->tin_order = normal_order; /* class characteristics */ for (i = 0; i < q->tin_cnt; i++) { struct cake_tin_data *b = &q->tins[i]; cake_set_rate(b, rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); b->tin_quantum = max_t(u16, 1U, quantum); /* calculate next class's parameters */ rate *= 7; rate >>= 3; quantum *= 7; quantum >>= 3; } return 0; } static int cake_config_diffserv4(struct Qdisc *sch) { /* Further pruned list of traffic classes for four-class system: * * Latency Sensitive (CS7, CS6, EF, VA, CS5, CS4) * Streaming Media (AF4x, AF3x, CS3, AF2x, TOS4, CS2) * Best Effort (DF, AF1x, TOS2, and those not specified) * Background Traffic (LE, CS1) * * Total 4 traffic classes. */ struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; u32 quantum = 1024; q->tin_cnt = 4; /* codepoint to class mapping */ q->tin_index = diffserv4; q->tin_order = bulk_order; /* class characteristics */ cake_set_rate(&q->tins[0], rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); cake_set_rate(&q->tins[1], rate >> 4, mtu, us_to_ns(q->target), us_to_ns(q->interval)); cake_set_rate(&q->tins[2], rate >> 1, mtu, us_to_ns(q->target), us_to_ns(q->interval)); cake_set_rate(&q->tins[3], rate >> 2, mtu, us_to_ns(q->target), us_to_ns(q->interval)); /* bandwidth-sharing weights */ q->tins[0].tin_quantum = quantum; q->tins[1].tin_quantum = quantum >> 4; q->tins[2].tin_quantum = quantum >> 1; q->tins[3].tin_quantum = quantum >> 2; return 0; } static int cake_config_diffserv3(struct Qdisc *sch) { /* Simplified Diffserv structure with 3 tins. * Latency Sensitive (CS7, CS6, EF, VA, TOS4) * Best Effort * Low Priority (LE, CS1) */ struct cake_sched_data *q = qdisc_priv(sch); u32 mtu = psched_mtu(qdisc_dev(sch)); u64 rate = q->rate_bps; u32 quantum = 1024; q->tin_cnt = 3; /* codepoint to class mapping */ q->tin_index = diffserv3; q->tin_order = bulk_order; /* class characteristics */ cake_set_rate(&q->tins[0], rate, mtu, us_to_ns(q->target), us_to_ns(q->interval)); cake_set_rate(&q->tins[1], rate >> 4, mtu, us_to_ns(q->target), us_to_ns(q->interval)); cake_set_rate(&q->tins[2], rate >> 2, mtu, us_to_ns(q->target), us_to_ns(q->interval)); /* bandwidth-sharing weights */ q->tins[0].tin_quantum = quantum; q->tins[1].tin_quantum = quantum >> 4; q->tins[2].tin_quantum = quantum >> 2; return 0; } static void cake_reconfigure(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); int c, ft; switch (q->tin_mode) { case CAKE_DIFFSERV_BESTEFFORT: ft = cake_config_besteffort(sch); break; case CAKE_DIFFSERV_PRECEDENCE: ft = cake_config_precedence(sch); break; case CAKE_DIFFSERV_DIFFSERV8: ft = cake_config_diffserv8(sch); break; case CAKE_DIFFSERV_DIFFSERV4: ft = cake_config_diffserv4(sch); break; case CAKE_DIFFSERV_DIFFSERV3: default: ft = cake_config_diffserv3(sch); break; } for (c = q->tin_cnt; c < CAKE_MAX_TINS; c++) { cake_clear_tin(sch, c); q->tins[c].cparams.mtu_time = q->tins[ft].cparams.mtu_time; } q->rate_ns = q->tins[ft].tin_rate_ns; q->rate_shft = q->tins[ft].tin_rate_shft; if (q->buffer_config_limit) { q->buffer_limit = q->buffer_config_limit; } else if (q->rate_bps) { u64 t = q->rate_bps * q->interval; do_div(t, USEC_PER_SEC / 4); q->buffer_limit = max_t(u32, t, 4U << 20); } else { q->buffer_limit = ~0; } sch->flags &= ~TCQ_F_CAN_BYPASS; q->buffer_limit = min(q->buffer_limit, max(sch->limit * psched_mtu(qdisc_dev(sch)), q->buffer_config_limit)); } static int cake_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct cake_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CAKE_MAX + 1]; u16 rate_flags; u8 flow_mode; int err; err = nla_parse_nested_deprecated(tb, TCA_CAKE_MAX, opt, cake_policy, extack); if (err < 0) return err; flow_mode = q->flow_mode; if (tb[TCA_CAKE_NAT]) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) flow_mode &= ~CAKE_FLOW_NAT_FLAG; flow_mode |= CAKE_FLOW_NAT_FLAG * !!nla_get_u32(tb[TCA_CAKE_NAT]); #else NL_SET_ERR_MSG_ATTR(extack, tb[TCA_CAKE_NAT], "No conntrack support in kernel"); return -EOPNOTSUPP; #endif } if (tb[TCA_CAKE_BASE_RATE64]) WRITE_ONCE(q->rate_bps, nla_get_u64(tb[TCA_CAKE_BASE_RATE64])); if (tb[TCA_CAKE_DIFFSERV_MODE]) WRITE_ONCE(q->tin_mode, nla_get_u32(tb[TCA_CAKE_DIFFSERV_MODE])); rate_flags = q->rate_flags; if (tb[TCA_CAKE_WASH]) { if (!!nla_get_u32(tb[TCA_CAKE_WASH])) rate_flags |= CAKE_FLAG_WASH; else rate_flags &= ~CAKE_FLAG_WASH; } if (tb[TCA_CAKE_FLOW_MODE]) flow_mode = ((flow_mode & CAKE_FLOW_NAT_FLAG) | (nla_get_u32(tb[TCA_CAKE_FLOW_MODE]) & CAKE_FLOW_MASK)); if (tb[TCA_CAKE_ATM]) WRITE_ONCE(q->atm_mode, nla_get_u32(tb[TCA_CAKE_ATM])); if (tb[TCA_CAKE_OVERHEAD]) { WRITE_ONCE(q->rate_overhead, nla_get_s32(tb[TCA_CAKE_OVERHEAD])); rate_flags |= CAKE_FLAG_OVERHEAD; q->max_netlen = 0; q->max_adjlen = 0; q->min_netlen = ~0; q->min_adjlen = ~0; } if (tb[TCA_CAKE_RAW]) { rate_flags &= ~CAKE_FLAG_OVERHEAD; q->max_netlen = 0; q->max_adjlen = 0; q->min_netlen = ~0; q->min_adjlen = ~0; } if (tb[TCA_CAKE_MPU]) WRITE_ONCE(q->rate_mpu, nla_get_u32(tb[TCA_CAKE_MPU])); if (tb[TCA_CAKE_RTT]) { u32 interval = nla_get_u32(tb[TCA_CAKE_RTT]); WRITE_ONCE(q->interval, max(interval, 1U)); } if (tb[TCA_CAKE_TARGET]) { u32 target = nla_get_u32(tb[TCA_CAKE_TARGET]); WRITE_ONCE(q->target, max(target, 1U)); } if (tb[TCA_CAKE_AUTORATE]) { if (!!nla_get_u32(tb[TCA_CAKE_AUTORATE])) rate_flags |= CAKE_FLAG_AUTORATE_INGRESS; else rate_flags &= ~CAKE_FLAG_AUTORATE_INGRESS; } if (tb[TCA_CAKE_INGRESS]) { if (!!nla_get_u32(tb[TCA_CAKE_INGRESS])) rate_flags |= CAKE_FLAG_INGRESS; else rate_flags &= ~CAKE_FLAG_INGRESS; } if (tb[TCA_CAKE_ACK_FILTER]) WRITE_ONCE(q->ack_filter, nla_get_u32(tb[TCA_CAKE_ACK_FILTER])); if (tb[TCA_CAKE_MEMORY]) WRITE_ONCE(q->buffer_config_limit, nla_get_u32(tb[TCA_CAKE_MEMORY])); if (tb[TCA_CAKE_SPLIT_GSO]) { if (!!nla_get_u32(tb[TCA_CAKE_SPLIT_GSO])) rate_flags |= CAKE_FLAG_SPLIT_GSO; else rate_flags &= ~CAKE_FLAG_SPLIT_GSO; } if (tb[TCA_CAKE_FWMARK]) { WRITE_ONCE(q->fwmark_mask, nla_get_u32(tb[TCA_CAKE_FWMARK])); WRITE_ONCE(q->fwmark_shft, q->fwmark_mask ? __ffs(q->fwmark_mask) : 0); } WRITE_ONCE(q->rate_flags, rate_flags); WRITE_ONCE(q->flow_mode, flow_mode); if (q->tins) { sch_tree_lock(sch); cake_reconfigure(sch); sch_tree_unlock(sch); } return 0; } static void cake_destroy(struct Qdisc *sch) { struct cake_sched_data *q = qdisc_priv(sch); qdisc_watchdog_cancel(&q->watchdog); tcf_block_put(q->block); kvfree(q->tins); } static int cake_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct cake_sched_data *q = qdisc_priv(sch); int i, j, err; sch->limit = 10240; q->tin_mode = CAKE_DIFFSERV_DIFFSERV3; q->flow_mode = CAKE_FLOW_TRIPLE; q->rate_bps = 0; /* unlimited by default */ q->interval = 100000; /* 100ms default */ q->target = 5000; /* 5ms: codel RFC argues * for 5 to 10% of interval */ q->rate_flags |= CAKE_FLAG_SPLIT_GSO; q->cur_tin = 0; q->cur_flow = 0; qdisc_watchdog_init(&q->watchdog, sch); if (opt) { err = cake_change(sch, opt, extack); if (err) return err; } err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) return err; quantum_div[0] = ~0; for (i = 1; i <= CAKE_QUEUES; i++) quantum_div[i] = 65535 / i; q->tins = kvcalloc(CAKE_MAX_TINS, sizeof(struct cake_tin_data), GFP_KERNEL); if (!q->tins) return -ENOMEM; for (i = 0; i < CAKE_MAX_TINS; i++) { struct cake_tin_data *b = q->tins + i; INIT_LIST_HEAD(&b->new_flows); INIT_LIST_HEAD(&b->old_flows); INIT_LIST_HEAD(&b->decaying_flows); b->sparse_flow_count = 0; b->bulk_flow_count = 0; b->decaying_flow_count = 0; for (j = 0; j < CAKE_QUEUES; j++) { struct cake_flow *flow = b->flows + j; u32 k = j * CAKE_MAX_TINS + i; INIT_LIST_HEAD(&flow->flowchain); cobalt_vars_init(&flow->cvars); q->overflow_heap[k].t = i; q->overflow_heap[k].b = j; b->overflow_idx[j] = k; } } cake_reconfigure(sch); q->avg_peak_bandwidth = q->rate_bps; q->min_netlen = ~0; q->min_adjlen = ~0; return 0; } static int cake_dump(struct Qdisc *sch, struct sk_buff *skb) { struct cake_sched_data *q = qdisc_priv(sch); struct nlattr *opts; u16 rate_flags; u8 flow_mode; opts = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!opts) goto nla_put_failure; if (nla_put_u64_64bit(skb, TCA_CAKE_BASE_RATE64, READ_ONCE(q->rate_bps), TCA_CAKE_PAD)) goto nla_put_failure; flow_mode = READ_ONCE(q->flow_mode); if (nla_put_u32(skb, TCA_CAKE_FLOW_MODE, flow_mode & CAKE_FLOW_MASK)) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_RTT, READ_ONCE(q->interval))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_TARGET, READ_ONCE(q->target))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_MEMORY, READ_ONCE(q->buffer_config_limit))) goto nla_put_failure; rate_flags = READ_ONCE(q->rate_flags); if (nla_put_u32(skb, TCA_CAKE_AUTORATE, !!(rate_flags & CAKE_FLAG_AUTORATE_INGRESS))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_INGRESS, !!(rate_flags & CAKE_FLAG_INGRESS))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_ACK_FILTER, READ_ONCE(q->ack_filter))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_NAT, !!(flow_mode & CAKE_FLOW_NAT_FLAG))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_DIFFSERV_MODE, READ_ONCE(q->tin_mode))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_WASH, !!(rate_flags & CAKE_FLAG_WASH))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_OVERHEAD, READ_ONCE(q->rate_overhead))) goto nla_put_failure; if (!(rate_flags & CAKE_FLAG_OVERHEAD)) if (nla_put_u32(skb, TCA_CAKE_RAW, 0)) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_ATM, READ_ONCE(q->atm_mode))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_MPU, READ_ONCE(q->rate_mpu))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_SPLIT_GSO, !!(rate_flags & CAKE_FLAG_SPLIT_GSO))) goto nla_put_failure; if (nla_put_u32(skb, TCA_CAKE_FWMARK, READ_ONCE(q->fwmark_mask))) goto nla_put_failure; return nla_nest_end(skb, opts); nla_put_failure: return -1; } static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct nlattr *stats = nla_nest_start_noflag(d->skb, TCA_STATS_APP); struct cake_sched_data *q = qdisc_priv(sch); struct nlattr *tstats, *ts; int i; if (!stats) return -1; #define PUT_STAT_U32(attr, data) do { \ if (nla_put_u32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \ goto nla_put_failure; \ } while (0) #define PUT_STAT_U64(attr, data) do { \ if (nla_put_u64_64bit(d->skb, TCA_CAKE_STATS_ ## attr, \ data, TCA_CAKE_STATS_PAD)) \ goto nla_put_failure; \ } while (0) PUT_STAT_U64(CAPACITY_ESTIMATE64, q->avg_peak_bandwidth); PUT_STAT_U32(MEMORY_LIMIT, q->buffer_limit); PUT_STAT_U32(MEMORY_USED, q->buffer_max_used); PUT_STAT_U32(AVG_NETOFF, ((q->avg_netoff + 0x8000) >> 16)); PUT_STAT_U32(MAX_NETLEN, q->max_netlen); PUT_STAT_U32(MAX_ADJLEN, q->max_adjlen); PUT_STAT_U32(MIN_NETLEN, q->min_netlen); PUT_STAT_U32(MIN_ADJLEN, q->min_adjlen); #undef PUT_STAT_U32 #undef PUT_STAT_U64 tstats = nla_nest_start_noflag(d->skb, TCA_CAKE_STATS_TIN_STATS); if (!tstats) goto nla_put_failure; #define PUT_TSTAT_U32(attr, data) do { \ if (nla_put_u32(d->skb, TCA_CAKE_TIN_STATS_ ## attr, data)) \ goto nla_put_failure; \ } while (0) #define PUT_TSTAT_U64(attr, data) do { \ if (nla_put_u64_64bit(d->skb, TCA_CAKE_TIN_STATS_ ## attr, \ data, TCA_CAKE_TIN_STATS_PAD)) \ goto nla_put_failure; \ } while (0) for (i = 0; i < q->tin_cnt; i++) { struct cake_tin_data *b = &q->tins[q->tin_order[i]]; ts = nla_nest_start_noflag(d->skb, i + 1); if (!ts) goto nla_put_failure; PUT_TSTAT_U64(THRESHOLD_RATE64, b->tin_rate_bps); PUT_TSTAT_U64(SENT_BYTES64, b->bytes); PUT_TSTAT_U32(BACKLOG_BYTES, b->tin_backlog); PUT_TSTAT_U32(TARGET_US, ktime_to_us(ns_to_ktime(b->cparams.target))); PUT_TSTAT_U32(INTERVAL_US, ktime_to_us(ns_to_ktime(b->cparams.interval))); PUT_TSTAT_U32(SENT_PACKETS, b->packets); PUT_TSTAT_U32(DROPPED_PACKETS, b->tin_dropped); PUT_TSTAT_U32(ECN_MARKED_PACKETS, b->tin_ecn_mark); PUT_TSTAT_U32(ACKS_DROPPED_PACKETS, b->ack_drops); PUT_TSTAT_U32(PEAK_DELAY_US, ktime_to_us(ns_to_ktime(b->peak_delay))); PUT_TSTAT_U32(AVG_DELAY_US, ktime_to_us(ns_to_ktime(b->avge_delay))); PUT_TSTAT_U32(BASE_DELAY_US, ktime_to_us(ns_to_ktime(b->base_delay))); PUT_TSTAT_U32(WAY_INDIRECT_HITS, b->way_hits); PUT_TSTAT_U32(WAY_MISSES, b->way_misses); PUT_TSTAT_U32(WAY_COLLISIONS, b->way_collisions); PUT_TSTAT_U32(SPARSE_FLOWS, b->sparse_flow_count + b->decaying_flow_count); PUT_TSTAT_U32(BULK_FLOWS, b->bulk_flow_count); PUT_TSTAT_U32(UNRESPONSIVE_FLOWS, b->unresponsive_flow_count); PUT_TSTAT_U32(MAX_SKBLEN, b->max_skblen); PUT_TSTAT_U32(FLOW_QUANTUM, b->flow_quantum); nla_nest_end(d->skb, ts); } #undef PUT_TSTAT_U32 #undef PUT_TSTAT_U64 nla_nest_end(d->skb, tstats); return nla_nest_end(d->skb, stats); nla_put_failure: nla_nest_cancel(d->skb, stats); return -1; } static struct Qdisc *cake_leaf(struct Qdisc *sch, unsigned long arg) { return NULL; } static unsigned long cake_find(struct Qdisc *sch, u32 classid) { return 0; } static unsigned long cake_bind(struct Qdisc *sch, unsigned long parent, u32 classid) { return 0; } static void cake_unbind(struct Qdisc *q, unsigned long cl) { } static struct tcf_block *cake_tcf_block(struct Qdisc *sch, unsigned long cl, struct netlink_ext_ack *extack) { struct cake_sched_data *q = qdisc_priv(sch); if (cl) return NULL; return q->block; } static int cake_dump_class(struct Qdisc *sch, unsigned long cl, struct sk_buff *skb, struct tcmsg *tcm) { tcm->tcm_handle |= TC_H_MIN(cl); return 0; } static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct gnet_dump *d) { struct cake_sched_data *q = qdisc_priv(sch); const struct cake_flow *flow = NULL; struct gnet_stats_queue qs = { 0 }; struct nlattr *stats; u32 idx = cl - 1; if (idx < CAKE_QUEUES * q->tin_cnt) { const struct cake_tin_data *b = \ &q->tins[q->tin_order[idx / CAKE_QUEUES]]; const struct sk_buff *skb; flow = &b->flows[idx % CAKE_QUEUES]; if (flow->head) { sch_tree_lock(sch); skb = flow->head; while (skb) { qs.qlen++; skb = skb->next; } sch_tree_unlock(sch); } qs.backlog = b->backlogs[idx % CAKE_QUEUES]; qs.drops = flow->dropped; } if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0) return -1; if (flow) { ktime_t now = ktime_get(); stats = nla_nest_start_noflag(d->skb, TCA_STATS_APP); if (!stats) return -1; #define PUT_STAT_U32(attr, data) do { \ if (nla_put_u32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \ goto nla_put_failure; \ } while (0) #define PUT_STAT_S32(attr, data) do { \ if (nla_put_s32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \ goto nla_put_failure; \ } while (0) PUT_STAT_S32(DEFICIT, flow->deficit); PUT_STAT_U32(DROPPING, flow->cvars.dropping); PUT_STAT_U32(COBALT_COUNT, flow->cvars.count); PUT_STAT_U32(P_DROP, flow->cvars.p_drop); if (flow->cvars.p_drop) { PUT_STAT_S32(BLUE_TIMER_US, ktime_to_us( ktime_sub(now, flow->cvars.blue_timer))); } if (flow->cvars.dropping) { PUT_STAT_S32(DROP_NEXT_US, ktime_to_us( ktime_sub(now, flow->cvars.drop_next))); } if (nla_nest_end(d->skb, stats) < 0) return -1; } return 0; nla_put_failure: nla_nest_cancel(d->skb, stats); return -1; } static void cake_walk(struct Qdisc *sch, struct qdisc_walker *arg) { struct cake_sched_data *q = qdisc_priv(sch); unsigned int i, j; if (arg->stop) return; for (i = 0; i < q->tin_cnt; i++) { struct cake_tin_data *b = &q->tins[q->tin_order[i]]; for (j = 0; j < CAKE_QUEUES; j++) { if (list_empty(&b->flows[j].flowchain)) { arg->count++; continue; } if (!tc_qdisc_stats_dump(sch, i * CAKE_QUEUES + j + 1, arg)) break; } } } static const struct Qdisc_class_ops cake_class_ops = { .leaf = cake_leaf, .find = cake_find, .tcf_block = cake_tcf_block, .bind_tcf = cake_bind, .unbind_tcf = cake_unbind, .dump = cake_dump_class, .dump_stats = cake_dump_class_stats, .walk = cake_walk, }; static struct Qdisc_ops cake_qdisc_ops __read_mostly = { .cl_ops = &cake_class_ops, .id = "cake", .priv_size = sizeof(struct cake_sched_data), .enqueue = cake_enqueue, .dequeue = cake_dequeue, .peek = qdisc_peek_dequeued, .init = cake_init, .reset = cake_reset, .destroy = cake_destroy, .change = cake_change, .dump = cake_dump, .dump_stats = cake_dump_stats, .owner = THIS_MODULE, }; MODULE_ALIAS_NET_SCH("cake"); static int __init cake_module_init(void) { return register_qdisc(&cake_qdisc_ops); } static void __exit cake_module_exit(void) { unregister_qdisc(&cake_qdisc_ops); } module_init(cake_module_init) module_exit(cake_module_exit) MODULE_AUTHOR("Jonathan Morton"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("The CAKE shaper."); |
| 2 2 1 2 2 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 11 11 1 1 4 1 3 2 2 1 1 4 2 2 2 2 2 2 2 2 2 1 1 1 4 1 1 3 2 1 1 1 2 4 2 1 1 1 1 2 11 11 11 11 11 11 11 11 11 11 11 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2016 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> */ #include "devl_internal.h" struct devlink_region { struct devlink *devlink; struct devlink_port *port; struct list_head list; union { const struct devlink_region_ops *ops; const struct devlink_port_region_ops *port_ops; }; struct mutex snapshot_lock; /* protects snapshot_list, * max_snapshots and cur_snapshots * consistency. */ struct list_head snapshot_list; u32 max_snapshots; u32 cur_snapshots; u64 size; }; struct devlink_snapshot { struct list_head list; struct devlink_region *region; u8 *data; u32 id; }; static struct devlink_region * devlink_region_get_by_name(struct devlink *devlink, const char *region_name) { struct devlink_region *region; list_for_each_entry(region, &devlink->region_list, list) if (!strcmp(region->ops->name, region_name)) return region; return NULL; } static struct devlink_region * devlink_port_region_get_by_name(struct devlink_port *port, const char *region_name) { struct devlink_region *region; list_for_each_entry(region, &port->region_list, list) if (!strcmp(region->ops->name, region_name)) return region; return NULL; } static struct devlink_snapshot * devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) { struct devlink_snapshot *snapshot; list_for_each_entry(snapshot, ®ion->snapshot_list, list) if (snapshot->id == id) return snapshot; return NULL; } static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg, struct devlink *devlink, struct devlink_snapshot *snapshot) { struct nlattr *snap_attr; int err; snap_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_SNAPSHOT); if (!snap_attr) return -EMSGSIZE; err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, snapshot->id); if (err) goto nla_put_failure; nla_nest_end(msg, snap_attr); return 0; nla_put_failure: nla_nest_cancel(msg, snap_attr); return err; } static int devlink_nl_region_snapshots_id_put(struct sk_buff *msg, struct devlink *devlink, struct devlink_region *region) { struct devlink_snapshot *snapshot; struct nlattr *snapshots_attr; int err; snapshots_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_SNAPSHOTS); if (!snapshots_attr) return -EMSGSIZE; list_for_each_entry(snapshot, ®ion->snapshot_list, list) { err = devlink_nl_region_snapshot_id_put(msg, devlink, snapshot); if (err) goto nla_put_failure; } nla_nest_end(msg, snapshots_attr); return 0; nla_put_failure: nla_nest_cancel(msg, snapshots_attr); return err; } static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, u32 portid, u32 seq, int flags, struct devlink_region *region) { void *hdr; int err; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; err = devlink_nl_put_handle(msg, devlink); if (err) goto nla_put_failure; if (region->port) { err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, region->port->index); if (err) goto nla_put_failure; } err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name); if (err) goto nla_put_failure; err = devlink_nl_put_u64(msg, DEVLINK_ATTR_REGION_SIZE, region->size); if (err) goto nla_put_failure; err = nla_put_u32(msg, DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, region->max_snapshots); if (err) goto nla_put_failure; err = devlink_nl_region_snapshots_id_put(msg, devlink, region); if (err) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return err; } static struct sk_buff * devlink_nl_region_notify_build(struct devlink_region *region, struct devlink_snapshot *snapshot, enum devlink_command cmd, u32 portid, u32 seq) { struct devlink *devlink = region->devlink; struct sk_buff *msg; void *hdr; int err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return ERR_PTR(-ENOMEM); hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, 0, cmd); if (!hdr) { err = -EMSGSIZE; goto out_free_msg; } err = devlink_nl_put_handle(msg, devlink); if (err) goto out_cancel_msg; if (region->port) { err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, region->port->index); if (err) goto out_cancel_msg; } err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name); if (err) goto out_cancel_msg; if (snapshot) { err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, snapshot->id); if (err) goto out_cancel_msg; } else { err = devlink_nl_put_u64(msg, DEVLINK_ATTR_REGION_SIZE, region->size); if (err) goto out_cancel_msg; } genlmsg_end(msg, hdr); return msg; out_cancel_msg: genlmsg_cancel(msg, hdr); out_free_msg: nlmsg_free(msg); return ERR_PTR(err); } static void devlink_nl_region_notify(struct devlink_region *region, struct devlink_snapshot *snapshot, enum devlink_command cmd) { struct devlink *devlink = region->devlink; struct sk_buff *msg; WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL); if (!__devl_is_registered(devlink) || !devlink_nl_notify_need(devlink)) return; msg = devlink_nl_region_notify_build(region, snapshot, cmd, 0, 0); if (IS_ERR(msg)) return; devlink_nl_notify_send(devlink, msg); } void devlink_regions_notify_register(struct devlink *devlink) { struct devlink_region *region; list_for_each_entry(region, &devlink->region_list, list) devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); } void devlink_regions_notify_unregister(struct devlink *devlink) { struct devlink_region *region; list_for_each_entry_reverse(region, &devlink->region_list, list) devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL); } /** * __devlink_snapshot_id_increment - Increment number of snapshots using an id * @devlink: devlink instance * @id: the snapshot id * * Track when a new snapshot begins using an id. Load the count for the * given id from the snapshot xarray, increment it, and store it back. * * Called when a new snapshot is created with the given id. * * The id *must* have been previously allocated by * devlink_region_snapshot_id_get(). * * Returns 0 on success, or an error on failure. */ static int __devlink_snapshot_id_increment(struct devlink *devlink, u32 id) { unsigned long count; void *p; int err; xa_lock(&devlink->snapshot_ids); p = xa_load(&devlink->snapshot_ids, id); if (WARN_ON(!p)) { err = -EINVAL; goto unlock; } if (WARN_ON(!xa_is_value(p))) { err = -EINVAL; goto unlock; } count = xa_to_value(p); count++; err = xa_err(__xa_store(&devlink->snapshot_ids, id, xa_mk_value(count), GFP_ATOMIC)); unlock: xa_unlock(&devlink->snapshot_ids); return err; } /** * __devlink_snapshot_id_decrement - Decrease number of snapshots using an id * @devlink: devlink instance * @id: the snapshot id * * Track when a snapshot is deleted and stops using an id. Load the count * for the given id from the snapshot xarray, decrement it, and store it * back. * * If the count reaches zero, erase this id from the xarray, freeing it * up for future re-use by devlink_region_snapshot_id_get(). * * Called when a snapshot using the given id is deleted, and when the * initial allocator of the id is finished using it. */ static void __devlink_snapshot_id_decrement(struct devlink *devlink, u32 id) { unsigned long count; void *p; xa_lock(&devlink->snapshot_ids); p = xa_load(&devlink->snapshot_ids, id); if (WARN_ON(!p)) goto unlock; if (WARN_ON(!xa_is_value(p))) goto unlock; count = xa_to_value(p); if (count > 1) { count--; __xa_store(&devlink->snapshot_ids, id, xa_mk_value(count), GFP_ATOMIC); } else { /* If this was the last user, we can erase this id */ __xa_erase(&devlink->snapshot_ids, id); } unlock: xa_unlock(&devlink->snapshot_ids); } /** * __devlink_snapshot_id_insert - Insert a specific snapshot ID * @devlink: devlink instance * @id: the snapshot id * * Mark the given snapshot id as used by inserting a zero value into the * snapshot xarray. * * This must be called while holding the devlink instance lock. Unlike * devlink_snapshot_id_get, the initial reference count is zero, not one. * It is expected that the id will immediately be used before * releasing the devlink instance lock. * * Returns zero on success, or an error code if the snapshot id could not * be inserted. */ static int __devlink_snapshot_id_insert(struct devlink *devlink, u32 id) { int err; xa_lock(&devlink->snapshot_ids); if (xa_load(&devlink->snapshot_ids, id)) { xa_unlock(&devlink->snapshot_ids); return -EEXIST; } err = xa_err(__xa_store(&devlink->snapshot_ids, id, xa_mk_value(0), GFP_ATOMIC)); xa_unlock(&devlink->snapshot_ids); return err; } /** * __devlink_region_snapshot_id_get - get snapshot ID * @devlink: devlink instance * @id: storage to return snapshot id * * Allocates a new snapshot id. Returns zero on success, or a negative * error on failure. Must be called while holding the devlink instance * lock. * * Snapshot IDs are tracked using an xarray which stores the number of * users of the snapshot id. * * Note that the caller of this function counts as a 'user', in order to * avoid race conditions. The caller must release its hold on the * snapshot by using devlink_region_snapshot_id_put. */ static int __devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id) { return xa_alloc(&devlink->snapshot_ids, id, xa_mk_value(1), xa_limit_32b, GFP_KERNEL); } /** * __devlink_region_snapshot_create - create a new snapshot * This will add a new snapshot of a region. The snapshot * will be stored on the region struct and can be accessed * from devlink. This is useful for future analyses of snapshots. * Multiple snapshots can be created on a region. * The @snapshot_id should be obtained using the getter function. * * Must be called only while holding the region snapshot lock. * * @region: devlink region of the snapshot * @data: snapshot data * @snapshot_id: snapshot id to be created */ static int __devlink_region_snapshot_create(struct devlink_region *region, u8 *data, u32 snapshot_id) { struct devlink *devlink = region->devlink; struct devlink_snapshot *snapshot; int err; lockdep_assert_held(®ion->snapshot_lock); /* check if region can hold one more snapshot */ if (region->cur_snapshots == region->max_snapshots) return -ENOSPC; if (devlink_region_snapshot_get_by_id(region, snapshot_id)) return -EEXIST; snapshot = kzalloc(sizeof(*snapshot), GFP_KERNEL); if (!snapshot) return -ENOMEM; err = __devlink_snapshot_id_increment(devlink, snapshot_id); if (err) goto err_snapshot_id_increment; snapshot->id = snapshot_id; snapshot->region = region; snapshot->data = data; list_add_tail(&snapshot->list, ®ion->snapshot_list); region->cur_snapshots++; devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_NEW); return 0; err_snapshot_id_increment: kfree(snapshot); return err; } static void devlink_region_snapshot_del(struct devlink_region *region, struct devlink_snapshot *snapshot) { struct devlink *devlink = region->devlink; lockdep_assert_held(®ion->snapshot_lock); devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL); region->cur_snapshots--; list_del(&snapshot->list); region->ops->destructor(snapshot->data); __devlink_snapshot_id_decrement(devlink, snapshot->id); kfree(snapshot); } int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_port *port = NULL; struct devlink_region *region; const char *region_name; struct sk_buff *msg; unsigned int index; int err; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME)) return -EINVAL; if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) return -ENODEV; } region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); if (port) region = devlink_port_region_get_by_name(port, region_name); else region = devlink_region_get_by_name(devlink, region_name); if (!region) return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET, info->snd_portid, info->snd_seq, 0, region); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_cmd_region_get_port_dumpit(struct sk_buff *msg, struct netlink_callback *cb, struct devlink_port *port, int *idx, int start, int flags) { struct devlink_region *region; int err = 0; list_for_each_entry(region, &port->region_list, list) { if (*idx < start) { (*idx)++; continue; } err = devlink_nl_region_fill(msg, port->devlink, DEVLINK_CMD_REGION_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, region); if (err) goto out; (*idx)++; } out: return err; } static int devlink_nl_region_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_region *region; struct devlink_port *port; unsigned long port_index; int idx = 0; int err; list_for_each_entry(region, &devlink->region_list, list) { if (idx < state->idx) { idx++; continue; } err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, region); if (err) { state->idx = idx; return err; } idx++; } xa_for_each(&devlink->ports, port_index, port) { err = devlink_nl_cmd_region_get_port_dumpit(msg, cb, port, &idx, state->idx, flags); if (err) { state->idx = idx; return err; } } return 0; } int devlink_nl_region_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_region_get_dump_one); } int devlink_nl_region_del_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_snapshot *snapshot; struct devlink_port *port = NULL; struct devlink_region *region; const char *region_name; unsigned int index; u32 snapshot_id; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME) || GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_SNAPSHOT_ID)) return -EINVAL; region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]); if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) return -ENODEV; } if (port) region = devlink_port_region_get_by_name(port, region_name); else region = devlink_region_get_by_name(devlink, region_name); if (!region) return -EINVAL; mutex_lock(®ion->snapshot_lock); snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); if (!snapshot) { mutex_unlock(®ion->snapshot_lock); return -EINVAL; } devlink_region_snapshot_del(region, snapshot); mutex_unlock(®ion->snapshot_lock); return 0; } int devlink_nl_region_new_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_snapshot *snapshot; struct devlink_port *port = NULL; struct nlattr *snapshot_id_attr; struct devlink_region *region; const char *region_name; unsigned int index; u32 snapshot_id; u8 *data; int err; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME)) { NL_SET_ERR_MSG(info->extack, "No region name provided"); return -EINVAL; } region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) return -ENODEV; } if (port) region = devlink_port_region_get_by_name(port, region_name); else region = devlink_region_get_by_name(devlink, region_name); if (!region) { NL_SET_ERR_MSG(info->extack, "The requested region does not exist"); return -EINVAL; } if (!region->ops->snapshot) { NL_SET_ERR_MSG(info->extack, "The requested region does not support taking an immediate snapshot"); return -EOPNOTSUPP; } mutex_lock(®ion->snapshot_lock); if (region->cur_snapshots == region->max_snapshots) { NL_SET_ERR_MSG(info->extack, "The region has reached the maximum number of stored snapshots"); err = -ENOSPC; goto unlock; } snapshot_id_attr = info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]; if (snapshot_id_attr) { snapshot_id = nla_get_u32(snapshot_id_attr); if (devlink_region_snapshot_get_by_id(region, snapshot_id)) { NL_SET_ERR_MSG(info->extack, "The requested snapshot id is already in use"); err = -EEXIST; goto unlock; } err = __devlink_snapshot_id_insert(devlink, snapshot_id); if (err) goto unlock; } else { err = __devlink_region_snapshot_id_get(devlink, &snapshot_id); if (err) { NL_SET_ERR_MSG(info->extack, "Failed to allocate a new snapshot id"); goto unlock; } } if (port) err = region->port_ops->snapshot(port, region->port_ops, info->extack, &data); else err = region->ops->snapshot(devlink, region->ops, info->extack, &data); if (err) goto err_snapshot_capture; err = __devlink_region_snapshot_create(region, data, snapshot_id); if (err) goto err_snapshot_create; if (!snapshot_id_attr) { struct sk_buff *msg; snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); if (WARN_ON(!snapshot)) { err = -EINVAL; goto unlock; } msg = devlink_nl_region_notify_build(region, snapshot, DEVLINK_CMD_REGION_NEW, info->snd_portid, info->snd_seq); err = PTR_ERR_OR_ZERO(msg); if (err) goto err_notify; err = genlmsg_reply(msg, info); if (err) goto err_notify; } mutex_unlock(®ion->snapshot_lock); return 0; err_snapshot_create: region->ops->destructor(data); err_snapshot_capture: __devlink_snapshot_id_decrement(devlink, snapshot_id); mutex_unlock(®ion->snapshot_lock); return err; err_notify: devlink_region_snapshot_del(region, snapshot); unlock: mutex_unlock(®ion->snapshot_lock); return err; } static int devlink_nl_cmd_region_read_chunk_fill(struct sk_buff *msg, u8 *chunk, u32 chunk_size, u64 addr) { struct nlattr *chunk_attr; int err; chunk_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_CHUNK); if (!chunk_attr) return -EINVAL; err = nla_put(msg, DEVLINK_ATTR_REGION_CHUNK_DATA, chunk_size, chunk); if (err) goto nla_put_failure; err = devlink_nl_put_u64(msg, DEVLINK_ATTR_REGION_CHUNK_ADDR, addr); if (err) goto nla_put_failure; nla_nest_end(msg, chunk_attr); return 0; nla_put_failure: nla_nest_cancel(msg, chunk_attr); return err; } #define DEVLINK_REGION_READ_CHUNK_SIZE 256 typedef int devlink_chunk_fill_t(void *cb_priv, u8 *chunk, u32 chunk_size, u64 curr_offset, struct netlink_ext_ack *extack); static int devlink_nl_region_read_fill(struct sk_buff *skb, devlink_chunk_fill_t *cb, void *cb_priv, u64 start_offset, u64 end_offset, u64 *new_offset, struct netlink_ext_ack *extack) { u64 curr_offset = start_offset; int err = 0; u8 *data; /* Allocate and re-use a single buffer */ data = kmalloc(DEVLINK_REGION_READ_CHUNK_SIZE, GFP_KERNEL); if (!data) return -ENOMEM; *new_offset = start_offset; while (curr_offset < end_offset) { u32 data_size; data_size = min_t(u32, end_offset - curr_offset, DEVLINK_REGION_READ_CHUNK_SIZE); err = cb(cb_priv, data, data_size, curr_offset, extack); if (err) break; err = devlink_nl_cmd_region_read_chunk_fill(skb, data, data_size, curr_offset); if (err) break; curr_offset += data_size; } *new_offset = curr_offset; kfree(data); return err; } static int devlink_region_snapshot_fill(void *cb_priv, u8 *chunk, u32 chunk_size, u64 curr_offset, struct netlink_ext_ack __always_unused *extack) { struct devlink_snapshot *snapshot = cb_priv; memcpy(chunk, &snapshot->data[curr_offset], chunk_size); return 0; } static int devlink_region_port_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size, u64 curr_offset, struct netlink_ext_ack *extack) { struct devlink_region *region = cb_priv; return region->port_ops->read(region->port, region->port_ops, extack, curr_offset, chunk_size, chunk); } static int devlink_region_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size, u64 curr_offset, struct netlink_ext_ack *extack) { struct devlink_region *region = cb_priv; return region->ops->read(region->devlink, region->ops, extack, curr_offset, chunk_size, chunk); } int devlink_nl_region_read_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct nlattr *chunks_attr, *region_attr, *snapshot_attr; u64 ret_offset, start_offset, end_offset = U64_MAX; struct nlattr **attrs = info->info.attrs; struct devlink_port *port = NULL; devlink_chunk_fill_t *region_cb; struct devlink_region *region; const char *region_name; struct devlink *devlink; unsigned int index; void *region_cb_priv; void *hdr; int err; start_offset = state->start_offset; devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs, false); if (IS_ERR(devlink)) return PTR_ERR(devlink); if (!attrs[DEVLINK_ATTR_REGION_NAME]) { NL_SET_ERR_MSG(cb->extack, "No region name provided"); err = -EINVAL; goto out_unlock; } if (attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) { err = -ENODEV; goto out_unlock; } } region_attr = attrs[DEVLINK_ATTR_REGION_NAME]; region_name = nla_data(region_attr); if (port) region = devlink_port_region_get_by_name(port, region_name); else region = devlink_region_get_by_name(devlink, region_name); if (!region) { NL_SET_ERR_MSG_ATTR(cb->extack, region_attr, "Requested region does not exist"); err = -EINVAL; goto out_unlock; } snapshot_attr = attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]; if (!snapshot_attr) { if (!nla_get_flag(attrs[DEVLINK_ATTR_REGION_DIRECT])) { NL_SET_ERR_MSG(cb->extack, "No snapshot id provided"); err = -EINVAL; goto out_unlock; } if (!region->ops->read) { NL_SET_ERR_MSG(cb->extack, "Requested region does not support direct read"); err = -EOPNOTSUPP; goto out_unlock; } if (port) region_cb = &devlink_region_port_direct_fill; else region_cb = &devlink_region_direct_fill; region_cb_priv = region; } else { struct devlink_snapshot *snapshot; u32 snapshot_id; if (nla_get_flag(attrs[DEVLINK_ATTR_REGION_DIRECT])) { NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Direct region read does not use snapshot"); err = -EINVAL; goto out_unlock; } snapshot_id = nla_get_u32(snapshot_attr); snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); if (!snapshot) { NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Requested snapshot does not exist"); err = -EINVAL; goto out_unlock; } region_cb = &devlink_region_snapshot_fill; region_cb_priv = snapshot; } if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] && attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]) { if (!start_offset) start_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]); } if (end_offset > region->size) end_offset = region->size; /* return 0 if there is no further data to read */ if (start_offset == end_offset) { err = 0; goto out_unlock; } hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI, DEVLINK_CMD_REGION_READ); if (!hdr) { err = -EMSGSIZE; goto out_unlock; } err = devlink_nl_put_handle(skb, devlink); if (err) goto nla_put_failure; if (region->port) { err = nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX, region->port->index); if (err) goto nla_put_failure; } err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name); if (err) goto nla_put_failure; chunks_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_REGION_CHUNKS); if (!chunks_attr) { err = -EMSGSIZE; goto nla_put_failure; } err = devlink_nl_region_read_fill(skb, region_cb, region_cb_priv, start_offset, end_offset, &ret_offset, cb->extack); if (err && err != -EMSGSIZE) goto nla_put_failure; /* Check if there was any progress done to prevent infinite loop */ if (ret_offset == start_offset) { err = -EINVAL; goto nla_put_failure; } state->start_offset = ret_offset; nla_nest_end(skb, chunks_attr); genlmsg_end(skb, hdr); devl_unlock(devlink); devlink_put(devlink); return skb->len; nla_put_failure: genlmsg_cancel(skb, hdr); out_unlock: devl_unlock(devlink); devlink_put(devlink); return err; } /** * devl_region_create - create a new address region * * @devlink: devlink * @ops: region operations and name * @region_max_snapshots: Maximum supported number of snapshots for region * @region_size: size of region */ struct devlink_region *devl_region_create(struct devlink *devlink, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size) { struct devlink_region *region; devl_assert_locked(devlink); if (WARN_ON(!ops) || WARN_ON(!ops->destructor)) return ERR_PTR(-EINVAL); if (devlink_region_get_by_name(devlink, ops->name)) return ERR_PTR(-EEXIST); region = kzalloc(sizeof(*region), GFP_KERNEL); if (!region) return ERR_PTR(-ENOMEM); region->devlink = devlink; region->max_snapshots = region_max_snapshots; region->ops = ops; region->size = region_size; INIT_LIST_HEAD(®ion->snapshot_list); mutex_init(®ion->snapshot_lock); list_add_tail(®ion->list, &devlink->region_list); devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); return region; } EXPORT_SYMBOL_GPL(devl_region_create); /** * devlink_region_create - create a new address region * * @devlink: devlink * @ops: region operations and name * @region_max_snapshots: Maximum supported number of snapshots for region * @region_size: size of region * * Context: Takes and release devlink->lock <mutex>. */ struct devlink_region * devlink_region_create(struct devlink *devlink, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size) { struct devlink_region *region; devl_lock(devlink); region = devl_region_create(devlink, ops, region_max_snapshots, region_size); devl_unlock(devlink); return region; } EXPORT_SYMBOL_GPL(devlink_region_create); /** * devlink_port_region_create - create a new address region for a port * * @port: devlink port * @ops: region operations and name * @region_max_snapshots: Maximum supported number of snapshots for region * @region_size: size of region * * Context: Takes and release devlink->lock <mutex>. */ struct devlink_region * devlink_port_region_create(struct devlink_port *port, const struct devlink_port_region_ops *ops, u32 region_max_snapshots, u64 region_size) { struct devlink *devlink = port->devlink; struct devlink_region *region; int err = 0; ASSERT_DEVLINK_PORT_INITIALIZED(port); if (WARN_ON(!ops) || WARN_ON(!ops->destructor)) return ERR_PTR(-EINVAL); devl_lock(devlink); if (devlink_port_region_get_by_name(port, ops->name)) { err = -EEXIST; goto unlock; } region = kzalloc(sizeof(*region), GFP_KERNEL); if (!region) { err = -ENOMEM; goto unlock; } region->devlink = devlink; region->port = port; region->max_snapshots = region_max_snapshots; region->port_ops = ops; region->size = region_size; INIT_LIST_HEAD(®ion->snapshot_list); mutex_init(®ion->snapshot_lock); list_add_tail(®ion->list, &port->region_list); devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); devl_unlock(devlink); return region; unlock: devl_unlock(devlink); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(devlink_port_region_create); /** * devl_region_destroy - destroy address region * * @region: devlink region to destroy */ void devl_region_destroy(struct devlink_region *region) { struct devlink *devlink = region->devlink; struct devlink_snapshot *snapshot, *ts; devl_assert_locked(devlink); /* Free all snapshots of region */ mutex_lock(®ion->snapshot_lock); list_for_each_entry_safe(snapshot, ts, ®ion->snapshot_list, list) devlink_region_snapshot_del(region, snapshot); mutex_unlock(®ion->snapshot_lock); list_del(®ion->list); mutex_destroy(®ion->snapshot_lock); devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL); kfree(region); } EXPORT_SYMBOL_GPL(devl_region_destroy); /** * devlink_region_destroy - destroy address region * * @region: devlink region to destroy * * Context: Takes and release devlink->lock <mutex>. */ void devlink_region_destroy(struct devlink_region *region) { struct devlink *devlink = region->devlink; devl_lock(devlink); devl_region_destroy(region); devl_unlock(devlink); } EXPORT_SYMBOL_GPL(devlink_region_destroy); /** * devlink_region_snapshot_id_get - get snapshot ID * * This callback should be called when adding a new snapshot, * Driver should use the same id for multiple snapshots taken * on multiple regions at the same time/by the same trigger. * * The caller of this function must use devlink_region_snapshot_id_put * when finished creating regions using this id. * * Returns zero on success, or a negative error code on failure. * * @devlink: devlink * @id: storage to return id */ int devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id) { return __devlink_region_snapshot_id_get(devlink, id); } EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_get); /** * devlink_region_snapshot_id_put - put snapshot ID reference * * This should be called by a driver after finishing creating snapshots * with an id. Doing so ensures that the ID can later be released in the * event that all snapshots using it have been destroyed. * * @devlink: devlink * @id: id to release reference on */ void devlink_region_snapshot_id_put(struct devlink *devlink, u32 id) { __devlink_snapshot_id_decrement(devlink, id); } EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_put); /** * devlink_region_snapshot_create - create a new snapshot * This will add a new snapshot of a region. The snapshot * will be stored on the region struct and can be accessed * from devlink. This is useful for future analyses of snapshots. * Multiple snapshots can be created on a region. * The @snapshot_id should be obtained using the getter function. * * @region: devlink region of the snapshot * @data: snapshot data * @snapshot_id: snapshot id to be created */ int devlink_region_snapshot_create(struct devlink_region *region, u8 *data, u32 snapshot_id) { int err; mutex_lock(®ion->snapshot_lock); err = __devlink_region_snapshot_create(region, data, snapshot_id); mutex_unlock(®ion->snapshot_lock); return err; } EXPORT_SYMBOL_GPL(devlink_region_snapshot_create); |
| 4 17 159 432 4 17 | 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 | /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ /* * Copyright (c) 2005 Voltaire Inc. All rights reserved. * Copyright (c) 2005 Intel Corporation. All rights reserved. */ #ifndef IB_ADDR_H #define IB_ADDR_H #include <linux/ethtool.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/socket.h> #include <linux/if_vlan.h> #include <net/ipv6.h> #include <net/if_inet6.h> #include <net/ip.h> #include <rdma/ib_verbs.h> #include <rdma/ib_pack.h> #include <net/net_namespace.h> /** * struct rdma_dev_addr - Contains resolved RDMA hardware addresses * @src_dev_addr: Source MAC address. * @dst_dev_addr: Destination MAC address. * @broadcast: Broadcast address of the device. * @dev_type: The interface hardware type of the device. * @bound_dev_if: An optional device interface index. * @transport: The transport type used. * @net: Network namespace containing the bound_dev_if net_dev. * @sgid_attr: GID attribute to use for identified SGID */ struct rdma_dev_addr { unsigned char src_dev_addr[MAX_ADDR_LEN]; unsigned char dst_dev_addr[MAX_ADDR_LEN]; unsigned char broadcast[MAX_ADDR_LEN]; unsigned short dev_type; int bound_dev_if; enum rdma_transport_type transport; struct net *net; const struct ib_gid_attr *sgid_attr; enum rdma_network_type network; int hoplimit; }; /** * rdma_translate_ip - Translate a local IP address to an RDMA hardware * address. * * The dev_addr->net field must be initialized. */ int rdma_translate_ip(const struct sockaddr *addr, struct rdma_dev_addr *dev_addr); /** * rdma_resolve_ip - Resolve source and destination IP addresses to * RDMA hardware addresses. * @src_addr: An optional source address to use in the resolution. If a * source address is not provided, a usable address will be returned via * the callback. * @dst_addr: The destination address to resolve. * @addr: A reference to a data location that will receive the resolved * addresses. The data location must remain valid until the callback has * been invoked. The net field of the addr struct must be valid. * @timeout_ms: Amount of time to wait for the address resolution to complete. * @callback: Call invoked once address resolution has completed, timed out, * or been canceled. A status of 0 indicates success. * @resolve_by_gid_attr: Resolve the ip based on the GID attribute from * rdma_dev_addr. * @context: User-specified context associated with the call. */ int rdma_resolve_ip(struct sockaddr *src_addr, const struct sockaddr *dst_addr, struct rdma_dev_addr *addr, unsigned long timeout_ms, void (*callback)(int status, struct sockaddr *src_addr, struct rdma_dev_addr *addr, void *context), bool resolve_by_gid_attr, void *context); void rdma_addr_cancel(struct rdma_dev_addr *addr); int rdma_addr_size(const struct sockaddr *addr); int rdma_addr_size_in6(struct sockaddr_in6 *addr); int rdma_addr_size_kss(struct __kernel_sockaddr_storage *addr); static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr) { return ((u16)dev_addr->broadcast[8] << 8) | (u16)dev_addr->broadcast[9]; } static inline void ib_addr_set_pkey(struct rdma_dev_addr *dev_addr, u16 pkey) { dev_addr->broadcast[8] = pkey >> 8; dev_addr->broadcast[9] = (unsigned char) pkey; } static inline void ib_addr_get_mgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(gid, dev_addr->broadcast + 4, sizeof *gid); } static inline int rdma_addr_gid_offset(struct rdma_dev_addr *dev_addr) { return dev_addr->dev_type == ARPHRD_INFINIBAND ? 4 : 0; } static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev) { return is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : 0xffff; } static inline int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid) { switch (addr->sa_family) { case AF_INET: ipv6_addr_set_v4mapped(((struct sockaddr_in *) addr)->sin_addr.s_addr, (struct in6_addr *)gid); break; case AF_INET6: *(struct in6_addr *)&gid->raw = ((struct sockaddr_in6 *)addr)->sin6_addr; break; default: return -EINVAL; } return 0; } /* Important - sockaddr should be a union of sockaddr_in and sockaddr_in6 */ static inline void rdma_gid2ip(struct sockaddr *out, const union ib_gid *gid) { if (ipv6_addr_v4mapped((struct in6_addr *)gid)) { struct sockaddr_in *out_in = (struct sockaddr_in *)out; memset(out_in, 0, sizeof(*out_in)); out_in->sin_family = AF_INET; memcpy(&out_in->sin_addr.s_addr, gid->raw + 12, 4); } else { struct sockaddr_in6 *out_in = (struct sockaddr_in6 *)out; memset(out_in, 0, sizeof(*out_in)); out_in->sin6_family = AF_INET6; memcpy(&out_in->sin6_addr.s6_addr, gid->raw, 16); } } /* * rdma_get/set_sgid/dgid() APIs are applicable to IB, and iWarp. * They are not applicable to RoCE. * RoCE GIDs are derived from the IP addresses. */ static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(*gid)); } static inline void rdma_addr_set_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), gid, sizeof *gid); } static inline void rdma_addr_get_dgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(gid, dev_addr->dst_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof *gid); } static inline void rdma_addr_set_dgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid) { memcpy(dev_addr->dst_dev_addr + rdma_addr_gid_offset(dev_addr), gid, sizeof *gid); } static inline enum ib_mtu iboe_get_mtu(int mtu) { /* * Reduce IB headers from effective IBoE MTU. */ mtu = mtu - (IB_GRH_BYTES + IB_UDP_BYTES + IB_BTH_BYTES + IB_EXT_XRC_BYTES + IB_EXT_ATOMICETH_BYTES + IB_ICRC_BYTES); if (mtu >= ib_mtu_enum_to_int(IB_MTU_4096)) return IB_MTU_4096; else if (mtu >= ib_mtu_enum_to_int(IB_MTU_2048)) return IB_MTU_2048; else if (mtu >= ib_mtu_enum_to_int(IB_MTU_1024)) return IB_MTU_1024; else if (mtu >= ib_mtu_enum_to_int(IB_MTU_512)) return IB_MTU_512; else if (mtu >= ib_mtu_enum_to_int(IB_MTU_256)) return IB_MTU_256; else return 0; } static inline int rdma_link_local_addr(struct in6_addr *addr) { if (addr->s6_addr32[0] == htonl(0xfe800000) && addr->s6_addr32[1] == 0) return 1; return 0; } static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac) { memcpy(mac, &addr->s6_addr[8], 3); memcpy(mac + 3, &addr->s6_addr[13], 3); mac[0] ^= 2; } static inline int rdma_is_multicast_addr(struct in6_addr *addr) { __be32 ipv4_addr; if (addr->s6_addr[0] == 0xff) return 1; ipv4_addr = addr->s6_addr32[3]; return (ipv6_addr_v4mapped(addr) && ipv4_is_multicast(ipv4_addr)); } static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac) { int i; mac[0] = 0x33; mac[1] = 0x33; for (i = 2; i < 6; ++i) mac[i] = addr->s6_addr[i + 10]; } static inline u16 rdma_get_vlan_id(union ib_gid *dgid) { u16 vid; vid = dgid->raw[11] << 8 | dgid->raw[12]; return vid < 0x1000 ? vid : 0xffff; } static inline struct net_device *rdma_vlan_dev_real_dev(const struct net_device *dev) { return is_vlan_dev(dev) ? vlan_dev_real_dev(dev) : NULL; } #endif /* IB_ADDR_H */ |
| 2 1 1 1 1 7 7 2 2 2 2 1 1 7 7 7 128 127 129 1 1 1 1 1 1 1 1 1 1 4 4 4 4 4 4 4 4 1 1 1 1 1 1 1 1 4 128 128 128 129 128 128 128 129 6 6 6 6 6 6 5 4 129 129 14 14 14 14 13 14 14 14 14 13 14 14 14 873 125 706 207 207 191 194 24 192 207 23 18 23 15 14 32 32 32 32 29 29 12 29 11 11 11 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Helpers for formatting and printing strings * * Copyright 31 August 2008 James Bottomley * Copyright (C) 2013, Intel Corporation */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/math64.h> #include <linux/export.h> #include <linux/ctype.h> #include <linux/device.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/limits.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/string_helpers.h> #include <kunit/test.h> #include <kunit/test-bug.h> /** * string_get_size - get the size in the specified units * @size: The size to be converted in blocks * @blk_size: Size of the block (use 1 for size in bytes) * @units: Units to use (powers of 1000 or 1024), whether to include space separator * @buf: buffer to format to * @len: length of buffer * * This function returns a string formatted to 3 significant figures * giving the size in the required units. @buf should have room for * at least 9 bytes and will always be zero terminated. * * Return value: number of characters of output that would have been written * (which may be greater than len, if output was truncated). */ int string_get_size(u64 size, u64 blk_size, const enum string_size_units units, char *buf, int len) { enum string_size_units units_base = units & STRING_UNITS_MASK; static const char *const units_10[] = { "", "k", "M", "G", "T", "P", "E", "Z", "Y", }; static const char *const units_2[] = { "", "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi", }; static const char *const *const units_str[] = { [STRING_UNITS_10] = units_10, [STRING_UNITS_2] = units_2, }; static const unsigned int divisor[] = { [STRING_UNITS_10] = 1000, [STRING_UNITS_2] = 1024, }; static const unsigned int rounding[] = { 500, 50, 5 }; int i = 0, j; u32 remainder = 0, sf_cap; char tmp[12]; const char *unit; tmp[0] = '\0'; if (blk_size == 0) size = 0; if (size == 0) goto out; /* This is Napier's algorithm. Reduce the original block size to * * coefficient * divisor[units_base]^i * * we do the reduction so both coefficients are just under 32 bits so * that multiplying them together won't overflow 64 bits and we keep * as much precision as possible in the numbers. * * Note: it's safe to throw away the remainders here because all the * precision is in the coefficients. */ while (blk_size >> 32) { do_div(blk_size, divisor[units_base]); i++; } while (size >> 32) { do_div(size, divisor[units_base]); i++; } /* now perform the actual multiplication keeping i as the sum of the * two logarithms */ size *= blk_size; /* and logarithmically reduce it until it's just under the divisor */ while (size >= divisor[units_base]) { remainder = do_div(size, divisor[units_base]); i++; } /* work out in j how many digits of precision we need from the * remainder */ sf_cap = size; for (j = 0; sf_cap*10 < 1000; j++) sf_cap *= 10; if (units_base == STRING_UNITS_2) { /* express the remainder as a decimal. It's currently the * numerator of a fraction whose denominator is * divisor[units_base], which is 1 << 10 for STRING_UNITS_2 */ remainder *= 1000; remainder >>= 10; } /* add a 5 to the digit below what will be printed to ensure * an arithmetical round up and carry it through to size */ remainder += rounding[j]; if (remainder >= 1000) { remainder -= 1000; size += 1; } if (j) { snprintf(tmp, sizeof(tmp), ".%03u", remainder); tmp[j+1] = '\0'; } out: if (i >= ARRAY_SIZE(units_2)) unit = "UNK"; else unit = units_str[units_base][i]; return snprintf(buf, len, "%u%s%s%s%s", (u32)size, tmp, (units & STRING_UNITS_NO_SPACE) ? "" : " ", unit, (units & STRING_UNITS_NO_BYTES) ? "" : "B"); } EXPORT_SYMBOL(string_get_size); /** * parse_int_array_user - Split string into a sequence of integers * @from: The user space buffer to read from * @count: The maximum number of bytes to read * @array: Returned pointer to sequence of integers * * On success @array is allocated and initialized with a sequence of * integers extracted from the @from plus an additional element that * begins the sequence and specifies the integers count. * * Caller takes responsibility for freeing @array when it is no longer * needed. */ int parse_int_array_user(const char __user *from, size_t count, int **array) { int *ints, nints; char *buf; int ret = 0; buf = memdup_user_nul(from, count); if (IS_ERR(buf)) return PTR_ERR(buf); get_options(buf, 0, &nints); if (!nints) { ret = -ENOENT; goto free_buf; } ints = kcalloc(nints + 1, sizeof(*ints), GFP_KERNEL); if (!ints) { ret = -ENOMEM; goto free_buf; } get_options(buf, nints + 1, ints); *array = ints; free_buf: kfree(buf); return ret; } EXPORT_SYMBOL(parse_int_array_user); static bool unescape_space(char **src, char **dst) { char *p = *dst, *q = *src; switch (*q) { case 'n': *p = '\n'; break; case 'r': *p = '\r'; break; case 't': *p = '\t'; break; case 'v': *p = '\v'; break; case 'f': *p = '\f'; break; default: return false; } *dst += 1; *src += 1; return true; } static bool unescape_octal(char **src, char **dst) { char *p = *dst, *q = *src; u8 num; if (isodigit(*q) == 0) return false; num = (*q++) & 7; while (num < 32 && isodigit(*q) && (q - *src < 3)) { num <<= 3; num += (*q++) & 7; } *p = num; *dst += 1; *src = q; return true; } static bool unescape_hex(char **src, char **dst) { char *p = *dst, *q = *src; int digit; u8 num; if (*q++ != 'x') return false; num = digit = hex_to_bin(*q++); if (digit < 0) return false; digit = hex_to_bin(*q); if (digit >= 0) { q++; num = (num << 4) | digit; } *p = num; *dst += 1; *src = q; return true; } static bool unescape_special(char **src, char **dst) { char *p = *dst, *q = *src; switch (*q) { case '\"': *p = '\"'; break; case '\\': *p = '\\'; break; case 'a': *p = '\a'; break; case 'e': *p = '\e'; break; default: return false; } *dst += 1; *src += 1; return true; } /** * string_unescape - unquote characters in the given string * @src: source buffer (escaped) * @dst: destination buffer (unescaped) * @size: size of the destination buffer (0 to unlimit) * @flags: combination of the flags. * * Description: * The function unquotes characters in the given string. * * Because the size of the output will be the same as or less than the size of * the input, the transformation may be performed in place. * * Caller must provide valid source and destination pointers. Be aware that * destination buffer will always be NULL-terminated. Source string must be * NULL-terminated as well. The supported flags are:: * * UNESCAPE_SPACE: * '\f' - form feed * '\n' - new line * '\r' - carriage return * '\t' - horizontal tab * '\v' - vertical tab * UNESCAPE_OCTAL: * '\NNN' - byte with octal value NNN (1 to 3 digits) * UNESCAPE_HEX: * '\xHH' - byte with hexadecimal value HH (1 to 2 digits) * UNESCAPE_SPECIAL: * '\"' - double quote * '\\' - backslash * '\a' - alert (BEL) * '\e' - escape * UNESCAPE_ANY: * all previous together * * Return: * The amount of the characters processed to the destination buffer excluding * trailing '\0' is returned. */ int string_unescape(char *src, char *dst, size_t size, unsigned int flags) { char *out = dst; if (!size) size = SIZE_MAX; while (*src && --size) { if (src[0] == '\\' && src[1] != '\0' && size > 1) { src++; size--; if (flags & UNESCAPE_SPACE && unescape_space(&src, &out)) continue; if (flags & UNESCAPE_OCTAL && unescape_octal(&src, &out)) continue; if (flags & UNESCAPE_HEX && unescape_hex(&src, &out)) continue; if (flags & UNESCAPE_SPECIAL && unescape_special(&src, &out)) continue; *out++ = '\\'; } *out++ = *src++; } *out = '\0'; return out - dst; } EXPORT_SYMBOL(string_unescape); static bool escape_passthrough(unsigned char c, char **dst, char *end) { char *out = *dst; if (out < end) *out = c; *dst = out + 1; return true; } static bool escape_space(unsigned char c, char **dst, char *end) { char *out = *dst; unsigned char to; switch (c) { case '\n': to = 'n'; break; case '\r': to = 'r'; break; case '\t': to = 't'; break; case '\v': to = 'v'; break; case '\f': to = 'f'; break; default: return false; } if (out < end) *out = '\\'; ++out; if (out < end) *out = to; ++out; *dst = out; return true; } static bool escape_special(unsigned char c, char **dst, char *end) { char *out = *dst; unsigned char to; switch (c) { case '\\': to = '\\'; break; case '\a': to = 'a'; break; case '\e': to = 'e'; break; case '"': to = '"'; break; default: return false; } if (out < end) *out = '\\'; ++out; if (out < end) *out = to; ++out; *dst = out; return true; } static bool escape_null(unsigned char c, char **dst, char *end) { char *out = *dst; if (c) return false; if (out < end) *out = '\\'; ++out; if (out < end) *out = '0'; ++out; *dst = out; return true; } static bool escape_octal(unsigned char c, char **dst, char *end) { char *out = *dst; if (out < end) *out = '\\'; ++out; if (out < end) *out = ((c >> 6) & 0x07) + '0'; ++out; if (out < end) *out = ((c >> 3) & 0x07) + '0'; ++out; if (out < end) *out = ((c >> 0) & 0x07) + '0'; ++out; *dst = out; return true; } static bool escape_hex(unsigned char c, char **dst, char *end) { char *out = *dst; if (out < end) *out = '\\'; ++out; if (out < end) *out = 'x'; ++out; if (out < end) *out = hex_asc_hi(c); ++out; if (out < end) *out = hex_asc_lo(c); ++out; *dst = out; return true; } /** * string_escape_mem - quote characters in the given memory buffer * @src: source buffer (unescaped) * @isz: source buffer size * @dst: destination buffer (escaped) * @osz: destination buffer size * @flags: combination of the flags * @only: NULL-terminated string containing characters used to limit * the selected escape class. If characters are included in @only * that would not normally be escaped by the classes selected * in @flags, they will be copied to @dst unescaped. * * Description: * The process of escaping byte buffer includes several parts. They are applied * in the following sequence. * * 1. The character is not matched to the one from @only string and thus * must go as-is to the output. * 2. The character is matched to the printable and ASCII classes, if asked, * and in case of match it passes through to the output. * 3. The character is matched to the printable or ASCII class, if asked, * and in case of match it passes through to the output. * 4. The character is checked if it falls into the class given by @flags. * %ESCAPE_OCTAL and %ESCAPE_HEX are going last since they cover any * character. Note that they actually can't go together, otherwise * %ESCAPE_HEX will be ignored. * * Caller must provide valid source and destination pointers. Be aware that * destination buffer will not be NULL-terminated, thus caller have to append * it if needs. The supported flags are:: * * %ESCAPE_SPACE: (special white space, not space itself) * '\f' - form feed * '\n' - new line * '\r' - carriage return * '\t' - horizontal tab * '\v' - vertical tab * %ESCAPE_SPECIAL: * '\"' - double quote * '\\' - backslash * '\a' - alert (BEL) * '\e' - escape * %ESCAPE_NULL: * '\0' - null * %ESCAPE_OCTAL: * '\NNN' - byte with octal value NNN (3 digits) * %ESCAPE_ANY: * all previous together * %ESCAPE_NP: * escape only non-printable characters, checked by isprint() * %ESCAPE_ANY_NP: * all previous together * %ESCAPE_HEX: * '\xHH' - byte with hexadecimal value HH (2 digits) * %ESCAPE_NA: * escape only non-ascii characters, checked by isascii() * %ESCAPE_NAP: * escape only non-printable or non-ascii characters * %ESCAPE_APPEND: * append characters from @only to be escaped by the given classes * * %ESCAPE_APPEND would help to pass additional characters to the escaped, when * one of %ESCAPE_NP, %ESCAPE_NA, or %ESCAPE_NAP is provided. * * One notable caveat, the %ESCAPE_NAP, %ESCAPE_NP and %ESCAPE_NA have the * higher priority than the rest of the flags (%ESCAPE_NAP is the highest). * It doesn't make much sense to use either of them without %ESCAPE_OCTAL * or %ESCAPE_HEX, because they cover most of the other character classes. * %ESCAPE_NAP can utilize %ESCAPE_SPACE or %ESCAPE_SPECIAL in addition to * the above. * * Return: * The total size of the escaped output that would be generated for * the given input and flags. To check whether the output was * truncated, compare the return value to osz. There is room left in * dst for a '\0' terminator if and only if ret < osz. */ int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz, unsigned int flags, const char *only) { char *p = dst; char *end = p + osz; bool is_dict = only && *only; bool is_append = flags & ESCAPE_APPEND; while (isz--) { unsigned char c = *src++; bool in_dict = is_dict && strchr(only, c); /* * Apply rules in the following sequence: * - the @only string is supplied and does not contain a * character under question * - the character is printable and ASCII, when @flags has * %ESCAPE_NAP bit set * - the character is printable, when @flags has * %ESCAPE_NP bit set * - the character is ASCII, when @flags has * %ESCAPE_NA bit set * - the character doesn't fall into a class of symbols * defined by given @flags * In these cases we just pass through a character to the * output buffer. * * When %ESCAPE_APPEND is passed, the characters from @only * have been excluded from the %ESCAPE_NAP, %ESCAPE_NP, and * %ESCAPE_NA cases. */ if (!(is_append || in_dict) && is_dict && escape_passthrough(c, &p, end)) continue; if (!(is_append && in_dict) && isascii(c) && isprint(c) && flags & ESCAPE_NAP && escape_passthrough(c, &p, end)) continue; if (!(is_append && in_dict) && isprint(c) && flags & ESCAPE_NP && escape_passthrough(c, &p, end)) continue; if (!(is_append && in_dict) && isascii(c) && flags & ESCAPE_NA && escape_passthrough(c, &p, end)) continue; if (flags & ESCAPE_SPACE && escape_space(c, &p, end)) continue; if (flags & ESCAPE_SPECIAL && escape_special(c, &p, end)) continue; if (flags & ESCAPE_NULL && escape_null(c, &p, end)) continue; /* ESCAPE_OCTAL and ESCAPE_HEX always go last */ if (flags & ESCAPE_OCTAL && escape_octal(c, &p, end)) continue; if (flags & ESCAPE_HEX && escape_hex(c, &p, end)) continue; escape_passthrough(c, &p, end); } return p - dst; } EXPORT_SYMBOL(string_escape_mem); /* * Return an allocated string that has been escaped of special characters * and double quotes, making it safe to log in quotes. */ char *kstrdup_quotable(const char *src, gfp_t gfp) { size_t slen, dlen; char *dst; const int flags = ESCAPE_HEX; const char esc[] = "\f\n\r\t\v\a\e\\\""; if (!src) return NULL; slen = strlen(src); dlen = string_escape_mem(src, slen, NULL, 0, flags, esc); dst = kmalloc(dlen + 1, gfp); if (!dst) return NULL; WARN_ON(string_escape_mem(src, slen, dst, dlen, flags, esc) != dlen); dst[dlen] = '\0'; return dst; } EXPORT_SYMBOL_GPL(kstrdup_quotable); /* * Returns allocated NULL-terminated string containing process * command line, with inter-argument NULLs replaced with spaces, * and other special characters escaped. */ char *kstrdup_quotable_cmdline(struct task_struct *task, gfp_t gfp) { char *buffer, *quoted; int i, res; buffer = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!buffer) return NULL; res = get_cmdline(task, buffer, PAGE_SIZE - 1); buffer[res] = '\0'; /* Collapse trailing NULLs, leave res pointing to last non-NULL. */ while (--res >= 0 && buffer[res] == '\0') ; /* Replace inter-argument NULLs. */ for (i = 0; i <= res; i++) if (buffer[i] == '\0') buffer[i] = ' '; /* Make sure result is printable. */ quoted = kstrdup_quotable(buffer, gfp); kfree(buffer); return quoted; } EXPORT_SYMBOL_GPL(kstrdup_quotable_cmdline); /* * Returns allocated NULL-terminated string containing pathname, * with special characters escaped, able to be safely logged. If * there is an error, the leading character will be "<". */ char *kstrdup_quotable_file(struct file *file, gfp_t gfp) { char *temp, *pathname; if (!file) return kstrdup("<unknown>", gfp); /* We add 11 spaces for ' (deleted)' to be appended */ temp = kmalloc(PATH_MAX + 11, GFP_KERNEL); if (!temp) return kstrdup("<no_memory>", gfp); pathname = file_path(file, temp, PATH_MAX + 11); if (IS_ERR(pathname)) pathname = kstrdup("<too_long>", gfp); else pathname = kstrdup_quotable(pathname, gfp); kfree(temp); return pathname; } EXPORT_SYMBOL_GPL(kstrdup_quotable_file); /* * Returns duplicate string in which the @old characters are replaced by @new. */ char *kstrdup_and_replace(const char *src, char old, char new, gfp_t gfp) { char *dst; dst = kstrdup(src, gfp); if (!dst) return NULL; return strreplace(dst, old, new); } EXPORT_SYMBOL_GPL(kstrdup_and_replace); /** * kasprintf_strarray - allocate and fill array of sequential strings * @gfp: flags for the slab allocator * @prefix: prefix to be used * @n: amount of lines to be allocated and filled * * Allocates and fills @n strings using pattern "%s-%zu", where prefix * is provided by caller. The caller is responsible to free them with * kfree_strarray() after use. * * Returns array of strings or NULL when memory can't be allocated. */ char **kasprintf_strarray(gfp_t gfp, const char *prefix, size_t n) { char **names; size_t i; names = kcalloc(n + 1, sizeof(char *), gfp); if (!names) return NULL; for (i = 0; i < n; i++) { names[i] = kasprintf(gfp, "%s-%zu", prefix, i); if (!names[i]) { kfree_strarray(names, i); return NULL; } } return names; } EXPORT_SYMBOL_GPL(kasprintf_strarray); /** * kfree_strarray - free a number of dynamically allocated strings contained * in an array and the array itself * * @array: Dynamically allocated array of strings to free. * @n: Number of strings (starting from the beginning of the array) to free. * * Passing a non-NULL @array and @n == 0 as well as NULL @array are valid * use-cases. If @array is NULL, the function does nothing. */ void kfree_strarray(char **array, size_t n) { unsigned int i; if (!array) return; for (i = 0; i < n; i++) kfree(array[i]); kfree(array); } EXPORT_SYMBOL_GPL(kfree_strarray); struct strarray { char **array; size_t n; }; static void devm_kfree_strarray(struct device *dev, void *res) { struct strarray *array = res; kfree_strarray(array->array, array->n); } char **devm_kasprintf_strarray(struct device *dev, const char *prefix, size_t n) { struct strarray *ptr; ptr = devres_alloc(devm_kfree_strarray, sizeof(*ptr), GFP_KERNEL); if (!ptr) return ERR_PTR(-ENOMEM); ptr->array = kasprintf_strarray(GFP_KERNEL, prefix, n); if (!ptr->array) { devres_free(ptr); return ERR_PTR(-ENOMEM); } ptr->n = n; devres_add(dev, ptr); return ptr->array; } EXPORT_SYMBOL_GPL(devm_kasprintf_strarray); /** * skip_spaces - Removes leading whitespace from @str. * @str: The string to be stripped. * * Returns a pointer to the first non-whitespace character in @str. */ char *skip_spaces(const char *str) { while (isspace(*str)) ++str; return (char *)str; } EXPORT_SYMBOL(skip_spaces); /** * strim - Removes leading and trailing whitespace from @s. * @s: The string to be stripped. * * Note that the first trailing whitespace is replaced with a %NUL-terminator * in the given string @s. Returns a pointer to the first non-whitespace * character in @s. */ char *strim(char *s) { size_t size; char *end; size = strlen(s); if (!size) return s; end = s + size - 1; while (end >= s && isspace(*end)) end--; *(end + 1) = '\0'; return skip_spaces(s); } EXPORT_SYMBOL(strim); /** * sysfs_streq - return true if strings are equal, modulo trailing newline * @s1: one string * @s2: another string * * This routine returns true iff two strings are equal, treating both * NUL and newline-then-NUL as equivalent string terminations. It's * geared for use with sysfs input strings, which generally terminate * with newlines but are compared against values without newlines. */ bool sysfs_streq(const char *s1, const char *s2) { while (*s1 && *s1 == *s2) { s1++; s2++; } if (*s1 == *s2) return true; if (!*s1 && *s2 == '\n' && !s2[1]) return true; if (*s1 == '\n' && !s1[1] && !*s2) return true; return false; } EXPORT_SYMBOL(sysfs_streq); /** * match_string - matches given string in an array * @array: array of strings * @n: number of strings in the array or -1 for NULL terminated arrays * @string: string to match with * * This routine will look for a string in an array of strings up to the * n-th element in the array or until the first NULL element. * * Historically the value of -1 for @n, was used to search in arrays that * are NULL terminated. However, the function does not make a distinction * when finishing the search: either @n elements have been compared OR * the first NULL element was found. * * Return: * index of a @string in the @array if matches, or %-EINVAL otherwise. */ int match_string(const char * const *array, size_t n, const char *string) { int index; const char *item; for (index = 0; index < n; index++) { item = array[index]; if (!item) break; if (!strcmp(item, string)) return index; } return -EINVAL; } EXPORT_SYMBOL(match_string); /** * __sysfs_match_string - matches given string in an array * @array: array of strings * @n: number of strings in the array or -1 for NULL terminated arrays * @str: string to match with * * Returns index of @str in the @array or -EINVAL, just like match_string(). * Uses sysfs_streq instead of strcmp for matching. * * This routine will look for a string in an array of strings up to the * n-th element in the array or until the first NULL element. * * Historically the value of -1 for @n, was used to search in arrays that * are NULL terminated. However, the function does not make a distinction * when finishing the search: either @n elements have been compared OR * the first NULL element was found. */ int __sysfs_match_string(const char * const *array, size_t n, const char *str) { const char *item; int index; for (index = 0; index < n; index++) { item = array[index]; if (!item) break; if (sysfs_streq(item, str)) return index; } return -EINVAL; } EXPORT_SYMBOL(__sysfs_match_string); /** * strreplace - Replace all occurrences of character in string. * @str: The string to operate on. * @old: The character being replaced. * @new: The character @old is replaced with. * * Replaces the each @old character with a @new one in the given string @str. * * Return: pointer to the string @str itself. */ char *strreplace(char *str, char old, char new) { char *s = str; for (; *s; ++s) if (*s == old) *s = new; return str; } EXPORT_SYMBOL(strreplace); /** * memcpy_and_pad - Copy one buffer to another with padding * @dest: Where to copy to * @dest_len: The destination buffer size * @src: Where to copy from * @count: The number of bytes to copy * @pad: Character to use for padding if space is left in destination. */ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, int pad) { if (dest_len > count) { memcpy(dest, src, count); memset(dest + count, pad, dest_len - count); } else { memcpy(dest, src, dest_len); } } EXPORT_SYMBOL(memcpy_and_pad); #ifdef CONFIG_FORTIFY_SOURCE /* These are placeholders for fortify compile-time warnings. */ void __read_overflow2_field(size_t avail, size_t wanted) { } EXPORT_SYMBOL(__read_overflow2_field); void __write_overflow_field(size_t avail, size_t wanted) { } EXPORT_SYMBOL(__write_overflow_field); static const char * const fortify_func_name[] = { #define MAKE_FORTIFY_FUNC_NAME(func) [MAKE_FORTIFY_FUNC(func)] = #func EACH_FORTIFY_FUNC(MAKE_FORTIFY_FUNC_NAME) #undef MAKE_FORTIFY_FUNC_NAME }; void __fortify_report(const u8 reason, const size_t avail, const size_t size) { const u8 func = FORTIFY_REASON_FUNC(reason); const bool write = FORTIFY_REASON_DIR(reason); const char *name; name = fortify_func_name[umin(func, FORTIFY_FUNC_UNKNOWN)]; WARN(1, "%s: detected buffer overflow: %zu byte %s of buffer size %zu\n", name, size, str_read_write(!write), avail); } EXPORT_SYMBOL(__fortify_report); void __fortify_panic(const u8 reason, const size_t avail, const size_t size) { __fortify_report(reason, avail, size); BUG(); } EXPORT_SYMBOL(__fortify_panic); #endif /* CONFIG_FORTIFY_SOURCE */ |
| 2 2 2 1 1 1 1 1 2 2 1 1 1 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * HID driver for Valve Steam Controller * * Copyright (c) 2018 Rodrigo Rivas Costa <rodrigorivascosta@gmail.com> * Copyright (c) 2022 Valve Software * * Supports both the wired and wireless interfaces. * * This controller has a builtin emulation of mouse and keyboard: the right pad * can be used as a mouse, the shoulder buttons are mouse buttons, A and B * buttons are ENTER and ESCAPE, and so on. This is implemented as additional * HID interfaces. * * This is known as the "lizard mode", because apparently lizards like to use * the computer from the coach, without a proper mouse and keyboard. * * This driver will disable the lizard mode when the input device is opened * and re-enable it when the input device is closed, so as not to break user * mode behaviour. The lizard_mode parameter can be used to change that. * * There are a few user space applications (notably Steam Client) that use * the hidraw interface directly to create input devices (XTest, uinput...). * In order to avoid breaking them this driver creates a layered hidraw device, * so it can detect when the client is running and then: * - it will not send any command to the controller. * - this input device will be removed, to avoid double input of the same * user action. * When the client is closed, this input device will be created again. * * For additional functions, such as changing the right-pad margin or switching * the led, you can use the user-space tool at: * * https://github.com/rodrigorc/steamctrl */ #include <linux/device.h> #include <linux/input.h> #include <linux/hid.h> #include <linux/module.h> #include <linux/workqueue.h> #include <linux/mutex.h> #include <linux/rcupdate.h> #include <linux/delay.h> #include <linux/power_supply.h> #include "hid-ids.h" MODULE_DESCRIPTION("HID driver for Valve Steam Controller"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Rodrigo Rivas Costa <rodrigorivascosta@gmail.com>"); static bool lizard_mode = true; static DEFINE_MUTEX(steam_devices_lock); static LIST_HEAD(steam_devices); #define STEAM_QUIRK_WIRELESS BIT(0) #define STEAM_QUIRK_DECK BIT(1) /* Touch pads are 40 mm in diameter and 65535 units */ #define STEAM_PAD_RESOLUTION 1638 /* Trigger runs are about 5 mm and 256 units */ #define STEAM_TRIGGER_RESOLUTION 51 /* Joystick runs are about 5 mm and 256 units */ #define STEAM_JOYSTICK_RESOLUTION 51 /* Trigger runs are about 6 mm and 32768 units */ #define STEAM_DECK_TRIGGER_RESOLUTION 5461 /* Joystick runs are about 5 mm and 32768 units */ #define STEAM_DECK_JOYSTICK_RESOLUTION 6553 /* Accelerometer has 16 bit resolution and a range of +/- 2g */ #define STEAM_DECK_ACCEL_RES_PER_G 16384 #define STEAM_DECK_ACCEL_RANGE 32768 #define STEAM_DECK_ACCEL_FUZZ 32 /* Gyroscope has 16 bit resolution and a range of +/- 2000 dps */ #define STEAM_DECK_GYRO_RES_PER_DPS 16 #define STEAM_DECK_GYRO_RANGE 32768 #define STEAM_DECK_GYRO_FUZZ 1 #define STEAM_PAD_FUZZ 256 /* * Commands that can be sent in a feature report. * Thanks to Valve and SDL for the names. */ enum { ID_SET_DIGITAL_MAPPINGS = 0x80, ID_CLEAR_DIGITAL_MAPPINGS = 0x81, ID_GET_DIGITAL_MAPPINGS = 0x82, ID_GET_ATTRIBUTES_VALUES = 0x83, ID_GET_ATTRIBUTE_LABEL = 0x84, ID_SET_DEFAULT_DIGITAL_MAPPINGS = 0x85, ID_FACTORY_RESET = 0x86, ID_SET_SETTINGS_VALUES = 0x87, ID_CLEAR_SETTINGS_VALUES = 0x88, ID_GET_SETTINGS_VALUES = 0x89, ID_GET_SETTING_LABEL = 0x8A, ID_GET_SETTINGS_MAXS = 0x8B, ID_GET_SETTINGS_DEFAULTS = 0x8C, ID_SET_CONTROLLER_MODE = 0x8D, ID_LOAD_DEFAULT_SETTINGS = 0x8E, ID_TRIGGER_HAPTIC_PULSE = 0x8F, ID_TURN_OFF_CONTROLLER = 0x9F, ID_GET_DEVICE_INFO = 0xA1, ID_CALIBRATE_TRACKPADS = 0xA7, ID_RESERVED_0 = 0xA8, ID_SET_SERIAL_NUMBER = 0xA9, ID_GET_TRACKPAD_CALIBRATION = 0xAA, ID_GET_TRACKPAD_FACTORY_CALIBRATION = 0xAB, ID_GET_TRACKPAD_RAW_DATA = 0xAC, ID_ENABLE_PAIRING = 0xAD, ID_GET_STRING_ATTRIBUTE = 0xAE, ID_RADIO_ERASE_RECORDS = 0xAF, ID_RADIO_WRITE_RECORD = 0xB0, ID_SET_DONGLE_SETTING = 0xB1, ID_DONGLE_DISCONNECT_DEVICE = 0xB2, ID_DONGLE_COMMIT_DEVICE = 0xB3, ID_DONGLE_GET_WIRELESS_STATE = 0xB4, ID_CALIBRATE_GYRO = 0xB5, ID_PLAY_AUDIO = 0xB6, ID_AUDIO_UPDATE_START = 0xB7, ID_AUDIO_UPDATE_DATA = 0xB8, ID_AUDIO_UPDATE_COMPLETE = 0xB9, ID_GET_CHIPID = 0xBA, ID_CALIBRATE_JOYSTICK = 0xBF, ID_CALIBRATE_ANALOG_TRIGGERS = 0xC0, ID_SET_AUDIO_MAPPING = 0xC1, ID_CHECK_GYRO_FW_LOAD = 0xC2, ID_CALIBRATE_ANALOG = 0xC3, ID_DONGLE_GET_CONNECTED_SLOTS = 0xC4, ID_RESET_IMU = 0xCE, ID_TRIGGER_HAPTIC_CMD = 0xEA, ID_TRIGGER_RUMBLE_CMD = 0xEB, }; /* Settings IDs */ enum { /* 0 */ SETTING_MOUSE_SENSITIVITY, SETTING_MOUSE_ACCELERATION, SETTING_TRACKBALL_ROTATION_ANGLE, SETTING_HAPTIC_INTENSITY_UNUSED, SETTING_LEFT_GAMEPAD_STICK_ENABLED, SETTING_RIGHT_GAMEPAD_STICK_ENABLED, SETTING_USB_DEBUG_MODE, SETTING_LEFT_TRACKPAD_MODE, SETTING_RIGHT_TRACKPAD_MODE, SETTING_MOUSE_POINTER_ENABLED, /* 10 */ SETTING_DPAD_DEADZONE, SETTING_MINIMUM_MOMENTUM_VEL, SETTING_MOMENTUM_DECAY_AMMOUNT, SETTING_TRACKPAD_RELATIVE_MODE_TICKS_PER_PIXEL, SETTING_HAPTIC_INCREMENT, SETTING_DPAD_ANGLE_SIN, SETTING_DPAD_ANGLE_COS, SETTING_MOMENTUM_VERTICAL_DIVISOR, SETTING_MOMENTUM_MAXIMUM_VELOCITY, SETTING_TRACKPAD_Z_ON, /* 20 */ SETTING_TRACKPAD_Z_OFF, SETTING_SENSITIVY_SCALE_AMMOUNT, SETTING_LEFT_TRACKPAD_SECONDARY_MODE, SETTING_RIGHT_TRACKPAD_SECONDARY_MODE, SETTING_SMOOTH_ABSOLUTE_MOUSE, SETTING_STEAMBUTTON_POWEROFF_TIME, SETTING_UNUSED_1, SETTING_TRACKPAD_OUTER_RADIUS, SETTING_TRACKPAD_Z_ON_LEFT, SETTING_TRACKPAD_Z_OFF_LEFT, /* 30 */ SETTING_TRACKPAD_OUTER_SPIN_VEL, SETTING_TRACKPAD_OUTER_SPIN_RADIUS, SETTING_TRACKPAD_OUTER_SPIN_HORIZONTAL_ONLY, SETTING_TRACKPAD_RELATIVE_MODE_DEADZONE, SETTING_TRACKPAD_RELATIVE_MODE_MAX_VEL, SETTING_TRACKPAD_RELATIVE_MODE_INVERT_Y, SETTING_TRACKPAD_DOUBLE_TAP_BEEP_ENABLED, SETTING_TRACKPAD_DOUBLE_TAP_BEEP_PERIOD, SETTING_TRACKPAD_DOUBLE_TAP_BEEP_COUNT, SETTING_TRACKPAD_OUTER_RADIUS_RELEASE_ON_TRANSITION, /* 40 */ SETTING_RADIAL_MODE_ANGLE, SETTING_HAPTIC_INTENSITY_MOUSE_MODE, SETTING_LEFT_DPAD_REQUIRES_CLICK, SETTING_RIGHT_DPAD_REQUIRES_CLICK, SETTING_LED_BASELINE_BRIGHTNESS, SETTING_LED_USER_BRIGHTNESS, SETTING_ENABLE_RAW_JOYSTICK, SETTING_ENABLE_FAST_SCAN, SETTING_IMU_MODE, SETTING_WIRELESS_PACKET_VERSION, /* 50 */ SETTING_SLEEP_INACTIVITY_TIMEOUT, SETTING_TRACKPAD_NOISE_THRESHOLD, SETTING_LEFT_TRACKPAD_CLICK_PRESSURE, SETTING_RIGHT_TRACKPAD_CLICK_PRESSURE, SETTING_LEFT_BUMPER_CLICK_PRESSURE, SETTING_RIGHT_BUMPER_CLICK_PRESSURE, SETTING_LEFT_GRIP_CLICK_PRESSURE, SETTING_RIGHT_GRIP_CLICK_PRESSURE, SETTING_LEFT_GRIP2_CLICK_PRESSURE, SETTING_RIGHT_GRIP2_CLICK_PRESSURE, /* 60 */ SETTING_PRESSURE_MODE, SETTING_CONTROLLER_TEST_MODE, SETTING_TRIGGER_MODE, SETTING_TRACKPAD_Z_THRESHOLD, SETTING_FRAME_RATE, SETTING_TRACKPAD_FILT_CTRL, SETTING_TRACKPAD_CLIP, SETTING_DEBUG_OUTPUT_SELECT, SETTING_TRIGGER_THRESHOLD_PERCENT, SETTING_TRACKPAD_FREQUENCY_HOPPING, /* 70 */ SETTING_HAPTICS_ENABLED, SETTING_STEAM_WATCHDOG_ENABLE, SETTING_TIMP_TOUCH_THRESHOLD_ON, SETTING_TIMP_TOUCH_THRESHOLD_OFF, SETTING_FREQ_HOPPING, SETTING_TEST_CONTROL, SETTING_HAPTIC_MASTER_GAIN_DB, SETTING_THUMB_TOUCH_THRESH, SETTING_DEVICE_POWER_STATUS, SETTING_HAPTIC_INTENSITY, /* 80 */ SETTING_STABILIZER_ENABLED, SETTING_TIMP_MODE_MTE, }; /* Input report identifiers */ enum { ID_CONTROLLER_STATE = 1, ID_CONTROLLER_DEBUG = 2, ID_CONTROLLER_WIRELESS = 3, ID_CONTROLLER_STATUS = 4, ID_CONTROLLER_DEBUG2 = 5, ID_CONTROLLER_SECONDARY_STATE = 6, ID_CONTROLLER_BLE_STATE = 7, ID_CONTROLLER_DECK_STATE = 9 }; /* String attribute identifiers */ enum { ATTRIB_STR_BOARD_SERIAL, ATTRIB_STR_UNIT_SERIAL, }; /* Values for GYRO_MODE (bitmask) */ enum { SETTING_GYRO_MODE_OFF = 0, SETTING_GYRO_MODE_STEERING = BIT(0), SETTING_GYRO_MODE_TILT = BIT(1), SETTING_GYRO_MODE_SEND_ORIENTATION = BIT(2), SETTING_GYRO_MODE_SEND_RAW_ACCEL = BIT(3), SETTING_GYRO_MODE_SEND_RAW_GYRO = BIT(4), }; /* Trackpad modes */ enum { TRACKPAD_ABSOLUTE_MOUSE, TRACKPAD_RELATIVE_MOUSE, TRACKPAD_DPAD_FOUR_WAY_DISCRETE, TRACKPAD_DPAD_FOUR_WAY_OVERLAP, TRACKPAD_DPAD_EIGHT_WAY, TRACKPAD_RADIAL_MODE, TRACKPAD_ABSOLUTE_DPAD, TRACKPAD_NONE, TRACKPAD_GESTURE_KEYBOARD, }; /* Pad identifiers for the deck */ #define STEAM_PAD_LEFT 0 #define STEAM_PAD_RIGHT 1 #define STEAM_PAD_BOTH 2 /* Other random constants */ #define STEAM_SERIAL_LEN 0x15 struct steam_device { struct list_head list; spinlock_t lock; struct hid_device *hdev, *client_hdev; struct mutex report_mutex; unsigned long client_opened; struct input_dev __rcu *input; struct input_dev __rcu *sensors; unsigned long quirks; struct work_struct work_connect; bool connected; char serial_no[STEAM_SERIAL_LEN + 1]; struct power_supply_desc battery_desc; struct power_supply __rcu *battery; u8 battery_charge; u16 voltage; struct delayed_work mode_switch; bool did_mode_switch; bool gamepad_mode; struct work_struct rumble_work; u16 rumble_left; u16 rumble_right; unsigned int sensor_timestamp_us; }; static int steam_recv_report(struct steam_device *steam, u8 *data, int size) { struct hid_report *r; u8 *buf; int ret; r = steam->hdev->report_enum[HID_FEATURE_REPORT].report_id_hash[0]; if (!r) { hid_err(steam->hdev, "No HID_FEATURE_REPORT submitted - nothing to read\n"); return -EINVAL; } if (hid_report_len(r) < 64) return -EINVAL; buf = hid_alloc_report_buf(r, GFP_KERNEL); if (!buf) return -ENOMEM; /* * The report ID is always 0, so strip the first byte from the output. * hid_report_len() is not counting the report ID, so +1 to the length * or else we get a EOVERFLOW. We are safe from a buffer overflow * because hid_alloc_report_buf() allocates +7 bytes. */ ret = hid_hw_raw_request(steam->hdev, 0x00, buf, hid_report_len(r) + 1, HID_FEATURE_REPORT, HID_REQ_GET_REPORT); if (ret > 0) memcpy(data, buf + 1, min(size, ret - 1)); kfree(buf); return ret; } static int steam_send_report(struct steam_device *steam, u8 *cmd, int size) { struct hid_report *r; u8 *buf; unsigned int retries = 50; int ret; r = steam->hdev->report_enum[HID_FEATURE_REPORT].report_id_hash[0]; if (!r) { hid_err(steam->hdev, "No HID_FEATURE_REPORT submitted - nothing to read\n"); return -EINVAL; } if (hid_report_len(r) < 64) return -EINVAL; buf = hid_alloc_report_buf(r, GFP_KERNEL); if (!buf) return -ENOMEM; /* The report ID is always 0 */ memcpy(buf + 1, cmd, size); /* * Sometimes the wireless controller fails with EPIPE * when sending a feature report. * Doing a HID_REQ_GET_REPORT and waiting for a while * seems to fix that. */ do { ret = hid_hw_raw_request(steam->hdev, 0, buf, max(size, 64) + 1, HID_FEATURE_REPORT, HID_REQ_SET_REPORT); if (ret != -EPIPE) break; msleep(20); } while (--retries); kfree(buf); if (ret < 0) hid_err(steam->hdev, "%s: error %d (%*ph)\n", __func__, ret, size, cmd); return ret; } static inline int steam_send_report_byte(struct steam_device *steam, u8 cmd) { return steam_send_report(steam, &cmd, 1); } static int steam_write_settings(struct steam_device *steam, /* u8 reg, u16 val */...) { /* Send: 0x87 len (reg valLo valHi)* */ u8 reg; u16 val; u8 cmd[64] = {ID_SET_SETTINGS_VALUES, 0x00}; int ret; va_list args; va_start(args, steam); for (;;) { reg = va_arg(args, int); if (reg == 0) break; val = va_arg(args, int); cmd[cmd[1] + 2] = reg; cmd[cmd[1] + 3] = val & 0xff; cmd[cmd[1] + 4] = val >> 8; cmd[1] += 3; } va_end(args); ret = steam_send_report(steam, cmd, 2 + cmd[1]); if (ret < 0) return ret; /* * Sometimes a lingering report for this command can * get read back instead of the last set report if * this isn't explicitly queried */ return steam_recv_report(steam, cmd, 2 + cmd[1]); } static int steam_get_serial(struct steam_device *steam) { /* * Send: 0xae 0x15 0x01 * Recv: 0xae 0x15 0x01 serialnumber */ int ret = 0; u8 cmd[] = {ID_GET_STRING_ATTRIBUTE, sizeof(steam->serial_no), ATTRIB_STR_UNIT_SERIAL}; u8 reply[3 + STEAM_SERIAL_LEN + 1]; mutex_lock(&steam->report_mutex); ret = steam_send_report(steam, cmd, sizeof(cmd)); if (ret < 0) goto out; ret = steam_recv_report(steam, reply, sizeof(reply)); if (ret < 0) goto out; if (reply[0] != ID_GET_STRING_ATTRIBUTE || reply[1] < 1 || reply[1] > sizeof(steam->serial_no) || reply[2] != ATTRIB_STR_UNIT_SERIAL) { ret = -EIO; goto out; } reply[3 + STEAM_SERIAL_LEN] = 0; strscpy(steam->serial_no, reply + 3, reply[1]); out: mutex_unlock(&steam->report_mutex); return ret; } /* * This command requests the wireless adaptor to post an event * with the connection status. Useful if this driver is loaded when * the controller is already connected. */ static inline int steam_request_conn_status(struct steam_device *steam) { int ret; mutex_lock(&steam->report_mutex); ret = steam_send_report_byte(steam, ID_DONGLE_GET_WIRELESS_STATE); mutex_unlock(&steam->report_mutex); return ret; } /* * Send a haptic pulse to the trackpads * Duration and interval are measured in microseconds, count is the number * of pulses to send for duration time with interval microseconds between them * and gain is measured in decibels, ranging from -24 to +6 */ static inline int steam_haptic_pulse(struct steam_device *steam, u8 pad, u16 duration, u16 interval, u16 count, u8 gain) { int ret; u8 report[10] = {ID_TRIGGER_HAPTIC_PULSE, 8}; /* Left and right are swapped on this report for legacy reasons */ if (pad < STEAM_PAD_BOTH) pad ^= 1; report[2] = pad; report[3] = duration & 0xFF; report[4] = duration >> 8; report[5] = interval & 0xFF; report[6] = interval >> 8; report[7] = count & 0xFF; report[8] = count >> 8; report[9] = gain; mutex_lock(&steam->report_mutex); ret = steam_send_report(steam, report, sizeof(report)); mutex_unlock(&steam->report_mutex); return ret; } static inline int steam_haptic_rumble(struct steam_device *steam, u16 intensity, u16 left_speed, u16 right_speed, u8 left_gain, u8 right_gain) { int ret; u8 report[11] = {ID_TRIGGER_RUMBLE_CMD, 9}; report[3] = intensity & 0xFF; report[4] = intensity >> 8; report[5] = left_speed & 0xFF; report[6] = left_speed >> 8; report[7] = right_speed & 0xFF; report[8] = right_speed >> 8; report[9] = left_gain; report[10] = right_gain; mutex_lock(&steam->report_mutex); ret = steam_send_report(steam, report, sizeof(report)); mutex_unlock(&steam->report_mutex); return ret; } static void steam_haptic_rumble_cb(struct work_struct *work) { struct steam_device *steam = container_of(work, struct steam_device, rumble_work); steam_haptic_rumble(steam, 0, steam->rumble_left, steam->rumble_right, 2, 0); } #ifdef CONFIG_STEAM_FF static int steam_play_effect(struct input_dev *dev, void *data, struct ff_effect *effect) { struct steam_device *steam = input_get_drvdata(dev); steam->rumble_left = effect->u.rumble.strong_magnitude; steam->rumble_right = effect->u.rumble.weak_magnitude; return schedule_work(&steam->rumble_work); } #endif static void steam_set_lizard_mode(struct steam_device *steam, bool enable) { if (steam->gamepad_mode) enable = false; if (enable) { mutex_lock(&steam->report_mutex); /* enable esc, enter, cursors */ steam_send_report_byte(steam, ID_SET_DEFAULT_DIGITAL_MAPPINGS); /* reset settings */ steam_send_report_byte(steam, ID_LOAD_DEFAULT_SETTINGS); mutex_unlock(&steam->report_mutex); } else { mutex_lock(&steam->report_mutex); /* disable esc, enter, cursor */ steam_send_report_byte(steam, ID_CLEAR_DIGITAL_MAPPINGS); if (steam->quirks & STEAM_QUIRK_DECK) { steam_write_settings(steam, SETTING_LEFT_TRACKPAD_MODE, TRACKPAD_NONE, /* disable mouse */ SETTING_RIGHT_TRACKPAD_MODE, TRACKPAD_NONE, /* disable mouse */ SETTING_LEFT_TRACKPAD_CLICK_PRESSURE, 0xFFFF, /* disable haptic click */ SETTING_RIGHT_TRACKPAD_CLICK_PRESSURE, 0xFFFF, /* disable haptic click */ SETTING_STEAM_WATCHDOG_ENABLE, 0, /* disable watchdog that tests if Steam is active */ 0); mutex_unlock(&steam->report_mutex); } else { steam_write_settings(steam, SETTING_LEFT_TRACKPAD_MODE, TRACKPAD_NONE, /* disable mouse */ SETTING_RIGHT_TRACKPAD_MODE, TRACKPAD_NONE, /* disable mouse */ 0); mutex_unlock(&steam->report_mutex); } } } static int steam_input_open(struct input_dev *dev) { struct steam_device *steam = input_get_drvdata(dev); unsigned long flags; bool set_lizard_mode; /* * Disabling lizard mode automatically is only done on the Steam * Controller. On the Steam Deck, this is toggled manually by holding * the options button instead, handled by steam_mode_switch_cb. */ if (!(steam->quirks & STEAM_QUIRK_DECK)) { spin_lock_irqsave(&steam->lock, flags); set_lizard_mode = !steam->client_opened && lizard_mode; spin_unlock_irqrestore(&steam->lock, flags); if (set_lizard_mode) steam_set_lizard_mode(steam, false); } return 0; } static void steam_input_close(struct input_dev *dev) { struct steam_device *steam = input_get_drvdata(dev); unsigned long flags; bool set_lizard_mode; if (!(steam->quirks & STEAM_QUIRK_DECK)) { spin_lock_irqsave(&steam->lock, flags); set_lizard_mode = !steam->client_opened && lizard_mode; spin_unlock_irqrestore(&steam->lock, flags); if (set_lizard_mode) steam_set_lizard_mode(steam, true); } } static enum power_supply_property steam_battery_props[] = { POWER_SUPPLY_PROP_PRESENT, POWER_SUPPLY_PROP_SCOPE, POWER_SUPPLY_PROP_VOLTAGE_NOW, POWER_SUPPLY_PROP_CAPACITY, }; static int steam_battery_get_property(struct power_supply *psy, enum power_supply_property psp, union power_supply_propval *val) { struct steam_device *steam = power_supply_get_drvdata(psy); unsigned long flags; s16 volts; u8 batt; int ret = 0; spin_lock_irqsave(&steam->lock, flags); volts = steam->voltage; batt = steam->battery_charge; spin_unlock_irqrestore(&steam->lock, flags); switch (psp) { case POWER_SUPPLY_PROP_PRESENT: val->intval = 1; break; case POWER_SUPPLY_PROP_SCOPE: val->intval = POWER_SUPPLY_SCOPE_DEVICE; break; case POWER_SUPPLY_PROP_VOLTAGE_NOW: val->intval = volts * 1000; /* mV -> uV */ break; case POWER_SUPPLY_PROP_CAPACITY: val->intval = batt; break; default: ret = -EINVAL; break; } return ret; } static int steam_battery_register(struct steam_device *steam) { struct power_supply *battery; struct power_supply_config battery_cfg = { .drv_data = steam, }; unsigned long flags; int ret; steam->battery_desc.type = POWER_SUPPLY_TYPE_BATTERY; steam->battery_desc.properties = steam_battery_props; steam->battery_desc.num_properties = ARRAY_SIZE(steam_battery_props); steam->battery_desc.get_property = steam_battery_get_property; steam->battery_desc.name = devm_kasprintf(&steam->hdev->dev, GFP_KERNEL, "steam-controller-%s-battery", steam->serial_no); if (!steam->battery_desc.name) return -ENOMEM; /* avoid the warning of 0% battery while waiting for the first info */ spin_lock_irqsave(&steam->lock, flags); steam->voltage = 3000; steam->battery_charge = 100; spin_unlock_irqrestore(&steam->lock, flags); battery = power_supply_register(&steam->hdev->dev, &steam->battery_desc, &battery_cfg); if (IS_ERR(battery)) { ret = PTR_ERR(battery); hid_err(steam->hdev, "%s:power_supply_register failed with error %d\n", __func__, ret); return ret; } rcu_assign_pointer(steam->battery, battery); power_supply_powers(battery, &steam->hdev->dev); return 0; } static int steam_input_register(struct steam_device *steam) { struct hid_device *hdev = steam->hdev; struct input_dev *input; int ret; rcu_read_lock(); input = rcu_dereference(steam->input); rcu_read_unlock(); if (input) { dbg_hid("%s: already connected\n", __func__); return 0; } input = input_allocate_device(); if (!input) return -ENOMEM; input_set_drvdata(input, steam); input->dev.parent = &hdev->dev; input->open = steam_input_open; input->close = steam_input_close; input->name = (steam->quirks & STEAM_QUIRK_WIRELESS) ? "Wireless Steam Controller" : (steam->quirks & STEAM_QUIRK_DECK) ? "Steam Deck" : "Steam Controller"; input->phys = hdev->phys; input->uniq = steam->serial_no; input->id.bustype = hdev->bus; input->id.vendor = hdev->vendor; input->id.product = hdev->product; input->id.version = hdev->version; input_set_capability(input, EV_KEY, BTN_TR2); input_set_capability(input, EV_KEY, BTN_TL2); input_set_capability(input, EV_KEY, BTN_TR); input_set_capability(input, EV_KEY, BTN_TL); input_set_capability(input, EV_KEY, BTN_Y); input_set_capability(input, EV_KEY, BTN_B); input_set_capability(input, EV_KEY, BTN_X); input_set_capability(input, EV_KEY, BTN_A); input_set_capability(input, EV_KEY, BTN_DPAD_UP); input_set_capability(input, EV_KEY, BTN_DPAD_RIGHT); input_set_capability(input, EV_KEY, BTN_DPAD_LEFT); input_set_capability(input, EV_KEY, BTN_DPAD_DOWN); input_set_capability(input, EV_KEY, BTN_SELECT); input_set_capability(input, EV_KEY, BTN_MODE); input_set_capability(input, EV_KEY, BTN_START); input_set_capability(input, EV_KEY, BTN_THUMBR); input_set_capability(input, EV_KEY, BTN_THUMBL); input_set_capability(input, EV_KEY, BTN_THUMB); input_set_capability(input, EV_KEY, BTN_THUMB2); if (steam->quirks & STEAM_QUIRK_DECK) { input_set_capability(input, EV_KEY, BTN_BASE); input_set_capability(input, EV_KEY, BTN_TRIGGER_HAPPY1); input_set_capability(input, EV_KEY, BTN_TRIGGER_HAPPY2); input_set_capability(input, EV_KEY, BTN_TRIGGER_HAPPY3); input_set_capability(input, EV_KEY, BTN_TRIGGER_HAPPY4); } else { input_set_capability(input, EV_KEY, BTN_GEAR_DOWN); input_set_capability(input, EV_KEY, BTN_GEAR_UP); } input_set_abs_params(input, ABS_X, -32767, 32767, 0, 0); input_set_abs_params(input, ABS_Y, -32767, 32767, 0, 0); input_set_abs_params(input, ABS_HAT0X, -32767, 32767, STEAM_PAD_FUZZ, 0); input_set_abs_params(input, ABS_HAT0Y, -32767, 32767, STEAM_PAD_FUZZ, 0); if (steam->quirks & STEAM_QUIRK_DECK) { input_set_abs_params(input, ABS_HAT2Y, 0, 32767, 0, 0); input_set_abs_params(input, ABS_HAT2X, 0, 32767, 0, 0); input_set_abs_params(input, ABS_RX, -32767, 32767, 0, 0); input_set_abs_params(input, ABS_RY, -32767, 32767, 0, 0); input_set_abs_params(input, ABS_HAT1X, -32767, 32767, STEAM_PAD_FUZZ, 0); input_set_abs_params(input, ABS_HAT1Y, -32767, 32767, STEAM_PAD_FUZZ, 0); input_abs_set_res(input, ABS_X, STEAM_DECK_JOYSTICK_RESOLUTION); input_abs_set_res(input, ABS_Y, STEAM_DECK_JOYSTICK_RESOLUTION); input_abs_set_res(input, ABS_RX, STEAM_DECK_JOYSTICK_RESOLUTION); input_abs_set_res(input, ABS_RY, STEAM_DECK_JOYSTICK_RESOLUTION); input_abs_set_res(input, ABS_HAT1X, STEAM_PAD_RESOLUTION); input_abs_set_res(input, ABS_HAT1Y, STEAM_PAD_RESOLUTION); input_abs_set_res(input, ABS_HAT2Y, STEAM_DECK_TRIGGER_RESOLUTION); input_abs_set_res(input, ABS_HAT2X, STEAM_DECK_TRIGGER_RESOLUTION); } else { input_set_abs_params(input, ABS_HAT2Y, 0, 255, 0, 0); input_set_abs_params(input, ABS_HAT2X, 0, 255, 0, 0); input_set_abs_params(input, ABS_RX, -32767, 32767, STEAM_PAD_FUZZ, 0); input_set_abs_params(input, ABS_RY, -32767, 32767, STEAM_PAD_FUZZ, 0); input_abs_set_res(input, ABS_X, STEAM_JOYSTICK_RESOLUTION); input_abs_set_res(input, ABS_Y, STEAM_JOYSTICK_RESOLUTION); input_abs_set_res(input, ABS_RX, STEAM_PAD_RESOLUTION); input_abs_set_res(input, ABS_RY, STEAM_PAD_RESOLUTION); input_abs_set_res(input, ABS_HAT2Y, STEAM_TRIGGER_RESOLUTION); input_abs_set_res(input, ABS_HAT2X, STEAM_TRIGGER_RESOLUTION); } input_abs_set_res(input, ABS_HAT0X, STEAM_PAD_RESOLUTION); input_abs_set_res(input, ABS_HAT0Y, STEAM_PAD_RESOLUTION); #ifdef CONFIG_STEAM_FF if (steam->quirks & STEAM_QUIRK_DECK) { input_set_capability(input, EV_FF, FF_RUMBLE); ret = input_ff_create_memless(input, NULL, steam_play_effect); if (ret) goto input_register_fail; } #endif ret = input_register_device(input); if (ret) goto input_register_fail; rcu_assign_pointer(steam->input, input); return 0; input_register_fail: input_free_device(input); return ret; } static int steam_sensors_register(struct steam_device *steam) { struct hid_device *hdev = steam->hdev; struct input_dev *sensors; int ret; if (!(steam->quirks & STEAM_QUIRK_DECK)) return 0; rcu_read_lock(); sensors = rcu_dereference(steam->sensors); rcu_read_unlock(); if (sensors) { dbg_hid("%s: already connected\n", __func__); return 0; } sensors = input_allocate_device(); if (!sensors) return -ENOMEM; input_set_drvdata(sensors, steam); sensors->dev.parent = &hdev->dev; sensors->name = "Steam Deck Motion Sensors"; sensors->phys = hdev->phys; sensors->uniq = steam->serial_no; sensors->id.bustype = hdev->bus; sensors->id.vendor = hdev->vendor; sensors->id.product = hdev->product; sensors->id.version = hdev->version; __set_bit(INPUT_PROP_ACCELEROMETER, sensors->propbit); __set_bit(EV_MSC, sensors->evbit); __set_bit(MSC_TIMESTAMP, sensors->mscbit); input_set_abs_params(sensors, ABS_X, -STEAM_DECK_ACCEL_RANGE, STEAM_DECK_ACCEL_RANGE, STEAM_DECK_ACCEL_FUZZ, 0); input_set_abs_params(sensors, ABS_Y, -STEAM_DECK_ACCEL_RANGE, STEAM_DECK_ACCEL_RANGE, STEAM_DECK_ACCEL_FUZZ, 0); input_set_abs_params(sensors, ABS_Z, -STEAM_DECK_ACCEL_RANGE, STEAM_DECK_ACCEL_RANGE, STEAM_DECK_ACCEL_FUZZ, 0); input_abs_set_res(sensors, ABS_X, STEAM_DECK_ACCEL_RES_PER_G); input_abs_set_res(sensors, ABS_Y, STEAM_DECK_ACCEL_RES_PER_G); input_abs_set_res(sensors, ABS_Z, STEAM_DECK_ACCEL_RES_PER_G); input_set_abs_params(sensors, ABS_RX, -STEAM_DECK_GYRO_RANGE, STEAM_DECK_GYRO_RANGE, STEAM_DECK_GYRO_FUZZ, 0); input_set_abs_params(sensors, ABS_RY, -STEAM_DECK_GYRO_RANGE, STEAM_DECK_GYRO_RANGE, STEAM_DECK_GYRO_FUZZ, 0); input_set_abs_params(sensors, ABS_RZ, -STEAM_DECK_GYRO_RANGE, STEAM_DECK_GYRO_RANGE, STEAM_DECK_GYRO_FUZZ, 0); input_abs_set_res(sensors, ABS_RX, STEAM_DECK_GYRO_RES_PER_DPS); input_abs_set_res(sensors, ABS_RY, STEAM_DECK_GYRO_RES_PER_DPS); input_abs_set_res(sensors, ABS_RZ, STEAM_DECK_GYRO_RES_PER_DPS); ret = input_register_device(sensors); if (ret) goto sensors_register_fail; rcu_assign_pointer(steam->sensors, sensors); return 0; sensors_register_fail: input_free_device(sensors); return ret; } static void steam_input_unregister(struct steam_device *steam) { struct input_dev *input; rcu_read_lock(); input = rcu_dereference(steam->input); rcu_read_unlock(); if (!input) return; RCU_INIT_POINTER(steam->input, NULL); synchronize_rcu(); input_unregister_device(input); } static void steam_sensors_unregister(struct steam_device *steam) { struct input_dev *sensors; if (!(steam->quirks & STEAM_QUIRK_DECK)) return; rcu_read_lock(); sensors = rcu_dereference(steam->sensors); rcu_read_unlock(); if (!sensors) return; RCU_INIT_POINTER(steam->sensors, NULL); synchronize_rcu(); input_unregister_device(sensors); } static void steam_battery_unregister(struct steam_device *steam) { struct power_supply *battery; rcu_read_lock(); battery = rcu_dereference(steam->battery); rcu_read_unlock(); if (!battery) return; RCU_INIT_POINTER(steam->battery, NULL); synchronize_rcu(); power_supply_unregister(battery); } static int steam_register(struct steam_device *steam) { int ret; unsigned long client_opened; unsigned long flags; /* * This function can be called several times in a row with the * wireless adaptor, without steam_unregister() between them, because * another client send a get_connection_status command, for example. * The battery and serial number are set just once per device. */ if (!steam->serial_no[0]) { /* * Unlikely, but getting the serial could fail, and it is not so * important, so make up a serial number and go on. */ if (steam_get_serial(steam) < 0) strscpy(steam->serial_no, "XXXXXXXXXX", sizeof(steam->serial_no)); hid_info(steam->hdev, "Steam Controller '%s' connected", steam->serial_no); /* ignore battery errors, we can live without it */ if (steam->quirks & STEAM_QUIRK_WIRELESS) steam_battery_register(steam); mutex_lock(&steam_devices_lock); if (list_empty(&steam->list)) list_add(&steam->list, &steam_devices); mutex_unlock(&steam_devices_lock); } spin_lock_irqsave(&steam->lock, flags); client_opened = steam->client_opened; spin_unlock_irqrestore(&steam->lock, flags); if (!client_opened) { steam_set_lizard_mode(steam, lizard_mode); ret = steam_input_register(steam); if (ret != 0) goto steam_register_input_fail; ret = steam_sensors_register(steam); if (ret != 0) goto steam_register_sensors_fail; } return 0; steam_register_sensors_fail: steam_input_unregister(steam); steam_register_input_fail: return ret; } static void steam_unregister(struct steam_device *steam) { steam_battery_unregister(steam); steam_sensors_unregister(steam); steam_input_unregister(steam); if (steam->serial_no[0]) { hid_info(steam->hdev, "Steam Controller '%s' disconnected", steam->serial_no); mutex_lock(&steam_devices_lock); list_del_init(&steam->list); mutex_unlock(&steam_devices_lock); steam->serial_no[0] = 0; } } static void steam_work_connect_cb(struct work_struct *work) { struct steam_device *steam = container_of(work, struct steam_device, work_connect); unsigned long flags; bool connected; int ret; spin_lock_irqsave(&steam->lock, flags); connected = steam->connected; spin_unlock_irqrestore(&steam->lock, flags); if (connected) { ret = steam_register(steam); if (ret) { hid_err(steam->hdev, "%s:steam_register failed with error %d\n", __func__, ret); } } else { steam_unregister(steam); } } static void steam_mode_switch_cb(struct work_struct *work) { struct steam_device *steam = container_of(to_delayed_work(work), struct steam_device, mode_switch); unsigned long flags; bool client_opened; steam->gamepad_mode = !steam->gamepad_mode; if (!lizard_mode) return; if (steam->gamepad_mode) steam_set_lizard_mode(steam, false); else { spin_lock_irqsave(&steam->lock, flags); client_opened = steam->client_opened; spin_unlock_irqrestore(&steam->lock, flags); if (!client_opened) steam_set_lizard_mode(steam, lizard_mode); } steam_haptic_pulse(steam, STEAM_PAD_RIGHT, 0x190, 0, 1, 0); if (steam->gamepad_mode) { steam_haptic_pulse(steam, STEAM_PAD_LEFT, 0x14D, 0x14D, 0x2D, 0); } else { steam_haptic_pulse(steam, STEAM_PAD_LEFT, 0x1F4, 0x1F4, 0x1E, 0); } } static bool steam_is_valve_interface(struct hid_device *hdev) { struct hid_report_enum *rep_enum; /* * The wired device creates 3 interfaces: * 0: emulated mouse. * 1: emulated keyboard. * 2: the real game pad. * The wireless device creates 5 interfaces: * 0: emulated keyboard. * 1-4: slots where up to 4 real game pads will be connected to. * We know which one is the real gamepad interface because they are the * only ones with a feature report. */ rep_enum = &hdev->report_enum[HID_FEATURE_REPORT]; return !list_empty(&rep_enum->report_list); } static int steam_client_ll_parse(struct hid_device *hdev) { struct steam_device *steam = hdev->driver_data; return hid_parse_report(hdev, steam->hdev->dev_rdesc, steam->hdev->dev_rsize); } static int steam_client_ll_start(struct hid_device *hdev) { return 0; } static void steam_client_ll_stop(struct hid_device *hdev) { } static int steam_client_ll_open(struct hid_device *hdev) { struct steam_device *steam = hdev->driver_data; unsigned long flags; spin_lock_irqsave(&steam->lock, flags); steam->client_opened++; spin_unlock_irqrestore(&steam->lock, flags); steam_sensors_unregister(steam); steam_input_unregister(steam); return 0; } static void steam_client_ll_close(struct hid_device *hdev) { struct steam_device *steam = hdev->driver_data; unsigned long flags; bool connected; spin_lock_irqsave(&steam->lock, flags); steam->client_opened--; connected = steam->connected && !steam->client_opened; spin_unlock_irqrestore(&steam->lock, flags); if (connected) { steam_set_lizard_mode(steam, lizard_mode); steam_input_register(steam); steam_sensors_register(steam); } } static int steam_client_ll_raw_request(struct hid_device *hdev, unsigned char reportnum, u8 *buf, size_t count, unsigned char report_type, int reqtype) { struct steam_device *steam = hdev->driver_data; return hid_hw_raw_request(steam->hdev, reportnum, buf, count, report_type, reqtype); } static const struct hid_ll_driver steam_client_ll_driver = { .parse = steam_client_ll_parse, .start = steam_client_ll_start, .stop = steam_client_ll_stop, .open = steam_client_ll_open, .close = steam_client_ll_close, .raw_request = steam_client_ll_raw_request, }; static struct hid_device *steam_create_client_hid(struct hid_device *hdev) { struct hid_device *client_hdev; client_hdev = hid_allocate_device(); if (IS_ERR(client_hdev)) return client_hdev; client_hdev->ll_driver = &steam_client_ll_driver; client_hdev->dev.parent = hdev->dev.parent; client_hdev->bus = hdev->bus; client_hdev->vendor = hdev->vendor; client_hdev->product = hdev->product; client_hdev->version = hdev->version; client_hdev->type = hdev->type; client_hdev->country = hdev->country; strscpy(client_hdev->name, hdev->name, sizeof(client_hdev->name)); strscpy(client_hdev->phys, hdev->phys, sizeof(client_hdev->phys)); /* * Since we use the same device info than the real interface to * trick userspace, we will be calling steam_probe recursively. * We need to recognize the client interface somehow. */ client_hdev->group = HID_GROUP_STEAM; return client_hdev; } static int steam_probe(struct hid_device *hdev, const struct hid_device_id *id) { struct steam_device *steam; int ret; ret = hid_parse(hdev); if (ret) { hid_err(hdev, "%s:parse of hid interface failed\n", __func__); return ret; } /* * The virtual client_dev is only used for hidraw. * Also avoid the recursive probe. */ if (hdev->group == HID_GROUP_STEAM) return hid_hw_start(hdev, HID_CONNECT_HIDRAW); /* * The non-valve interfaces (mouse and keyboard emulation) are * connected without changes. */ if (!steam_is_valve_interface(hdev)) return hid_hw_start(hdev, HID_CONNECT_DEFAULT); steam = devm_kzalloc(&hdev->dev, sizeof(*steam), GFP_KERNEL); if (!steam) return -ENOMEM; steam->hdev = hdev; hid_set_drvdata(hdev, steam); spin_lock_init(&steam->lock); mutex_init(&steam->report_mutex); steam->quirks = id->driver_data; INIT_WORK(&steam->work_connect, steam_work_connect_cb); INIT_DELAYED_WORK(&steam->mode_switch, steam_mode_switch_cb); INIT_LIST_HEAD(&steam->list); INIT_WORK(&steam->rumble_work, steam_haptic_rumble_cb); steam->sensor_timestamp_us = 0; /* * With the real steam controller interface, do not connect hidraw. * Instead, create the client_hid and connect that. */ ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT & ~HID_CONNECT_HIDRAW); if (ret) goto err_cancel_work; ret = hid_hw_open(hdev); if (ret) { hid_err(hdev, "%s:hid_hw_open\n", __func__); goto err_hw_stop; } if (steam->quirks & STEAM_QUIRK_WIRELESS) { hid_info(hdev, "Steam wireless receiver connected"); /* If using a wireless adaptor ask for connection status */ steam->connected = false; steam_request_conn_status(steam); } else { /* A wired connection is always present */ steam->connected = true; ret = steam_register(steam); if (ret) { hid_err(hdev, "%s:steam_register failed with error %d\n", __func__, ret); goto err_hw_close; } } steam->client_hdev = steam_create_client_hid(hdev); if (IS_ERR(steam->client_hdev)) { ret = PTR_ERR(steam->client_hdev); goto err_steam_unregister; } steam->client_hdev->driver_data = steam; ret = hid_add_device(steam->client_hdev); if (ret) goto err_destroy; return 0; err_destroy: hid_destroy_device(steam->client_hdev); err_steam_unregister: if (steam->connected) steam_unregister(steam); err_hw_close: hid_hw_close(hdev); err_hw_stop: hid_hw_stop(hdev); err_cancel_work: cancel_work_sync(&steam->work_connect); cancel_delayed_work_sync(&steam->mode_switch); cancel_work_sync(&steam->rumble_work); return ret; } static void steam_remove(struct hid_device *hdev) { struct steam_device *steam = hid_get_drvdata(hdev); if (!steam || hdev->group == HID_GROUP_STEAM) { hid_hw_stop(hdev); return; } cancel_delayed_work_sync(&steam->mode_switch); cancel_work_sync(&steam->work_connect); hid_destroy_device(steam->client_hdev); steam->client_hdev = NULL; steam->client_opened = 0; if (steam->quirks & STEAM_QUIRK_WIRELESS) { hid_info(hdev, "Steam wireless receiver disconnected"); } hid_hw_close(hdev); hid_hw_stop(hdev); steam_unregister(steam); } static void steam_do_connect_event(struct steam_device *steam, bool connected) { unsigned long flags; bool changed; spin_lock_irqsave(&steam->lock, flags); changed = steam->connected != connected; steam->connected = connected; spin_unlock_irqrestore(&steam->lock, flags); if (changed && schedule_work(&steam->work_connect) == 0) dbg_hid("%s: connected=%d event already queued\n", __func__, connected); } /* * Some input data in the protocol has the opposite sign. * Clamp the values to 32767..-32767 so that the range is * symmetrical and can be negated safely. */ static inline s16 steam_le16(u8 *data) { s16 x = (s16) le16_to_cpup((__le16 *)data); return x == -32768 ? -32767 : x; } /* * The size for this message payload is 60. * The known values are: * (* values are not sent through wireless) * (* accelerator/gyro is disabled by default) * Offset| Type | Mapped to |Meaning * -------+-------+-----------+-------------------------- * 4-7 | u32 | -- | sequence number * 8-10 | 24bit | see below | buttons * 11 | u8 | ABS_HAT2Y | left trigger * 12 | u8 | ABS_HAT2X | right trigger * 13-15 | -- | -- | always 0 * 16-17 | s16 | ABS_X/ABS_HAT0X | X value * 18-19 | s16 | ABS_Y/ABS_HAT0Y | Y value * 20-21 | s16 | ABS_RX | right-pad X value * 22-23 | s16 | ABS_RY | right-pad Y value * 24-25 | s16 | -- | * left trigger * 26-27 | s16 | -- | * right trigger * 28-29 | s16 | -- | * accelerometer X value * 30-31 | s16 | -- | * accelerometer Y value * 32-33 | s16 | -- | * accelerometer Z value * 34-35 | s16 | -- | gyro X value * 36-36 | s16 | -- | gyro Y value * 38-39 | s16 | -- | gyro Z value * 40-41 | s16 | -- | quaternion W value * 42-43 | s16 | -- | quaternion X value * 44-45 | s16 | -- | quaternion Y value * 46-47 | s16 | -- | quaternion Z value * 48-49 | -- | -- | always 0 * 50-51 | s16 | -- | * left trigger (uncalibrated) * 52-53 | s16 | -- | * right trigger (uncalibrated) * 54-55 | s16 | -- | * joystick X value (uncalibrated) * 56-57 | s16 | -- | * joystick Y value (uncalibrated) * 58-59 | s16 | -- | * left-pad X value * 60-61 | s16 | -- | * left-pad Y value * 62-63 | u16 | -- | * battery voltage * * The buttons are: * Bit | Mapped to | Description * ------+------------+-------------------------------- * 8.0 | BTN_TR2 | right trigger fully pressed * 8.1 | BTN_TL2 | left trigger fully pressed * 8.2 | BTN_TR | right shoulder * 8.3 | BTN_TL | left shoulder * 8.4 | BTN_Y | button Y * 8.5 | BTN_B | button B * 8.6 | BTN_X | button X * 8.7 | BTN_A | button A * 9.0 | BTN_DPAD_UP | left-pad up * 9.1 | BTN_DPAD_RIGHT | left-pad right * 9.2 | BTN_DPAD_LEFT | left-pad left * 9.3 | BTN_DPAD_DOWN | left-pad down * 9.4 | BTN_SELECT | menu left * 9.5 | BTN_MODE | steam logo * 9.6 | BTN_START | menu right * 9.7 | BTN_GEAR_DOWN | left back lever * 10.0 | BTN_GEAR_UP | right back lever * 10.1 | -- | left-pad clicked * 10.2 | BTN_THUMBR | right-pad clicked * 10.3 | BTN_THUMB | left-pad touched (but see explanation below) * 10.4 | BTN_THUMB2 | right-pad touched * 10.5 | -- | unknown * 10.6 | BTN_THUMBL | joystick clicked * 10.7 | -- | lpad_and_joy */ static void steam_do_input_event(struct steam_device *steam, struct input_dev *input, u8 *data) { /* 24 bits of buttons */ u8 b8, b9, b10; s16 x, y; bool lpad_touched, lpad_and_joy; b8 = data[8]; b9 = data[9]; b10 = data[10]; input_report_abs(input, ABS_HAT2Y, data[11]); input_report_abs(input, ABS_HAT2X, data[12]); /* * These two bits tells how to interpret the values X and Y. * lpad_and_joy tells that the joystick and the lpad are used at the * same time. * lpad_touched tells whether X/Y are to be read as lpad coord or * joystick values. * (lpad_touched || lpad_and_joy) tells if the lpad is really touched. */ lpad_touched = b10 & BIT(3); lpad_and_joy = b10 & BIT(7); x = steam_le16(data + 16); y = -steam_le16(data + 18); input_report_abs(input, lpad_touched ? ABS_HAT0X : ABS_X, x); input_report_abs(input, lpad_touched ? ABS_HAT0Y : ABS_Y, y); /* Check if joystick is centered */ if (lpad_touched && !lpad_and_joy) { input_report_abs(input, ABS_X, 0); input_report_abs(input, ABS_Y, 0); } /* Check if lpad is untouched */ if (!(lpad_touched || lpad_and_joy)) { input_report_abs(input, ABS_HAT0X, 0); input_report_abs(input, ABS_HAT0Y, 0); } input_report_abs(input, ABS_RX, steam_le16(data + 20)); input_report_abs(input, ABS_RY, -steam_le16(data + 22)); input_event(input, EV_KEY, BTN_TR2, !!(b8 & BIT(0))); input_event(input, EV_KEY, BTN_TL2, !!(b8 & BIT(1))); input_event(input, EV_KEY, BTN_TR, !!(b8 & BIT(2))); input_event(input, EV_KEY, BTN_TL, !!(b8 & BIT(3))); input_event(input, EV_KEY, BTN_Y, !!(b8 & BIT(4))); input_event(input, EV_KEY, BTN_B, !!(b8 & BIT(5))); input_event(input, EV_KEY, BTN_X, !!(b8 & BIT(6))); input_event(input, EV_KEY, BTN_A, !!(b8 & BIT(7))); input_event(input, EV_KEY, BTN_SELECT, !!(b9 & BIT(4))); input_event(input, EV_KEY, BTN_MODE, !!(b9 & BIT(5))); input_event(input, EV_KEY, BTN_START, !!(b9 & BIT(6))); input_event(input, EV_KEY, BTN_GEAR_DOWN, !!(b9 & BIT(7))); input_event(input, EV_KEY, BTN_GEAR_UP, !!(b10 & BIT(0))); input_event(input, EV_KEY, BTN_THUMBR, !!(b10 & BIT(2))); input_event(input, EV_KEY, BTN_THUMBL, !!(b10 & BIT(6))); input_event(input, EV_KEY, BTN_THUMB, lpad_touched || lpad_and_joy); input_event(input, EV_KEY, BTN_THUMB2, !!(b10 & BIT(4))); input_event(input, EV_KEY, BTN_DPAD_UP, !!(b9 & BIT(0))); input_event(input, EV_KEY, BTN_DPAD_RIGHT, !!(b9 & BIT(1))); input_event(input, EV_KEY, BTN_DPAD_LEFT, !!(b9 & BIT(2))); input_event(input, EV_KEY, BTN_DPAD_DOWN, !!(b9 & BIT(3))); input_sync(input); } /* * The size for this message payload is 56. * The known values are: * Offset| Type | Mapped to |Meaning * -------+-------+-----------+-------------------------- * 4-7 | u32 | -- | sequence number * 8-15 | u64 | see below | buttons * 16-17 | s16 | ABS_HAT0X | left-pad X value * 18-19 | s16 | ABS_HAT0Y | left-pad Y value * 20-21 | s16 | ABS_HAT1X | right-pad X value * 22-23 | s16 | ABS_HAT1Y | right-pad Y value * 24-25 | s16 | IMU ABS_X | accelerometer X value * 26-27 | s16 | IMU ABS_Z | accelerometer Y value * 28-29 | s16 | IMU ABS_Y | accelerometer Z value * 30-31 | s16 | IMU ABS_RX | gyro X value * 32-33 | s16 | IMU ABS_RZ | gyro Y value * 34-35 | s16 | IMU ABS_RY | gyro Z value * 36-37 | s16 | -- | quaternion W value * 38-39 | s16 | -- | quaternion X value * 40-41 | s16 | -- | quaternion Y value * 42-43 | s16 | -- | quaternion Z value * 44-45 | u16 | ABS_HAT2Y | left trigger (uncalibrated) * 46-47 | u16 | ABS_HAT2X | right trigger (uncalibrated) * 48-49 | s16 | ABS_X | left joystick X * 50-51 | s16 | ABS_Y | left joystick Y * 52-53 | s16 | ABS_RX | right joystick X * 54-55 | s16 | ABS_RY | right joystick Y * 56-57 | u16 | -- | left pad pressure * 58-59 | u16 | -- | right pad pressure * * The buttons are: * Bit | Mapped to | Description * ------+------------+-------------------------------- * 8.0 | BTN_TR2 | right trigger fully pressed * 8.1 | BTN_TL2 | left trigger fully pressed * 8.2 | BTN_TR | right shoulder * 8.3 | BTN_TL | left shoulder * 8.4 | BTN_Y | button Y * 8.5 | BTN_B | button B * 8.6 | BTN_X | button X * 8.7 | BTN_A | button A * 9.0 | BTN_DPAD_UP | left-pad up * 9.1 | BTN_DPAD_RIGHT | left-pad right * 9.2 | BTN_DPAD_LEFT | left-pad left * 9.3 | BTN_DPAD_DOWN | left-pad down * 9.4 | BTN_SELECT | menu left * 9.5 | BTN_MODE | steam logo * 9.6 | BTN_START | menu right * 9.7 | BTN_TRIGGER_HAPPY3 | left bottom grip button * 10.0 | BTN_TRIGGER_HAPPY4 | right bottom grip button * 10.1 | BTN_THUMB | left pad pressed * 10.2 | BTN_THUMB2 | right pad pressed * 10.3 | -- | left pad touched * 10.4 | -- | right pad touched * 10.5 | -- | unknown * 10.6 | BTN_THUMBL | left joystick clicked * 10.7 | -- | unknown * 11.0 | -- | unknown * 11.1 | -- | unknown * 11.2 | BTN_THUMBR | right joystick clicked * 11.3 | -- | unknown * 11.4 | -- | unknown * 11.5 | -- | unknown * 11.6 | -- | unknown * 11.7 | -- | unknown * 12.0 | -- | unknown * 12.1 | -- | unknown * 12.2 | -- | unknown * 12.3 | -- | unknown * 12.4 | -- | unknown * 12.5 | -- | unknown * 12.6 | -- | unknown * 12.7 | -- | unknown * 13.0 | -- | unknown * 13.1 | BTN_TRIGGER_HAPPY1 | left top grip button * 13.2 | BTN_TRIGGER_HAPPY2 | right top grip button * 13.3 | -- | unknown * 13.4 | -- | unknown * 13.5 | -- | unknown * 13.6 | -- | left joystick touched * 13.7 | -- | right joystick touched * 14.0 | -- | unknown * 14.1 | -- | unknown * 14.2 | BTN_BASE | quick access button * 14.3 | -- | unknown * 14.4 | -- | unknown * 14.5 | -- | unknown * 14.6 | -- | unknown * 14.7 | -- | unknown * 15.0 | -- | unknown * 15.1 | -- | unknown * 15.2 | -- | unknown * 15.3 | -- | unknown * 15.4 | -- | unknown * 15.5 | -- | unknown * 15.6 | -- | unknown * 15.7 | -- | unknown */ static void steam_do_deck_input_event(struct steam_device *steam, struct input_dev *input, u8 *data) { u8 b8, b9, b10, b11, b13, b14; bool lpad_touched, rpad_touched; b8 = data[8]; b9 = data[9]; b10 = data[10]; b11 = data[11]; b13 = data[13]; b14 = data[14]; if (!(b9 & BIT(6)) && steam->did_mode_switch) { steam->did_mode_switch = false; cancel_delayed_work_sync(&steam->mode_switch); } else if (!steam->client_opened && (b9 & BIT(6)) && !steam->did_mode_switch) { steam->did_mode_switch = true; schedule_delayed_work(&steam->mode_switch, 45 * HZ / 100); } if (!steam->gamepad_mode) return; lpad_touched = b10 & BIT(3); rpad_touched = b10 & BIT(4); if (lpad_touched) { input_report_abs(input, ABS_HAT0X, steam_le16(data + 16)); input_report_abs(input, ABS_HAT0Y, steam_le16(data + 18)); } else { input_report_abs(input, ABS_HAT0X, 0); input_report_abs(input, ABS_HAT0Y, 0); } if (rpad_touched) { input_report_abs(input, ABS_HAT1X, steam_le16(data + 20)); input_report_abs(input, ABS_HAT1Y, steam_le16(data + 22)); } else { input_report_abs(input, ABS_HAT1X, 0); input_report_abs(input, ABS_HAT1Y, 0); } input_report_abs(input, ABS_X, steam_le16(data + 48)); input_report_abs(input, ABS_Y, -steam_le16(data + 50)); input_report_abs(input, ABS_RX, steam_le16(data + 52)); input_report_abs(input, ABS_RY, -steam_le16(data + 54)); input_report_abs(input, ABS_HAT2Y, steam_le16(data + 44)); input_report_abs(input, ABS_HAT2X, steam_le16(data + 46)); input_event(input, EV_KEY, BTN_TR2, !!(b8 & BIT(0))); input_event(input, EV_KEY, BTN_TL2, !!(b8 & BIT(1))); input_event(input, EV_KEY, BTN_TR, !!(b8 & BIT(2))); input_event(input, EV_KEY, BTN_TL, !!(b8 & BIT(3))); input_event(input, EV_KEY, BTN_Y, !!(b8 & BIT(4))); input_event(input, EV_KEY, BTN_B, !!(b8 & BIT(5))); input_event(input, EV_KEY, BTN_X, !!(b8 & BIT(6))); input_event(input, EV_KEY, BTN_A, !!(b8 & BIT(7))); input_event(input, EV_KEY, BTN_SELECT, !!(b9 & BIT(4))); input_event(input, EV_KEY, BTN_MODE, !!(b9 & BIT(5))); input_event(input, EV_KEY, BTN_START, !!(b9 & BIT(6))); input_event(input, EV_KEY, BTN_TRIGGER_HAPPY3, !!(b9 & BIT(7))); input_event(input, EV_KEY, BTN_TRIGGER_HAPPY4, !!(b10 & BIT(0))); input_event(input, EV_KEY, BTN_THUMBL, !!(b10 & BIT(6))); input_event(input, EV_KEY, BTN_THUMBR, !!(b11 & BIT(2))); input_event(input, EV_KEY, BTN_DPAD_UP, !!(b9 & BIT(0))); input_event(input, EV_KEY, BTN_DPAD_RIGHT, !!(b9 & BIT(1))); input_event(input, EV_KEY, BTN_DPAD_LEFT, !!(b9 & BIT(2))); input_event(input, EV_KEY, BTN_DPAD_DOWN, !!(b9 & BIT(3))); input_event(input, EV_KEY, BTN_THUMB, !!(b10 & BIT(1))); input_event(input, EV_KEY, BTN_THUMB2, !!(b10 & BIT(2))); input_event(input, EV_KEY, BTN_TRIGGER_HAPPY1, !!(b13 & BIT(1))); input_event(input, EV_KEY, BTN_TRIGGER_HAPPY2, !!(b13 & BIT(2))); input_event(input, EV_KEY, BTN_BASE, !!(b14 & BIT(2))); input_sync(input); } static void steam_do_deck_sensors_event(struct steam_device *steam, struct input_dev *sensors, u8 *data) { /* * The deck input report is received every 4 ms on average, * with a jitter of +/- 4 ms even though the USB descriptor claims * that it uses 1 kHz. * Since the HID report does not include a sensor timestamp, * use a fixed increment here. */ steam->sensor_timestamp_us += 4000; if (!steam->gamepad_mode) return; input_event(sensors, EV_MSC, MSC_TIMESTAMP, steam->sensor_timestamp_us); input_report_abs(sensors, ABS_X, steam_le16(data + 24)); input_report_abs(sensors, ABS_Z, -steam_le16(data + 26)); input_report_abs(sensors, ABS_Y, steam_le16(data + 28)); input_report_abs(sensors, ABS_RX, steam_le16(data + 30)); input_report_abs(sensors, ABS_RZ, -steam_le16(data + 32)); input_report_abs(sensors, ABS_RY, steam_le16(data + 34)); input_sync(sensors); } /* * The size for this message payload is 11. * The known values are: * Offset| Type | Meaning * -------+-------+--------------------------- * 4-7 | u32 | sequence number * 8-11 | -- | always 0 * 12-13 | u16 | voltage (mV) * 14 | u8 | battery percent */ static void steam_do_battery_event(struct steam_device *steam, struct power_supply *battery, u8 *data) { unsigned long flags; s16 volts = steam_le16(data + 12); u8 batt = data[14]; /* Creating the battery may have failed */ rcu_read_lock(); battery = rcu_dereference(steam->battery); if (likely(battery)) { spin_lock_irqsave(&steam->lock, flags); steam->voltage = volts; steam->battery_charge = batt; spin_unlock_irqrestore(&steam->lock, flags); power_supply_changed(battery); } rcu_read_unlock(); } static int steam_raw_event(struct hid_device *hdev, struct hid_report *report, u8 *data, int size) { struct steam_device *steam = hid_get_drvdata(hdev); struct input_dev *input; struct input_dev *sensors; struct power_supply *battery; if (!steam) return 0; if (steam->client_opened) hid_input_report(steam->client_hdev, HID_FEATURE_REPORT, data, size, 0); /* * All messages are size=64, all values little-endian. * The format is: * Offset| Meaning * -------+-------------------------------------------- * 0-1 | always 0x01, 0x00, maybe protocol version? * 2 | type of message * 3 | length of the real payload (not checked) * 4-n | payload data, depends on the type * * There are these known types of message: * 0x01: input data (60 bytes) * 0x03: wireless connect/disconnect (1 byte) * 0x04: battery status (11 bytes) * 0x09: Steam Deck input data (56 bytes) */ if (size != 64 || data[0] != 1 || data[1] != 0) return 0; switch (data[2]) { case ID_CONTROLLER_STATE: if (steam->client_opened) return 0; rcu_read_lock(); input = rcu_dereference(steam->input); if (likely(input)) steam_do_input_event(steam, input, data); rcu_read_unlock(); break; case ID_CONTROLLER_DECK_STATE: if (steam->client_opened) return 0; rcu_read_lock(); input = rcu_dereference(steam->input); if (likely(input)) steam_do_deck_input_event(steam, input, data); sensors = rcu_dereference(steam->sensors); if (likely(sensors)) steam_do_deck_sensors_event(steam, sensors, data); rcu_read_unlock(); break; case ID_CONTROLLER_WIRELESS: /* * The payload of this event is a single byte: * 0x01: disconnected. * 0x02: connected. */ switch (data[4]) { case 0x01: steam_do_connect_event(steam, false); break; case 0x02: steam_do_connect_event(steam, true); break; } break; case ID_CONTROLLER_STATUS: if (steam->quirks & STEAM_QUIRK_WIRELESS) { rcu_read_lock(); battery = rcu_dereference(steam->battery); if (likely(battery)) { steam_do_battery_event(steam, battery, data); } else { dbg_hid( "%s: battery data without connect event\n", __func__); steam_do_connect_event(steam, true); } rcu_read_unlock(); } break; } return 0; } static int steam_param_set_lizard_mode(const char *val, const struct kernel_param *kp) { struct steam_device *steam; int ret; ret = param_set_bool(val, kp); if (ret) return ret; mutex_lock(&steam_devices_lock); list_for_each_entry(steam, &steam_devices, list) { if (!steam->client_opened) steam_set_lizard_mode(steam, lizard_mode); } mutex_unlock(&steam_devices_lock); return 0; } static const struct kernel_param_ops steam_lizard_mode_ops = { .set = steam_param_set_lizard_mode, .get = param_get_bool, }; module_param_cb(lizard_mode, &steam_lizard_mode_ops, &lizard_mode, 0644); MODULE_PARM_DESC(lizard_mode, "Enable mouse and keyboard emulation (lizard mode) when the gamepad is not in use"); static const struct hid_device_id steam_controllers[] = { { /* Wired Steam Controller */ HID_USB_DEVICE(USB_VENDOR_ID_VALVE, USB_DEVICE_ID_STEAM_CONTROLLER) }, { /* Wireless Steam Controller */ HID_USB_DEVICE(USB_VENDOR_ID_VALVE, USB_DEVICE_ID_STEAM_CONTROLLER_WIRELESS), .driver_data = STEAM_QUIRK_WIRELESS }, { /* Steam Deck */ HID_USB_DEVICE(USB_VENDOR_ID_VALVE, USB_DEVICE_ID_STEAM_DECK), .driver_data = STEAM_QUIRK_DECK }, {} }; MODULE_DEVICE_TABLE(hid, steam_controllers); static struct hid_driver steam_controller_driver = { .name = "hid-steam", .id_table = steam_controllers, .probe = steam_probe, .remove = steam_remove, .raw_event = steam_raw_event, }; module_hid_driver(steam_controller_driver); |
| 308 3 1 2 554 842 18140 1399 844 845 845 842 553 554 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_KERNEL_FPU_XSTATE_H #define __X86_KERNEL_FPU_XSTATE_H #include <asm/cpufeature.h> #include <asm/fpu/xstate.h> #include <asm/fpu/xcr.h> #ifdef CONFIG_X86_64 DECLARE_PER_CPU(u64, xfd_state); #endif static inline void xstate_init_xcomp_bv(struct xregs_state *xsave, u64 mask) { /* * XRSTORS requires these bits set in xcomp_bv, or it will * trigger #GP: */ if (cpu_feature_enabled(X86_FEATURE_XCOMPACTED)) xsave->header.xcomp_bv = mask | XCOMP_BV_COMPACTED_FORMAT; } static inline u64 xstate_get_group_perm(bool guest) { struct fpu *fpu = ¤t->group_leader->thread.fpu; struct fpu_state_perm *perm; /* Pairs with WRITE_ONCE() in xstate_request_perm() */ perm = guest ? &fpu->guest_perm : &fpu->perm; return READ_ONCE(perm->__state_perm); } static inline u64 xstate_get_host_group_perm(void) { return xstate_get_group_perm(false); } enum xstate_copy_mode { XSTATE_COPY_FP, XSTATE_COPY_FX, XSTATE_COPY_XSAVE, }; struct membuf; extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, u64 xfeatures, u32 pkru_val, enum xstate_copy_mode copy_mode); extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode mode); extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru); extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void __user *ubuf); extern void fpu__init_cpu_xstate(void); extern void fpu__init_system_xstate(unsigned int legacy_size); extern void __user *get_xsave_addr_user(struct xregs_state __user *xsave, int xfeature_nr); static inline u64 xfeatures_mask_supervisor(void) { return fpu_kernel_cfg.max_features & XFEATURE_MASK_SUPERVISOR_SUPPORTED; } static inline u64 xfeatures_mask_independent(void) { if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) return fpu_kernel_cfg.independent_features & ~XFEATURE_MASK_LBR; return fpu_kernel_cfg.independent_features; } /* * Update the value of PKRU register that was already pushed onto the signal frame. */ static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 mask, u32 pkru) { u64 xstate_bv; int err; if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE))) return 0; /* Mark PKRU as in-use so that it is restored correctly. */ xstate_bv = (mask & xfeatures_in_use()) | XFEATURE_MASK_PKRU; err = __put_user(xstate_bv, &buf->header.xfeatures); if (err) return err; /* Update PKRU value in the userspace xsave buffer. */ return __put_user(pkru, (unsigned int __user *)get_xsave_addr_user(buf, XFEATURE_PKRU)); } /* XSAVE/XRSTOR wrapper functions */ #ifdef CONFIG_X86_64 #define REX_PREFIX "0x48, " #else #define REX_PREFIX #endif /* These macros all use (%edi)/(%rdi) as the single memory argument. */ #define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" #define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" #define XSAVEC ".byte " REX_PREFIX "0x0f,0xc7,0x27" #define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" #define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" #define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" /* * After this @err contains 0 on success or the trap number when the * operation raises an exception. */ #define XSTATE_OP(op, st, lmask, hmask, err) \ asm volatile("1:" op "\n\t" \ "xor %[err], %[err]\n" \ "2:\n\t" \ _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_FAULT_MCE_SAFE) \ : [err] "=a" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") /* * If XSAVES is enabled, it replaces XSAVEC because it supports supervisor * states in addition to XSAVEC. * * Otherwise if XSAVEC is enabled, it replaces XSAVEOPT because it supports * compacted storage format in addition to XSAVEOPT. * * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT * supports modified optimization which is not supported by XSAVE. * * Use XSAVE as a fallback. */ #define XSTATE_XSAVE(st, lmask, hmask, err) \ asm volatile("1: " ALTERNATIVE_3(XSAVE, \ XSAVEOPT, X86_FEATURE_XSAVEOPT, \ XSAVEC, X86_FEATURE_XSAVEC, \ XSAVES, X86_FEATURE_XSAVES) \ "\n" \ "xor %[err], %[err]\n" \ "3:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG, %[err]) \ : [err] "=r" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") /* * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact * XSAVE area format. */ #define XSTATE_XRESTORE(st, lmask, hmask) \ asm volatile("1: " ALTERNATIVE(XRSTOR, \ XRSTORS, X86_FEATURE_XSAVES) \ "\n" \ "3:\n" \ _ASM_EXTABLE_TYPE(1b, 3b, EX_TYPE_FPU_RESTORE) \ : \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") #if defined(CONFIG_X86_64) && defined(CONFIG_X86_DEBUG_FPU) extern void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor); #else static inline void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rstor) { } #endif #ifdef CONFIG_X86_64 static inline void xfd_set_state(u64 xfd) { wrmsrl(MSR_IA32_XFD, xfd); __this_cpu_write(xfd_state, xfd); } static inline void xfd_update_state(struct fpstate *fpstate) { if (fpu_state_size_dynamic()) { u64 xfd = fpstate->xfd; if (__this_cpu_read(xfd_state) != xfd) xfd_set_state(xfd); } } extern int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu); #else static inline void xfd_set_state(u64 xfd) { } static inline void xfd_update_state(struct fpstate *fpstate) { } static inline int __xfd_enable_feature(u64 which, struct fpu_guest *guest_fpu) { return -EPERM; } #endif /* * Save processor xstate to xsave area. * * Uses either XSAVE or XSAVEOPT or XSAVES depending on the CPU features * and command line options. The choice is permanent until the next reboot. */ static inline void os_xsave(struct fpstate *fpstate) { u64 mask = fpstate->xfeatures; u32 lmask = mask; u32 hmask = mask >> 32; int err; WARN_ON_FPU(!alternatives_patched); xfd_validate_state(fpstate, mask, false); XSTATE_XSAVE(&fpstate->regs.xsave, lmask, hmask, err); /* We should never fault when copying to a kernel buffer: */ WARN_ON_FPU(err); } /* * Restore processor xstate from xsave area. * * Uses XRSTORS when XSAVES is used, XRSTOR otherwise. */ static inline void os_xrstor(struct fpstate *fpstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; xfd_validate_state(fpstate, mask, true); XSTATE_XRESTORE(&fpstate->regs.xsave, lmask, hmask); } /* Restore of supervisor state. Does not require XFD */ static inline void os_xrstor_supervisor(struct fpstate *fpstate) { u64 mask = xfeatures_mask_supervisor(); u32 lmask = mask; u32 hmask = mask >> 32; XSTATE_XRESTORE(&fpstate->regs.xsave, lmask, hmask); } /* * XSAVE itself always writes all requested xfeatures. Removing features * from the request bitmap reduces the features which are written. * Generate a mask of features which must be written to a sigframe. The * unset features can be optimized away and not written. * * This optimization is user-visible. Only use for states where * uninitialized sigframe contents are tolerable, like dynamic features. * * Users of buffers produced with this optimization must check XSTATE_BV * to determine which features have been optimized out. */ static inline u64 xfeatures_need_sigframe_write(void) { u64 xfeaures_to_write; /* In-use features must be written: */ xfeaures_to_write = xfeatures_in_use(); /* Also write all non-optimizable sigframe features: */ xfeaures_to_write |= XFEATURE_MASK_USER_SUPPORTED & ~XFEATURE_MASK_SIGFRAME_INITOPT; return xfeaures_to_write; } /* * Save xstate to user space xsave area. * * We don't use modified optimization because xrstor/xrstors might track * a different application. * * We don't use compacted format xsave area for backward compatibility for * old applications which don't understand the compacted format of the * xsave area. * * The caller has to zero buf::header before calling this because XSAVE* * does not touch the reserved fields in the header. */ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkru) { /* * Include the features which are not xsaved/rstored by the kernel * internally, e.g. PKRU. That's user space ABI and also required * to allow the signal handler to modify PKRU. */ struct fpstate *fpstate = current->thread.fpu.fpstate; u64 mask = fpstate->user_xfeatures; u32 lmask; u32 hmask; int err; /* Optimize away writing unnecessary xfeatures: */ if (fpu_state_size_dynamic()) mask &= xfeatures_need_sigframe_write(); lmask = mask; hmask = mask >> 32; xfd_validate_state(fpstate, mask, false); stac(); XSTATE_OP(XSAVE, buf, lmask, hmask, err); clac(); if (!err) err = update_pkru_in_sigframe(buf, mask, pkru); return err; } /* * Restore xstate from user space xsave area. */ static inline int xrstor_from_user_sigframe(struct xregs_state __user *buf, u64 mask) { struct xregs_state *xstate = ((__force struct xregs_state *)buf); u32 lmask = mask; u32 hmask = mask >> 32; int err; xfd_validate_state(current->thread.fpu.fpstate, mask, true); stac(); XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); clac(); return err; } /* * Restore xstate from kernel space xsave area, return an error code instead of * an exception. */ static inline int os_xrstor_safe(struct fpstate *fpstate, u64 mask) { struct xregs_state *xstate = &fpstate->regs.xsave; u32 lmask = mask; u32 hmask = mask >> 32; int err; /* Ensure that XFD is up to date */ xfd_update_state(fpstate); if (cpu_feature_enabled(X86_FEATURE_XSAVES)) XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); return err; } #endif |
| 1691 561 43231 539 20577 20610 18052 539 537 20591 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_KERNEL_FPU_CONTEXT_H #define __X86_KERNEL_FPU_CONTEXT_H #include <asm/fpu/xstate.h> #include <asm/trace/fpu.h> /* Functions related to FPU context tracking */ /* * The in-register FPU state for an FPU context on a CPU is assumed to be * valid if the fpu->last_cpu matches the CPU, and the fpu_fpregs_owner_ctx * matches the FPU. * * If the FPU register state is valid, the kernel can skip restoring the * FPU state from memory. * * Any code that clobbers the FPU registers or updates the in-memory * FPU state for a task MUST let the rest of the kernel know that the * FPU registers are no longer valid for this task. * * Invalidate a resource you control: CPU if using the CPU for something else * (with preemption disabled), FPU for the current task, or a task that * is prevented from running by the current task. */ static inline void __cpu_invalidate_fpregs_state(void) { __this_cpu_write(fpu_fpregs_owner_ctx, NULL); } static inline void __fpu_invalidate_fpregs_state(struct fpu *fpu) { fpu->last_cpu = -1; } static inline int fpregs_state_valid(struct fpu *fpu, unsigned int cpu) { return fpu == this_cpu_read(fpu_fpregs_owner_ctx) && cpu == fpu->last_cpu; } static inline void fpregs_deactivate(struct fpu *fpu) { __this_cpu_write(fpu_fpregs_owner_ctx, NULL); trace_x86_fpu_regs_deactivated(fpu); } static inline void fpregs_activate(struct fpu *fpu) { __this_cpu_write(fpu_fpregs_owner_ctx, fpu); trace_x86_fpu_regs_activated(fpu); } /* Internal helper for switch_fpu_return() and signal frame setup */ static inline void fpregs_restore_userregs(void) { struct fpu *fpu = ¤t->thread.fpu; int cpu = smp_processor_id(); if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_USER_WORKER))) return; if (!fpregs_state_valid(fpu, cpu)) { /* * This restores _all_ xstate which has not been * established yet. * * If PKRU is enabled, then the PKRU value is already * correct because it was either set in switch_to() or in * flush_thread(). So it is excluded because it might be * not up to date in current->thread.fpu.xsave state. * * XFD state is handled in restore_fpregs_from_fpstate(). */ restore_fpregs_from_fpstate(fpu->fpstate, XFEATURE_MASK_FPSTATE); fpregs_activate(fpu); fpu->last_cpu = cpu; } clear_thread_flag(TIF_NEED_FPU_LOAD); } #endif |
| 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Helpers for controlling modem lines via GPIO * * Copyright (C) 2014 Paratronic S.A. */ #include <linux/err.h> #include <linux/device.h> #include <linux/irq.h> #include <linux/gpio/consumer.h> #include <linux/termios.h> #include <linux/serial_core.h> #include <linux/module.h> #include <linux/property.h> #include "serial_mctrl_gpio.h" struct mctrl_gpios { struct uart_port *port; struct gpio_desc *gpio[UART_GPIO_MAX]; int irq[UART_GPIO_MAX]; unsigned int mctrl_prev; bool mctrl_on; }; static const struct { const char *name; unsigned int mctrl; enum gpiod_flags flags; } mctrl_gpios_desc[UART_GPIO_MAX] = { { "cts", TIOCM_CTS, GPIOD_IN, }, { "dsr", TIOCM_DSR, GPIOD_IN, }, { "dcd", TIOCM_CD, GPIOD_IN, }, { "rng", TIOCM_RNG, GPIOD_IN, }, { "rts", TIOCM_RTS, GPIOD_OUT_LOW, }, { "dtr", TIOCM_DTR, GPIOD_OUT_LOW, }, }; static bool mctrl_gpio_flags_is_dir_out(unsigned int idx) { return mctrl_gpios_desc[idx].flags & GPIOD_FLAGS_BIT_DIR_OUT; } /** * mctrl_gpio_set - set gpios according to mctrl state * @gpios: gpios to set * @mctrl: state to set * * Set the gpios according to the mctrl state. */ void mctrl_gpio_set(struct mctrl_gpios *gpios, unsigned int mctrl) { enum mctrl_gpio_idx i; struct gpio_desc *desc_array[UART_GPIO_MAX]; DECLARE_BITMAP(values, UART_GPIO_MAX); unsigned int count = 0; if (gpios == NULL) return; for (i = 0; i < UART_GPIO_MAX; i++) if (gpios->gpio[i] && mctrl_gpio_flags_is_dir_out(i)) { desc_array[count] = gpios->gpio[i]; __assign_bit(count, values, mctrl & mctrl_gpios_desc[i].mctrl); count++; } gpiod_set_array_value(count, desc_array, NULL, values); } EXPORT_SYMBOL_GPL(mctrl_gpio_set); /** * mctrl_gpio_to_gpiod - obtain gpio_desc of modem line index * @gpios: gpios to look into * @gidx: index of the modem line * Returns: the gpio_desc structure associated to the modem line index */ struct gpio_desc *mctrl_gpio_to_gpiod(struct mctrl_gpios *gpios, enum mctrl_gpio_idx gidx) { if (gpios == NULL) return NULL; return gpios->gpio[gidx]; } EXPORT_SYMBOL_GPL(mctrl_gpio_to_gpiod); /** * mctrl_gpio_get - update mctrl with the gpios values. * @gpios: gpios to get the info from * @mctrl: mctrl to set * Returns: modified mctrl (the same value as in @mctrl) * * Update mctrl with the gpios values. */ unsigned int mctrl_gpio_get(struct mctrl_gpios *gpios, unsigned int *mctrl) { enum mctrl_gpio_idx i; if (gpios == NULL) return *mctrl; for (i = 0; i < UART_GPIO_MAX; i++) { if (gpios->gpio[i] && !mctrl_gpio_flags_is_dir_out(i)) { if (gpiod_get_value(gpios->gpio[i])) *mctrl |= mctrl_gpios_desc[i].mctrl; else *mctrl &= ~mctrl_gpios_desc[i].mctrl; } } return *mctrl; } EXPORT_SYMBOL_GPL(mctrl_gpio_get); unsigned int mctrl_gpio_get_outputs(struct mctrl_gpios *gpios, unsigned int *mctrl) { enum mctrl_gpio_idx i; if (gpios == NULL) return *mctrl; for (i = 0; i < UART_GPIO_MAX; i++) { if (gpios->gpio[i] && mctrl_gpio_flags_is_dir_out(i)) { if (gpiod_get_value(gpios->gpio[i])) *mctrl |= mctrl_gpios_desc[i].mctrl; else *mctrl &= ~mctrl_gpios_desc[i].mctrl; } } return *mctrl; } EXPORT_SYMBOL_GPL(mctrl_gpio_get_outputs); struct mctrl_gpios *mctrl_gpio_init_noauto(struct device *dev, unsigned int idx) { struct mctrl_gpios *gpios; enum mctrl_gpio_idx i; gpios = devm_kzalloc(dev, sizeof(*gpios), GFP_KERNEL); if (!gpios) return ERR_PTR(-ENOMEM); for (i = 0; i < UART_GPIO_MAX; i++) { char *gpio_str; bool present; /* Check if GPIO property exists and continue if not */ gpio_str = kasprintf(GFP_KERNEL, "%s-gpios", mctrl_gpios_desc[i].name); if (!gpio_str) continue; present = device_property_present(dev, gpio_str); kfree(gpio_str); if (!present) continue; gpios->gpio[i] = devm_gpiod_get_index_optional(dev, mctrl_gpios_desc[i].name, idx, mctrl_gpios_desc[i].flags); if (IS_ERR(gpios->gpio[i])) return ERR_CAST(gpios->gpio[i]); } return gpios; } EXPORT_SYMBOL_GPL(mctrl_gpio_init_noauto); #define MCTRL_ANY_DELTA (TIOCM_RI | TIOCM_DSR | TIOCM_CD | TIOCM_CTS) static irqreturn_t mctrl_gpio_irq_handle(int irq, void *context) { struct mctrl_gpios *gpios = context; struct uart_port *port = gpios->port; u32 mctrl = gpios->mctrl_prev; u32 mctrl_diff; unsigned long flags; mctrl_gpio_get(gpios, &mctrl); uart_port_lock_irqsave(port, &flags); mctrl_diff = mctrl ^ gpios->mctrl_prev; gpios->mctrl_prev = mctrl; if (mctrl_diff & MCTRL_ANY_DELTA && port->state != NULL) { if ((mctrl_diff & mctrl) & TIOCM_RI) port->icount.rng++; if ((mctrl_diff & mctrl) & TIOCM_DSR) port->icount.dsr++; if (mctrl_diff & TIOCM_CD) uart_handle_dcd_change(port, mctrl & TIOCM_CD); if (mctrl_diff & TIOCM_CTS) uart_handle_cts_change(port, mctrl & TIOCM_CTS); wake_up_interruptible(&port->state->port.delta_msr_wait); } uart_port_unlock_irqrestore(port, flags); return IRQ_HANDLED; } /** * mctrl_gpio_init - initialize uart gpios * @port: port to initialize gpios for * @idx: index of the gpio in the @port's device * * This will get the {cts,rts,...}-gpios from device tree if they are present * and request them, set direction etc, and return an allocated structure. * `devm_*` functions are used, so there's no need to call mctrl_gpio_free(). * As this sets up the irq handling, make sure to not handle changes to the * gpio input lines in your driver, too. */ struct mctrl_gpios *mctrl_gpio_init(struct uart_port *port, unsigned int idx) { struct mctrl_gpios *gpios; enum mctrl_gpio_idx i; gpios = mctrl_gpio_init_noauto(port->dev, idx); if (IS_ERR(gpios)) return gpios; gpios->port = port; for (i = 0; i < UART_GPIO_MAX; ++i) { int ret; if (!gpios->gpio[i] || mctrl_gpio_flags_is_dir_out(i)) continue; ret = gpiod_to_irq(gpios->gpio[i]); if (ret < 0) { dev_err(port->dev, "failed to find corresponding irq for %s (idx=%d, err=%d)\n", mctrl_gpios_desc[i].name, idx, ret); return ERR_PTR(ret); } gpios->irq[i] = ret; /* irqs should only be enabled in .enable_ms */ irq_set_status_flags(gpios->irq[i], IRQ_NOAUTOEN); ret = devm_request_irq(port->dev, gpios->irq[i], mctrl_gpio_irq_handle, IRQ_TYPE_EDGE_BOTH, dev_name(port->dev), gpios); if (ret) { /* alternatively implement polling */ dev_err(port->dev, "failed to request irq for %s (idx=%d, err=%d)\n", mctrl_gpios_desc[i].name, idx, ret); return ERR_PTR(ret); } } return gpios; } EXPORT_SYMBOL_GPL(mctrl_gpio_init); /** * mctrl_gpio_free - explicitly free uart gpios * @dev: uart port's device * @gpios: gpios structure to be freed * * This will free the requested gpios in mctrl_gpio_init(). As `devm_*` * functions are used, there's generally no need to call this function. */ void mctrl_gpio_free(struct device *dev, struct mctrl_gpios *gpios) { enum mctrl_gpio_idx i; if (gpios == NULL) return; for (i = 0; i < UART_GPIO_MAX; i++) { if (gpios->irq[i]) devm_free_irq(gpios->port->dev, gpios->irq[i], gpios); if (gpios->gpio[i]) devm_gpiod_put(dev, gpios->gpio[i]); } devm_kfree(dev, gpios); } EXPORT_SYMBOL_GPL(mctrl_gpio_free); /** * mctrl_gpio_enable_ms - enable irqs and handling of changes to the ms lines * @gpios: gpios to enable */ void mctrl_gpio_enable_ms(struct mctrl_gpios *gpios) { enum mctrl_gpio_idx i; if (gpios == NULL) return; /* .enable_ms may be called multiple times */ if (gpios->mctrl_on) return; gpios->mctrl_on = true; /* get initial status of modem lines GPIOs */ mctrl_gpio_get(gpios, &gpios->mctrl_prev); for (i = 0; i < UART_GPIO_MAX; ++i) { if (!gpios->irq[i]) continue; enable_irq(gpios->irq[i]); } } EXPORT_SYMBOL_GPL(mctrl_gpio_enable_ms); /** * mctrl_gpio_disable_ms - disable irqs and handling of changes to the ms lines * @gpios: gpios to disable */ void mctrl_gpio_disable_ms(struct mctrl_gpios *gpios) { enum mctrl_gpio_idx i; if (gpios == NULL) return; if (!gpios->mctrl_on) return; gpios->mctrl_on = false; for (i = 0; i < UART_GPIO_MAX; ++i) { if (!gpios->irq[i]) continue; disable_irq(gpios->irq[i]); } } EXPORT_SYMBOL_GPL(mctrl_gpio_disable_ms); void mctrl_gpio_enable_irq_wake(struct mctrl_gpios *gpios) { enum mctrl_gpio_idx i; if (!gpios) return; if (!gpios->mctrl_on) return; for (i = 0; i < UART_GPIO_MAX; ++i) { if (!gpios->irq[i]) continue; enable_irq_wake(gpios->irq[i]); } } EXPORT_SYMBOL_GPL(mctrl_gpio_enable_irq_wake); void mctrl_gpio_disable_irq_wake(struct mctrl_gpios *gpios) { enum mctrl_gpio_idx i; if (!gpios) return; if (!gpios->mctrl_on) return; for (i = 0; i < UART_GPIO_MAX; ++i) { if (!gpios->irq[i]) continue; disable_irq_wake(gpios->irq[i]); } } EXPORT_SYMBOL_GPL(mctrl_gpio_disable_irq_wake); MODULE_DESCRIPTION("Helpers for controlling modem lines via GPIO"); MODULE_LICENSE("GPL"); |
| 1 1 1 1 2 2 2 1 1 1 1 1 1 2 3 3 9 12 12 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2018 Oracle and/or its affiliates. All rights reserved. */ #include <crypto/aead.h> #include <linux/debugfs.h> #include <net/xfrm.h> #include "netdevsim.h" #define NSIM_IPSEC_AUTH_BITS 128 static ssize_t nsim_dbg_netdev_ops_read(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { struct netdevsim *ns = filp->private_data; struct nsim_ipsec *ipsec = &ns->ipsec; size_t bufsize; char *buf, *p; int len; int i; /* the buffer needed is * (num SAs * 3 lines each * ~60 bytes per line) + one more line */ bufsize = (ipsec->count * 4 * 60) + 60; buf = kzalloc(bufsize, GFP_KERNEL); if (!buf) return -ENOMEM; p = buf; p += scnprintf(p, bufsize - (p - buf), "SA count=%u tx=%u\n", ipsec->count, ipsec->tx); for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) { struct nsim_sa *sap = &ipsec->sa[i]; if (!sap->used) continue; if (sap->xs->props.family == AF_INET6) p += scnprintf(p, bufsize - (p - buf), "sa[%i] %cx ipaddr=%pI6c\n", i, (sap->rx ? 'r' : 't'), &sap->ipaddr); else p += scnprintf(p, bufsize - (p - buf), "sa[%i] %cx ipaddr=%pI4\n", i, (sap->rx ? 'r' : 't'), &sap->ipaddr[3]); p += scnprintf(p, bufsize - (p - buf), "sa[%i] spi=0x%08x proto=0x%x salt=0x%08x crypt=%d\n", i, be32_to_cpu(sap->xs->id.spi), sap->xs->id.proto, sap->salt, sap->crypt); p += scnprintf(p, bufsize - (p - buf), "sa[%i] key=0x%08x %08x %08x %08x\n", i, sap->key[0], sap->key[1], sap->key[2], sap->key[3]); } len = simple_read_from_buffer(buffer, count, ppos, buf, p - buf); kfree(buf); return len; } static const struct file_operations ipsec_dbg_fops = { .owner = THIS_MODULE, .open = simple_open, .read = nsim_dbg_netdev_ops_read, }; static int nsim_ipsec_find_empty_idx(struct nsim_ipsec *ipsec) { u32 i; if (ipsec->count == NSIM_IPSEC_MAX_SA_COUNT) return -ENOSPC; /* search sa table */ for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) { if (!ipsec->sa[i].used) return i; } return -ENOSPC; } static int nsim_ipsec_parse_proto_keys(struct xfrm_state *xs, u32 *mykey, u32 *mysalt) { const char aes_gcm_name[] = "rfc4106(gcm(aes))"; struct net_device *dev = xs->xso.real_dev; unsigned char *key_data; char *alg_name = NULL; int key_len; if (!xs->aead) { netdev_err(dev, "Unsupported IPsec algorithm\n"); return -EINVAL; } if (xs->aead->alg_icv_len != NSIM_IPSEC_AUTH_BITS) { netdev_err(dev, "IPsec offload requires %d bit authentication\n", NSIM_IPSEC_AUTH_BITS); return -EINVAL; } key_data = &xs->aead->alg_key[0]; key_len = xs->aead->alg_key_len; alg_name = xs->aead->alg_name; if (strcmp(alg_name, aes_gcm_name)) { netdev_err(dev, "Unsupported IPsec algorithm - please use %s\n", aes_gcm_name); return -EINVAL; } /* 160 accounts for 16 byte key and 4 byte salt */ if (key_len > NSIM_IPSEC_AUTH_BITS) { *mysalt = ((u32 *)key_data)[4]; } else if (key_len == NSIM_IPSEC_AUTH_BITS) { *mysalt = 0; } else { netdev_err(dev, "IPsec hw offload only supports 128 bit keys with optional 32 bit salt\n"); return -EINVAL; } memcpy(mykey, key_data, 16); return 0; } static int nsim_ipsec_add_sa(struct xfrm_state *xs, struct netlink_ext_ack *extack) { struct nsim_ipsec *ipsec; struct net_device *dev; struct netdevsim *ns; struct nsim_sa sa; u16 sa_idx; int ret; dev = xs->xso.real_dev; ns = netdev_priv(dev); ipsec = &ns->ipsec; if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) { NL_SET_ERR_MSG_MOD(extack, "Unsupported protocol for ipsec offload"); return -EINVAL; } if (xs->calg) { NL_SET_ERR_MSG_MOD(extack, "Compression offload not supported"); return -EINVAL; } if (xs->xso.type != XFRM_DEV_OFFLOAD_CRYPTO) { NL_SET_ERR_MSG_MOD(extack, "Unsupported ipsec offload type"); return -EINVAL; } /* find the first unused index */ ret = nsim_ipsec_find_empty_idx(ipsec); if (ret < 0) { NL_SET_ERR_MSG_MOD(extack, "No space for SA in Rx table!"); return ret; } sa_idx = (u16)ret; memset(&sa, 0, sizeof(sa)); sa.used = true; sa.xs = xs; if (sa.xs->id.proto & IPPROTO_ESP) sa.crypt = xs->ealg || xs->aead; /* get the key and salt */ ret = nsim_ipsec_parse_proto_keys(xs, sa.key, &sa.salt); if (ret) { NL_SET_ERR_MSG_MOD(extack, "Failed to get key data for SA table"); return ret; } if (xs->xso.dir == XFRM_DEV_OFFLOAD_IN) sa.rx = true; if (xs->props.family == AF_INET6) memcpy(sa.ipaddr, &xs->id.daddr.a6, 16); else memcpy(&sa.ipaddr[3], &xs->id.daddr.a4, 4); /* the preparations worked, so save the info */ memcpy(&ipsec->sa[sa_idx], &sa, sizeof(sa)); /* the XFRM stack doesn't like offload_handle == 0, * so add a bitflag in case our array index is 0 */ xs->xso.offload_handle = sa_idx | NSIM_IPSEC_VALID; ipsec->count++; return 0; } static void nsim_ipsec_del_sa(struct xfrm_state *xs) { struct netdevsim *ns = netdev_priv(xs->xso.real_dev); struct nsim_ipsec *ipsec = &ns->ipsec; u16 sa_idx; sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID; if (!ipsec->sa[sa_idx].used) { netdev_err(ns->netdev, "Invalid SA for delete sa_idx=%d\n", sa_idx); return; } memset(&ipsec->sa[sa_idx], 0, sizeof(struct nsim_sa)); ipsec->count--; } static bool nsim_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) { struct netdevsim *ns = netdev_priv(xs->xso.real_dev); struct nsim_ipsec *ipsec = &ns->ipsec; ipsec->ok++; return true; } static const struct xfrmdev_ops nsim_xfrmdev_ops = { .xdo_dev_state_add = nsim_ipsec_add_sa, .xdo_dev_state_delete = nsim_ipsec_del_sa, .xdo_dev_offload_ok = nsim_ipsec_offload_ok, }; bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb) { struct sec_path *sp = skb_sec_path(skb); struct nsim_ipsec *ipsec = &ns->ipsec; struct xfrm_state *xs; struct nsim_sa *tsa; u32 sa_idx; /* do we even need to check this packet? */ if (!sp) return true; if (unlikely(!sp->len)) { netdev_err(ns->netdev, "no xfrm state len = %d\n", sp->len); return false; } xs = xfrm_input_state(skb); if (unlikely(!xs)) { netdev_err(ns->netdev, "no xfrm_input_state() xs = %p\n", xs); return false; } sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID; if (unlikely(sa_idx >= NSIM_IPSEC_MAX_SA_COUNT)) { netdev_err(ns->netdev, "bad sa_idx=%d max=%d\n", sa_idx, NSIM_IPSEC_MAX_SA_COUNT); return false; } tsa = &ipsec->sa[sa_idx]; if (unlikely(!tsa->used)) { netdev_err(ns->netdev, "unused sa_idx=%d\n", sa_idx); return false; } if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) { netdev_err(ns->netdev, "unexpected proto=%d\n", xs->id.proto); return false; } ipsec->tx++; return true; } void nsim_ipsec_init(struct netdevsim *ns) { ns->netdev->xfrmdev_ops = &nsim_xfrmdev_ops; #define NSIM_ESP_FEATURES (NETIF_F_HW_ESP | \ NETIF_F_HW_ESP_TX_CSUM | \ NETIF_F_GSO_ESP) ns->netdev->features |= NSIM_ESP_FEATURES; ns->netdev->hw_enc_features |= NSIM_ESP_FEATURES; ns->ipsec.pfile = debugfs_create_file("ipsec", 0400, ns->nsim_dev_port->ddir, ns, &ipsec_dbg_fops); } void nsim_ipsec_teardown(struct netdevsim *ns) { struct nsim_ipsec *ipsec = &ns->ipsec; if (ipsec->count) netdev_err(ns->netdev, "tearing down IPsec offload with %d SAs left\n", ipsec->count); debugfs_remove_recursive(ipsec->pfile); } |
| 28 29 1 1 1 1 29 29 29 29 29 29 29 29 4 4 4 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Request key authorisation token key definition. * * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * See Documentation/security/keys/request-key.rst */ #include <linux/sched.h> #include <linux/err.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/uaccess.h> #include "internal.h" #include <keys/request_key_auth-type.h> static int request_key_auth_preparse(struct key_preparsed_payload *); static void request_key_auth_free_preparse(struct key_preparsed_payload *); static int request_key_auth_instantiate(struct key *, struct key_preparsed_payload *); static void request_key_auth_describe(const struct key *, struct seq_file *); static void request_key_auth_revoke(struct key *); static void request_key_auth_destroy(struct key *); static long request_key_auth_read(const struct key *, char *, size_t); /* * The request-key authorisation key type definition. */ struct key_type key_type_request_key_auth = { .name = ".request_key_auth", .def_datalen = sizeof(struct request_key_auth), .preparse = request_key_auth_preparse, .free_preparse = request_key_auth_free_preparse, .instantiate = request_key_auth_instantiate, .describe = request_key_auth_describe, .revoke = request_key_auth_revoke, .destroy = request_key_auth_destroy, .read = request_key_auth_read, }; static int request_key_auth_preparse(struct key_preparsed_payload *prep) { return 0; } static void request_key_auth_free_preparse(struct key_preparsed_payload *prep) { } /* * Instantiate a request-key authorisation key. */ static int request_key_auth_instantiate(struct key *key, struct key_preparsed_payload *prep) { rcu_assign_keypointer(key, (struct request_key_auth *)prep->data); return 0; } /* * Describe an authorisation token. */ static void request_key_auth_describe(const struct key *key, struct seq_file *m) { struct request_key_auth *rka = dereference_key_rcu(key); if (!rka) return; seq_puts(m, "key:"); seq_puts(m, key->description); if (key_is_positive(key)) seq_printf(m, " pid:%d ci:%zu", rka->pid, rka->callout_len); } /* * Read the callout_info data (retrieves the callout information). * - the key's semaphore is read-locked */ static long request_key_auth_read(const struct key *key, char *buffer, size_t buflen) { struct request_key_auth *rka = dereference_key_locked(key); size_t datalen; long ret; if (!rka) return -EKEYREVOKED; datalen = rka->callout_len; ret = datalen; /* we can return the data as is */ if (buffer && buflen > 0) { if (buflen > datalen) buflen = datalen; memcpy(buffer, rka->callout_info, buflen); } return ret; } static void free_request_key_auth(struct request_key_auth *rka) { if (!rka) return; key_put(rka->target_key); key_put(rka->dest_keyring); if (rka->cred) put_cred(rka->cred); kfree(rka->callout_info); kfree(rka); } /* * Dispose of the request_key_auth record under RCU conditions */ static void request_key_auth_rcu_disposal(struct rcu_head *rcu) { struct request_key_auth *rka = container_of(rcu, struct request_key_auth, rcu); free_request_key_auth(rka); } /* * Handle revocation of an authorisation token key. * * Called with the key sem write-locked. */ static void request_key_auth_revoke(struct key *key) { struct request_key_auth *rka = dereference_key_locked(key); kenter("{%d}", key->serial); rcu_assign_keypointer(key, NULL); call_rcu(&rka->rcu, request_key_auth_rcu_disposal); } /* * Destroy an instantiation authorisation token key. */ static void request_key_auth_destroy(struct key *key) { struct request_key_auth *rka = rcu_access_pointer(key->payload.rcu_data0); kenter("{%d}", key->serial); if (rka) { rcu_assign_keypointer(key, NULL); call_rcu(&rka->rcu, request_key_auth_rcu_disposal); } } /* * Create an authorisation token for /sbin/request-key or whoever to gain * access to the caller's security data. */ struct key *request_key_auth_new(struct key *target, const char *op, const void *callout_info, size_t callout_len, struct key *dest_keyring) { struct request_key_auth *rka, *irka; const struct cred *cred = current_cred(); struct key *authkey = NULL; char desc[20]; int ret = -ENOMEM; kenter("%d,", target->serial); /* allocate a auth record */ rka = kzalloc(sizeof(*rka), GFP_KERNEL); if (!rka) goto error; rka->callout_info = kmemdup(callout_info, callout_len, GFP_KERNEL); if (!rka->callout_info) goto error_free_rka; rka->callout_len = callout_len; strscpy(rka->op, op, sizeof(rka->op)); /* see if the calling process is already servicing the key request of * another process */ if (cred->request_key_auth) { /* it is - use that instantiation context here too */ down_read(&cred->request_key_auth->sem); /* if the auth key has been revoked, then the key we're * servicing is already instantiated */ if (test_bit(KEY_FLAG_REVOKED, &cred->request_key_auth->flags)) { up_read(&cred->request_key_auth->sem); ret = -EKEYREVOKED; goto error_free_rka; } irka = cred->request_key_auth->payload.data[0]; rka->cred = get_cred(irka->cred); rka->pid = irka->pid; up_read(&cred->request_key_auth->sem); } else { /* it isn't - use this process as the context */ rka->cred = get_cred(cred); rka->pid = current->pid; } rka->target_key = key_get(target); rka->dest_keyring = key_get(dest_keyring); /* allocate the auth key */ sprintf(desc, "%x", target->serial); authkey = key_alloc(&key_type_request_key_auth, desc, cred->fsuid, cred->fsgid, cred, KEY_POS_VIEW | KEY_POS_READ | KEY_POS_SEARCH | KEY_POS_LINK | KEY_USR_VIEW, KEY_ALLOC_NOT_IN_QUOTA, NULL); if (IS_ERR(authkey)) { ret = PTR_ERR(authkey); goto error_free_rka; } /* construct the auth key */ ret = key_instantiate_and_link(authkey, rka, 0, NULL, NULL); if (ret < 0) goto error_put_authkey; kleave(" = {%d,%d}", authkey->serial, refcount_read(&authkey->usage)); return authkey; error_put_authkey: key_put(authkey); error_free_rka: free_request_key_auth(rka); error: kleave("= %d", ret); return ERR_PTR(ret); } /* * Search the current process's keyrings for the authorisation key for * instantiation of a key. */ struct key *key_get_instantiation_authkey(key_serial_t target_id) { char description[16]; struct keyring_search_context ctx = { .index_key.type = &key_type_request_key_auth, .index_key.description = description, .cred = current_cred(), .match_data.cmp = key_default_cmp, .match_data.raw_data = description, .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT, .flags = (KEYRING_SEARCH_DO_STATE_CHECK | KEYRING_SEARCH_RECURSE), }; struct key *authkey; key_ref_t authkey_ref; ctx.index_key.desc_len = sprintf(description, "%x", target_id); rcu_read_lock(); authkey_ref = search_process_keyrings_rcu(&ctx); rcu_read_unlock(); if (IS_ERR(authkey_ref)) { authkey = ERR_CAST(authkey_ref); if (authkey == ERR_PTR(-EAGAIN)) authkey = ERR_PTR(-ENOKEY); goto error; } authkey = key_ref_to_ptr(authkey_ref); if (test_bit(KEY_FLAG_REVOKED, &authkey->flags)) { key_put(authkey); authkey = ERR_PTR(-EKEYREVOKED); } error: return authkey; } |
| 180 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * procfs namespace bits */ #ifndef _LINUX_PROC_NS_H #define _LINUX_PROC_NS_H #include <linux/ns_common.h> struct pid_namespace; struct nsset; struct path; struct task_struct; struct inode; struct proc_ns_operations { const char *name; const char *real_ns_name; int type; struct ns_common *(*get)(struct task_struct *task); void (*put)(struct ns_common *ns); int (*install)(struct nsset *nsset, struct ns_common *ns); struct user_namespace *(*owner)(struct ns_common *ns); struct ns_common *(*get_parent)(struct ns_common *ns); } __randomize_layout; extern const struct proc_ns_operations netns_operations; extern const struct proc_ns_operations utsns_operations; extern const struct proc_ns_operations ipcns_operations; extern const struct proc_ns_operations pidns_operations; extern const struct proc_ns_operations pidns_for_children_operations; extern const struct proc_ns_operations userns_operations; extern const struct proc_ns_operations mntns_operations; extern const struct proc_ns_operations cgroupns_operations; extern const struct proc_ns_operations timens_operations; extern const struct proc_ns_operations timens_for_children_operations; /* * We always define these enumerators */ enum { PROC_ROOT_INO = 1, PROC_IPC_INIT_INO = 0xEFFFFFFFU, PROC_UTS_INIT_INO = 0xEFFFFFFEU, PROC_USER_INIT_INO = 0xEFFFFFFDU, PROC_PID_INIT_INO = 0xEFFFFFFCU, PROC_CGROUP_INIT_INO = 0xEFFFFFFBU, PROC_TIME_INIT_INO = 0xEFFFFFFAU, }; #ifdef CONFIG_PROC_FS extern int proc_alloc_inum(unsigned int *pino); extern void proc_free_inum(unsigned int inum); #else /* CONFIG_PROC_FS */ static inline int proc_alloc_inum(unsigned int *inum) { *inum = 1; return 0; } static inline void proc_free_inum(unsigned int inum) {} #endif /* CONFIG_PROC_FS */ static inline int ns_alloc_inum(struct ns_common *ns) { WRITE_ONCE(ns->stashed, NULL); return proc_alloc_inum(&ns->inum); } #define ns_free_inum(ns) proc_free_inum((ns)->inum) #define get_proc_ns(inode) ((struct ns_common *)(inode)->i_private) extern int ns_get_path(struct path *path, struct task_struct *task, const struct proc_ns_operations *ns_ops); typedef struct ns_common *ns_get_path_helper_t(void *); extern int ns_get_path_cb(struct path *path, ns_get_path_helper_t ns_get_cb, void *private_data); extern bool ns_match(const struct ns_common *ns, dev_t dev, ino_t ino); extern int ns_get_name(char *buf, size_t size, struct task_struct *task, const struct proc_ns_operations *ns_ops); extern void nsfs_init(void); #endif /* _LINUX_PROC_NS_H */ |
| 3 3 3 3 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (c) International Business Machines Corp., 2006 * * Author: Artem Bityutskiy (Битюцкий Артём) */ #ifndef __UBI_DEBUG_H__ #define __UBI_DEBUG_H__ void ubi_dump_flash(struct ubi_device *ubi, int pnum, int offset, int len); void ubi_dump_ec_hdr(const struct ubi_ec_hdr *ec_hdr); void ubi_dump_vid_hdr(const struct ubi_vid_hdr *vid_hdr); #include <linux/random.h> #define ubi_assert(expr) do { \ if (unlikely(!(expr))) { \ pr_crit("UBI assert failed in %s at %u (pid %d)\n", \ __func__, __LINE__, current->pid); \ dump_stack(); \ } \ } while (0) #define ubi_dbg_print_hex_dump(l, ps, pt, r, g, b, len, a) \ print_hex_dump(l, ps, pt, r, g, b, len, a) #define ubi_dbg_msg(type, fmt, ...) \ pr_debug("UBI DBG " type " (pid %d): " fmt "\n", current->pid, \ ##__VA_ARGS__) /* General debugging messages */ #define dbg_gen(fmt, ...) ubi_dbg_msg("gen", fmt, ##__VA_ARGS__) /* Messages from the eraseblock association sub-system */ #define dbg_eba(fmt, ...) ubi_dbg_msg("eba", fmt, ##__VA_ARGS__) /* Messages from the wear-leveling sub-system */ #define dbg_wl(fmt, ...) ubi_dbg_msg("wl", fmt, ##__VA_ARGS__) /* Messages from the input/output sub-system */ #define dbg_io(fmt, ...) ubi_dbg_msg("io", fmt, ##__VA_ARGS__) /* Initialization and build messages */ #define dbg_bld(fmt, ...) ubi_dbg_msg("bld", fmt, ##__VA_ARGS__) void ubi_dump_vol_info(const struct ubi_volume *vol); void ubi_dump_vtbl_record(const struct ubi_vtbl_record *r, int idx); void ubi_dump_av(const struct ubi_ainf_volume *av); void ubi_dump_aeb(const struct ubi_ainf_peb *aeb, int type); void ubi_dump_mkvol_req(const struct ubi_mkvol_req *req); int ubi_self_check_all_ff(struct ubi_device *ubi, int pnum, int offset, int len); int ubi_debugfs_init(void); void ubi_debugfs_exit(void); int ubi_debugfs_init_dev(struct ubi_device *ubi); void ubi_debugfs_exit_dev(struct ubi_device *ubi); /** * The following function is a legacy implementation of UBI fault-injection * hook. When using more powerful fault injection capabilities, the legacy * fault injection interface should be retained. */ int ubi_dbg_power_cut(struct ubi_device *ubi, int caller); static inline int ubi_dbg_bitflip(const struct ubi_device *ubi) { if (ubi->dbg.emulate_bitflips) return !get_random_u32_below(200); return 0; } static inline int ubi_dbg_write_failure(const struct ubi_device *ubi) { if (ubi->dbg.emulate_io_failures) return !get_random_u32_below(500); return 0; } static inline int ubi_dbg_erase_failure(const struct ubi_device *ubi) { if (ubi->dbg.emulate_io_failures) return !get_random_u32_below(400); return 0; } /** * MASK_XXX: Mask for emulate_failures in ubi_debug_info.The mask is used to * precisely control the type and process of fault injection. */ /* Emulate a power cut when writing EC/VID header */ #define MASK_POWER_CUT_EC (1 << 0) #define MASK_POWER_CUT_VID (1 << 1) /* Emulate a power cut when writing data*/ #define MASK_POWER_CUT_DATA (1 << 2) /* Emulate bit-flips */ #define MASK_BITFLIPS (1 << 3) /* Emulate ecc error */ #define MASK_ECCERR (1 << 4) /* Emulates -EIO during data read */ #define MASK_READ_FAILURE (1 << 5) #define MASK_READ_FAILURE_EC (1 << 6) #define MASK_READ_FAILURE_VID (1 << 7) /* Emulates -EIO during data write */ #define MASK_WRITE_FAILURE (1 << 8) /* Emulates -EIO during erase a PEB*/ #define MASK_ERASE_FAILURE (1 << 9) /* Return UBI_IO_FF when reading EC/VID header */ #define MASK_IO_FF_EC (1 << 10) #define MASK_IO_FF_VID (1 << 11) /* Return UBI_IO_FF_BITFLIPS when reading EC/VID header */ #define MASK_IO_FF_BITFLIPS_EC (1 << 12) #define MASK_IO_FF_BITFLIPS_VID (1 << 13) /* Return UBI_IO_BAD_HDR when reading EC/VID header */ #define MASK_BAD_HDR_EC (1 << 14) #define MASK_BAD_HDR_VID (1 << 15) /* Return UBI_IO_BAD_HDR_EBADMSG when reading EC/VID header */ #define MASK_BAD_HDR_EBADMSG_EC (1 << 16) #define MASK_BAD_HDR_EBADMSG_VID (1 << 17) #ifdef CONFIG_MTD_UBI_FAULT_INJECTION extern bool should_fail_eccerr(void); extern bool should_fail_bitflips(void); extern bool should_fail_read_failure(void); extern bool should_fail_write_failure(void); extern bool should_fail_erase_failure(void); extern bool should_fail_power_cut(void); extern bool should_fail_io_ff(void); extern bool should_fail_io_ff_bitflips(void); extern bool should_fail_bad_hdr(void); extern bool should_fail_bad_hdr_ebadmsg(void); static inline bool ubi_dbg_fail_bitflip(const struct ubi_device *ubi) { if (ubi->dbg.emulate_failures & MASK_BITFLIPS) return should_fail_bitflips(); return false; } static inline bool ubi_dbg_fail_write(const struct ubi_device *ubi) { if (ubi->dbg.emulate_failures & MASK_WRITE_FAILURE) return should_fail_write_failure(); return false; } static inline bool ubi_dbg_fail_erase(const struct ubi_device *ubi) { if (ubi->dbg.emulate_failures & MASK_ERASE_FAILURE) return should_fail_erase_failure(); return false; } static inline bool ubi_dbg_fail_power_cut(const struct ubi_device *ubi, unsigned int caller) { if (ubi->dbg.emulate_failures & caller) return should_fail_power_cut(); return false; } static inline bool ubi_dbg_fail_read(const struct ubi_device *ubi, unsigned int caller) { if (ubi->dbg.emulate_failures & caller) return should_fail_read_failure(); return false; } static inline bool ubi_dbg_fail_eccerr(const struct ubi_device *ubi) { if (ubi->dbg.emulate_failures & MASK_ECCERR) return should_fail_eccerr(); return false; } static inline bool ubi_dbg_fail_ff(const struct ubi_device *ubi, unsigned int caller) { if (ubi->dbg.emulate_failures & caller) return should_fail_io_ff(); return false; } static inline bool ubi_dbg_fail_ff_bitflips(const struct ubi_device *ubi, unsigned int caller) { if (ubi->dbg.emulate_failures & caller) return should_fail_io_ff_bitflips(); return false; } static inline bool ubi_dbg_fail_bad_hdr(const struct ubi_device *ubi, unsigned int caller) { if (ubi->dbg.emulate_failures & caller) return should_fail_bad_hdr(); return false; } static inline bool ubi_dbg_fail_bad_hdr_ebadmsg(const struct ubi_device *ubi, unsigned int caller) { if (ubi->dbg.emulate_failures & caller) return should_fail_bad_hdr_ebadmsg(); return false; } #else /* CONFIG_MTD_UBI_FAULT_INJECTION */ #define ubi_dbg_fail_bitflip(u) false #define ubi_dbg_fail_write(u) false #define ubi_dbg_fail_erase(u) false #define ubi_dbg_fail_power_cut(u, c) false #define ubi_dbg_fail_read(u, c) false #define ubi_dbg_fail_eccerr(u) false #define ubi_dbg_fail_ff(u, c) false #define ubi_dbg_fail_ff_bitflips(u, v) false #define ubi_dbg_fail_bad_hdr(u, c) false #define ubi_dbg_fail_bad_hdr_ebadmsg(u, c) false #endif /** * ubi_dbg_is_power_cut - if it is time to emulate power cut. * @ubi: UBI device description object * * Returns true if power cut should be emulated, otherwise returns false. */ static inline bool ubi_dbg_is_power_cut(struct ubi_device *ubi, unsigned int caller) { if (ubi_dbg_power_cut(ubi, caller)) return true; return ubi_dbg_fail_power_cut(ubi, caller); } /** * ubi_dbg_is_bitflip - if it is time to emulate a bit-flip. * @ubi: UBI device description object * * Returns true if a bit-flip should be emulated, otherwise returns false. */ static inline bool ubi_dbg_is_bitflip(const struct ubi_device *ubi) { if (ubi_dbg_bitflip(ubi)) return true; return ubi_dbg_fail_bitflip(ubi); } /** * ubi_dbg_is_write_failure - if it is time to emulate a write failure. * @ubi: UBI device description object * * Returns true if a write failure should be emulated, otherwise returns * false. */ static inline bool ubi_dbg_is_write_failure(const struct ubi_device *ubi) { if (ubi_dbg_write_failure(ubi)) return true; return ubi_dbg_fail_write(ubi); } /** * ubi_dbg_is_erase_failure - if its time to emulate an erase failure. * @ubi: UBI device description object * * Returns true if an erase failure should be emulated, otherwise returns * false. */ static inline bool ubi_dbg_is_erase_failure(const struct ubi_device *ubi) { if (ubi_dbg_erase_failure(ubi)) return true; return ubi_dbg_fail_erase(ubi); } /** * ubi_dbg_is_eccerr - if it is time to emulate ECC error. * @ubi: UBI device description object * * Returns true if a ECC error should be emulated, otherwise returns false. */ static inline bool ubi_dbg_is_eccerr(const struct ubi_device *ubi) { return ubi_dbg_fail_eccerr(ubi); } /** * ubi_dbg_is_read_failure - if it is time to emulate a read failure. * @ubi: UBI device description object * * Returns true if a read failure should be emulated, otherwise returns * false. */ static inline bool ubi_dbg_is_read_failure(const struct ubi_device *ubi, unsigned int caller) { return ubi_dbg_fail_read(ubi, caller); } /** * ubi_dbg_is_ff - if it is time to emulate that read region is only 0xFF. * @ubi: UBI device description object * * Returns true if read region should be emulated 0xFF, otherwise * returns false. */ static inline bool ubi_dbg_is_ff(const struct ubi_device *ubi, unsigned int caller) { return ubi_dbg_fail_ff(ubi, caller); } /** * ubi_dbg_is_ff_bitflips - if it is time to emulate that read region is only 0xFF * with error reported by the MTD driver * * @ubi: UBI device description object * * Returns true if read region should be emulated 0xFF and error * reported by the MTD driver, otherwise returns false. */ static inline bool ubi_dbg_is_ff_bitflips(const struct ubi_device *ubi, unsigned int caller) { return ubi_dbg_fail_ff_bitflips(ubi, caller); } /** * ubi_dbg_is_bad_hdr - if it is time to emulate a bad header * @ubi: UBI device description object * * Returns true if a bad header error should be emulated, otherwise * returns false. */ static inline bool ubi_dbg_is_bad_hdr(const struct ubi_device *ubi, unsigned int caller) { return ubi_dbg_fail_bad_hdr(ubi, caller); } /** * ubi_dbg_is_bad_hdr_ebadmsg - if it is time to emulate a bad header with * ECC error. * * @ubi: UBI device description object * * Returns true if a bad header with ECC error should be emulated, otherwise * returns false. */ static inline bool ubi_dbg_is_bad_hdr_ebadmsg(const struct ubi_device *ubi, unsigned int caller) { return ubi_dbg_fail_bad_hdr_ebadmsg(ubi, caller); } /** * ubi_dbg_is_bgt_disabled - if the background thread is disabled. * @ubi: UBI device description object * * Returns non-zero if the UBI background thread is disabled for testing * purposes. */ static inline int ubi_dbg_is_bgt_disabled(const struct ubi_device *ubi) { return ubi->dbg.disable_bgt; } static inline int ubi_dbg_chk_io(const struct ubi_device *ubi) { return ubi->dbg.chk_io; } static inline int ubi_dbg_chk_gen(const struct ubi_device *ubi) { return ubi->dbg.chk_gen; } static inline int ubi_dbg_chk_fastmap(const struct ubi_device *ubi) { return ubi->dbg.chk_fastmap; } static inline void ubi_enable_dbg_chk_fastmap(struct ubi_device *ubi) { ubi->dbg.chk_fastmap = 1; } #endif /* !__UBI_DEBUG_H__ */ |
| 511 254 249 254 149 248 254 11 8 308 306 307 306 12 9 12 12 12 207 193 207 119 355 16 14 356 356 356 432 432 424 433 433 431 367 433 352 352 352 209 41 208 352 19 352 350 23 23 352 25 351 117 112 4 4 306 300 300 303 6 17 9 4 4 4 2 9 5 9 315 229 545 542 19 544 130 379 377 546 546 545 68 13 544 379 543 436 437 302 544 10 545 310 544 133 133 133 133 133 546 115 20 114 114 114 115 546 544 306 307 19 19 70 71 70 22 1 1 22 308 35 9 303 308 303 303 306 308 308 306 9 308 115 114 115 308 307 121 121 120 121 307 7 1 2 71 2 71 7 7 7 71 2 1 71 70 71 70 375 375 47 311 312 310 374 123 31 122 374 133 133 375 31 31 31 14 10 10 31 1613 1607 215 215 31 215 27 214 22 214 6 215 190 407 408 408 408 18 18 18 18 18 18 407 408 433 49 36 19 433 475 474 474 442 29 440 443 475 443 474 475 308 352 78 475 475 12 474 475 474 475 475 475 50 49 47 9 9 475 352 9 308 474 61 12 474 474 474 356 474 207 207 474 472 474 474 475 14 475 475 72 471 431 300 75 75 75 270 16 118 5 101 14 14 14 14 14 14 14 87 101 101 101 2 2 17 17 17 17 2 2 17 17 17 17 16 17 17 17 17 13 17 17 17 17 9 9 9 9 5 5 9 9 9 9 9 9 9 9 9 9 404 404 373 4 404 15 404 404 404 4 403 287 286 284 282 1 287 90 287 7 6 6 6 7 254 210 192 168 254 222 105 218 212 218 217 10 7 218 187 13 11 54 26 208 84 107 95 271 271 246 271 270 16 255 271 77 72 89 54 51 20 260 261 10 11 2 10 201 187 84 229 3 4 100 100 101 3 101 101 100 101 101 103 101 96 96 96 91 80 80 54 54 45 42 12 13 1 1 1 1 78 270 3 1 1 1 1 1 1 1 17 261 17 15 15 15 5 5 248 229 248 2 1 248 5 247 5 637 10 191 623 283 254 546 708 546 484 82 252 126 97 97 96 78 78 271 270 271 271 271 271 11 11 11 261 261 91 260 252 261 228 103 222 103 103 103 93 248 101 248 248 248 254 208 254 271 243 270 161 254 253 254 25 254 254 161 328 327 328 328 237 232 231 170 132 230 232 82 231 232 232 233 42 16 16 16 42 5 5 4 1 4 4 4 4 2 2 2 4 4 5 5 271 271 59 57 57 57 352 122 354 5 353 354 85 87 87 74 349 314 350 354 19 19 10 19 2 86 2 2 2 2 2 2 2 2 20 20 20 20 20 20 20 20 20 7 2 2 42 42 31 32 32 32 31 32 13 30 30 26 30 11 30 20 32 32 32 32 32 32 1 1 32 38 28 28 38 28 38 28 37 38 38 38 28 38 38 38 38 38 38 38 8 38 38 38 28 21 28 28 38 26 26 436 419 2 420 87 87 12 73 75 75 87 24 24 24 24 117 117 116 117 111 111 111 111 117 117 71 71 39 70 71 71 32 5 67 62 71 71 1 71 71 70 17 71 7 1 71 1 365 365 364 365 27 364 366 366 362 366 8 7 366 364 366 11 365 305 61 364 365 305 305 132 132 17 15 17 17 15 1 14 14 1 16 15 16 16 14 16 13 8 125 125 42 113 367 366 61 306 306 306 306 306 306 132 179 221 306 8 9 306 367 138 122 71 40 71 71 71 122 59 122 304 303 303 303 304 11 12 12 12 12 6 6 6 4 4 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Implementation of the Transmission Control Protocol(TCP). * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche, <flla@stud.uni-sb.de> * Charles Hedrick, <hedrick@klinzhai.rutgers.edu> * Linus Torvalds, <torvalds@cs.helsinki.fi> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Matthew Dillon, <dillon@apollo.west.oic.com> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Jorge Cwik, <jorge@laser.satlink.net> */ /* * Changes: Pedro Roque : Retransmit queue handled by TCP. * : Fragmentation on mtu decrease * : Segment collapse on retransmit * : AF independence * * Linus Torvalds : send_delayed_ack * David S. Miller : Charge memory using the right skb * during syn/ack processing. * David S. Miller : Output engine completely rewritten. * Andrea Arcangeli: SYNACK carry ts_recent in tsecr. * Cacophonix Gaul : draft-minshall-nagle-01 * J Hadi Salim : ECN support * */ #define pr_fmt(fmt) "TCP: " fmt #include <net/tcp.h> #include <net/mptcp.h> #include <net/proto_memory.h> #include <linux/compiler.h> #include <linux/gfp.h> #include <linux/module.h> #include <linux/static_key.h> #include <linux/skbuff_ref.h> #include <trace/events/tcp.h> /* Refresh clocks of a TCP socket, * ensuring monotically increasing values. */ void tcp_mstamp_refresh(struct tcp_sock *tp) { u64 val = tcp_clock_ns(); tp->tcp_clock_cache = val; tp->tcp_mstamp = div_u64(val, NSEC_PER_USEC); } static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp); /* Account for new data that has been sent to the network. */ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out; WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(skb)->end_seq); __skb_unlink(skb, &sk->sk_write_queue); tcp_rbtree_insert(&sk->tcp_rtx_queue, skb); if (tp->highest_sack == NULL) tp->highest_sack = skb; tp->packets_out += tcp_skb_pcount(skb); if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, tcp_skb_pcount(skb)); tcp_check_space(sk); } /* SND.NXT, if window was not shrunk or the amount of shrunk was less than one * window scaling factor due to loss of precision. * If window has been shrunk, what should we make? It is not clear at all. * Using SND.UNA we will fail to open window, SND.NXT is out of window. :-( * Anything in between SND.UNA...SND.UNA+SND.WND also can be already * invalid. OK, let's make this for now: */ static inline __u32 tcp_acceptable_seq(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); if (!before(tcp_wnd_end(tp), tp->snd_nxt) || (tp->rx_opt.wscale_ok && ((tp->snd_nxt - tcp_wnd_end(tp)) < (1 << tp->rx_opt.rcv_wscale)))) return tp->snd_nxt; else return tcp_wnd_end(tp); } /* Calculate mss to advertise in SYN segment. * RFC1122, RFC1063, draft-ietf-tcpimpl-pmtud-01 state that: * * 1. It is independent of path mtu. * 2. Ideally, it is maximal possible segment size i.e. 65535-40. * 3. For IPv4 it is reasonable to calculate it from maximal MTU of * attached devices, because some buggy hosts are confused by * large MSS. * 4. We do not make 3, we advertise MSS, calculated from first * hop device mtu, but allow to raise it to ip_rt_min_advmss. * This may be overridden via information stored in routing table. * 5. Value 65535 for MSS is valid in IPv6 and means "as large as possible, * probably even Jumbo". */ static __u16 tcp_advertise_mss(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); const struct dst_entry *dst = __sk_dst_get(sk); int mss = tp->advmss; if (dst) { unsigned int metric = dst_metric_advmss(dst); if (metric < mss) { mss = metric; tp->advmss = mss; } } return (__u16)mss; } /* RFC2861. Reset CWND after idle period longer RTO to "restart window". * This is the first part of cwnd validation mechanism. */ void tcp_cwnd_restart(struct sock *sk, s32 delta) { struct tcp_sock *tp = tcp_sk(sk); u32 restart_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk)); u32 cwnd = tcp_snd_cwnd(tp); tcp_ca_event(sk, CA_EVENT_CWND_RESTART); tp->snd_ssthresh = tcp_current_ssthresh(sk); restart_cwnd = min(restart_cwnd, cwnd); while ((delta -= inet_csk(sk)->icsk_rto) > 0 && cwnd > restart_cwnd) cwnd >>= 1; tcp_snd_cwnd_set(tp, max(cwnd, restart_cwnd)); tp->snd_cwnd_stamp = tcp_jiffies32; tp->snd_cwnd_used = 0; } /* Congestion state accounting after a packet has been sent. */ static void tcp_event_data_sent(struct tcp_sock *tp, struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); const u32 now = tcp_jiffies32; if (tcp_packets_in_flight(tp) == 0) tcp_ca_event(sk, CA_EVENT_TX_START); tp->lsndtime = now; /* If it is a reply for ato after last received * packet, increase pingpong count. */ if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) inet_csk_inc_pingpong_cnt(sk); } /* Account for an ACK we sent. */ static inline void tcp_event_ack_sent(struct sock *sk, u32 rcv_nxt) { struct tcp_sock *tp = tcp_sk(sk); if (unlikely(tp->compressed_ack)) { NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED, tp->compressed_ack); tp->compressed_ack = 0; if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1) __sock_put(sk); } if (unlikely(rcv_nxt != tp->rcv_nxt)) return; /* Special ACK sent by DCTCP to reflect ECN */ tcp_dec_quickack_mode(sk); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } /* Determine a window scaling and initial window to offer. * Based on the assumption that the given amount of space * will be offered. Store the results in the tp structure. * NOTE: for smooth operation initial space offering should * be a multiple of mss if possible. We assume here that mss >= 1. * This MUST be enforced by all callers. */ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, __u32 *rcv_wnd, __u32 *__window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd) { unsigned int space = (__space < 0 ? 0 : __space); u32 window_clamp = READ_ONCE(*__window_clamp); /* If no clamp set the clamp to the max possible scaled window */ if (window_clamp == 0) window_clamp = (U16_MAX << TCP_MAX_WSCALE); space = min(window_clamp, space); /* Quantize space offering to a multiple of mss if possible. */ if (space > mss) space = rounddown(space, mss); /* NOTE: offering an initial window larger than 32767 * will break some buggy TCP stacks. If the admin tells us * it is likely we could be speaking with such a buggy stack * we will truncate our initial window offering to 32K-1 * unless the remote has sent us a window scaling option, * which we interpret as a sign the remote TCP is not * misinterpreting the window field as a signed quantity. */ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)) (*rcv_wnd) = min(space, MAX_TCP_WINDOW); else (*rcv_wnd) = space; if (init_rcv_wnd) *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); *rcv_wscale = 0; if (wscale_ok) { /* Set window scaling on max possible window */ space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); space = max_t(u32, space, READ_ONCE(sysctl_rmem_max)); space = min_t(u32, space, window_clamp); *rcv_wscale = clamp_t(int, ilog2(space) - 15, 0, TCP_MAX_WSCALE); } /* Set the clamp no higher than max representable value */ WRITE_ONCE(*__window_clamp, min_t(__u32, U16_MAX << (*rcv_wscale), window_clamp)); } EXPORT_SYMBOL(tcp_select_initial_window); /* Chose a new window to advertise, update state in tcp_sock for the * socket, and return result with RFC1323 scaling applied. The return * value can be stuffed directly into th->window for an outgoing * frame. */ static u16 tcp_select_window(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); u32 old_win = tp->rcv_wnd; u32 cur_win, new_win; /* Make the window 0 if we failed to queue the data because we * are out of memory. The window is temporary, so we don't store * it on the socket. */ if (unlikely(inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOMEM)) return 0; cur_win = tcp_receive_window(tp); new_win = __tcp_select_window(sk); if (new_win < cur_win) { /* Danger Will Robinson! * Don't update rcv_wup/rcv_wnd here or else * we will not be able to advertise a zero * window in time. --DaveM * * Relax Will Robinson. */ if (!READ_ONCE(net->ipv4.sysctl_tcp_shrink_window) || !tp->rx_opt.rcv_wscale) { /* Never shrink the offered window */ if (new_win == 0) NET_INC_STATS(net, LINUX_MIB_TCPWANTZEROWINDOWADV); new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale); } } tp->rcv_wnd = new_win; tp->rcv_wup = tp->rcv_nxt; /* Make sure we do not exceed the maximum possible * scaled window. */ if (!tp->rx_opt.rcv_wscale && READ_ONCE(net->ipv4.sysctl_tcp_workaround_signed_windows)) new_win = min(new_win, MAX_TCP_WINDOW); else new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale)); /* RFC1323 scaling applied */ new_win >>= tp->rx_opt.rcv_wscale; /* If we advertise zero window, disable fast path. */ if (new_win == 0) { tp->pred_flags = 0; if (old_win) NET_INC_STATS(net, LINUX_MIB_TCPTOZEROWINDOWADV); } else if (old_win == 0) { NET_INC_STATS(net, LINUX_MIB_TCPFROMZEROWINDOWADV); } return new_win; } /* Packet ECN state for a SYN-ACK */ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) { const struct tcp_sock *tp = tcp_sk(sk); TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR; if (!(tp->ecn_flags & TCP_ECN_OK)) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE; else if (tcp_ca_needs_ecn(sk) || tcp_bpf_ca_needs_ecn(sk)) INET_ECN_xmit(sk); } /* Packet ECN state for a SYN. */ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk); bool use_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn) == 1 || tcp_ca_needs_ecn(sk) || bpf_needs_ecn; if (!use_ecn) { const struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst_feature(dst, RTAX_FEATURE_ECN)) use_ecn = true; } tp->ecn_flags = 0; if (use_ecn) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; tp->ecn_flags = TCP_ECN_OK; if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn) INET_ECN_xmit(sk); } } static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb) { if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback)) /* tp->ecn_flags are cleared at a later point in time when * SYN ACK is ultimatively being received. */ TCP_SKB_CB(skb)->tcp_flags &= ~(TCPHDR_ECE | TCPHDR_CWR); } static void tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th) { if (inet_rsk(req)->ecn_ok) th->ece = 1; } /* Set up ECN state for a packet on a ESTABLISHED socket that is about to * be sent. */ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb, struct tcphdr *th, int tcp_header_len) { struct tcp_sock *tp = tcp_sk(sk); if (tp->ecn_flags & TCP_ECN_OK) { /* Not-retransmitted data segment: set ECT and inject CWR. */ if (skb->len != tcp_header_len && !before(TCP_SKB_CB(skb)->seq, tp->snd_nxt)) { INET_ECN_xmit(sk); if (tp->ecn_flags & TCP_ECN_QUEUE_CWR) { tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR; th->cwr = 1; skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; } } else if (!tcp_ca_needs_ecn(sk)) { /* ACK or retransmitted segment: clear ECT|CE */ INET_ECN_dontxmit(sk); } if (tp->ecn_flags & TCP_ECN_DEMAND_CWR) th->ece = 1; } } /* Constructs common control bits of non-data skb. If SYN/FIN is present, * auto increment end seqno. */ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags) { skb->ip_summed = CHECKSUM_PARTIAL; TCP_SKB_CB(skb)->tcp_flags = flags; tcp_skb_pcount_set(skb, 1); TCP_SKB_CB(skb)->seq = seq; if (flags & (TCPHDR_SYN | TCPHDR_FIN)) seq++; TCP_SKB_CB(skb)->end_seq = seq; } static inline bool tcp_urg_mode(const struct tcp_sock *tp) { return tp->snd_una != tp->snd_up; } #define OPTION_SACK_ADVERTISE BIT(0) #define OPTION_TS BIT(1) #define OPTION_MD5 BIT(2) #define OPTION_WSCALE BIT(3) #define OPTION_FAST_OPEN_COOKIE BIT(8) #define OPTION_SMC BIT(9) #define OPTION_MPTCP BIT(10) #define OPTION_AO BIT(11) static void smc_options_write(__be32 *ptr, u16 *options) { #if IS_ENABLED(CONFIG_SMC) if (static_branch_unlikely(&tcp_have_smc)) { if (unlikely(OPTION_SMC & *options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_EXP << 8) | (TCPOLEN_EXP_SMC_BASE)); *ptr++ = htonl(TCPOPT_SMC_MAGIC); } } #endif } struct tcp_out_options { u16 options; /* bit field of OPTION_* */ u16 mss; /* 0 to disable */ u8 ws; /* window scale, 0 to disable */ u8 num_sack_blocks; /* number of SACK blocks to include */ u8 hash_size; /* bytes in hash_location */ u8 bpf_opt_len; /* length of BPF hdr option */ __u8 *hash_location; /* temporary pointer, overloaded */ __u32 tsval, tsecr; /* need to include OPTION_TS */ struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */ struct mptcp_out_options mptcp; }; static void mptcp_options_write(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, struct tcp_out_options *opts) { #if IS_ENABLED(CONFIG_MPTCP) if (unlikely(OPTION_MPTCP & opts->options)) mptcp_write_options(th, ptr, tp, &opts->mptcp); #endif } #ifdef CONFIG_CGROUP_BPF static int bpf_skops_write_hdr_opt_arg0(struct sk_buff *skb, enum tcp_synack_type synack_type) { if (unlikely(!skb)) return BPF_WRITE_HDR_TCP_CURRENT_MSS; if (unlikely(synack_type == TCP_SYNACK_COOKIE)) return BPF_WRITE_HDR_TCP_SYNACK_COOKIE; return 0; } /* req, syn_skb and synack_type are used when writing synack */ static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct sk_buff *syn_skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts, unsigned int *remaining) { struct bpf_sock_ops_kern sock_ops; int err; if (likely(!BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG)) || !*remaining) return; /* *remaining has already been aligned to 4 bytes, so *remaining >= 4 */ /* init sock_ops */ memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); sock_ops.op = BPF_SOCK_OPS_HDR_OPT_LEN_CB; if (req) { /* The listen "sk" cannot be passed here because * it is not locked. It would not make too much * sense to do bpf_setsockopt(listen_sk) based * on individual connection request also. * * Thus, "req" is passed here and the cgroup-bpf-progs * of the listen "sk" will be run. * * "req" is also used here for fastopen even the "sk" here is * a fullsock "child" sk. It is to keep the behavior * consistent between fastopen and non-fastopen on * the bpf programming side. */ sock_ops.sk = (struct sock *)req; sock_ops.syn_skb = syn_skb; } else { sock_owned_by_me(sk); sock_ops.is_fullsock = 1; sock_ops.sk = sk; } sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type); sock_ops.remaining_opt_len = *remaining; /* tcp_current_mss() does not pass a skb */ if (skb) bpf_skops_init_skb(&sock_ops, skb, 0); err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk); if (err || sock_ops.remaining_opt_len == *remaining) return; opts->bpf_opt_len = *remaining - sock_ops.remaining_opt_len; /* round up to 4 bytes */ opts->bpf_opt_len = (opts->bpf_opt_len + 3) & ~3; *remaining -= opts->bpf_opt_len; } static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct sk_buff *syn_skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts) { u8 first_opt_off, nr_written, max_opt_len = opts->bpf_opt_len; struct bpf_sock_ops_kern sock_ops; int err; if (likely(!max_opt_len)) return; memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp)); sock_ops.op = BPF_SOCK_OPS_WRITE_HDR_OPT_CB; if (req) { sock_ops.sk = (struct sock *)req; sock_ops.syn_skb = syn_skb; } else { sock_owned_by_me(sk); sock_ops.is_fullsock = 1; sock_ops.sk = sk; } sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type); sock_ops.remaining_opt_len = max_opt_len; first_opt_off = tcp_hdrlen(skb) - max_opt_len; bpf_skops_init_skb(&sock_ops, skb, first_opt_off); err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk); if (err) nr_written = 0; else nr_written = max_opt_len - sock_ops.remaining_opt_len; if (nr_written < max_opt_len) memset(skb->data + first_opt_off + nr_written, TCPOPT_NOP, max_opt_len - nr_written); } #else static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct sk_buff *syn_skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts, unsigned int *remaining) { } static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct sk_buff *syn_skb, enum tcp_synack_type synack_type, struct tcp_out_options *opts) { } #endif static __be32 *process_tcp_ao_options(struct tcp_sock *tp, const struct tcp_request_sock *tcprsk, struct tcp_out_options *opts, struct tcp_key *key, __be32 *ptr) { #ifdef CONFIG_TCP_AO u8 maclen = tcp_ao_maclen(key->ao_key); if (tcprsk) { u8 aolen = maclen + sizeof(struct tcp_ao_hdr); *ptr++ = htonl((TCPOPT_AO << 24) | (aolen << 16) | (tcprsk->ao_keyid << 8) | (tcprsk->ao_rcv_next)); } else { struct tcp_ao_key *rnext_key; struct tcp_ao_info *ao_info; ao_info = rcu_dereference_check(tp->ao_info, lockdep_sock_is_held(&tp->inet_conn.icsk_inet.sk)); rnext_key = READ_ONCE(ao_info->rnext_key); if (WARN_ON_ONCE(!rnext_key)) return ptr; *ptr++ = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key->ao_key) << 16) | (key->ao_key->sndid << 8) | (rnext_key->rcvid)); } opts->hash_location = (__u8 *)ptr; ptr += maclen / sizeof(*ptr); if (unlikely(maclen % sizeof(*ptr))) { memset(ptr, TCPOPT_NOP, sizeof(*ptr)); ptr++; } #endif return ptr; } /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of * TCP options, we learned this through the hard way, so be careful here. * Luckily we can at least blame others for their non-compliance but from * inter-operability perspective it seems that we're somewhat stuck with * the ordering which we have been using if we want to keep working with * those broken things (not that it currently hurts anybody as there isn't * particular reason why the ordering would need to be changed). * * At least SACK_PERM as the first option is known to lead to a disaster * (but it may well be that other scenarios fail similarly). */ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, const struct tcp_request_sock *tcprsk, struct tcp_out_options *opts, struct tcp_key *key) { __be32 *ptr = (__be32 *)(th + 1); u16 options = opts->options; /* mungable copy */ if (tcp_key_is_md5(key)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); /* overload cookie hash location */ opts->hash_location = (__u8 *)ptr; ptr += 4; } else if (tcp_key_is_ao(key)) { ptr = process_tcp_ao_options(tp, tcprsk, opts, key, ptr); } if (unlikely(opts->mss)) { *ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | opts->mss); } if (likely(OPTION_TS & options)) { if (unlikely(OPTION_SACK_ADVERTISE & options)) { *ptr++ = htonl((TCPOPT_SACK_PERM << 24) | (TCPOLEN_SACK_PERM << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); options &= ~OPTION_SACK_ADVERTISE; } else { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); } *ptr++ = htonl(opts->tsval); *ptr++ = htonl(opts->tsecr); } if (unlikely(OPTION_SACK_ADVERTISE & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM); } if (unlikely(OPTION_WSCALE & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | opts->ws); } if (unlikely(opts->num_sack_blocks)) { struct tcp_sack_block *sp = tp->rx_opt.dsack ? tp->duplicate_sack : tp->selective_acks; int this_sack; *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_SACK << 8) | (TCPOLEN_SACK_BASE + (opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK))); for (this_sack = 0; this_sack < opts->num_sack_blocks; ++this_sack) { *ptr++ = htonl(sp[this_sack].start_seq); *ptr++ = htonl(sp[this_sack].end_seq); } tp->rx_opt.dsack = 0; } if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) { struct tcp_fastopen_cookie *foc = opts->fastopen_cookie; u8 *p = (u8 *)ptr; u32 len; /* Fast Open option length */ if (foc->exp) { len = TCPOLEN_EXP_FASTOPEN_BASE + foc->len; *ptr = htonl((TCPOPT_EXP << 24) | (len << 16) | TCPOPT_FASTOPEN_MAGIC); p += TCPOLEN_EXP_FASTOPEN_BASE; } else { len = TCPOLEN_FASTOPEN_BASE + foc->len; *p++ = TCPOPT_FASTOPEN; *p++ = len; } memcpy(p, foc->val, foc->len); if ((len & 3) == 2) { p[foc->len] = TCPOPT_NOP; p[foc->len + 1] = TCPOPT_NOP; } ptr += (len + 3) >> 2; } smc_options_write(ptr, &options); mptcp_options_write(th, ptr, tp, opts); } static void smc_set_option(const struct tcp_sock *tp, struct tcp_out_options *opts, unsigned int *remaining) { #if IS_ENABLED(CONFIG_SMC) if (static_branch_unlikely(&tcp_have_smc)) { if (tp->syn_smc) { if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { opts->options |= OPTION_SMC; *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; } } } #endif } static void smc_set_option_cond(const struct tcp_sock *tp, const struct inet_request_sock *ireq, struct tcp_out_options *opts, unsigned int *remaining) { #if IS_ENABLED(CONFIG_SMC) if (static_branch_unlikely(&tcp_have_smc)) { if (tp->syn_smc && ireq->smc_ok) { if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { opts->options |= OPTION_SMC; *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; } } } #endif } static void mptcp_set_option_cond(const struct request_sock *req, struct tcp_out_options *opts, unsigned int *remaining) { if (rsk_is_mptcp(req)) { unsigned int size; if (mptcp_synack_options(req, &size, &opts->mptcp)) { if (*remaining >= size) { opts->options |= OPTION_MPTCP; *remaining -= size; } } } } /* Compute TCP options for SYN packets. This is not the final * network wire format yet. */ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_key *key) { struct tcp_sock *tp = tcp_sk(sk); unsigned int remaining = MAX_TCP_OPTION_SPACE; struct tcp_fastopen_request *fastopen = tp->fastopen_req; bool timestamps; /* Better than switch (key.type) as it has static branches */ if (tcp_key_is_md5(key)) { timestamps = false; opts->options |= OPTION_MD5; remaining -= TCPOLEN_MD5SIG_ALIGNED; } else { timestamps = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps); if (tcp_key_is_ao(key)) { opts->options |= OPTION_AO; remaining -= tcp_ao_len_aligned(key->ao_key); } } /* We always get an MSS option. The option bytes which will be seen in * normal data packets should timestamps be used, must be in the MSS * advertised. But we subtract them from tp->mss_cache so that * calculations in tcp_sendmsg are simpler etc. So account for this * fact here if necessary. If we don't do this correctly, as a * receiver we won't recognize data packets as being full sized when we * should, and thus we won't abide by the delayed ACK rules correctly. * SACKs don't matter, we never delay an ACK when we have any of those * going out. */ opts->mss = tcp_advertise_mss(sk); remaining -= TCPOLEN_MSS_ALIGNED; if (likely(timestamps)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb) + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling))) { opts->ws = tp->rx_opt.rcv_wscale; opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_sack))) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!(OPTION_TS & opts->options))) remaining -= TCPOLEN_SACKPERM_ALIGNED; } if (fastopen && fastopen->cookie.len >= 0) { u32 need = fastopen->cookie.len; need += fastopen->cookie.exp ? TCPOLEN_EXP_FASTOPEN_BASE : TCPOLEN_FASTOPEN_BASE; need = (need + 3) & ~3U; /* Align to 32 bits */ if (remaining >= need) { opts->options |= OPTION_FAST_OPEN_COOKIE; opts->fastopen_cookie = &fastopen->cookie; remaining -= need; tp->syn_fastopen = 1; tp->syn_fastopen_exp = fastopen->cookie.exp ? 1 : 0; } } smc_set_option(tp, opts, &remaining); if (sk_is_mptcp(sk)) { unsigned int size; if (mptcp_syn_options(sk, skb, &size, &opts->mptcp)) { if (remaining >= size) { opts->options |= OPTION_MPTCP; remaining -= size; } } } bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining); return MAX_TCP_OPTION_SPACE - remaining; } /* Set up TCP options for SYN-ACKs. */ static unsigned int tcp_synack_options(const struct sock *sk, struct request_sock *req, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, const struct tcp_key *key, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; if (tcp_key_is_md5(key)) { opts->options |= OPTION_MD5; remaining -= TCPOLEN_MD5SIG_ALIGNED; /* We can't fit any SACK blocks in a packet with MD5 + TS * options. There was discussion about disabling SACK * rather than TS in order to fit in better with old, * buggy kernels, but that was deemed to be unnecessary. */ if (synack_type != TCP_SYNACK_COOKIE) ireq->tstamp_ok &= !ireq->sack_ok; } else if (tcp_key_is_ao(key)) { opts->options |= OPTION_AO; remaining -= tcp_ao_len_aligned(key->ao_key); ireq->tstamp_ok &= !ireq->sack_ok; } /* We always send an MSS option. */ opts->mss = mss; remaining -= TCPOLEN_MSS_ALIGNED; if (likely(ireq->wscale_ok)) { opts->ws = ireq->rcv_wscale; opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } if (likely(ireq->tstamp_ok)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp_ts(tcp_rsk(req)->req_usec_ts, skb) + tcp_rsk(req)->ts_off; opts->tsecr = READ_ONCE(req->ts_recent); remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(ireq->sack_ok)) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!ireq->tstamp_ok)) remaining -= TCPOLEN_SACKPERM_ALIGNED; } if (foc != NULL && foc->len >= 0) { u32 need = foc->len; need += foc->exp ? TCPOLEN_EXP_FASTOPEN_BASE : TCPOLEN_FASTOPEN_BASE; need = (need + 3) & ~3U; /* Align to 32 bits */ if (remaining >= need) { opts->options |= OPTION_FAST_OPEN_COOKIE; opts->fastopen_cookie = foc; remaining -= need; } } mptcp_set_option_cond(req, opts, &remaining); smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining); bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb, synack_type, opts, &remaining); return MAX_TCP_OPTION_SPACE - remaining; } /* Compute TCP options for ESTABLISHED sockets. This is not the * final wire format yet. */ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_key *key) { struct tcp_sock *tp = tcp_sk(sk); unsigned int size = 0; unsigned int eff_sacks; opts->options = 0; /* Better than switch (key.type) as it has static branches */ if (tcp_key_is_md5(key)) { opts->options |= OPTION_MD5; size += TCPOLEN_MD5SIG_ALIGNED; } else if (tcp_key_is_ao(key)) { opts->options |= OPTION_AO; size += tcp_ao_len_aligned(key->ao_key); } if (likely(tp->rx_opt.tstamp_ok)) { opts->options |= OPTION_TS; opts->tsval = skb ? tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb) + tp->tsoffset : 0; opts->tsecr = tp->rx_opt.ts_recent; size += TCPOLEN_TSTAMP_ALIGNED; } /* MPTCP options have precedence over SACK for the limited TCP * option space because a MPTCP connection would be forced to * fall back to regular TCP if a required multipath option is * missing. SACK still gets a chance to use whatever space is * left. */ if (sk_is_mptcp(sk)) { unsigned int remaining = MAX_TCP_OPTION_SPACE - size; unsigned int opt_size = 0; if (mptcp_established_options(sk, skb, &opt_size, remaining, &opts->mptcp)) { opts->options |= OPTION_MPTCP; size += opt_size; } } eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack; if (unlikely(eff_sacks)) { const unsigned int remaining = MAX_TCP_OPTION_SPACE - size; if (unlikely(remaining < TCPOLEN_SACK_BASE_ALIGNED + TCPOLEN_SACK_PERBLOCK)) return size; opts->num_sack_blocks = min_t(unsigned int, eff_sacks, (remaining - TCPOLEN_SACK_BASE_ALIGNED) / TCPOLEN_SACK_PERBLOCK); size += TCPOLEN_SACK_BASE_ALIGNED + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; } if (unlikely(BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG))) { unsigned int remaining = MAX_TCP_OPTION_SPACE - size; bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining); size = MAX_TCP_OPTION_SPACE - remaining; } return size; } /* TCP SMALL QUEUES (TSQ) * * TSQ goal is to keep small amount of skbs per tcp flow in tx queues (qdisc+dev) * to reduce RTT and bufferbloat. * We do this using a special skb destructor (tcp_wfree). * * Its important tcp_wfree() can be replaced by sock_wfree() in the event skb * needs to be reallocated in a driver. * The invariant being skb->truesize subtracted from sk->sk_wmem_alloc * * Since transmit from skb destructor is forbidden, we use a tasklet * to process all sockets that eventually need to send more skbs. * We use one tasklet per cpu, with its own queue of sockets. */ struct tsq_tasklet { struct tasklet_struct tasklet; struct list_head head; /* queue of tcp sockets */ }; static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet); static void tcp_tsq_write(struct sock *sk) { if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) { struct tcp_sock *tp = tcp_sk(sk); if (tp->lost_out > tp->retrans_out && tcp_snd_cwnd(tp) > tcp_packets_in_flight(tp)) { tcp_mstamp_refresh(tp); tcp_xmit_retransmit_queue(sk); } tcp_write_xmit(sk, tcp_current_mss(sk), tp->nonagle, 0, GFP_ATOMIC); } } static void tcp_tsq_handler(struct sock *sk) { bh_lock_sock(sk); if (!sock_owned_by_user(sk)) tcp_tsq_write(sk); else if (!test_and_set_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); bh_unlock_sock(sk); } /* * One tasklet per cpu tries to send more skbs. * We run in tasklet context but need to disable irqs when * transferring tsq->head because tcp_wfree() might * interrupt us (non NAPI drivers) */ static void tcp_tasklet_func(struct tasklet_struct *t) { struct tsq_tasklet *tsq = from_tasklet(tsq, t, tasklet); LIST_HEAD(list); unsigned long flags; struct list_head *q, *n; struct tcp_sock *tp; struct sock *sk; local_irq_save(flags); list_splice_init(&tsq->head, &list); local_irq_restore(flags); list_for_each_safe(q, n, &list) { tp = list_entry(q, struct tcp_sock, tsq_node); list_del(&tp->tsq_node); sk = (struct sock *)tp; smp_mb__before_atomic(); clear_bit(TSQ_QUEUED, &sk->sk_tsq_flags); tcp_tsq_handler(sk); sk_free(sk); } } #define TCP_DEFERRED_ALL (TCPF_TSQ_DEFERRED | \ TCPF_WRITE_TIMER_DEFERRED | \ TCPF_DELACK_TIMER_DEFERRED | \ TCPF_MTU_REDUCED_DEFERRED | \ TCPF_ACK_DEFERRED) /** * tcp_release_cb - tcp release_sock() callback * @sk: socket * * called from release_sock() to perform protocol dependent * actions before socket release. */ void tcp_release_cb(struct sock *sk) { unsigned long flags = smp_load_acquire(&sk->sk_tsq_flags); unsigned long nflags; /* perform an atomic operation only if at least one flag is set */ do { if (!(flags & TCP_DEFERRED_ALL)) return; nflags = flags & ~TCP_DEFERRED_ALL; } while (!try_cmpxchg(&sk->sk_tsq_flags, &flags, nflags)); if (flags & TCPF_TSQ_DEFERRED) { tcp_tsq_write(sk); __sock_put(sk); } if (flags & TCPF_WRITE_TIMER_DEFERRED) { tcp_write_timer_handler(sk); __sock_put(sk); } if (flags & TCPF_DELACK_TIMER_DEFERRED) { tcp_delack_timer_handler(sk); __sock_put(sk); } if (flags & TCPF_MTU_REDUCED_DEFERRED) { inet_csk(sk)->icsk_af_ops->mtu_reduced(sk); __sock_put(sk); } if ((flags & TCPF_ACK_DEFERRED) && inet_csk_ack_scheduled(sk)) tcp_send_ack(sk); } EXPORT_SYMBOL(tcp_release_cb); void __init tcp_tasklet_init(void) { int i; for_each_possible_cpu(i) { struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i); INIT_LIST_HEAD(&tsq->head); tasklet_setup(&tsq->tasklet, tcp_tasklet_func); } } /* * Write buffer destructor automatically called from kfree_skb. * We can't xmit new skbs from this context, as we might already * hold qdisc lock. */ void tcp_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; struct tcp_sock *tp = tcp_sk(sk); unsigned long flags, nval, oval; struct tsq_tasklet *tsq; bool empty; /* Keep one reference on sk_wmem_alloc. * Will be released by sk_free() from here or tcp_tasklet_func() */ WARN_ON(refcount_sub_and_test(skb->truesize - 1, &sk->sk_wmem_alloc)); /* If this softirq is serviced by ksoftirqd, we are likely under stress. * Wait until our queues (qdisc + devices) are drained. * This gives : * - less callbacks to tcp_write_xmit(), reducing stress (batches) * - chance for incoming ACK (processed by another cpu maybe) * to migrate this flow (skb->ooo_okay will be eventually set) */ if (refcount_read(&sk->sk_wmem_alloc) >= SKB_TRUESIZE(1) && this_cpu_ksoftirqd() == current) goto out; oval = smp_load_acquire(&sk->sk_tsq_flags); do { if (!(oval & TSQF_THROTTLED) || (oval & TSQF_QUEUED)) goto out; nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED; } while (!try_cmpxchg(&sk->sk_tsq_flags, &oval, nval)); /* queue this socket to tasklet queue */ local_irq_save(flags); tsq = this_cpu_ptr(&tsq_tasklet); empty = list_empty(&tsq->head); list_add(&tp->tsq_node, &tsq->head); if (empty) tasklet_schedule(&tsq->tasklet); local_irq_restore(flags); return; out: sk_free(sk); } /* Note: Called under soft irq. * We can call TCP stack right away, unless socket is owned by user. */ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer) { struct tcp_sock *tp = container_of(timer, struct tcp_sock, pacing_timer); struct sock *sk = (struct sock *)tp; tcp_tsq_handler(sk); sock_put(sk); return HRTIMER_NORESTART; } static void tcp_update_skb_after_send(struct sock *sk, struct sk_buff *skb, u64 prior_wstamp) { struct tcp_sock *tp = tcp_sk(sk); if (sk->sk_pacing_status != SK_PACING_NONE) { unsigned long rate = READ_ONCE(sk->sk_pacing_rate); /* Original sch_fq does not pace first 10 MSS * Note that tp->data_segs_out overflows after 2^32 packets, * this is a minor annoyance. */ if (rate != ~0UL && rate && tp->data_segs_out >= 10) { u64 len_ns = div64_ul((u64)skb->len * NSEC_PER_SEC, rate); u64 credit = tp->tcp_wstamp_ns - prior_wstamp; /* take into account OS jitter */ len_ns -= min_t(u64, len_ns / 2, credit); tp->tcp_wstamp_ns += len_ns; } } list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); } INDIRECT_CALLABLE_DECLARE(int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)); INDIRECT_CALLABLE_DECLARE(int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)); INDIRECT_CALLABLE_DECLARE(void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)); /* This routine actually transmits TCP packets queued in by * tcp_do_sendmsg(). This is used by both the initial * transmission and possible later retransmissions. * All SKB's seen here are completely headerless. It is our * job to build the TCP header, and pass the packet down to * IP so it can do the same plus pass the packet off to the * device. * * We are working here with either a clone of the original * SKB, or a fresh unique copy made by the retransmit engine. */ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, gfp_t gfp_mask, u32 rcv_nxt) { const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet; struct tcp_sock *tp; struct tcp_skb_cb *tcb; struct tcp_out_options opts; unsigned int tcp_options_size, tcp_header_size; struct sk_buff *oskb = NULL; struct tcp_key key; struct tcphdr *th; u64 prior_wstamp; int err; BUG_ON(!skb || !tcp_skb_pcount(skb)); tp = tcp_sk(sk); prior_wstamp = tp->tcp_wstamp_ns; tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache); skb_set_delivery_time(skb, tp->tcp_wstamp_ns, SKB_CLOCK_MONOTONIC); if (clone_it) { oskb = skb; tcp_skb_tsorted_save(oskb) { if (unlikely(skb_cloned(oskb))) skb = pskb_copy(oskb, gfp_mask); else skb = skb_clone(oskb, gfp_mask); } tcp_skb_tsorted_restore(oskb); if (unlikely(!skb)) return -ENOBUFS; /* retransmit skbs might have a non zero value in skb->dev * because skb->dev is aliased with skb->rbnode.rb_left */ skb->dev = NULL; } inet = inet_sk(sk); tcb = TCP_SKB_CB(skb); memset(&opts, 0, sizeof(opts)); tcp_get_current_key(sk, &key); if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) { tcp_options_size = tcp_syn_options(sk, skb, &opts, &key); } else { tcp_options_size = tcp_established_options(sk, skb, &opts, &key); /* Force a PSH flag on all (GSO) packets to expedite GRO flush * at receiver : This slightly improve GRO performance. * Note that we do not force the PSH flag for non GSO packets, * because they might be sent under high congestion events, * and in this case it is better to delay the delivery of 1-MSS * packets and thus the corresponding ACK packet that would * release the following packet. */ if (tcp_skb_pcount(skb) > 1) tcb->tcp_flags |= TCPHDR_PSH; } tcp_header_size = tcp_options_size + sizeof(struct tcphdr); /* We set skb->ooo_okay to one if this packet can select * a different TX queue than prior packets of this flow, * to avoid self inflicted reorders. * The 'other' queue decision is based on current cpu number * if XPS is enabled, or sk->sk_txhash otherwise. * We can switch to another (and better) queue if: * 1) No packet with payload is in qdisc/device queues. * Delays in TX completion can defeat the test * even if packets were already sent. * 2) Or rtx queue is empty. * This mitigates above case if ACK packets for * all prior packets were already processed. */ skb->ooo_okay = sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1) || tcp_rtx_queue_empty(sk); /* If we had to use memory reserve to allocate this skb, * this might cause drops if packet is looped back : * Other socket might not have SOCK_MEMALLOC. * Packets not looped back do not care about pfmemalloc. */ skb->pfmemalloc = 0; skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); skb_orphan(skb); skb->sk = sk; skb->destructor = skb_is_tcp_pure_ack(skb) ? __sock_wfree : tcp_wfree; refcount_add(skb->truesize, &sk->sk_wmem_alloc); skb_set_dst_pending_confirm(skb, READ_ONCE(sk->sk_dst_pending_confirm)); /* Build TCP header and checksum it. */ th = (struct tcphdr *)skb->data; th->source = inet->inet_sport; th->dest = inet->inet_dport; th->seq = htonl(tcb->seq); th->ack_seq = htonl(rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | tcb->tcp_flags); th->check = 0; th->urg_ptr = 0; /* The urg_mode check is necessary during a below snd_una win probe */ if (unlikely(tcp_urg_mode(tp) && before(tcb->seq, tp->snd_up))) { if (before(tp->snd_up, tcb->seq + 0x10000)) { th->urg_ptr = htons(tp->snd_up - tcb->seq); th->urg = 1; } else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) { th->urg_ptr = htons(0xFFFF); th->urg = 1; } } skb_shinfo(skb)->gso_type = sk->sk_gso_type; if (likely(!(tcb->tcp_flags & TCPHDR_SYN))) { th->window = htons(tcp_select_window(sk)); tcp_ecn_send(sk, skb, th, tcp_header_size); } else { /* RFC1323: The window in SYN & SYN/ACK segments * is never scaled. */ th->window = htons(min(tp->rcv_wnd, 65535U)); } tcp_options_write(th, tp, NULL, &opts, &key); if (tcp_key_is_md5(&key)) { #ifdef CONFIG_TCP_MD5SIG /* Calculate the MD5 hash, as we have all we need now */ sk_gso_disable(sk); tp->af_specific->calc_md5_hash(opts.hash_location, key.md5_key, sk, skb); #endif } else if (tcp_key_is_ao(&key)) { int err; err = tcp_ao_transmit_skb(sk, skb, key.ao_key, th, opts.hash_location); if (err) { kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); return -ENOMEM; } } /* BPF prog is the last one writing header option */ bpf_skops_write_hdr_opt(sk, skb, NULL, NULL, 0, &opts); INDIRECT_CALL_INET(icsk->icsk_af_ops->send_check, tcp_v6_send_check, tcp_v4_send_check, sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) tcp_event_ack_sent(sk, rcv_nxt); if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); tp->data_segs_out += tcp_skb_pcount(skb); tp->bytes_sent += skb->len - tcp_header_size; } if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb)); tp->segs_out += tcp_skb_pcount(skb); skb_set_hash_from_sk(skb, sk); /* OK, its time to fill skb_shinfo(skb)->gso_{segs|size} */ skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb); skb_shinfo(skb)->gso_size = tcp_skb_mss(skb); /* Leave earliest departure time in skb->tstamp (skb->skb_mstamp_ns) */ /* Cleanup our debris for IP stacks */ memset(skb->cb, 0, max(sizeof(struct inet_skb_parm), sizeof(struct inet6_skb_parm))); tcp_add_tx_delay(skb, tp); err = INDIRECT_CALL_INET(icsk->icsk_af_ops->queue_xmit, inet6_csk_xmit, ip_queue_xmit, sk, skb, &inet->cork.fl); if (unlikely(err > 0)) { tcp_enter_cwr(sk); err = net_xmit_eval(err); } if (!err && oskb) { tcp_update_skb_after_send(sk, oskb, prior_wstamp); tcp_rate_skb_sent(sk, oskb); } return err; } static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, gfp_t gfp_mask) { return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask, tcp_sk(sk)->rcv_nxt); } /* This routine just queues the buffer for sending. * * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames, * otherwise socket can stall. */ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); /* Advance write_seq and place onto the write_queue. */ WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq); __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); } /* Initialize TSO segments for a packet. */ static int tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now) { int tso_segs; if (skb->len <= mss_now) { /* Avoid the costly divide in the normal * non-TSO case. */ TCP_SKB_CB(skb)->tcp_gso_size = 0; tcp_skb_pcount_set(skb, 1); return 1; } TCP_SKB_CB(skb)->tcp_gso_size = mss_now; tso_segs = DIV_ROUND_UP(skb->len, mss_now); tcp_skb_pcount_set(skb, tso_segs); return tso_segs; } /* Pcount in the middle of the write queue got changed, we need to do various * tweaks to fix counters */ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int decr) { struct tcp_sock *tp = tcp_sk(sk); tp->packets_out -= decr; if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) tp->sacked_out -= decr; if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) tp->retrans_out -= decr; if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) tp->lost_out -= decr; /* Reno case is special. Sigh... */ if (tcp_is_reno(tp) && decr > 0) tp->sacked_out -= min_t(u32, tp->sacked_out, decr); if (tp->lost_skb_hint && before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) tp->lost_cnt_hint -= decr; tcp_verify_left_out(tp); } static bool tcp_has_tx_tstamp(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->txstamp_ack || (skb_shinfo(skb)->tx_flags & SKBTX_ANY_TSTAMP); } static void tcp_fragment_tstamp(struct sk_buff *skb, struct sk_buff *skb2) { struct skb_shared_info *shinfo = skb_shinfo(skb); if (unlikely(tcp_has_tx_tstamp(skb)) && !before(shinfo->tskey, TCP_SKB_CB(skb2)->seq)) { struct skb_shared_info *shinfo2 = skb_shinfo(skb2); u8 tsflags = shinfo->tx_flags & SKBTX_ANY_TSTAMP; shinfo->tx_flags &= ~tsflags; shinfo2->tx_flags |= tsflags; swap(shinfo->tskey, shinfo2->tskey); TCP_SKB_CB(skb2)->txstamp_ack = TCP_SKB_CB(skb)->txstamp_ack; TCP_SKB_CB(skb)->txstamp_ack = 0; } } static void tcp_skb_fragment_eor(struct sk_buff *skb, struct sk_buff *skb2) { TCP_SKB_CB(skb2)->eor = TCP_SKB_CB(skb)->eor; TCP_SKB_CB(skb)->eor = 0; } /* Insert buff after skb on the write or rtx queue of sk. */ static void tcp_insert_write_queue_after(struct sk_buff *skb, struct sk_buff *buff, struct sock *sk, enum tcp_queue tcp_queue) { if (tcp_queue == TCP_FRAG_IN_WRITE_QUEUE) __skb_queue_after(&sk->sk_write_queue, skb, buff); else tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); } /* Function to create two new TCP segments. Shrinks the given segment * to the specified size and appends a new segment with the rest of the * packet to the list. This won't be called frequently, I hope. * Remember, these are still headerless SKBs at this point. */ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, struct sk_buff *skb, u32 len, unsigned int mss_now, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; int old_factor; long limit; int nlen; u8 flags; if (WARN_ON(len > skb->len)) return -EINVAL; DEBUG_NET_WARN_ON_ONCE(skb_headlen(skb)); /* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb. * We need some allowance to not penalize applications setting small * SO_SNDBUF values. * Also allow first and last skb in retransmit queue to be split. */ limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_LEGACY_MAX_SIZE); if (unlikely((sk->sk_wmem_queued >> 1) > limit && tcp_queue != TCP_FRAG_IN_WRITE_QUEUE && skb != tcp_rtx_queue_head(sk) && skb != tcp_rtx_queue_tail(sk))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG); return -ENOMEM; } if (skb_unclone_keeptruesize(skb, gfp)) return -ENOMEM; /* Get a new skb... force flag on. */ buff = tcp_stream_alloc_skb(sk, gfp, true); if (!buff) return -ENOMEM; /* We'll just try again later. */ skb_copy_decrypted(buff, skb); mptcp_skb_ext_copy(buff, skb); sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); nlen = skb->len - len; buff->truesize += nlen; skb->truesize -= nlen; /* Correct the sequence numbers. */ TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len; TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq; TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq; /* PSH and FIN should only be set in the second packet. */ flags = TCP_SKB_CB(skb)->tcp_flags; TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH); TCP_SKB_CB(buff)->tcp_flags = flags; TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked; tcp_skb_fragment_eor(skb, buff); skb_split(skb, buff, len); skb_set_delivery_time(buff, skb->tstamp, SKB_CLOCK_MONOTONIC); tcp_fragment_tstamp(skb, buff); old_factor = tcp_skb_pcount(skb); /* Fix up tso_factor for both original and new SKB. */ tcp_set_skb_tso_segs(skb, mss_now); tcp_set_skb_tso_segs(buff, mss_now); /* Update delivered info for the new segment */ TCP_SKB_CB(buff)->tx = TCP_SKB_CB(skb)->tx; /* If this packet has been sent out already, we must * adjust the various packet counters. */ if (!before(tp->snd_nxt, TCP_SKB_CB(buff)->end_seq)) { int diff = old_factor - tcp_skb_pcount(skb) - tcp_skb_pcount(buff); if (diff) tcp_adjust_pcount(sk, skb, diff); } /* Link BUFF into the send queue. */ __skb_header_release(buff); tcp_insert_write_queue_after(skb, buff, sk, tcp_queue); if (tcp_queue == TCP_FRAG_IN_RTX_QUEUE) list_add(&buff->tcp_tsorted_anchor, &skb->tcp_tsorted_anchor); return 0; } /* This is similar to __pskb_pull_tail(). The difference is that pulled * data is not copied, but immediately discarded. */ static int __pskb_trim_head(struct sk_buff *skb, int len) { struct skb_shared_info *shinfo; int i, k, eat; DEBUG_NET_WARN_ON_ONCE(skb_headlen(skb)); eat = len; k = 0; shinfo = skb_shinfo(skb); for (i = 0; i < shinfo->nr_frags; i++) { int size = skb_frag_size(&shinfo->frags[i]); if (size <= eat) { skb_frag_unref(skb, i); eat -= size; } else { shinfo->frags[k] = shinfo->frags[i]; if (eat) { skb_frag_off_add(&shinfo->frags[k], eat); skb_frag_size_sub(&shinfo->frags[k], eat); eat = 0; } k++; } } shinfo->nr_frags = k; skb->data_len -= len; skb->len = skb->data_len; return len; } /* Remove acked data from a packet in the transmit queue. */ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) { u32 delta_truesize; if (skb_unclone_keeptruesize(skb, GFP_ATOMIC)) return -ENOMEM; delta_truesize = __pskb_trim_head(skb, len); TCP_SKB_CB(skb)->seq += len; skb->truesize -= delta_truesize; sk_wmem_queued_add(sk, -delta_truesize); if (!skb_zcopy_pure(skb)) sk_mem_uncharge(sk, delta_truesize); /* Any change of skb->len requires recalculation of tso factor. */ if (tcp_skb_pcount(skb) > 1) tcp_set_skb_tso_segs(skb, tcp_skb_mss(skb)); return 0; } /* Calculate MSS not accounting any TCP options. */ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); int mss_now; /* Calculate base mss without TCP options: It is MMS_S - sizeof(tcphdr) of rfc1122 */ mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr); /* Clamp it (mss_clamp does not include tcp options) */ if (mss_now > tp->rx_opt.mss_clamp) mss_now = tp->rx_opt.mss_clamp; /* Now subtract optional transport overhead */ mss_now -= icsk->icsk_ext_hdr_len; /* Then reserve room for full set of TCP options and 8 bytes of data */ mss_now = max(mss_now, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss)); return mss_now; } /* Calculate MSS. Not accounting for SACKs here. */ int tcp_mtu_to_mss(struct sock *sk, int pmtu) { /* Subtract TCP options size, not including SACKs */ return __tcp_mtu_to_mss(sk, pmtu) - (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr)); } EXPORT_SYMBOL(tcp_mtu_to_mss); /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); return mss + tp->tcp_header_len + icsk->icsk_ext_hdr_len + icsk->icsk_af_ops->net_header_len; } EXPORT_SYMBOL(tcp_mss_to_mtu); /* MTU probing init per socket */ void tcp_mtup_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); icsk->icsk_mtup.enabled = READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing) > 1; icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) + icsk->icsk_af_ops->net_header_len; icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, READ_ONCE(net->ipv4.sysctl_tcp_base_mss)); icsk->icsk_mtup.probe_size = 0; if (icsk->icsk_mtup.enabled) icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } EXPORT_SYMBOL(tcp_mtup_init); /* This function synchronize snd mss to current pmtu/exthdr set. tp->rx_opt.user_mss is mss set by user by TCP_MAXSEG. It does NOT counts for TCP options, but includes only bare TCP header. tp->rx_opt.mss_clamp is mss negotiated at connection setup. It is minimum of user_mss and mss received with SYN. It also does not include TCP options. inet_csk(sk)->icsk_pmtu_cookie is last pmtu, seen by this function. tp->mss_cache is current effective sending mss, including all tcp options except for SACKs. It is evaluated, taking into account current pmtu, but never exceeds tp->rx_opt.mss_clamp. NOTE1. rfc1122 clearly states that advertised MSS DOES NOT include either tcp or ip options. NOTE2. inet_csk(sk)->icsk_pmtu_cookie and tp->mss_cache are READ ONLY outside this function. --ANK (980731) */ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); int mss_now; if (icsk->icsk_mtup.search_high > pmtu) icsk->icsk_mtup.search_high = pmtu; mss_now = tcp_mtu_to_mss(sk, pmtu); mss_now = tcp_bound_to_half_wnd(tp, mss_now); /* And store cached results */ icsk->icsk_pmtu_cookie = pmtu; if (icsk->icsk_mtup.enabled) mss_now = min(mss_now, tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low)); tp->mss_cache = mss_now; return mss_now; } EXPORT_SYMBOL(tcp_sync_mss); /* Compute the current effective MSS, taking SACKs and IP options, * and even PMTU discovery events into account. */ unsigned int tcp_current_mss(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); const struct dst_entry *dst = __sk_dst_get(sk); u32 mss_now; unsigned int header_len; struct tcp_out_options opts; struct tcp_key key; mss_now = tp->mss_cache; if (dst) { u32 mtu = dst_mtu(dst); if (mtu != inet_csk(sk)->icsk_pmtu_cookie) mss_now = tcp_sync_mss(sk, mtu); } tcp_get_current_key(sk, &key); header_len = tcp_established_options(sk, NULL, &opts, &key) + sizeof(struct tcphdr); /* The mss_cache is sized based on tp->tcp_header_len, which assumes * some common options. If this is an odd packet (because we have SACK * blocks etc) then our calculated header_len will be different, and * we have to adjust mss_now correspondingly */ if (header_len != tp->tcp_header_len) { int delta = (int) header_len - tp->tcp_header_len; mss_now -= delta; } return mss_now; } /* RFC2861, slow part. Adjust cwnd, after it was not full during one rto. * As additional protections, we do not touch cwnd in retransmission phases, * and if application hit its sndbuf limit recently. */ static void tcp_cwnd_application_limited(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open && sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { /* Limited by application or receiver window. */ u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk)); u32 win_used = max(tp->snd_cwnd_used, init_win); if (win_used < tcp_snd_cwnd(tp)) { tp->snd_ssthresh = tcp_current_ssthresh(sk); tcp_snd_cwnd_set(tp, (tcp_snd_cwnd(tp) + win_used) >> 1); } tp->snd_cwnd_used = 0; } tp->snd_cwnd_stamp = tcp_jiffies32; } static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; struct tcp_sock *tp = tcp_sk(sk); /* Track the strongest available signal of the degree to which the cwnd * is fully utilized. If cwnd-limited then remember that fact for the * current window. If not cwnd-limited then track the maximum number of * outstanding packets in the current window. (If cwnd-limited then we * chose to not update tp->max_packets_out to avoid an extra else * clause with no functional impact.) */ if (!before(tp->snd_una, tp->cwnd_usage_seq) || is_cwnd_limited || (!tp->is_cwnd_limited && tp->packets_out > tp->max_packets_out)) { tp->is_cwnd_limited = is_cwnd_limited; tp->max_packets_out = tp->packets_out; tp->cwnd_usage_seq = tp->snd_nxt; } if (tcp_is_cwnd_limited(sk)) { /* Network is feed fully. */ tp->snd_cwnd_used = 0; tp->snd_cwnd_stamp = tcp_jiffies32; } else { /* Network starves. */ if (tp->packets_out > tp->snd_cwnd_used) tp->snd_cwnd_used = tp->packets_out; if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) && (s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto && !ca_ops->cong_control) tcp_cwnd_application_limited(sk); /* The following conditions together indicate the starvation * is caused by insufficient sender buffer: * 1) just sent some data (see tcp_write_xmit) * 2) not cwnd limited (this else condition) * 3) no more data to send (tcp_write_queue_empty()) * 4) application is hitting buffer limit (SOCK_NOSPACE) */ if (tcp_write_queue_empty(sk) && sk->sk_socket && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags) && (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) tcp_chrono_start(sk, TCP_CHRONO_SNDBUF_LIMITED); } } /* Minshall's variant of the Nagle send check. */ static bool tcp_minshall_check(const struct tcp_sock *tp) { return after(tp->snd_sml, tp->snd_una) && !after(tp->snd_sml, tp->snd_nxt); } /* Update snd_sml if this skb is under mss * Note that a TSO packet might end with a sub-mss segment * The test is really : * if ((skb->len % mss) != 0) * tp->snd_sml = TCP_SKB_CB(skb)->end_seq; * But we can avoid doing the divide again given we already have * skb_pcount = skb->len / mss_now */ static void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss_now, const struct sk_buff *skb) { if (skb->len < tcp_skb_pcount(skb) * mss_now) tp->snd_sml = TCP_SKB_CB(skb)->end_seq; } /* Return false, if packet can be sent now without violation Nagle's rules: * 1. It is full sized. (provided by caller in %partial bool) * 2. Or it contains FIN. (already checked by caller) * 3. Or TCP_CORK is not set, and TCP_NODELAY is set. * 4. Or TCP_CORK is not set, and all sent packets are ACKed. * With Minshall's modification: all sent small packets are ACKed. */ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp, int nonagle) { return partial && ((nonagle & TCP_NAGLE_CORK) || (!nonagle && tp->packets_out && tcp_minshall_check(tp))); } /* Return how many segs we'd like on a TSO packet, * depending on current pacing rate, and how close the peer is. * * Rationale is: * - For close peers, we rather send bigger packets to reduce * cpu costs, because occasional losses will be repaired fast. * - For long distance/rtt flows, we would like to get ACK clocking * with 1 ACK per ms. * * Use min_rtt to help adapt TSO burst size, with smaller min_rtt resulting * in bigger TSO bursts. We we cut the RTT-based allowance in half * for every 2^9 usec (aka 512 us) of RTT, so that the RTT-based allowance * is below 1500 bytes after 6 * ~500 usec = 3ms. */ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, int min_tso_segs) { unsigned long bytes; u32 r; bytes = READ_ONCE(sk->sk_pacing_rate) >> READ_ONCE(sk->sk_pacing_shift); r = tcp_min_rtt(tcp_sk(sk)) >> READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log); if (r < BITS_PER_TYPE(sk->sk_gso_max_size)) bytes += sk->sk_gso_max_size >> r; bytes = min_t(unsigned long, bytes, sk->sk_gso_max_size); return max_t(u32, bytes / mss_now, min_tso_segs); } /* Return the number of segments we want in the skb we are transmitting. * See if congestion control module wants to decide; otherwise, autosize. */ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; u32 min_tso, tso_segs; min_tso = ca_ops->min_tso_segs ? ca_ops->min_tso_segs(sk) : READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs); tso_segs = tcp_tso_autosize(sk, mss_now, min_tso); return min_t(u32, tso_segs, sk->sk_gso_max_segs); } /* Returns the portion of skb which can be sent right away */ static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_buff *skb, unsigned int mss_now, unsigned int max_segs, int nonagle) { const struct tcp_sock *tp = tcp_sk(sk); u32 partial, needed, window, max_len; window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; max_len = mss_now * max_segs; if (likely(max_len <= window && skb != tcp_write_queue_tail(sk))) return max_len; needed = min(skb->len, window); if (max_len <= needed) return max_len; partial = needed % mss_now; /* If last segment is not a full MSS, check if Nagle rules allow us * to include this last segment in this skb. * Otherwise, we'll split the skb at last MSS boundary */ if (tcp_nagle_check(partial != 0, tp, nonagle)) return needed - partial; return needed; } /* Can at least one segment of SKB be sent right now, according to the * congestion window rules? If so, return how many segments are allowed. */ static u32 tcp_cwnd_test(const struct tcp_sock *tp) { u32 in_flight, cwnd, halfcwnd; in_flight = tcp_packets_in_flight(tp); cwnd = tcp_snd_cwnd(tp); if (in_flight >= cwnd) return 0; /* For better scheduling, ensure we have at least * 2 GSO packets in flight. */ halfcwnd = max(cwnd >> 1, 1U); return min(halfcwnd, cwnd - in_flight); } /* Initialize TSO state of a skb. * This must be invoked the first time we consider transmitting * SKB onto the wire. */ static int tcp_init_tso_segs(struct sk_buff *skb, unsigned int mss_now) { int tso_segs = tcp_skb_pcount(skb); if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) return tcp_set_skb_tso_segs(skb, mss_now); return tso_segs; } /* Return true if the Nagle test allows this packet to be * sent now. */ static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff *skb, unsigned int cur_mss, int nonagle) { /* Nagle rule does not apply to frames, which sit in the middle of the * write_queue (they have no chances to get new data). * * This is implemented in the callers, where they modify the 'nonagle' * argument based upon the location of SKB in the send queue. */ if (nonagle & TCP_NAGLE_PUSH) return true; /* Don't use the nagle rule for urgent data (or for the final FIN). */ if (tcp_urg_mode(tp) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) return true; if (!tcp_nagle_check(skb->len < cur_mss, tp, nonagle)) return true; return false; } /* Does at least the first segment of SKB fit into the send window? */ static bool tcp_snd_wnd_test(const struct tcp_sock *tp, const struct sk_buff *skb, unsigned int cur_mss) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; if (skb->len > cur_mss) end_seq = TCP_SKB_CB(skb)->seq + cur_mss; return !after(end_seq, tcp_wnd_end(tp)); } /* Trim TSO SKB to LEN bytes, put the remaining data into a new packet * which is put after SKB on the list. It is very much like * tcp_fragment() except that it may make several kinds of assumptions * in order to speed up the splitting operation. In particular, we * know that all the data is in scatter-gather pages, and that the * packet has never been sent out before (and thus is not cloned). */ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, unsigned int mss_now, gfp_t gfp) { int nlen = skb->len - len; struct sk_buff *buff; u8 flags; /* All of a TSO frame must be composed of paged data. */ DEBUG_NET_WARN_ON_ONCE(skb->len != skb->data_len); buff = tcp_stream_alloc_skb(sk, gfp, true); if (unlikely(!buff)) return -ENOMEM; skb_copy_decrypted(buff, skb); mptcp_skb_ext_copy(buff, skb); sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); buff->truesize += nlen; skb->truesize -= nlen; /* Correct the sequence numbers. */ TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len; TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq; TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq; /* PSH and FIN should only be set in the second packet. */ flags = TCP_SKB_CB(skb)->tcp_flags; TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH); TCP_SKB_CB(buff)->tcp_flags = flags; tcp_skb_fragment_eor(skb, buff); skb_split(skb, buff, len); tcp_fragment_tstamp(skb, buff); /* Fix up tso_factor for both original and new SKB. */ tcp_set_skb_tso_segs(skb, mss_now); tcp_set_skb_tso_segs(buff, mss_now); /* Link BUFF into the send queue. */ __skb_header_release(buff); tcp_insert_write_queue_after(skb, buff, sk, TCP_FRAG_IN_WRITE_QUEUE); return 0; } /* Try to defer sending, if possible, in order to minimize the amount * of TSO splitting we do. View it as a kind of TSO Nagle test. * * This algorithm is from John Heffner. */ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, bool *is_cwnd_limited, bool *is_rwnd_limited, u32 max_segs) { const struct inet_connection_sock *icsk = inet_csk(sk); u32 send_win, cong_win, limit, in_flight; struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *head; int win_divisor; s64 delta; if (icsk->icsk_ca_state >= TCP_CA_Recovery) goto send_now; /* Avoid bursty behavior by allowing defer * only if the last write was recent (1 ms). * Note that tp->tcp_wstamp_ns can be in the future if we have * packets waiting in a qdisc or device for EDT delivery. */ delta = tp->tcp_clock_cache - tp->tcp_wstamp_ns - NSEC_PER_MSEC; if (delta > 0) goto send_now; in_flight = tcp_packets_in_flight(tp); BUG_ON(tcp_skb_pcount(skb) <= 1); BUG_ON(tcp_snd_cwnd(tp) <= in_flight); send_win = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; /* From in_flight test above, we know that cwnd > in_flight. */ cong_win = (tcp_snd_cwnd(tp) - in_flight) * tp->mss_cache; limit = min(send_win, cong_win); /* If a full-sized TSO skb can be sent, do it. */ if (limit >= max_segs * tp->mss_cache) goto send_now; /* Middle in queue won't get any more data, full sendable already? */ if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len)) goto send_now; win_divisor = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_win_divisor); if (win_divisor) { u32 chunk = min(tp->snd_wnd, tcp_snd_cwnd(tp) * tp->mss_cache); /* If at least some fraction of a window is available, * just use it. */ chunk /= win_divisor; if (limit >= chunk) goto send_now; } else { /* Different approach, try not to defer past a single * ACK. Receiver should ACK every other full sized * frame, so if we have space for more than 3 frames * then send now. */ if (limit > tcp_max_tso_deferred_mss(tp) * tp->mss_cache) goto send_now; } /* TODO : use tsorted_sent_queue ? */ head = tcp_rtx_queue_head(sk); if (!head) goto send_now; delta = tp->tcp_clock_cache - head->tstamp; /* If next ACK is likely to come too late (half srtt), do not defer */ if ((s64)(delta - (u64)NSEC_PER_USEC * (tp->srtt_us >> 4)) < 0) goto send_now; /* Ok, it looks like it is advisable to defer. * Three cases are tracked : * 1) We are cwnd-limited * 2) We are rwnd-limited * 3) We are application limited. */ if (cong_win < send_win) { if (cong_win <= skb->len) { *is_cwnd_limited = true; return true; } } else { if (send_win <= skb->len) { *is_rwnd_limited = true; return true; } } /* If this packet won't get more data, do not wait. */ if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) || TCP_SKB_CB(skb)->eor) goto send_now; return true; send_now: return false; } static inline void tcp_mtu_check_reprobe(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); u32 interval; s32 delta; interval = READ_ONCE(net->ipv4.sysctl_tcp_probe_interval); delta = tcp_jiffies32 - icsk->icsk_mtup.probe_timestamp; if (unlikely(delta >= interval * HZ)) { int mss = tcp_current_mss(sk); /* Update current search range */ icsk->icsk_mtup.probe_size = 0; icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) + icsk->icsk_af_ops->net_header_len; icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); /* Update probe time stamp */ icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } } static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) { struct sk_buff *skb, *next; skb = tcp_send_head(sk); tcp_for_write_queue_from_safe(skb, next, sk) { if (len <= skb->len) break; if (tcp_has_tx_tstamp(skb) || !tcp_skb_can_collapse(skb, next)) return false; len -= skb->len; } return true; } static int tcp_clone_payload(struct sock *sk, struct sk_buff *to, int probe_size) { skb_frag_t *lastfrag = NULL, *fragto = skb_shinfo(to)->frags; int i, todo, len = 0, nr_frags = 0; const struct sk_buff *skb; if (!sk_wmem_schedule(sk, to->truesize + probe_size)) return -ENOMEM; skb_queue_walk(&sk->sk_write_queue, skb) { const skb_frag_t *fragfrom = skb_shinfo(skb)->frags; if (skb_headlen(skb)) return -EINVAL; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++, fragfrom++) { if (len >= probe_size) goto commit; todo = min_t(int, skb_frag_size(fragfrom), probe_size - len); len += todo; if (lastfrag && skb_frag_page(fragfrom) == skb_frag_page(lastfrag) && skb_frag_off(fragfrom) == skb_frag_off(lastfrag) + skb_frag_size(lastfrag)) { skb_frag_size_add(lastfrag, todo); continue; } if (unlikely(nr_frags == MAX_SKB_FRAGS)) return -E2BIG; skb_frag_page_copy(fragto, fragfrom); skb_frag_off_copy(fragto, fragfrom); skb_frag_size_set(fragto, todo); nr_frags++; lastfrag = fragto++; } } commit: WARN_ON_ONCE(len != probe_size); for (i = 0; i < nr_frags; i++) skb_frag_ref(to, i); skb_shinfo(to)->nr_frags = nr_frags; to->truesize += probe_size; to->len += probe_size; to->data_len += probe_size; __skb_header_release(to); return 0; } /* tcp_mtu_probe() and tcp_grow_skb() can both eat an skb (src) if * all its payload was moved to another one (dst). * Make sure to transfer tcp_flags, eor, and tstamp. */ static void tcp_eat_one_skb(struct sock *sk, struct sk_buff *dst, struct sk_buff *src) { TCP_SKB_CB(dst)->tcp_flags |= TCP_SKB_CB(src)->tcp_flags; TCP_SKB_CB(dst)->eor = TCP_SKB_CB(src)->eor; tcp_skb_collapse_tstamp(dst, src); tcp_unlink_write_queue(src, sk); tcp_wmem_free_skb(sk, src); } /* Create a new MTU probe if we are ready. * MTU probe is regularly attempting to increase the path MTU by * deliberately sending larger packets. This discovers routing * changes resulting in larger path MTUs. * * Returns 0 if we should wait to probe (no cwnd available), * 1 if a probe was sent, * -1 otherwise */ static int tcp_mtu_probe(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb, *nskb, *next; struct net *net = sock_net(sk); int probe_size; int size_needed; int copy, len; int mss_now; int interval; /* Not currently probing/verifying, * not in recovery, * have enough cwnd, and * not SACKing (the variable headers throw things off) */ if (likely(!icsk->icsk_mtup.enabled || icsk->icsk_mtup.probe_size || inet_csk(sk)->icsk_ca_state != TCP_CA_Open || tcp_snd_cwnd(tp) < 11 || tp->rx_opt.num_sacks || tp->rx_opt.dsack)) return -1; /* Use binary search for probe_size between tcp_mss_base, * and current mss_clamp. if (search_high - search_low) * smaller than a threshold, backoff from probing. */ mss_now = tcp_current_mss(sk); probe_size = tcp_mtu_to_mss(sk, (icsk->icsk_mtup.search_high + icsk->icsk_mtup.search_low) >> 1); size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache; interval = icsk->icsk_mtup.search_high - icsk->icsk_mtup.search_low; /* When misfortune happens, we are reprobing actively, * and then reprobe timer has expired. We stick with current * probing process by not resetting search range to its orignal. */ if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) || interval < READ_ONCE(net->ipv4.sysctl_tcp_probe_threshold)) { /* Check whether enough time has elaplased for * another round of probing. */ tcp_mtu_check_reprobe(sk); return -1; } /* Have enough data in the send queue to probe? */ if (tp->write_seq - tp->snd_nxt < size_needed) return -1; if (tp->snd_wnd < size_needed) return -1; if (after(tp->snd_nxt + size_needed, tcp_wnd_end(tp))) return 0; /* Do we need to wait to drain cwnd? With none in flight, don't stall */ if (tcp_packets_in_flight(tp) + 2 > tcp_snd_cwnd(tp)) { if (!tcp_packets_in_flight(tp)) return -1; else return 0; } if (!tcp_can_coalesce_send_queue_head(sk, probe_size)) return -1; /* We're allowed to probe. Build it now. */ nskb = tcp_stream_alloc_skb(sk, GFP_ATOMIC, false); if (!nskb) return -1; /* build the payload, and be prepared to abort if this fails. */ if (tcp_clone_payload(sk, nskb, probe_size)) { tcp_skb_tsorted_anchor_cleanup(nskb); consume_skb(nskb); return -1; } sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); skb = tcp_send_head(sk); skb_copy_decrypted(nskb, skb); mptcp_skb_ext_copy(nskb, skb); TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq; TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size; TCP_SKB_CB(nskb)->tcp_flags = TCPHDR_ACK; tcp_insert_write_queue_before(nskb, skb, sk); tcp_highest_sack_replace(sk, skb, nskb); len = 0; tcp_for_write_queue_from_safe(skb, next, sk) { copy = min_t(int, skb->len, probe_size - len); if (skb->len <= copy) { tcp_eat_one_skb(sk, nskb, skb); } else { TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags & ~(TCPHDR_FIN|TCPHDR_PSH); __pskb_trim_head(skb, copy); tcp_set_skb_tso_segs(skb, mss_now); TCP_SKB_CB(skb)->seq += copy; } len += copy; if (len >= probe_size) break; } tcp_init_tso_segs(nskb, nskb->len); /* We're ready to send. If this fails, the probe will * be resegmented into mss-sized pieces by tcp_write_xmit(). */ if (!tcp_transmit_skb(sk, nskb, 1, GFP_ATOMIC)) { /* Decrement cwnd here because we are sending * effectively two packets. */ tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) - 1); tcp_event_new_data_sent(sk, nskb); icsk->icsk_mtup.probe_size = tcp_mss_to_mtu(sk, nskb->len); tp->mtu_probe.probe_seq_start = TCP_SKB_CB(nskb)->seq; tp->mtu_probe.probe_seq_end = TCP_SKB_CB(nskb)->end_seq; return 1; } return -1; } static bool tcp_pacing_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (!tcp_needs_internal_pacing(sk)) return false; if (tp->tcp_wstamp_ns <= tp->tcp_clock_cache) return false; if (!hrtimer_is_queued(&tp->pacing_timer)) { hrtimer_start(&tp->pacing_timer, ns_to_ktime(tp->tcp_wstamp_ns), HRTIMER_MODE_ABS_PINNED_SOFT); sock_hold(sk); } return true; } static bool tcp_rtx_queue_empty_or_single_skb(const struct sock *sk) { const struct rb_node *node = sk->tcp_rtx_queue.rb_node; /* No skb in the rtx queue. */ if (!node) return true; /* Only one skb in rtx queue. */ return !node->rb_left && !node->rb_right; } /* TCP Small Queues : * Control number of packets in qdisc/devices to two packets / or ~1 ms. * (These limits are doubled for retransmits) * This allows for : * - better RTT estimation and ACK scheduling * - faster recovery * - high rates * Alas, some drivers / subsystems require a fair amount * of queued bytes to ensure line rate. * One example is wifi aggregation (802.11 AMPDU) */ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, unsigned int factor) { unsigned long limit; limit = max_t(unsigned long, 2 * skb->truesize, READ_ONCE(sk->sk_pacing_rate) >> READ_ONCE(sk->sk_pacing_shift)); if (sk->sk_pacing_status == SK_PACING_NONE) limit = min_t(unsigned long, limit, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes)); limit <<= factor; if (static_branch_unlikely(&tcp_tx_delay_enabled) && tcp_sk(sk)->tcp_tx_delay) { u64 extra_bytes = (u64)READ_ONCE(sk->sk_pacing_rate) * tcp_sk(sk)->tcp_tx_delay; /* TSQ is based on skb truesize sum (sk_wmem_alloc), so we * approximate our needs assuming an ~100% skb->truesize overhead. * USEC_PER_SEC is approximated by 2^20. * do_div(extra_bytes, USEC_PER_SEC/2) is replaced by a right shift. */ extra_bytes >>= (20 - 1); limit += extra_bytes; } if (refcount_read(&sk->sk_wmem_alloc) > limit) { /* Always send skb if rtx queue is empty or has one skb. * No need to wait for TX completion to call us back, * after softirq/tasklet schedule. * This helps when TX completions are delayed too much. */ if (tcp_rtx_queue_empty_or_single_skb(sk)) return false; set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); /* It is possible TX completion already happened * before we set TSQ_THROTTLED, so we must * test again the condition. */ smp_mb__after_atomic(); if (refcount_read(&sk->sk_wmem_alloc) > limit) return true; } return false; } static void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new) { const u32 now = tcp_jiffies32; enum tcp_chrono old = tp->chrono_type; if (old > TCP_CHRONO_UNSPEC) tp->chrono_stat[old - 1] += now - tp->chrono_start; tp->chrono_start = now; tp->chrono_type = new; } void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type) { struct tcp_sock *tp = tcp_sk(sk); /* If there are multiple conditions worthy of tracking in a * chronograph then the highest priority enum takes precedence * over the other conditions. So that if something "more interesting" * starts happening, stop the previous chrono and start a new one. */ if (type > tp->chrono_type) tcp_chrono_set(tp, type); } void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type) { struct tcp_sock *tp = tcp_sk(sk); /* There are multiple conditions worthy of tracking in a * chronograph, so that the highest priority enum takes * precedence over the other conditions (see tcp_chrono_start). * If a condition stops, we only stop chrono tracking if * it's the "most interesting" or current chrono we are * tracking and starts busy chrono if we have pending data. */ if (tcp_rtx_and_write_queues_empty(sk)) tcp_chrono_set(tp, TCP_CHRONO_UNSPEC); else if (type == tp->chrono_type) tcp_chrono_set(tp, TCP_CHRONO_BUSY); } /* First skb in the write queue is smaller than ideal packet size. * Check if we can move payload from the second skb in the queue. */ static void tcp_grow_skb(struct sock *sk, struct sk_buff *skb, int amount) { struct sk_buff *next_skb = skb->next; unsigned int nlen; if (tcp_skb_is_last(sk, skb)) return; if (!tcp_skb_can_collapse(skb, next_skb)) return; nlen = min_t(u32, amount, next_skb->len); if (!nlen || !skb_shift(skb, next_skb, nlen)) return; TCP_SKB_CB(skb)->end_seq += nlen; TCP_SKB_CB(next_skb)->seq += nlen; if (!next_skb->len) { /* In case FIN is set, we need to update end_seq */ TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq; tcp_eat_one_skb(sk, skb, next_skb); } } /* This routine writes packets to the network. It advances the * send_head. This happens as incoming acks open up the remote * window for us. * * LARGESEND note: !tcp_urg_mode is overkill, only frames between * snd_up-64k-mss .. snd_up cannot be large. However, taking into * account rare use of URG, this is not a big flaw. * * Send at most one packet when push_one > 0. Temporarily ignore * cwnd limit to force at most one packet out when push_one == 2. * Returns true, if no segments are in flight and we have queued segments, * but cannot send anything now because of SWS or another problem. */ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; unsigned int tso_segs, sent_pkts; u32 cwnd_quota, max_segs; int result; bool is_cwnd_limited = false, is_rwnd_limited = false; sent_pkts = 0; tcp_mstamp_refresh(tp); if (!push_one) { /* Do MTU probing. */ result = tcp_mtu_probe(sk); if (!result) { return false; } else if (result > 0) { sent_pkts = 1; } } max_segs = tcp_tso_segs(sk, mss_now); while ((skb = tcp_send_head(sk))) { unsigned int limit; int missing_bytes; if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { /* "skb_mstamp_ns" is used as a start point for the retransmit timer */ tp->tcp_wstamp_ns = tp->tcp_clock_cache; skb_set_delivery_time(skb, tp->tcp_wstamp_ns, SKB_CLOCK_MONOTONIC); list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); tcp_init_tso_segs(skb, mss_now); goto repair; /* Skip network transmission */ } if (tcp_pacing_check(sk)) break; cwnd_quota = tcp_cwnd_test(tp); if (!cwnd_quota) { if (push_one == 2) /* Force out a loss probe pkt. */ cwnd_quota = 1; else break; } cwnd_quota = min(cwnd_quota, max_segs); missing_bytes = cwnd_quota * mss_now - skb->len; if (missing_bytes > 0) tcp_grow_skb(sk, skb, missing_bytes); tso_segs = tcp_set_skb_tso_segs(skb, mss_now); if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) { is_rwnd_limited = true; break; } if (tso_segs == 1) { if (unlikely(!tcp_nagle_test(tp, skb, mss_now, (tcp_skb_is_last(sk, skb) ? nonagle : TCP_NAGLE_PUSH)))) break; } else { if (!push_one && tcp_tso_should_defer(sk, skb, &is_cwnd_limited, &is_rwnd_limited, max_segs)) break; } limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, cwnd_quota, nonagle); if (skb->len > limit && unlikely(tso_fragment(sk, skb, limit, mss_now, gfp))) break; if (tcp_small_queue_check(sk, skb, 0)) break; /* Argh, we hit an empty skb(), presumably a thread * is sleeping in sendmsg()/sk_stream_wait_memory(). * We do not want to send a pure-ack packet and have * a strange looking rtx queue with empty packet(s). */ if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) break; if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; repair: /* Advance the send_head. This one is sent out. * This call will increment packets_out. */ tcp_event_new_data_sent(sk, skb); tcp_minshall_update(tp, mss_now, skb); sent_pkts += tcp_skb_pcount(skb); if (push_one) break; } if (is_rwnd_limited) tcp_chrono_start(sk, TCP_CHRONO_RWND_LIMITED); else tcp_chrono_stop(sk, TCP_CHRONO_RWND_LIMITED); is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tcp_snd_cwnd(tp)); if (likely(sent_pkts || is_cwnd_limited)) tcp_cwnd_validate(sk, is_cwnd_limited); if (likely(sent_pkts)) { if (tcp_in_cwnd_reduction(sk)) tp->prr_out += sent_pkts; /* Send one loss probe per tail loss episode. */ if (push_one != 2) tcp_schedule_loss_probe(sk, false); return false; } return !tp->packets_out && !tcp_write_queue_empty(sk); } bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); u32 timeout, timeout_us, rto_delta_us; int early_retrans; /* Don't do any loss probe on a Fast Open connection before 3WHS * finishes. */ if (rcu_access_pointer(tp->fastopen_rsk)) return false; early_retrans = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_early_retrans); /* Schedule a loss probe in 2*RTT for SACK capable connections * not in loss recovery, that are either limited by cwnd or application. */ if ((early_retrans != 3 && early_retrans != 4) || !tp->packets_out || !tcp_is_sack(tp) || (icsk->icsk_ca_state != TCP_CA_Open && icsk->icsk_ca_state != TCP_CA_CWR)) return false; /* Probe timeout is 2*rtt. Add minimum RTO to account * for delayed ack when there's one outstanding packet. If no RTT * sample is available then probe after TCP_TIMEOUT_INIT. */ if (tp->srtt_us) { timeout_us = tp->srtt_us >> 2; if (tp->packets_out == 1) timeout_us += tcp_rto_min_us(sk); else timeout_us += TCP_TIMEOUT_MIN_US; timeout = usecs_to_jiffies(timeout_us); } else { timeout = TCP_TIMEOUT_INIT; } /* If the RTO formula yields an earlier time, then use that time. */ rto_delta_us = advancing_rto ? jiffies_to_usecs(inet_csk(sk)->icsk_rto) : tcp_rto_delta_us(sk); /* How far in future is RTO? */ if (rto_delta_us > 0) timeout = min_t(u32, timeout, usecs_to_jiffies(rto_delta_us)); tcp_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, TCP_RTO_MAX); return true; } /* Thanks to skb fast clones, we can detect if a prior transmit of * a packet is still in a qdisc or driver queue. * In this case, there is very little point doing a retransmit ! */ static bool skb_still_in_host_queue(struct sock *sk, const struct sk_buff *skb) { if (unlikely(skb_fclone_busy(sk, skb))) { set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); smp_mb__after_atomic(); if (skb_fclone_busy(sk, skb)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); return true; } } return false; } /* When probe timeout (PTO) fires, try send a new segment if possible, else * retransmit the last segment. */ void tcp_send_loss_probe(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; int pcount; int mss = tcp_current_mss(sk); /* At most one outstanding TLP */ if (tp->tlp_high_seq) goto rearm_timer; tp->tlp_retrans = 0; skb = tcp_send_head(sk); if (skb && tcp_snd_wnd_test(tp, skb, mss)) { pcount = tp->packets_out; tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); if (tp->packets_out > pcount) goto probe_sent; goto rearm_timer; } skb = skb_rb_last(&sk->tcp_rtx_queue); if (unlikely(!skb)) { tcp_warn_once(sk, tp->packets_out, "invalid inflight: "); smp_store_release(&inet_csk(sk)->icsk_pending, 0); return; } if (skb_still_in_host_queue(sk, skb)) goto rearm_timer; pcount = tcp_skb_pcount(skb); if (WARN_ON(!pcount)) goto rearm_timer; if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) { if (unlikely(tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, (pcount - 1) * mss, mss, GFP_ATOMIC))) goto rearm_timer; skb = skb_rb_next(skb); } if (WARN_ON(!skb || !tcp_skb_pcount(skb))) goto rearm_timer; if (__tcp_retransmit_skb(sk, skb, 1)) goto rearm_timer; tp->tlp_retrans = 1; probe_sent: /* Record snd_nxt for loss detection. */ tp->tlp_high_seq = tp->snd_nxt; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); /* Reset s.t. tcp_rearm_rto will restart timer from now */ smp_store_release(&inet_csk(sk)->icsk_pending, 0); rearm_timer: tcp_rearm_rto(sk); } /* Push out any pending frames which were held back due to * TCP_CORK or attempt at coalescing tiny packets. * The socket must be locked by the caller. */ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle) { /* If we are closed, the bytes will have to remain here. * In time closedown will finish, we empty the write queue and * all will be happy. */ if (unlikely(sk->sk_state == TCP_CLOSE)) return; if (tcp_write_xmit(sk, cur_mss, nonagle, 0, sk_gfp_mask(sk, GFP_ATOMIC))) tcp_check_probe_timer(sk); } /* Send _single_ skb sitting at the send head. This function requires * true push pending frames to setup probe timer etc. */ void tcp_push_one(struct sock *sk, unsigned int mss_now) { struct sk_buff *skb = tcp_send_head(sk); BUG_ON(!skb || skb->len < mss_now); tcp_write_xmit(sk, mss_now, TCP_NAGLE_PUSH, 1, sk->sk_allocation); } /* This function returns the amount that we can raise the * usable window based on the following constraints * * 1. The window can never be shrunk once it is offered (RFC 793) * 2. We limit memory per socket * * RFC 1122: * "the suggested [SWS] avoidance algorithm for the receiver is to keep * RECV.NEXT + RCV.WIN fixed until: * RCV.BUFF - RCV.USER - RCV.WINDOW >= min(1/2 RCV.BUFF, MSS)" * * i.e. don't raise the right edge of the window until you can raise * it at least MSS bytes. * * Unfortunately, the recommended algorithm breaks header prediction, * since header prediction assumes th->window stays fixed. * * Strictly speaking, keeping th->window fixed violates the receiver * side SWS prevention criteria. The problem is that under this rule * a stream of single byte packets will cause the right side of the * window to always advance by a single byte. * * Of course, if the sender implements sender side SWS prevention * then this will not be a problem. * * BSD seems to make the following compromise: * * If the free space is less than the 1/4 of the maximum * space available and the free space is less than 1/2 mss, * then set the window to 0. * [ Actually, bsd uses MSS and 1/4 of maximal _window_ ] * Otherwise, just prevent the window from shrinking * and from being larger than the largest representable value. * * This prevents incremental opening of the window in the regime * where TCP is limited by the speed of the reader side taking * data out of the TCP receive queue. It does nothing about * those cases where the window is constrained on the sender side * because the pipeline is full. * * BSD also seems to "accidentally" limit itself to windows that are a * multiple of MSS, at least until the free space gets quite small. * This would appear to be a side effect of the mbuf implementation. * Combining these two algorithms results in the observed behavior * of having a fixed window size at almost all times. * * Below we obtain similar behavior by forcing the offered window to * a multiple of the mss when it is feasible to do so. * * Note, we don't "adjust" for TIMESTAMP or SACK option bytes. * Regular options like TIMESTAMP are taken into account. */ u32 __tcp_select_window(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); /* MSS for the peer's data. Previous versions used mss_clamp * here. I don't know if the value based on our guesses * of peer's MSS is better for the performance. It's more correct * but may be worse for the performance because of rcv_mss * fluctuations. --SAW 1998/11/1 */ int mss = icsk->icsk_ack.rcv_mss; int free_space = tcp_space(sk); int allowed_space = tcp_full_space(sk); int full_space, window; if (sk_is_mptcp(sk)) mptcp_space(sk, &free_space, &allowed_space); full_space = min_t(int, tp->window_clamp, allowed_space); if (unlikely(mss > full_space)) { mss = full_space; if (mss <= 0) return 0; } /* Only allow window shrink if the sysctl is enabled and we have * a non-zero scaling factor in effect. */ if (READ_ONCE(net->ipv4.sysctl_tcp_shrink_window) && tp->rx_opt.rcv_wscale) goto shrink_window_allowed; /* do not allow window to shrink */ if (free_space < (full_space >> 1)) { icsk->icsk_ack.quick = 0; if (tcp_under_memory_pressure(sk)) tcp_adjust_rcv_ssthresh(sk); /* free_space might become our new window, make sure we don't * increase it due to wscale. */ free_space = round_down(free_space, 1 << tp->rx_opt.rcv_wscale); /* if free space is less than mss estimate, or is below 1/16th * of the maximum allowed, try to move to zero-window, else * tcp_clamp_window() will grow rcv buf up to tcp_rmem[2], and * new incoming data is dropped due to memory limits. * With large window, mss test triggers way too late in order * to announce zero window in time before rmem limit kicks in. */ if (free_space < (allowed_space >> 4) || free_space < mss) return 0; } if (free_space > tp->rcv_ssthresh) free_space = tp->rcv_ssthresh; /* Don't do rounding if we are using window scaling, since the * scaled window will not line up with the MSS boundary anyway. */ if (tp->rx_opt.rcv_wscale) { window = free_space; /* Advertise enough space so that it won't get scaled away. * Import case: prevent zero window announcement if * 1<<rcv_wscale > mss. */ window = ALIGN(window, (1 << tp->rx_opt.rcv_wscale)); } else { window = tp->rcv_wnd; /* Get the largest window that is a nice multiple of mss. * Window clamp already applied above. * If our current window offering is within 1 mss of the * free space we just keep it. This prevents the divide * and multiply from happening most of the time. * We also don't do any window rounding when the free space * is too small. */ if (window <= free_space - mss || window > free_space) window = rounddown(free_space, mss); else if (mss == full_space && free_space > window + (full_space >> 1)) window = free_space; } return window; shrink_window_allowed: /* new window should always be an exact multiple of scaling factor */ free_space = round_down(free_space, 1 << tp->rx_opt.rcv_wscale); if (free_space < (full_space >> 1)) { icsk->icsk_ack.quick = 0; if (tcp_under_memory_pressure(sk)) tcp_adjust_rcv_ssthresh(sk); /* if free space is too low, return a zero window */ if (free_space < (allowed_space >> 4) || free_space < mss || free_space < (1 << tp->rx_opt.rcv_wscale)) return 0; } if (free_space > tp->rcv_ssthresh) { free_space = tp->rcv_ssthresh; /* new window should always be an exact multiple of scaling factor * * For this case, we ALIGN "up" (increase free_space) because * we know free_space is not zero here, it has been reduced from * the memory-based limit, and rcv_ssthresh is not a hard limit * (unlike sk_rcvbuf). */ free_space = ALIGN(free_space, (1 << tp->rx_opt.rcv_wscale)); } return free_space; } void tcp_skb_collapse_tstamp(struct sk_buff *skb, const struct sk_buff *next_skb) { if (unlikely(tcp_has_tx_tstamp(next_skb))) { const struct skb_shared_info *next_shinfo = skb_shinfo(next_skb); struct skb_shared_info *shinfo = skb_shinfo(skb); shinfo->tx_flags |= next_shinfo->tx_flags & SKBTX_ANY_TSTAMP; shinfo->tskey = next_shinfo->tskey; TCP_SKB_CB(skb)->txstamp_ack |= TCP_SKB_CB(next_skb)->txstamp_ack; } } /* Collapses two adjacent SKB's during retransmission. */ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *next_skb = skb_rb_next(skb); int next_skb_size; next_skb_size = next_skb->len; BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1); if (next_skb_size && !tcp_skb_shift(skb, next_skb, 1, next_skb_size)) return false; tcp_highest_sack_replace(sk, next_skb, skb); /* Update sequence range on original skb. */ TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq; /* Merge over control information. This moves PSH/FIN etc. over */ TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(next_skb)->tcp_flags; /* All done, get rid of second SKB and account for it so * packet counting does not break. */ TCP_SKB_CB(skb)->sacked |= TCP_SKB_CB(next_skb)->sacked & TCPCB_EVER_RETRANS; TCP_SKB_CB(skb)->eor = TCP_SKB_CB(next_skb)->eor; /* changed transmit queue under us so clear hints */ tcp_clear_retrans_hints_partial(tp); if (next_skb == tp->retransmit_skb_hint) tp->retransmit_skb_hint = skb; tcp_adjust_pcount(sk, next_skb, tcp_skb_pcount(next_skb)); tcp_skb_collapse_tstamp(skb, next_skb); tcp_rtx_queue_unlink_and_free(next_skb, sk); return true; } /* Check if coalescing SKBs is legal. */ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) { if (tcp_skb_pcount(skb) > 1) return false; if (skb_cloned(skb)) return false; if (!skb_frags_readable(skb)) return false; /* Some heuristics for collapsing over SACK'd could be invented */ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) return false; return true; } /* Collapse packets in the retransmit queue to make to create * less packets on the wire. This is only done on retransmission. */ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, int space) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb = to, *tmp; bool first = true; if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse)) return; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) return; skb_rbtree_walk_from_safe(skb, tmp) { if (!tcp_can_collapse(sk, skb)) break; if (!tcp_skb_can_collapse(to, skb)) break; space -= skb->len; if (first) { first = false; continue; } if (space < 0) break; if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp))) break; if (!tcp_collapse_retrans(sk, to)) break; } } /* This retransmits one SKB. Policy decisions and retransmit queue * state updates are done by the caller. Returns non-zero if an * error occurred which prevented the send. */ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned int cur_mss; int diff, len, err; int avail_wnd; /* Inconclusive MTU probe */ if (icsk->icsk_mtup.probe_size) icsk->icsk_mtup.probe_size = 0; if (skb_still_in_host_queue(sk, skb)) return -EBUSY; start: if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN; TCP_SKB_CB(skb)->seq++; goto start; } if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) { WARN_ON_ONCE(1); return -EINVAL; } if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) return -ENOMEM; } if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) return -EHOSTUNREACH; /* Routing failure or similar. */ cur_mss = tcp_current_mss(sk); avail_wnd = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; /* If receiver has shrunk his window, and skb is out of * new window, do not retransmit it. The exception is the * case, when window is shrunk to zero. In this case * our retransmit of one segment serves as a zero window probe. */ if (avail_wnd <= 0) { if (TCP_SKB_CB(skb)->seq != tp->snd_una) return -EAGAIN; avail_wnd = cur_mss; } len = cur_mss * segs; if (len > avail_wnd) { len = rounddown(avail_wnd, cur_mss); if (!len) len = avail_wnd; } if (skb->len > len) { if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len, cur_mss, GFP_ATOMIC)) return -ENOMEM; /* We'll try again later. */ } else { if (skb_unclone_keeptruesize(skb, GFP_ATOMIC)) return -ENOMEM; diff = tcp_skb_pcount(skb); tcp_set_skb_tso_segs(skb, cur_mss); diff -= tcp_skb_pcount(skb); if (diff) tcp_adjust_pcount(sk, skb, diff); avail_wnd = min_t(int, avail_wnd, cur_mss); if (skb->len < avail_wnd) tcp_retrans_try_collapse(sk, skb, avail_wnd); } /* RFC3168, section 6.1.1.1. ECN fallback */ if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN) tcp_ecn_clear_syn(sk, skb); /* Update global and local TCP statistics. */ segs = tcp_skb_pcount(skb); TCP_ADD_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS, segs); if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); tp->total_retrans += segs; tp->bytes_retrans += skb->len; /* make sure skb->data is aligned on arches that require it * and check if ack-trimming & collapsing extended the headroom * beyond what csum_start can cover. */ if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) || skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb; tcp_skb_tsorted_save(skb) { nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); if (nskb) { nskb->dev = NULL; err = tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC); } else { err = -ENOBUFS; } } tcp_skb_tsorted_restore(skb); if (!err) { tcp_update_skb_after_send(sk, skb, tp->tcp_wstamp_ns); tcp_rate_skb_sent(sk, skb); } } else { err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG)) tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB, TCP_SKB_CB(skb)->seq, segs, err); if (likely(!err)) { trace_tcp_retransmit_skb(sk, skb); } else if (err != -EBUSY) { NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs); } /* To avoid taking spuriously low RTT samples based on a timestamp * for a transmit that never happened, always mark EVER_RETRANS */ TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; return err; } int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) { struct tcp_sock *tp = tcp_sk(sk); int err = __tcp_retransmit_skb(sk, skb, segs); if (err == 0) { #if FASTRETRANS_DEBUG > 0 if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { net_dbg_ratelimited("retrans_out leaked\n"); } #endif TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS; tp->retrans_out += tcp_skb_pcount(skb); } /* Save stamp of the first (attempted) retransmit. */ if (!tp->retrans_stamp) tp->retrans_stamp = tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb); if (tp->undo_retrans < 0) tp->undo_retrans = 0; tp->undo_retrans += tcp_skb_pcount(skb); return err; } /* This gets called after a retransmit timeout, and the initially * retransmitted data is acknowledged. It tries to continue * resending the rest of the retransmit queue, until either * we've sent it all or the congestion window limit is reached. */ void tcp_xmit_retransmit_queue(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); struct sk_buff *skb, *rtx_head, *hole = NULL; struct tcp_sock *tp = tcp_sk(sk); bool rearm_timer = false; u32 max_segs; int mib_idx; if (!tp->packets_out) return; rtx_head = tcp_rtx_queue_head(sk); skb = tp->retransmit_skb_hint ?: rtx_head; max_segs = tcp_tso_segs(sk, tcp_current_mss(sk)); skb_rbtree_walk_from(skb) { __u8 sacked; int segs; if (tcp_pacing_check(sk)) break; /* we could do better than to assign each time */ if (!hole) tp->retransmit_skb_hint = skb; segs = tcp_snd_cwnd(tp) - tcp_packets_in_flight(tp); if (segs <= 0) break; sacked = TCP_SKB_CB(skb)->sacked; /* In case tcp_shift_skb_data() have aggregated large skbs, * we need to make sure not sending too bigs TSO packets */ segs = min_t(int, segs, max_segs); if (tp->retrans_out >= tp->lost_out) { break; } else if (!(sacked & TCPCB_LOST)) { if (!hole && !(sacked & (TCPCB_SACKED_RETRANS|TCPCB_SACKED_ACKED))) hole = skb; continue; } else { if (icsk->icsk_ca_state != TCP_CA_Loss) mib_idx = LINUX_MIB_TCPFASTRETRANS; else mib_idx = LINUX_MIB_TCPSLOWSTARTRETRANS; } if (sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS)) continue; if (tcp_small_queue_check(sk, skb, 1)) break; if (tcp_retransmit_skb(sk, skb, segs)) break; NET_ADD_STATS(sock_net(sk), mib_idx, tcp_skb_pcount(skb)); if (tcp_in_cwnd_reduction(sk)) tp->prr_out += tcp_skb_pcount(skb); if (skb == rtx_head && icsk->icsk_pending != ICSK_TIME_REO_TIMEOUT) rearm_timer = true; } if (rearm_timer) tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, TCP_RTO_MAX); } /* We allow to exceed memory limits for FIN packets to expedite * connection tear down and (memory) recovery. * Otherwise tcp_send_fin() could be tempted to either delay FIN * or even be forced to close flow without any FIN. * In general, we want to allow one skb per socket to avoid hangs * with edge trigger epoll() */ void sk_forced_mem_schedule(struct sock *sk, int size) { int delta, amt; delta = size - sk->sk_forward_alloc; if (delta <= 0) return; amt = sk_mem_pages(delta); sk_forward_alloc_add(sk, amt << PAGE_SHIFT); sk_memory_allocated_add(sk, amt); if (mem_cgroup_sockets_enabled && sk->sk_memcg) mem_cgroup_charge_skmem(sk->sk_memcg, amt, gfp_memcg_charge() | __GFP_NOFAIL); } /* Send a FIN. The caller locks the socket for us. * We should try to send a FIN packet really hard, but eventually give up. */ void tcp_send_fin(struct sock *sk) { struct sk_buff *skb, *tskb, *tail = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); /* Optimization, tack on the FIN if we have one skb in write queue and * this skb was not yet sent, or we are under memory pressure. * Note: in the latter case, FIN packet will be sent after a timeout, * as TCP stack thinks it has already been transmitted. */ tskb = tail; if (!tskb && tcp_under_memory_pressure(sk)) tskb = skb_rb_last(&sk->tcp_rtx_queue); if (tskb) { TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; if (!tail) { /* This means tskb was already sent. * Pretend we included the FIN on previous transmit. * We need to set tp->snd_nxt to the value it would have * if FIN had been sent. This is because retransmit path * does not change tp->snd_nxt. */ WRITE_ONCE(tp->snd_nxt, tp->snd_nxt + 1); return; } } else { skb = alloc_skb_fclone(MAX_TCP_HEADER, sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN)); if (unlikely(!skb)) return; INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); skb_reserve(skb, MAX_TCP_HEADER); sk_forced_mem_schedule(sk, skb->truesize); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ tcp_init_nondata_skb(skb, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); tcp_queue_skb(sk, skb); } __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF); } /* We get here when a process closes a file descriptor (either due to * an explicit close() or as a byproduct of exit()'ing) and there * was unread data in the receive queue. This behavior is recommended * by RFC 2525, section 2.17. -DaveM */ void tcp_send_active_reset(struct sock *sk, gfp_t priority, enum sk_rst_reason reason) { struct sk_buff *skb; TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS); /* NOTE: No TCP options attached and we never retransmit this. */ skb = alloc_skb(MAX_TCP_HEADER, priority); if (!skb) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); return; } /* Reserve space for headers and prepare control bits. */ skb_reserve(skb, MAX_TCP_HEADER); tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk), TCPHDR_ACK | TCPHDR_RST); tcp_mstamp_refresh(tcp_sk(sk)); /* Send it off. */ if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); /* skb of trace_tcp_send_reset() keeps the skb that caused RST, * skb here is different to the troublesome skb, so use NULL */ trace_tcp_send_reset(sk, NULL, reason); } /* Send a crossed SYN-ACK during socket establishment. * WARNING: This routine must only be called when we have already sent * a SYN packet that crossed the incoming SYN that caused this routine * to get called. If this assumption fails then the initial rcv_wnd * and rcv_wscale values will not be correct. */ int tcp_send_synack(struct sock *sk) { struct sk_buff *skb; skb = tcp_rtx_queue_head(sk); if (!skb || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { pr_err("%s: wrong queue state\n", __func__); return -EFAULT; } if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) { if (skb_cloned(skb)) { struct sk_buff *nskb; tcp_skb_tsorted_save(skb) { nskb = skb_copy(skb, GFP_ATOMIC); } tcp_skb_tsorted_restore(skb); if (!nskb) return -ENOMEM; INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor); tcp_highest_sack_replace(sk, skb, nskb); tcp_rtx_queue_unlink_and_free(skb, sk); __skb_header_release(nskb); tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb); sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); skb = nskb; } TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ACK; tcp_ecn_send_synack(sk, skb); } return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } /** * tcp_make_synack - Allocate one skb and build a SYNACK packet. * @sk: listener socket * @dst: dst entry attached to the SYNACK. It is consumed and caller * should not use it again. * @req: request_sock pointer * @foc: cookie for tcp fast open * @synack_type: Type of synack to prepare * @syn_skb: SYN packet just received. It could be NULL for rtx case. */ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type, struct sk_buff *syn_skb) { struct inet_request_sock *ireq = inet_rsk(req); const struct tcp_sock *tp = tcp_sk(sk); struct tcp_out_options opts; struct tcp_key key = {}; struct sk_buff *skb; int tcp_header_size; struct tcphdr *th; int mss; u64 now; skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); if (unlikely(!skb)) { dst_release(dst); return NULL; } /* Reserve space for headers. */ skb_reserve(skb, MAX_TCP_HEADER); switch (synack_type) { case TCP_SYNACK_NORMAL: skb_set_owner_edemux(skb, req_to_sk(req)); break; case TCP_SYNACK_COOKIE: /* Under synflood, we do not attach skb to a socket, * to avoid false sharing. */ break; case TCP_SYNACK_FASTOPEN: /* sk is a const pointer, because we want to express multiple * cpu might call us concurrently. * sk->sk_wmem_alloc in an atomic, we can promote to rw. */ skb_set_owner_w(skb, (struct sock *)sk); break; } skb_dst_set(skb, dst); mss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); memset(&opts, 0, sizeof(opts)); now = tcp_clock_ns(); #ifdef CONFIG_SYN_COOKIES if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok)) skb_set_delivery_time(skb, cookie_init_timestamp(req, now), SKB_CLOCK_MONOTONIC); else #endif { skb_set_delivery_time(skb, now, SKB_CLOCK_MONOTONIC); if (!tcp_rsk(req)->snt_synack) /* Timestamp first SYNACK */ tcp_rsk(req)->snt_synack = tcp_skb_timestamp_us(skb); } #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) rcu_read_lock(); #endif if (tcp_rsk_used_ao(req)) { #ifdef CONFIG_TCP_AO struct tcp_ao_key *ao_key = NULL; u8 keyid = tcp_rsk(req)->ao_keyid; u8 rnext = tcp_rsk(req)->ao_rcv_next; ao_key = tcp_sk(sk)->af_specific->ao_lookup(sk, req_to_sk(req), keyid, -1); /* If there is no matching key - avoid sending anything, * especially usigned segments. It could try harder and lookup * for another peer-matching key, but the peer has requested * ao_keyid (RFC5925 RNextKeyID), so let's keep it simple here. */ if (unlikely(!ao_key)) { trace_tcp_ao_synack_no_key(sk, keyid, rnext); rcu_read_unlock(); kfree_skb(skb); net_warn_ratelimited("TCP-AO: the keyid %u from SYN packet is not present - not sending SYNACK\n", keyid); return NULL; } key.ao_key = ao_key; key.type = TCP_KEY_AO; #endif } else { #ifdef CONFIG_TCP_MD5SIG key.md5_key = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); if (key.md5_key) key.type = TCP_KEY_MD5; #endif } skb_set_hash(skb, READ_ONCE(tcp_rsk(req)->txhash), PKT_HASH_TYPE_L4); /* bpf program will be interested in the tcp_flags */ TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK; tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, &key, foc, synack_type, syn_skb) + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); th = (struct tcphdr *)skb->data; memset(th, 0, sizeof(struct tcphdr)); th->syn = 1; th->ack = 1; tcp_ecn_make_synack(req, th); th->source = htons(ireq->ir_num); th->dest = ireq->ir_rmt_port; skb->mark = ireq->ir_mark; skb->ip_summed = CHECKSUM_PARTIAL; th->seq = htonl(tcp_rsk(req)->snt_isn); /* XXX data is queued and acked as is. No buffer/window check */ th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt); /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(min(req->rsk_rcv_wnd, 65535U)); tcp_options_write(th, NULL, tcp_rsk(req), &opts, &key); th->doff = (tcp_header_size >> 2); TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); /* Okay, we have all we need - do the md5 hash if needed */ if (tcp_key_is_md5(&key)) { #ifdef CONFIG_TCP_MD5SIG tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location, key.md5_key, req_to_sk(req), skb); #endif } else if (tcp_key_is_ao(&key)) { #ifdef CONFIG_TCP_AO tcp_rsk(req)->af_specific->ao_synack_hash(opts.hash_location, key.ao_key, req, skb, opts.hash_location - (u8 *)th, 0); #endif } #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) rcu_read_unlock(); #endif bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb, synack_type, &opts); skb_set_delivery_time(skb, now, SKB_CLOCK_MONOTONIC); tcp_add_tx_delay(skb, tp); return skb; } EXPORT_SYMBOL(tcp_make_synack); static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst) { struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_congestion_ops *ca; u32 ca_key = dst_metric(dst, RTAX_CC_ALGO); if (ca_key == TCP_CA_UNSPEC) return; rcu_read_lock(); ca = tcp_ca_find_key(ca_key); if (likely(ca && bpf_try_module_get(ca, ca->owner))) { bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); icsk->icsk_ca_ops = ca; } rcu_read_unlock(); } /* Do all connect socket setups that can be done AF independent. */ static void tcp_connect_init(struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); __u8 rcv_wscale; u32 rcv_wnd; /* We'll fix this up when we get a response from the other end. * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT. */ tp->tcp_header_len = sizeof(struct tcphdr); if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps)) tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED; tcp_ao_connect_init(sk); /* If user gave his TCP_MAXSEG, record it to clamp */ if (tp->rx_opt.user_mss) tp->rx_opt.mss_clamp = tp->rx_opt.user_mss; tp->max_window = 0; tcp_mtup_init(sk); tcp_sync_mss(sk, dst_mtu(dst)); tcp_ca_dst_init(sk, dst); if (!tp->window_clamp) WRITE_ONCE(tp->window_clamp, dst_metric(dst, RTAX_WINDOW)); tp->advmss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); tcp_initialize_rcv_mss(sk); /* limit the window selection if the user enforce a smaller rx buffer */ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0)) WRITE_ONCE(tp->window_clamp, tcp_full_space(sk)); rcv_wnd = tcp_rwnd_init_bpf(sk); if (rcv_wnd == 0) rcv_wnd = dst_metric(dst, RTAX_INITRWND); tcp_select_initial_window(sk, tcp_full_space(sk), tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling), &rcv_wscale, rcv_wnd); tp->rx_opt.rcv_wscale = rcv_wscale; tp->rcv_ssthresh = tp->rcv_wnd; WRITE_ONCE(sk->sk_err, 0); sock_reset_flag(sk, SOCK_DONE); tp->snd_wnd = 0; tcp_init_wl(tp, 0); tcp_write_queue_purge(sk); tp->snd_una = tp->write_seq; tp->snd_sml = tp->write_seq; tp->snd_up = tp->write_seq; WRITE_ONCE(tp->snd_nxt, tp->write_seq); if (likely(!tp->repair)) tp->rcv_nxt = 0; else tp->rcv_tstamp = tcp_jiffies32; tp->rcv_wup = tp->rcv_nxt; WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); inet_csk(sk)->icsk_rto = tcp_timeout_init(sk); inet_csk(sk)->icsk_retransmits = 0; tcp_clear_retrans(tp); } static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); tcb->end_seq += skb->len; __skb_header_release(skb); sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); WRITE_ONCE(tp->write_seq, tcb->end_seq); tp->packets_out += tcp_skb_pcount(skb); } /* Build and send a SYN with data and (cached) Fast Open cookie. However, * queue a data-only packet after the regular SYN, such that regular SYNs * are retransmitted on timeouts. Also if the remote SYN-ACK acknowledges * only the SYN sequence, the data are retransmitted in the first ACK. * If cookie is not cached or other error occurs, falls back to send a * regular SYN with Fast Open cookie request option. */ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_request *fo = tp->fastopen_req; struct page_frag *pfrag = sk_page_frag(sk); struct sk_buff *syn_data; int space, err = 0; tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */ if (!tcp_fastopen_cookie_check(sk, &tp->rx_opt.mss_clamp, &fo->cookie)) goto fallback; /* MSS for SYN-data is based on cached MSS and bounded by PMTU and * user-MSS. Reserve maximum option space for middleboxes that add * private TCP options. The cost is reduced data space in SYN :( */ tp->rx_opt.mss_clamp = tcp_mss_clamp(tp, tp->rx_opt.mss_clamp); /* Sync mss_cache after updating the mss_clamp */ tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); space = __tcp_mtu_to_mss(sk, icsk->icsk_pmtu_cookie) - MAX_TCP_OPTION_SPACE; space = min_t(size_t, space, fo->size); if (space && !skb_page_frag_refill(min_t(size_t, space, PAGE_SIZE), pfrag, sk->sk_allocation)) goto fallback; syn_data = tcp_stream_alloc_skb(sk, sk->sk_allocation, false); if (!syn_data) goto fallback; memcpy(syn_data->cb, syn->cb, sizeof(syn->cb)); if (space) { space = min_t(size_t, space, pfrag->size - pfrag->offset); space = tcp_wmem_schedule(sk, space); } if (space) { space = copy_page_from_iter(pfrag->page, pfrag->offset, space, &fo->data->msg_iter); if (unlikely(!space)) { tcp_skb_tsorted_anchor_cleanup(syn_data); kfree_skb(syn_data); goto fallback; } skb_fill_page_desc(syn_data, 0, pfrag->page, pfrag->offset, space); page_ref_inc(pfrag->page); pfrag->offset += space; skb_len_add(syn_data, space); skb_zcopy_set(syn_data, fo->uarg, NULL); } /* No more data pending in inet_wait_for_connect() */ if (space == fo->size) fo->data = NULL; fo->copied = space; tcp_connect_queue_skb(sk, syn_data); if (syn_data->len) tcp_chrono_start(sk, TCP_CHRONO_BUSY); err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation); skb_set_delivery_time(syn, syn_data->skb_mstamp_ns, SKB_CLOCK_MONOTONIC); /* Now full SYN+DATA was cloned and sent (or not), * remove the SYN from the original skb (syn_data) * we keep in write queue in case of a retransmit, as we * also have the SYN packet (with no data) in the same queue. */ TCP_SKB_CB(syn_data)->seq++; TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH; if (!err) { tp->syn_data = (fo->copied > 0); tcp_rbtree_insert(&sk->tcp_rtx_queue, syn_data); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT); goto done; } /* data was not sent, put it in write_queue */ __skb_queue_tail(&sk->sk_write_queue, syn_data); tp->packets_out -= tcp_skb_pcount(syn_data); fallback: /* Send a regular SYN with Fast Open cookie request option */ if (fo->cookie.len > 0) fo->cookie.len = 0; err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation); if (err) tp->syn_fastopen = 0; done: fo->cookie.len = -1; /* Exclude Fast Open option for SYN retries */ return err; } /* Build a SYN and send it off. */ int tcp_connect(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; int err; tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB, 0, NULL); #if defined(CONFIG_TCP_MD5SIG) && defined(CONFIG_TCP_AO) /* Has to be checked late, after setting daddr/saddr/ops. * Return error if the peer has both a md5 and a tcp-ao key * configured as this is ambiguous. */ if (unlikely(rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)))) { bool needs_ao = !!tp->af_specific->ao_lookup(sk, sk, -1, -1); bool needs_md5 = !!tp->af_specific->md5_lookup(sk, sk); struct tcp_ao_info *ao_info; ao_info = rcu_dereference_check(tp->ao_info, lockdep_sock_is_held(sk)); if (ao_info) { /* This is an extra check: tcp_ao_required() in * tcp_v{4,6}_parse_md5_keys() should prevent adding * md5 keys on ao_required socket. */ needs_ao |= ao_info->ao_required; WARN_ON_ONCE(ao_info->ao_required && needs_md5); } if (needs_md5 && needs_ao) return -EKEYREJECTED; /* If we have a matching md5 key and no matching tcp-ao key * then free up ao_info if allocated. */ if (needs_md5) { tcp_ao_destroy_sock(sk, false); } else if (needs_ao) { tcp_clear_md5_list(sk); kfree(rcu_replace_pointer(tp->md5sig_info, NULL, lockdep_sock_is_held(sk))); } } #endif #ifdef CONFIG_TCP_AO if (unlikely(rcu_dereference_protected(tp->ao_info, lockdep_sock_is_held(sk)))) { /* Don't allow connecting if ao is configured but no * matching key is found. */ if (!tp->af_specific->ao_lookup(sk, sk, -1, -1)) return -EKEYREJECTED; } #endif if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) return -EHOSTUNREACH; /* Routing failure or similar. */ tcp_connect_init(sk); if (unlikely(tp->repair)) { tcp_finish_connect(sk, NULL); return 0; } buff = tcp_stream_alloc_skb(sk, sk->sk_allocation, true); if (unlikely(!buff)) return -ENOBUFS; /* SYN eats a sequence byte, write_seq updated by * tcp_connect_queue_skb(). */ tcp_init_nondata_skb(buff, tp->write_seq, TCPHDR_SYN); tcp_mstamp_refresh(tp); tp->retrans_stamp = tcp_time_stamp_ts(tp); tcp_connect_queue_skb(sk, buff); tcp_ecn_send_syn(sk, buff); tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); /* Send off SYN; include data in Fast Open. */ err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) : tcp_transmit_skb(sk, buff, 1, sk->sk_allocation); if (err == -ECONNREFUSED) return err; /* We change tp->snd_nxt after the tcp_transmit_skb() call * in order to make this packet get counted in tcpOutSegs. */ WRITE_ONCE(tp->snd_nxt, tp->write_seq); tp->pushed_seq = tp->write_seq; buff = tcp_send_head(sk); if (unlikely(buff)) { WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(buff)->seq); tp->pushed_seq = TCP_SKB_CB(buff)->seq; } TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS); /* Timer for repeating the SYN until an answer. */ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, TCP_RTO_MAX); return 0; } EXPORT_SYMBOL(tcp_connect); u32 tcp_delack_max(const struct sock *sk) { u32 delack_from_rto_min = max(tcp_rto_min(sk), 2) - 1; return min(inet_csk(sk)->icsk_delack_max, delack_from_rto_min); } /* Send out a delayed ack, the caller does the policy checking * to see if we should even be here. See tcp_input.c:tcp_ack_snd_check() * for details. */ void tcp_send_delayed_ack(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); int ato = icsk->icsk_ack.ato; unsigned long timeout; if (ato > TCP_DELACK_MIN) { const struct tcp_sock *tp = tcp_sk(sk); int max_ato = HZ / 2; if (inet_csk_in_pingpong_mode(sk) || (icsk->icsk_ack.pending & ICSK_ACK_PUSHED)) max_ato = TCP_DELACK_MAX; /* Slow path, intersegment interval is "high". */ /* If some rtt estimate is known, use it to bound delayed ack. * Do not use inet_csk(sk)->icsk_rto here, use results of rtt measurements * directly. */ if (tp->srtt_us) { int rtt = max_t(int, usecs_to_jiffies(tp->srtt_us >> 3), TCP_DELACK_MIN); if (rtt < max_ato) max_ato = rtt; } ato = min(ato, max_ato); } ato = min_t(u32, ato, tcp_delack_max(sk)); /* Stay within the limit we were given */ timeout = jiffies + ato; /* Use new timeout only if there wasn't a older one earlier. */ if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) { /* If delack timer is about to expire, send ACK now. */ if (time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) { tcp_send_ack(sk); return; } if (!time_before(timeout, icsk->icsk_ack.timeout)) timeout = icsk->icsk_ack.timeout; } smp_store_release(&icsk->icsk_ack.pending, icsk->icsk_ack.pending | ICSK_ACK_SCHED | ICSK_ACK_TIMER); icsk->icsk_ack.timeout = timeout; sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout); } /* This routine sends an ack and also updates the window. */ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) { struct sk_buff *buff; /* If we have been reset, we may not send again. */ if (sk->sk_state == TCP_CLOSE) return; /* We are not putting this on the write queue, so * tcp_transmit_skb() will set the ownership to this * sock. */ buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN)); if (unlikely(!buff)) { struct inet_connection_sock *icsk = inet_csk(sk); unsigned long delay; delay = TCP_DELACK_MAX << icsk->icsk_ack.retry; if (delay < TCP_RTO_MAX) icsk->icsk_ack.retry++; inet_csk_schedule_ack(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, delay, TCP_RTO_MAX); return; } /* Reserve space for headers and prepare control bits. */ skb_reserve(buff, MAX_TCP_HEADER); tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK); /* We do not want pure acks influencing TCP Small Queues or fq/pacing * too much. * SKB_TRUESIZE(max(1 .. 66, MAX_TCP_HEADER)) is unfortunately ~784 */ skb_set_tcp_pure_ack(buff); /* Send it off, this clears delayed acks for us. */ __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt); } EXPORT_SYMBOL_GPL(__tcp_send_ack); void tcp_send_ack(struct sock *sk) { __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt); } /* This routine sends a packet with an out of date sequence * number. It assumes the other end will try to ack it. * * Question: what should we make while urgent mode? * 4.4BSD forces sending single byte of data. We cannot send * out of window data, because we have SND.NXT==SND.MAX... * * Current solution: to send TWO zero-length segments in urgent mode: * one is with SEG.SEQ=SND.UNA to deliver urgent pointer, another is * out-of-date with SND.UNA-1 to probe window. */ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; /* We don't queue it, tcp_transmit_skb() sets ownership. */ skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN)); if (!skb) return -1; /* Reserve space for headers and set control bits. */ skb_reserve(skb, MAX_TCP_HEADER); /* Use a previous sequence. This should cause the other * end to send an ack. Don't queue or clone SKB, just * send it. */ tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK); NET_INC_STATS(sock_net(sk), mib); return tcp_transmit_skb(sk, skb, 0, (__force gfp_t)0); } /* Called from setsockopt( ... TCP_REPAIR ) */ void tcp_send_window_probe(struct sock *sk) { if (sk->sk_state == TCP_ESTABLISHED) { tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1; tcp_mstamp_refresh(tcp_sk(sk)); tcp_xmit_probe_skb(sk, 0, LINUX_MIB_TCPWINPROBE); } } /* Initiate keepalive or window probe from timer. */ int tcp_write_wakeup(struct sock *sk, int mib) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; if (sk->sk_state == TCP_CLOSE) return -1; skb = tcp_send_head(sk); if (skb && before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) { int err; unsigned int mss = tcp_current_mss(sk); unsigned int seg_size = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; if (before(tp->pushed_seq, TCP_SKB_CB(skb)->end_seq)) tp->pushed_seq = TCP_SKB_CB(skb)->end_seq; /* We are probing the opening of a window * but the window size is != 0 * must have been a result SWS avoidance ( sender ) */ if (seg_size < TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq || skb->len > mss) { seg_size = min(seg_size, mss); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; if (tcp_fragment(sk, TCP_FRAG_IN_WRITE_QUEUE, skb, seg_size, mss, GFP_ATOMIC)) return -1; } else if (!tcp_skb_pcount(skb)) tcp_set_skb_tso_segs(skb, mss); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); if (!err) tcp_event_new_data_sent(sk, skb); return err; } else { if (between(tp->snd_up, tp->snd_una + 1, tp->snd_una + 0xFFFF)) tcp_xmit_probe_skb(sk, 1, mib); return tcp_xmit_probe_skb(sk, 0, mib); } } /* A window probe timeout has occurred. If window is not closed send * a partial packet else a zero probe. */ void tcp_send_probe0(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); unsigned long timeout; int err; err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE); if (tp->packets_out || tcp_write_queue_empty(sk)) { /* Cancel probe timer, if it is not required. */ icsk->icsk_probes_out = 0; icsk->icsk_backoff = 0; icsk->icsk_probes_tstamp = 0; return; } icsk->icsk_probes_out++; if (err <= 0) { if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2)) icsk->icsk_backoff++; timeout = tcp_probe0_when(sk, TCP_RTO_MAX); } else { /* If packet was not sent due to local congestion, * Let senders fight for local resources conservatively. */ timeout = TCP_RESOURCE_PROBE_INTERVAL; } timeout = tcp_clamp_probe0_to_user_timeout(sk, timeout); tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX); } int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) { const struct tcp_request_sock_ops *af_ops = tcp_rsk(req)->af_specific; struct flowi fl; int res; /* Paired with WRITE_ONCE() in sock_setsockopt() */ if (READ_ONCE(sk->sk_txrehash) == SOCK_TXREHASH_ENABLED) WRITE_ONCE(tcp_rsk(req)->txhash, net_tx_rndhash()); res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, NULL); if (!res) { TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); if (unlikely(tcp_passive_fastopen(sk))) { /* sk has const attribute because listeners are lockless. * However in this case, we are dealing with a passive fastopen * socket thus we can change total_retrans value. */ tcp_sk_rw(sk)->total_retrans++; } trace_tcp_retransmit_synack(sk, req); } return res; } EXPORT_SYMBOL(tcp_rtx_synack); |
| 57 151 150 1 97 97 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. * Authors: David Chinner and Glauber Costa * * Generic LRU infrastructure */ #ifndef _LRU_LIST_H #define _LRU_LIST_H #include <linux/list.h> #include <linux/nodemask.h> #include <linux/shrinker.h> #include <linux/xarray.h> struct mem_cgroup; /* list_lru_walk_cb has to always return one of those */ enum lru_status { LRU_REMOVED, /* item removed from list */ LRU_REMOVED_RETRY, /* item removed, but lock has been dropped and reacquired */ LRU_ROTATE, /* item referenced, give another pass */ LRU_SKIP, /* item cannot be locked, skip */ LRU_RETRY, /* item not freeable. May drop the lock internally, but has to return locked. */ LRU_STOP, /* stop lru list walking. May drop the lock internally, but has to return locked. */ }; struct list_lru_one { struct list_head list; /* may become negative during memcg reparenting */ long nr_items; /* protects all fields above */ spinlock_t lock; }; struct list_lru_memcg { struct rcu_head rcu; /* array of per cgroup per node lists, indexed by node id */ struct list_lru_one node[]; }; struct list_lru_node { /* global list, used for the root cgroup in cgroup aware lrus */ struct list_lru_one lru; atomic_long_t nr_items; } ____cacheline_aligned_in_smp; struct list_lru { struct list_lru_node *node; #ifdef CONFIG_MEMCG struct list_head list; int shrinker_id; bool memcg_aware; struct xarray xa; #endif #ifdef CONFIG_LOCKDEP struct lock_class_key *key; #endif }; void list_lru_destroy(struct list_lru *lru); int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct shrinker *shrinker); #define list_lru_init(lru) \ __list_lru_init((lru), false, NULL) #define list_lru_init_memcg(lru, shrinker) \ __list_lru_init((lru), true, shrinker) static inline int list_lru_init_memcg_key(struct list_lru *lru, struct shrinker *shrinker, struct lock_class_key *key) { #ifdef CONFIG_LOCKDEP lru->key = key; #endif return list_lru_init_memcg(lru, shrinker); } int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp); void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent); /** * list_lru_add: add an element to the lru list's tail * @lru: the lru pointer * @item: the item to be added. * @nid: the node id of the sublist to add the item to. * @memcg: the cgroup of the sublist to add the item to. * * If the element is already part of a list, this function returns doing * nothing. Therefore the caller does not need to keep state about whether or * not the element already belongs in the list and is allowed to lazy update * it. Note however that this is valid for *a* list, not *this* list. If * the caller organize itself in a way that elements can be in more than * one type of list, it is up to the caller to fully remove the item from * the previous list (with list_lru_del() for instance) before moving it * to @lru. * * Return: true if the list was updated, false otherwise */ bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg); /** * list_lru_add_obj: add an element to the lru list's tail * @lru: the lru pointer * @item: the item to be added. * * This function is similar to list_lru_add(), but the NUMA node and the * memcg of the sublist is determined by @item list_head. This assumption is * valid for slab objects LRU such as dentries, inodes, etc. * * Return value: true if the list was updated, false otherwise */ bool list_lru_add_obj(struct list_lru *lru, struct list_head *item); /** * list_lru_del: delete an element from the lru list * @lru: the lru pointer * @item: the item to be deleted. * @nid: the node id of the sublist to delete the item from. * @memcg: the cgroup of the sublist to delete the item from. * * This function works analogously as list_lru_add() in terms of list * manipulation. The comments about an element already pertaining to * a list are also valid for list_lru_del(). * * Return: true if the list was updated, false otherwise */ bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg); /** * list_lru_del_obj: delete an element from the lru list * @lru: the lru pointer * @item: the item to be deleted. * * This function is similar to list_lru_del(), but the NUMA node and the * memcg of the sublist is determined by @item list_head. This assumption is * valid for slab objects LRU such as dentries, inodes, etc. * * Return value: true if the list was updated, false otherwise. */ bool list_lru_del_obj(struct list_lru *lru, struct list_head *item); /** * list_lru_count_one: return the number of objects currently held by @lru * @lru: the lru pointer. * @nid: the node id to count from. * @memcg: the cgroup to count from. * * There is no guarantee that the list is not updated while the count is being * computed. Callers that want such a guarantee need to provide an outer lock. * * Return: 0 for empty lists, otherwise the number of objects * currently held by @lru. */ unsigned long list_lru_count_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg); unsigned long list_lru_count_node(struct list_lru *lru, int nid); static inline unsigned long list_lru_shrink_count(struct list_lru *lru, struct shrink_control *sc) { return list_lru_count_one(lru, sc->nid, sc->memcg); } static inline unsigned long list_lru_count(struct list_lru *lru) { long count = 0; int nid; for_each_node_state(nid, N_NORMAL_MEMORY) count += list_lru_count_node(lru, nid); return count; } void list_lru_isolate(struct list_lru_one *list, struct list_head *item); void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head); typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item, struct list_lru_one *list, void *cb_arg); /** * list_lru_walk_one: walk a @lru, isolating and disposing freeable items. * @lru: the lru pointer. * @nid: the node id to scan from. * @memcg: the cgroup to scan from. * @isolate: callback function that is responsible for deciding what to do with * the item currently being scanned * @cb_arg: opaque type that will be passed to @isolate * @nr_to_walk: how many items to scan. * * This function will scan all elements in a particular @lru, calling the * @isolate callback for each of those items, along with the current list * spinlock and a caller-provided opaque. The @isolate callback can choose to * drop the lock internally, but *must* return with the lock held. The callback * will return an enum lru_status telling the @lru infrastructure what to * do with the object being scanned. * * Please note that @nr_to_walk does not mean how many objects will be freed, * just how many objects will be scanned. * * Return: the number of objects effectively removed from the LRU. */ unsigned long list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk); /** * list_lru_walk_one_irq: walk a @lru, isolating and disposing freeable items. * @lru: the lru pointer. * @nid: the node id to scan from. * @memcg: the cgroup to scan from. * @isolate: callback function that is responsible for deciding what to do with * the item currently being scanned * @cb_arg: opaque type that will be passed to @isolate * @nr_to_walk: how many items to scan. * * Same as list_lru_walk_one() except that the spinlock is acquired with * spin_lock_irq(). */ unsigned long list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk); unsigned long list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk); static inline unsigned long list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc, list_lru_walk_cb isolate, void *cb_arg) { return list_lru_walk_one(lru, sc->nid, sc->memcg, isolate, cb_arg, &sc->nr_to_scan); } static inline unsigned long list_lru_shrink_walk_irq(struct list_lru *lru, struct shrink_control *sc, list_lru_walk_cb isolate, void *cb_arg) { return list_lru_walk_one_irq(lru, sc->nid, sc->memcg, isolate, cb_arg, &sc->nr_to_scan); } static inline unsigned long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate, void *cb_arg, unsigned long nr_to_walk) { long isolated = 0; int nid; for_each_node_state(nid, N_NORMAL_MEMORY) { isolated += list_lru_walk_node(lru, nid, isolate, cb_arg, &nr_to_walk); if (nr_to_walk <= 0) break; } return isolated; } #endif /* _LRU_LIST_H */ |
| 18 5 126 4 4 4 3 4 4 4 2 2 2 64 64 64 64 13 6 6 60 70 4 78 2 67 67 67 32 32 66 6 6 6 5 6 37 37 37 21 19 4 4 3 3 3 3 3 21 37 16 17 17 1 1 17 16 47 16 47 5 2 2 2 2 2 2 2 1 3 3 3 3 2 2 2 1 1 1 1 1 1 5 5 5 5 5 8 9 9 8 8 7 7 2 4 4 4 4 4 4 4 4 4 3 3 4 3 4 4 4 43 43 25 4 4 4 17 22 2 41 41 41 41 26 22 15 37 43 41 43 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 7 7 1 6 5 1 1 1 4 5 3 2 2 2 1 5 7 15 1 1 1 7 5 2 17 17 1 16 15 1 16 16 16 16 9 7 7 7 7 5 5 5 2 7 7 17 5 12 17 3 3 13 10 3 2 2 1 3 3 7 3 2 3 2 1 4 4 4 3 1 3 7 6 10 45 45 45 45 45 45 44 36 35 35 5 28 34 1 45 1 44 10 34 38 38 28 33 33 33 33 33 29 5 13 45 9 9 9 9 9 7 7 7 7 6 19 6 19 2 28 28 43 43 42 43 43 43 43 78 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* L2TP core. * * Copyright (c) 2008,2009,2010 Katalix Systems Ltd * * This file contains some code of the original L2TPv2 pppol2tp * driver, which has the following copyright: * * Authors: Martijn van Oosterhout <kleptog@svana.org> * James Chapman (jchapman@katalix.com) * Contributors: * Michal Ostrowski <mostrows@speakeasy.net> * Arnaldo Carvalho de Melo <acme@xconectiva.com.br> * David S. Miller (davem@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/string.h> #include <linux/list.h> #include <linux/rculist.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/spinlock.h> #include <linux/kthread.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/jiffies.h> #include <linux/netdevice.h> #include <linux/net.h> #include <linux/inetdevice.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/udp.h> #include <linux/l2tp.h> #include <linux/sort.h> #include <linux/file.h> #include <linux/nsproxy.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/dst.h> #include <net/ip.h> #include <net/udp.h> #include <net/udp_tunnel.h> #include <net/inet_common.h> #include <net/xfrm.h> #include <net/protocol.h> #include <net/inet6_connection_sock.h> #include <net/inet_ecn.h> #include <net/ip6_route.h> #include <net/ip6_checksum.h> #include <asm/byteorder.h> #include <linux/atomic.h> #include "l2tp_core.h" #define CREATE_TRACE_POINTS #include "trace.h" #define L2TP_DRV_VERSION "V2.0" /* L2TP header constants */ #define L2TP_HDRFLAG_T 0x8000 #define L2TP_HDRFLAG_L 0x4000 #define L2TP_HDRFLAG_S 0x0800 #define L2TP_HDRFLAG_O 0x0200 #define L2TP_HDRFLAG_P 0x0100 #define L2TP_HDR_VER_MASK 0x000F #define L2TP_HDR_VER_2 0x0002 #define L2TP_HDR_VER_3 0x0003 /* L2TPv3 default L2-specific sublayer */ #define L2TP_SLFLAG_S 0x40000000 #define L2TP_SL_SEQ_MASK 0x00ffffff #define L2TP_HDR_SIZE_MAX 14 /* Default trace flags */ #define L2TP_DEFAULT_DEBUG_FLAGS 0 #define L2TP_DEPTH_NESTING 2 #if L2TP_DEPTH_NESTING == SINGLE_DEPTH_NESTING #error "L2TP requires its own lockdep subclass" #endif /* Private data stored for received packets in the skb. */ struct l2tp_skb_cb { u32 ns; u16 has_seq; u16 length; unsigned long expires; }; #define L2TP_SKB_CB(skb) ((struct l2tp_skb_cb *)&(skb)->cb[sizeof(struct inet_skb_parm)]) static struct workqueue_struct *l2tp_wq; /* per-net private data for this module */ static unsigned int l2tp_net_id; struct l2tp_net { /* Lock for write access to l2tp_tunnel_idr */ spinlock_t l2tp_tunnel_idr_lock; struct idr l2tp_tunnel_idr; /* Lock for write access to l2tp_v[23]_session_idr/htable */ spinlock_t l2tp_session_idr_lock; struct idr l2tp_v2_session_idr; struct idr l2tp_v3_session_idr; struct hlist_head l2tp_v3_session_htable[16]; }; static u32 l2tp_v2_session_key(u16 tunnel_id, u16 session_id) { return ((u32)tunnel_id) << 16 | session_id; } static unsigned long l2tp_v3_session_hashkey(struct sock *sk, u32 session_id) { return ((unsigned long)sk) + session_id; } #if IS_ENABLED(CONFIG_IPV6) static bool l2tp_sk_is_v6(struct sock *sk) { return sk->sk_family == PF_INET6 && !ipv6_addr_v4mapped(&sk->sk_v6_daddr); } #endif static struct l2tp_net *l2tp_pernet(const struct net *net) { return net_generic(net, l2tp_net_id); } static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { struct sock *sk = tunnel->sock; trace_free_tunnel(tunnel); if (sk) { /* Disable udp encapsulation */ switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: /* No longer an encapsulation socket. See net/ipv4/udp.c */ WRITE_ONCE(udp_sk(sk)->encap_type, 0); udp_sk(sk)->encap_rcv = NULL; udp_sk(sk)->encap_destroy = NULL; break; case L2TP_ENCAPTYPE_IP: break; } tunnel->sock = NULL; sock_put(sk); } kfree_rcu(tunnel, rcu); } static void l2tp_session_free(struct l2tp_session *session) { trace_free_session(session); if (session->tunnel) l2tp_tunnel_put(session->tunnel); kfree_rcu(session, rcu); } struct l2tp_tunnel *l2tp_sk_to_tunnel(const struct sock *sk) { const struct net *net = sock_net(sk); unsigned long tunnel_id, tmp; struct l2tp_tunnel *tunnel; struct l2tp_net *pn; rcu_read_lock_bh(); pn = l2tp_pernet(net); idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { if (tunnel && tunnel->sock == sk && refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; } } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_sk_to_tunnel); void l2tp_tunnel_put(struct l2tp_tunnel *tunnel) { if (refcount_dec_and_test(&tunnel->ref_count)) l2tp_tunnel_free(tunnel); } EXPORT_SYMBOL_GPL(l2tp_tunnel_put); void l2tp_session_put(struct l2tp_session *session) { if (refcount_dec_and_test(&session->ref_count)) l2tp_session_free(session); } EXPORT_SYMBOL_GPL(l2tp_session_put); /* Lookup a tunnel. A new reference is held on the returned tunnel. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) { const struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel; rcu_read_lock_bh(); tunnel = idr_find(&pn->l2tp_tunnel_idr, tunnel_id); if (tunnel && refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_tunnel_get); struct l2tp_tunnel *l2tp_tunnel_get_next(const struct net *net, unsigned long *key) { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel = NULL; rcu_read_lock_bh(); again: tunnel = idr_get_next_ul(&pn->l2tp_tunnel_idr, key); if (tunnel) { if (refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; } (*key)++; goto again; } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_tunnel_get_next); struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id) { const struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_session *session; rcu_read_lock_bh(); session = idr_find(&pn->l2tp_v3_session_idr, session_id); if (session && !hash_hashed(&session->hlist) && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } /* If we get here and session is non-NULL, the session_id * collides with one in another tunnel. If sk is non-NULL, * find the session matching sk. */ if (session && sk) { unsigned long key = l2tp_v3_session_hashkey(sk, session->session_id); hash_for_each_possible_rcu(pn->l2tp_v3_session_htable, session, hlist, key) { /* session->tunnel may be NULL if another thread is in * l2tp_session_register and has added an item to * l2tp_v3_session_htable but hasn't yet added the * session to its tunnel's session_list. */ struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); if (session->session_id == session_id && tunnel && tunnel->sock == sk && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } } } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_v3_session_get); struct l2tp_session *l2tp_v2_session_get(const struct net *net, u16 tunnel_id, u16 session_id) { u32 session_key = l2tp_v2_session_key(tunnel_id, session_id); const struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_session *session; rcu_read_lock_bh(); session = idr_find(&pn->l2tp_v2_session_idr, session_key); if (session && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_v2_session_get); struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, int pver, u32 tunnel_id, u32 session_id) { if (pver == L2TP_HDR_VER_2) return l2tp_v2_session_get(net, tunnel_id, session_id); else return l2tp_v3_session_get(net, sk, session_id); } EXPORT_SYMBOL_GPL(l2tp_session_get); static struct l2tp_session *l2tp_v2_session_get_next(const struct net *net, u16 tid, unsigned long *key) { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_session *session = NULL; /* Start searching within the range of the tid */ if (*key == 0) *key = l2tp_v2_session_key(tid, 0); rcu_read_lock_bh(); again: session = idr_get_next_ul(&pn->l2tp_v2_session_idr, key); if (session) { struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); /* ignore sessions with id 0 as they are internal for pppol2tp */ if (session->session_id == 0) { (*key)++; goto again; } if (tunnel->tunnel_id == tid && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } (*key)++; if (tunnel->tunnel_id == tid) goto again; } rcu_read_unlock_bh(); return NULL; } static struct l2tp_session *l2tp_v3_session_get_next(const struct net *net, u32 tid, struct sock *sk, unsigned long *key) { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_session *session = NULL; rcu_read_lock_bh(); again: session = idr_get_next_ul(&pn->l2tp_v3_session_idr, key); if (session && !hash_hashed(&session->hlist)) { struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); if (tunnel && tunnel->tunnel_id == tid && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } (*key)++; goto again; } /* If we get here and session is non-NULL, the IDR entry may be one * where the session_id collides with one in another tunnel. Check * session_htable for a match. There can only be one session of a given * ID per tunnel so we can return as soon as a match is found. */ if (session && hash_hashed(&session->hlist)) { unsigned long hkey = l2tp_v3_session_hashkey(sk, session->session_id); u32 sid = session->session_id; hash_for_each_possible_rcu(pn->l2tp_v3_session_htable, session, hlist, hkey) { struct l2tp_tunnel *tunnel = READ_ONCE(session->tunnel); if (session->session_id == sid && tunnel && tunnel->tunnel_id == tid && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } } /* If no match found, the colliding session ID isn't in our * tunnel so try the next session ID. */ (*key)++; goto again; } rcu_read_unlock_bh(); return NULL; } struct l2tp_session *l2tp_session_get_next(const struct net *net, struct sock *sk, int pver, u32 tunnel_id, unsigned long *key) { if (pver == L2TP_HDR_VER_2) return l2tp_v2_session_get_next(net, tunnel_id, key); else return l2tp_v3_session_get_next(net, tunnel_id, sk, key); } EXPORT_SYMBOL_GPL(l2tp_session_get_next); /* Lookup a session by interface name. * This is very inefficient but is only used by management interfaces. */ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, const char *ifname) { struct l2tp_net *pn = l2tp_pernet(net); unsigned long tunnel_id, tmp; struct l2tp_session *session; struct l2tp_tunnel *tunnel; rcu_read_lock_bh(); idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { if (tunnel) { list_for_each_entry_rcu(session, &tunnel->session_list, list) { if (!strcmp(session->ifname, ifname)) { refcount_inc(&session->ref_count); rcu_read_unlock_bh(); return session; } } } } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname); static void l2tp_session_coll_list_add(struct l2tp_session_coll_list *clist, struct l2tp_session *session) { refcount_inc(&session->ref_count); WARN_ON_ONCE(session->coll_list); session->coll_list = clist; spin_lock(&clist->lock); list_add(&session->clist, &clist->list); spin_unlock(&clist->lock); } static int l2tp_session_collision_add(struct l2tp_net *pn, struct l2tp_session *session1, struct l2tp_session *session2) { struct l2tp_session_coll_list *clist; lockdep_assert_held(&pn->l2tp_session_idr_lock); if (!session2) return -EEXIST; /* If existing session is in IP-encap tunnel, refuse new session */ if (session2->tunnel->encap == L2TP_ENCAPTYPE_IP) return -EEXIST; clist = session2->coll_list; if (!clist) { /* First collision. Allocate list to manage the collided sessions * and add the existing session to the list. */ clist = kmalloc(sizeof(*clist), GFP_ATOMIC); if (!clist) return -ENOMEM; spin_lock_init(&clist->lock); INIT_LIST_HEAD(&clist->list); refcount_set(&clist->ref_count, 1); l2tp_session_coll_list_add(clist, session2); } /* If existing session isn't already in the session hlist, add it. */ if (!hash_hashed(&session2->hlist)) hash_add_rcu(pn->l2tp_v3_session_htable, &session2->hlist, session2->hlist_key); /* Add new session to the hlist and collision list */ hash_add_rcu(pn->l2tp_v3_session_htable, &session1->hlist, session1->hlist_key); refcount_inc(&clist->ref_count); l2tp_session_coll_list_add(clist, session1); return 0; } static void l2tp_session_collision_del(struct l2tp_net *pn, struct l2tp_session *session) { struct l2tp_session_coll_list *clist = session->coll_list; unsigned long session_key = session->session_id; struct l2tp_session *session2; lockdep_assert_held(&pn->l2tp_session_idr_lock); hash_del_rcu(&session->hlist); if (clist) { /* Remove session from its collision list. If there * are other sessions with the same ID, replace this * session's IDR entry with that session, otherwise * remove the IDR entry. If this is the last session, * the collision list data is freed. */ spin_lock(&clist->lock); list_del_init(&session->clist); session2 = list_first_entry_or_null(&clist->list, struct l2tp_session, clist); if (session2) { void *old = idr_replace(&pn->l2tp_v3_session_idr, session2, session_key); WARN_ON_ONCE(IS_ERR_VALUE(old)); } else { void *removed = idr_remove(&pn->l2tp_v3_session_idr, session_key); WARN_ON_ONCE(removed != session); } session->coll_list = NULL; spin_unlock(&clist->lock); if (refcount_dec_and_test(&clist->ref_count)) kfree(clist); l2tp_session_put(session); } } int l2tp_session_register(struct l2tp_session *session, struct l2tp_tunnel *tunnel) { struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); struct l2tp_session *other_session = NULL; void *old = NULL; u32 session_key; int err; spin_lock_bh(&tunnel->list_lock); spin_lock_bh(&pn->l2tp_session_idr_lock); if (!tunnel->acpt_newsess) { err = -ENODEV; goto out; } if (tunnel->version == L2TP_HDR_VER_3) { session_key = session->session_id; err = idr_alloc_u32(&pn->l2tp_v3_session_idr, NULL, &session_key, session_key, GFP_ATOMIC); /* IP encap expects session IDs to be globally unique, while * UDP encap doesn't. This isn't per the RFC, which says that * sessions are identified only by the session ID, but is to * support existing userspace which depends on it. */ if (err == -ENOSPC && tunnel->encap == L2TP_ENCAPTYPE_UDP) { other_session = idr_find(&pn->l2tp_v3_session_idr, session_key); err = l2tp_session_collision_add(pn, session, other_session); } } else { session_key = l2tp_v2_session_key(tunnel->tunnel_id, session->session_id); err = idr_alloc_u32(&pn->l2tp_v2_session_idr, NULL, &session_key, session_key, GFP_ATOMIC); } if (err) { if (err == -ENOSPC) err = -EEXIST; goto out; } refcount_inc(&tunnel->ref_count); WRITE_ONCE(session->tunnel, tunnel); list_add_rcu(&session->list, &tunnel->session_list); /* this makes session available to lockless getters */ if (tunnel->version == L2TP_HDR_VER_3) { if (!other_session) old = idr_replace(&pn->l2tp_v3_session_idr, session, session_key); } else { old = idr_replace(&pn->l2tp_v2_session_idr, session, session_key); } /* old should be NULL, unless something removed or modified * the IDR entry after our idr_alloc_32 above (which shouldn't * happen). */ WARN_ON_ONCE(old); out: spin_unlock_bh(&pn->l2tp_session_idr_lock); spin_unlock_bh(&tunnel->list_lock); if (!err) trace_register_session(session); return err; } EXPORT_SYMBOL_GPL(l2tp_session_register); /***************************************************************************** * Receive data handling *****************************************************************************/ /* Queue a skb in order. We come here only if the skb has an L2TP sequence * number. */ static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *skb) { struct sk_buff *skbp; struct sk_buff *tmp; u32 ns = L2TP_SKB_CB(skb)->ns; spin_lock_bh(&session->reorder_q.lock); skb_queue_walk_safe(&session->reorder_q, skbp, tmp) { if (L2TP_SKB_CB(skbp)->ns > ns) { __skb_queue_before(&session->reorder_q, skbp, skb); atomic_long_inc(&session->stats.rx_oos_packets); goto out; } } __skb_queue_tail(&session->reorder_q, skb); out: spin_unlock_bh(&session->reorder_q.lock); } /* Dequeue a single skb. */ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff *skb) { struct l2tp_tunnel *tunnel = session->tunnel; int length = L2TP_SKB_CB(skb)->length; /* We're about to requeue the skb, so return resources * to its current owner (a socket receive buffer). */ skb_orphan(skb); atomic_long_inc(&tunnel->stats.rx_packets); atomic_long_add(length, &tunnel->stats.rx_bytes); atomic_long_inc(&session->stats.rx_packets); atomic_long_add(length, &session->stats.rx_bytes); if (L2TP_SKB_CB(skb)->has_seq) { /* Bump our Nr */ session->nr++; session->nr &= session->nr_max; trace_session_seqnum_update(session); } /* call private receive handler */ if (session->recv_skb) (*session->recv_skb)(session, skb, L2TP_SKB_CB(skb)->length); else kfree_skb(skb); } /* Dequeue skbs from the session's reorder_q, subject to packet order. * Skbs that have been in the queue for too long are simply discarded. */ static void l2tp_recv_dequeue(struct l2tp_session *session) { struct sk_buff *skb; struct sk_buff *tmp; /* If the pkt at the head of the queue has the nr that we * expect to send up next, dequeue it and any other * in-sequence packets behind it. */ start: spin_lock_bh(&session->reorder_q.lock); skb_queue_walk_safe(&session->reorder_q, skb, tmp) { struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb); /* If the packet has been pending on the queue for too long, discard it */ if (time_after(jiffies, cb->expires)) { atomic_long_inc(&session->stats.rx_seq_discards); atomic_long_inc(&session->stats.rx_errors); trace_session_pkt_expired(session, cb->ns); session->reorder_skip = 1; __skb_unlink(skb, &session->reorder_q); kfree_skb(skb); continue; } if (cb->has_seq) { if (session->reorder_skip) { session->reorder_skip = 0; session->nr = cb->ns; trace_session_seqnum_reset(session); } if (cb->ns != session->nr) goto out; } __skb_unlink(skb, &session->reorder_q); /* Process the skb. We release the queue lock while we * do so to let other contexts process the queue. */ spin_unlock_bh(&session->reorder_q.lock); l2tp_recv_dequeue_skb(session, skb); goto start; } out: spin_unlock_bh(&session->reorder_q.lock); } static int l2tp_seq_check_rx_window(struct l2tp_session *session, u32 nr) { u32 nws; if (nr >= session->nr) nws = nr - session->nr; else nws = (session->nr_max + 1) - (session->nr - nr); return nws < session->nr_window_size; } /* If packet has sequence numbers, queue it if acceptable. Returns 0 if * acceptable, else non-zero. */ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb) { struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb); if (!l2tp_seq_check_rx_window(session, cb->ns)) { /* Packet sequence number is outside allowed window. * Discard it. */ trace_session_pkt_outside_rx_window(session, cb->ns); goto discard; } if (session->reorder_timeout != 0) { /* Packet reordering enabled. Add skb to session's * reorder queue, in order of ns. */ l2tp_recv_queue_skb(session, skb); goto out; } /* Packet reordering disabled. Discard out-of-sequence packets, while * tracking the number if in-sequence packets after the first OOS packet * is seen. After nr_oos_count_max in-sequence packets, reset the * sequence number to re-enable packet reception. */ if (cb->ns == session->nr) { skb_queue_tail(&session->reorder_q, skb); } else { u32 nr_oos = cb->ns; u32 nr_next = (session->nr_oos + 1) & session->nr_max; if (nr_oos == nr_next) session->nr_oos_count++; else session->nr_oos_count = 0; session->nr_oos = nr_oos; if (session->nr_oos_count > session->nr_oos_count_max) { session->reorder_skip = 1; } if (!session->reorder_skip) { atomic_long_inc(&session->stats.rx_seq_discards); trace_session_pkt_oos(session, cb->ns); goto discard; } skb_queue_tail(&session->reorder_q, skb); } out: return 0; discard: return 1; } /* Do receive processing of L2TP data frames. We handle both L2TPv2 * and L2TPv3 data frames here. * * L2TPv2 Data Message Header * * 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 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |T|L|x|x|S|x|O|P|x|x|x|x| Ver | Length (opt) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Tunnel ID | Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Ns (opt) | Nr (opt) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Offset Size (opt) | Offset pad... (opt) * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Data frames are marked by T=0. All other fields are the same as * those in L2TP control frames. * * L2TPv3 Data Message Header * * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | L2TP Session Header | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | L2-Specific Sublayer | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Tunnel Payload ... * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * 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 L2-Specific Sublayer Format * * 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 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |x|S|x|x|x|x|x|x| Sequence Number | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Cookie value and sublayer format are negotiated with the peer when * the session is set up. Unlike L2TPv2, we do not need to parse the * packet header to determine if optional fields are present. * * Caller must already have parsed the frame and determined that it is * a data (not control) frame before coming here. Fields up to the * session-id have already been parsed and ptr points to the data * after the session-id. */ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, int length) { struct l2tp_tunnel *tunnel = session->tunnel; int offset; /* Parse and check optional cookie */ if (session->peer_cookie_len > 0) { if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) { pr_debug_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n", tunnel->name, tunnel->tunnel_id, session->session_id); atomic_long_inc(&session->stats.rx_cookie_discards); goto discard; } ptr += session->peer_cookie_len; } /* Handle the optional sequence numbers. Sequence numbers are * in different places for L2TPv2 and L2TPv3. * * If we are the LAC, enable/disable sequence numbers under * the control of the LNS. If no sequence numbers present but * we were expecting them, discard frame. */ L2TP_SKB_CB(skb)->has_seq = 0; if (tunnel->version == L2TP_HDR_VER_2) { if (hdrflags & L2TP_HDRFLAG_S) { /* Store L2TP info in the skb */ L2TP_SKB_CB(skb)->ns = ntohs(*(__be16 *)ptr); L2TP_SKB_CB(skb)->has_seq = 1; ptr += 2; /* Skip past nr in the header */ ptr += 2; } } else if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) { u32 l2h = ntohl(*(__be32 *)ptr); if (l2h & 0x40000000) { /* Store L2TP info in the skb */ L2TP_SKB_CB(skb)->ns = l2h & 0x00ffffff; L2TP_SKB_CB(skb)->has_seq = 1; } ptr += 4; } if (L2TP_SKB_CB(skb)->has_seq) { /* Received a packet with sequence numbers. If we're the LAC, * check if we sre sending sequence numbers and if not, * configure it so. */ if (!session->lns_mode && !session->send_seq) { trace_session_seqnum_lns_enable(session); session->send_seq = 1; l2tp_session_set_header_len(session, tunnel->version, tunnel->encap); } } else { /* No sequence numbers. * If user has configured mandatory sequence numbers, discard. */ if (session->recv_seq) { pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } /* If we're the LAC and we're sending sequence numbers, the * LNS has requested that we no longer send sequence numbers. * If we're the LNS and we're sending sequence numbers, the * LAC is broken. Discard the frame. */ if (!session->lns_mode && session->send_seq) { trace_session_seqnum_lns_disable(session); session->send_seq = 0; l2tp_session_set_header_len(session, tunnel->version, tunnel->encap); } else if (session->send_seq) { pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } } /* Session data offset is defined only for L2TPv2 and is * indicated by an optional 16-bit value in the header. */ if (tunnel->version == L2TP_HDR_VER_2) { /* If offset bit set, skip it. */ if (hdrflags & L2TP_HDRFLAG_O) { offset = ntohs(*(__be16 *)ptr); ptr += 2 + offset; } } offset = ptr - optr; if (!pskb_may_pull(skb, offset)) goto discard; __skb_pull(skb, offset); /* Prepare skb for adding to the session's reorder_q. Hold * packets for max reorder_timeout or 1 second if not * reordering. */ L2TP_SKB_CB(skb)->length = length; L2TP_SKB_CB(skb)->expires = jiffies + (session->reorder_timeout ? session->reorder_timeout : HZ); /* Add packet to the session's receive queue. Reordering is done here, if * enabled. Saved L2TP protocol info is stored in skb->sb[]. */ if (L2TP_SKB_CB(skb)->has_seq) { if (l2tp_recv_data_seq(session, skb)) goto discard; } else { /* No sequence numbers. Add the skb to the tail of the * reorder queue. This ensures that it will be * delivered after all previous sequenced skbs. */ skb_queue_tail(&session->reorder_q, skb); } /* Try to dequeue as many skbs from reorder_q as we can. */ l2tp_recv_dequeue(session); return; discard: atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); } EXPORT_SYMBOL_GPL(l2tp_recv_common); /* Drop skbs from the session's reorder_q */ static void l2tp_session_queue_purge(struct l2tp_session *session) { struct sk_buff *skb = NULL; while ((skb = skb_dequeue(&session->reorder_q))) { atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); } } /* UDP encapsulation receive handler. See net/ipv4/udp.c for details. */ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct l2tp_session *session = NULL; struct l2tp_tunnel *tunnel = NULL; struct net *net = sock_net(sk); unsigned char *ptr, *optr; u16 hdrflags; u16 version; int length; /* UDP has verified checksum */ /* UDP always verifies the packet length. */ __skb_pull(skb, sizeof(struct udphdr)); /* Short packet? */ if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) goto pass; /* Point to L2TP header */ optr = skb->data; ptr = skb->data; /* Get L2TP header flags */ hdrflags = ntohs(*(__be16 *)ptr); /* Get protocol version */ version = hdrflags & L2TP_HDR_VER_MASK; /* Get length of L2TP packet */ length = skb->len; /* If type is control packet, it is handled by userspace. */ if (hdrflags & L2TP_HDRFLAG_T) goto pass; /* Skip flags */ ptr += 2; if (version == L2TP_HDR_VER_2) { u16 tunnel_id, session_id; /* If length is present, skip it */ if (hdrflags & L2TP_HDRFLAG_L) ptr += 2; /* Extract tunnel and session ID */ tunnel_id = ntohs(*(__be16 *)ptr); ptr += 2; session_id = ntohs(*(__be16 *)ptr); ptr += 2; session = l2tp_v2_session_get(net, tunnel_id, session_id); } else { u32 session_id; ptr += 2; /* skip reserved bits */ session_id = ntohl(*(__be32 *)ptr); ptr += 4; session = l2tp_v3_session_get(net, sk, session_id); } if (!session || !session->recv_skb) { if (session) l2tp_session_put(session); /* Not found? Pass to userspace to deal with */ goto pass; } tunnel = session->tunnel; /* Check protocol version */ if (version != tunnel->version) goto invalid; if (version == L2TP_HDR_VER_3 && l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) { l2tp_session_put(session); goto invalid; } l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_put(session); return 0; invalid: atomic_long_inc(&tunnel->stats.rx_invalid); pass: /* Put UDP header back */ __skb_push(skb, sizeof(struct udphdr)); return 1; } EXPORT_SYMBOL_GPL(l2tp_udp_encap_recv); /* UDP encapsulation receive error handler. See net/ipv4/udp.c for details. */ static void l2tp_udp_encap_err_recv(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) { sk->sk_err = err; sk_error_report(sk); if (ip_hdr(skb)->version == IPVERSION) { if (inet_test_bit(RECVERR, sk)) return ip_icmp_error(sk, skb, err, port, info, payload); #if IS_ENABLED(CONFIG_IPV6) } else { if (inet6_test_bit(RECVERR6, sk)) return ipv6_icmp_error(sk, skb, err, port, info, payload); #endif } } /************************************************************************ * Transmit handling ***********************************************************************/ /* Build an L2TP header for the session into the buffer provided. */ static int l2tp_build_l2tpv2_header(struct l2tp_session *session, void *buf) { struct l2tp_tunnel *tunnel = session->tunnel; __be16 *bufp = buf; __be16 *optr = buf; u16 flags = L2TP_HDR_VER_2; u32 tunnel_id = tunnel->peer_tunnel_id; u32 session_id = session->peer_session_id; if (session->send_seq) flags |= L2TP_HDRFLAG_S; /* Setup L2TP header. */ *bufp++ = htons(flags); *bufp++ = htons(tunnel_id); *bufp++ = htons(session_id); if (session->send_seq) { *bufp++ = htons(session->ns); *bufp++ = 0; session->ns++; session->ns &= 0xffff; trace_session_seqnum_update(session); } return bufp - optr; } static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf) { struct l2tp_tunnel *tunnel = session->tunnel; char *bufp = buf; char *optr = bufp; /* Setup L2TP header. The header differs slightly for UDP and * IP encapsulations. For UDP, there is 4 bytes of flags. */ if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { u16 flags = L2TP_HDR_VER_3; *((__be16 *)bufp) = htons(flags); bufp += 2; *((__be16 *)bufp) = 0; bufp += 2; } *((__be32 *)bufp) = htonl(session->peer_session_id); bufp += 4; if (session->cookie_len) { memcpy(bufp, &session->cookie[0], session->cookie_len); bufp += session->cookie_len; } if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) { u32 l2h = 0; if (session->send_seq) { l2h = 0x40000000 | session->ns; session->ns++; session->ns &= 0xffffff; trace_session_seqnum_update(session); } *((__be32 *)bufp) = htonl(l2h); bufp += 4; } return bufp - optr; } /* Queue the packet to IP for output: tunnel socket lock must be held */ static int l2tp_xmit_queue(struct l2tp_tunnel *tunnel, struct sk_buff *skb, struct flowi *fl) { int err; skb->ignore_df = 1; skb_dst_drop(skb); #if IS_ENABLED(CONFIG_IPV6) if (l2tp_sk_is_v6(tunnel->sock)) err = inet6_csk_xmit(tunnel->sock, skb, NULL); else #endif err = ip_queue_xmit(tunnel->sock, skb, fl); return err >= 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; } static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, unsigned int *len) { struct l2tp_tunnel *tunnel = session->tunnel; unsigned int data_len = skb->len; struct sock *sk = tunnel->sock; int headroom, uhlen, udp_len; int ret = NET_XMIT_SUCCESS; struct inet_sock *inet; struct udphdr *uh; /* Check that there's enough headroom in the skb to insert IP, * UDP and L2TP headers. If not enough, expand it to * make room. Adjust truesize. */ uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(*uh) : 0; headroom = NET_SKB_PAD + sizeof(struct iphdr) + uhlen + session->hdr_len; if (skb_cow_head(skb, headroom)) { kfree_skb(skb); return NET_XMIT_DROP; } /* Setup L2TP header */ if (tunnel->version == L2TP_HDR_VER_2) l2tp_build_l2tpv2_header(session, __skb_push(skb, session->hdr_len)); else l2tp_build_l2tpv3_header(session, __skb_push(skb, session->hdr_len)); /* Reset skb netfilter state */ memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); nf_reset_ct(skb); /* L2TP uses its own lockdep subclass to avoid lockdep splats caused by * nested socket calls on the same lockdep socket class. This can * happen when data from a user socket is routed over l2tp, which uses * another userspace socket. */ spin_lock_nested(&sk->sk_lock.slock, L2TP_DEPTH_NESTING); if (sock_owned_by_user(sk)) { kfree_skb(skb); ret = NET_XMIT_DROP; goto out_unlock; } /* The user-space may change the connection status for the user-space * provided socket at run time: we must check it under the socket lock */ if (tunnel->fd >= 0 && sk->sk_state != TCP_ESTABLISHED) { kfree_skb(skb); ret = NET_XMIT_DROP; goto out_unlock; } /* Report transmitted length before we add encap header, which keeps * statistics consistent for both UDP and IP encap tx/rx paths. */ *len = skb->len; inet = inet_sk(sk); switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: /* Setup UDP header */ __skb_push(skb, sizeof(*uh)); skb_reset_transport_header(skb); uh = udp_hdr(skb); uh->source = inet->inet_sport; uh->dest = inet->inet_dport; udp_len = uhlen + session->hdr_len + data_len; uh->len = htons(udp_len); /* Calculate UDP checksum if configured to do so */ #if IS_ENABLED(CONFIG_IPV6) if (l2tp_sk_is_v6(sk)) udp6_set_csum(udp_get_no_check6_tx(sk), skb, &inet6_sk(sk)->saddr, &sk->sk_v6_daddr, udp_len); else #endif udp_set_csum(sk->sk_no_check_tx, skb, inet->inet_saddr, inet->inet_daddr, udp_len); break; case L2TP_ENCAPTYPE_IP: break; } ret = l2tp_xmit_queue(tunnel, skb, &inet->cork.fl); out_unlock: spin_unlock(&sk->sk_lock.slock); return ret; } /* If caller requires the skb to have a ppp header, the header must be * inserted in the skb data before calling this function. */ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb) { unsigned int len = 0; int ret; ret = l2tp_xmit_core(session, skb, &len); if (ret == NET_XMIT_SUCCESS) { atomic_long_inc(&session->tunnel->stats.tx_packets); atomic_long_add(len, &session->tunnel->stats.tx_bytes); atomic_long_inc(&session->stats.tx_packets); atomic_long_add(len, &session->stats.tx_bytes); } else { atomic_long_inc(&session->tunnel->stats.tx_errors); atomic_long_inc(&session->stats.tx_errors); } return ret; } EXPORT_SYMBOL_GPL(l2tp_xmit_skb); /***************************************************************************** * Tinnel and session create/destroy. *****************************************************************************/ /* Remove an l2tp session from l2tp_core's lists. */ static void l2tp_session_unhash(struct l2tp_session *session) { struct l2tp_tunnel *tunnel = session->tunnel; if (tunnel) { struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); struct l2tp_session *removed = session; spin_lock_bh(&tunnel->list_lock); spin_lock_bh(&pn->l2tp_session_idr_lock); /* Remove from the per-tunnel list */ list_del_init(&session->list); /* Remove from per-net IDR */ if (tunnel->version == L2TP_HDR_VER_3) { if (hash_hashed(&session->hlist)) l2tp_session_collision_del(pn, session); else removed = idr_remove(&pn->l2tp_v3_session_idr, session->session_id); } else { u32 session_key = l2tp_v2_session_key(tunnel->tunnel_id, session->session_id); removed = idr_remove(&pn->l2tp_v2_session_idr, session_key); } WARN_ON_ONCE(removed && removed != session); spin_unlock_bh(&pn->l2tp_session_idr_lock); spin_unlock_bh(&tunnel->list_lock); } } /* When the tunnel is closed, all the attached sessions need to go too. */ static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) { struct l2tp_session *session; spin_lock_bh(&tunnel->list_lock); tunnel->acpt_newsess = false; list_for_each_entry(session, &tunnel->session_list, list) l2tp_session_delete(session); spin_unlock_bh(&tunnel->list_lock); } /* Tunnel socket destroy hook for UDP encapsulation */ static void l2tp_udp_encap_destroy(struct sock *sk) { struct l2tp_tunnel *tunnel; tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) { l2tp_tunnel_delete(tunnel); l2tp_tunnel_put(tunnel); } } static void l2tp_tunnel_remove(struct net *net, struct l2tp_tunnel *tunnel) { struct l2tp_net *pn = l2tp_pernet(net); spin_lock_bh(&pn->l2tp_tunnel_idr_lock); idr_remove(&pn->l2tp_tunnel_idr, tunnel->tunnel_id); spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); } /* Workqueue tunnel deletion function */ static void l2tp_tunnel_del_work(struct work_struct *work) { struct l2tp_tunnel *tunnel = container_of(work, struct l2tp_tunnel, del_work); struct sock *sk = tunnel->sock; struct socket *sock = sk->sk_socket; l2tp_tunnel_closeall(tunnel); /* If the tunnel socket was created within the kernel, use * the sk API to release it here. */ if (tunnel->fd < 0) { if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } } l2tp_tunnel_remove(tunnel->l2tp_net, tunnel); /* drop initial ref */ l2tp_tunnel_put(tunnel); /* drop workqueue ref */ l2tp_tunnel_put(tunnel); } /* Create a socket for the tunnel, if one isn't set up by * userspace. This is used for static tunnels where there is no * managing L2TP daemon. * * Since we don't want these sockets to keep a namespace alive by * themselves, we drop the socket's namespace refcount after creation. * These sockets are freed when the namespace exits using the pernet * exit hook. */ static int l2tp_tunnel_sock_create(struct net *net, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct socket **sockp) { int err = -EINVAL; struct socket *sock = NULL; struct udp_port_cfg udp_conf; switch (cfg->encap) { case L2TP_ENCAPTYPE_UDP: memset(&udp_conf, 0, sizeof(udp_conf)); #if IS_ENABLED(CONFIG_IPV6) if (cfg->local_ip6 && cfg->peer_ip6) { udp_conf.family = AF_INET6; memcpy(&udp_conf.local_ip6, cfg->local_ip6, sizeof(udp_conf.local_ip6)); memcpy(&udp_conf.peer_ip6, cfg->peer_ip6, sizeof(udp_conf.peer_ip6)); udp_conf.use_udp6_tx_checksums = !cfg->udp6_zero_tx_checksums; udp_conf.use_udp6_rx_checksums = !cfg->udp6_zero_rx_checksums; } else #endif { udp_conf.family = AF_INET; udp_conf.local_ip = cfg->local_ip; udp_conf.peer_ip = cfg->peer_ip; udp_conf.use_udp_checksums = cfg->use_udp_checksums; } udp_conf.local_udp_port = htons(cfg->local_udp_port); udp_conf.peer_udp_port = htons(cfg->peer_udp_port); err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) goto out; break; case L2TP_ENCAPTYPE_IP: #if IS_ENABLED(CONFIG_IPV6) if (cfg->local_ip6 && cfg->peer_ip6) { struct sockaddr_l2tpip6 ip6_addr = {0}; err = sock_create_kern(net, AF_INET6, SOCK_DGRAM, IPPROTO_L2TP, &sock); if (err < 0) goto out; ip6_addr.l2tp_family = AF_INET6; memcpy(&ip6_addr.l2tp_addr, cfg->local_ip6, sizeof(ip6_addr.l2tp_addr)); ip6_addr.l2tp_conn_id = tunnel_id; err = kernel_bind(sock, (struct sockaddr *)&ip6_addr, sizeof(ip6_addr)); if (err < 0) goto out; ip6_addr.l2tp_family = AF_INET6; memcpy(&ip6_addr.l2tp_addr, cfg->peer_ip6, sizeof(ip6_addr.l2tp_addr)); ip6_addr.l2tp_conn_id = peer_tunnel_id; err = kernel_connect(sock, (struct sockaddr *)&ip6_addr, sizeof(ip6_addr), 0); if (err < 0) goto out; } else #endif { struct sockaddr_l2tpip ip_addr = {0}; err = sock_create_kern(net, AF_INET, SOCK_DGRAM, IPPROTO_L2TP, &sock); if (err < 0) goto out; ip_addr.l2tp_family = AF_INET; ip_addr.l2tp_addr = cfg->local_ip; ip_addr.l2tp_conn_id = tunnel_id; err = kernel_bind(sock, (struct sockaddr *)&ip_addr, sizeof(ip_addr)); if (err < 0) goto out; ip_addr.l2tp_family = AF_INET; ip_addr.l2tp_addr = cfg->peer_ip; ip_addr.l2tp_conn_id = peer_tunnel_id; err = kernel_connect(sock, (struct sockaddr *)&ip_addr, sizeof(ip_addr), 0); if (err < 0) goto out; } break; default: goto out; } out: *sockp = sock; if (err < 0 && sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); *sockp = NULL; } return err; } int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp) { struct l2tp_tunnel *tunnel = NULL; int err; enum l2tp_encap_type encap = L2TP_ENCAPTYPE_UDP; if (cfg) encap = cfg->encap; tunnel = kzalloc(sizeof(*tunnel), GFP_KERNEL); if (!tunnel) { err = -ENOMEM; goto err; } tunnel->version = version; tunnel->tunnel_id = tunnel_id; tunnel->peer_tunnel_id = peer_tunnel_id; sprintf(&tunnel->name[0], "tunl %u", tunnel_id); spin_lock_init(&tunnel->list_lock); tunnel->acpt_newsess = true; INIT_LIST_HEAD(&tunnel->session_list); tunnel->encap = encap; refcount_set(&tunnel->ref_count, 1); tunnel->fd = fd; /* Init delete workqueue struct */ INIT_WORK(&tunnel->del_work, l2tp_tunnel_del_work); err = 0; err: if (tunnelp) *tunnelp = tunnel; return err; } EXPORT_SYMBOL_GPL(l2tp_tunnel_create); static int l2tp_validate_socket(const struct sock *sk, const struct net *net, enum l2tp_encap_type encap) { struct l2tp_tunnel *tunnel; if (!net_eq(sock_net(sk), net)) return -EINVAL; if (sk->sk_type != SOCK_DGRAM) return -EPROTONOSUPPORT; if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6) return -EPROTONOSUPPORT; if ((encap == L2TP_ENCAPTYPE_UDP && sk->sk_protocol != IPPROTO_UDP) || (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP)) return -EPROTONOSUPPORT; if (encap == L2TP_ENCAPTYPE_UDP && sk->sk_user_data) return -EBUSY; tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) { l2tp_tunnel_put(tunnel); return -EBUSY; } return 0; } int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, struct l2tp_tunnel_cfg *cfg) { struct l2tp_net *pn = l2tp_pernet(net); u32 tunnel_id = tunnel->tunnel_id; struct socket *sock; struct sock *sk; int ret; spin_lock_bh(&pn->l2tp_tunnel_idr_lock); ret = idr_alloc_u32(&pn->l2tp_tunnel_idr, NULL, &tunnel_id, tunnel_id, GFP_ATOMIC); spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); if (ret) return ret == -ENOSPC ? -EEXIST : ret; if (tunnel->fd < 0) { ret = l2tp_tunnel_sock_create(net, tunnel->tunnel_id, tunnel->peer_tunnel_id, cfg, &sock); if (ret < 0) goto err; } else { sock = sockfd_lookup(tunnel->fd, &ret); if (!sock) goto err; } sk = sock->sk; lock_sock(sk); write_lock_bh(&sk->sk_callback_lock); ret = l2tp_validate_socket(sk, net, tunnel->encap); if (ret < 0) goto err_inval_sock; write_unlock_bh(&sk->sk_callback_lock); if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { struct udp_tunnel_sock_cfg udp_cfg = { .encap_type = UDP_ENCAP_L2TPINUDP, .encap_rcv = l2tp_udp_encap_recv, .encap_err_rcv = l2tp_udp_encap_err_recv, .encap_destroy = l2tp_udp_encap_destroy, }; setup_udp_tunnel_sock(net, sock, &udp_cfg); } sk->sk_allocation = GFP_ATOMIC; release_sock(sk); sock_hold(sk); tunnel->sock = sk; tunnel->l2tp_net = net; spin_lock_bh(&pn->l2tp_tunnel_idr_lock); idr_replace(&pn->l2tp_tunnel_idr, tunnel, tunnel->tunnel_id); spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); trace_register_tunnel(tunnel); if (tunnel->fd >= 0) sockfd_put(sock); return 0; err_inval_sock: write_unlock_bh(&sk->sk_callback_lock); release_sock(sk); if (tunnel->fd < 0) sock_release(sock); else sockfd_put(sock); err: l2tp_tunnel_remove(net, tunnel); return ret; } EXPORT_SYMBOL_GPL(l2tp_tunnel_register); /* This function is used by the netlink TUNNEL_DELETE command. */ void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { if (!test_and_set_bit(0, &tunnel->dead)) { trace_delete_tunnel(tunnel); refcount_inc(&tunnel->ref_count); queue_work(l2tp_wq, &tunnel->del_work); } } EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); void l2tp_session_delete(struct l2tp_session *session) { if (!test_and_set_bit(0, &session->dead)) { trace_delete_session(session); refcount_inc(&session->ref_count); queue_work(l2tp_wq, &session->del_work); } } EXPORT_SYMBOL_GPL(l2tp_session_delete); /* Workqueue session deletion function */ static void l2tp_session_del_work(struct work_struct *work) { struct l2tp_session *session = container_of(work, struct l2tp_session, del_work); l2tp_session_unhash(session); l2tp_session_queue_purge(session); if (session->session_close) (*session->session_close)(session); /* drop initial ref */ l2tp_session_put(session); /* drop workqueue ref */ l2tp_session_put(session); } /* We come here whenever a session's send_seq, cookie_len or * l2specific_type parameters are set. */ void l2tp_session_set_header_len(struct l2tp_session *session, int version, enum l2tp_encap_type encap) { if (version == L2TP_HDR_VER_2) { session->hdr_len = 6; if (session->send_seq) session->hdr_len += 4; } else { session->hdr_len = 4 + session->cookie_len; session->hdr_len += l2tp_get_l2specific_len(session); if (encap == L2TP_ENCAPTYPE_UDP) session->hdr_len += 4; } } EXPORT_SYMBOL_GPL(l2tp_session_set_header_len); 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) { struct l2tp_session *session; session = kzalloc(sizeof(*session) + priv_size, GFP_KERNEL); if (session) { session->magic = L2TP_SESSION_MAGIC; session->session_id = session_id; session->peer_session_id = peer_session_id; session->nr = 0; if (tunnel->version == L2TP_HDR_VER_2) session->nr_max = 0xffff; else session->nr_max = 0xffffff; session->nr_window_size = session->nr_max / 2; session->nr_oos_count_max = 4; /* Use NR of first received packet */ session->reorder_skip = 1; sprintf(&session->name[0], "sess %u/%u", tunnel->tunnel_id, session->session_id); skb_queue_head_init(&session->reorder_q); session->hlist_key = l2tp_v3_session_hashkey(tunnel->sock, session->session_id); INIT_HLIST_NODE(&session->hlist); INIT_LIST_HEAD(&session->clist); INIT_LIST_HEAD(&session->list); INIT_WORK(&session->del_work, l2tp_session_del_work); if (cfg) { session->pwtype = cfg->pw_type; session->send_seq = cfg->send_seq; session->recv_seq = cfg->recv_seq; session->lns_mode = cfg->lns_mode; session->reorder_timeout = cfg->reorder_timeout; session->l2specific_type = cfg->l2specific_type; session->cookie_len = cfg->cookie_len; memcpy(&session->cookie[0], &cfg->cookie[0], cfg->cookie_len); session->peer_cookie_len = cfg->peer_cookie_len; memcpy(&session->peer_cookie[0], &cfg->peer_cookie[0], cfg->peer_cookie_len); } l2tp_session_set_header_len(session, tunnel->version, tunnel->encap); refcount_set(&session->ref_count, 1); return session; } return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(l2tp_session_create); /***************************************************************************** * Init and cleanup *****************************************************************************/ static __net_init int l2tp_init_net(struct net *net) { struct l2tp_net *pn = net_generic(net, l2tp_net_id); idr_init(&pn->l2tp_tunnel_idr); spin_lock_init(&pn->l2tp_tunnel_idr_lock); idr_init(&pn->l2tp_v2_session_idr); idr_init(&pn->l2tp_v3_session_idr); spin_lock_init(&pn->l2tp_session_idr_lock); return 0; } static __net_exit void l2tp_pre_exit_net(struct net *net) { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel = NULL; unsigned long tunnel_id, tmp; rcu_read_lock_bh(); idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { if (tunnel) l2tp_tunnel_delete(tunnel); } rcu_read_unlock_bh(); if (l2tp_wq) { /* Run all TUNNEL_DELETE work items just queued. */ __flush_workqueue(l2tp_wq); /* Each TUNNEL_DELETE work item will queue a SESSION_DELETE * work item for each session in the tunnel. Flush the * workqueue again to process these. */ __flush_workqueue(l2tp_wq); } } static int l2tp_idr_item_unexpected(int id, void *p, void *data) { const char *idr_name = data; pr_err("l2tp: %s IDR not empty at net %d exit\n", idr_name, id); WARN_ON_ONCE(1); return 1; } static __net_exit void l2tp_exit_net(struct net *net) { struct l2tp_net *pn = l2tp_pernet(net); /* Our per-net IDRs should be empty. Check that is so, to * help catch cleanup races or refcnt leaks. */ idr_for_each(&pn->l2tp_v2_session_idr, l2tp_idr_item_unexpected, "v2_session"); idr_for_each(&pn->l2tp_v3_session_idr, l2tp_idr_item_unexpected, "v3_session"); idr_for_each(&pn->l2tp_tunnel_idr, l2tp_idr_item_unexpected, "tunnel"); idr_destroy(&pn->l2tp_v2_session_idr); idr_destroy(&pn->l2tp_v3_session_idr); idr_destroy(&pn->l2tp_tunnel_idr); } static struct pernet_operations l2tp_net_ops = { .init = l2tp_init_net, .exit = l2tp_exit_net, .pre_exit = l2tp_pre_exit_net, .id = &l2tp_net_id, .size = sizeof(struct l2tp_net), }; static int __init l2tp_init(void) { int rc = 0; rc = register_pernet_device(&l2tp_net_ops); if (rc) goto out; l2tp_wq = alloc_workqueue("l2tp", WQ_UNBOUND, 0); if (!l2tp_wq) { pr_err("alloc_workqueue failed\n"); unregister_pernet_device(&l2tp_net_ops); rc = -ENOMEM; goto out; } pr_info("L2TP core driver, %s\n", L2TP_DRV_VERSION); out: return rc; } static void __exit l2tp_exit(void) { unregister_pernet_device(&l2tp_net_ops); if (l2tp_wq) { destroy_workqueue(l2tp_wq); l2tp_wq = NULL; } } module_init(l2tp_init); module_exit(l2tp_exit); MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("L2TP core"); MODULE_LICENSE("GPL"); MODULE_VERSION(L2TP_DRV_VERSION); |
| 2347 1926 1902 3 576 574 2 1 22 5 22 22 694 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIME64_H #define _LINUX_TIME64_H #include <linux/math64.h> #include <vdso/time64.h> typedef __s64 time64_t; typedef __u64 timeu64_t; #include <uapi/linux/time.h> struct timespec64 { time64_t tv_sec; /* seconds */ long tv_nsec; /* nanoseconds */ }; struct itimerspec64 { struct timespec64 it_interval; struct timespec64 it_value; }; /* Parameters used to convert the timespec values: */ #define PSEC_PER_NSEC 1000L /* Located here for timespec[64]_valid_strict */ #define TIME64_MAX ((s64)~((u64)1 << 63)) #define TIME64_MIN (-TIME64_MAX - 1) #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_MIN (-KTIME_MAX - 1) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) #define KTIME_SEC_MIN (KTIME_MIN / NSEC_PER_SEC) /* * Limits for settimeofday(): * * To prevent setting the time close to the wraparound point time setting * is limited so a reasonable uptime can be accomodated. Uptime of 30 years * should be really sufficient, which means the cutoff is 2232. At that * point the cutoff is just a small part of the larger problem. */ #define TIME_UPTIME_SEC_MAX (30LL * 365 * 24 *3600) #define TIME_SETTOD_SEC_MAX (KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX) static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); } /* * lhs < rhs: return <0 * lhs == rhs: return 0 * lhs > rhs: return >0 */ static inline int timespec64_compare(const struct timespec64 *lhs, const struct timespec64 *rhs) { if (lhs->tv_sec < rhs->tv_sec) return -1; if (lhs->tv_sec > rhs->tv_sec) return 1; return lhs->tv_nsec - rhs->tv_nsec; } extern void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec); static inline struct timespec64 timespec64_add(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); return ts_delta; } /* * sub = lhs - rhs, in normalized form */ static inline struct timespec64 timespec64_sub(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec - rhs.tv_sec, lhs.tv_nsec - rhs.tv_nsec); return ts_delta; } /* * Returns true if the timespec64 is norm, false if denorm: */ static inline bool timespec64_valid(const struct timespec64 *ts) { /* Dates before 1970 are bogus */ if (ts->tv_sec < 0) return false; /* Can't have more nanoseconds then a second */ if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return false; return true; } static inline bool timespec64_valid_strict(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values that could overflow ktime_t */ if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) return false; return true; } static inline bool timespec64_valid_settod(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values which cause overflow issues vs. CLOCK_REALTIME */ if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX) return false; return true; } /** * timespec64_to_ns - Convert timespec64 to nanoseconds * @ts: pointer to the timespec64 variable to be converted * * Returns the scalar nanosecond representation of the timespec64 * parameter. */ static inline s64 timespec64_to_ns(const struct timespec64 *ts) { /* Prevent multiplication overflow / underflow */ if (ts->tv_sec >= KTIME_SEC_MAX) return KTIME_MAX; if (ts->tv_sec <= KTIME_SEC_MIN) return KTIME_MIN; return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; } /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Returns the timespec64 representation of the nsec parameter. */ extern struct timespec64 ns_to_timespec64(s64 nsec); /** * timespec64_add_ns - Adds nanoseconds to a timespec64 * @a: pointer to timespec64 to be incremented * @ns: unsigned nanoseconds value to be added * * This must always be inlined because its used from the x86-64 vdso, * which cannot call other kernel functions. */ static __always_inline void timespec64_add_ns(struct timespec64 *a, u64 ns) { a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); a->tv_nsec = ns; } /* * timespec64_add_safe assumes both values are positive and checks for * overflow. It will return TIME64_MAX in case of overflow. */ extern struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs); #endif /* _LINUX_TIME64_H */ |
| 79 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Key-agreement Protocol Primitives (KPP) * * Copyright (c) 2016, Intel Corporation * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com> */ #ifndef _CRYPTO_KPP_INT_H #define _CRYPTO_KPP_INT_H #include <crypto/kpp.h> #include <crypto/algapi.h> /** * struct kpp_instance - KPP template instance * @free: Callback getting invoked upon instance destruction. Must be set. * @s: Internal. Generic crypto core instance state properly layout * to alias with @alg as needed. * @alg: The &struct kpp_alg implementation provided by the instance. */ struct kpp_instance { void (*free)(struct kpp_instance *inst); union { struct { char head[offsetof(struct kpp_alg, base)]; struct crypto_instance base; } s; struct kpp_alg alg; }; }; /** * struct crypto_kpp_spawn - KPP algorithm spawn * @base: Internal. Generic crypto core spawn state. * * Template instances can get a hold on some inner KPP algorithm by * binding a &struct crypto_kpp_spawn via * crypto_grab_kpp(). Transforms may subsequently get instantiated * from the referenced inner &struct kpp_alg by means of * crypto_spawn_kpp(). */ struct crypto_kpp_spawn { struct crypto_spawn base; }; /* * Transform internal helpers. */ static inline void *kpp_request_ctx(struct kpp_request *req) { return req->__ctx; } static inline void *kpp_request_ctx_dma(struct kpp_request *req) { unsigned int align = crypto_dma_align(); if (align <= crypto_tfm_ctx_alignment()) align = 1; return PTR_ALIGN(kpp_request_ctx(req), align); } static inline void kpp_set_reqsize(struct crypto_kpp *kpp, unsigned int reqsize) { kpp->reqsize = reqsize; } static inline void kpp_set_reqsize_dma(struct crypto_kpp *kpp, unsigned int reqsize) { reqsize += crypto_dma_align() & ~(crypto_tfm_ctx_alignment() - 1); kpp->reqsize = reqsize; } static inline void *kpp_tfm_ctx(struct crypto_kpp *tfm) { return crypto_tfm_ctx(&tfm->base); } static inline void *kpp_tfm_ctx_dma(struct crypto_kpp *tfm) { return crypto_tfm_ctx_dma(&tfm->base); } static inline void kpp_request_complete(struct kpp_request *req, int err) { crypto_request_complete(&req->base, err); } static inline const char *kpp_alg_name(struct crypto_kpp *tfm) { return crypto_kpp_tfm(tfm)->__crt_alg->cra_name; } /* * Template instance internal helpers. */ /** * kpp_crypto_instance() - Cast a &struct kpp_instance to the corresponding * generic &struct crypto_instance. * @inst: Pointer to the &struct kpp_instance to be cast. * Return: A pointer to the &struct crypto_instance embedded in @inst. */ static inline struct crypto_instance *kpp_crypto_instance( struct kpp_instance *inst) { return &inst->s.base; } /** * kpp_instance() - Cast a generic &struct crypto_instance to the corresponding * &struct kpp_instance. * @inst: Pointer to the &struct crypto_instance to be cast. * Return: A pointer to the &struct kpp_instance @inst is embedded in. */ static inline struct kpp_instance *kpp_instance(struct crypto_instance *inst) { return container_of(inst, struct kpp_instance, s.base); } /** * kpp_alg_instance() - Get the &struct kpp_instance a given KPP transform has * been instantiated from. * @kpp: The KPP transform instantiated from some &struct kpp_instance. * Return: The &struct kpp_instance associated with @kpp. */ static inline struct kpp_instance *kpp_alg_instance(struct crypto_kpp *kpp) { return kpp_instance(crypto_tfm_alg_instance(&kpp->base)); } /** * kpp_instance_ctx() - Get a pointer to a &struct kpp_instance's implementation * specific context data. * @inst: The &struct kpp_instance whose context data to access. * * A KPP template implementation may allocate extra memory beyond the * end of a &struct kpp_instance instantiated from &crypto_template.create(). * This function provides a means to obtain a pointer to this area. * * Return: A pointer to the implementation specific context data. */ static inline void *kpp_instance_ctx(struct kpp_instance *inst) { return crypto_instance_ctx(kpp_crypto_instance(inst)); } /* * KPP algorithm (un)registration functions. */ /** * crypto_register_kpp() -- Register key-agreement protocol primitives algorithm * * Function registers an implementation of a key-agreement protocol primitive * algorithm * * @alg: algorithm definition * * Return: zero on success; error code in case of error */ int crypto_register_kpp(struct kpp_alg *alg); /** * crypto_unregister_kpp() -- Unregister key-agreement protocol primitive * algorithm * * Function unregisters an implementation of a key-agreement protocol primitive * algorithm * * @alg: algorithm definition */ void crypto_unregister_kpp(struct kpp_alg *alg); /** * kpp_register_instance() - Register a KPP template instance. * @tmpl: The instantiating template. * @inst: The KPP template instance to be registered. * Return: %0 on success, negative error code otherwise. */ int kpp_register_instance(struct crypto_template *tmpl, struct kpp_instance *inst); /* * KPP spawn related functions. */ /** * crypto_grab_kpp() - Look up a KPP algorithm and bind a spawn to it. * @spawn: The KPP spawn to bind. * @inst: The template instance owning @spawn. * @name: The KPP algorithm name to look up. * @type: The type bitset to pass on to the lookup. * @mask: The mask bismask to pass on to the lookup. * Return: %0 on success, a negative error code otherwise. */ int crypto_grab_kpp(struct crypto_kpp_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); /** * crypto_drop_kpp() - Release a spawn previously bound via crypto_grab_kpp(). * @spawn: The spawn to release. */ static inline void crypto_drop_kpp(struct crypto_kpp_spawn *spawn) { crypto_drop_spawn(&spawn->base); } /** * crypto_spawn_kpp_alg() - Get the algorithm a KPP spawn has been bound to. * @spawn: The spawn to get the referenced &struct kpp_alg for. * * This function as well as the returned result are safe to use only * after @spawn has been successfully bound via crypto_grab_kpp() and * up to until the template instance owning @spawn has either been * registered successfully or the spawn has been released again via * crypto_drop_spawn(). * * Return: A pointer to the &struct kpp_alg referenced from the spawn. */ static inline struct kpp_alg *crypto_spawn_kpp_alg( struct crypto_kpp_spawn *spawn) { return container_of(spawn->base.alg, struct kpp_alg, base); } /** * crypto_spawn_kpp() - Create a transform from a KPP spawn. * @spawn: The spawn previously bound to some &struct kpp_alg via * crypto_grab_kpp(). * * Once a &struct crypto_kpp_spawn has been successfully bound to a * &struct kpp_alg via crypto_grab_kpp(), transforms for the latter * may get instantiated from the former by means of this function. * * Return: A pointer to the freshly created KPP transform on success * or an ``ERR_PTR()`` otherwise. */ static inline struct crypto_kpp *crypto_spawn_kpp( struct crypto_kpp_spawn *spawn) { return crypto_spawn_tfm2(&spawn->base); } #endif |
| 3 3 3 3 3 3 3 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 | // SPDX-License-Identifier: GPL-2.0-only // // ethtool interface for Ethernet PSE (Power Sourcing Equipment) // and PD (Powered Device) // // Copyright (c) 2022 Pengutronix, Oleksij Rempel <kernel@pengutronix.de> // #include "common.h" #include "linux/pse-pd/pse.h" #include "netlink.h" #include <linux/ethtool_netlink.h> #include <linux/ethtool.h> #include <linux/phy.h> struct pse_req_info { struct ethnl_req_info base; }; struct pse_reply_data { struct ethnl_reply_data base; struct pse_control_status status; }; #define PSE_REPDATA(__reply_base) \ container_of(__reply_base, struct pse_reply_data, base) /* PSE_GET */ const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1] = { [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), }; static int pse_get_pse_attributes(struct phy_device *phydev, struct netlink_ext_ack *extack, struct pse_reply_data *data) { if (!phydev) { NL_SET_ERR_MSG(extack, "No PHY found"); return -EOPNOTSUPP; } if (!phydev->psec) { NL_SET_ERR_MSG(extack, "No PSE is attached"); return -EOPNOTSUPP; } memset(&data->status, 0, sizeof(data->status)); return pse_ethtool_get_status(phydev->psec, extack, &data->status); } static int pse_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct pse_reply_data *data = PSE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; struct nlattr **tb = info->attrs; struct phy_device *phydev; int ret; ret = ethnl_ops_begin(dev); if (ret < 0) return ret; phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PSE_HEADER], info->extack); if (IS_ERR(phydev)) return -ENODEV; ret = pse_get_pse_attributes(phydev, info->extack, data); ethnl_ops_complete(dev); return ret; } static int pse_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct pse_reply_data *data = PSE_REPDATA(reply_base); const struct pse_control_status *st = &data->status; int len = 0; if (st->podl_admin_state > 0) len += nla_total_size(sizeof(u32)); /* _PODL_PSE_ADMIN_STATE */ if (st->podl_pw_status > 0) len += nla_total_size(sizeof(u32)); /* _PODL_PSE_PW_D_STATUS */ if (st->c33_admin_state > 0) len += nla_total_size(sizeof(u32)); /* _C33_PSE_ADMIN_STATE */ if (st->c33_pw_status > 0) len += nla_total_size(sizeof(u32)); /* _C33_PSE_PW_D_STATUS */ if (st->c33_pw_class > 0) len += nla_total_size(sizeof(u32)); /* _C33_PSE_PW_CLASS */ if (st->c33_actual_pw > 0) len += nla_total_size(sizeof(u32)); /* _C33_PSE_ACTUAL_PW */ if (st->c33_ext_state_info.c33_pse_ext_state > 0) { len += nla_total_size(sizeof(u32)); /* _C33_PSE_EXT_STATE */ if (st->c33_ext_state_info.__c33_pse_ext_substate > 0) /* _C33_PSE_EXT_SUBSTATE */ len += nla_total_size(sizeof(u32)); } if (st->c33_avail_pw_limit > 0) /* _C33_AVAIL_PSE_PW_LIMIT */ len += nla_total_size(sizeof(u32)); if (st->c33_pw_limit_nb_ranges > 0) /* _C33_PSE_PW_LIMIT_RANGES */ len += st->c33_pw_limit_nb_ranges * (nla_total_size(0) + nla_total_size(sizeof(u32)) * 2); return len; } static int pse_put_pw_limit_ranges(struct sk_buff *skb, const struct pse_control_status *st) { const struct ethtool_c33_pse_pw_limit_range *pw_limit_ranges; int i; pw_limit_ranges = st->c33_pw_limit_ranges; for (i = 0; i < st->c33_pw_limit_nb_ranges; i++) { struct nlattr *nest; nest = nla_nest_start(skb, ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES); if (!nest) return -EMSGSIZE; if (nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_LIMIT_MIN, pw_limit_ranges->min) || nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_LIMIT_MAX, pw_limit_ranges->max)) { nla_nest_cancel(skb, nest); return -EMSGSIZE; } nla_nest_end(skb, nest); pw_limit_ranges++; } return 0; } static int pse_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct pse_reply_data *data = PSE_REPDATA(reply_base); const struct pse_control_status *st = &data->status; if (st->podl_admin_state > 0 && nla_put_u32(skb, ETHTOOL_A_PODL_PSE_ADMIN_STATE, st->podl_admin_state)) return -EMSGSIZE; if (st->podl_pw_status > 0 && nla_put_u32(skb, ETHTOOL_A_PODL_PSE_PW_D_STATUS, st->podl_pw_status)) return -EMSGSIZE; if (st->c33_admin_state > 0 && nla_put_u32(skb, ETHTOOL_A_C33_PSE_ADMIN_STATE, st->c33_admin_state)) return -EMSGSIZE; if (st->c33_pw_status > 0 && nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_D_STATUS, st->c33_pw_status)) return -EMSGSIZE; if (st->c33_pw_class > 0 && nla_put_u32(skb, ETHTOOL_A_C33_PSE_PW_CLASS, st->c33_pw_class)) return -EMSGSIZE; if (st->c33_actual_pw > 0 && nla_put_u32(skb, ETHTOOL_A_C33_PSE_ACTUAL_PW, st->c33_actual_pw)) return -EMSGSIZE; if (st->c33_ext_state_info.c33_pse_ext_state > 0) { if (nla_put_u32(skb, ETHTOOL_A_C33_PSE_EXT_STATE, st->c33_ext_state_info.c33_pse_ext_state)) return -EMSGSIZE; if (st->c33_ext_state_info.__c33_pse_ext_substate > 0 && nla_put_u32(skb, ETHTOOL_A_C33_PSE_EXT_SUBSTATE, st->c33_ext_state_info.__c33_pse_ext_substate)) return -EMSGSIZE; } if (st->c33_avail_pw_limit > 0 && nla_put_u32(skb, ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT, st->c33_avail_pw_limit)) return -EMSGSIZE; if (st->c33_pw_limit_nb_ranges > 0 && pse_put_pw_limit_ranges(skb, st)) return -EMSGSIZE; return 0; } static void pse_cleanup_data(struct ethnl_reply_data *reply_base) { const struct pse_reply_data *data = PSE_REPDATA(reply_base); kfree(data->status.c33_pw_limit_ranges); } /* PSE_SET */ const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1] = { [ETHTOOL_A_PSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), [ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] = NLA_POLICY_RANGE(NLA_U32, ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED, ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED), [ETHTOOL_A_C33_PSE_ADMIN_CONTROL] = NLA_POLICY_RANGE(NLA_U32, ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED, ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED), [ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT] = { .type = NLA_U32 }, }; static int ethnl_set_pse_validate(struct phy_device *phydev, struct genl_info *info) { struct nlattr **tb = info->attrs; if (IS_ERR_OR_NULL(phydev)) { NL_SET_ERR_MSG(info->extack, "No PHY is attached"); return -EOPNOTSUPP; } if (!phydev->psec) { NL_SET_ERR_MSG(info->extack, "No PSE is attached"); return -EOPNOTSUPP; } if (tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] && !pse_has_podl(phydev->psec)) { NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL], "setting PoDL PSE admin control not supported"); return -EOPNOTSUPP; } if (tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL] && !pse_has_c33(phydev->psec)) { NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL], "setting C33 PSE admin control not supported"); return -EOPNOTSUPP; } return 0; } static int ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info) { struct nlattr **tb = info->attrs; struct phy_device *phydev; int ret; phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PSE_HEADER], info->extack); ret = ethnl_set_pse_validate(phydev, info); if (ret) return ret; if (tb[ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT]) { unsigned int pw_limit; pw_limit = nla_get_u32(tb[ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT]); ret = pse_ethtool_set_pw_limit(phydev->psec, info->extack, pw_limit); if (ret) return ret; } /* These values are already validated by the ethnl_pse_set_policy */ if (tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL] || tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]) { struct pse_control_config config = {}; if (tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]) config.podl_admin_control = nla_get_u32(tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]); if (tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]) config.c33_admin_control = nla_get_u32(tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]); /* pse_ethtool_set_config() will do nothing if the config * is zero */ ret = pse_ethtool_set_config(phydev->psec, info->extack, &config); if (ret) return ret; } /* Return errno or zero - PSE has no notification */ return ret; } const struct ethnl_request_ops ethnl_pse_request_ops = { .request_cmd = ETHTOOL_MSG_PSE_GET, .reply_cmd = ETHTOOL_MSG_PSE_GET_REPLY, .hdr_attr = ETHTOOL_A_PSE_HEADER, .req_info_size = sizeof(struct pse_req_info), .reply_data_size = sizeof(struct pse_reply_data), .prepare_data = pse_prepare_data, .reply_size = pse_reply_size, .fill_reply = pse_fill_reply, .cleanup_data = pse_cleanup_data, .set = ethnl_set_pse, /* PSE has no notification */ }; |
| 36 36 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * History * 03-01-2007 Added forwarding for x.25 Andrew Hendry */ #define pr_fmt(fmt) "X25: " fmt #include <linux/if_arp.h> #include <linux/init.h> #include <linux/slab.h> #include <net/x25.h> LIST_HEAD(x25_forward_list); DEFINE_RWLOCK(x25_forward_list_lock); int x25_forward_call(struct x25_address *dest_addr, struct x25_neigh *from, struct sk_buff *skb, int lci) { struct x25_route *rt; struct x25_neigh *neigh_new = NULL; struct x25_forward *x25_frwd, *new_frwd; struct sk_buff *skbn; short same_lci = 0; int rc = 0; if ((rt = x25_get_route(dest_addr)) == NULL) goto out_no_route; if ((neigh_new = x25_get_neigh(rt->dev)) == NULL) { /* This shouldn't happen, if it occurs somehow * do something sensible */ goto out_put_route; } /* Avoid a loop. This is the normal exit path for a * system with only one x.25 iface and default route */ if (rt->dev == from->dev) { goto out_put_nb; } /* Remote end sending a call request on an already * established LCI? It shouldn't happen, just in case.. */ read_lock_bh(&x25_forward_list_lock); list_for_each_entry(x25_frwd, &x25_forward_list, node) { if (x25_frwd->lci == lci) { pr_warn("call request for lci which is already registered!, transmitting but not registering new pair\n"); same_lci = 1; } } read_unlock_bh(&x25_forward_list_lock); /* Save the forwarding details for future traffic */ if (!same_lci){ if ((new_frwd = kmalloc(sizeof(struct x25_forward), GFP_ATOMIC)) == NULL){ rc = -ENOMEM; goto out_put_nb; } new_frwd->lci = lci; new_frwd->dev1 = rt->dev; new_frwd->dev2 = from->dev; write_lock_bh(&x25_forward_list_lock); list_add(&new_frwd->node, &x25_forward_list); write_unlock_bh(&x25_forward_list_lock); } /* Forward the call request */ if ( (skbn = skb_clone(skb, GFP_ATOMIC)) == NULL){ goto out_put_nb; } x25_transmit_link(skbn, neigh_new); rc = 1; out_put_nb: x25_neigh_put(neigh_new); out_put_route: x25_route_put(rt); out_no_route: return rc; } int x25_forward_data(int lci, struct x25_neigh *from, struct sk_buff *skb) { struct x25_forward *frwd; struct net_device *peer = NULL; struct x25_neigh *nb; struct sk_buff *skbn; int rc = 0; read_lock_bh(&x25_forward_list_lock); list_for_each_entry(frwd, &x25_forward_list, node) { if (frwd->lci == lci) { /* The call is established, either side can send */ if (from->dev == frwd->dev1) { peer = frwd->dev2; } else { peer = frwd->dev1; } break; } } read_unlock_bh(&x25_forward_list_lock); if ( (nb = x25_get_neigh(peer)) == NULL) goto out; if ( (skbn = pskb_copy(skb, GFP_ATOMIC)) == NULL){ goto output; } x25_transmit_link(skbn, nb); rc = 1; output: x25_neigh_put(nb); out: return rc; } void x25_clear_forward_by_lci(unsigned int lci) { struct x25_forward *fwd, *tmp; write_lock_bh(&x25_forward_list_lock); list_for_each_entry_safe(fwd, tmp, &x25_forward_list, node) { if (fwd->lci == lci) { list_del(&fwd->node); kfree(fwd); } } write_unlock_bh(&x25_forward_list_lock); } void x25_clear_forward_by_dev(struct net_device *dev) { struct x25_forward *fwd, *tmp; write_lock_bh(&x25_forward_list_lock); list_for_each_entry_safe(fwd, tmp, &x25_forward_list, node) { if ((fwd->dev1 == dev) || (fwd->dev2 == dev)){ list_del(&fwd->node); kfree(fwd); } } write_unlock_bh(&x25_forward_list_lock); } |
| 15 15 15 62 62 62 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 61 62 62 51 414 417 416 1054 | 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/path.h> #include <linux/slab.h> #include <linux/fs_struct.h> #include "internal.h" /* * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_root(struct fs_struct *fs, const struct path *path) { struct path old_root; path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_root = fs->root; fs->root = *path; write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_root.dentry) path_put(&old_root); } /* * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values. * It can block. */ void set_fs_pwd(struct fs_struct *fs, const struct path *path) { struct path old_pwd; path_get(path); spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); old_pwd = fs->pwd; fs->pwd = *path; write_seqcount_end(&fs->seq); spin_unlock(&fs->lock); if (old_pwd.dentry) path_put(&old_pwd); } static inline int replace_path(struct path *p, const struct path *old, const struct path *new) { if (likely(p->dentry != old->dentry || p->mnt != old->mnt)) return 0; *p = *new; return 1; } void chroot_fs_refs(const struct path *old_root, const struct path *new_root) { struct task_struct *g, *p; struct fs_struct *fs; int count = 0; read_lock(&tasklist_lock); for_each_process_thread(g, p) { task_lock(p); fs = p->fs; if (fs) { int hits = 0; spin_lock(&fs->lock); write_seqcount_begin(&fs->seq); hits += replace_path(&fs->root, old_root, new_root); hits += replace_path(&fs->pwd, old_root, new_root); write_seqcount_end(&fs->seq); while (hits--) { count++; path_get(new_root); } spin_unlock(&fs->lock); } task_unlock(p); } read_unlock(&tasklist_lock); while (count--) path_put(old_root); } void free_fs_struct(struct fs_struct *fs) { path_put(&fs->root); path_put(&fs->pwd); kmem_cache_free(fs_cachep, fs); } void exit_fs(struct task_struct *tsk) { struct fs_struct *fs = tsk->fs; if (fs) { int kill; task_lock(tsk); spin_lock(&fs->lock); tsk->fs = NULL; kill = !--fs->users; spin_unlock(&fs->lock); task_unlock(tsk); if (kill) free_fs_struct(fs); } } struct fs_struct *copy_fs_struct(struct fs_struct *old) { struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL); /* We don't need to lock fs - think why ;-) */ if (fs) { fs->users = 1; fs->in_exec = 0; spin_lock_init(&fs->lock); seqcount_spinlock_init(&fs->seq, &fs->lock); fs->umask = old->umask; spin_lock(&old->lock); fs->root = old->root; path_get(&fs->root); fs->pwd = old->pwd; path_get(&fs->pwd); spin_unlock(&old->lock); } return fs; } int unshare_fs_struct(void) { struct fs_struct *fs = current->fs; struct fs_struct *new_fs = copy_fs_struct(fs); int kill; if (!new_fs) return -ENOMEM; task_lock(current); spin_lock(&fs->lock); kill = !--fs->users; current->fs = new_fs; spin_unlock(&fs->lock); task_unlock(current); if (kill) free_fs_struct(fs); return 0; } EXPORT_SYMBOL_GPL(unshare_fs_struct); int current_umask(void) { return current->fs->umask; } EXPORT_SYMBOL(current_umask); /* to be mentioned only in INIT_TASK */ struct fs_struct init_fs = { .users = 1, .lock = __SPIN_LOCK_UNLOCKED(init_fs.lock), .seq = SEQCNT_SPINLOCK_ZERO(init_fs.seq, &init_fs.lock), .umask = 0022, }; |
| 5 5 5 5 5 5 5 5 5 14 14 14 14 14 14 1 13 13 13 13 13 1 16 16 16 16 16 16 16 14 14 14 14 16 13 5 12 11 9 11 10 10 9 10 9 9 9 9 8 3 3 9 3 3 3 3 3 3 3 3 4 4 2 4 4 4 4 3 1 3 2 2 2 3 4 5 2 2 2 2 2 5 2 10 10 10 10 10 3 2 1 1 3 5 4 3 3 2 2 2 2 2 2 1 1 5 2 3 2 1 1 3 5 5 5 5 5 10 10 10 9 9 10 5 5 5 5 5 5 5 5 10 10 10 10 9 10 10 10 10 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * HWSIM IEEE 802.15.4 interface * * (C) 2018 Mojatau, Alexander Aring <aring@mojatau.com> * Copyright 2007-2012 Siemens AG * * Based on fakelb, original Written by: * Sergey Lapin <slapin@ossfans.org> * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ #include <linux/module.h> #include <linux/timer.h> #include <linux/platform_device.h> #include <linux/rtnetlink.h> #include <linux/netdevice.h> #include <linux/device.h> #include <linux/spinlock.h> #include <net/ieee802154_netdev.h> #include <net/mac802154.h> #include <net/cfg802154.h> #include <net/genetlink.h> #include "mac802154_hwsim.h" MODULE_DESCRIPTION("Software simulator of IEEE 802.15.4 radio(s) for mac802154"); MODULE_LICENSE("GPL"); static LIST_HEAD(hwsim_phys); static DEFINE_MUTEX(hwsim_phys_lock); static struct platform_device *mac802154hwsim_dev; /* MAC802154_HWSIM netlink family */ static struct genl_family hwsim_genl_family; static int hwsim_radio_idx; enum hwsim_multicast_groups { HWSIM_MCGRP_CONFIG, }; static const struct genl_multicast_group hwsim_mcgrps[] = { [HWSIM_MCGRP_CONFIG] = { .name = "config", }, }; struct hwsim_pib { u8 page; u8 channel; struct ieee802154_hw_addr_filt filt; enum ieee802154_filtering_level filt_level; struct rcu_head rcu; }; struct hwsim_edge_info { u8 lqi; struct rcu_head rcu; }; struct hwsim_edge { struct hwsim_phy *endpoint; struct hwsim_edge_info __rcu *info; struct list_head list; struct rcu_head rcu; }; struct hwsim_phy { struct ieee802154_hw *hw; u32 idx; struct hwsim_pib __rcu *pib; bool suspended; struct list_head edges; struct list_head list; }; static int hwsim_add_one(struct genl_info *info, struct device *dev, bool init); static void hwsim_del(struct hwsim_phy *phy); static int hwsim_hw_ed(struct ieee802154_hw *hw, u8 *level) { *level = 0xbe; return 0; } static int hwsim_update_pib(struct ieee802154_hw *hw, u8 page, u8 channel, struct ieee802154_hw_addr_filt *filt, enum ieee802154_filtering_level filt_level) { struct hwsim_phy *phy = hw->priv; struct hwsim_pib *pib, *pib_old; pib = kzalloc(sizeof(*pib), GFP_ATOMIC); if (!pib) return -ENOMEM; pib_old = rtnl_dereference(phy->pib); pib->page = page; pib->channel = channel; pib->filt.short_addr = filt->short_addr; pib->filt.pan_id = filt->pan_id; pib->filt.ieee_addr = filt->ieee_addr; pib->filt.pan_coord = filt->pan_coord; pib->filt_level = filt_level; rcu_assign_pointer(phy->pib, pib); kfree_rcu(pib_old, rcu); return 0; } static int hwsim_hw_channel(struct ieee802154_hw *hw, u8 page, u8 channel) { struct hwsim_phy *phy = hw->priv; struct hwsim_pib *pib; int ret; rcu_read_lock(); pib = rcu_dereference(phy->pib); ret = hwsim_update_pib(hw, page, channel, &pib->filt, pib->filt_level); rcu_read_unlock(); return ret; } static int hwsim_hw_addr_filt(struct ieee802154_hw *hw, struct ieee802154_hw_addr_filt *filt, unsigned long changed) { struct hwsim_phy *phy = hw->priv; struct hwsim_pib *pib; int ret; rcu_read_lock(); pib = rcu_dereference(phy->pib); ret = hwsim_update_pib(hw, pib->page, pib->channel, filt, pib->filt_level); rcu_read_unlock(); return ret; } static void hwsim_hw_receive(struct ieee802154_hw *hw, struct sk_buff *skb, u8 lqi) { struct ieee802154_hdr hdr; struct hwsim_phy *phy = hw->priv; struct hwsim_pib *pib; rcu_read_lock(); pib = rcu_dereference(phy->pib); if (!pskb_may_pull(skb, 3)) { dev_dbg(hw->parent, "invalid frame\n"); goto drop; } memcpy(&hdr, skb->data, 3); /* Level 4 filtering: Frame fields validity */ if (pib->filt_level == IEEE802154_FILTERING_4_FRAME_FIELDS) { /* a) Drop reserved frame types */ switch (mac_cb(skb)->type) { case IEEE802154_FC_TYPE_BEACON: case IEEE802154_FC_TYPE_DATA: case IEEE802154_FC_TYPE_ACK: case IEEE802154_FC_TYPE_MAC_CMD: break; default: dev_dbg(hw->parent, "unrecognized frame type 0x%x\n", mac_cb(skb)->type); goto drop; } /* b) Drop reserved frame versions */ switch (hdr.fc.version) { case IEEE802154_2003_STD: case IEEE802154_2006_STD: case IEEE802154_STD: break; default: dev_dbg(hw->parent, "unrecognized frame version 0x%x\n", hdr.fc.version); goto drop; } /* c) PAN ID constraints */ if ((mac_cb(skb)->dest.mode == IEEE802154_ADDR_LONG || mac_cb(skb)->dest.mode == IEEE802154_ADDR_SHORT) && mac_cb(skb)->dest.pan_id != pib->filt.pan_id && mac_cb(skb)->dest.pan_id != cpu_to_le16(IEEE802154_PANID_BROADCAST)) { dev_dbg(hw->parent, "unrecognized PAN ID %04x\n", le16_to_cpu(mac_cb(skb)->dest.pan_id)); goto drop; } /* d1) Short address constraints */ if (mac_cb(skb)->dest.mode == IEEE802154_ADDR_SHORT && mac_cb(skb)->dest.short_addr != pib->filt.short_addr && mac_cb(skb)->dest.short_addr != cpu_to_le16(IEEE802154_ADDR_BROADCAST)) { dev_dbg(hw->parent, "unrecognized short address %04x\n", le16_to_cpu(mac_cb(skb)->dest.short_addr)); goto drop; } /* d2) Extended address constraints */ if (mac_cb(skb)->dest.mode == IEEE802154_ADDR_LONG && mac_cb(skb)->dest.extended_addr != pib->filt.ieee_addr) { dev_dbg(hw->parent, "unrecognized long address 0x%016llx\n", mac_cb(skb)->dest.extended_addr); goto drop; } /* d4) Specific PAN coordinator case (no parent) */ if ((mac_cb(skb)->type == IEEE802154_FC_TYPE_DATA || mac_cb(skb)->type == IEEE802154_FC_TYPE_MAC_CMD) && mac_cb(skb)->dest.mode == IEEE802154_ADDR_NONE) { dev_dbg(hw->parent, "relaying is not supported\n"); goto drop; } /* e) Beacon frames follow specific PAN ID rules */ if (mac_cb(skb)->type == IEEE802154_FC_TYPE_BEACON && pib->filt.pan_id != cpu_to_le16(IEEE802154_PANID_BROADCAST) && mac_cb(skb)->dest.pan_id != pib->filt.pan_id) { dev_dbg(hw->parent, "invalid beacon PAN ID %04x\n", le16_to_cpu(mac_cb(skb)->dest.pan_id)); goto drop; } } rcu_read_unlock(); ieee802154_rx_irqsafe(hw, skb, lqi); return; drop: rcu_read_unlock(); kfree_skb(skb); } static int hwsim_hw_xmit(struct ieee802154_hw *hw, struct sk_buff *skb) { struct hwsim_phy *current_phy = hw->priv; struct hwsim_pib *current_pib, *endpoint_pib; struct hwsim_edge_info *einfo; struct hwsim_edge *e; WARN_ON(current_phy->suspended); rcu_read_lock(); current_pib = rcu_dereference(current_phy->pib); list_for_each_entry_rcu(e, ¤t_phy->edges, list) { /* Can be changed later in rx_irqsafe, but this is only a * performance tweak. Received radio should drop the frame * in mac802154 stack anyway... so we don't need to be * 100% of locking here to check on suspended */ if (e->endpoint->suspended) continue; endpoint_pib = rcu_dereference(e->endpoint->pib); if (current_pib->page == endpoint_pib->page && current_pib->channel == endpoint_pib->channel) { struct sk_buff *newskb = pskb_copy(skb, GFP_ATOMIC); einfo = rcu_dereference(e->info); if (newskb) hwsim_hw_receive(e->endpoint->hw, newskb, einfo->lqi); } } rcu_read_unlock(); ieee802154_xmit_complete(hw, skb, false); return 0; } static int hwsim_hw_start(struct ieee802154_hw *hw) { struct hwsim_phy *phy = hw->priv; phy->suspended = false; return 0; } static void hwsim_hw_stop(struct ieee802154_hw *hw) { struct hwsim_phy *phy = hw->priv; phy->suspended = true; } static int hwsim_set_promiscuous_mode(struct ieee802154_hw *hw, const bool on) { enum ieee802154_filtering_level filt_level; struct hwsim_phy *phy = hw->priv; struct hwsim_pib *pib; int ret; if (on) filt_level = IEEE802154_FILTERING_NONE; else filt_level = IEEE802154_FILTERING_4_FRAME_FIELDS; rcu_read_lock(); pib = rcu_dereference(phy->pib); ret = hwsim_update_pib(hw, pib->page, pib->channel, &pib->filt, filt_level); rcu_read_unlock(); return ret; } static const struct ieee802154_ops hwsim_ops = { .owner = THIS_MODULE, .xmit_async = hwsim_hw_xmit, .ed = hwsim_hw_ed, .set_channel = hwsim_hw_channel, .start = hwsim_hw_start, .stop = hwsim_hw_stop, .set_promiscuous_mode = hwsim_set_promiscuous_mode, .set_hw_addr_filt = hwsim_hw_addr_filt, }; static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) { return hwsim_add_one(info, &mac802154hwsim_dev->dev, false); } static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info) { struct hwsim_phy *phy, *tmp; s64 idx = -1; if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]) return -EINVAL; idx = nla_get_u32(info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]); mutex_lock(&hwsim_phys_lock); list_for_each_entry_safe(phy, tmp, &hwsim_phys, list) { if (idx == phy->idx) { hwsim_del(phy); mutex_unlock(&hwsim_phys_lock); return 0; } } mutex_unlock(&hwsim_phys_lock); return -ENODEV; } static int append_radio_msg(struct sk_buff *skb, struct hwsim_phy *phy) { struct nlattr *nl_edges, *nl_edge; struct hwsim_edge_info *einfo; struct hwsim_edge *e; int ret; ret = nla_put_u32(skb, MAC802154_HWSIM_ATTR_RADIO_ID, phy->idx); if (ret < 0) return ret; rcu_read_lock(); if (list_empty(&phy->edges)) { rcu_read_unlock(); return 0; } nl_edges = nla_nest_start_noflag(skb, MAC802154_HWSIM_ATTR_RADIO_EDGES); if (!nl_edges) { rcu_read_unlock(); return -ENOBUFS; } list_for_each_entry_rcu(e, &phy->edges, list) { nl_edge = nla_nest_start_noflag(skb, MAC802154_HWSIM_ATTR_RADIO_EDGE); if (!nl_edge) { rcu_read_unlock(); nla_nest_cancel(skb, nl_edges); return -ENOBUFS; } ret = nla_put_u32(skb, MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID, e->endpoint->idx); if (ret < 0) { rcu_read_unlock(); nla_nest_cancel(skb, nl_edge); nla_nest_cancel(skb, nl_edges); return ret; } einfo = rcu_dereference(e->info); ret = nla_put_u8(skb, MAC802154_HWSIM_EDGE_ATTR_LQI, einfo->lqi); if (ret < 0) { rcu_read_unlock(); nla_nest_cancel(skb, nl_edge); nla_nest_cancel(skb, nl_edges); return ret; } nla_nest_end(skb, nl_edge); } rcu_read_unlock(); nla_nest_end(skb, nl_edges); return 0; } static int hwsim_get_radio(struct sk_buff *skb, struct hwsim_phy *phy, u32 portid, u32 seq, struct netlink_callback *cb, int flags) { void *hdr; int res; hdr = genlmsg_put(skb, portid, seq, &hwsim_genl_family, flags, MAC802154_HWSIM_CMD_GET_RADIO); if (!hdr) return -EMSGSIZE; if (cb) genl_dump_check_consistent(cb, hdr); res = append_radio_msg(skb, phy); if (res < 0) goto out_err; genlmsg_end(skb, hdr); return 0; out_err: genlmsg_cancel(skb, hdr); return res; } static int hwsim_get_radio_nl(struct sk_buff *msg, struct genl_info *info) { struct hwsim_phy *phy; struct sk_buff *skb; int idx, res = -ENODEV; if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]) return -EINVAL; idx = nla_get_u32(info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]); mutex_lock(&hwsim_phys_lock); list_for_each_entry(phy, &hwsim_phys, list) { if (phy->idx != idx) continue; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) { res = -ENOMEM; goto out_err; } res = hwsim_get_radio(skb, phy, info->snd_portid, info->snd_seq, NULL, 0); if (res < 0) { nlmsg_free(skb); goto out_err; } res = genlmsg_reply(skb, info); break; } out_err: mutex_unlock(&hwsim_phys_lock); return res; } static int hwsim_dump_radio_nl(struct sk_buff *skb, struct netlink_callback *cb) { int idx = cb->args[0]; struct hwsim_phy *phy; int res; mutex_lock(&hwsim_phys_lock); if (idx == hwsim_radio_idx) goto done; list_for_each_entry(phy, &hwsim_phys, list) { if (phy->idx < idx) continue; res = hwsim_get_radio(skb, phy, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb, NLM_F_MULTI); if (res < 0) break; idx = phy->idx + 1; } cb->args[0] = idx; done: mutex_unlock(&hwsim_phys_lock); return skb->len; } /* caller need to held hwsim_phys_lock */ static struct hwsim_phy *hwsim_get_radio_by_id(uint32_t idx) { struct hwsim_phy *phy; list_for_each_entry(phy, &hwsim_phys, list) { if (phy->idx == idx) return phy; } return NULL; } static const struct nla_policy hwsim_edge_policy[MAC802154_HWSIM_EDGE_ATTR_MAX + 1] = { [MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID] = { .type = NLA_U32 }, [MAC802154_HWSIM_EDGE_ATTR_LQI] = { .type = NLA_U8 }, }; static struct hwsim_edge *hwsim_alloc_edge(struct hwsim_phy *endpoint, u8 lqi) { struct hwsim_edge_info *einfo; struct hwsim_edge *e; e = kzalloc(sizeof(*e), GFP_KERNEL); if (!e) return NULL; einfo = kzalloc(sizeof(*einfo), GFP_KERNEL); if (!einfo) { kfree(e); return NULL; } einfo->lqi = 0xff; rcu_assign_pointer(e->info, einfo); e->endpoint = endpoint; return e; } static void hwsim_free_edge(struct hwsim_edge *e) { struct hwsim_edge_info *einfo; rcu_read_lock(); einfo = rcu_dereference(e->info); rcu_read_unlock(); kfree_rcu(einfo, rcu); kfree_rcu(e, rcu); } static int hwsim_new_edge_nl(struct sk_buff *msg, struct genl_info *info) { struct nlattr *edge_attrs[MAC802154_HWSIM_EDGE_ATTR_MAX + 1]; struct hwsim_phy *phy_v0, *phy_v1; struct hwsim_edge *e; u32 v0, v1; if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID] || !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE]) return -EINVAL; if (nla_parse_nested_deprecated(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX, info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE], hwsim_edge_policy, NULL)) return -EINVAL; if (!edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID]) return -EINVAL; v0 = nla_get_u32(info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]); v1 = nla_get_u32(edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID]); if (v0 == v1) return -EINVAL; mutex_lock(&hwsim_phys_lock); phy_v0 = hwsim_get_radio_by_id(v0); if (!phy_v0) { mutex_unlock(&hwsim_phys_lock); return -ENOENT; } phy_v1 = hwsim_get_radio_by_id(v1); if (!phy_v1) { mutex_unlock(&hwsim_phys_lock); return -ENOENT; } rcu_read_lock(); list_for_each_entry_rcu(e, &phy_v0->edges, list) { if (e->endpoint->idx == v1) { mutex_unlock(&hwsim_phys_lock); rcu_read_unlock(); return -EEXIST; } } rcu_read_unlock(); e = hwsim_alloc_edge(phy_v1, 0xff); if (!e) { mutex_unlock(&hwsim_phys_lock); return -ENOMEM; } list_add_rcu(&e->list, &phy_v0->edges); /* wait until changes are done under hwsim_phys_lock lock * should prevent of calling this function twice while * edges list has not the changes yet. */ synchronize_rcu(); mutex_unlock(&hwsim_phys_lock); return 0; } static int hwsim_del_edge_nl(struct sk_buff *msg, struct genl_info *info) { struct nlattr *edge_attrs[MAC802154_HWSIM_EDGE_ATTR_MAX + 1]; struct hwsim_phy *phy_v0; struct hwsim_edge *e; u32 v0, v1; if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID] || !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE]) return -EINVAL; if (nla_parse_nested_deprecated(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX, info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE], hwsim_edge_policy, NULL)) return -EINVAL; if (!edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID]) return -EINVAL; v0 = nla_get_u32(info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]); v1 = nla_get_u32(edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID]); mutex_lock(&hwsim_phys_lock); phy_v0 = hwsim_get_radio_by_id(v0); if (!phy_v0) { mutex_unlock(&hwsim_phys_lock); return -ENOENT; } rcu_read_lock(); list_for_each_entry_rcu(e, &phy_v0->edges, list) { if (e->endpoint->idx == v1) { rcu_read_unlock(); list_del_rcu(&e->list); hwsim_free_edge(e); /* same again - wait until list changes are done */ synchronize_rcu(); mutex_unlock(&hwsim_phys_lock); return 0; } } rcu_read_unlock(); mutex_unlock(&hwsim_phys_lock); return -ENOENT; } static int hwsim_set_edge_lqi(struct sk_buff *msg, struct genl_info *info) { struct nlattr *edge_attrs[MAC802154_HWSIM_EDGE_ATTR_MAX + 1]; struct hwsim_edge_info *einfo, *einfo_old; struct hwsim_phy *phy_v0; struct hwsim_edge *e; u32 v0, v1; u8 lqi; if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID] || !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE]) return -EINVAL; if (nla_parse_nested_deprecated(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX, info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE], hwsim_edge_policy, NULL)) return -EINVAL; if (!edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID] || !edge_attrs[MAC802154_HWSIM_EDGE_ATTR_LQI]) return -EINVAL; v0 = nla_get_u32(info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]); v1 = nla_get_u32(edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID]); lqi = nla_get_u8(edge_attrs[MAC802154_HWSIM_EDGE_ATTR_LQI]); mutex_lock(&hwsim_phys_lock); phy_v0 = hwsim_get_radio_by_id(v0); if (!phy_v0) { mutex_unlock(&hwsim_phys_lock); return -ENOENT; } einfo = kzalloc(sizeof(*einfo), GFP_KERNEL); if (!einfo) { mutex_unlock(&hwsim_phys_lock); return -ENOMEM; } rcu_read_lock(); list_for_each_entry_rcu(e, &phy_v0->edges, list) { if (e->endpoint->idx == v1) { einfo->lqi = lqi; einfo_old = rcu_replace_pointer(e->info, einfo, lockdep_is_held(&hwsim_phys_lock)); rcu_read_unlock(); kfree_rcu(einfo_old, rcu); mutex_unlock(&hwsim_phys_lock); return 0; } } rcu_read_unlock(); kfree(einfo); mutex_unlock(&hwsim_phys_lock); return -ENOENT; } /* MAC802154_HWSIM netlink policy */ static const struct nla_policy hwsim_genl_policy[MAC802154_HWSIM_ATTR_MAX + 1] = { [MAC802154_HWSIM_ATTR_RADIO_ID] = { .type = NLA_U32 }, [MAC802154_HWSIM_ATTR_RADIO_EDGE] = { .type = NLA_NESTED }, [MAC802154_HWSIM_ATTR_RADIO_EDGES] = { .type = NLA_NESTED }, }; /* Generic Netlink operations array */ static const struct genl_small_ops hwsim_nl_ops[] = { { .cmd = MAC802154_HWSIM_CMD_NEW_RADIO, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = hwsim_new_radio_nl, .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = MAC802154_HWSIM_CMD_DEL_RADIO, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = hwsim_del_radio_nl, .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = MAC802154_HWSIM_CMD_GET_RADIO, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = hwsim_get_radio_nl, .dumpit = hwsim_dump_radio_nl, }, { .cmd = MAC802154_HWSIM_CMD_NEW_EDGE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = hwsim_new_edge_nl, .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = MAC802154_HWSIM_CMD_DEL_EDGE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = hwsim_del_edge_nl, .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = MAC802154_HWSIM_CMD_SET_EDGE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = hwsim_set_edge_lqi, .flags = GENL_UNS_ADMIN_PERM, }, }; static struct genl_family hwsim_genl_family __ro_after_init = { .name = "MAC802154_HWSIM", .version = 1, .maxattr = MAC802154_HWSIM_ATTR_MAX, .policy = hwsim_genl_policy, .module = THIS_MODULE, .small_ops = hwsim_nl_ops, .n_small_ops = ARRAY_SIZE(hwsim_nl_ops), .resv_start_op = MAC802154_HWSIM_CMD_NEW_EDGE + 1, .mcgrps = hwsim_mcgrps, .n_mcgrps = ARRAY_SIZE(hwsim_mcgrps), }; static void hwsim_mcast_config_msg(struct sk_buff *mcast_skb, struct genl_info *info) { if (info) genl_notify(&hwsim_genl_family, mcast_skb, info, HWSIM_MCGRP_CONFIG, GFP_KERNEL); else genlmsg_multicast(&hwsim_genl_family, mcast_skb, 0, HWSIM_MCGRP_CONFIG, GFP_KERNEL); } static void hwsim_mcast_new_radio(struct genl_info *info, struct hwsim_phy *phy) { struct sk_buff *mcast_skb; void *data; mcast_skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!mcast_skb) return; data = genlmsg_put(mcast_skb, 0, 0, &hwsim_genl_family, 0, MAC802154_HWSIM_CMD_NEW_RADIO); if (!data) goto out_err; if (append_radio_msg(mcast_skb, phy) < 0) goto out_err; genlmsg_end(mcast_skb, data); hwsim_mcast_config_msg(mcast_skb, info); return; out_err: genlmsg_cancel(mcast_skb, data); nlmsg_free(mcast_skb); } static void hwsim_edge_unsubscribe_me(struct hwsim_phy *phy) { struct hwsim_phy *tmp; struct hwsim_edge *e; rcu_read_lock(); /* going to all phy edges and remove phy from it */ list_for_each_entry(tmp, &hwsim_phys, list) { list_for_each_entry_rcu(e, &tmp->edges, list) { if (e->endpoint->idx == phy->idx) { list_del_rcu(&e->list); hwsim_free_edge(e); } } } rcu_read_unlock(); synchronize_rcu(); } static int hwsim_subscribe_all_others(struct hwsim_phy *phy) { struct hwsim_phy *sub; struct hwsim_edge *e; list_for_each_entry(sub, &hwsim_phys, list) { e = hwsim_alloc_edge(sub, 0xff); if (!e) goto me_fail; list_add_rcu(&e->list, &phy->edges); } list_for_each_entry(sub, &hwsim_phys, list) { e = hwsim_alloc_edge(phy, 0xff); if (!e) goto sub_fail; list_add_rcu(&e->list, &sub->edges); } return 0; sub_fail: hwsim_edge_unsubscribe_me(phy); me_fail: rcu_read_lock(); list_for_each_entry_rcu(e, &phy->edges, list) { list_del_rcu(&e->list); hwsim_free_edge(e); } rcu_read_unlock(); return -ENOMEM; } static int hwsim_add_one(struct genl_info *info, struct device *dev, bool init) { struct ieee802154_hw *hw; struct hwsim_phy *phy; struct hwsim_pib *pib; int idx; int err; idx = hwsim_radio_idx++; hw = ieee802154_alloc_hw(sizeof(*phy), &hwsim_ops); if (!hw) return -ENOMEM; phy = hw->priv; phy->hw = hw; /* 868 MHz BPSK 802.15.4-2003 */ hw->phy->supported.channels[0] |= 1; /* 915 MHz BPSK 802.15.4-2003 */ hw->phy->supported.channels[0] |= 0x7fe; /* 2.4 GHz O-QPSK 802.15.4-2003 */ hw->phy->supported.channels[0] |= 0x7FFF800; /* 868 MHz ASK 802.15.4-2006 */ hw->phy->supported.channels[1] |= 1; /* 915 MHz ASK 802.15.4-2006 */ hw->phy->supported.channels[1] |= 0x7fe; /* 868 MHz O-QPSK 802.15.4-2006 */ hw->phy->supported.channels[2] |= 1; /* 915 MHz O-QPSK 802.15.4-2006 */ hw->phy->supported.channels[2] |= 0x7fe; /* 2.4 GHz CSS 802.15.4a-2007 */ hw->phy->supported.channels[3] |= 0x3fff; /* UWB Sub-gigahertz 802.15.4a-2007 */ hw->phy->supported.channels[4] |= 1; /* UWB Low band 802.15.4a-2007 */ hw->phy->supported.channels[4] |= 0x1e; /* UWB High band 802.15.4a-2007 */ hw->phy->supported.channels[4] |= 0xffe0; /* 750 MHz O-QPSK 802.15.4c-2009 */ hw->phy->supported.channels[5] |= 0xf; /* 750 MHz MPSK 802.15.4c-2009 */ hw->phy->supported.channels[5] |= 0xf0; /* 950 MHz BPSK 802.15.4d-2009 */ hw->phy->supported.channels[6] |= 0x3ff; /* 950 MHz GFSK 802.15.4d-2009 */ hw->phy->supported.channels[6] |= 0x3ffc00; ieee802154_random_extended_addr(&hw->phy->perm_extended_addr); /* hwsim phy channel 13 as default */ hw->phy->current_channel = 13; pib = kzalloc(sizeof(*pib), GFP_KERNEL); if (!pib) { err = -ENOMEM; goto err_pib; } pib->channel = 13; pib->filt.short_addr = cpu_to_le16(IEEE802154_ADDR_BROADCAST); pib->filt.pan_id = cpu_to_le16(IEEE802154_PANID_BROADCAST); rcu_assign_pointer(phy->pib, pib); phy->idx = idx; INIT_LIST_HEAD(&phy->edges); hw->flags = IEEE802154_HW_PROMISCUOUS; hw->parent = dev; err = ieee802154_register_hw(hw); if (err) goto err_reg; mutex_lock(&hwsim_phys_lock); if (init) { err = hwsim_subscribe_all_others(phy); if (err < 0) { mutex_unlock(&hwsim_phys_lock); goto err_subscribe; } } list_add_tail(&phy->list, &hwsim_phys); mutex_unlock(&hwsim_phys_lock); hwsim_mcast_new_radio(info, phy); return idx; err_subscribe: ieee802154_unregister_hw(phy->hw); err_reg: kfree(pib); err_pib: ieee802154_free_hw(phy->hw); return err; } static void hwsim_del(struct hwsim_phy *phy) { struct hwsim_pib *pib; struct hwsim_edge *e; hwsim_edge_unsubscribe_me(phy); list_del(&phy->list); rcu_read_lock(); list_for_each_entry_rcu(e, &phy->edges, list) { list_del_rcu(&e->list); hwsim_free_edge(e); } pib = rcu_dereference(phy->pib); rcu_read_unlock(); kfree_rcu(pib, rcu); ieee802154_unregister_hw(phy->hw); ieee802154_free_hw(phy->hw); } static int hwsim_probe(struct platform_device *pdev) { struct hwsim_phy *phy, *tmp; int err, i; for (i = 0; i < 2; i++) { err = hwsim_add_one(NULL, &pdev->dev, true); if (err < 0) goto err_slave; } dev_info(&pdev->dev, "Added 2 mac802154 hwsim hardware radios\n"); return 0; err_slave: mutex_lock(&hwsim_phys_lock); list_for_each_entry_safe(phy, tmp, &hwsim_phys, list) hwsim_del(phy); mutex_unlock(&hwsim_phys_lock); return err; } static void hwsim_remove(struct platform_device *pdev) { struct hwsim_phy *phy, *tmp; mutex_lock(&hwsim_phys_lock); list_for_each_entry_safe(phy, tmp, &hwsim_phys, list) hwsim_del(phy); mutex_unlock(&hwsim_phys_lock); } static struct platform_driver mac802154hwsim_driver = { .probe = hwsim_probe, .remove = hwsim_remove, .driver = { .name = "mac802154_hwsim", }, }; static __init int hwsim_init_module(void) { int rc; rc = genl_register_family(&hwsim_genl_family); if (rc) return rc; mac802154hwsim_dev = platform_device_register_simple("mac802154_hwsim", -1, NULL, 0); if (IS_ERR(mac802154hwsim_dev)) { rc = PTR_ERR(mac802154hwsim_dev); goto platform_dev; } rc = platform_driver_register(&mac802154hwsim_driver); if (rc < 0) goto platform_drv; return 0; platform_drv: platform_device_unregister(mac802154hwsim_dev); platform_dev: genl_unregister_family(&hwsim_genl_family); return rc; } static __exit void hwsim_remove_module(void) { genl_unregister_family(&hwsim_genl_family); platform_driver_unregister(&mac802154hwsim_driver); platform_device_unregister(mac802154hwsim_dev); } module_init(hwsim_init_module); module_exit(hwsim_remove_module); |
| 1506 1363 1505 1503 968 968 1366 1508 170 1507 1504 1507 1508 1506 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * jump label x86 support * * Copyright (C) 2009 Jason Baron <jbaron@redhat.com> * */ #include <linux/jump_label.h> #include <linux/memory.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/list.h> #include <linux/jhash.h> #include <linux/cpu.h> #include <asm/kprobes.h> #include <asm/alternative.h> #include <asm/text-patching.h> #include <asm/insn.h> int arch_jump_entry_size(struct jump_entry *entry) { struct insn insn = {}; insn_decode_kernel(&insn, (void *)jump_entry_code(entry)); BUG_ON(insn.length != 2 && insn.length != 5); return insn.length; } struct jump_label_patch { const void *code; int size; }; static struct jump_label_patch __jump_label_patch(struct jump_entry *entry, enum jump_label_type type) { const void *expect, *code, *nop; const void *addr, *dest; int size; addr = (void *)jump_entry_code(entry); dest = (void *)jump_entry_target(entry); size = arch_jump_entry_size(entry); switch (size) { case JMP8_INSN_SIZE: code = text_gen_insn(JMP8_INSN_OPCODE, addr, dest); nop = x86_nops[size]; break; case JMP32_INSN_SIZE: code = text_gen_insn(JMP32_INSN_OPCODE, addr, dest); nop = x86_nops[size]; break; default: BUG(); } if (type == JUMP_LABEL_JMP) expect = nop; else expect = code; if (memcmp(addr, expect, size)) { /* * The location is not an op that we were expecting. * Something went wrong. Crash the box, as something could be * corrupting the kernel. */ pr_crit("jump_label: Fatal kernel bug, unexpected op at %pS [%p] (%5ph != %5ph)) size:%d type:%d\n", addr, addr, addr, expect, size, type); BUG(); } if (type == JUMP_LABEL_NOP) code = nop; return (struct jump_label_patch){.code = code, .size = size}; } static __always_inline void __jump_label_transform(struct jump_entry *entry, enum jump_label_type type, int init) { const struct jump_label_patch jlp = __jump_label_patch(entry, type); /* * As long as only a single processor is running and the code is still * not marked as RO, text_poke_early() can be used; Checking that * system_state is SYSTEM_BOOTING guarantees it. It will be set to * SYSTEM_SCHEDULING before other cores are awaken and before the * code is write-protected. * * At the time the change is being done, just ignore whether we * are doing nop -> jump or jump -> nop transition, and assume * always nop being the 'currently valid' instruction */ if (init || system_state == SYSTEM_BOOTING) { text_poke_early((void *)jump_entry_code(entry), jlp.code, jlp.size); return; } text_poke_bp((void *)jump_entry_code(entry), jlp.code, jlp.size, NULL); } static void __ref jump_label_transform(struct jump_entry *entry, enum jump_label_type type, int init) { mutex_lock(&text_mutex); __jump_label_transform(entry, type, init); mutex_unlock(&text_mutex); } void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type) { jump_label_transform(entry, type, 0); } bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type) { struct jump_label_patch jlp; if (system_state == SYSTEM_BOOTING) { /* * Fallback to the non-batching mode. */ arch_jump_label_transform(entry, type); return true; } mutex_lock(&text_mutex); jlp = __jump_label_patch(entry, type); text_poke_queue((void *)jump_entry_code(entry), jlp.code, jlp.size, NULL); mutex_unlock(&text_mutex); return true; } void arch_jump_label_transform_apply(void) { mutex_lock(&text_mutex); text_poke_finish(); mutex_unlock(&text_mutex); } |
| 6 3 4 1 4 3 3 3 2 1 1 3 6 6 6 1719 1721 24 23 14 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 | /* Copyright 2011, Siemens AG * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ /* Based on patches from Jon Smirl <jonsmirl@gmail.com> * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 * as published by the Free Software Foundation. * * 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 General Public License for more details. */ /* Jon's code is based on 6lowpan implementation for Contiki which is: * Copyright (c) 2008, Swedish Institute of Computer Science. * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of the Institute nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/ieee802154.h> #include <linux/if_arp.h> #include <net/ipv6.h> #include "6lowpan_i.h" static int open_count; static const struct header_ops lowpan_header_ops = { .create = lowpan_header_create, }; static int lowpan_dev_init(struct net_device *ldev) { netdev_lockdep_set_classes(ldev); return 0; } static int lowpan_open(struct net_device *dev) { if (!open_count) lowpan_rx_init(); open_count++; return 0; } static int lowpan_stop(struct net_device *dev) { open_count--; if (!open_count) lowpan_rx_exit(); return 0; } static int lowpan_neigh_construct(struct net_device *dev, struct neighbour *n) { struct lowpan_802154_neigh *neigh = lowpan_802154_neigh(neighbour_priv(n)); /* default no short_addr is available for a neighbour */ neigh->short_addr = cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC); return 0; } static int lowpan_get_iflink(const struct net_device *dev) { return READ_ONCE(lowpan_802154_dev(dev)->wdev->ifindex); } static const struct net_device_ops lowpan_netdev_ops = { .ndo_init = lowpan_dev_init, .ndo_start_xmit = lowpan_xmit, .ndo_open = lowpan_open, .ndo_stop = lowpan_stop, .ndo_neigh_construct = lowpan_neigh_construct, .ndo_get_iflink = lowpan_get_iflink, }; static void lowpan_setup(struct net_device *ldev) { memset(ldev->broadcast, 0xff, IEEE802154_ADDR_LEN); /* We need an ipv6hdr as minimum len when calling xmit */ ldev->hard_header_len = sizeof(struct ipv6hdr); ldev->flags = IFF_BROADCAST | IFF_MULTICAST; ldev->priv_flags |= IFF_NO_QUEUE; ldev->netdev_ops = &lowpan_netdev_ops; ldev->header_ops = &lowpan_header_ops; ldev->needs_free_netdev = true; ldev->netns_local = true; } static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != IEEE802154_ADDR_LEN) return -EINVAL; } return 0; } static int lowpan_newlink(struct net *src_net, struct net_device *ldev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_device *wdev; int ret; ASSERT_RTNL(); pr_debug("adding new link\n"); if (!tb[IFLA_LINK]) return -EINVAL; /* find and hold wpan device */ wdev = dev_get_by_index(dev_net(ldev), nla_get_u32(tb[IFLA_LINK])); if (!wdev) return -ENODEV; if (wdev->type != ARPHRD_IEEE802154) { dev_put(wdev); return -EINVAL; } if (wdev->ieee802154_ptr->lowpan_dev) { dev_put(wdev); return -EBUSY; } lowpan_802154_dev(ldev)->wdev = wdev; /* Set the lowpan hardware address to the wpan hardware address. */ __dev_addr_set(ldev, wdev->dev_addr, IEEE802154_ADDR_LEN); /* We need headroom for possible wpan_dev_hard_header call and tailroom * for encryption/fcs handling. The lowpan interface will replace * the IPv6 header with 6LoWPAN header. At worst case the 6LoWPAN * header has LOWPAN_IPHC_MAX_HEADER_LEN more bytes than the IPv6 * header. */ ldev->needed_headroom = LOWPAN_IPHC_MAX_HEADER_LEN + wdev->needed_headroom; ldev->needed_tailroom = wdev->needed_tailroom; ldev->neigh_priv_len = sizeof(struct lowpan_802154_neigh); ret = lowpan_register_netdevice(ldev, LOWPAN_LLTYPE_IEEE802154); if (ret < 0) { dev_put(wdev); return ret; } wdev->ieee802154_ptr->lowpan_dev = ldev; return 0; } static void lowpan_dellink(struct net_device *ldev, struct list_head *head) { struct net_device *wdev = lowpan_802154_dev(ldev)->wdev; ASSERT_RTNL(); wdev->ieee802154_ptr->lowpan_dev = NULL; lowpan_unregister_netdevice(ldev); dev_put(wdev); } static struct rtnl_link_ops lowpan_link_ops __read_mostly = { .kind = "lowpan", .priv_size = LOWPAN_PRIV_SIZE(sizeof(struct lowpan_802154_dev)), .setup = lowpan_setup, .newlink = lowpan_newlink, .dellink = lowpan_dellink, .validate = lowpan_validate, }; static inline int __init lowpan_netlink_init(void) { return rtnl_link_register(&lowpan_link_ops); } static inline void lowpan_netlink_fini(void) { rtnl_link_unregister(&lowpan_link_ops); } static int lowpan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct wpan_dev *wpan_dev; if (ndev->type != ARPHRD_IEEE802154) return NOTIFY_DONE; wpan_dev = ndev->ieee802154_ptr; if (!wpan_dev) return NOTIFY_DONE; switch (event) { case NETDEV_UNREGISTER: /* Check if wpan interface is unregistered that we * also delete possible lowpan interfaces which belongs * to the wpan interface. */ if (wpan_dev->lowpan_dev) lowpan_dellink(wpan_dev->lowpan_dev, NULL); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static struct notifier_block lowpan_dev_notifier = { .notifier_call = lowpan_device_event, }; static int __init lowpan_init_module(void) { int err = 0; err = lowpan_net_frag_init(); if (err < 0) goto out; err = lowpan_netlink_init(); if (err < 0) goto out_frag; err = register_netdevice_notifier(&lowpan_dev_notifier); if (err < 0) goto out_pack; return 0; out_pack: lowpan_netlink_fini(); out_frag: lowpan_net_frag_exit(); out: return err; } static void __exit lowpan_cleanup_module(void) { lowpan_netlink_fini(); lowpan_net_frag_exit(); unregister_netdevice_notifier(&lowpan_dev_notifier); } module_init(lowpan_init_module); module_exit(lowpan_cleanup_module); MODULE_DESCRIPTION("IPv6 over Low power Wireless Personal Area Network IEEE 802.15.4 core"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("lowpan"); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * befs.h * * Copyright (C) 2001-2002 Will Dyson <will_dyson@pobox.com> * Copyright (C) 1999 Makoto Kato (m_kato@ga2.so-net.ne.jp) */ #ifndef _LINUX_BEFS_H #define _LINUX_BEFS_H #include "befs_fs_types.h" /* used in debug.c */ #define BEFS_VERSION "0.9.3" typedef u64 befs_blocknr_t; /* * BeFS in memory structures */ struct befs_mount_options { kgid_t gid; kuid_t uid; int use_gid; int use_uid; int debug; char *iocharset; }; struct befs_sb_info { u32 magic1; u32 block_size; u32 block_shift; int byte_order; befs_off_t num_blocks; befs_off_t used_blocks; u32 inode_size; u32 magic2; /* Allocation group information */ u32 blocks_per_ag; u32 ag_shift; u32 num_ags; /* State of the superblock */ u32 flags; /* Journal log entry */ befs_block_run log_blocks; befs_off_t log_start; befs_off_t log_end; befs_inode_addr root_dir; befs_inode_addr indices; u32 magic3; struct befs_mount_options mount_opts; struct nls_table *nls; }; struct befs_inode_info { u32 i_flags; u32 i_type; befs_inode_addr i_inode_num; befs_inode_addr i_parent; befs_inode_addr i_attribute; union { befs_data_stream ds; char symlink[BEFS_SYMLINK_LEN]; } i_data; struct inode vfs_inode; }; enum befs_err { BEFS_OK, BEFS_ERR, BEFS_BAD_INODE, BEFS_BT_END, BEFS_BT_EMPTY, BEFS_BT_MATCH, BEFS_BT_OVERFLOW, BEFS_BT_NOT_FOUND }; /****************************/ /* debug.c */ __printf(2, 3) void befs_error(const struct super_block *sb, const char *fmt, ...); __printf(2, 3) void befs_warning(const struct super_block *sb, const char *fmt, ...); __printf(2, 3) void befs_debug(const struct super_block *sb, const char *fmt, ...); void befs_dump_super_block(const struct super_block *sb, befs_super_block *); void befs_dump_inode(const struct super_block *sb, befs_inode *); void befs_dump_index_entry(const struct super_block *sb, befs_disk_btree_super *); void befs_dump_index_node(const struct super_block *sb, befs_btree_nodehead *); /****************************/ /* Gets a pointer to the private portion of the super_block * structure from the public part */ static inline struct befs_sb_info * BEFS_SB(const struct super_block *super) { return (struct befs_sb_info *) super->s_fs_info; } static inline struct befs_inode_info * BEFS_I(const struct inode *inode) { return container_of(inode, struct befs_inode_info, vfs_inode); } static inline befs_blocknr_t iaddr2blockno(struct super_block *sb, const befs_inode_addr *iaddr) { return ((iaddr->allocation_group << BEFS_SB(sb)->ag_shift) + iaddr->start); } static inline befs_inode_addr blockno2iaddr(struct super_block *sb, befs_blocknr_t blockno) { befs_inode_addr iaddr; iaddr.allocation_group = blockno >> BEFS_SB(sb)->ag_shift; iaddr.start = blockno - (iaddr.allocation_group << BEFS_SB(sb)->ag_shift); iaddr.len = 1; return iaddr; } static inline unsigned int befs_iaddrs_per_block(struct super_block *sb) { return BEFS_SB(sb)->block_size / sizeof(befs_disk_inode_addr); } #include "endian.h" #endif /* _LINUX_BEFS_H */ |
| 22688 5 22676 997 16378 | 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 | // SPDX-License-Identifier: GPL-2.0-only #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/init.h> #include <linux/export.h> #include <linux/timer.h> #include <linux/acpi_pmtmr.h> #include <linux/cpufreq.h> #include <linux/delay.h> #include <linux/clocksource.h> #include <linux/percpu.h> #include <linux/timex.h> #include <linux/static_key.h> #include <linux/static_call.h> #include <asm/hpet.h> #include <asm/timer.h> #include <asm/vgtod.h> #include <asm/time.h> #include <asm/delay.h> #include <asm/hypervisor.h> #include <asm/nmi.h> #include <asm/x86_init.h> #include <asm/geode.h> #include <asm/apic.h> #include <asm/cpu_device_id.h> #include <asm/i8259.h> #include <asm/topology.h> #include <asm/uv/uv.h> unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); unsigned int __read_mostly tsc_khz; EXPORT_SYMBOL(tsc_khz); #define KHZ 1000 /* * TSC can be unstable due to cpufreq or due to unsynced TSCs */ static int __read_mostly tsc_unstable; static unsigned int __initdata tsc_early_khz; static DEFINE_STATIC_KEY_FALSE_RO(__use_tsc); int tsc_clocksource_reliable; static int __read_mostly tsc_force_recalibrate; static struct clocksource_base art_base_clk = { .id = CSID_X86_ART, }; static bool have_art; struct cyc2ns { struct cyc2ns_data data[2]; /* 0 + 2*16 = 32 */ seqcount_latch_t seq; /* 32 + 4 = 36 */ }; /* fits one cacheline */ static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns); static int __init tsc_early_khz_setup(char *buf) { return kstrtouint(buf, 0, &tsc_early_khz); } early_param("tsc_early_khz", tsc_early_khz_setup); __always_inline void __cyc2ns_read(struct cyc2ns_data *data) { int seq, idx; do { seq = this_cpu_read(cyc2ns.seq.seqcount.sequence); idx = seq & 1; data->cyc2ns_offset = this_cpu_read(cyc2ns.data[idx].cyc2ns_offset); data->cyc2ns_mul = this_cpu_read(cyc2ns.data[idx].cyc2ns_mul); data->cyc2ns_shift = this_cpu_read(cyc2ns.data[idx].cyc2ns_shift); } while (unlikely(seq != this_cpu_read(cyc2ns.seq.seqcount.sequence))); } __always_inline void cyc2ns_read_begin(struct cyc2ns_data *data) { preempt_disable_notrace(); __cyc2ns_read(data); } __always_inline void cyc2ns_read_end(void) { preempt_enable_notrace(); } /* * Accelerators for sched_clock() * convert from cycles(64bits) => nanoseconds (64bits) * basic equation: * ns = cycles / (freq / ns_per_sec) * ns = cycles * (ns_per_sec / freq) * ns = cycles * (10^9 / (cpu_khz * 10^3)) * ns = cycles * (10^6 / cpu_khz) * * Then we use scaling math (suggested by george@mvista.com) to get: * ns = cycles * (10^6 * SC / cpu_khz) / SC * ns = cycles * cyc2ns_scale / SC * * And since SC is a constant power of two, we can convert the div * into a shift. The larger SC is, the more accurate the conversion, but * cyc2ns_scale needs to be a 32-bit value so that 32-bit multiplication * (64-bit result) can be used. * * We can use khz divisor instead of mhz to keep a better precision. * (mathieu.desnoyers@polymtl.ca) * * -johnstul@us.ibm.com "math is hard, lets go shopping!" */ static __always_inline unsigned long long __cycles_2_ns(unsigned long long cyc) { struct cyc2ns_data data; unsigned long long ns; __cyc2ns_read(&data); ns = data.cyc2ns_offset; ns += mul_u64_u32_shr(cyc, data.cyc2ns_mul, data.cyc2ns_shift); return ns; } static __always_inline unsigned long long cycles_2_ns(unsigned long long cyc) { unsigned long long ns; preempt_disable_notrace(); ns = __cycles_2_ns(cyc); preempt_enable_notrace(); return ns; } static void __set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now) { unsigned long long ns_now; struct cyc2ns_data data; struct cyc2ns *c2n; ns_now = cycles_2_ns(tsc_now); /* * Compute a new multiplier as per the above comment and ensure our * time function is continuous; see the comment near struct * cyc2ns_data. */ clocks_calc_mult_shift(&data.cyc2ns_mul, &data.cyc2ns_shift, khz, NSEC_PER_MSEC, 0); /* * cyc2ns_shift is exported via arch_perf_update_userpage() where it is * not expected to be greater than 31 due to the original published * conversion algorithm shifting a 32-bit value (now specifies a 64-bit * value) - refer perf_event_mmap_page documentation in perf_event.h. */ if (data.cyc2ns_shift == 32) { data.cyc2ns_shift = 31; data.cyc2ns_mul >>= 1; } data.cyc2ns_offset = ns_now - mul_u64_u32_shr(tsc_now, data.cyc2ns_mul, data.cyc2ns_shift); c2n = per_cpu_ptr(&cyc2ns, cpu); write_seqcount_latch_begin(&c2n->seq); c2n->data[0] = data; write_seqcount_latch(&c2n->seq); c2n->data[1] = data; write_seqcount_latch_end(&c2n->seq); } static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now) { unsigned long flags; local_irq_save(flags); sched_clock_idle_sleep_event(); if (khz) __set_cyc2ns_scale(khz, cpu, tsc_now); sched_clock_idle_wakeup_event(); local_irq_restore(flags); } /* * Initialize cyc2ns for boot cpu */ static void __init cyc2ns_init_boot_cpu(void) { struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns); seqcount_latch_init(&c2n->seq); __set_cyc2ns_scale(tsc_khz, smp_processor_id(), rdtsc()); } /* * Secondary CPUs do not run through tsc_init(), so set up * all the scale factors for all CPUs, assuming the same * speed as the bootup CPU. */ static void __init cyc2ns_init_secondary_cpus(void) { unsigned int cpu, this_cpu = smp_processor_id(); struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns); struct cyc2ns_data *data = c2n->data; for_each_possible_cpu(cpu) { if (cpu != this_cpu) { seqcount_latch_init(&c2n->seq); c2n = per_cpu_ptr(&cyc2ns, cpu); c2n->data[0] = data[0]; c2n->data[1] = data[1]; } } } /* * Scheduler clock - returns current time in nanosec units. */ noinstr u64 native_sched_clock(void) { if (static_branch_likely(&__use_tsc)) { u64 tsc_now = rdtsc(); /* return the value in ns */ return __cycles_2_ns(tsc_now); } /* * Fall back to jiffies if there's no TSC available: * ( But note that we still use it if the TSC is marked * unstable. We do this because unlike Time Of Day, * the scheduler clock tolerates small errors and it's * very important for it to be as fast as the platform * can achieve it. ) */ /* No locking but a rare wrong value is not a big deal: */ return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ); } /* * Generate a sched_clock if you already have a TSC value. */ u64 native_sched_clock_from_tsc(u64 tsc) { return cycles_2_ns(tsc); } /* We need to define a real function for sched_clock, to override the weak default version */ #ifdef CONFIG_PARAVIRT noinstr u64 sched_clock_noinstr(void) { return paravirt_sched_clock(); } bool using_native_sched_clock(void) { return static_call_query(pv_sched_clock) == native_sched_clock; } #else u64 sched_clock_noinstr(void) __attribute__((alias("native_sched_clock"))); bool using_native_sched_clock(void) { return true; } #endif notrace u64 sched_clock(void) { u64 now; preempt_disable_notrace(); now = sched_clock_noinstr(); preempt_enable_notrace(); return now; } int check_tsc_unstable(void) { return tsc_unstable; } EXPORT_SYMBOL_GPL(check_tsc_unstable); #ifdef CONFIG_X86_TSC int __init notsc_setup(char *str) { mark_tsc_unstable("boot parameter notsc"); return 1; } #else /* * disable flag for tsc. Takes effect by clearing the TSC cpu flag * in cpu/common.c */ int __init notsc_setup(char *str) { setup_clear_cpu_cap(X86_FEATURE_TSC); return 1; } #endif __setup("notsc", notsc_setup); static int no_sched_irq_time; static int no_tsc_watchdog; static int tsc_as_watchdog; static int __init tsc_setup(char *str) { if (!strcmp(str, "reliable")) tsc_clocksource_reliable = 1; if (!strncmp(str, "noirqtime", 9)) no_sched_irq_time = 1; if (!strcmp(str, "unstable")) mark_tsc_unstable("boot parameter"); if (!strcmp(str, "nowatchdog")) { no_tsc_watchdog = 1; if (tsc_as_watchdog) pr_alert("%s: Overriding earlier tsc=watchdog with tsc=nowatchdog\n", __func__); tsc_as_watchdog = 0; } if (!strcmp(str, "recalibrate")) tsc_force_recalibrate = 1; if (!strcmp(str, "watchdog")) { if (no_tsc_watchdog) pr_alert("%s: tsc=watchdog overridden by earlier tsc=nowatchdog\n", __func__); else tsc_as_watchdog = 1; } return 1; } __setup("tsc=", tsc_setup); #define MAX_RETRIES 5 #define TSC_DEFAULT_THRESHOLD 0x20000 /* * Read TSC and the reference counters. Take care of any disturbances */ static u64 tsc_read_refs(u64 *p, int hpet) { u64 t1, t2; u64 thresh = tsc_khz ? tsc_khz >> 5 : TSC_DEFAULT_THRESHOLD; int i; for (i = 0; i < MAX_RETRIES; i++) { t1 = get_cycles(); if (hpet) *p = hpet_readl(HPET_COUNTER) & 0xFFFFFFFF; else *p = acpi_pm_read_early(); t2 = get_cycles(); if ((t2 - t1) < thresh) return t2; } return ULLONG_MAX; } /* * Calculate the TSC frequency from HPET reference */ static unsigned long calc_hpet_ref(u64 deltatsc, u64 hpet1, u64 hpet2) { u64 tmp; if (hpet2 < hpet1) hpet2 += 0x100000000ULL; hpet2 -= hpet1; tmp = ((u64)hpet2 * hpet_readl(HPET_PERIOD)); do_div(tmp, 1000000); deltatsc = div64_u64(deltatsc, tmp); return (unsigned long) deltatsc; } /* * Calculate the TSC frequency from PMTimer reference */ static unsigned long calc_pmtimer_ref(u64 deltatsc, u64 pm1, u64 pm2) { u64 tmp; if (!pm1 && !pm2) return ULONG_MAX; if (pm2 < pm1) pm2 += (u64)ACPI_PM_OVRRUN; pm2 -= pm1; tmp = pm2 * 1000000000LL; do_div(tmp, PMTMR_TICKS_PER_SEC); do_div(deltatsc, tmp); return (unsigned long) deltatsc; } #define CAL_MS 10 #define CAL_LATCH (PIT_TICK_RATE / (1000 / CAL_MS)) #define CAL_PIT_LOOPS 1000 #define CAL2_MS 50 #define CAL2_LATCH (PIT_TICK_RATE / (1000 / CAL2_MS)) #define CAL2_PIT_LOOPS 5000 /* * Try to calibrate the TSC against the Programmable * Interrupt Timer and return the frequency of the TSC * in kHz. * * Return ULONG_MAX on failure to calibrate. */ static unsigned long pit_calibrate_tsc(u32 latch, unsigned long ms, int loopmin) { u64 tsc, t1, t2, delta; unsigned long tscmin, tscmax; int pitcnt; if (!has_legacy_pic()) { /* * Relies on tsc_early_delay_calibrate() to have given us semi * usable udelay(), wait for the same 50ms we would have with * the PIT loop below. */ udelay(10 * USEC_PER_MSEC); udelay(10 * USEC_PER_MSEC); udelay(10 * USEC_PER_MSEC); udelay(10 * USEC_PER_MSEC); udelay(10 * USEC_PER_MSEC); return ULONG_MAX; } /* Set the Gate high, disable speaker */ outb((inb(0x61) & ~0x02) | 0x01, 0x61); /* * Setup CTC channel 2* for mode 0, (interrupt on terminal * count mode), binary count. Set the latch register to 50ms * (LSB then MSB) to begin countdown. */ outb(0xb0, 0x43); outb(latch & 0xff, 0x42); outb(latch >> 8, 0x42); tsc = t1 = t2 = get_cycles(); pitcnt = 0; tscmax = 0; tscmin = ULONG_MAX; while ((inb(0x61) & 0x20) == 0) { t2 = get_cycles(); delta = t2 - tsc; tsc = t2; if ((unsigned long) delta < tscmin) tscmin = (unsigned int) delta; if ((unsigned long) delta > tscmax) tscmax = (unsigned int) delta; pitcnt++; } /* * Sanity checks: * * If we were not able to read the PIT more than loopmin * times, then we have been hit by a massive SMI * * If the maximum is 10 times larger than the minimum, * then we got hit by an SMI as well. */ if (pitcnt < loopmin || tscmax > 10 * tscmin) return ULONG_MAX; /* Calculate the PIT value */ delta = t2 - t1; do_div(delta, ms); return delta; } /* * This reads the current MSB of the PIT counter, and * checks if we are running on sufficiently fast and * non-virtualized hardware. * * Our expectations are: * * - the PIT is running at roughly 1.19MHz * * - each IO is going to take about 1us on real hardware, * but we allow it to be much faster (by a factor of 10) or * _slightly_ slower (ie we allow up to a 2us read+counter * update - anything else implies a unacceptably slow CPU * or PIT for the fast calibration to work. * * - with 256 PIT ticks to read the value, we have 214us to * see the same MSB (and overhead like doing a single TSC * read per MSB value etc). * * - We're doing 2 reads per loop (LSB, MSB), and we expect * them each to take about a microsecond on real hardware. * So we expect a count value of around 100. But we'll be * generous, and accept anything over 50. * * - if the PIT is stuck, and we see *many* more reads, we * return early (and the next caller of pit_expect_msb() * then consider it a failure when they don't see the * next expected value). * * These expectations mean that we know that we have seen the * transition from one expected value to another with a fairly * high accuracy, and we didn't miss any events. We can thus * use the TSC value at the transitions to calculate a pretty * good value for the TSC frequency. */ static inline int pit_verify_msb(unsigned char val) { /* Ignore LSB */ inb(0x42); return inb(0x42) == val; } static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap) { int count; u64 tsc = 0, prev_tsc = 0; for (count = 0; count < 50000; count++) { if (!pit_verify_msb(val)) break; prev_tsc = tsc; tsc = get_cycles(); } *deltap = get_cycles() - prev_tsc; *tscp = tsc; /* * We require _some_ success, but the quality control * will be based on the error terms on the TSC values. */ return count > 5; } /* * How many MSB values do we want to see? We aim for * a maximum error rate of 500ppm (in practice the * real error is much smaller), but refuse to spend * more than 50ms on it. */ #define MAX_QUICK_PIT_MS 50 #define MAX_QUICK_PIT_ITERATIONS (MAX_QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256) static unsigned long quick_pit_calibrate(void) { int i; u64 tsc, delta; unsigned long d1, d2; if (!has_legacy_pic()) return 0; /* Set the Gate high, disable speaker */ outb((inb(0x61) & ~0x02) | 0x01, 0x61); /* * Counter 2, mode 0 (one-shot), binary count * * NOTE! Mode 2 decrements by two (and then the * output is flipped each time, giving the same * final output frequency as a decrement-by-one), * so mode 0 is much better when looking at the * individual counts. */ outb(0xb0, 0x43); /* Start at 0xffff */ outb(0xff, 0x42); outb(0xff, 0x42); /* * The PIT starts counting at the next edge, so we * need to delay for a microsecond. The easiest way * to do that is to just read back the 16-bit counter * once from the PIT. */ pit_verify_msb(0); if (pit_expect_msb(0xff, &tsc, &d1)) { for (i = 1; i <= MAX_QUICK_PIT_ITERATIONS; i++) { if (!pit_expect_msb(0xff-i, &delta, &d2)) break; delta -= tsc; /* * Extrapolate the error and fail fast if the error will * never be below 500 ppm. */ if (i == 1 && d1 + d2 >= (delta * MAX_QUICK_PIT_ITERATIONS) >> 11) return 0; /* * Iterate until the error is less than 500 ppm */ if (d1+d2 >= delta >> 11) continue; /* * Check the PIT one more time to verify that * all TSC reads were stable wrt the PIT. * * This also guarantees serialization of the * last cycle read ('d2') in pit_expect_msb. */ if (!pit_verify_msb(0xfe - i)) break; goto success; } } pr_info("Fast TSC calibration failed\n"); return 0; success: /* * Ok, if we get here, then we've seen the * MSB of the PIT decrement 'i' times, and the * error has shrunk to less than 500 ppm. * * As a result, we can depend on there not being * any odd delays anywhere, and the TSC reads are * reliable (within the error). * * kHz = ticks / time-in-seconds / 1000; * kHz = (t2 - t1) / (I * 256 / PIT_TICK_RATE) / 1000 * kHz = ((t2 - t1) * PIT_TICK_RATE) / (I * 256 * 1000) */ delta *= PIT_TICK_RATE; do_div(delta, i*256*1000); pr_info("Fast TSC calibration using PIT\n"); return delta; } /** * native_calibrate_tsc - determine TSC frequency * Determine TSC frequency via CPUID, else return 0. */ unsigned long native_calibrate_tsc(void) { unsigned int eax_denominator, ebx_numerator, ecx_hz, edx; unsigned int crystal_khz; if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 0; if (boot_cpu_data.cpuid_level < 0x15) return 0; eax_denominator = ebx_numerator = ecx_hz = edx = 0; /* CPUID 15H TSC/Crystal ratio, plus optionally Crystal Hz */ cpuid(0x15, &eax_denominator, &ebx_numerator, &ecx_hz, &edx); if (ebx_numerator == 0 || eax_denominator == 0) return 0; crystal_khz = ecx_hz / 1000; /* * Denverton SoCs don't report crystal clock, and also don't support * CPUID.0x16 for the calculation below, so hardcode the 25MHz crystal * clock. */ if (crystal_khz == 0 && boot_cpu_data.x86_vfm == INTEL_ATOM_GOLDMONT_D) crystal_khz = 25000; /* * TSC frequency reported directly by CPUID is a "hardware reported" * frequency and is the most accurate one so far we have. This * is considered a known frequency. */ if (crystal_khz != 0) setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); /* * Some Intel SoCs like Skylake and Kabylake don't report the crystal * clock, but we can easily calculate it to a high degree of accuracy * by considering the crystal ratio and the CPU speed. */ if (crystal_khz == 0 && boot_cpu_data.cpuid_level >= 0x16) { unsigned int eax_base_mhz, ebx, ecx, edx; cpuid(0x16, &eax_base_mhz, &ebx, &ecx, &edx); crystal_khz = eax_base_mhz * 1000 * eax_denominator / ebx_numerator; } if (crystal_khz == 0) return 0; /* * For Atom SoCs TSC is the only reliable clocksource. * Mark TSC reliable so no watchdog on it. */ if (boot_cpu_data.x86_vfm == INTEL_ATOM_GOLDMONT) setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); #ifdef CONFIG_X86_LOCAL_APIC /* * The local APIC appears to be fed by the core crystal clock * (which sounds entirely sensible). We can set the global * lapic_timer_period here to avoid having to calibrate the APIC * timer later. */ lapic_timer_period = crystal_khz * 1000 / HZ; #endif return crystal_khz * ebx_numerator / eax_denominator; } static unsigned long cpu_khz_from_cpuid(void) { unsigned int eax_base_mhz, ebx_max_mhz, ecx_bus_mhz, edx; if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 0; if (boot_cpu_data.cpuid_level < 0x16) return 0; eax_base_mhz = ebx_max_mhz = ecx_bus_mhz = edx = 0; cpuid(0x16, &eax_base_mhz, &ebx_max_mhz, &ecx_bus_mhz, &edx); return eax_base_mhz * 1000; } /* * calibrate cpu using pit, hpet, and ptimer methods. They are available * later in boot after acpi is initialized. */ static unsigned long pit_hpet_ptimer_calibrate_cpu(void) { u64 tsc1, tsc2, delta, ref1, ref2; unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX; unsigned long flags, latch, ms; int hpet = is_hpet_enabled(), i, loopmin; /* * Run 5 calibration loops to get the lowest frequency value * (the best estimate). We use two different calibration modes * here: * * 1) PIT loop. We set the PIT Channel 2 to oneshot mode and * load a timeout of 50ms. We read the time right after we * started the timer and wait until the PIT count down reaches * zero. In each wait loop iteration we read the TSC and check * the delta to the previous read. We keep track of the min * and max values of that delta. The delta is mostly defined * by the IO time of the PIT access, so we can detect when * any disturbance happened between the two reads. If the * maximum time is significantly larger than the minimum time, * then we discard the result and have another try. * * 2) Reference counter. If available we use the HPET or the * PMTIMER as a reference to check the sanity of that value. * We use separate TSC readouts and check inside of the * reference read for any possible disturbance. We discard * disturbed values here as well. We do that around the PIT * calibration delay loop as we have to wait for a certain * amount of time anyway. */ /* Preset PIT loop values */ latch = CAL_LATCH; ms = CAL_MS; loopmin = CAL_PIT_LOOPS; for (i = 0; i < 3; i++) { unsigned long tsc_pit_khz; /* * Read the start value and the reference count of * hpet/pmtimer when available. Then do the PIT * calibration, which will take at least 50ms, and * read the end value. */ local_irq_save(flags); tsc1 = tsc_read_refs(&ref1, hpet); tsc_pit_khz = pit_calibrate_tsc(latch, ms, loopmin); tsc2 = tsc_read_refs(&ref2, hpet); local_irq_restore(flags); /* Pick the lowest PIT TSC calibration so far */ tsc_pit_min = min(tsc_pit_min, tsc_pit_khz); /* hpet or pmtimer available ? */ if (ref1 == ref2) continue; /* Check, whether the sampling was disturbed */ if (tsc1 == ULLONG_MAX || tsc2 == ULLONG_MAX) continue; tsc2 = (tsc2 - tsc1) * 1000000LL; if (hpet) tsc2 = calc_hpet_ref(tsc2, ref1, ref2); else tsc2 = calc_pmtimer_ref(tsc2, ref1, ref2); tsc_ref_min = min(tsc_ref_min, (unsigned long) tsc2); /* Check the reference deviation */ delta = ((u64) tsc_pit_min) * 100; do_div(delta, tsc_ref_min); /* * If both calibration results are inside a 10% window * then we can be sure, that the calibration * succeeded. We break out of the loop right away. We * use the reference value, as it is more precise. */ if (delta >= 90 && delta <= 110) { pr_info("PIT calibration matches %s. %d loops\n", hpet ? "HPET" : "PMTIMER", i + 1); return tsc_ref_min; } /* * Check whether PIT failed more than once. This * happens in virtualized environments. We need to * give the virtual PC a slightly longer timeframe for * the HPET/PMTIMER to make the result precise. */ if (i == 1 && tsc_pit_min == ULONG_MAX) { latch = CAL2_LATCH; ms = CAL2_MS; loopmin = CAL2_PIT_LOOPS; } } /* * Now check the results. */ if (tsc_pit_min == ULONG_MAX) { /* PIT gave no useful value */ pr_warn("Unable to calibrate against PIT\n"); /* We don't have an alternative source, disable TSC */ if (!hpet && !ref1 && !ref2) { pr_notice("No reference (HPET/PMTIMER) available\n"); return 0; } /* The alternative source failed as well, disable TSC */ if (tsc_ref_min == ULONG_MAX) { pr_warn("HPET/PMTIMER calibration failed\n"); return 0; } /* Use the alternative source */ pr_info("using %s reference calibration\n", hpet ? "HPET" : "PMTIMER"); return tsc_ref_min; } /* We don't have an alternative source, use the PIT calibration value */ if (!hpet && !ref1 && !ref2) { pr_info("Using PIT calibration value\n"); return tsc_pit_min; } /* The alternative source failed, use the PIT calibration value */ if (tsc_ref_min == ULONG_MAX) { pr_warn("HPET/PMTIMER calibration failed. Using PIT calibration.\n"); return tsc_pit_min; } /* * The calibration values differ too much. In doubt, we use * the PIT value as we know that there are PMTIMERs around * running at double speed. At least we let the user know: */ pr_warn("PIT calibration deviates from %s: %lu %lu\n", hpet ? "HPET" : "PMTIMER", tsc_pit_min, tsc_ref_min); pr_info("Using PIT calibration value\n"); return tsc_pit_min; } /** * native_calibrate_cpu_early - can calibrate the cpu early in boot */ unsigned long native_calibrate_cpu_early(void) { unsigned long flags, fast_calibrate = cpu_khz_from_cpuid(); if (!fast_calibrate) fast_calibrate = cpu_khz_from_msr(); if (!fast_calibrate) { local_irq_save(flags); fast_calibrate = quick_pit_calibrate(); local_irq_restore(flags); } return fast_calibrate; } /** * native_calibrate_cpu - calibrate the cpu */ static unsigned long native_calibrate_cpu(void) { unsigned long tsc_freq = native_calibrate_cpu_early(); if (!tsc_freq) tsc_freq = pit_hpet_ptimer_calibrate_cpu(); return tsc_freq; } void recalibrate_cpu_khz(void) { #ifndef CONFIG_SMP unsigned long cpu_khz_old = cpu_khz; if (!boot_cpu_has(X86_FEATURE_TSC)) return; cpu_khz = x86_platform.calibrate_cpu(); tsc_khz = x86_platform.calibrate_tsc(); if (tsc_khz == 0) tsc_khz = cpu_khz; else if (abs(cpu_khz - tsc_khz) * 10 > tsc_khz) cpu_khz = tsc_khz; cpu_data(0).loops_per_jiffy = cpufreq_scale(cpu_data(0).loops_per_jiffy, cpu_khz_old, cpu_khz); #endif } EXPORT_SYMBOL_GPL(recalibrate_cpu_khz); static unsigned long long cyc2ns_suspend; void tsc_save_sched_clock_state(void) { if (!sched_clock_stable()) return; cyc2ns_suspend = sched_clock(); } /* * Even on processors with invariant TSC, TSC gets reset in some the * ACPI system sleep states. And in some systems BIOS seem to reinit TSC to * arbitrary value (still sync'd across cpu's) during resume from such sleep * states. To cope up with this, recompute the cyc2ns_offset for each cpu so * that sched_clock() continues from the point where it was left off during * suspend. */ void tsc_restore_sched_clock_state(void) { unsigned long long offset; unsigned long flags; int cpu; if (!sched_clock_stable()) return; local_irq_save(flags); /* * We're coming out of suspend, there's no concurrency yet; don't * bother being nice about the RCU stuff, just write to both * data fields. */ this_cpu_write(cyc2ns.data[0].cyc2ns_offset, 0); this_cpu_write(cyc2ns.data[1].cyc2ns_offset, 0); offset = cyc2ns_suspend - sched_clock(); for_each_possible_cpu(cpu) { per_cpu(cyc2ns.data[0].cyc2ns_offset, cpu) = offset; per_cpu(cyc2ns.data[1].cyc2ns_offset, cpu) = offset; } local_irq_restore(flags); } #ifdef CONFIG_CPU_FREQ /* * Frequency scaling support. Adjust the TSC based timer when the CPU frequency * changes. * * NOTE: On SMP the situation is not fixable in general, so simply mark the TSC * as unstable and give up in those cases. * * Should fix up last_tsc too. Currently gettimeofday in the * first tick after the change will be slightly wrong. */ static unsigned int ref_freq; static unsigned long loops_per_jiffy_ref; static unsigned long tsc_khz_ref; static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data) { struct cpufreq_freqs *freq = data; if (num_online_cpus() > 1) { mark_tsc_unstable("cpufreq changes on SMP"); return 0; } if (!ref_freq) { ref_freq = freq->old; loops_per_jiffy_ref = boot_cpu_data.loops_per_jiffy; tsc_khz_ref = tsc_khz; } if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) || (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) { boot_cpu_data.loops_per_jiffy = cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new); tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new); if (!(freq->flags & CPUFREQ_CONST_LOOPS)) mark_tsc_unstable("cpufreq changes"); set_cyc2ns_scale(tsc_khz, freq->policy->cpu, rdtsc()); } return 0; } static struct notifier_block time_cpufreq_notifier_block = { .notifier_call = time_cpufreq_notifier }; static int __init cpufreq_register_tsc_scaling(void) { if (!boot_cpu_has(X86_FEATURE_TSC)) return 0; if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) return 0; cpufreq_register_notifier(&time_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); return 0; } core_initcall(cpufreq_register_tsc_scaling); #endif /* CONFIG_CPU_FREQ */ #define ART_CPUID_LEAF (0x15) #define ART_MIN_DENOMINATOR (1) /* * If ART is present detect the numerator:denominator to convert to TSC */ static void __init detect_art(void) { unsigned int unused; if (boot_cpu_data.cpuid_level < ART_CPUID_LEAF) return; /* * Don't enable ART in a VM, non-stop TSC and TSC_ADJUST required, * and the TSC counter resets must not occur asynchronously. */ if (boot_cpu_has(X86_FEATURE_HYPERVISOR) || !boot_cpu_has(X86_FEATURE_NONSTOP_TSC) || !boot_cpu_has(X86_FEATURE_TSC_ADJUST) || tsc_async_resets) return; cpuid(ART_CPUID_LEAF, &art_base_clk.denominator, &art_base_clk.numerator, &art_base_clk.freq_khz, &unused); art_base_clk.freq_khz /= KHZ; if (art_base_clk.denominator < ART_MIN_DENOMINATOR) return; rdmsrl(MSR_IA32_TSC_ADJUST, art_base_clk.offset); /* Make this sticky over multiple CPU init calls */ setup_force_cpu_cap(X86_FEATURE_ART); } /* clocksource code */ static void tsc_resume(struct clocksource *cs) { tsc_verify_tsc_adjust(true); } /* * We used to compare the TSC to the cycle_last value in the clocksource * structure to avoid a nasty time-warp. This can be observed in a * very small window right after one CPU updated cycle_last under * xtime/vsyscall_gtod lock and the other CPU reads a TSC value which * is smaller than the cycle_last reference value due to a TSC which * is slightly behind. This delta is nowhere else observable, but in * that case it results in a forward time jump in the range of hours * due to the unsigned delta calculation of the time keeping core * code, which is necessary to support wrapping clocksources like pm * timer. * * This sanity check is now done in the core timekeeping code. * checking the result of read_tsc() - cycle_last for being negative. * That works because CLOCKSOURCE_MASK(64) does not mask out any bit. */ static u64 read_tsc(struct clocksource *cs) { return (u64)rdtsc_ordered(); } static void tsc_cs_mark_unstable(struct clocksource *cs) { if (tsc_unstable) return; tsc_unstable = 1; if (using_native_sched_clock()) clear_sched_clock_stable(); disable_sched_clock_irqtime(); pr_info("Marking TSC unstable due to clocksource watchdog\n"); } static void tsc_cs_tick_stable(struct clocksource *cs) { if (tsc_unstable) return; if (using_native_sched_clock()) sched_clock_tick_stable(); } static int tsc_cs_enable(struct clocksource *cs) { vclocks_set_used(VDSO_CLOCKMODE_TSC); return 0; } /* * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc() */ static struct clocksource clocksource_tsc_early = { .name = "tsc-early", .rating = 299, .uncertainty_margin = 32 * NSEC_PER_MSEC, .read = read_tsc, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_MUST_VERIFY, .id = CSID_X86_TSC_EARLY, .vdso_clock_mode = VDSO_CLOCKMODE_TSC, .enable = tsc_cs_enable, .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, .tick_stable = tsc_cs_tick_stable, .list = LIST_HEAD_INIT(clocksource_tsc_early.list), }; /* * Must mark VALID_FOR_HRES early such that when we unregister tsc_early * this one will immediately take over. We will only register if TSC has * been found good. */ static struct clocksource clocksource_tsc = { .name = "tsc", .rating = 300, .read = read_tsc, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_MUST_VERIFY | CLOCK_SOURCE_VERIFY_PERCPU, .id = CSID_X86_TSC, .vdso_clock_mode = VDSO_CLOCKMODE_TSC, .enable = tsc_cs_enable, .resume = tsc_resume, .mark_unstable = tsc_cs_mark_unstable, .tick_stable = tsc_cs_tick_stable, .list = LIST_HEAD_INIT(clocksource_tsc.list), }; void mark_tsc_unstable(char *reason) { if (tsc_unstable) return; tsc_unstable = 1; if (using_native_sched_clock()) clear_sched_clock_stable(); disable_sched_clock_irqtime(); pr_info("Marking TSC unstable due to %s\n", reason); clocksource_mark_unstable(&clocksource_tsc_early); clocksource_mark_unstable(&clocksource_tsc); } EXPORT_SYMBOL_GPL(mark_tsc_unstable); static void __init tsc_disable_clocksource_watchdog(void) { clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY; clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY; } bool tsc_clocksource_watchdog_disabled(void) { return !(clocksource_tsc.flags & CLOCK_SOURCE_MUST_VERIFY) && tsc_as_watchdog && !no_tsc_watchdog; } static void __init check_system_tsc_reliable(void) { #if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC) if (is_geode_lx()) { /* RTSC counts during suspend */ #define RTSC_SUSP 0x100 unsigned long res_low, res_high; rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high); /* Geode_LX - the OLPC CPU has a very reliable TSC */ if (res_low & RTSC_SUSP) tsc_clocksource_reliable = 1; } #endif if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) tsc_clocksource_reliable = 1; /* * Disable the clocksource watchdog when the system has: * - TSC running at constant frequency * - TSC which does not stop in C-States * - the TSC_ADJUST register which allows to detect even minimal * modifications * - not more than four packages */ if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC) && boot_cpu_has(X86_FEATURE_NONSTOP_TSC) && boot_cpu_has(X86_FEATURE_TSC_ADJUST) && topology_max_packages() <= 4) tsc_disable_clocksource_watchdog(); } /* * Make an educated guess if the TSC is trustworthy and synchronized * over all CPUs. */ int unsynchronized_tsc(void) { if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_unstable) return 1; #ifdef CONFIG_SMP if (apic_is_clustered_box()) return 1; #endif if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) return 0; if (tsc_clocksource_reliable) return 0; /* * Intel systems are normally all synchronized. * Exceptions must mark TSC as unstable: */ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) { /* assume multi socket systems are not synchronized: */ if (topology_max_packages() > 1) return 1; } return 0; } static void tsc_refine_calibration_work(struct work_struct *work); static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work); /** * tsc_refine_calibration_work - Further refine tsc freq calibration * @work: ignored. * * This functions uses delayed work over a period of a * second to further refine the TSC freq value. Since this is * timer based, instead of loop based, we don't block the boot * process while this longer calibration is done. * * If there are any calibration anomalies (too many SMIs, etc), * or the refined calibration is off by 1% of the fast early * calibration, we throw out the new calibration and use the * early calibration. */ static void tsc_refine_calibration_work(struct work_struct *work) { static u64 tsc_start = ULLONG_MAX, ref_start; static int hpet; u64 tsc_stop, ref_stop, delta; unsigned long freq; int cpu; /* Don't bother refining TSC on unstable systems */ if (tsc_unstable) goto unreg; /* * Since the work is started early in boot, we may be * delayed the first time we expire. So set the workqueue * again once we know timers are working. */ if (tsc_start == ULLONG_MAX) { restart: /* * Only set hpet once, to avoid mixing hardware * if the hpet becomes enabled later. */ hpet = is_hpet_enabled(); tsc_start = tsc_read_refs(&ref_start, hpet); schedule_delayed_work(&tsc_irqwork, HZ); return; } tsc_stop = tsc_read_refs(&ref_stop, hpet); /* hpet or pmtimer available ? */ if (ref_start == ref_stop) goto out; /* Check, whether the sampling was disturbed */ if (tsc_stop == ULLONG_MAX) goto restart; delta = tsc_stop - tsc_start; delta *= 1000000LL; if (hpet) freq = calc_hpet_ref(delta, ref_start, ref_stop); else freq = calc_pmtimer_ref(delta, ref_start, ref_stop); /* Will hit this only if tsc_force_recalibrate has been set */ if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) { /* Warn if the deviation exceeds 500 ppm */ if (abs(tsc_khz - freq) > (tsc_khz >> 11)) { pr_warn("Warning: TSC freq calibrated by CPUID/MSR differs from what is calibrated by HW timer, please check with vendor!!\n"); pr_info("Previous calibrated TSC freq:\t %lu.%03lu MHz\n", (unsigned long)tsc_khz / 1000, (unsigned long)tsc_khz % 1000); } pr_info("TSC freq recalibrated by [%s]:\t %lu.%03lu MHz\n", hpet ? "HPET" : "PM_TIMER", (unsigned long)freq / 1000, (unsigned long)freq % 1000); return; } /* Make sure we're within 1% */ if (abs(tsc_khz - freq) > tsc_khz/100) goto out; tsc_khz = freq; pr_info("Refined TSC clocksource calibration: %lu.%03lu MHz\n", (unsigned long)tsc_khz / 1000, (unsigned long)tsc_khz % 1000); /* Inform the TSC deadline clockevent devices about the recalibration */ lapic_update_tsc_freq(); /* Update the sched_clock() rate to match the clocksource one */ for_each_possible_cpu(cpu) set_cyc2ns_scale(tsc_khz, cpu, tsc_stop); out: if (tsc_unstable) goto unreg; if (boot_cpu_has(X86_FEATURE_ART)) { have_art = true; clocksource_tsc.base = &art_base_clk; } clocksource_register_khz(&clocksource_tsc, tsc_khz); unreg: clocksource_unregister(&clocksource_tsc_early); } static int __init init_tsc_clocksource(void) { if (!boot_cpu_has(X86_FEATURE_TSC) || !tsc_khz) return 0; if (tsc_unstable) { clocksource_unregister(&clocksource_tsc_early); return 0; } if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3)) clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP; /* * When TSC frequency is known (retrieved via MSR or CPUID), we skip * the refined calibration and directly register it as a clocksource. */ if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) { if (boot_cpu_has(X86_FEATURE_ART)) { have_art = true; clocksource_tsc.base = &art_base_clk; } clocksource_register_khz(&clocksource_tsc, tsc_khz); clocksource_unregister(&clocksource_tsc_early); if (!tsc_force_recalibrate) return 0; } schedule_delayed_work(&tsc_irqwork, 0); return 0; } /* * We use device_initcall here, to ensure we run after the hpet * is fully initialized, which may occur at fs_initcall time. */ device_initcall(init_tsc_clocksource); static bool __init determine_cpu_tsc_frequencies(bool early) { /* Make sure that cpu and tsc are not already calibrated */ WARN_ON(cpu_khz || tsc_khz); if (early) { cpu_khz = x86_platform.calibrate_cpu(); if (tsc_early_khz) { tsc_khz = tsc_early_khz; } else { tsc_khz = x86_platform.calibrate_tsc(); clocksource_tsc.freq_khz = tsc_khz; } } else { /* We should not be here with non-native cpu calibration */ WARN_ON(x86_platform.calibrate_cpu != native_calibrate_cpu); cpu_khz = pit_hpet_ptimer_calibrate_cpu(); } /* * Trust non-zero tsc_khz as authoritative, * and use it to sanity check cpu_khz, * which will be off if system timer is off. */ if (tsc_khz == 0) tsc_khz = cpu_khz; else if (abs(cpu_khz - tsc_khz) * 10 > tsc_khz) cpu_khz = tsc_khz; if (tsc_khz == 0) return false; pr_info("Detected %lu.%03lu MHz processor\n", (unsigned long)cpu_khz / KHZ, (unsigned long)cpu_khz % KHZ); if (cpu_khz != tsc_khz) { pr_info("Detected %lu.%03lu MHz TSC", (unsigned long)tsc_khz / KHZ, (unsigned long)tsc_khz % KHZ); } return true; } static unsigned long __init get_loops_per_jiffy(void) { u64 lpj = (u64)tsc_khz * KHZ; do_div(lpj, HZ); return lpj; } static void __init tsc_enable_sched_clock(void) { loops_per_jiffy = get_loops_per_jiffy(); use_tsc_delay(); /* Sanitize TSC ADJUST before cyc2ns gets initialized */ tsc_store_and_check_tsc_adjust(true); cyc2ns_init_boot_cpu(); static_branch_enable(&__use_tsc); } void __init tsc_early_init(void) { if (!boot_cpu_has(X86_FEATURE_TSC)) return; /* Don't change UV TSC multi-chassis synchronization */ if (is_early_uv_system()) return; if (!determine_cpu_tsc_frequencies(true)) return; tsc_enable_sched_clock(); } void __init tsc_init(void) { if (!cpu_feature_enabled(X86_FEATURE_TSC)) { setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; } /* * native_calibrate_cpu_early can only calibrate using methods that are * available early in boot. */ if (x86_platform.calibrate_cpu == native_calibrate_cpu_early) x86_platform.calibrate_cpu = native_calibrate_cpu; if (!tsc_khz) { /* We failed to determine frequencies earlier, try again */ if (!determine_cpu_tsc_frequencies(false)) { mark_tsc_unstable("could not calculate TSC khz"); setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; } tsc_enable_sched_clock(); } cyc2ns_init_secondary_cpus(); if (!no_sched_irq_time) enable_sched_clock_irqtime(); lpj_fine = get_loops_per_jiffy(); check_system_tsc_reliable(); if (unsynchronized_tsc()) { mark_tsc_unstable("TSCs unsynchronized"); return; } if (tsc_clocksource_reliable || no_tsc_watchdog) tsc_disable_clocksource_watchdog(); clocksource_register_khz(&clocksource_tsc_early, tsc_khz); detect_art(); } #ifdef CONFIG_SMP /* * Check whether existing calibration data can be reused. */ unsigned long calibrate_delay_is_known(void) { int sibling, cpu = smp_processor_id(); int constant_tsc = cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC); const struct cpumask *mask = topology_core_cpumask(cpu); /* * If TSC has constant frequency and TSC is synchronized across * sockets then reuse CPU0 calibration. */ if (constant_tsc && !tsc_unstable) return cpu_data(0).loops_per_jiffy; /* * If TSC has constant frequency and TSC is not synchronized across * sockets and this is not the first CPU in the socket, then reuse * the calibration value of an already online CPU on that socket. * * This assumes that CONSTANT_TSC is consistent for all CPUs in a * socket. */ if (!constant_tsc || !mask) return 0; sibling = cpumask_any_but(mask, cpu); if (sibling < nr_cpu_ids) return cpu_data(sibling).loops_per_jiffy; return 0; } #endif |
| 287 287 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * tracing clocks * * Copyright (C) 2009 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> * * Implements 3 trace clock variants, with differing scalability/precision * tradeoffs: * * - local: CPU-local trace clock * - medium: scalable global clock with some jitter * - global: globally monotonic, serialized clock * * Tracer plugins will chose a default from these clocks. */ #include <linux/spinlock.h> #include <linux/irqflags.h> #include <linux/hardirq.h> #include <linux/module.h> #include <linux/percpu.h> #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/ktime.h> #include <linux/trace_clock.h> /* * trace_clock_local(): the simplest and least coherent tracing clock. * * Useful for tracing that does not cross to other CPUs nor * does it go through idle events. */ u64 notrace trace_clock_local(void) { u64 clock; /* * sched_clock() is an architecture implemented, fast, scalable, * lockless clock. It is not guaranteed to be coherent across * CPUs, nor across CPU idle events. */ preempt_disable_notrace(); clock = sched_clock(); preempt_enable_notrace(); return clock; } EXPORT_SYMBOL_GPL(trace_clock_local); /* * trace_clock(): 'between' trace clock. Not completely serialized, * but not completely incorrect when crossing CPUs either. * * This is based on cpu_clock(), which will allow at most ~1 jiffy of * jitter between CPUs. So it's a pretty scalable clock, but there * can be offsets in the trace data. */ u64 notrace trace_clock(void) { return local_clock(); } EXPORT_SYMBOL_GPL(trace_clock); /* * trace_jiffy_clock(): Simply use jiffies as a clock counter. * Note that this use of jiffies_64 is not completely safe on * 32-bit systems. But the window is tiny, and the effect if * we are affected is that we will have an obviously bogus * timestamp on a trace event - i.e. not life threatening. */ u64 notrace trace_clock_jiffies(void) { return jiffies_64_to_clock_t(jiffies_64 - INITIAL_JIFFIES); } EXPORT_SYMBOL_GPL(trace_clock_jiffies); /* * trace_clock_global(): special globally coherent trace clock * * It has higher overhead than the other trace clocks but is still * an order of magnitude faster than GTOD derived hardware clocks. * * Used by plugins that need globally coherent timestamps. */ /* keep prev_time and lock in the same cacheline. */ static struct { u64 prev_time; arch_spinlock_t lock; } trace_clock_struct ____cacheline_aligned_in_smp = { .lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED, }; u64 notrace trace_clock_global(void) { unsigned long flags; int this_cpu; u64 now, prev_time; raw_local_irq_save(flags); this_cpu = raw_smp_processor_id(); /* * The global clock "guarantees" that the events are ordered * between CPUs. But if two events on two different CPUS call * trace_clock_global at roughly the same time, it really does * not matter which one gets the earlier time. Just make sure * that the same CPU will always show a monotonic clock. * * Use a read memory barrier to get the latest written * time that was recorded. */ smp_rmb(); prev_time = READ_ONCE(trace_clock_struct.prev_time); now = sched_clock_cpu(this_cpu); /* Make sure that now is always greater than or equal to prev_time */ if ((s64)(now - prev_time) < 0) now = prev_time; /* * If in an NMI context then dont risk lockups and simply return * the current time. */ if (unlikely(in_nmi())) goto out; /* Tracing can cause strange recursion, always use a try lock */ if (arch_spin_trylock(&trace_clock_struct.lock)) { /* Reread prev_time in case it was already updated */ prev_time = READ_ONCE(trace_clock_struct.prev_time); if ((s64)(now - prev_time) < 0) now = prev_time; trace_clock_struct.prev_time = now; /* The unlock acts as the wmb for the above rmb */ arch_spin_unlock(&trace_clock_struct.lock); } out: raw_local_irq_restore(flags); return now; } EXPORT_SYMBOL_GPL(trace_clock_global); static atomic64_t trace_counter; /* * trace_clock_counter(): simply an atomic counter. * Use the trace_counter "counter" for cases where you do not care * about timings, but are interested in strict ordering. */ u64 notrace trace_clock_counter(void) { return atomic64_inc_return(&trace_counter); } |
| 8 8 8 8 4 8 8 8 5 5 5 5 5 5 2 2 2 2 2 2 2 2 2 2 2 2 2 13 13 13 3 12 4 2 4 11 11 5 13 13 13 13 13 3 3 3 1 3 13 7 7 13 13 13 13 13 13 13 13 13 13 13 5 13 13 13 111 111 111 111 111 3 3 3 3 3 3 3 111 111 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <net/wext.h> #include <net/hotdata.h> #include "dev.h" static void *dev_seq_from_index(struct seq_file *seq, loff_t *pos) { unsigned long ifindex = *pos; struct net_device *dev; for_each_netdev_dump(seq_file_net(seq), dev, ifindex) { *pos = dev->ifindex; return dev; } return NULL; } static void *dev_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); if (!*pos) return SEQ_START_TOKEN; return dev_seq_from_index(seq, pos); } static void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return dev_seq_from_index(seq, pos); } static void dev_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu " "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n", dev->name, stats->rx_bytes, stats->rx_packets, stats->rx_errors, stats->rx_dropped + stats->rx_missed_errors, stats->rx_fifo_errors, stats->rx_length_errors + stats->rx_over_errors + stats->rx_crc_errors + stats->rx_frame_errors, stats->rx_compressed, stats->multicast, stats->tx_bytes, stats->tx_packets, stats->tx_errors, stats->tx_dropped, stats->tx_fifo_errors, stats->collisions, stats->tx_carrier_errors + stats->tx_aborted_errors + stats->tx_window_errors + stats->tx_heartbeat_errors, stats->tx_compressed); } /* * Called from the PROCfs module. This now uses the new arbitrary sized * /proc/net interface to create /proc/net/dev */ static int dev_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_puts(seq, "Inter-| Receive " " | Transmit\n" " face |bytes packets errs drop fifo frame " "compressed multicast|bytes packets errs " "drop fifo colls carrier compressed\n"); else dev_seq_printf_stats(seq, v); return 0; } static u32 softnet_input_pkt_queue_len(struct softnet_data *sd) { return skb_queue_len_lockless(&sd->input_pkt_queue); } static u32 softnet_process_queue_len(struct softnet_data *sd) { return skb_queue_len_lockless(&sd->process_queue); } static struct softnet_data *softnet_get_online(loff_t *pos) { struct softnet_data *sd = NULL; while (*pos < nr_cpu_ids) if (cpu_online(*pos)) { sd = &per_cpu(softnet_data, *pos); break; } else ++*pos; return sd; } static void *softnet_seq_start(struct seq_file *seq, loff_t *pos) { return softnet_get_online(pos); } static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return softnet_get_online(pos); } static void softnet_seq_stop(struct seq_file *seq, void *v) { } static int softnet_seq_show(struct seq_file *seq, void *v) { struct softnet_data *sd = v; u32 input_qlen = softnet_input_pkt_queue_len(sd); u32 process_qlen = softnet_process_queue_len(sd); unsigned int flow_limit_count = 0; #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit *fl; rcu_read_lock(); fl = rcu_dereference(sd->flow_limit); if (fl) flow_limit_count = fl->count; rcu_read_unlock(); #endif /* the index is the CPU id owing this sd. Since offline CPUs are not * displayed, it would be othrwise not trivial for the user-space * mapping the data a specific CPU */ seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x " "%08x %08x\n", sd->processed, atomic_read(&sd->dropped), sd->time_squeeze, 0, 0, 0, 0, 0, /* was fastroute */ 0, /* was cpu_collision */ sd->received_rps, flow_limit_count, input_qlen + process_qlen, (int)seq->index, input_qlen, process_qlen); return 0; } static const struct seq_operations dev_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, .show = dev_seq_show, }; static const struct seq_operations softnet_seq_ops = { .start = softnet_seq_start, .next = softnet_seq_next, .stop = softnet_seq_stop, .show = softnet_seq_show, }; static void *ptype_get_idx(struct seq_file *seq, loff_t pos) { struct list_head *ptype_list = NULL; struct packet_type *pt = NULL; struct net_device *dev; loff_t i = 0; int t; for_each_netdev_rcu(seq_file_net(seq), dev) { ptype_list = &dev->ptype_all; list_for_each_entry_rcu(pt, ptype_list, list) { if (i == pos) return pt; ++i; } } list_for_each_entry_rcu(pt, &net_hotdata.ptype_all, list) { if (i == pos) return pt; ++i; } for (t = 0; t < PTYPE_HASH_SIZE; t++) { list_for_each_entry_rcu(pt, &ptype_base[t], list) { if (i == pos) return pt; ++i; } } return NULL; } static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return *pos ? ptype_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net_device *dev; struct packet_type *pt; struct list_head *nxt; int hash; ++*pos; if (v == SEQ_START_TOKEN) return ptype_get_idx(seq, 0); pt = v; nxt = pt->list.next; if (pt->dev) { if (nxt != &pt->dev->ptype_all) goto found; dev = pt->dev; for_each_netdev_continue_rcu(seq_file_net(seq), dev) { if (!list_empty(&dev->ptype_all)) { nxt = dev->ptype_all.next; goto found; } } nxt = net_hotdata.ptype_all.next; goto ptype_all; } if (pt->type == htons(ETH_P_ALL)) { ptype_all: if (nxt != &net_hotdata.ptype_all) goto found; hash = 0; nxt = ptype_base[0].next; } else hash = ntohs(pt->type) & PTYPE_HASH_MASK; while (nxt == &ptype_base[hash]) { if (++hash >= PTYPE_HASH_SIZE) return NULL; nxt = ptype_base[hash].next; } found: return list_entry(nxt, struct packet_type, list); } static void ptype_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int ptype_seq_show(struct seq_file *seq, void *v) { struct packet_type *pt = v; if (v == SEQ_START_TOKEN) seq_puts(seq, "Type Device Function\n"); else if ((!pt->af_packet_net || net_eq(pt->af_packet_net, seq_file_net(seq))) && (!pt->dev || net_eq(dev_net(pt->dev), seq_file_net(seq)))) { if (pt->type == htons(ETH_P_ALL)) seq_puts(seq, "ALL "); else seq_printf(seq, "%04x", ntohs(pt->type)); seq_printf(seq, " %-8s %ps\n", pt->dev ? pt->dev->name : "", pt->func); } return 0; } static const struct seq_operations ptype_seq_ops = { .start = ptype_seq_start, .next = ptype_seq_next, .stop = ptype_seq_stop, .show = ptype_seq_show, }; static int __net_init dev_proc_net_init(struct net *net) { int rc = -ENOMEM; if (!proc_create_net("dev", 0444, net->proc_net, &dev_seq_ops, sizeof(struct seq_net_private))) goto out; if (!proc_create_seq("softnet_stat", 0444, net->proc_net, &softnet_seq_ops)) goto out_dev; if (!proc_create_net("ptype", 0444, net->proc_net, &ptype_seq_ops, sizeof(struct seq_net_private))) goto out_softnet; if (wext_proc_init(net)) goto out_ptype; rc = 0; out: return rc; out_ptype: remove_proc_entry("ptype", net->proc_net); out_softnet: remove_proc_entry("softnet_stat", net->proc_net); out_dev: remove_proc_entry("dev", net->proc_net); goto out; } static void __net_exit dev_proc_net_exit(struct net *net) { wext_proc_exit(net); remove_proc_entry("ptype", net->proc_net); remove_proc_entry("softnet_stat", net->proc_net); remove_proc_entry("dev", net->proc_net); } static struct pernet_operations __net_initdata dev_proc_ops = { .init = dev_proc_net_init, .exit = dev_proc_net_exit, }; static int dev_mc_seq_show(struct seq_file *seq, void *v) { struct netdev_hw_addr *ha; struct net_device *dev = v; if (v == SEQ_START_TOKEN) return 0; netif_addr_lock_bh(dev); netdev_for_each_mc_addr(ha, dev) { seq_printf(seq, "%-4d %-15s %-5d %-5d %*phN\n", dev->ifindex, dev->name, ha->refcount, ha->global_use, (int)dev->addr_len, ha->addr); } netif_addr_unlock_bh(dev); return 0; } static const struct seq_operations dev_mc_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, .show = dev_mc_seq_show, }; static int __net_init dev_mc_net_init(struct net *net) { if (!proc_create_net("dev_mcast", 0, net->proc_net, &dev_mc_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } static void __net_exit dev_mc_net_exit(struct net *net) { remove_proc_entry("dev_mcast", net->proc_net); } static struct pernet_operations __net_initdata dev_mc_net_ops = { .init = dev_mc_net_init, .exit = dev_mc_net_exit, }; int __init dev_proc_init(void) { int ret = register_pernet_subsys(&dev_proc_ops); if (!ret) return register_pernet_subsys(&dev_mc_net_ops); return ret; } |
| 15 15 14 15 20 19 18 16 15 18 15 15 15 15 14 6 6 15 14 15 15 15 15 14 15 15 6 14 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <linux/rculist.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/bpf.h> #include <linux/btf_ids.h> #include <linux/bpf_local_storage.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> #include <linux/rcupdate.h> #include <linux/rcupdate_trace.h> #include <linux/rcupdate_wait.h> #define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE) static struct bpf_local_storage_map_bucket * select_bucket(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem) { return &smap->buckets[hash_ptr(selem, smap->bucket_log)]; } static int mem_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) { struct bpf_map *map = &smap->map; if (!map->ops->map_local_storage_charge) return 0; return map->ops->map_local_storage_charge(smap, owner, size); } static void mem_uncharge(struct bpf_local_storage_map *smap, void *owner, u32 size) { struct bpf_map *map = &smap->map; if (map->ops->map_local_storage_uncharge) map->ops->map_local_storage_uncharge(smap, owner, size); } static struct bpf_local_storage __rcu ** owner_storage(struct bpf_local_storage_map *smap, void *owner) { struct bpf_map *map = &smap->map; return map->ops->map_owner_storage_ptr(owner); } static bool selem_linked_to_storage_lockless(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed_lockless(&selem->snode); } static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->snode); } static bool selem_linked_to_map_lockless(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed_lockless(&selem->map_node); } static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->map_node); } struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, bool charge_mem, bool swap_uptrs, gfp_t gfp_flags) { struct bpf_local_storage_elem *selem; if (charge_mem && mem_charge(smap, owner, smap->elem_size)) return NULL; if (smap->bpf_ma) { migrate_disable(); selem = bpf_mem_cache_alloc_flags(&smap->selem_ma, gfp_flags); migrate_enable(); if (selem) /* Keep the original bpf_map_kzalloc behavior * before started using the bpf_mem_cache_alloc. * * No need to use zero_map_value. The bpf_selem_free() * only does bpf_mem_cache_free when there is * no other bpf prog is using the selem. */ memset(SDATA(selem)->data, 0, smap->map.value_size); } else { selem = bpf_map_kzalloc(&smap->map, smap->elem_size, gfp_flags | __GFP_NOWARN); } if (selem) { if (value) { /* No need to call check_and_init_map_value as memory is zero init */ copy_map_value(&smap->map, SDATA(selem)->data, value); if (swap_uptrs) bpf_obj_swap_uptrs(smap->map.record, SDATA(selem)->data, value); } return selem; } if (charge_mem) mem_uncharge(smap, owner, smap->elem_size); return NULL; } /* rcu tasks trace callback for bpf_ma == false */ static void __bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage *local_storage; /* If RCU Tasks Trace grace period implies RCU grace period, do * kfree(), else do kfree_rcu(). */ local_storage = container_of(rcu, struct bpf_local_storage, rcu); if (rcu_trace_implies_rcu_gp()) kfree(local_storage); else kfree_rcu(local_storage, rcu); } static void bpf_local_storage_free_rcu(struct rcu_head *rcu) { struct bpf_local_storage *local_storage; local_storage = container_of(rcu, struct bpf_local_storage, rcu); bpf_mem_cache_raw_free(local_storage); } static void bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) { if (rcu_trace_implies_rcu_gp()) bpf_local_storage_free_rcu(rcu); else call_rcu(rcu, bpf_local_storage_free_rcu); } /* Handle bpf_ma == false */ static void __bpf_local_storage_free(struct bpf_local_storage *local_storage, bool vanilla_rcu) { if (vanilla_rcu) kfree_rcu(local_storage, rcu); else call_rcu_tasks_trace(&local_storage->rcu, __bpf_local_storage_free_trace_rcu); } static void bpf_local_storage_free(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *smap, bool bpf_ma, bool reuse_now) { if (!local_storage) return; if (!bpf_ma) { __bpf_local_storage_free(local_storage, reuse_now); return; } if (!reuse_now) { call_rcu_tasks_trace(&local_storage->rcu, bpf_local_storage_free_trace_rcu); return; } if (smap) { migrate_disable(); bpf_mem_cache_free(&smap->storage_ma, local_storage); migrate_enable(); } else { /* smap could be NULL if the selem that triggered * this 'local_storage' creation had been long gone. * In this case, directly do call_rcu(). */ call_rcu(&local_storage->rcu, bpf_local_storage_free_rcu); } } /* rcu tasks trace callback for bpf_ma == false */ static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage_elem *selem; selem = container_of(rcu, struct bpf_local_storage_elem, rcu); if (rcu_trace_implies_rcu_gp()) kfree(selem); else kfree_rcu(selem, rcu); } /* Handle bpf_ma == false */ static void __bpf_selem_free(struct bpf_local_storage_elem *selem, bool vanilla_rcu) { if (vanilla_rcu) kfree_rcu(selem, rcu); else call_rcu_tasks_trace(&selem->rcu, __bpf_selem_free_trace_rcu); } static void bpf_selem_free_rcu(struct rcu_head *rcu) { struct bpf_local_storage_elem *selem; struct bpf_local_storage_map *smap; selem = container_of(rcu, struct bpf_local_storage_elem, rcu); /* The bpf_local_storage_map_free will wait for rcu_barrier */ smap = rcu_dereference_check(SDATA(selem)->smap, 1); bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); bpf_mem_cache_raw_free(selem); } static void bpf_selem_free_trace_rcu(struct rcu_head *rcu) { if (rcu_trace_implies_rcu_gp()) bpf_selem_free_rcu(rcu); else call_rcu(rcu, bpf_selem_free_rcu); } void bpf_selem_free(struct bpf_local_storage_elem *selem, struct bpf_local_storage_map *smap, bool reuse_now) { if (!smap->bpf_ma) { /* Only task storage has uptrs and task storage * has moved to bpf_mem_alloc. Meaning smap->bpf_ma == true * for task storage, so this bpf_obj_free_fields() won't unpin * any uptr. */ bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); __bpf_selem_free(selem, reuse_now); return; } if (reuse_now) { /* reuse_now == true only happens when the storage owner * (e.g. task_struct) is being destructed or the map itself * is being destructed (ie map_free). In both cases, * no bpf prog can have a hold on the selem. It is * safe to unpin the uptrs and free the selem now. */ bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); /* Instead of using the vanilla call_rcu(), * bpf_mem_cache_free will be able to reuse selem * immediately. */ migrate_disable(); bpf_mem_cache_free(&smap->selem_ma, selem); migrate_enable(); return; } call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_trace_rcu); } static void bpf_selem_free_list(struct hlist_head *list, bool reuse_now) { struct bpf_local_storage_elem *selem; struct bpf_local_storage_map *smap; struct hlist_node *n; /* The "_safe" iteration is needed. * The loop is not removing the selem from the list * but bpf_selem_free will use the selem->rcu_head * which is union-ized with the selem->free_node. */ hlist_for_each_entry_safe(selem, n, list, free_node) { smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); bpf_selem_free(selem, smap, reuse_now); } } /* local_storage->lock must be held and selem->local_storage == local_storage. * The caller must ensure selem->smap is still valid to be * dereferenced for its smap->elem_size and smap->cache_idx. */ static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem, bool uncharge_mem, struct hlist_head *free_selem_list) { struct bpf_local_storage_map *smap; bool free_local_storage; void *owner; smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); owner = local_storage->owner; /* All uncharging on the owner must be done first. * The owner may be freed once the last selem is unlinked * from local_storage. */ if (uncharge_mem) mem_uncharge(smap, owner, smap->elem_size); free_local_storage = hlist_is_singular_node(&selem->snode, &local_storage->list); if (free_local_storage) { mem_uncharge(smap, owner, sizeof(struct bpf_local_storage)); local_storage->owner = NULL; /* After this RCU_INIT, owner may be freed and cannot be used */ RCU_INIT_POINTER(*owner_storage(smap, owner), NULL); /* local_storage is not freed now. local_storage->lock is * still held and raw_spin_unlock_bh(&local_storage->lock) * will be done by the caller. * * Although the unlock will be done under * rcu_read_lock(), it is more intuitive to * read if the freeing of the storage is done * after the raw_spin_unlock_bh(&local_storage->lock). * * Hence, a "bool free_local_storage" is returned * to the caller which then calls then frees the storage after * all the RCU grace periods have expired. */ } hlist_del_init_rcu(&selem->snode); if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) == SDATA(selem)) RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); hlist_add_head(&selem->free_node, free_selem_list); if (rcu_access_pointer(local_storage->smap) == smap) RCU_INIT_POINTER(local_storage->smap, NULL); return free_local_storage; } static bool check_storage_bpf_ma(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *storage_smap, struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map *selem_smap; /* local_storage->smap may be NULL. If it is, get the bpf_ma * from any selem in the local_storage->list. The bpf_ma of all * local_storage and selem should have the same value * for the same map type. * * If the local_storage->list is already empty, the caller will not * care about the bpf_ma value also because the caller is not * responsible to free the local_storage. */ if (storage_smap) return storage_smap->bpf_ma; if (!selem) { struct hlist_node *n; n = rcu_dereference_check(hlist_first_rcu(&local_storage->list), bpf_rcu_lock_held()); if (!n) return false; selem = hlist_entry(n, struct bpf_local_storage_elem, snode); } selem_smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); return selem_smap->bpf_ma; } static void bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem, bool reuse_now) { struct bpf_local_storage_map *storage_smap; struct bpf_local_storage *local_storage; bool bpf_ma, free_local_storage = false; HLIST_HEAD(selem_free_list); unsigned long flags; if (unlikely(!selem_linked_to_storage_lockless(selem))) /* selem has already been unlinked from sk */ return; local_storage = rcu_dereference_check(selem->local_storage, bpf_rcu_lock_held()); storage_smap = rcu_dereference_check(local_storage->smap, bpf_rcu_lock_held()); bpf_ma = check_storage_bpf_ma(local_storage, storage_smap, selem); raw_spin_lock_irqsave(&local_storage->lock, flags); if (likely(selem_linked_to_storage(selem))) free_local_storage = bpf_selem_unlink_storage_nolock( local_storage, selem, true, &selem_free_list); raw_spin_unlock_irqrestore(&local_storage->lock, flags); bpf_selem_free_list(&selem_free_list, reuse_now); if (free_local_storage) bpf_local_storage_free(local_storage, storage_smap, bpf_ma, reuse_now); } void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem) { RCU_INIT_POINTER(selem->local_storage, local_storage); hlist_add_head_rcu(&selem->snode, &local_storage->list); } static void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map *smap; struct bpf_local_storage_map_bucket *b; unsigned long flags; if (unlikely(!selem_linked_to_map_lockless(selem))) /* selem has already be unlinked from smap */ return; smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); b = select_bucket(smap, selem); raw_spin_lock_irqsave(&b->lock, flags); if (likely(selem_linked_to_map(selem))) hlist_del_init_rcu(&selem->map_node); raw_spin_unlock_irqrestore(&b->lock, flags); } void bpf_selem_link_map(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map_bucket *b = select_bucket(smap, selem); unsigned long flags; raw_spin_lock_irqsave(&b->lock, flags); RCU_INIT_POINTER(SDATA(selem)->smap, smap); hlist_add_head_rcu(&selem->map_node, &b->list); raw_spin_unlock_irqrestore(&b->lock, flags); } void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool reuse_now) { /* Always unlink from map before unlinking from local_storage * because selem will be freed after successfully unlinked from * the local_storage. */ bpf_selem_unlink_map(selem); bpf_selem_unlink_storage(selem, reuse_now); } void __bpf_local_storage_insert_cache(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem) { unsigned long flags; /* spinlock is needed to avoid racing with the * parallel delete. Otherwise, publishing an already * deleted sdata to the cache will become a use-after-free * problem in the next bpf_local_storage_lookup(). */ raw_spin_lock_irqsave(&local_storage->lock, flags); if (selem_linked_to_storage(selem)) rcu_assign_pointer(local_storage->cache[smap->cache_idx], SDATA(selem)); raw_spin_unlock_irqrestore(&local_storage->lock, flags); } static int check_flags(const struct bpf_local_storage_data *old_sdata, u64 map_flags) { if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) /* elem already exists */ return -EEXIST; if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) /* elem doesn't exist, cannot update it */ return -ENOENT; return 0; } int bpf_local_storage_alloc(void *owner, struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *first_selem, gfp_t gfp_flags) { struct bpf_local_storage *prev_storage, *storage; struct bpf_local_storage **owner_storage_ptr; int err; err = mem_charge(smap, owner, sizeof(*storage)); if (err) return err; if (smap->bpf_ma) { migrate_disable(); storage = bpf_mem_cache_alloc_flags(&smap->storage_ma, gfp_flags); migrate_enable(); } else { storage = bpf_map_kzalloc(&smap->map, sizeof(*storage), gfp_flags | __GFP_NOWARN); } if (!storage) { err = -ENOMEM; goto uncharge; } RCU_INIT_POINTER(storage->smap, smap); INIT_HLIST_HEAD(&storage->list); raw_spin_lock_init(&storage->lock); storage->owner = owner; bpf_selem_link_storage_nolock(storage, first_selem); bpf_selem_link_map(smap, first_selem); owner_storage_ptr = (struct bpf_local_storage **)owner_storage(smap, owner); /* Publish storage to the owner. * Instead of using any lock of the kernel object (i.e. owner), * cmpxchg will work with any kernel object regardless what * the running context is, bh, irq...etc. * * From now on, the owner->storage pointer (e.g. sk->sk_bpf_storage) * is protected by the storage->lock. Hence, when freeing * the owner->storage, the storage->lock must be held before * setting owner->storage ptr to NULL. */ prev_storage = cmpxchg(owner_storage_ptr, NULL, storage); if (unlikely(prev_storage)) { bpf_selem_unlink_map(first_selem); err = -EAGAIN; goto uncharge; /* Note that even first_selem was linked to smap's * bucket->list, first_selem can be freed immediately * (instead of kfree_rcu) because * bpf_local_storage_map_free() does a * synchronize_rcu_mult (waiting for both sleepable and * normal programs) before walking the bucket->list. * Hence, no one is accessing selem from the * bucket->list under rcu_read_lock(). */ } return 0; uncharge: bpf_local_storage_free(storage, smap, smap->bpf_ma, true); mem_uncharge(smap, owner, sizeof(*storage)); return err; } /* sk cannot be going away because it is linking new elem * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0). * Otherwise, it will become a leak (and other memory issues * during map destruction). */ struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, void *value, u64 map_flags, bool swap_uptrs, gfp_t gfp_flags) { struct bpf_local_storage_data *old_sdata = NULL; struct bpf_local_storage_elem *alloc_selem, *selem = NULL; struct bpf_local_storage *local_storage; HLIST_HEAD(old_selem_free_list); unsigned long flags; int err; /* BPF_EXIST and BPF_NOEXIST cannot be both set */ if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || /* BPF_F_LOCK can only be used in a value with spin_lock */ unlikely((map_flags & BPF_F_LOCK) && !btf_record_has_field(smap->map.record, BPF_SPIN_LOCK))) return ERR_PTR(-EINVAL); if (gfp_flags == GFP_KERNEL && (map_flags & ~BPF_F_LOCK) != BPF_NOEXIST) return ERR_PTR(-EINVAL); local_storage = rcu_dereference_check(*owner_storage(smap, owner), bpf_rcu_lock_held()); if (!local_storage || hlist_empty(&local_storage->list)) { /* Very first elem for the owner */ err = check_flags(NULL, map_flags); if (err) return ERR_PTR(err); selem = bpf_selem_alloc(smap, owner, value, true, swap_uptrs, gfp_flags); if (!selem) return ERR_PTR(-ENOMEM); err = bpf_local_storage_alloc(owner, smap, selem, gfp_flags); if (err) { bpf_selem_free(selem, smap, true); mem_uncharge(smap, owner, smap->elem_size); return ERR_PTR(err); } return SDATA(selem); } if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { /* Hoping to find an old_sdata to do inline update * such that it can avoid taking the local_storage->lock * and changing the lists. */ old_sdata = bpf_local_storage_lookup(local_storage, smap, false); err = check_flags(old_sdata, map_flags); if (err) return ERR_PTR(err); if (old_sdata && selem_linked_to_storage_lockless(SELEM(old_sdata))) { copy_map_value_locked(&smap->map, old_sdata->data, value, false); return old_sdata; } } /* A lookup has just been done before and concluded a new selem is * needed. The chance of an unnecessary alloc is unlikely. */ alloc_selem = selem = bpf_selem_alloc(smap, owner, value, true, swap_uptrs, gfp_flags); if (!alloc_selem) return ERR_PTR(-ENOMEM); raw_spin_lock_irqsave(&local_storage->lock, flags); /* Recheck local_storage->list under local_storage->lock */ if (unlikely(hlist_empty(&local_storage->list))) { /* A parallel del is happening and local_storage is going * away. It has just been checked before, so very * unlikely. Return instead of retry to keep things * simple. */ err = -EAGAIN; goto unlock; } old_sdata = bpf_local_storage_lookup(local_storage, smap, false); err = check_flags(old_sdata, map_flags); if (err) goto unlock; if (old_sdata && (map_flags & BPF_F_LOCK)) { copy_map_value_locked(&smap->map, old_sdata->data, value, false); selem = SELEM(old_sdata); goto unlock; } alloc_selem = NULL; /* First, link the new selem to the map */ bpf_selem_link_map(smap, selem); /* Second, link (and publish) the new selem to local_storage */ bpf_selem_link_storage_nolock(local_storage, selem); /* Third, remove old selem, SELEM(old_sdata) */ if (old_sdata) { bpf_selem_unlink_map(SELEM(old_sdata)); bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata), true, &old_selem_free_list); } unlock: raw_spin_unlock_irqrestore(&local_storage->lock, flags); bpf_selem_free_list(&old_selem_free_list, false); if (alloc_selem) { mem_uncharge(smap, owner, smap->elem_size); bpf_selem_free(alloc_selem, smap, true); } return err ? ERR_PTR(err) : SDATA(selem); } static u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) { u64 min_usage = U64_MAX; u16 i, res = 0; spin_lock(&cache->idx_lock); for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) { if (cache->idx_usage_counts[i] < min_usage) { min_usage = cache->idx_usage_counts[i]; res = i; /* Found a free cache_idx */ if (!min_usage) break; } } cache->idx_usage_counts[res]++; spin_unlock(&cache->idx_lock); return res; } static void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, u16 idx) { spin_lock(&cache->idx_lock); cache->idx_usage_counts[idx]--; spin_unlock(&cache->idx_lock); } int bpf_local_storage_map_alloc_check(union bpf_attr *attr) { if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK || !(attr->map_flags & BPF_F_NO_PREALLOC) || attr->max_entries || attr->key_size != sizeof(int) || !attr->value_size || /* Enforce BTF for userspace sk dumping */ !attr->btf_key_type_id || !attr->btf_value_type_id) return -EINVAL; if (attr->value_size > BPF_LOCAL_STORAGE_MAX_VALUE_SIZE) return -E2BIG; return 0; } int bpf_local_storage_map_check_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { u32 int_data; if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) return -EINVAL; int_data = *(u32 *)(key_type + 1); if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data)) return -EINVAL; return 0; } void bpf_local_storage_destroy(struct bpf_local_storage *local_storage) { struct bpf_local_storage_map *storage_smap; struct bpf_local_storage_elem *selem; bool bpf_ma, free_storage = false; HLIST_HEAD(free_selem_list); struct hlist_node *n; unsigned long flags; storage_smap = rcu_dereference_check(local_storage->smap, bpf_rcu_lock_held()); bpf_ma = check_storage_bpf_ma(local_storage, storage_smap, NULL); /* Neither the bpf_prog nor the bpf_map's syscall * could be modifying the local_storage->list now. * Thus, no elem can be added to or deleted from the * local_storage->list by the bpf_prog or by the bpf_map's syscall. * * It is racing with bpf_local_storage_map_free() alone * when unlinking elem from the local_storage->list and * the map's bucket->list. */ raw_spin_lock_irqsave(&local_storage->lock, flags); hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) { /* Always unlink from map before unlinking from * local_storage. */ bpf_selem_unlink_map(selem); /* If local_storage list has only one element, the * bpf_selem_unlink_storage_nolock() will return true. * Otherwise, it will return false. The current loop iteration * intends to remove all local storage. So the last iteration * of the loop will set the free_cgroup_storage to true. */ free_storage = bpf_selem_unlink_storage_nolock( local_storage, selem, true, &free_selem_list); } raw_spin_unlock_irqrestore(&local_storage->lock, flags); bpf_selem_free_list(&free_selem_list, true); if (free_storage) bpf_local_storage_free(local_storage, storage_smap, bpf_ma, true); } u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map) { struct bpf_local_storage_map *smap = (struct bpf_local_storage_map *)map; u64 usage = sizeof(*smap); /* The dynamically callocated selems are not counted currently. */ usage += sizeof(*smap->buckets) * (1ULL << smap->bucket_log); return usage; } /* When bpf_ma == true, the bpf_mem_alloc is used to allocate and free memory. * A deadlock free allocator is useful for storage that the bpf prog can easily * get a hold of the owner PTR_TO_BTF_ID in any context. eg. bpf_get_current_task_btf. * The task and cgroup storage fall into this case. The bpf_mem_alloc reuses * memory immediately. To be reuse-immediate safe, the owner destruction * code path needs to go through a rcu grace period before calling * bpf_local_storage_destroy(). * * When bpf_ma == false, the kmalloc and kfree are used. */ struct bpf_map * bpf_local_storage_map_alloc(union bpf_attr *attr, struct bpf_local_storage_cache *cache, bool bpf_ma) { struct bpf_local_storage_map *smap; unsigned int i; u32 nbuckets; int err; smap = bpf_map_area_alloc(sizeof(*smap), NUMA_NO_NODE); if (!smap) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&smap->map, attr); nbuckets = roundup_pow_of_two(num_possible_cpus()); /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ nbuckets = max_t(u32, 2, nbuckets); smap->bucket_log = ilog2(nbuckets); smap->buckets = bpf_map_kvcalloc(&smap->map, nbuckets, sizeof(*smap->buckets), GFP_USER | __GFP_NOWARN); if (!smap->buckets) { err = -ENOMEM; goto free_smap; } for (i = 0; i < nbuckets; i++) { INIT_HLIST_HEAD(&smap->buckets[i].list); raw_spin_lock_init(&smap->buckets[i].lock); } smap->elem_size = offsetof(struct bpf_local_storage_elem, sdata.data[attr->value_size]); smap->bpf_ma = bpf_ma; if (bpf_ma) { err = bpf_mem_alloc_init(&smap->selem_ma, smap->elem_size, false); if (err) goto free_smap; err = bpf_mem_alloc_init(&smap->storage_ma, sizeof(struct bpf_local_storage), false); if (err) { bpf_mem_alloc_destroy(&smap->selem_ma); goto free_smap; } } smap->cache_idx = bpf_local_storage_cache_idx_get(cache); return &smap->map; free_smap: kvfree(smap->buckets); bpf_map_area_free(smap); return ERR_PTR(err); } void bpf_local_storage_map_free(struct bpf_map *map, struct bpf_local_storage_cache *cache, int __percpu *busy_counter) { struct bpf_local_storage_map_bucket *b; struct bpf_local_storage_elem *selem; struct bpf_local_storage_map *smap; unsigned int i; smap = (struct bpf_local_storage_map *)map; bpf_local_storage_cache_idx_free(cache, smap->cache_idx); /* Note that this map might be concurrently cloned from * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone * RCU read section to finish before proceeding. New RCU * read sections should be prevented via bpf_map_inc_not_zero. */ synchronize_rcu(); /* bpf prog and the userspace can no longer access this map * now. No new selem (of this map) can be added * to the owner->storage or to the map bucket's list. * * The elem of this map can be cleaned up here * or when the storage is freed e.g. * by bpf_sk_storage_free() during __sk_destruct(). */ for (i = 0; i < (1U << smap->bucket_log); i++) { b = &smap->buckets[i]; rcu_read_lock(); /* No one is adding to b->list now */ while ((selem = hlist_entry_safe( rcu_dereference_raw(hlist_first_rcu(&b->list)), struct bpf_local_storage_elem, map_node))) { if (busy_counter) { migrate_disable(); this_cpu_inc(*busy_counter); } bpf_selem_unlink(selem, true); if (busy_counter) { this_cpu_dec(*busy_counter); migrate_enable(); } cond_resched_rcu(); } rcu_read_unlock(); } /* While freeing the storage we may still need to access the map. * * e.g. when bpf_sk_storage_free() has unlinked selem from the map * which then made the above while((selem = ...)) loop * exit immediately. * * However, while freeing the storage one still needs to access the * smap->elem_size to do the uncharging in * bpf_selem_unlink_storage_nolock(). * * Hence, wait another rcu grace period for the storage to be freed. */ synchronize_rcu(); if (smap->bpf_ma) { rcu_barrier_tasks_trace(); if (!rcu_trace_implies_rcu_gp()) rcu_barrier(); bpf_mem_alloc_destroy(&smap->selem_ma); bpf_mem_alloc_destroy(&smap->storage_ma); } kvfree(smap->buckets); bpf_map_area_free(smap); } |
| 4 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 1 1 1 1 1 1 1 1 3 3 3 1 1 1932 1932 735 660 735 1933 825 2 823 820 824 1743 1740 1932 1932 1930 1929 81 40 40 41 42 821 824 137 137 137 137 117 118 118 117 118 46 46 52 36 6 19 19 19 118 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/char_dev.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/init.h> #include <linux/fs.h> #include <linux/kdev_t.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/major.h> #include <linux/errno.h> #include <linux/module.h> #include <linux/seq_file.h> #include <linux/kobject.h> #include <linux/kobj_map.h> #include <linux/cdev.h> #include <linux/mutex.h> #include <linux/backing-dev.h> #include <linux/tty.h> #include "internal.h" static struct kobj_map *cdev_map __ro_after_init; static DEFINE_MUTEX(chrdevs_lock); #define CHRDEV_MAJOR_HASH_SIZE 255 static struct char_device_struct { struct char_device_struct *next; unsigned int major; unsigned int baseminor; int minorct; char name[64]; struct cdev *cdev; /* will die */ } *chrdevs[CHRDEV_MAJOR_HASH_SIZE]; /* index in the above */ static inline int major_to_index(unsigned major) { return major % CHRDEV_MAJOR_HASH_SIZE; } #ifdef CONFIG_PROC_FS void chrdev_show(struct seq_file *f, off_t offset) { struct char_device_struct *cd; mutex_lock(&chrdevs_lock); for (cd = chrdevs[major_to_index(offset)]; cd; cd = cd->next) { if (cd->major == offset) seq_printf(f, "%3d %s\n", cd->major, cd->name); } mutex_unlock(&chrdevs_lock); } #endif /* CONFIG_PROC_FS */ static int find_dynamic_major(void) { int i; struct char_device_struct *cd; for (i = ARRAY_SIZE(chrdevs)-1; i >= CHRDEV_MAJOR_DYN_END; i--) { if (chrdevs[i] == NULL) return i; } for (i = CHRDEV_MAJOR_DYN_EXT_START; i >= CHRDEV_MAJOR_DYN_EXT_END; i--) { for (cd = chrdevs[major_to_index(i)]; cd; cd = cd->next) if (cd->major == i) break; if (cd == NULL) return i; } return -EBUSY; } /* * Register a single major with a specified minor range. * * If major == 0 this function will dynamically allocate an unused major. * If major > 0 this function will attempt to reserve the range of minors * with given major. * */ static struct char_device_struct * __register_chrdev_region(unsigned int major, unsigned int baseminor, int minorct, const char *name) { struct char_device_struct *cd, *curr, *prev = NULL; int ret; int i; if (major >= CHRDEV_MAJOR_MAX) { pr_err("CHRDEV \"%s\" major requested (%u) is greater than the maximum (%u)\n", name, major, CHRDEV_MAJOR_MAX-1); return ERR_PTR(-EINVAL); } if (minorct > MINORMASK + 1 - baseminor) { pr_err("CHRDEV \"%s\" minor range requested (%u-%u) is out of range of maximum range (%u-%u) for a single major\n", name, baseminor, baseminor + minorct - 1, 0, MINORMASK); return ERR_PTR(-EINVAL); } cd = kzalloc(sizeof(struct char_device_struct), GFP_KERNEL); if (cd == NULL) return ERR_PTR(-ENOMEM); mutex_lock(&chrdevs_lock); if (major == 0) { ret = find_dynamic_major(); if (ret < 0) { pr_err("CHRDEV \"%s\" dynamic allocation region is full\n", name); goto out; } major = ret; } ret = -EBUSY; i = major_to_index(major); for (curr = chrdevs[i]; curr; prev = curr, curr = curr->next) { if (curr->major < major) continue; if (curr->major > major) break; if (curr->baseminor + curr->minorct <= baseminor) continue; if (curr->baseminor >= baseminor + minorct) break; goto out; } cd->major = major; cd->baseminor = baseminor; cd->minorct = minorct; strscpy(cd->name, name, sizeof(cd->name)); if (!prev) { cd->next = curr; chrdevs[i] = cd; } else { cd->next = prev->next; prev->next = cd; } mutex_unlock(&chrdevs_lock); return cd; out: mutex_unlock(&chrdevs_lock); kfree(cd); return ERR_PTR(ret); } static struct char_device_struct * __unregister_chrdev_region(unsigned major, unsigned baseminor, int minorct) { struct char_device_struct *cd = NULL, **cp; int i = major_to_index(major); mutex_lock(&chrdevs_lock); for (cp = &chrdevs[i]; *cp; cp = &(*cp)->next) if ((*cp)->major == major && (*cp)->baseminor == baseminor && (*cp)->minorct == minorct) break; if (*cp) { cd = *cp; *cp = cd->next; } mutex_unlock(&chrdevs_lock); return cd; } /** * register_chrdev_region() - register a range of device numbers * @from: the first in the desired range of device numbers; must include * the major number. * @count: the number of consecutive device numbers required * @name: the name of the device or driver. * * Return value is zero on success, a negative error code on failure. */ int register_chrdev_region(dev_t from, unsigned count, const char *name) { struct char_device_struct *cd; dev_t to = from + count; dev_t n, next; for (n = from; n < to; n = next) { next = MKDEV(MAJOR(n)+1, 0); if (next > to) next = to; cd = __register_chrdev_region(MAJOR(n), MINOR(n), next - n, name); if (IS_ERR(cd)) goto fail; } return 0; fail: to = n; for (n = from; n < to; n = next) { next = MKDEV(MAJOR(n)+1, 0); kfree(__unregister_chrdev_region(MAJOR(n), MINOR(n), next - n)); } return PTR_ERR(cd); } /** * alloc_chrdev_region() - register a range of char device numbers * @dev: output parameter for first assigned number * @baseminor: first of the requested range of minor numbers * @count: the number of minor numbers required * @name: the name of the associated device or driver * * Allocates a range of char device numbers. The major number will be * chosen dynamically, and returned (along with the first minor number) * in @dev. Returns zero or a negative error code. */ int alloc_chrdev_region(dev_t *dev, unsigned baseminor, unsigned count, const char *name) { struct char_device_struct *cd; cd = __register_chrdev_region(0, baseminor, count, name); if (IS_ERR(cd)) return PTR_ERR(cd); *dev = MKDEV(cd->major, cd->baseminor); return 0; } /** * __register_chrdev() - create and register a cdev occupying a range of minors * @major: major device number or 0 for dynamic allocation * @baseminor: first of the requested range of minor numbers * @count: the number of minor numbers required * @name: name of this range of devices * @fops: file operations associated with this devices * * If @major == 0 this functions will dynamically allocate a major and return * its number. * * If @major > 0 this function will attempt to reserve a device with the given * major number and will return zero on success. * * Returns a -ve errno on failure. * * The name of this device has nothing to do with the name of the device in * /dev. It only helps to keep track of the different owners of devices. If * your module name has only one type of devices it's ok to use e.g. the name * of the module here. */ int __register_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name, const struct file_operations *fops) { struct char_device_struct *cd; struct cdev *cdev; int err = -ENOMEM; cd = __register_chrdev_region(major, baseminor, count, name); if (IS_ERR(cd)) return PTR_ERR(cd); cdev = cdev_alloc(); if (!cdev) goto out2; cdev->owner = fops->owner; cdev->ops = fops; kobject_set_name(&cdev->kobj, "%s", name); err = cdev_add(cdev, MKDEV(cd->major, baseminor), count); if (err) goto out; cd->cdev = cdev; return major ? 0 : cd->major; out: kobject_put(&cdev->kobj); out2: kfree(__unregister_chrdev_region(cd->major, baseminor, count)); return err; } /** * unregister_chrdev_region() - unregister a range of device numbers * @from: the first in the range of numbers to unregister * @count: the number of device numbers to unregister * * This function will unregister a range of @count device numbers, * starting with @from. The caller should normally be the one who * allocated those numbers in the first place... */ void unregister_chrdev_region(dev_t from, unsigned count) { dev_t to = from + count; dev_t n, next; for (n = from; n < to; n = next) { next = MKDEV(MAJOR(n)+1, 0); if (next > to) next = to; kfree(__unregister_chrdev_region(MAJOR(n), MINOR(n), next - n)); } } /** * __unregister_chrdev - unregister and destroy a cdev * @major: major device number * @baseminor: first of the range of minor numbers * @count: the number of minor numbers this cdev is occupying * @name: name of this range of devices * * Unregister and destroy the cdev occupying the region described by * @major, @baseminor and @count. This function undoes what * __register_chrdev() did. */ void __unregister_chrdev(unsigned int major, unsigned int baseminor, unsigned int count, const char *name) { struct char_device_struct *cd; cd = __unregister_chrdev_region(major, baseminor, count); if (cd && cd->cdev) cdev_del(cd->cdev); kfree(cd); } static DEFINE_SPINLOCK(cdev_lock); static struct kobject *cdev_get(struct cdev *p) { struct module *owner = p->owner; struct kobject *kobj; if (!try_module_get(owner)) return NULL; kobj = kobject_get_unless_zero(&p->kobj); if (!kobj) module_put(owner); return kobj; } void cdev_put(struct cdev *p) { if (p) { struct module *owner = p->owner; kobject_put(&p->kobj); module_put(owner); } } /* * Called every time a character special file is opened */ static int chrdev_open(struct inode *inode, struct file *filp) { const struct file_operations *fops; struct cdev *p; struct cdev *new = NULL; int ret = 0; spin_lock(&cdev_lock); p = inode->i_cdev; if (!p) { struct kobject *kobj; int idx; spin_unlock(&cdev_lock); kobj = kobj_lookup(cdev_map, inode->i_rdev, &idx); if (!kobj) return -ENXIO; new = container_of(kobj, struct cdev, kobj); spin_lock(&cdev_lock); /* Check i_cdev again in case somebody beat us to it while we dropped the lock. */ p = inode->i_cdev; if (!p) { inode->i_cdev = p = new; list_add(&inode->i_devices, &p->list); new = NULL; } else if (!cdev_get(p)) ret = -ENXIO; } else if (!cdev_get(p)) ret = -ENXIO; spin_unlock(&cdev_lock); cdev_put(new); if (ret) return ret; ret = -ENXIO; fops = fops_get(p->ops); if (!fops) goto out_cdev_put; replace_fops(filp, fops); if (filp->f_op->open) { ret = filp->f_op->open(inode, filp); if (ret) goto out_cdev_put; } return 0; out_cdev_put: cdev_put(p); return ret; } void cd_forget(struct inode *inode) { spin_lock(&cdev_lock); list_del_init(&inode->i_devices); inode->i_cdev = NULL; inode->i_mapping = &inode->i_data; spin_unlock(&cdev_lock); } static void cdev_purge(struct cdev *cdev) { spin_lock(&cdev_lock); while (!list_empty(&cdev->list)) { struct inode *inode; inode = container_of(cdev->list.next, struct inode, i_devices); list_del_init(&inode->i_devices); inode->i_cdev = NULL; } spin_unlock(&cdev_lock); } /* * Dummy default file-operations: the only thing this does * is contain the open that then fills in the correct operations * depending on the special file... */ const struct file_operations def_chr_fops = { .open = chrdev_open, .llseek = noop_llseek, }; static struct kobject *exact_match(dev_t dev, int *part, void *data) { struct cdev *p = data; return &p->kobj; } static int exact_lock(dev_t dev, void *data) { struct cdev *p = data; return cdev_get(p) ? 0 : -1; } /** * cdev_add() - add a char device to the system * @p: the cdev structure for the device * @dev: the first device number for which this device is responsible * @count: the number of consecutive minor numbers corresponding to this * device * * cdev_add() adds the device represented by @p to the system, making it * live immediately. A negative error code is returned on failure. */ int cdev_add(struct cdev *p, dev_t dev, unsigned count) { int error; p->dev = dev; p->count = count; if (WARN_ON(dev == WHITEOUT_DEV)) { error = -EBUSY; goto err; } error = kobj_map(cdev_map, dev, count, NULL, exact_match, exact_lock, p); if (error) goto err; kobject_get(p->kobj.parent); return 0; err: kfree_const(p->kobj.name); p->kobj.name = NULL; return error; } /** * cdev_set_parent() - set the parent kobject for a char device * @p: the cdev structure * @kobj: the kobject to take a reference to * * cdev_set_parent() sets a parent kobject which will be referenced * appropriately so the parent is not freed before the cdev. This * should be called before cdev_add. */ void cdev_set_parent(struct cdev *p, struct kobject *kobj) { WARN_ON(!kobj->state_initialized); p->kobj.parent = kobj; } /** * cdev_device_add() - add a char device and it's corresponding * struct device, linkink * @dev: the device structure * @cdev: the cdev structure * * cdev_device_add() adds the char device represented by @cdev to the system, * just as cdev_add does. It then adds @dev to the system using device_add * The dev_t for the char device will be taken from the struct device which * needs to be initialized first. This helper function correctly takes a * reference to the parent device so the parent will not get released until * all references to the cdev are released. * * This helper uses dev->devt for the device number. If it is not set * it will not add the cdev and it will be equivalent to device_add. * * This function should be used whenever the struct cdev and the * struct device are members of the same structure whose lifetime is * managed by the struct device. * * NOTE: Callers must assume that userspace was able to open the cdev and * can call cdev fops callbacks at any time, even if this function fails. */ int cdev_device_add(struct cdev *cdev, struct device *dev) { int rc = 0; if (dev->devt) { cdev_set_parent(cdev, &dev->kobj); rc = cdev_add(cdev, dev->devt, 1); if (rc) return rc; } rc = device_add(dev); if (rc && dev->devt) cdev_del(cdev); return rc; } /** * cdev_device_del() - inverse of cdev_device_add * @cdev: the cdev structure * @dev: the device structure * * cdev_device_del() is a helper function to call cdev_del and device_del. * It should be used whenever cdev_device_add is used. * * If dev->devt is not set it will not remove the cdev and will be equivalent * to device_del. * * NOTE: This guarantees that associated sysfs callbacks are not running * or runnable, however any cdevs already open will remain and their fops * will still be callable even after this function returns. */ void cdev_device_del(struct cdev *cdev, struct device *dev) { device_del(dev); if (dev->devt) cdev_del(cdev); } static void cdev_unmap(dev_t dev, unsigned count) { kobj_unmap(cdev_map, dev, count); } /** * cdev_del() - remove a cdev from the system * @p: the cdev structure to be removed * * cdev_del() removes @p from the system, possibly freeing the structure * itself. * * NOTE: This guarantees that cdev device will no longer be able to be * opened, however any cdevs already open will remain and their fops will * still be callable even after cdev_del returns. */ void cdev_del(struct cdev *p) { cdev_unmap(p->dev, p->count); kobject_put(&p->kobj); } static void cdev_default_release(struct kobject *kobj) { struct cdev *p = container_of(kobj, struct cdev, kobj); struct kobject *parent = kobj->parent; cdev_purge(p); kobject_put(parent); } static void cdev_dynamic_release(struct kobject *kobj) { struct cdev *p = container_of(kobj, struct cdev, kobj); struct kobject *parent = kobj->parent; cdev_purge(p); kfree(p); kobject_put(parent); } static struct kobj_type ktype_cdev_default = { .release = cdev_default_release, }; static struct kobj_type ktype_cdev_dynamic = { .release = cdev_dynamic_release, }; /** * cdev_alloc() - allocate a cdev structure * * Allocates and returns a cdev structure, or NULL on failure. */ struct cdev *cdev_alloc(void) { struct cdev *p = kzalloc(sizeof(struct cdev), GFP_KERNEL); if (p) { INIT_LIST_HEAD(&p->list); kobject_init(&p->kobj, &ktype_cdev_dynamic); } return p; } /** * cdev_init() - initialize a cdev structure * @cdev: the structure to initialize * @fops: the file_operations for this device * * Initializes @cdev, remembering @fops, making it ready to add to the * system with cdev_add(). */ void cdev_init(struct cdev *cdev, const struct file_operations *fops) { memset(cdev, 0, sizeof *cdev); INIT_LIST_HEAD(&cdev->list); kobject_init(&cdev->kobj, &ktype_cdev_default); cdev->ops = fops; } static struct kobject *base_probe(dev_t dev, int *part, void *data) { if (request_module("char-major-%d-%d", MAJOR(dev), MINOR(dev)) > 0) /* Make old-style 2.4 aliases work */ request_module("char-major-%d", MAJOR(dev)); return NULL; } void __init chrdev_init(void) { cdev_map = kobj_map_init(base_probe, &chrdevs_lock); } /* Let modules do char dev stuff */ EXPORT_SYMBOL(register_chrdev_region); EXPORT_SYMBOL(unregister_chrdev_region); EXPORT_SYMBOL(alloc_chrdev_region); EXPORT_SYMBOL(cdev_init); EXPORT_SYMBOL(cdev_alloc); EXPORT_SYMBOL(cdev_del); EXPORT_SYMBOL(cdev_add); EXPORT_SYMBOL(cdev_set_parent); EXPORT_SYMBOL(cdev_device_add); EXPORT_SYMBOL(cdev_device_del); EXPORT_SYMBOL(__register_chrdev); EXPORT_SYMBOL(__unregister_chrdev); |
| 233 230 233 14 14 14 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * scsi_pm.c Copyright (C) 2010 Alan Stern * * SCSI dynamic Power Management * Initial version: Alan Stern <stern@rowland.harvard.edu> */ #include <linux/pm_runtime.h> #include <linux/export.h> #include <linux/blk-pm.h> #include <scsi/scsi.h> #include <scsi/scsi_device.h> #include <scsi/scsi_driver.h> #include <scsi/scsi_host.h> #include "scsi_priv.h" #ifdef CONFIG_PM_SLEEP static int do_scsi_suspend(struct device *dev, const struct dev_pm_ops *pm) { return pm && pm->suspend ? pm->suspend(dev) : 0; } static int do_scsi_freeze(struct device *dev, const struct dev_pm_ops *pm) { return pm && pm->freeze ? pm->freeze(dev) : 0; } static int do_scsi_poweroff(struct device *dev, const struct dev_pm_ops *pm) { return pm && pm->poweroff ? pm->poweroff(dev) : 0; } static int do_scsi_resume(struct device *dev, const struct dev_pm_ops *pm) { return pm && pm->resume ? pm->resume(dev) : 0; } static int do_scsi_thaw(struct device *dev, const struct dev_pm_ops *pm) { return pm && pm->thaw ? pm->thaw(dev) : 0; } static int do_scsi_restore(struct device *dev, const struct dev_pm_ops *pm) { return pm && pm->restore ? pm->restore(dev) : 0; } static int scsi_dev_type_suspend(struct device *dev, int (*cb)(struct device *, const struct dev_pm_ops *)) { const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; int err; err = scsi_device_quiesce(to_scsi_device(dev)); if (err == 0) { err = cb(dev, pm); if (err) scsi_device_resume(to_scsi_device(dev)); } dev_dbg(dev, "scsi suspend: %d\n", err); return err; } static int scsi_bus_suspend_common(struct device *dev, int (*cb)(struct device *, const struct dev_pm_ops *)) { if (!scsi_is_sdev_device(dev)) return 0; return scsi_dev_type_suspend(dev, cb); } static int scsi_bus_resume_common(struct device *dev, int (*cb)(struct device *, const struct dev_pm_ops *)) { const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; int err; if (!scsi_is_sdev_device(dev)) return 0; err = cb(dev, pm); scsi_device_resume(to_scsi_device(dev)); dev_dbg(dev, "scsi resume: %d\n", err); return err; } static int scsi_bus_prepare(struct device *dev) { if (scsi_is_host_device(dev)) { /* Wait until async scanning is finished */ scsi_complete_async_scans(); } return 0; } static int scsi_bus_suspend(struct device *dev) { return scsi_bus_suspend_common(dev, do_scsi_suspend); } static int scsi_bus_resume(struct device *dev) { return scsi_bus_resume_common(dev, do_scsi_resume); } static int scsi_bus_freeze(struct device *dev) { return scsi_bus_suspend_common(dev, do_scsi_freeze); } static int scsi_bus_thaw(struct device *dev) { return scsi_bus_resume_common(dev, do_scsi_thaw); } static int scsi_bus_poweroff(struct device *dev) { return scsi_bus_suspend_common(dev, do_scsi_poweroff); } static int scsi_bus_restore(struct device *dev) { return scsi_bus_resume_common(dev, do_scsi_restore); } #else /* CONFIG_PM_SLEEP */ #define scsi_bus_prepare NULL #define scsi_bus_suspend NULL #define scsi_bus_resume NULL #define scsi_bus_freeze NULL #define scsi_bus_thaw NULL #define scsi_bus_poweroff NULL #define scsi_bus_restore NULL #endif /* CONFIG_PM_SLEEP */ static int sdev_runtime_suspend(struct device *dev) { const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; struct scsi_device *sdev = to_scsi_device(dev); int err = 0; err = blk_pre_runtime_suspend(sdev->request_queue); if (err) return err; if (pm && pm->runtime_suspend) err = pm->runtime_suspend(dev); blk_post_runtime_suspend(sdev->request_queue, err); return err; } static int scsi_runtime_suspend(struct device *dev) { int err = 0; dev_dbg(dev, "scsi_runtime_suspend\n"); if (scsi_is_sdev_device(dev)) err = sdev_runtime_suspend(dev); /* Insert hooks here for targets, hosts, and transport classes */ return err; } static int sdev_runtime_resume(struct device *dev) { struct scsi_device *sdev = to_scsi_device(dev); const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; int err = 0; blk_pre_runtime_resume(sdev->request_queue); if (pm && pm->runtime_resume) err = pm->runtime_resume(dev); blk_post_runtime_resume(sdev->request_queue); return err; } static int scsi_runtime_resume(struct device *dev) { int err = 0; dev_dbg(dev, "scsi_runtime_resume\n"); if (scsi_is_sdev_device(dev)) err = sdev_runtime_resume(dev); /* Insert hooks here for targets, hosts, and transport classes */ return err; } static int scsi_runtime_idle(struct device *dev) { dev_dbg(dev, "scsi_runtime_idle\n"); /* Insert hooks here for targets, hosts, and transport classes */ if (scsi_is_sdev_device(dev)) { pm_runtime_mark_last_busy(dev); pm_runtime_autosuspend(dev); return -EBUSY; } return 0; } int scsi_autopm_get_device(struct scsi_device *sdev) { int err; err = pm_runtime_get_sync(&sdev->sdev_gendev); if (err < 0 && err !=-EACCES) pm_runtime_put_sync(&sdev->sdev_gendev); else err = 0; return err; } EXPORT_SYMBOL_GPL(scsi_autopm_get_device); void scsi_autopm_put_device(struct scsi_device *sdev) { pm_runtime_put_sync(&sdev->sdev_gendev); } EXPORT_SYMBOL_GPL(scsi_autopm_put_device); void scsi_autopm_get_target(struct scsi_target *starget) { pm_runtime_get_sync(&starget->dev); } void scsi_autopm_put_target(struct scsi_target *starget) { pm_runtime_put_sync(&starget->dev); } int scsi_autopm_get_host(struct Scsi_Host *shost) { int err; err = pm_runtime_get_sync(&shost->shost_gendev); if (err < 0 && err !=-EACCES) pm_runtime_put_sync(&shost->shost_gendev); else err = 0; return err; } void scsi_autopm_put_host(struct Scsi_Host *shost) { pm_runtime_put_sync(&shost->shost_gendev); } const struct dev_pm_ops scsi_bus_pm_ops = { .prepare = scsi_bus_prepare, .suspend = scsi_bus_suspend, .resume = scsi_bus_resume, .freeze = scsi_bus_freeze, .thaw = scsi_bus_thaw, .poweroff = scsi_bus_poweroff, .restore = scsi_bus_restore, .runtime_suspend = scsi_runtime_suspend, .runtime_resume = scsi_runtime_resume, .runtime_idle = scsi_runtime_idle, }; |
| 77 45 39 4 4 77 2 1 40 14 44 2 29 7 6 16 12 13 2 81 71 82 71 81 71 20 13 7 907 5 2 5 841 236 201 41 131 148 40 40 22 23 23 5 149 39 3 2 2 15 13 23 89 25 89 233 230 234 234 234 233 234 150 127 30 100 99 100 100 100 8 8 5 100 74 74 73 74 74 74 73 1 73 73 74 73 72 1 74 74 11 74 171 12 171 11 10 10 10 3 297 102 296 1 282 293 295 16 12 303 303 301 303 302 74 74 241 172 172 168 271 271 240 168 167 167 236 89 239 74 280 301 232 295 280 297 294 36 9 39 301 302 303 9 9 9 5 4 3 3 1 4 22 31 29 27 9 22 7 22 22 22 22 22 22 30 24 479 428 6 6 2 12 20 20 20 20 20 20 4 20 3 14 20 14 6 6 4 6 78 78 41 41 78 78 78 5 5 5 5 5 5 5 5 5 5 5 5 5 2 2 35 35 35 35 258 259 259 259 260 257 260 259 176 176 175 175 1 176 17 8 17 66 66 17 17 17 17 17 17 17 17 17 66 4 4 4 4 4 4 4 4 6 6 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Support for INET connection oriented protocols. * * Authors: See the TCP sources */ #include <linux/module.h> #include <linux/jhash.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #include <net/inet_timewait_sock.h> #include <net/ip.h> #include <net/route.h> #include <net/tcp_states.h> #include <net/xfrm.h> #include <net/tcp.h> #include <net/sock_reuseport.h> #include <net/addrconf.h> #if IS_ENABLED(CONFIG_IPV6) /* match_sk*_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses * if IPv6 only, and any IPv4 addresses * if not IPv6 only * match_sk*_wildcard == false: addresses must be exactly the same, i.e. * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY, * and 0.0.0.0 equals to 0.0.0.0 only */ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, const struct in6_addr *sk2_rcv_saddr6, __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, bool sk1_ipv6only, bool sk2_ipv6only, bool match_sk1_wildcard, bool match_sk2_wildcard) { int addr_type = ipv6_addr_type(sk1_rcv_saddr6); int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; /* if both are mapped, treat as IPv4 */ if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) { if (!sk2_ipv6only) { if (sk1_rcv_saddr == sk2_rcv_saddr) return true; return (match_sk1_wildcard && !sk1_rcv_saddr) || (match_sk2_wildcard && !sk2_rcv_saddr); } return false; } if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY) return true; if (addr_type2 == IPV6_ADDR_ANY && match_sk2_wildcard && !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) return true; if (addr_type == IPV6_ADDR_ANY && match_sk1_wildcard && !(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED)) return true; if (sk2_rcv_saddr6 && ipv6_addr_equal(sk1_rcv_saddr6, sk2_rcv_saddr6)) return true; return false; } #endif /* match_sk*_wildcard == true: 0.0.0.0 equals to any IPv4 addresses * match_sk*_wildcard == false: addresses must be exactly the same, i.e. * 0.0.0.0 only equals to 0.0.0.0 */ static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, bool sk2_ipv6only, bool match_sk1_wildcard, bool match_sk2_wildcard) { if (!sk2_ipv6only) { if (sk1_rcv_saddr == sk2_rcv_saddr) return true; return (match_sk1_wildcard && !sk1_rcv_saddr) || (match_sk2_wildcard && !sk2_rcv_saddr); } return false; } bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, bool match_wildcard) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) return ipv6_rcv_saddr_equal(&sk->sk_v6_rcv_saddr, inet6_rcv_saddr(sk2), sk->sk_rcv_saddr, sk2->sk_rcv_saddr, ipv6_only_sock(sk), ipv6_only_sock(sk2), match_wildcard, match_wildcard); #endif return ipv4_rcv_saddr_equal(sk->sk_rcv_saddr, sk2->sk_rcv_saddr, ipv6_only_sock(sk2), match_wildcard, match_wildcard); } EXPORT_SYMBOL(inet_rcv_saddr_equal); bool inet_rcv_saddr_any(const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) return ipv6_addr_any(&sk->sk_v6_rcv_saddr); #endif return !sk->sk_rcv_saddr; } /** * inet_sk_get_local_port_range - fetch ephemeral ports range * @sk: socket * @low: pointer to low port * @high: pointer to high port * * Fetch netns port range (/proc/sys/net/ipv4/ip_local_port_range) * Range can be overridden if socket got IP_LOCAL_PORT_RANGE option. * Returns true if IP_LOCAL_PORT_RANGE was set on this socket. */ bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high) { int lo, hi, sk_lo, sk_hi; bool local_range = false; u32 sk_range; inet_get_local_port_range(sock_net(sk), &lo, &hi); sk_range = READ_ONCE(inet_sk(sk)->local_port_range); if (unlikely(sk_range)) { sk_lo = sk_range & 0xffff; sk_hi = sk_range >> 16; if (lo <= sk_lo && sk_lo <= hi) lo = sk_lo; if (lo <= sk_hi && sk_hi <= hi) hi = sk_hi; local_range = true; } *low = lo; *high = hi; return local_range; } EXPORT_SYMBOL(inet_sk_get_local_port_range); static bool inet_use_bhash2_on_bind(const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) { int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); if (addr_type == IPV6_ADDR_ANY) return false; if (addr_type != IPV6_ADDR_MAPPED) return true; } #endif return sk->sk_rcv_saddr != htonl(INADDR_ANY); } static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2, kuid_t sk_uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { int bound_dev_if2; if (sk == sk2) return false; bound_dev_if2 = READ_ONCE(sk2->sk_bound_dev_if); if (!sk->sk_bound_dev_if || !bound_dev_if2 || sk->sk_bound_dev_if == bound_dev_if2) { if (sk->sk_reuse && sk2->sk_reuse && sk2->sk_state != TCP_LISTEN) { if (!relax || (!reuseport_ok && sk->sk_reuseport && sk2->sk_reuseport && reuseport_cb_ok && (sk2->sk_state == TCP_TIME_WAIT || uid_eq(sk_uid, sock_i_uid(sk2))))) return true; } else if (!reuseport_ok || !sk->sk_reuseport || !sk2->sk_reuseport || !reuseport_cb_ok || (sk2->sk_state != TCP_TIME_WAIT && !uid_eq(sk_uid, sock_i_uid(sk2)))) { return true; } } return false; } static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2, kuid_t sk_uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { if (ipv6_only_sock(sk2)) { if (sk->sk_family == AF_INET) return false; #if IS_ENABLED(CONFIG_IPV6) if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) return false; #endif } return inet_bind_conflict(sk, sk2, sk_uid, relax, reuseport_cb_ok, reuseport_ok); } static bool inet_bhash2_conflict(const struct sock *sk, const struct inet_bind2_bucket *tb2, kuid_t sk_uid, bool relax, bool reuseport_cb_ok, bool reuseport_ok) { struct sock *sk2; sk_for_each_bound(sk2, &tb2->owners) { if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax, reuseport_cb_ok, reuseport_ok)) return true; } return false; } #define sk_for_each_bound_bhash(__sk, __tb2, __tb) \ hlist_for_each_entry(__tb2, &(__tb)->bhash2, bhash_node) \ sk_for_each_bound((__sk), &(__tb2)->owners) /* This should be called only when the tb and tb2 hashbuckets' locks are held */ static int inet_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, const struct inet_bind2_bucket *tb2, /* may be null */ bool relax, bool reuseport_ok) { kuid_t uid = sock_i_uid((struct sock *)sk); struct sock_reuseport *reuseport_cb; bool reuseport_cb_ok; struct sock *sk2; rcu_read_lock(); reuseport_cb = rcu_dereference(sk->sk_reuseport_cb); /* paired with WRITE_ONCE() in __reuseport_(add|detach)_closed_sock */ reuseport_cb_ok = !reuseport_cb || READ_ONCE(reuseport_cb->num_closed_socks); rcu_read_unlock(); /* Conflicts with an existing IPV6_ADDR_ANY (if ipv6) or INADDR_ANY (if * ipv4) should have been checked already. We need to do these two * checks separately because their spinlocks have to be acquired/released * independently of each other, to prevent possible deadlocks */ if (inet_use_bhash2_on_bind(sk)) return tb2 && inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, reuseport_ok); /* Unlike other sk lookup places we do not check * for sk_net here, since _all_ the socks listed * in tb->owners and tb2->owners list belong * to the same net - the one this bucket belongs to. */ sk_for_each_bound_bhash(sk2, tb2, tb) { if (!inet_bind_conflict(sk, sk2, uid, relax, reuseport_cb_ok, reuseport_ok)) continue; if (inet_rcv_saddr_equal(sk, sk2, true)) return true; } return false; } /* Determine if there is a bind conflict with an existing IPV6_ADDR_ANY (if ipv6) or * INADDR_ANY (if ipv4) socket. * * Caller must hold bhash hashbucket lock with local bh disabled, to protect * against concurrent binds on the port for addr any */ static bool inet_bhash2_addr_any_conflict(const struct sock *sk, int port, int l3mdev, bool relax, bool reuseport_ok) { kuid_t uid = sock_i_uid((struct sock *)sk); const struct net *net = sock_net(sk); struct sock_reuseport *reuseport_cb; struct inet_bind_hashbucket *head2; struct inet_bind2_bucket *tb2; bool conflict = false; bool reuseport_cb_ok; rcu_read_lock(); reuseport_cb = rcu_dereference(sk->sk_reuseport_cb); /* paired with WRITE_ONCE() in __reuseport_(add|detach)_closed_sock */ reuseport_cb_ok = !reuseport_cb || READ_ONCE(reuseport_cb->num_closed_socks); rcu_read_unlock(); head2 = inet_bhash2_addr_any_hashbucket(sk, net, port); spin_lock(&head2->lock); inet_bind_bucket_for_each(tb2, &head2->chain) { if (!inet_bind2_bucket_match_addr_any(tb2, net, port, l3mdev, sk)) continue; if (!inet_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, reuseport_ok)) continue; conflict = true; break; } spin_unlock(&head2->lock); return conflict; } /* * Find an open port number for the socket. Returns with the * inet_bind_hashbucket locks held if successful. */ static struct inet_bind_hashbucket * inet_csk_find_open_port(const struct sock *sk, struct inet_bind_bucket **tb_ret, struct inet_bind2_bucket **tb2_ret, struct inet_bind_hashbucket **head2_ret, int *port_ret) { struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); int i, low, high, attempt_half, port, l3mdev; struct inet_bind_hashbucket *head, *head2; struct net *net = sock_net(sk); struct inet_bind2_bucket *tb2; struct inet_bind_bucket *tb; u32 remaining, offset; bool relax = false; l3mdev = inet_sk_bound_l3mdev(sk); ports_exhausted: attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0; other_half_scan: inet_sk_get_local_port_range(sk, &low, &high); high++; /* [32768, 60999] -> [32768, 61000[ */ if (high - low < 4) attempt_half = 0; if (attempt_half) { int half = low + (((high - low) >> 2) << 1); if (attempt_half == 1) high = half; else low = half; } remaining = high - low; if (likely(remaining > 1)) remaining &= ~1U; offset = get_random_u32_below(remaining); /* __inet_hash_connect() favors ports having @low parity * We do the opposite to not pollute connect() users. */ offset |= 1U; other_parity_scan: port = low + offset; for (i = 0; i < remaining; i += 2, port += 2) { if (unlikely(port >= high)) port -= remaining; if (inet_is_local_reserved_port(net, port)) continue; head = &hinfo->bhash[inet_bhashfn(net, port, hinfo->bhash_size)]; spin_lock_bh(&head->lock); if (inet_use_bhash2_on_bind(sk)) { if (inet_bhash2_addr_any_conflict(sk, port, l3mdev, relax, false)) goto next_port; } head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); spin_lock(&head2->lock); tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); inet_bind_bucket_for_each(tb, &head->chain) if (inet_bind_bucket_match(tb, net, port, l3mdev)) { if (!inet_csk_bind_conflict(sk, tb, tb2, relax, false)) goto success; spin_unlock(&head2->lock); goto next_port; } tb = NULL; goto success; next_port: spin_unlock_bh(&head->lock); cond_resched(); } offset--; if (!(offset & 1)) goto other_parity_scan; if (attempt_half == 1) { /* OK we now try the upper half of the range */ attempt_half = 2; goto other_half_scan; } if (READ_ONCE(net->ipv4.sysctl_ip_autobind_reuse) && !relax) { /* We still have a chance to connect to different destinations */ relax = true; goto ports_exhausted; } return NULL; success: *port_ret = port; *tb_ret = tb; *tb2_ret = tb2; *head2_ret = head2; return head; } static inline int sk_reuseport_match(struct inet_bind_bucket *tb, struct sock *sk) { kuid_t uid = sock_i_uid(sk); if (tb->fastreuseport <= 0) return 0; if (!sk->sk_reuseport) return 0; if (rcu_access_pointer(sk->sk_reuseport_cb)) return 0; if (!uid_eq(tb->fastuid, uid)) return 0; /* We only need to check the rcv_saddr if this tb was once marked * without fastreuseport and then was reset, as we can only know that * the fast_*rcv_saddr doesn't have any conflicts with the socks on the * owners list. */ if (tb->fastreuseport == FASTREUSEPORT_ANY) return 1; #if IS_ENABLED(CONFIG_IPV6) if (tb->fast_sk_family == AF_INET6) return ipv6_rcv_saddr_equal(&tb->fast_v6_rcv_saddr, inet6_rcv_saddr(sk), tb->fast_rcv_saddr, sk->sk_rcv_saddr, tb->fast_ipv6_only, ipv6_only_sock(sk), true, false); #endif return ipv4_rcv_saddr_equal(tb->fast_rcv_saddr, sk->sk_rcv_saddr, ipv6_only_sock(sk), true, false); } void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, struct sock *sk) { kuid_t uid = sock_i_uid(sk); bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; if (hlist_empty(&tb->bhash2)) { tb->fastreuse = reuse; if (sk->sk_reuseport) { tb->fastreuseport = FASTREUSEPORT_ANY; tb->fastuid = uid; tb->fast_rcv_saddr = sk->sk_rcv_saddr; tb->fast_ipv6_only = ipv6_only_sock(sk); tb->fast_sk_family = sk->sk_family; #if IS_ENABLED(CONFIG_IPV6) tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; #endif } else { tb->fastreuseport = 0; } } else { if (!reuse) tb->fastreuse = 0; if (sk->sk_reuseport) { /* We didn't match or we don't have fastreuseport set on * the tb, but we have sk_reuseport set on this socket * and we know that there are no bind conflicts with * this socket in this tb, so reset our tb's reuseport * settings so that any subsequent sockets that match * our current socket will be put on the fast path. * * If we reset we need to set FASTREUSEPORT_STRICT so we * do extra checking for all subsequent sk_reuseport * socks. */ if (!sk_reuseport_match(tb, sk)) { tb->fastreuseport = FASTREUSEPORT_STRICT; tb->fastuid = uid; tb->fast_rcv_saddr = sk->sk_rcv_saddr; tb->fast_ipv6_only = ipv6_only_sock(sk); tb->fast_sk_family = sk->sk_family; #if IS_ENABLED(CONFIG_IPV6) tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; #endif } } else { tb->fastreuseport = 0; } } } /* Obtain a reference to a local port for the given sock, * if snum is zero it means select any available local port. * We try to allocate an odd port (and leave even ports for connect()) */ int inet_csk_get_port(struct sock *sk, unsigned short snum) { struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; bool found_port = false, check_bind_conflict = true; bool bhash_created = false, bhash2_created = false; int ret = -EADDRINUSE, port = snum, l3mdev; struct inet_bind_hashbucket *head, *head2; struct inet_bind2_bucket *tb2 = NULL; struct inet_bind_bucket *tb = NULL; bool head2_lock_acquired = false; struct net *net = sock_net(sk); l3mdev = inet_sk_bound_l3mdev(sk); if (!port) { head = inet_csk_find_open_port(sk, &tb, &tb2, &head2, &port); if (!head) return ret; head2_lock_acquired = true; if (tb && tb2) goto success; found_port = true; } else { head = &hinfo->bhash[inet_bhashfn(net, port, hinfo->bhash_size)]; spin_lock_bh(&head->lock); inet_bind_bucket_for_each(tb, &head->chain) if (inet_bind_bucket_match(tb, net, port, l3mdev)) break; } if (!tb) { tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep, net, head, port, l3mdev); if (!tb) goto fail_unlock; bhash_created = true; } if (!found_port) { if (!hlist_empty(&tb->bhash2)) { if (sk->sk_reuse == SK_FORCE_REUSE || (tb->fastreuse > 0 && reuse) || sk_reuseport_match(tb, sk)) check_bind_conflict = false; } if (check_bind_conflict && inet_use_bhash2_on_bind(sk)) { if (inet_bhash2_addr_any_conflict(sk, port, l3mdev, true, true)) goto fail_unlock; } head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); spin_lock(&head2->lock); head2_lock_acquired = true; tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); } if (!tb2) { tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep, net, head2, tb, sk); if (!tb2) goto fail_unlock; bhash2_created = true; } if (!found_port && check_bind_conflict) { if (inet_csk_bind_conflict(sk, tb, tb2, true, true)) goto fail_unlock; } success: inet_csk_update_fastreuse(tb, sk); if (!inet_csk(sk)->icsk_bind_hash) inet_bind_hash(sk, tb, tb2, port); WARN_ON(inet_csk(sk)->icsk_bind_hash != tb); WARN_ON(inet_csk(sk)->icsk_bind2_hash != tb2); ret = 0; fail_unlock: if (ret) { if (bhash2_created) inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, tb2); if (bhash_created) inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb); } if (head2_lock_acquired) spin_unlock(&head2->lock); spin_unlock_bh(&head->lock); return ret; } EXPORT_SYMBOL_GPL(inet_csk_get_port); /* * Wait for an incoming connection, avoid race conditions. This must be called * with the socket locked. */ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) { struct inet_connection_sock *icsk = inet_csk(sk); DEFINE_WAIT(wait); int err; /* * True wake-one mechanism for incoming connections: only * one process gets woken up, not the 'whole herd'. * Since we do not 'race & poll' for established sockets * anymore, the common case will execute the loop only once. * * Subtle issue: "add_wait_queue_exclusive()" will be added * after any current non-exclusive waiters, and we know that * it will always _stay_ after any new non-exclusive waiters * because all non-exclusive waiters are added at the * beginning of the wait-queue. As such, it's ok to "drop" * our exclusiveness temporarily when we get woken up without * having to remove and re-insert us on the wait queue. */ for (;;) { prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); release_sock(sk); if (reqsk_queue_empty(&icsk->icsk_accept_queue)) timeo = schedule_timeout(timeo); sched_annotate_sleep(); lock_sock(sk); err = 0; if (!reqsk_queue_empty(&icsk->icsk_accept_queue)) break; err = -EINVAL; if (sk->sk_state != TCP_LISTEN) break; err = sock_intr_errno(timeo); if (signal_pending(current)) break; err = -EAGAIN; if (!timeo) break; } finish_wait(sk_sleep(sk), &wait); return err; } /* * This will accept the next outstanding connection. */ struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg) { struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct request_sock *req; struct sock *newsk; int error; lock_sock(sk); /* We need to make sure that this socket is listening, * and that it has something pending. */ error = -EINVAL; if (sk->sk_state != TCP_LISTEN) goto out_err; /* Find already established connection */ if (reqsk_queue_empty(queue)) { long timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); /* If this is a non blocking socket don't sleep */ error = -EAGAIN; if (!timeo) goto out_err; error = inet_csk_wait_for_connect(sk, timeo); if (error) goto out_err; } req = reqsk_queue_remove(queue, sk); arg->is_empty = reqsk_queue_empty(queue); newsk = req->sk; if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { spin_lock_bh(&queue->fastopenq.lock); if (tcp_rsk(req)->tfo_listener) { /* We are still waiting for the final ACK from 3WHS * so can't free req now. Instead, we set req->sk to * NULL to signify that the child socket is taken * so reqsk_fastopen_remove() will free the req * when 3WHS finishes (or is aborted). */ req->sk = NULL; req = NULL; } spin_unlock_bh(&queue->fastopenq.lock); } out: release_sock(sk); if (newsk && mem_cgroup_sockets_enabled) { gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL; int amt = 0; /* atomically get the memory usage, set and charge the * newsk->sk_memcg. */ lock_sock(newsk); mem_cgroup_sk_alloc(newsk); if (newsk->sk_memcg) { /* The socket has not been accepted yet, no need * to look at newsk->sk_wmem_queued. */ amt = sk_mem_pages(newsk->sk_forward_alloc + atomic_read(&newsk->sk_rmem_alloc)); } if (amt) mem_cgroup_charge_skmem(newsk->sk_memcg, amt, gfp); kmem_cache_charge(newsk, gfp); release_sock(newsk); } if (req) reqsk_put(req); if (newsk) inet_init_csk_locks(newsk); return newsk; out_err: newsk = NULL; req = NULL; arg->err = error; goto out; } EXPORT_SYMBOL(inet_csk_accept); /* * Using different timers for retransmit, delayed acks and probes * We may wish use just one timer maintaining a list of expire jiffies * to optimize. */ void inet_csk_init_xmit_timers(struct sock *sk, void (*retransmit_handler)(struct timer_list *t), void (*delack_handler)(struct timer_list *t), void (*keepalive_handler)(struct timer_list *t)) { struct inet_connection_sock *icsk = inet_csk(sk); timer_setup(&icsk->icsk_retransmit_timer, retransmit_handler, 0); timer_setup(&icsk->icsk_delack_timer, delack_handler, 0); timer_setup(&sk->sk_timer, keepalive_handler, 0); icsk->icsk_pending = icsk->icsk_ack.pending = 0; } EXPORT_SYMBOL(inet_csk_init_xmit_timers); void inet_csk_clear_xmit_timers(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); smp_store_release(&icsk->icsk_pending, 0); smp_store_release(&icsk->icsk_ack.pending, 0); sk_stop_timer(sk, &icsk->icsk_retransmit_timer); sk_stop_timer(sk, &icsk->icsk_delack_timer); sk_stop_timer(sk, &sk->sk_timer); } EXPORT_SYMBOL(inet_csk_clear_xmit_timers); void inet_csk_clear_xmit_timers_sync(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); /* ongoing timer handlers need to acquire socket lock. */ sock_not_owned_by_me(sk); smp_store_release(&icsk->icsk_pending, 0); smp_store_release(&icsk->icsk_ack.pending, 0); sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer); sk_stop_timer_sync(sk, &icsk->icsk_delack_timer); sk_stop_timer_sync(sk, &sk->sk_timer); } void inet_csk_delete_keepalive_timer(struct sock *sk) { sk_stop_timer(sk, &sk->sk_timer); } EXPORT_SYMBOL(inet_csk_delete_keepalive_timer); void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len) { sk_reset_timer(sk, &sk->sk_timer, jiffies + len); } EXPORT_SYMBOL(inet_csk_reset_keepalive_timer); struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, const struct request_sock *req) { const struct inet_request_sock *ireq = inet_rsk(req); struct net *net = read_pnet(&ireq->ireq_net); struct ip_options_rcu *opt; struct rtable *rt; rcu_read_lock(); opt = rcu_dereference(ireq->ireq_opt); flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), sk->sk_protocol, inet_sk_flowi_flags(sk), (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr, ireq->ir_loc_addr, ireq->ir_rmt_port, htons(ireq->ir_num), sk->sk_uid); security_req_classify_flow(req, flowi4_to_flowi_common(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; rcu_read_unlock(); return &rt->dst; route_err: ip_rt_put(rt); no_route: rcu_read_unlock(); __IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } EXPORT_SYMBOL_GPL(inet_csk_route_req); struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *newsk, const struct request_sock *req) { const struct inet_request_sock *ireq = inet_rsk(req); struct net *net = read_pnet(&ireq->ireq_net); struct inet_sock *newinet = inet_sk(newsk); struct ip_options_rcu *opt; struct flowi4 *fl4; struct rtable *rt; opt = rcu_dereference(ireq->ireq_opt); fl4 = &newinet->cork.fl.u.ip4; flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark, ip_sock_rt_tos(sk), ip_sock_rt_scope(sk), sk->sk_protocol, inet_sk_flowi_flags(sk), (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr, ireq->ir_loc_addr, ireq->ir_rmt_port, htons(ireq->ir_num), sk->sk_uid); security_req_classify_flow(req, flowi4_to_flowi_common(fl4)); rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; return &rt->dst; route_err: ip_rt_put(rt); no_route: __IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } EXPORT_SYMBOL_GPL(inet_csk_route_child_sock); /* Decide when to expire the request and when to resend SYN-ACK */ static void syn_ack_recalc(struct request_sock *req, const int max_syn_ack_retries, const u8 rskq_defer_accept, int *expire, int *resend) { if (!rskq_defer_accept) { *expire = req->num_timeout >= max_syn_ack_retries; *resend = 1; return; } *expire = req->num_timeout >= max_syn_ack_retries && (!inet_rsk(req)->acked || req->num_timeout >= rskq_defer_accept); /* Do not resend while waiting for data after ACK, * start to resend on end of deferring period to give * last chance for data or ACK to create established socket. */ *resend = !inet_rsk(req)->acked || req->num_timeout >= rskq_defer_accept - 1; } int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req) { int err = req->rsk_ops->rtx_syn_ack(parent, req); if (!err) req->num_retrans++; return err; } EXPORT_SYMBOL(inet_rtx_syn_ack); static struct request_sock * reqsk_alloc_noprof(const struct request_sock_ops *ops, struct sock *sk_listener, bool attach_listener) { struct request_sock *req; req = kmem_cache_alloc_noprof(ops->slab, GFP_ATOMIC | __GFP_NOWARN); if (!req) return NULL; req->rsk_listener = NULL; if (attach_listener) { if (unlikely(!refcount_inc_not_zero(&sk_listener->sk_refcnt))) { kmem_cache_free(ops->slab, req); return NULL; } req->rsk_listener = sk_listener; } req->rsk_ops = ops; req_to_sk(req)->sk_prot = sk_listener->sk_prot; sk_node_init(&req_to_sk(req)->sk_node); sk_tx_queue_clear(req_to_sk(req)); req->saved_syn = NULL; req->syncookie = 0; req->timeout = 0; req->num_timeout = 0; req->num_retrans = 0; req->sk = NULL; refcount_set(&req->rsk_refcnt, 0); return req; } #define reqsk_alloc(...) alloc_hooks(reqsk_alloc_noprof(__VA_ARGS__)) struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, bool attach_listener) { struct request_sock *req = reqsk_alloc(ops, sk_listener, attach_listener); if (req) { struct inet_request_sock *ireq = inet_rsk(req); ireq->ireq_opt = NULL; #if IS_ENABLED(CONFIG_IPV6) ireq->pktopts = NULL; #endif atomic64_set(&ireq->ir_cookie, 0); ireq->ireq_state = TCP_NEW_SYN_RECV; write_pnet(&ireq->ireq_net, sock_net(sk_listener)); ireq->ireq_family = sk_listener->sk_family; req->timeout = TCP_TIMEOUT_INIT; } return req; } EXPORT_SYMBOL(inet_reqsk_alloc); static struct request_sock *inet_reqsk_clone(struct request_sock *req, struct sock *sk) { struct sock *req_sk, *nreq_sk; struct request_sock *nreq; nreq = kmem_cache_alloc(req->rsk_ops->slab, GFP_ATOMIC | __GFP_NOWARN); if (!nreq) { __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); /* paired with refcount_inc_not_zero() in reuseport_migrate_sock() */ sock_put(sk); return NULL; } req_sk = req_to_sk(req); nreq_sk = req_to_sk(nreq); memcpy(nreq_sk, req_sk, offsetof(struct sock, sk_dontcopy_begin)); unsafe_memcpy(&nreq_sk->sk_dontcopy_end, &req_sk->sk_dontcopy_end, req->rsk_ops->obj_size - offsetof(struct sock, sk_dontcopy_end), /* alloc is larger than struct, see above */); sk_node_init(&nreq_sk->sk_node); nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping; #ifdef CONFIG_SOCK_RX_QUEUE_MAPPING nreq_sk->sk_rx_queue_mapping = req_sk->sk_rx_queue_mapping; #endif nreq_sk->sk_incoming_cpu = req_sk->sk_incoming_cpu; nreq->rsk_listener = sk; /* We need not acquire fastopenq->lock * because the child socket is locked in inet_csk_listen_stop(). */ if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(nreq)->tfo_listener) rcu_assign_pointer(tcp_sk(nreq->sk)->fastopen_rsk, nreq); return nreq; } static void reqsk_queue_migrated(struct request_sock_queue *queue, const struct request_sock *req) { if (req->num_timeout == 0) atomic_inc(&queue->young); atomic_inc(&queue->qlen); } static void reqsk_migrate_reset(struct request_sock *req) { req->saved_syn = NULL; #if IS_ENABLED(CONFIG_IPV6) inet_rsk(req)->ipv6_opt = NULL; inet_rsk(req)->pktopts = NULL; #else inet_rsk(req)->ireq_opt = NULL; #endif } /* return true if req was found in the ehash table */ static bool reqsk_queue_unlink(struct request_sock *req) { struct sock *sk = req_to_sk(req); bool found = false; if (sk_hashed(sk)) { struct inet_hashinfo *hashinfo = tcp_or_dccp_get_hashinfo(sk); spinlock_t *lock = inet_ehash_lockp(hashinfo, req->rsk_hash); spin_lock(lock); found = __sk_nulls_del_node_init_rcu(sk); spin_unlock(lock); } return found; } static bool __inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req, bool from_timer) { bool unlinked = reqsk_queue_unlink(req); if (!from_timer && timer_delete_sync(&req->rsk_timer)) reqsk_put(req); if (unlinked) { reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); reqsk_put(req); } return unlinked; } bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) { return __inet_csk_reqsk_queue_drop(sk, req, false); } EXPORT_SYMBOL(inet_csk_reqsk_queue_drop); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req) { inet_csk_reqsk_queue_drop(sk, req); reqsk_put(req); } EXPORT_SYMBOL(inet_csk_reqsk_queue_drop_and_put); static void reqsk_timer_handler(struct timer_list *t) { struct request_sock *req = from_timer(req, t, rsk_timer); struct request_sock *nreq = NULL, *oreq = req; struct sock *sk_listener = req->rsk_listener; struct inet_connection_sock *icsk; struct request_sock_queue *queue; struct net *net; int max_syn_ack_retries, qlen, expire = 0, resend = 0; if (inet_sk_state_load(sk_listener) != TCP_LISTEN) { struct sock *nsk; nsk = reuseport_migrate_sock(sk_listener, req_to_sk(req), NULL); if (!nsk) goto drop; nreq = inet_reqsk_clone(req, nsk); if (!nreq) goto drop; /* The new timer for the cloned req can decrease the 2 * by calling inet_csk_reqsk_queue_drop_and_put(), so * hold another count to prevent use-after-free and * call reqsk_put() just before return. */ refcount_set(&nreq->rsk_refcnt, 2 + 1); timer_setup(&nreq->rsk_timer, reqsk_timer_handler, TIMER_PINNED); reqsk_queue_migrated(&inet_csk(nsk)->icsk_accept_queue, req); req = nreq; sk_listener = nsk; } icsk = inet_csk(sk_listener); net = sock_net(sk_listener); max_syn_ack_retries = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_synack_retries); /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. * If synack was not acknowledged for 1 second, it means * one of the following things: synack was lost, ack was lost, * rtt is high or nobody planned to ack (i.e. synflood). * When server is a bit loaded, queue is populated with old * open requests, reducing effective size of queue. * When server is well loaded, queue size reduces to zero * after several minutes of work. It is not synflood, * it is normal operation. The solution is pruning * too old entries overriding normal timeout, when * situation becomes dangerous. * * Essentially, we reserve half of room for young * embrions; and abort old ones without pity, if old * ones are about to clog our table. */ queue = &icsk->icsk_accept_queue; qlen = reqsk_queue_len(queue); if ((qlen << 1) > max(8U, READ_ONCE(sk_listener->sk_max_ack_backlog))) { int young = reqsk_queue_len_young(queue) << 1; while (max_syn_ack_retries > 2) { if (qlen < young) break; max_syn_ack_retries--; young <<= 1; } } syn_ack_recalc(req, max_syn_ack_retries, READ_ONCE(queue->rskq_defer_accept), &expire, &resend); req->rsk_ops->syn_ack_timeout(req); if (!expire && (!resend || !inet_rtx_syn_ack(sk_listener, req) || inet_rsk(req)->acked)) { if (req->num_timeout++ == 0) atomic_dec(&queue->young); mod_timer(&req->rsk_timer, jiffies + reqsk_timeout(req, TCP_RTO_MAX)); if (!nreq) return; if (!inet_ehash_insert(req_to_sk(nreq), req_to_sk(oreq), NULL)) { /* delete timer */ __inet_csk_reqsk_queue_drop(sk_listener, nreq, true); goto no_ownership; } __NET_INC_STATS(net, LINUX_MIB_TCPMIGRATEREQSUCCESS); reqsk_migrate_reset(oreq); reqsk_queue_removed(&inet_csk(oreq->rsk_listener)->icsk_accept_queue, oreq); reqsk_put(oreq); reqsk_put(nreq); return; } /* Even if we can clone the req, we may need not retransmit any more * SYN+ACKs (nreq->num_timeout > max_syn_ack_retries, etc), or another * CPU may win the "own_req" race so that inet_ehash_insert() fails. */ if (nreq) { __NET_INC_STATS(net, LINUX_MIB_TCPMIGRATEREQFAILURE); no_ownership: reqsk_migrate_reset(nreq); reqsk_queue_removed(queue, nreq); __reqsk_free(nreq); } drop: __inet_csk_reqsk_queue_drop(sk_listener, oreq, true); reqsk_put(oreq); } static bool reqsk_queue_hash_req(struct request_sock *req, unsigned long timeout) { bool found_dup_sk = false; if (!inet_ehash_insert(req_to_sk(req), NULL, &found_dup_sk)) return false; /* The timer needs to be setup after a successful insertion. */ timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); mod_timer(&req->rsk_timer, jiffies + timeout); /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. */ smp_wmb(); refcount_set(&req->rsk_refcnt, 2 + 1); return true; } bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout) { if (!reqsk_queue_hash_req(req, timeout)) return false; inet_csk_reqsk_queue_added(sk); return true; } EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add); static void inet_clone_ulp(const struct request_sock *req, struct sock *newsk, const gfp_t priority) { struct inet_connection_sock *icsk = inet_csk(newsk); if (!icsk->icsk_ulp_ops) return; icsk->icsk_ulp_ops->clone(req, newsk, priority); } /** * inet_csk_clone_lock - clone an inet socket, and lock its clone * @sk: the socket to clone * @req: request_sock * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) * * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) */ struct sock *inet_csk_clone_lock(const struct sock *sk, const struct request_sock *req, const gfp_t priority) { struct sock *newsk = sk_clone_lock(sk, priority); if (newsk) { struct inet_connection_sock *newicsk = inet_csk(newsk); inet_sk_set_state(newsk, TCP_SYN_RECV); newicsk->icsk_bind_hash = NULL; newicsk->icsk_bind2_hash = NULL; inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port; inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num; inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num); /* listeners have SOCK_RCU_FREE, not the children */ sock_reset_flag(newsk, SOCK_RCU_FREE); inet_sk(newsk)->mc_list = NULL; newsk->sk_mark = inet_rsk(req)->ir_mark; atomic64_set(&newsk->sk_cookie, atomic64_read(&inet_rsk(req)->ir_cookie)); newicsk->icsk_retransmits = 0; newicsk->icsk_backoff = 0; newicsk->icsk_probes_out = 0; newicsk->icsk_probes_tstamp = 0; /* Deinitialize accept_queue to trap illegal accesses. */ memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue)); inet_clone_ulp(req, newsk, priority); security_inet_csk_clone(newsk, req); } return newsk; } EXPORT_SYMBOL_GPL(inet_csk_clone_lock); /* * At this point, there should be no process reference to this * socket, and thus no user references at all. Therefore we * can assume the socket waitqueue is inactive and nobody will * try to jump onto it. */ void inet_csk_destroy_sock(struct sock *sk) { WARN_ON(sk->sk_state != TCP_CLOSE); WARN_ON(!sock_flag(sk, SOCK_DEAD)); /* It cannot be in hash table! */ WARN_ON(!sk_unhashed(sk)); /* If it has not 0 inet_sk(sk)->inet_num, it must be bound */ WARN_ON(inet_sk(sk)->inet_num && !inet_csk(sk)->icsk_bind_hash); sk->sk_prot->destroy(sk); sk_stream_kill_queues(sk); xfrm_sk_free_policy(sk); this_cpu_dec(*sk->sk_prot->orphan_count); sock_put(sk); } EXPORT_SYMBOL(inet_csk_destroy_sock); /* This function allows to force a closure of a socket after the call to * tcp/dccp_create_openreq_child(). */ void inet_csk_prepare_forced_close(struct sock *sk) __releases(&sk->sk_lock.slock) { /* sk_clone_lock locked the socket and set refcnt to 2 */ bh_unlock_sock(sk); sock_put(sk); inet_csk_prepare_for_destroy_sock(sk); inet_sk(sk)->inet_num = 0; } EXPORT_SYMBOL(inet_csk_prepare_forced_close); static int inet_ulp_can_listen(const struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ulp_ops && !icsk->icsk_ulp_ops->clone) return -EINVAL; return 0; } int inet_csk_listen_start(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); int err; err = inet_ulp_can_listen(sk); if (unlikely(err)) return err; reqsk_queue_alloc(&icsk->icsk_accept_queue); sk->sk_ack_backlog = 0; inet_csk_delack_init(sk); /* There is race window here: we announce ourselves listening, * but this transition is still not validated by get_port(). * It is OK, because this socket enters to hash table only * after validation is complete. */ inet_sk_state_store(sk, TCP_LISTEN); err = sk->sk_prot->get_port(sk, inet->inet_num); if (!err) { inet->inet_sport = htons(inet->inet_num); sk_dst_reset(sk); err = sk->sk_prot->hash(sk); if (likely(!err)) return 0; } inet_sk_set_state(sk, TCP_CLOSE); return err; } EXPORT_SYMBOL_GPL(inet_csk_listen_start); static void inet_child_forget(struct sock *sk, struct request_sock *req, struct sock *child) { sk->sk_prot->disconnect(child, O_NONBLOCK); sock_orphan(child); this_cpu_inc(*sk->sk_prot->orphan_count); if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req); BUG_ON(sk != req->rsk_listener); /* Paranoid, to prevent race condition if * an inbound pkt destined for child is * blocked by sock lock in tcp_v4_rcv(). * Also to satisfy an assertion in * tcp_v4_destroy_sock(). */ RCU_INIT_POINTER(tcp_sk(child)->fastopen_rsk, NULL); } inet_csk_destroy_sock(child); } struct sock *inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, struct sock *child) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; spin_lock(&queue->rskq_lock); if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_child_forget(sk, req, child); child = NULL; } else { req->sk = child; req->dl_next = NULL; if (queue->rskq_accept_head == NULL) WRITE_ONCE(queue->rskq_accept_head, req); else queue->rskq_accept_tail->dl_next = req; queue->rskq_accept_tail = req; sk_acceptq_added(sk); } spin_unlock(&queue->rskq_lock); return child; } EXPORT_SYMBOL(inet_csk_reqsk_queue_add); struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, struct request_sock *req, bool own_req) { if (own_req) { inet_csk_reqsk_queue_drop(req->rsk_listener, req); reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req); if (sk != req->rsk_listener) { /* another listening sk has been selected, * migrate the req to it. */ struct request_sock *nreq; /* hold a refcnt for the nreq->rsk_listener * which is assigned in inet_reqsk_clone() */ sock_hold(sk); nreq = inet_reqsk_clone(req, sk); if (!nreq) { inet_child_forget(sk, req, child); goto child_put; } refcount_set(&nreq->rsk_refcnt, 1); if (inet_csk_reqsk_queue_add(sk, nreq, child)) { __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQSUCCESS); reqsk_migrate_reset(req); reqsk_put(req); return child; } __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); reqsk_migrate_reset(nreq); __reqsk_free(nreq); } else if (inet_csk_reqsk_queue_add(sk, req, child)) { return child; } } /* Too bad, another child took ownership of the request, undo. */ child_put: bh_unlock_sock(child); sock_put(child); return NULL; } EXPORT_SYMBOL(inet_csk_complete_hashdance); /* * This routine closes sockets which have been at least partially * opened, but not yet accepted. */ void inet_csk_listen_stop(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct request_sock *next, *req; /* Following specs, it would be better either to send FIN * (and enter FIN-WAIT-1, it is normal close) * or to send active reset (abort). * Certainly, it is pretty dangerous while synflood, but it is * bad justification for our negligence 8) * To be honest, we are not able to make either * of the variants now. --ANK */ while ((req = reqsk_queue_remove(queue, sk)) != NULL) { struct sock *child = req->sk, *nsk; struct request_sock *nreq; local_bh_disable(); bh_lock_sock(child); WARN_ON(sock_owned_by_user(child)); sock_hold(child); nsk = reuseport_migrate_sock(sk, child, NULL); if (nsk) { nreq = inet_reqsk_clone(req, nsk); if (nreq) { refcount_set(&nreq->rsk_refcnt, 1); if (inet_csk_reqsk_queue_add(nsk, nreq, child)) { __NET_INC_STATS(sock_net(nsk), LINUX_MIB_TCPMIGRATEREQSUCCESS); reqsk_migrate_reset(req); } else { __NET_INC_STATS(sock_net(nsk), LINUX_MIB_TCPMIGRATEREQFAILURE); reqsk_migrate_reset(nreq); __reqsk_free(nreq); } /* inet_csk_reqsk_queue_add() has already * called inet_child_forget() on failure case. */ goto skip_child_forget; } } inet_child_forget(sk, req, child); skip_child_forget: reqsk_put(req); bh_unlock_sock(child); local_bh_enable(); sock_put(child); cond_resched(); } if (queue->fastopenq.rskq_rst_head) { /* Free all the reqs queued in rskq_rst_head. */ spin_lock_bh(&queue->fastopenq.lock); req = queue->fastopenq.rskq_rst_head; queue->fastopenq.rskq_rst_head = NULL; spin_unlock_bh(&queue->fastopenq.lock); while (req != NULL) { next = req->dl_next; reqsk_put(req); req = next; } } WARN_ON_ONCE(sk->sk_ack_backlog); } EXPORT_SYMBOL_GPL(inet_csk_listen_stop); void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr) { struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; const struct inet_sock *inet = inet_sk(sk); sin->sin_family = AF_INET; sin->sin_addr.s_addr = inet->inet_daddr; sin->sin_port = inet->inet_dport; } EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr); static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *fl) { const struct inet_sock *inet = inet_sk(sk); const struct ip_options_rcu *inet_opt; __be32 daddr = inet->inet_daddr; struct flowi4 *fl4; struct rtable *rt; rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; fl4 = &fl->u.ip4; rt = ip_route_output_ports(sock_net(sk), fl4, sk, daddr, inet->inet_saddr, inet->inet_dport, inet->inet_sport, sk->sk_protocol, ip_sock_rt_tos(sk), sk->sk_bound_dev_if); if (IS_ERR(rt)) rt = NULL; if (rt) sk_setup_caps(sk, &rt->dst); rcu_read_unlock(); return &rt->dst; } struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu) { struct dst_entry *dst = __sk_dst_check(sk, 0); struct inet_sock *inet = inet_sk(sk); if (!dst) { dst = inet_csk_rebuild_route(sk, &inet->cork.fl); if (!dst) goto out; } dst->ops->update_pmtu(dst, sk, NULL, mtu, true); dst = __sk_dst_check(sk, 0); if (!dst) dst = inet_csk_rebuild_route(sk, &inet->cork.fl); out: return dst; } EXPORT_SYMBOL_GPL(inet_csk_update_pmtu); |
| 101 45 38 99 99 99 261 260 98 96 260 260 258 260 260 258 5 260 4 258 260 260 259 257 223 259 2 2 2 2 2 259 1 252 252 252 252 252 275 272 275 197 197 197 197 63 165 166 66 104 104 68 118 118 103 118 118 57 118 116 97 60 61 61 97 44 97 56 12 12 12 56 193 182 190 26 193 193 193 192 26 193 159 158 158 4 2 158 159 4 4 4 4 4 4 4 4 4 4 4 4 23 19 19 19 23 23 23 23 23 23 23 23 23 23 23 10 10 10 10 10 11 11 10 6 6 6 11 8 9 2 9 2 9 6 9 3 9 4 9 4 9 7 9 1 3 2 2 1 1 12 11 12 11 9 2 2 11 1 1 10 1 9 2 2 9 9 3 3 1 6 2 7 7 12 99 95 95 55 55 6 88 64 52 99 3 3 3 3 2 2 2 1 1 1 1 3 137 36 36 11 6 5 5 5 5 1 1 5 1 4 1 27 27 27 8 8 8 8 8 8 8 8 6 8 8 8 8 1 1 1 1 1 11 1 11 2 9 5 1 2 14 12 3 2 11 7 6 5 5 3 5 1 10 10 8 7 3 2 1 1 11 2 11 11 11 10 8 10 25 3 1 2 26 2 2 2 2 23 7 1 6 16 16 6 19 31 31 31 30 2 28 20 20 8 8 8 28 2 1 27 4 23 26 2 2 2 31 24 17 17 17 17 2 1 5 2 5 5 5 3 3 2 2 5 4 4 4 4 4 18 18 18 18 18 18 6 6 6 4 4 3 4 4 4 3 3 2 3 1 3 3 3 2 3 1 3 2 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Forwarding database * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/rculist.h> #include <linux/spinlock.h> #include <linux/times.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/jhash.h> #include <linux/random.h> #include <linux/slab.h> #include <linux/atomic.h> #include <linux/unaligned.h> #include <linux/if_vlan.h> #include <net/switchdev.h> #include <trace/events/bridge.h> #include "br_private.h" static const struct rhashtable_params br_fdb_rht_params = { .head_offset = offsetof(struct net_bridge_fdb_entry, rhnode), .key_offset = offsetof(struct net_bridge_fdb_entry, key), .key_len = sizeof(struct net_bridge_fdb_key), .automatic_shrinking = true, }; static struct kmem_cache *br_fdb_cache __read_mostly; int __init br_fdb_init(void) { br_fdb_cache = KMEM_CACHE(net_bridge_fdb_entry, SLAB_HWCACHE_ALIGN); if (!br_fdb_cache) return -ENOMEM; return 0; } void br_fdb_fini(void) { kmem_cache_destroy(br_fdb_cache); } int br_fdb_hash_init(struct net_bridge *br) { return rhashtable_init(&br->fdb_hash_tbl, &br_fdb_rht_params); } void br_fdb_hash_fini(struct net_bridge *br) { rhashtable_destroy(&br->fdb_hash_tbl); } /* if topology_changing then use forward_delay (default 15 sec) * otherwise keep longer (default 5 minutes) */ static inline unsigned long hold_time(const struct net_bridge *br) { return br->topology_change ? br->forward_delay : br->ageing_time; } static inline int has_expired(const struct net_bridge *br, const struct net_bridge_fdb_entry *fdb) { return !test_bit(BR_FDB_STATIC, &fdb->flags) && !test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags) && time_before_eq(fdb->updated + hold_time(br), jiffies); } static int fdb_to_nud(const struct net_bridge *br, const struct net_bridge_fdb_entry *fdb) { if (test_bit(BR_FDB_LOCAL, &fdb->flags)) return NUD_PERMANENT; else if (test_bit(BR_FDB_STATIC, &fdb->flags)) return NUD_NOARP; else if (has_expired(br, fdb)) return NUD_STALE; else return NUD_REACHABLE; } static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, const struct net_bridge_fdb_entry *fdb, u32 portid, u32 seq, int type, unsigned int flags) { const struct net_bridge_port *dst = READ_ONCE(fdb->dst); unsigned long now = jiffies; struct nda_cacheinfo ci; struct nlmsghdr *nlh; struct ndmsg *ndm; u32 ext_flags = 0; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) return -EMSGSIZE; ndm = nlmsg_data(nlh); ndm->ndm_family = AF_BRIDGE; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; ndm->ndm_flags = 0; ndm->ndm_type = 0; ndm->ndm_ifindex = dst ? dst->dev->ifindex : br->dev->ifindex; ndm->ndm_state = fdb_to_nud(br, fdb); if (test_bit(BR_FDB_OFFLOADED, &fdb->flags)) ndm->ndm_flags |= NTF_OFFLOADED; if (test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) ndm->ndm_flags |= NTF_EXT_LEARNED; if (test_bit(BR_FDB_STICKY, &fdb->flags)) ndm->ndm_flags |= NTF_STICKY; if (test_bit(BR_FDB_LOCKED, &fdb->flags)) ext_flags |= NTF_EXT_LOCKED; if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->key.addr)) goto nla_put_failure; if (nla_put_u32(skb, NDA_MASTER, br->dev->ifindex)) goto nla_put_failure; if (nla_put_u32(skb, NDA_FLAGS_EXT, ext_flags)) goto nla_put_failure; ci.ndm_used = jiffies_to_clock_t(now - fdb->used); ci.ndm_confirmed = 0; ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); ci.ndm_refcnt = 0; if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci)) goto nla_put_failure; if (fdb->key.vlan_id && nla_put(skb, NDA_VLAN, sizeof(u16), &fdb->key.vlan_id)) goto nla_put_failure; if (test_bit(BR_FDB_NOTIFY, &fdb->flags)) { struct nlattr *nest = nla_nest_start(skb, NDA_FDB_EXT_ATTRS); u8 notify_bits = FDB_NOTIFY_BIT; if (!nest) goto nla_put_failure; if (test_bit(BR_FDB_NOTIFY_INACTIVE, &fdb->flags)) notify_bits |= FDB_NOTIFY_INACTIVE_BIT; if (nla_put_u8(skb, NFEA_ACTIVITY_NOTIFY, notify_bits)) { nla_nest_cancel(skb, nest); goto nla_put_failure; } nla_nest_end(skb, nest); } nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static inline size_t fdb_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + nla_total_size(sizeof(u32)) /* NDA_MASTER */ + nla_total_size(sizeof(u32)) /* NDA_FLAGS_EXT */ + nla_total_size(sizeof(u16)) /* NDA_VLAN */ + nla_total_size(sizeof(struct nda_cacheinfo)) + nla_total_size(0) /* NDA_FDB_EXT_ATTRS */ + nla_total_size(sizeof(u8)); /* NFEA_ACTIVITY_NOTIFY */ } static void fdb_notify(struct net_bridge *br, const struct net_bridge_fdb_entry *fdb, int type, bool swdev_notify) { struct net *net = dev_net(br->dev); struct sk_buff *skb; int err = -ENOBUFS; if (swdev_notify) br_switchdev_fdb_notify(br, fdb, type); skb = nlmsg_new(fdb_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) goto errout; err = fdb_fill_info(skb, br, fdb, 0, 0, type, 0); if (err < 0) { /* -EMSGSIZE implies BUG in fdb_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); } static struct net_bridge_fdb_entry *fdb_find_rcu(struct rhashtable *tbl, const unsigned char *addr, __u16 vid) { struct net_bridge_fdb_key key; WARN_ON_ONCE(!rcu_read_lock_held()); key.vlan_id = vid; memcpy(key.addr.addr, addr, sizeof(key.addr.addr)); return rhashtable_lookup(tbl, &key, br_fdb_rht_params); } /* requires bridge hash_lock */ static struct net_bridge_fdb_entry *br_fdb_find(struct net_bridge *br, const unsigned char *addr, __u16 vid) { struct net_bridge_fdb_entry *fdb; lockdep_assert_held_once(&br->hash_lock); rcu_read_lock(); fdb = fdb_find_rcu(&br->fdb_hash_tbl, addr, vid); rcu_read_unlock(); return fdb; } struct net_device *br_fdb_find_port(const struct net_device *br_dev, const unsigned char *addr, __u16 vid) { struct net_bridge_fdb_entry *f; struct net_device *dev = NULL; struct net_bridge *br; ASSERT_RTNL(); if (!netif_is_bridge_master(br_dev)) return NULL; br = netdev_priv(br_dev); rcu_read_lock(); f = br_fdb_find_rcu(br, addr, vid); if (f && f->dst) dev = f->dst->dev; rcu_read_unlock(); return dev; } EXPORT_SYMBOL_GPL(br_fdb_find_port); struct net_bridge_fdb_entry *br_fdb_find_rcu(struct net_bridge *br, const unsigned char *addr, __u16 vid) { return fdb_find_rcu(&br->fdb_hash_tbl, addr, vid); } /* When a static FDB entry is added, the mac address from the entry is * added to the bridge private HW address list and all required ports * are then updated with the new information. * Called under RTNL. */ static void fdb_add_hw_addr(struct net_bridge *br, const unsigned char *addr) { int err; struct net_bridge_port *p; ASSERT_RTNL(); list_for_each_entry(p, &br->port_list, list) { if (!br_promisc_port(p)) { err = dev_uc_add(p->dev, addr); if (err) goto undo; } } return; undo: list_for_each_entry_continue_reverse(p, &br->port_list, list) { if (!br_promisc_port(p)) dev_uc_del(p->dev, addr); } } /* When a static FDB entry is deleted, the HW address from that entry is * also removed from the bridge private HW address list and updates all * the ports with needed information. * Called under RTNL. */ static void fdb_del_hw_addr(struct net_bridge *br, const unsigned char *addr) { struct net_bridge_port *p; ASSERT_RTNL(); list_for_each_entry(p, &br->port_list, list) { if (!br_promisc_port(p)) dev_uc_del(p->dev, addr); } } static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f, bool swdev_notify) { trace_fdb_delete(br, f); if (test_bit(BR_FDB_STATIC, &f->flags)) fdb_del_hw_addr(br, f->key.addr.addr); hlist_del_init_rcu(&f->fdb_node); rhashtable_remove_fast(&br->fdb_hash_tbl, &f->rhnode, br_fdb_rht_params); if (test_and_clear_bit(BR_FDB_DYNAMIC_LEARNED, &f->flags)) atomic_dec(&br->fdb_n_learned); fdb_notify(br, f, RTM_DELNEIGH, swdev_notify); kfree_rcu(f, rcu); } /* Delete a local entry if no other port had the same address. * * This function should only be called on entries with BR_FDB_LOCAL set, * so even with BR_FDB_ADDED_BY_USER cleared we never need to increase * the accounting for dynamically learned entries again. */ static void fdb_delete_local(struct net_bridge *br, const struct net_bridge_port *p, struct net_bridge_fdb_entry *f) { const unsigned char *addr = f->key.addr.addr; struct net_bridge_vlan_group *vg; const struct net_bridge_vlan *v; struct net_bridge_port *op; u16 vid = f->key.vlan_id; /* Maybe another port has same hw addr? */ list_for_each_entry(op, &br->port_list, list) { vg = nbp_vlan_group(op); if (op != p && ether_addr_equal(op->dev->dev_addr, addr) && (!vid || br_vlan_find(vg, vid))) { f->dst = op; clear_bit(BR_FDB_ADDED_BY_USER, &f->flags); return; } } vg = br_vlan_group(br); v = br_vlan_find(vg, vid); /* Maybe bridge device has same hw addr? */ if (p && ether_addr_equal(br->dev->dev_addr, addr) && (!vid || (v && br_vlan_should_use(v)))) { f->dst = NULL; clear_bit(BR_FDB_ADDED_BY_USER, &f->flags); return; } fdb_delete(br, f, true); } void br_fdb_find_delete_local(struct net_bridge *br, const struct net_bridge_port *p, const unsigned char *addr, u16 vid) { struct net_bridge_fdb_entry *f; spin_lock_bh(&br->hash_lock); f = br_fdb_find(br, addr, vid); if (f && test_bit(BR_FDB_LOCAL, &f->flags) && !test_bit(BR_FDB_ADDED_BY_USER, &f->flags) && f->dst == p) fdb_delete_local(br, p, f); spin_unlock_bh(&br->hash_lock); } static struct net_bridge_fdb_entry *fdb_create(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr, __u16 vid, unsigned long flags) { bool learned = !test_bit(BR_FDB_ADDED_BY_USER, &flags) && !test_bit(BR_FDB_LOCAL, &flags); u32 max_learned = READ_ONCE(br->fdb_max_learned); struct net_bridge_fdb_entry *fdb; int err; if (likely(learned)) { int n_learned = atomic_read(&br->fdb_n_learned); if (unlikely(max_learned && n_learned >= max_learned)) return NULL; __set_bit(BR_FDB_DYNAMIC_LEARNED, &flags); } fdb = kmem_cache_alloc(br_fdb_cache, GFP_ATOMIC); if (!fdb) return NULL; memcpy(fdb->key.addr.addr, addr, ETH_ALEN); WRITE_ONCE(fdb->dst, source); fdb->key.vlan_id = vid; fdb->flags = flags; fdb->updated = fdb->used = jiffies; err = rhashtable_lookup_insert_fast(&br->fdb_hash_tbl, &fdb->rhnode, br_fdb_rht_params); if (err) { kmem_cache_free(br_fdb_cache, fdb); return NULL; } if (likely(learned)) atomic_inc(&br->fdb_n_learned); hlist_add_head_rcu(&fdb->fdb_node, &br->fdb_list); return fdb; } static int fdb_add_local(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr, u16 vid) { struct net_bridge_fdb_entry *fdb; if (!is_valid_ether_addr(addr)) return -EINVAL; fdb = br_fdb_find(br, addr, vid); if (fdb) { /* it is okay to have multiple ports with same * address, just use the first one. */ if (test_bit(BR_FDB_LOCAL, &fdb->flags)) return 0; br_warn(br, "adding interface %s with same address as a received packet (addr:%pM, vlan:%u)\n", source ? source->dev->name : br->dev->name, addr, vid); fdb_delete(br, fdb, true); } fdb = fdb_create(br, source, addr, vid, BIT(BR_FDB_LOCAL) | BIT(BR_FDB_STATIC)); if (!fdb) return -ENOMEM; fdb_add_hw_addr(br, addr); fdb_notify(br, fdb, RTM_NEWNEIGH, true); return 0; } void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) { struct net_bridge_vlan_group *vg; struct net_bridge_fdb_entry *f; struct net_bridge *br = p->br; struct net_bridge_vlan *v; spin_lock_bh(&br->hash_lock); vg = nbp_vlan_group(p); hlist_for_each_entry(f, &br->fdb_list, fdb_node) { if (f->dst == p && test_bit(BR_FDB_LOCAL, &f->flags) && !test_bit(BR_FDB_ADDED_BY_USER, &f->flags)) { /* delete old one */ fdb_delete_local(br, p, f); /* if this port has no vlan information * configured, we can safely be done at * this point. */ if (!vg || !vg->num_vlans) goto insert; } } insert: /* insert new address, may fail if invalid address or dup. */ fdb_add_local(br, p, newaddr, 0); if (!vg || !vg->num_vlans) goto done; /* Now add entries for every VLAN configured on the port. * This function runs under RTNL so the bitmap will not change * from under us. */ list_for_each_entry(v, &vg->vlan_list, vlist) fdb_add_local(br, p, newaddr, v->vid); done: spin_unlock_bh(&br->hash_lock); } void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) { struct net_bridge_vlan_group *vg; struct net_bridge_fdb_entry *f; struct net_bridge_vlan *v; spin_lock_bh(&br->hash_lock); /* If old entry was unassociated with any port, then delete it. */ f = br_fdb_find(br, br->dev->dev_addr, 0); if (f && test_bit(BR_FDB_LOCAL, &f->flags) && !f->dst && !test_bit(BR_FDB_ADDED_BY_USER, &f->flags)) fdb_delete_local(br, NULL, f); fdb_add_local(br, NULL, newaddr, 0); vg = br_vlan_group(br); if (!vg || !vg->num_vlans) goto out; /* Now remove and add entries for every VLAN configured on the * bridge. This function runs under RTNL so the bitmap will not * change from under us. */ list_for_each_entry(v, &vg->vlan_list, vlist) { if (!br_vlan_should_use(v)) continue; f = br_fdb_find(br, br->dev->dev_addr, v->vid); if (f && test_bit(BR_FDB_LOCAL, &f->flags) && !f->dst && !test_bit(BR_FDB_ADDED_BY_USER, &f->flags)) fdb_delete_local(br, NULL, f); fdb_add_local(br, NULL, newaddr, v->vid); } out: spin_unlock_bh(&br->hash_lock); } void br_fdb_cleanup(struct work_struct *work) { struct net_bridge *br = container_of(work, struct net_bridge, gc_work.work); struct net_bridge_fdb_entry *f = NULL; unsigned long delay = hold_time(br); unsigned long work_delay = delay; unsigned long now = jiffies; /* this part is tricky, in order to avoid blocking learning and * consequently forwarding, we rely on rcu to delete objects with * delayed freeing allowing us to continue traversing */ rcu_read_lock(); hlist_for_each_entry_rcu(f, &br->fdb_list, fdb_node) { unsigned long this_timer = f->updated + delay; if (test_bit(BR_FDB_STATIC, &f->flags) || test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &f->flags)) { if (test_bit(BR_FDB_NOTIFY, &f->flags)) { if (time_after(this_timer, now)) work_delay = min(work_delay, this_timer - now); else if (!test_and_set_bit(BR_FDB_NOTIFY_INACTIVE, &f->flags)) fdb_notify(br, f, RTM_NEWNEIGH, false); } continue; } if (time_after(this_timer, now)) { work_delay = min(work_delay, this_timer - now); } else { spin_lock_bh(&br->hash_lock); if (!hlist_unhashed(&f->fdb_node)) fdb_delete(br, f, true); spin_unlock_bh(&br->hash_lock); } } rcu_read_unlock(); /* Cleanup minimum 10 milliseconds apart */ work_delay = max_t(unsigned long, work_delay, msecs_to_jiffies(10)); mod_delayed_work(system_long_wq, &br->gc_work, work_delay); } static bool __fdb_flush_matches(const struct net_bridge *br, const struct net_bridge_fdb_entry *f, const struct net_bridge_fdb_flush_desc *desc) { const struct net_bridge_port *dst = READ_ONCE(f->dst); int port_ifidx = dst ? dst->dev->ifindex : br->dev->ifindex; if (desc->vlan_id && desc->vlan_id != f->key.vlan_id) return false; if (desc->port_ifindex && desc->port_ifindex != port_ifidx) return false; if (desc->flags_mask && (f->flags & desc->flags_mask) != desc->flags) return false; return true; } /* Flush forwarding database entries matching the description */ void br_fdb_flush(struct net_bridge *br, const struct net_bridge_fdb_flush_desc *desc) { struct net_bridge_fdb_entry *f; rcu_read_lock(); hlist_for_each_entry_rcu(f, &br->fdb_list, fdb_node) { if (!__fdb_flush_matches(br, f, desc)) continue; spin_lock_bh(&br->hash_lock); if (!hlist_unhashed(&f->fdb_node)) fdb_delete(br, f, true); spin_unlock_bh(&br->hash_lock); } rcu_read_unlock(); } static unsigned long __ndm_state_to_fdb_flags(u16 ndm_state) { unsigned long flags = 0; if (ndm_state & NUD_PERMANENT) __set_bit(BR_FDB_LOCAL, &flags); if (ndm_state & NUD_NOARP) __set_bit(BR_FDB_STATIC, &flags); return flags; } static unsigned long __ndm_flags_to_fdb_flags(u8 ndm_flags) { unsigned long flags = 0; if (ndm_flags & NTF_USE) __set_bit(BR_FDB_ADDED_BY_USER, &flags); if (ndm_flags & NTF_EXT_LEARNED) __set_bit(BR_FDB_ADDED_BY_EXT_LEARN, &flags); if (ndm_flags & NTF_OFFLOADED) __set_bit(BR_FDB_OFFLOADED, &flags); if (ndm_flags & NTF_STICKY) __set_bit(BR_FDB_STICKY, &flags); return flags; } static int __fdb_flush_validate_ifindex(const struct net_bridge *br, int ifindex, struct netlink_ext_ack *extack) { const struct net_device *dev; dev = __dev_get_by_index(dev_net(br->dev), ifindex); if (!dev) { NL_SET_ERR_MSG_MOD(extack, "Unknown flush device ifindex"); return -ENODEV; } if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) { NL_SET_ERR_MSG_MOD(extack, "Flush device is not a bridge or bridge port"); return -EINVAL; } if (netif_is_bridge_master(dev) && dev != br->dev) { NL_SET_ERR_MSG_MOD(extack, "Flush bridge device does not match target bridge device"); return -EINVAL; } if (netif_is_bridge_port(dev)) { struct net_bridge_port *p = br_port_get_rtnl(dev); if (p->br != br) { NL_SET_ERR_MSG_MOD(extack, "Port belongs to a different bridge device"); return -EINVAL; } } return 0; } static const struct nla_policy br_fdb_del_bulk_policy[NDA_MAX + 1] = { [NDA_VLAN] = NLA_POLICY_RANGE(NLA_U16, 1, VLAN_N_VID - 2), [NDA_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1), [NDA_NDM_STATE_MASK] = { .type = NLA_U16 }, [NDA_NDM_FLAGS_MASK] = { .type = NLA_U8 }, }; int br_fdb_delete_bulk(struct nlmsghdr *nlh, struct net_device *dev, struct netlink_ext_ack *extack) { struct net_bridge_fdb_flush_desc desc = {}; struct ndmsg *ndm = nlmsg_data(nlh); struct net_bridge_port *p = NULL; struct nlattr *tb[NDA_MAX + 1]; struct net_bridge *br; u8 ndm_flags; int err; ndm_flags = ndm->ndm_flags & ~FDB_FLUSH_IGNORED_NDM_FLAGS; err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, br_fdb_del_bulk_policy, extack); if (err) return err; if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); } else { p = br_port_get_rtnl(dev); if (!p) { NL_SET_ERR_MSG_MOD(extack, "Device is not a bridge port"); return -EINVAL; } br = p->br; } if (tb[NDA_VLAN]) desc.vlan_id = nla_get_u16(tb[NDA_VLAN]); if (ndm_flags & ~FDB_FLUSH_ALLOWED_NDM_FLAGS) { NL_SET_ERR_MSG(extack, "Unsupported fdb flush ndm flag bits set"); return -EINVAL; } if (ndm->ndm_state & ~FDB_FLUSH_ALLOWED_NDM_STATES) { NL_SET_ERR_MSG(extack, "Unsupported fdb flush ndm state bits set"); return -EINVAL; } desc.flags |= __ndm_state_to_fdb_flags(ndm->ndm_state); desc.flags |= __ndm_flags_to_fdb_flags(ndm_flags); if (tb[NDA_NDM_STATE_MASK]) { u16 ndm_state_mask = nla_get_u16(tb[NDA_NDM_STATE_MASK]); desc.flags_mask |= __ndm_state_to_fdb_flags(ndm_state_mask); } if (tb[NDA_NDM_FLAGS_MASK]) { u8 ndm_flags_mask = nla_get_u8(tb[NDA_NDM_FLAGS_MASK]); desc.flags_mask |= __ndm_flags_to_fdb_flags(ndm_flags_mask); } if (tb[NDA_IFINDEX]) { int ifidx = nla_get_s32(tb[NDA_IFINDEX]); err = __fdb_flush_validate_ifindex(br, ifidx, extack); if (err) return err; desc.port_ifindex = ifidx; } else if (p) { /* flush was invoked with port device and NTF_MASTER */ desc.port_ifindex = p->dev->ifindex; } br_debug(br, "flushing port ifindex: %d vlan id: %u flags: 0x%lx flags mask: 0x%lx\n", desc.port_ifindex, desc.vlan_id, desc.flags, desc.flags_mask); br_fdb_flush(br, &desc); return 0; } /* Flush all entries referring to a specific port. * if do_all is set also flush static entries * if vid is set delete all entries that match the vlan_id */ void br_fdb_delete_by_port(struct net_bridge *br, const struct net_bridge_port *p, u16 vid, int do_all) { struct net_bridge_fdb_entry *f; struct hlist_node *tmp; spin_lock_bh(&br->hash_lock); hlist_for_each_entry_safe(f, tmp, &br->fdb_list, fdb_node) { if (f->dst != p) continue; if (!do_all) if (test_bit(BR_FDB_STATIC, &f->flags) || (test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &f->flags) && !test_bit(BR_FDB_OFFLOADED, &f->flags)) || (vid && f->key.vlan_id != vid)) continue; if (test_bit(BR_FDB_LOCAL, &f->flags)) fdb_delete_local(br, p, f); else fdb_delete(br, f, true); } spin_unlock_bh(&br->hash_lock); } #if IS_ENABLED(CONFIG_ATM_LANE) /* Interface used by ATM LANE hook to test * if an addr is on some other bridge port */ int br_fdb_test_addr(struct net_device *dev, unsigned char *addr) { struct net_bridge_fdb_entry *fdb; struct net_bridge_port *port; int ret; rcu_read_lock(); port = br_port_get_rcu(dev); if (!port) ret = 0; else { const struct net_bridge_port *dst = NULL; fdb = br_fdb_find_rcu(port->br, addr, 0); if (fdb) dst = READ_ONCE(fdb->dst); ret = dst && dst->dev != dev && dst->state == BR_STATE_FORWARDING; } rcu_read_unlock(); return ret; } #endif /* CONFIG_ATM_LANE */ /* * Fill buffer with forwarding table records in * the API format. */ int br_fdb_fillbuf(struct net_bridge *br, void *buf, unsigned long maxnum, unsigned long skip) { struct net_bridge_fdb_entry *f; struct __fdb_entry *fe = buf; int num = 0; memset(buf, 0, maxnum*sizeof(struct __fdb_entry)); rcu_read_lock(); hlist_for_each_entry_rcu(f, &br->fdb_list, fdb_node) { if (num >= maxnum) break; if (has_expired(br, f)) continue; /* ignore pseudo entry for local MAC address */ if (!f->dst) continue; if (skip) { --skip; continue; } /* convert from internal format to API */ memcpy(fe->mac_addr, f->key.addr.addr, ETH_ALEN); /* due to ABI compat need to split into hi/lo */ fe->port_no = f->dst->port_no; fe->port_hi = f->dst->port_no >> 8; fe->is_local = test_bit(BR_FDB_LOCAL, &f->flags); if (!test_bit(BR_FDB_STATIC, &f->flags)) fe->ageing_timer_value = jiffies_delta_to_clock_t(jiffies - f->updated); ++fe; ++num; } rcu_read_unlock(); return num; } /* Add entry for local address of interface */ int br_fdb_add_local(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr, u16 vid) { int ret; spin_lock_bh(&br->hash_lock); ret = fdb_add_local(br, source, addr, vid); spin_unlock_bh(&br->hash_lock); return ret; } /* returns true if the fdb was modified */ static bool __fdb_mark_active(struct net_bridge_fdb_entry *fdb) { return !!(test_bit(BR_FDB_NOTIFY_INACTIVE, &fdb->flags) && test_and_clear_bit(BR_FDB_NOTIFY_INACTIVE, &fdb->flags)); } void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr, u16 vid, unsigned long flags) { struct net_bridge_fdb_entry *fdb; /* some users want to always flood. */ if (hold_time(br) == 0) return; fdb = fdb_find_rcu(&br->fdb_hash_tbl, addr, vid); if (likely(fdb)) { /* attempt to update an entry for a local interface */ if (unlikely(test_bit(BR_FDB_LOCAL, &fdb->flags))) { if (net_ratelimit()) br_warn(br, "received packet on %s with own address as source address (addr:%pM, vlan:%u)\n", source->dev->name, addr, vid); } else { unsigned long now = jiffies; bool fdb_modified = false; if (now != fdb->updated) { fdb->updated = now; fdb_modified = __fdb_mark_active(fdb); } /* fastpath: update of existing entry */ if (unlikely(source != READ_ONCE(fdb->dst) && !test_bit(BR_FDB_STICKY, &fdb->flags))) { br_switchdev_fdb_notify(br, fdb, RTM_DELNEIGH); WRITE_ONCE(fdb->dst, source); fdb_modified = true; /* Take over HW learned entry */ if (unlikely(test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags))) clear_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags); /* Clear locked flag when roaming to an * unlocked port. */ if (unlikely(test_bit(BR_FDB_LOCKED, &fdb->flags))) clear_bit(BR_FDB_LOCKED, &fdb->flags); } if (unlikely(test_bit(BR_FDB_ADDED_BY_USER, &flags))) { set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); if (test_and_clear_bit(BR_FDB_DYNAMIC_LEARNED, &fdb->flags)) atomic_dec(&br->fdb_n_learned); } if (unlikely(fdb_modified)) { trace_br_fdb_update(br, source, addr, vid, flags); fdb_notify(br, fdb, RTM_NEWNEIGH, true); } } } else { spin_lock(&br->hash_lock); fdb = fdb_create(br, source, addr, vid, flags); if (fdb) { trace_br_fdb_update(br, source, addr, vid, flags); fdb_notify(br, fdb, RTM_NEWNEIGH, true); } /* else we lose race and someone else inserts * it first, don't bother updating */ spin_unlock(&br->hash_lock); } } /* Dump information about entries, in response to GETNEIGH */ int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx) { struct net_bridge *br = netdev_priv(dev); struct net_bridge_fdb_entry *f; int err = 0; if (!netif_is_bridge_master(dev)) return err; if (!filter_dev) { err = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx); if (err < 0) return err; } rcu_read_lock(); hlist_for_each_entry_rcu(f, &br->fdb_list, fdb_node) { if (*idx < cb->args[2]) goto skip; if (filter_dev && (!f->dst || f->dst->dev != filter_dev)) { if (filter_dev != dev) goto skip; /* !f->dst is a special case for bridge * It means the MAC belongs to the bridge * Therefore need a little more filtering * we only want to dump the !f->dst case */ if (f->dst) goto skip; } if (!filter_dev && f->dst) goto skip; err = fdb_fill_info(skb, br, f, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI); if (err < 0) break; skip: *idx += 1; } rcu_read_unlock(); return err; } int br_fdb_get(struct sk_buff *skb, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u32 portid, u32 seq, struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(dev); struct net_bridge_fdb_entry *f; int err = 0; rcu_read_lock(); f = br_fdb_find_rcu(br, addr, vid); if (!f) { NL_SET_ERR_MSG(extack, "Fdb entry not found"); err = -ENOENT; goto errout; } err = fdb_fill_info(skb, br, f, portid, seq, RTM_NEWNEIGH, 0); errout: rcu_read_unlock(); return err; } /* returns true if the fdb is modified */ static bool fdb_handle_notify(struct net_bridge_fdb_entry *fdb, u8 notify) { bool modified = false; /* allow to mark an entry as inactive, usually done on creation */ if ((notify & FDB_NOTIFY_INACTIVE_BIT) && !test_and_set_bit(BR_FDB_NOTIFY_INACTIVE, &fdb->flags)) modified = true; if ((notify & FDB_NOTIFY_BIT) && !test_and_set_bit(BR_FDB_NOTIFY, &fdb->flags)) { /* enabled activity tracking */ modified = true; } else if (!(notify & FDB_NOTIFY_BIT) && test_and_clear_bit(BR_FDB_NOTIFY, &fdb->flags)) { /* disabled activity tracking, clear notify state */ clear_bit(BR_FDB_NOTIFY_INACTIVE, &fdb->flags); modified = true; } return modified; } /* Update (create or replace) forwarding database entry */ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, const u8 *addr, struct ndmsg *ndm, u16 flags, u16 vid, struct nlattr *nfea_tb[]) { bool is_sticky = !!(ndm->ndm_flags & NTF_STICKY); bool refresh = !nfea_tb[NFEA_DONT_REFRESH]; struct net_bridge_fdb_entry *fdb; u16 state = ndm->ndm_state; bool modified = false; u8 notify = 0; /* If the port cannot learn allow only local and static entries */ if (source && !(state & NUD_PERMANENT) && !(state & NUD_NOARP) && !(source->state == BR_STATE_LEARNING || source->state == BR_STATE_FORWARDING)) return -EPERM; if (!source && !(state & NUD_PERMANENT)) { pr_info("bridge: RTM_NEWNEIGH %s without NUD_PERMANENT\n", br->dev->name); return -EINVAL; } if (is_sticky && (state & NUD_PERMANENT)) return -EINVAL; if (nfea_tb[NFEA_ACTIVITY_NOTIFY]) { notify = nla_get_u8(nfea_tb[NFEA_ACTIVITY_NOTIFY]); if ((notify & ~BR_FDB_NOTIFY_SETTABLE_BITS) || (notify & BR_FDB_NOTIFY_SETTABLE_BITS) == FDB_NOTIFY_INACTIVE_BIT) return -EINVAL; } fdb = br_fdb_find(br, addr, vid); if (fdb == NULL) { if (!(flags & NLM_F_CREATE)) return -ENOENT; fdb = fdb_create(br, source, addr, vid, BIT(BR_FDB_ADDED_BY_USER)); if (!fdb) return -ENOMEM; modified = true; } else { if (flags & NLM_F_EXCL) return -EEXIST; if (READ_ONCE(fdb->dst) != source) { WRITE_ONCE(fdb->dst, source); modified = true; } set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); if (test_and_clear_bit(BR_FDB_DYNAMIC_LEARNED, &fdb->flags)) atomic_dec(&br->fdb_n_learned); } if (fdb_to_nud(br, fdb) != state) { if (state & NUD_PERMANENT) { set_bit(BR_FDB_LOCAL, &fdb->flags); if (!test_and_set_bit(BR_FDB_STATIC, &fdb->flags)) fdb_add_hw_addr(br, addr); } else if (state & NUD_NOARP) { clear_bit(BR_FDB_LOCAL, &fdb->flags); if (!test_and_set_bit(BR_FDB_STATIC, &fdb->flags)) fdb_add_hw_addr(br, addr); } else { clear_bit(BR_FDB_LOCAL, &fdb->flags); if (test_and_clear_bit(BR_FDB_STATIC, &fdb->flags)) fdb_del_hw_addr(br, addr); } modified = true; } if (is_sticky != test_bit(BR_FDB_STICKY, &fdb->flags)) { change_bit(BR_FDB_STICKY, &fdb->flags); modified = true; } if (test_and_clear_bit(BR_FDB_LOCKED, &fdb->flags)) modified = true; if (fdb_handle_notify(fdb, notify)) modified = true; fdb->used = jiffies; if (modified) { if (refresh) fdb->updated = jiffies; fdb_notify(br, fdb, RTM_NEWNEIGH, true); } return 0; } static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 nlh_flags, u16 vid, struct nlattr *nfea_tb[], bool *notified, struct netlink_ext_ack *extack) { int err = 0; if (ndm->ndm_flags & NTF_USE) { if (!p) { pr_info("bridge: RTM_NEWNEIGH %s with NTF_USE is not supported\n", br->dev->name); return -EINVAL; } if (!nbp_state_should_learn(p)) return 0; local_bh_disable(); rcu_read_lock(); br_fdb_update(br, p, addr, vid, BIT(BR_FDB_ADDED_BY_USER)); rcu_read_unlock(); local_bh_enable(); } else if (ndm->ndm_flags & NTF_EXT_LEARNED) { if (!p && !(ndm->ndm_state & NUD_PERMANENT)) { NL_SET_ERR_MSG_MOD(extack, "FDB entry towards bridge must be permanent"); return -EINVAL; } err = br_fdb_external_learn_add(br, p, addr, vid, false, true); } else { spin_lock_bh(&br->hash_lock); err = fdb_add_entry(br, p, addr, ndm, nlh_flags, vid, nfea_tb); spin_unlock_bh(&br->hash_lock); } if (!err) *notified = true; return err; } static const struct nla_policy br_nda_fdb_pol[NFEA_MAX + 1] = { [NFEA_ACTIVITY_NOTIFY] = { .type = NLA_U8 }, [NFEA_DONT_REFRESH] = { .type = NLA_FLAG }, }; /* Add new permanent fdb entry with RTM_NEWNEIGH */ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 nlh_flags, bool *notified, struct netlink_ext_ack *extack) { struct nlattr *nfea_tb[NFEA_MAX + 1], *attr; struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; struct net_bridge_vlan *v; struct net_bridge *br = NULL; u32 ext_flags = 0; int err = 0; trace_br_fdb_add(ndm, dev, addr, vid, nlh_flags); if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) { pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state); return -EINVAL; } if (is_zero_ether_addr(addr)) { pr_info("bridge: RTM_NEWNEIGH with invalid ether address\n"); return -EINVAL; } if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group(br); } else { p = br_port_get_rtnl(dev); if (!p) { pr_info("bridge: RTM_NEWNEIGH %s not a bridge port\n", dev->name); return -EINVAL; } br = p->br; vg = nbp_vlan_group(p); } if (tb[NDA_FLAGS_EXT]) ext_flags = nla_get_u32(tb[NDA_FLAGS_EXT]); if (ext_flags & NTF_EXT_LOCKED) { NL_SET_ERR_MSG_MOD(extack, "Cannot add FDB entry with \"locked\" flag set"); return -EINVAL; } if (tb[NDA_FDB_EXT_ATTRS]) { attr = tb[NDA_FDB_EXT_ATTRS]; err = nla_parse_nested(nfea_tb, NFEA_MAX, attr, br_nda_fdb_pol, extack); if (err) return err; } else { memset(nfea_tb, 0, sizeof(struct nlattr *) * (NFEA_MAX + 1)); } if (vid) { v = br_vlan_find(vg, vid); if (!v || !br_vlan_should_use(v)) { pr_info("bridge: RTM_NEWNEIGH with unconfigured vlan %d on %s\n", vid, dev->name); return -EINVAL; } /* VID was specified, so use it. */ err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid, nfea_tb, notified, extack); } else { err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0, nfea_tb, notified, extack); if (err || !vg || !vg->num_vlans) goto out; /* We have vlans configured on this port and user didn't * specify a VLAN. To be nice, add/update entry for every * vlan on this port. */ list_for_each_entry(v, &vg->vlan_list, vlist) { if (!br_vlan_should_use(v)) continue; err = __br_fdb_add(ndm, br, p, addr, nlh_flags, v->vid, nfea_tb, notified, extack); if (err) goto out; } } out: return err; } static int fdb_delete_by_addr_and_port(struct net_bridge *br, const struct net_bridge_port *p, const u8 *addr, u16 vlan, bool *notified) { struct net_bridge_fdb_entry *fdb; fdb = br_fdb_find(br, addr, vlan); if (!fdb || READ_ONCE(fdb->dst) != p) return -ENOENT; fdb_delete(br, fdb, true); *notified = true; return 0; } static int __br_fdb_delete(struct net_bridge *br, const struct net_bridge_port *p, const unsigned char *addr, u16 vid, bool *notified) { int err; spin_lock_bh(&br->hash_lock); err = fdb_delete_by_addr_and_port(br, p, addr, vid, notified); spin_unlock_bh(&br->hash_lock); return err; } /* Remove neighbor entry with RTM_DELNEIGH */ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, bool *notified, struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; struct net_bridge *br; int err; if (netif_is_bridge_master(dev)) { br = netdev_priv(dev); vg = br_vlan_group(br); } else { p = br_port_get_rtnl(dev); if (!p) { pr_info("bridge: RTM_DELNEIGH %s not a bridge port\n", dev->name); return -EINVAL; } vg = nbp_vlan_group(p); br = p->br; } if (vid) { err = __br_fdb_delete(br, p, addr, vid, notified); } else { struct net_bridge_vlan *v; err = -ENOENT; err &= __br_fdb_delete(br, p, addr, 0, notified); if (!vg || !vg->num_vlans) return err; list_for_each_entry(v, &vg->vlan_list, vlist) { if (!br_vlan_should_use(v)) continue; err &= __br_fdb_delete(br, p, addr, v->vid, notified); } } return err; } int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p) { struct net_bridge_fdb_entry *f, *tmp; int err = 0; ASSERT_RTNL(); /* the key here is that static entries change only under rtnl */ rcu_read_lock(); hlist_for_each_entry_rcu(f, &br->fdb_list, fdb_node) { /* We only care for static entries */ if (!test_bit(BR_FDB_STATIC, &f->flags)) continue; err = dev_uc_add(p->dev, f->key.addr.addr); if (err) goto rollback; } done: rcu_read_unlock(); return err; rollback: hlist_for_each_entry_rcu(tmp, &br->fdb_list, fdb_node) { /* We only care for static entries */ if (!test_bit(BR_FDB_STATIC, &tmp->flags)) continue; if (tmp == f) break; dev_uc_del(p->dev, tmp->key.addr.addr); } goto done; } void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p) { struct net_bridge_fdb_entry *f; ASSERT_RTNL(); rcu_read_lock(); hlist_for_each_entry_rcu(f, &br->fdb_list, fdb_node) { /* We only care for static entries */ if (!test_bit(BR_FDB_STATIC, &f->flags)) continue; dev_uc_del(p->dev, f->key.addr.addr); } rcu_read_unlock(); } int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid, bool locked, bool swdev_notify) { struct net_bridge_fdb_entry *fdb; bool modified = false; int err = 0; trace_br_fdb_external_learn_add(br, p, addr, vid); if (locked && (!p || !(p->flags & BR_PORT_MAB))) return -EINVAL; spin_lock_bh(&br->hash_lock); fdb = br_fdb_find(br, addr, vid); if (!fdb) { unsigned long flags = BIT(BR_FDB_ADDED_BY_EXT_LEARN); if (swdev_notify) flags |= BIT(BR_FDB_ADDED_BY_USER); if (!p) flags |= BIT(BR_FDB_LOCAL); if (locked) flags |= BIT(BR_FDB_LOCKED); fdb = fdb_create(br, p, addr, vid, flags); if (!fdb) { err = -ENOMEM; goto err_unlock; } fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } else { if (locked && (!test_bit(BR_FDB_LOCKED, &fdb->flags) || READ_ONCE(fdb->dst) != p)) { err = -EINVAL; goto err_unlock; } fdb->updated = jiffies; if (READ_ONCE(fdb->dst) != p) { WRITE_ONCE(fdb->dst, p); modified = true; } if (test_and_set_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) { /* Refresh entry */ fdb->used = jiffies; } else { modified = true; } if (locked != test_bit(BR_FDB_LOCKED, &fdb->flags)) { change_bit(BR_FDB_LOCKED, &fdb->flags); modified = true; } if (swdev_notify) set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags); if (!p) set_bit(BR_FDB_LOCAL, &fdb->flags); if ((swdev_notify || !p) && test_and_clear_bit(BR_FDB_DYNAMIC_LEARNED, &fdb->flags)) atomic_dec(&br->fdb_n_learned); if (modified) fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } err_unlock: spin_unlock_bh(&br->hash_lock); return err; } int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid, bool swdev_notify) { struct net_bridge_fdb_entry *fdb; int err = 0; spin_lock_bh(&br->hash_lock); fdb = br_fdb_find(br, addr, vid); if (fdb && test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) fdb_delete(br, fdb, swdev_notify); else err = -ENOENT; spin_unlock_bh(&br->hash_lock); return err; } void br_fdb_offloaded_set(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid, bool offloaded) { struct net_bridge_fdb_entry *fdb; spin_lock_bh(&br->hash_lock); fdb = br_fdb_find(br, addr, vid); if (fdb && offloaded != test_bit(BR_FDB_OFFLOADED, &fdb->flags)) change_bit(BR_FDB_OFFLOADED, &fdb->flags); spin_unlock_bh(&br->hash_lock); } void br_fdb_clear_offload(const struct net_device *dev, u16 vid) { struct net_bridge_fdb_entry *f; struct net_bridge_port *p; ASSERT_RTNL(); p = br_port_get_rtnl(dev); if (!p) return; spin_lock_bh(&p->br->hash_lock); hlist_for_each_entry(f, &p->br->fdb_list, fdb_node) { if (f->dst == p && f->key.vlan_id == vid) clear_bit(BR_FDB_OFFLOADED, &f->flags); } spin_unlock_bh(&p->br->hash_lock); } EXPORT_SYMBOL_GPL(br_fdb_clear_offload); |
| 4 4 4 2 2 4 4 1 14 1 12 12 12 12 12 32 32 32 15 12 17 16 32 32 32 11 32 21 10 4 4 4 6 6 6 3 3 3 3 3 1 1 1 3 1 2 2 3 3 3 3 12 12 12 12 6 12 12 2 7 12 12 12 12 6 6 3 3 12 12 1 11 12 12 12 6 6 6 6 7 7 7 7 7 6 7 6 6 4 4 1 6 4 4 2 6 5 17 16 16 16 16 15 13 14 2 2 13 13 13 13 13 6 13 12 13 13 16 17 14 14 14 14 11 3 2 1 3 12 12 4 12 12 2 1 2 70 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 | // SPDX-License-Identifier: GPL-2.0 /* * Provide access to virtual console memory. * /dev/vcs: the screen as it is being viewed right now (possibly scrolled) * /dev/vcsN: the screen of /dev/ttyN (1 <= N <= 63) * [minor: N] * * /dev/vcsaN: idem, but including attributes, and prefixed with * the 4 bytes lines,columns,x,y (as screendump used to give). * Attribute/character pair is in native endianity. * [minor: N+128] * * /dev/vcsuN: similar to /dev/vcsaN but using 4-byte unicode values * instead of 1-byte screen glyph values. * [minor: N+64] * * /dev/vcsuaN: same idea as /dev/vcsaN for unicode (not yet implemented). * * This replaces screendump and part of selection, so that the system * administrator can control access using file system permissions. * * aeb@cwi.nl - efter Friedas begravelse - 950211 * * machek@k332.feld.cvut.cz - modified not to send characters to wrong console * - fixed some fatal off-by-one bugs (0-- no longer == -1 -> looping and looping and looping...) * - making it shorter - scr_readw are macros which expand in PRETTY long code */ #include <linux/kernel.h> #include <linux/major.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/tty.h> #include <linux/interrupt.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/vt_kern.h> #include <linux/selection.h> #include <linux/kbd_kern.h> #include <linux/console.h> #include <linux/device.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/poll.h> #include <linux/signal.h> #include <linux/slab.h> #include <linux/notifier.h> #include <linux/uaccess.h> #include <asm/byteorder.h> #include <linux/unaligned.h> #define HEADER_SIZE 4u #define CON_BUF_SIZE (IS_ENABLED(CONFIG_BASE_SMALL) ? 256 : PAGE_SIZE) /* * Our minor space: * * 0 ... 63 glyph mode without attributes * 64 ... 127 unicode mode without attributes * 128 ... 191 glyph mode with attributes * 192 ... 255 unused (reserved for unicode with attributes) * * This relies on MAX_NR_CONSOLES being <= 63, meaning 63 actual consoles * with minors 0, 64, 128 and 192 being proxies for the foreground console. */ #if MAX_NR_CONSOLES > 63 #warning "/dev/vcs* devices may not accommodate more than 63 consoles" #endif #define console(inode) (iminor(inode) & 63) #define use_unicode(inode) (iminor(inode) & 64) #define use_attributes(inode) (iminor(inode) & 128) struct vcs_poll_data { struct notifier_block notifier; unsigned int cons_num; int event; wait_queue_head_t waitq; struct fasync_struct *fasync; }; static int vcs_notifier(struct notifier_block *nb, unsigned long code, void *_param) { struct vt_notifier_param *param = _param; struct vc_data *vc = param->vc; struct vcs_poll_data *poll = container_of(nb, struct vcs_poll_data, notifier); int currcons = poll->cons_num; int fa_band; switch (code) { case VT_UPDATE: fa_band = POLL_PRI; break; case VT_DEALLOCATE: fa_band = POLL_HUP; break; default: return NOTIFY_DONE; } if (currcons == 0) currcons = fg_console; else currcons--; if (currcons != vc->vc_num) return NOTIFY_DONE; poll->event = code; wake_up_interruptible(&poll->waitq); kill_fasync(&poll->fasync, SIGIO, fa_band); return NOTIFY_OK; } static void vcs_poll_data_free(struct vcs_poll_data *poll) { unregister_vt_notifier(&poll->notifier); kfree(poll); } static struct vcs_poll_data * vcs_poll_data_get(struct file *file) { struct vcs_poll_data *poll = file->private_data, *kill = NULL; if (poll) return poll; poll = kzalloc(sizeof(*poll), GFP_KERNEL); if (!poll) return NULL; poll->cons_num = console(file_inode(file)); init_waitqueue_head(&poll->waitq); poll->notifier.notifier_call = vcs_notifier; /* * In order not to lose any update event, we must pretend one might * have occurred before we have a chance to register our notifier. * This is also how user space has come to detect which kernels * support POLLPRI on /dev/vcs* devices i.e. using poll() with * POLLPRI and a zero timeout. */ poll->event = VT_UPDATE; if (register_vt_notifier(&poll->notifier) != 0) { kfree(poll); return NULL; } /* * This code may be called either through ->poll() or ->fasync(). * If we have two threads using the same file descriptor, they could * both enter this function, both notice that the structure hasn't * been allocated yet and go ahead allocating it in parallel, but * only one of them must survive and be shared otherwise we'd leak * memory with a dangling notifier callback. */ spin_lock(&file->f_lock); if (!file->private_data) { file->private_data = poll; } else { /* someone else raced ahead of us */ kill = poll; poll = file->private_data; } spin_unlock(&file->f_lock); if (kill) vcs_poll_data_free(kill); return poll; } /** * vcs_vc - return VC for @inode * @inode: inode for which to return a VC * @viewed: returns whether this console is currently foreground (viewed) * * Must be called with console_lock. */ static struct vc_data *vcs_vc(struct inode *inode, bool *viewed) { unsigned int currcons = console(inode); WARN_CONSOLE_UNLOCKED(); if (currcons == 0) { currcons = fg_console; if (viewed) *viewed = true; } else { currcons--; if (viewed) *viewed = false; } return vc_cons[currcons].d; } /** * vcs_size - return size for a VC in @vc * @vc: which VC * @attr: does it use attributes? * @unicode: is it unicode? * * Must be called with console_lock. */ static int vcs_size(const struct vc_data *vc, bool attr, bool unicode) { int size; WARN_CONSOLE_UNLOCKED(); size = vc->vc_rows * vc->vc_cols; if (attr) { if (unicode) return -EOPNOTSUPP; size = 2 * size + HEADER_SIZE; } else if (unicode) size *= 4; return size; } static loff_t vcs_lseek(struct file *file, loff_t offset, int orig) { struct inode *inode = file_inode(file); struct vc_data *vc; int size; console_lock(); vc = vcs_vc(inode, NULL); if (!vc) { console_unlock(); return -ENXIO; } size = vcs_size(vc, use_attributes(inode), use_unicode(inode)); console_unlock(); if (size < 0) return size; return fixed_size_llseek(file, offset, orig, size); } static int vcs_read_buf_uni(struct vc_data *vc, char *con_buf, unsigned int pos, unsigned int count, bool viewed) { unsigned int nr, row, col, maxcol = vc->vc_cols; int ret; ret = vc_uniscr_check(vc); if (ret) return ret; pos /= 4; row = pos / maxcol; col = pos % maxcol; nr = maxcol - col; do { if (nr > count / 4) nr = count / 4; vc_uniscr_copy_line(vc, con_buf, viewed, row, col, nr); con_buf += nr * 4; count -= nr * 4; row++; col = 0; nr = maxcol; } while (count); return 0; } static void vcs_read_buf_noattr(const struct vc_data *vc, char *con_buf, unsigned int pos, unsigned int count, bool viewed) { u16 *org; unsigned int col, maxcol = vc->vc_cols; org = screen_pos(vc, pos, viewed); col = pos % maxcol; pos += maxcol - col; while (count-- > 0) { *con_buf++ = (vcs_scr_readw(vc, org++) & 0xff); if (++col == maxcol) { org = screen_pos(vc, pos, viewed); col = 0; pos += maxcol; } } } static unsigned int vcs_read_buf(const struct vc_data *vc, char *con_buf, unsigned int pos, unsigned int count, bool viewed, unsigned int *skip) { u16 *org, *con_buf16; unsigned int col, maxcol = vc->vc_cols; unsigned int filled = count; if (pos < HEADER_SIZE) { /* clamp header values if they don't fit */ con_buf[0] = min(vc->vc_rows, 0xFFu); con_buf[1] = min(vc->vc_cols, 0xFFu); getconsxy(vc, con_buf + 2); *skip += pos; count += pos; if (count > CON_BUF_SIZE) { count = CON_BUF_SIZE; filled = count - pos; } /* Advance state pointers and move on. */ count -= min(HEADER_SIZE, count); pos = HEADER_SIZE; con_buf += HEADER_SIZE; /* If count >= 0, then pos is even... */ } else if (pos & 1) { /* * Skip first byte for output if start address is odd. Update * region sizes up/down depending on free space in buffer. */ (*skip)++; if (count < CON_BUF_SIZE) count++; else filled--; } if (!count) return filled; pos -= HEADER_SIZE; pos /= 2; col = pos % maxcol; org = screen_pos(vc, pos, viewed); pos += maxcol - col; /* * Buffer has even length, so we can always copy character + attribute. * We do not copy last byte to userspace if count is odd. */ count = (count + 1) / 2; con_buf16 = (u16 *)con_buf; while (count) { *con_buf16++ = vcs_scr_readw(vc, org++); count--; if (++col == maxcol) { org = screen_pos(vc, pos, viewed); col = 0; pos += maxcol; } } return filled; } static ssize_t vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct inode *inode = file_inode(file); struct vc_data *vc; struct vcs_poll_data *poll; unsigned int read; ssize_t ret; char *con_buf; loff_t pos; bool viewed, attr, uni_mode; con_buf = (char *) __get_free_page(GFP_KERNEL); if (!con_buf) return -ENOMEM; pos = *ppos; /* Select the proper current console and verify * sanity of the situation under the console lock. */ console_lock(); uni_mode = use_unicode(inode); attr = use_attributes(inode); ret = -EINVAL; if (pos < 0) goto unlock_out; /* we enforce 32-bit alignment for pos and count in unicode mode */ if (uni_mode && (pos | count) & 3) goto unlock_out; poll = file->private_data; if (count && poll) poll->event = 0; read = 0; ret = 0; while (count) { unsigned int this_round, skip = 0; int size; vc = vcs_vc(inode, &viewed); if (!vc) { ret = -ENXIO; break; } /* Check whether we are above size each round, * as copy_to_user at the end of this loop * could sleep. */ size = vcs_size(vc, attr, uni_mode); if (size < 0) { ret = size; break; } if (pos >= size) break; if (count > size - pos) count = size - pos; this_round = count; if (this_round > CON_BUF_SIZE) this_round = CON_BUF_SIZE; /* Perform the whole read into the local con_buf. * Then we can drop the console spinlock and safely * attempt to move it to userspace. */ if (uni_mode) { ret = vcs_read_buf_uni(vc, con_buf, pos, this_round, viewed); if (ret) break; } else if (!attr) { vcs_read_buf_noattr(vc, con_buf, pos, this_round, viewed); } else { this_round = vcs_read_buf(vc, con_buf, pos, this_round, viewed, &skip); } /* Finally, release the console semaphore while we push * all the data to userspace from our temporary buffer. * * AKPM: Even though it's a semaphore, we should drop it because * the pagefault handling code may want to call printk(). */ console_unlock(); ret = copy_to_user(buf, con_buf + skip, this_round); console_lock(); if (ret) { read += this_round - ret; ret = -EFAULT; break; } buf += this_round; pos += this_round; read += this_round; count -= this_round; } *ppos += read; if (read) ret = read; unlock_out: console_unlock(); free_page((unsigned long) con_buf); return ret; } static u16 *vcs_write_buf_noattr(struct vc_data *vc, const char *con_buf, unsigned int pos, unsigned int count, bool viewed, u16 **org0) { u16 *org; unsigned int col, maxcol = vc->vc_cols; *org0 = org = screen_pos(vc, pos, viewed); col = pos % maxcol; pos += maxcol - col; while (count > 0) { unsigned char c = *con_buf++; count--; vcs_scr_writew(vc, (vcs_scr_readw(vc, org) & 0xff00) | c, org); org++; if (++col == maxcol) { org = screen_pos(vc, pos, viewed); col = 0; pos += maxcol; } } return org; } /* * Compilers (gcc 10) are unable to optimize the swap in cpu_to_le16. So do it * the poor man way. */ static inline u16 vc_compile_le16(u8 hi, u8 lo) { #ifdef __BIG_ENDIAN return (lo << 8u) | hi; #else return (hi << 8u) | lo; #endif } static u16 *vcs_write_buf(struct vc_data *vc, const char *con_buf, unsigned int pos, unsigned int count, bool viewed, u16 **org0) { u16 *org; unsigned int col, maxcol = vc->vc_cols; unsigned char c; /* header */ if (pos < HEADER_SIZE) { char header[HEADER_SIZE]; getconsxy(vc, header + 2); while (pos < HEADER_SIZE && count > 0) { count--; header[pos++] = *con_buf++; } if (!viewed) putconsxy(vc, header + 2); } if (!count) return NULL; pos -= HEADER_SIZE; col = (pos/2) % maxcol; *org0 = org = screen_pos(vc, pos/2, viewed); /* odd pos -- the first single character */ if (pos & 1) { count--; c = *con_buf++; vcs_scr_writew(vc, vc_compile_le16(c, vcs_scr_readw(vc, org)), org); org++; pos++; if (++col == maxcol) { org = screen_pos(vc, pos/2, viewed); col = 0; } } pos /= 2; pos += maxcol - col; /* even pos -- handle attr+character pairs */ while (count > 1) { unsigned short w; w = get_unaligned(((unsigned short *)con_buf)); vcs_scr_writew(vc, w, org++); con_buf += 2; count -= 2; if (++col == maxcol) { org = screen_pos(vc, pos, viewed); col = 0; pos += maxcol; } } if (!count) return org; /* odd pos -- the remaining character */ c = *con_buf++; vcs_scr_writew(vc, vc_compile_le16(vcs_scr_readw(vc, org) >> 8, c), org); return org; } static ssize_t vcs_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct inode *inode = file_inode(file); struct vc_data *vc; char *con_buf; u16 *org0, *org; unsigned int written; int size; ssize_t ret; loff_t pos; bool viewed, attr; if (use_unicode(inode)) return -EOPNOTSUPP; con_buf = (char *) __get_free_page(GFP_KERNEL); if (!con_buf) return -ENOMEM; pos = *ppos; /* Select the proper current console and verify * sanity of the situation under the console lock. */ console_lock(); attr = use_attributes(inode); ret = -ENXIO; vc = vcs_vc(inode, &viewed); if (!vc) goto unlock_out; size = vcs_size(vc, attr, false); if (size < 0) { ret = size; goto unlock_out; } ret = -EINVAL; if (pos < 0 || pos > size) goto unlock_out; if (count > size - pos) count = size - pos; written = 0; while (count) { unsigned int this_round = count; if (this_round > CON_BUF_SIZE) this_round = CON_BUF_SIZE; /* Temporarily drop the console lock so that we can read * in the write data from userspace safely. */ console_unlock(); ret = copy_from_user(con_buf, buf, this_round); console_lock(); if (ret) { this_round -= ret; if (!this_round) { /* Abort loop if no data were copied. Otherwise * fail with -EFAULT. */ if (written) break; ret = -EFAULT; goto unlock_out; } } /* The vc might have been freed or vcs_size might have changed * while we slept to grab the user buffer, so recheck. * Return data written up to now on failure. */ vc = vcs_vc(inode, &viewed); if (!vc) { if (written) break; ret = -ENXIO; goto unlock_out; } size = vcs_size(vc, attr, false); if (size < 0) { if (written) break; ret = size; goto unlock_out; } if (pos >= size) break; if (this_round > size - pos) this_round = size - pos; /* OK, now actually push the write to the console * under the lock using the local kernel buffer. */ if (attr) org = vcs_write_buf(vc, con_buf, pos, this_round, viewed, &org0); else org = vcs_write_buf_noattr(vc, con_buf, pos, this_round, viewed, &org0); count -= this_round; written += this_round; buf += this_round; pos += this_round; if (org) update_region(vc, (unsigned long)(org0), org - org0); } *ppos += written; ret = written; if (written) vcs_scr_updated(vc); unlock_out: console_unlock(); free_page((unsigned long) con_buf); return ret; } static __poll_t vcs_poll(struct file *file, poll_table *wait) { struct vcs_poll_data *poll = vcs_poll_data_get(file); __poll_t ret = DEFAULT_POLLMASK|EPOLLERR; if (poll) { poll_wait(file, &poll->waitq, wait); switch (poll->event) { case VT_UPDATE: ret = DEFAULT_POLLMASK|EPOLLPRI; break; case VT_DEALLOCATE: ret = DEFAULT_POLLMASK|EPOLLHUP|EPOLLERR; break; case 0: ret = DEFAULT_POLLMASK; break; } } return ret; } static int vcs_fasync(int fd, struct file *file, int on) { struct vcs_poll_data *poll = file->private_data; if (!poll) { /* don't allocate anything if all we want is disable fasync */ if (!on) return 0; poll = vcs_poll_data_get(file); if (!poll) return -ENOMEM; } return fasync_helper(fd, file, on, &poll->fasync); } static int vcs_open(struct inode *inode, struct file *filp) { unsigned int currcons = console(inode); bool attr = use_attributes(inode); bool uni_mode = use_unicode(inode); int ret = 0; /* we currently don't support attributes in unicode mode */ if (attr && uni_mode) return -EOPNOTSUPP; console_lock(); if(currcons && !vc_cons_allocated(currcons-1)) ret = -ENXIO; console_unlock(); return ret; } static int vcs_release(struct inode *inode, struct file *file) { struct vcs_poll_data *poll = file->private_data; if (poll) vcs_poll_data_free(poll); return 0; } static const struct file_operations vcs_fops = { .llseek = vcs_lseek, .read = vcs_read, .write = vcs_write, .poll = vcs_poll, .fasync = vcs_fasync, .open = vcs_open, .release = vcs_release, }; static const struct class vc_class = { .name = "vc", }; void vcs_make_sysfs(int index) { device_create(&vc_class, NULL, MKDEV(VCS_MAJOR, index + 1), NULL, "vcs%u", index + 1); device_create(&vc_class, NULL, MKDEV(VCS_MAJOR, index + 65), NULL, "vcsu%u", index + 1); device_create(&vc_class, NULL, MKDEV(VCS_MAJOR, index + 129), NULL, "vcsa%u", index + 1); } void vcs_remove_sysfs(int index) { device_destroy(&vc_class, MKDEV(VCS_MAJOR, index + 1)); device_destroy(&vc_class, MKDEV(VCS_MAJOR, index + 65)); device_destroy(&vc_class, MKDEV(VCS_MAJOR, index + 129)); } int __init vcs_init(void) { unsigned int i; if (register_chrdev(VCS_MAJOR, "vcs", &vcs_fops)) panic("unable to get major %d for vcs device", VCS_MAJOR); if (class_register(&vc_class)) panic("unable to create vc_class"); device_create(&vc_class, NULL, MKDEV(VCS_MAJOR, 0), NULL, "vcs"); device_create(&vc_class, NULL, MKDEV(VCS_MAJOR, 64), NULL, "vcsu"); device_create(&vc_class, NULL, MKDEV(VCS_MAJOR, 128), NULL, "vcsa"); for (i = 0; i < MIN_NR_CONSOLES; i++) vcs_make_sysfs(i); return 0; } |
| 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved. */ #include <linux/skbuff.h> #include <linux/delay.h> #include <linux/sched.h> #include <linux/vmalloc.h> #include <rdma/uverbs_ioctl.h> #include "rxe.h" #include "rxe_loc.h" #include "rxe_queue.h" #include "rxe_task.h" static int rxe_qp_chk_cap(struct rxe_dev *rxe, struct ib_qp_cap *cap, int has_srq) { if (cap->max_send_wr > rxe->attr.max_qp_wr) { rxe_dbg_dev(rxe, "invalid send wr = %u > %d\n", cap->max_send_wr, rxe->attr.max_qp_wr); goto err1; } if (cap->max_send_sge > rxe->attr.max_send_sge) { rxe_dbg_dev(rxe, "invalid send sge = %u > %d\n", cap->max_send_sge, rxe->attr.max_send_sge); goto err1; } if (!has_srq) { if (cap->max_recv_wr > rxe->attr.max_qp_wr) { rxe_dbg_dev(rxe, "invalid recv wr = %u > %d\n", cap->max_recv_wr, rxe->attr.max_qp_wr); goto err1; } if (cap->max_recv_sge > rxe->attr.max_recv_sge) { rxe_dbg_dev(rxe, "invalid recv sge = %u > %d\n", cap->max_recv_sge, rxe->attr.max_recv_sge); goto err1; } } if (cap->max_inline_data > rxe->max_inline_data) { rxe_dbg_dev(rxe, "invalid max inline data = %u > %d\n", cap->max_inline_data, rxe->max_inline_data); goto err1; } return 0; err1: return -EINVAL; } int rxe_qp_chk_init(struct rxe_dev *rxe, struct ib_qp_init_attr *init) { struct ib_qp_cap *cap = &init->cap; struct rxe_port *port; int port_num = init->port_num; switch (init->qp_type) { case IB_QPT_GSI: case IB_QPT_RC: case IB_QPT_UC: case IB_QPT_UD: break; default: return -EOPNOTSUPP; } if (!init->recv_cq || !init->send_cq) { rxe_dbg_dev(rxe, "missing cq\n"); goto err1; } if (rxe_qp_chk_cap(rxe, cap, !!init->srq)) goto err1; if (init->qp_type == IB_QPT_GSI) { if (!rdma_is_port_valid(&rxe->ib_dev, port_num)) { rxe_dbg_dev(rxe, "invalid port = %d\n", port_num); goto err1; } port = &rxe->port; if (init->qp_type == IB_QPT_GSI && port->qp_gsi_index) { rxe_dbg_dev(rxe, "GSI QP exists for port %d\n", port_num); goto err1; } } return 0; err1: return -EINVAL; } static int alloc_rd_atomic_resources(struct rxe_qp *qp, unsigned int n) { qp->resp.res_head = 0; qp->resp.res_tail = 0; qp->resp.resources = kcalloc(n, sizeof(struct resp_res), GFP_KERNEL); if (!qp->resp.resources) return -ENOMEM; return 0; } static void free_rd_atomic_resources(struct rxe_qp *qp) { if (qp->resp.resources) { int i; for (i = 0; i < qp->attr.max_dest_rd_atomic; i++) { struct resp_res *res = &qp->resp.resources[i]; free_rd_atomic_resource(res); } kfree(qp->resp.resources); qp->resp.resources = NULL; } } void free_rd_atomic_resource(struct resp_res *res) { res->type = 0; } static void cleanup_rd_atomic_resources(struct rxe_qp *qp) { int i; struct resp_res *res; if (qp->resp.resources) { for (i = 0; i < qp->attr.max_dest_rd_atomic; i++) { res = &qp->resp.resources[i]; free_rd_atomic_resource(res); } } } static void rxe_qp_init_misc(struct rxe_dev *rxe, struct rxe_qp *qp, struct ib_qp_init_attr *init) { struct rxe_port *port; u32 qpn; qp->sq_sig_type = init->sq_sig_type; qp->attr.path_mtu = 1; qp->mtu = ib_mtu_enum_to_int(qp->attr.path_mtu); qpn = qp->elem.index; port = &rxe->port; switch (init->qp_type) { case IB_QPT_GSI: qp->ibqp.qp_num = 1; port->qp_gsi_index = qpn; qp->attr.port_num = init->port_num; break; default: qp->ibqp.qp_num = qpn; break; } spin_lock_init(&qp->state_lock); spin_lock_init(&qp->sq.sq_lock); spin_lock_init(&qp->rq.producer_lock); spin_lock_init(&qp->rq.consumer_lock); skb_queue_head_init(&qp->req_pkts); skb_queue_head_init(&qp->resp_pkts); atomic_set(&qp->ssn, 0); atomic_set(&qp->skb_out, 0); } static int rxe_init_sq(struct rxe_qp *qp, struct ib_qp_init_attr *init, struct ib_udata *udata, struct rxe_create_qp_resp __user *uresp) { struct rxe_dev *rxe = to_rdev(qp->ibqp.device); int wqe_size; int err; qp->sq.max_wr = init->cap.max_send_wr; wqe_size = max_t(int, init->cap.max_send_sge * sizeof(struct ib_sge), init->cap.max_inline_data); qp->sq.max_sge = wqe_size / sizeof(struct ib_sge); qp->sq.max_inline = wqe_size; wqe_size += sizeof(struct rxe_send_wqe); qp->sq.queue = rxe_queue_init(rxe, &qp->sq.max_wr, wqe_size, QUEUE_TYPE_FROM_CLIENT); if (!qp->sq.queue) { rxe_err_qp(qp, "Unable to allocate send queue\n"); err = -ENOMEM; goto err_out; } /* prepare info for caller to mmap send queue if user space qp */ err = do_mmap_info(rxe, uresp ? &uresp->sq_mi : NULL, udata, qp->sq.queue->buf, qp->sq.queue->buf_size, &qp->sq.queue->ip); if (err) { rxe_err_qp(qp, "do_mmap_info failed, err = %d\n", err); goto err_free; } /* return actual capabilities to caller which may be larger * than requested */ init->cap.max_send_wr = qp->sq.max_wr; init->cap.max_send_sge = qp->sq.max_sge; init->cap.max_inline_data = qp->sq.max_inline; return 0; err_free: vfree(qp->sq.queue->buf); kfree(qp->sq.queue); qp->sq.queue = NULL; err_out: return err; } static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp, struct ib_qp_init_attr *init, struct ib_udata *udata, struct rxe_create_qp_resp __user *uresp) { int err; /* if we don't finish qp create make sure queue is valid */ skb_queue_head_init(&qp->req_pkts); err = sock_create_kern(&init_net, AF_INET, SOCK_DGRAM, 0, &qp->sk); if (err < 0) return err; qp->sk->sk->sk_user_data = (void *)(uintptr_t)qp->elem.index; /* pick a source UDP port number for this QP based on * the source QPN. this spreads traffic for different QPs * across different NIC RX queues (while using a single * flow for a given QP to maintain packet order). * the port number must be in the Dynamic Ports range * (0xc000 - 0xffff). */ qp->src_port = RXE_ROCE_V2_SPORT + (hash_32(qp_num(qp), 14) & 0x3fff); err = rxe_init_sq(qp, init, udata, uresp); if (err) return err; qp->req.wqe_index = queue_get_producer(qp->sq.queue, QUEUE_TYPE_FROM_CLIENT); qp->req.opcode = -1; qp->comp.opcode = -1; rxe_init_task(&qp->send_task, qp, rxe_sender); qp->qp_timeout_jiffies = 0; /* Can't be set for UD/UC in modify_qp */ if (init->qp_type == IB_QPT_RC) { timer_setup(&qp->rnr_nak_timer, rnr_nak_timer, 0); timer_setup(&qp->retrans_timer, retransmit_timer, 0); } return 0; } static int rxe_init_rq(struct rxe_qp *qp, struct ib_qp_init_attr *init, struct ib_udata *udata, struct rxe_create_qp_resp __user *uresp) { struct rxe_dev *rxe = to_rdev(qp->ibqp.device); int wqe_size; int err; qp->rq.max_wr = init->cap.max_recv_wr; qp->rq.max_sge = init->cap.max_recv_sge; wqe_size = sizeof(struct rxe_recv_wqe) + qp->rq.max_sge*sizeof(struct ib_sge); qp->rq.queue = rxe_queue_init(rxe, &qp->rq.max_wr, wqe_size, QUEUE_TYPE_FROM_CLIENT); if (!qp->rq.queue) { rxe_err_qp(qp, "Unable to allocate recv queue\n"); err = -ENOMEM; goto err_out; } /* prepare info for caller to mmap recv queue if user space qp */ err = do_mmap_info(rxe, uresp ? &uresp->rq_mi : NULL, udata, qp->rq.queue->buf, qp->rq.queue->buf_size, &qp->rq.queue->ip); if (err) { rxe_err_qp(qp, "do_mmap_info failed, err = %d\n", err); goto err_free; } /* return actual capabilities to caller which may be larger * than requested */ init->cap.max_recv_wr = qp->rq.max_wr; return 0; err_free: vfree(qp->rq.queue->buf); kfree(qp->rq.queue); qp->rq.queue = NULL; err_out: return err; } static int rxe_qp_init_resp(struct rxe_dev *rxe, struct rxe_qp *qp, struct ib_qp_init_attr *init, struct ib_udata *udata, struct rxe_create_qp_resp __user *uresp) { int err; /* if we don't finish qp create make sure queue is valid */ skb_queue_head_init(&qp->resp_pkts); if (!qp->srq) { err = rxe_init_rq(qp, init, udata, uresp); if (err) return err; } rxe_init_task(&qp->recv_task, qp, rxe_receiver); qp->resp.opcode = OPCODE_NONE; qp->resp.msn = 0; return 0; } /* called by the create qp verb */ int rxe_qp_from_init(struct rxe_dev *rxe, struct rxe_qp *qp, struct rxe_pd *pd, struct ib_qp_init_attr *init, struct rxe_create_qp_resp __user *uresp, struct ib_pd *ibpd, struct ib_udata *udata) { int err; struct rxe_cq *rcq = to_rcq(init->recv_cq); struct rxe_cq *scq = to_rcq(init->send_cq); struct rxe_srq *srq = init->srq ? to_rsrq(init->srq) : NULL; unsigned long flags; rxe_get(pd); rxe_get(rcq); rxe_get(scq); if (srq) rxe_get(srq); qp->pd = pd; qp->rcq = rcq; qp->scq = scq; qp->srq = srq; atomic_inc(&rcq->num_wq); atomic_inc(&scq->num_wq); rxe_qp_init_misc(rxe, qp, init); err = rxe_qp_init_req(rxe, qp, init, udata, uresp); if (err) goto err1; err = rxe_qp_init_resp(rxe, qp, init, udata, uresp); if (err) goto err2; spin_lock_irqsave(&qp->state_lock, flags); qp->attr.qp_state = IB_QPS_RESET; qp->valid = 1; spin_unlock_irqrestore(&qp->state_lock, flags); return 0; err2: rxe_queue_cleanup(qp->sq.queue); qp->sq.queue = NULL; err1: atomic_dec(&rcq->num_wq); atomic_dec(&scq->num_wq); qp->pd = NULL; qp->rcq = NULL; qp->scq = NULL; qp->srq = NULL; if (srq) rxe_put(srq); rxe_put(scq); rxe_put(rcq); rxe_put(pd); return err; } /* called by the query qp verb */ int rxe_qp_to_init(struct rxe_qp *qp, struct ib_qp_init_attr *init) { init->event_handler = qp->ibqp.event_handler; init->qp_context = qp->ibqp.qp_context; init->send_cq = qp->ibqp.send_cq; init->recv_cq = qp->ibqp.recv_cq; init->srq = qp->ibqp.srq; init->cap.max_send_wr = qp->sq.max_wr; init->cap.max_send_sge = qp->sq.max_sge; init->cap.max_inline_data = qp->sq.max_inline; if (!qp->srq) { init->cap.max_recv_wr = qp->rq.max_wr; init->cap.max_recv_sge = qp->rq.max_sge; } init->sq_sig_type = qp->sq_sig_type; init->qp_type = qp->ibqp.qp_type; init->port_num = 1; return 0; } int rxe_qp_chk_attr(struct rxe_dev *rxe, struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) { if (mask & IB_QP_PORT) { if (!rdma_is_port_valid(&rxe->ib_dev, attr->port_num)) { rxe_dbg_qp(qp, "invalid port %d\n", attr->port_num); goto err1; } } if (mask & IB_QP_CAP && rxe_qp_chk_cap(rxe, &attr->cap, !!qp->srq)) goto err1; if (mask & IB_QP_ACCESS_FLAGS) { if (!(qp_type(qp) == IB_QPT_RC || qp_type(qp) == IB_QPT_UC)) goto err1; if (attr->qp_access_flags & ~RXE_ACCESS_SUPPORTED_QP) goto err1; } if (mask & IB_QP_AV && rxe_av_chk_attr(qp, &attr->ah_attr)) goto err1; if (mask & IB_QP_ALT_PATH) { if (rxe_av_chk_attr(qp, &attr->alt_ah_attr)) goto err1; if (!rdma_is_port_valid(&rxe->ib_dev, attr->alt_port_num)) { rxe_dbg_qp(qp, "invalid alt port %d\n", attr->alt_port_num); goto err1; } if (attr->alt_timeout > 31) { rxe_dbg_qp(qp, "invalid alt timeout %d > 31\n", attr->alt_timeout); goto err1; } } if (mask & IB_QP_PATH_MTU) { struct rxe_port *port = &rxe->port; enum ib_mtu max_mtu = port->attr.max_mtu; enum ib_mtu mtu = attr->path_mtu; if (mtu > max_mtu) { rxe_dbg_qp(qp, "invalid mtu (%d) > (%d)\n", ib_mtu_enum_to_int(mtu), ib_mtu_enum_to_int(max_mtu)); goto err1; } } if (mask & IB_QP_MAX_QP_RD_ATOMIC) { if (attr->max_rd_atomic > rxe->attr.max_qp_rd_atom) { rxe_dbg_qp(qp, "invalid max_rd_atomic %d > %d\n", attr->max_rd_atomic, rxe->attr.max_qp_rd_atom); goto err1; } } if (mask & IB_QP_TIMEOUT) { if (attr->timeout > 31) { rxe_dbg_qp(qp, "invalid timeout %d > 31\n", attr->timeout); goto err1; } } return 0; err1: return -EINVAL; } /* move the qp to the reset state */ static void rxe_qp_reset(struct rxe_qp *qp) { /* stop tasks from running */ rxe_disable_task(&qp->recv_task); rxe_disable_task(&qp->send_task); /* drain work and packet queuesc */ rxe_sender(qp); rxe_receiver(qp); if (qp->rq.queue) rxe_queue_reset(qp->rq.queue); if (qp->sq.queue) rxe_queue_reset(qp->sq.queue); /* cleanup attributes */ atomic_set(&qp->ssn, 0); qp->req.opcode = -1; qp->req.need_retry = 0; qp->req.wait_for_rnr_timer = 0; qp->req.noack_pkts = 0; qp->resp.msn = 0; qp->resp.opcode = -1; qp->resp.drop_msg = 0; qp->resp.goto_error = 0; qp->resp.sent_psn_nak = 0; if (qp->resp.mr) { rxe_put(qp->resp.mr); qp->resp.mr = NULL; } cleanup_rd_atomic_resources(qp); /* reenable tasks */ rxe_enable_task(&qp->recv_task); rxe_enable_task(&qp->send_task); } /* move the qp to the error state */ void rxe_qp_error(struct rxe_qp *qp) { unsigned long flags; spin_lock_irqsave(&qp->state_lock, flags); qp->attr.qp_state = IB_QPS_ERR; /* drain work and packet queues */ rxe_sched_task(&qp->recv_task); rxe_sched_task(&qp->send_task); spin_unlock_irqrestore(&qp->state_lock, flags); } static void rxe_qp_sqd(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) { unsigned long flags; spin_lock_irqsave(&qp->state_lock, flags); qp->attr.sq_draining = 1; rxe_sched_task(&qp->send_task); spin_unlock_irqrestore(&qp->state_lock, flags); } /* caller should hold qp->state_lock */ static int __qp_chk_state(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) { enum ib_qp_state cur_state; enum ib_qp_state new_state; cur_state = (mask & IB_QP_CUR_STATE) ? attr->cur_qp_state : qp->attr.qp_state; new_state = (mask & IB_QP_STATE) ? attr->qp_state : cur_state; if (!ib_modify_qp_is_ok(cur_state, new_state, qp_type(qp), mask)) return -EINVAL; if (mask & IB_QP_STATE && cur_state == IB_QPS_SQD) { if (qp->attr.sq_draining && new_state != IB_QPS_ERR) return -EINVAL; } return 0; } static const char *const qps2str[] = { [IB_QPS_RESET] = "RESET", [IB_QPS_INIT] = "INIT", [IB_QPS_RTR] = "RTR", [IB_QPS_RTS] = "RTS", [IB_QPS_SQD] = "SQD", [IB_QPS_SQE] = "SQE", [IB_QPS_ERR] = "ERR", }; /* called by the modify qp verb */ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, struct ib_udata *udata) { int err; if (mask & IB_QP_CUR_STATE) qp->attr.cur_qp_state = attr->qp_state; if (mask & IB_QP_STATE) { unsigned long flags; spin_lock_irqsave(&qp->state_lock, flags); err = __qp_chk_state(qp, attr, mask); if (!err) { qp->attr.qp_state = attr->qp_state; rxe_dbg_qp(qp, "state -> %s\n", qps2str[attr->qp_state]); } spin_unlock_irqrestore(&qp->state_lock, flags); if (err) return err; switch (attr->qp_state) { case IB_QPS_RESET: rxe_qp_reset(qp); break; case IB_QPS_SQD: rxe_qp_sqd(qp, attr, mask); break; case IB_QPS_ERR: rxe_qp_error(qp); break; default: break; } } if (mask & IB_QP_MAX_QP_RD_ATOMIC) { int max_rd_atomic = attr->max_rd_atomic ? roundup_pow_of_two(attr->max_rd_atomic) : 0; qp->attr.max_rd_atomic = max_rd_atomic; atomic_set(&qp->req.rd_atomic, max_rd_atomic); } if (mask & IB_QP_MAX_DEST_RD_ATOMIC) { int max_dest_rd_atomic = attr->max_dest_rd_atomic ? roundup_pow_of_two(attr->max_dest_rd_atomic) : 0; qp->attr.max_dest_rd_atomic = max_dest_rd_atomic; free_rd_atomic_resources(qp); err = alloc_rd_atomic_resources(qp, max_dest_rd_atomic); if (err) return err; } if (mask & IB_QP_EN_SQD_ASYNC_NOTIFY) qp->attr.en_sqd_async_notify = attr->en_sqd_async_notify; if (mask & IB_QP_ACCESS_FLAGS) qp->attr.qp_access_flags = attr->qp_access_flags; if (mask & IB_QP_PKEY_INDEX) qp->attr.pkey_index = attr->pkey_index; if (mask & IB_QP_PORT) qp->attr.port_num = attr->port_num; if (mask & IB_QP_QKEY) qp->attr.qkey = attr->qkey; if (mask & IB_QP_AV) rxe_init_av(&attr->ah_attr, &qp->pri_av); if (mask & IB_QP_ALT_PATH) { rxe_init_av(&attr->alt_ah_attr, &qp->alt_av); qp->attr.alt_port_num = attr->alt_port_num; qp->attr.alt_pkey_index = attr->alt_pkey_index; qp->attr.alt_timeout = attr->alt_timeout; } if (mask & IB_QP_PATH_MTU) { qp->attr.path_mtu = attr->path_mtu; qp->mtu = ib_mtu_enum_to_int(attr->path_mtu); } if (mask & IB_QP_TIMEOUT) { qp->attr.timeout = attr->timeout; if (attr->timeout == 0) { qp->qp_timeout_jiffies = 0; } else { /* According to the spec, timeout = 4.096 * 2 ^ attr->timeout [us] */ int j = nsecs_to_jiffies(4096ULL << attr->timeout); qp->qp_timeout_jiffies = j ? j : 1; } } if (mask & IB_QP_RETRY_CNT) { qp->attr.retry_cnt = attr->retry_cnt; qp->comp.retry_cnt = attr->retry_cnt; rxe_dbg_qp(qp, "set retry count = %d\n", attr->retry_cnt); } if (mask & IB_QP_RNR_RETRY) { qp->attr.rnr_retry = attr->rnr_retry; qp->comp.rnr_retry = attr->rnr_retry; rxe_dbg_qp(qp, "set rnr retry count = %d\n", attr->rnr_retry); } if (mask & IB_QP_RQ_PSN) { qp->attr.rq_psn = (attr->rq_psn & BTH_PSN_MASK); qp->resp.psn = qp->attr.rq_psn; rxe_dbg_qp(qp, "set resp psn = 0x%x\n", qp->resp.psn); } if (mask & IB_QP_MIN_RNR_TIMER) { qp->attr.min_rnr_timer = attr->min_rnr_timer; rxe_dbg_qp(qp, "set min rnr timer = 0x%x\n", attr->min_rnr_timer); } if (mask & IB_QP_SQ_PSN) { qp->attr.sq_psn = (attr->sq_psn & BTH_PSN_MASK); qp->req.psn = qp->attr.sq_psn; qp->comp.psn = qp->attr.sq_psn; rxe_dbg_qp(qp, "set req psn = 0x%x\n", qp->req.psn); } if (mask & IB_QP_PATH_MIG_STATE) qp->attr.path_mig_state = attr->path_mig_state; if (mask & IB_QP_DEST_QPN) qp->attr.dest_qp_num = attr->dest_qp_num; return 0; } /* called by the query qp verb */ int rxe_qp_to_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask) { unsigned long flags; *attr = qp->attr; attr->rq_psn = qp->resp.psn; attr->sq_psn = qp->req.psn; attr->cap.max_send_wr = qp->sq.max_wr; attr->cap.max_send_sge = qp->sq.max_sge; attr->cap.max_inline_data = qp->sq.max_inline; if (!qp->srq) { attr->cap.max_recv_wr = qp->rq.max_wr; attr->cap.max_recv_sge = qp->rq.max_sge; } rxe_av_to_attr(&qp->pri_av, &attr->ah_attr); rxe_av_to_attr(&qp->alt_av, &attr->alt_ah_attr); /* Applications that get this state typically spin on it. * Yield the processor */ spin_lock_irqsave(&qp->state_lock, flags); attr->cur_qp_state = qp_state(qp); if (qp->attr.sq_draining) { spin_unlock_irqrestore(&qp->state_lock, flags); cond_resched(); } else { spin_unlock_irqrestore(&qp->state_lock, flags); } return 0; } int rxe_qp_chk_destroy(struct rxe_qp *qp) { /* See IBA o10-2.2.3 * An attempt to destroy a QP while attached to a mcast group * will fail immediately. */ if (atomic_read(&qp->mcg_num)) { rxe_dbg_qp(qp, "Attempt to destroy while attached to multicast group\n"); return -EBUSY; } return 0; } /* called when the last reference to the qp is dropped */ static void rxe_qp_do_cleanup(struct work_struct *work) { struct rxe_qp *qp = container_of(work, typeof(*qp), cleanup_work.work); unsigned long flags; spin_lock_irqsave(&qp->state_lock, flags); qp->valid = 0; spin_unlock_irqrestore(&qp->state_lock, flags); qp->qp_timeout_jiffies = 0; if (qp_type(qp) == IB_QPT_RC) { del_timer_sync(&qp->retrans_timer); del_timer_sync(&qp->rnr_nak_timer); } if (qp->recv_task.func) rxe_cleanup_task(&qp->recv_task); if (qp->send_task.func) rxe_cleanup_task(&qp->send_task); /* flush out any receive wr's or pending requests */ rxe_sender(qp); rxe_receiver(qp); if (qp->sq.queue) rxe_queue_cleanup(qp->sq.queue); if (qp->srq) rxe_put(qp->srq); if (qp->rq.queue) rxe_queue_cleanup(qp->rq.queue); if (qp->scq) { atomic_dec(&qp->scq->num_wq); rxe_put(qp->scq); } if (qp->rcq) { atomic_dec(&qp->rcq->num_wq); rxe_put(qp->rcq); } if (qp->pd) rxe_put(qp->pd); if (qp->resp.mr) rxe_put(qp->resp.mr); free_rd_atomic_resources(qp); if (qp->sk) { if (qp_type(qp) == IB_QPT_RC) sk_dst_reset(qp->sk->sk); kernel_sock_shutdown(qp->sk, SHUT_RDWR); sock_release(qp->sk); } } /* called when the last reference to the qp is dropped */ void rxe_qp_cleanup(struct rxe_pool_elem *elem) { struct rxe_qp *qp = container_of(elem, typeof(*qp), elem); execute_in_process_context(rxe_qp_do_cleanup, &qp->cleanup_work); } |
| 4 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nft_meta.h> #include <linux/if_bridge.h> #include <uapi/linux/netfilter_bridge.h> /* NF_BR_PRE_ROUTING */ #include "../br_private.h" static const struct net_device * nft_meta_get_bridge(const struct net_device *dev) { if (dev && netif_is_bridge_port(dev)) return netdev_master_upper_dev_get_rcu((struct net_device *)dev); return NULL; } static void nft_meta_bridge_get_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_meta *priv = nft_expr_priv(expr); const struct net_device *in = nft_in(pkt), *out = nft_out(pkt); u32 *dest = ®s->data[priv->dreg]; const struct net_device *br_dev; switch (priv->key) { case NFT_META_BRI_IIFNAME: br_dev = nft_meta_get_bridge(in); break; case NFT_META_BRI_OIFNAME: br_dev = nft_meta_get_bridge(out); break; case NFT_META_BRI_IIFPVID: { u16 p_pvid; br_dev = nft_meta_get_bridge(in); if (!br_dev || !br_vlan_enabled(br_dev)) goto err; br_vlan_get_pvid_rcu(in, &p_pvid); nft_reg_store16(dest, p_pvid); return; } case NFT_META_BRI_IIFVPROTO: { u16 p_proto; br_dev = nft_meta_get_bridge(in); if (!br_dev || !br_vlan_enabled(br_dev)) goto err; br_vlan_get_proto(br_dev, &p_proto); nft_reg_store_be16(dest, htons(p_proto)); return; } default: return nft_meta_get_eval(expr, regs, pkt); } strscpy_pad((char *)dest, br_dev ? br_dev->name : "", IFNAMSIZ); return; err: regs->verdict.code = NFT_BREAK; } static int nft_meta_bridge_get_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int len; priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); switch (priv->key) { case NFT_META_BRI_IIFNAME: case NFT_META_BRI_OIFNAME: len = IFNAMSIZ; break; case NFT_META_BRI_IIFPVID: case NFT_META_BRI_IIFVPROTO: len = sizeof(u16); break; default: return nft_meta_get_init(ctx, expr, tb); } priv->len = len; return nft_parse_register_store(ctx, tb[NFTA_META_DREG], &priv->dreg, NULL, NFT_DATA_VALUE, len); } static struct nft_expr_type nft_meta_bridge_type; static const struct nft_expr_ops nft_meta_bridge_get_ops = { .type = &nft_meta_bridge_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), .eval = nft_meta_bridge_get_eval, .init = nft_meta_bridge_get_init, .dump = nft_meta_get_dump, .reduce = nft_meta_get_reduce, }; static void nft_meta_bridge_set_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_meta *meta = nft_expr_priv(expr); u32 *sreg = ®s->data[meta->sreg]; struct sk_buff *skb = pkt->skb; u8 value8; switch (meta->key) { case NFT_META_BRI_BROUTE: value8 = nft_reg_load8(sreg); BR_INPUT_SKB_CB(skb)->br_netfilter_broute = !!value8; break; default: nft_meta_set_eval(expr, regs, pkt); } } static int nft_meta_bridge_set_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int len; int err; priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); switch (priv->key) { case NFT_META_BRI_BROUTE: len = sizeof(u8); break; default: return nft_meta_set_init(ctx, expr, tb); } priv->len = len; err = nft_parse_register_load(ctx, tb[NFTA_META_SREG], &priv->sreg, len); if (err < 0) return err; return 0; } static bool nft_meta_bridge_set_reduce(struct nft_regs_track *track, const struct nft_expr *expr) { int i; for (i = 0; i < NFT_REG32_NUM; i++) { if (!track->regs[i].selector) continue; if (track->regs[i].selector->ops != &nft_meta_bridge_get_ops) continue; __nft_reg_track_cancel(track, i); } return false; } static int nft_meta_bridge_set_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int hooks; switch (priv->key) { case NFT_META_BRI_BROUTE: hooks = 1 << NF_BR_PRE_ROUTING; break; default: return nft_meta_set_validate(ctx, expr); } return nft_chain_validate_hooks(ctx->chain, hooks); } static const struct nft_expr_ops nft_meta_bridge_set_ops = { .type = &nft_meta_bridge_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), .eval = nft_meta_bridge_set_eval, .init = nft_meta_bridge_set_init, .destroy = nft_meta_set_destroy, .dump = nft_meta_set_dump, .reduce = nft_meta_bridge_set_reduce, .validate = nft_meta_bridge_set_validate, }; static const struct nft_expr_ops * nft_meta_bridge_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { if (tb[NFTA_META_KEY] == NULL) return ERR_PTR(-EINVAL); if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG]) return ERR_PTR(-EINVAL); if (tb[NFTA_META_DREG]) return &nft_meta_bridge_get_ops; if (tb[NFTA_META_SREG]) return &nft_meta_bridge_set_ops; return ERR_PTR(-EINVAL); } static struct nft_expr_type nft_meta_bridge_type __read_mostly = { .family = NFPROTO_BRIDGE, .name = "meta", .select_ops = nft_meta_bridge_select_ops, .policy = nft_meta_policy, .maxattr = NFTA_META_MAX, .owner = THIS_MODULE, }; static int __init nft_meta_bridge_module_init(void) { return nft_register_expr(&nft_meta_bridge_type); } static void __exit nft_meta_bridge_module_exit(void) { nft_unregister_expr(&nft_meta_bridge_type); } module_init(nft_meta_bridge_module_init); module_exit(nft_meta_bridge_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("wenxu <wenxu@ucloud.cn>"); MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "meta"); MODULE_DESCRIPTION("Support for bridge dedicated meta key"); |
| 7 2662 848 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_COMPAT_H #define _LINUX_COMPAT_H /* * These are the type definitions for the architecture specific * syscall compatibility layer. */ #include <linux/types.h> #include <linux/time.h> #include <linux/stat.h> #include <linux/param.h> /* for HZ */ #include <linux/sem.h> #include <linux/socket.h> #include <linux/if.h> #include <linux/fs.h> #include <linux/aio_abi.h> /* for aio_context_t */ #include <linux/uaccess.h> #include <linux/unistd.h> #include <asm/compat.h> #include <asm/siginfo.h> #include <asm/signal.h> #ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER /* * It may be useful for an architecture to override the definitions of the * COMPAT_SYSCALL_DEFINE0 and COMPAT_SYSCALL_DEFINEx() macros, in particular * to use a different calling convention for syscalls. To allow for that, + the prototypes for the compat_sys_*() functions below will *not* be included * if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. */ #include <asm/syscall_wrapper.h> #endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ #ifndef COMPAT_USE_64BIT_TIME #define COMPAT_USE_64BIT_TIME 0 #endif #ifndef __SC_DELOUSE #define __SC_DELOUSE(t,v) ((__force t)(unsigned long)(v)) #endif #ifndef COMPAT_SYSCALL_DEFINE0 #define COMPAT_SYSCALL_DEFINE0(name) \ asmlinkage long compat_sys_##name(void); \ ALLOW_ERROR_INJECTION(compat_sys_##name, ERRNO); \ asmlinkage long compat_sys_##name(void) #endif /* COMPAT_SYSCALL_DEFINE0 */ #define COMPAT_SYSCALL_DEFINE1(name, ...) \ COMPAT_SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINE2(name, ...) \ COMPAT_SYSCALL_DEFINEx(2, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINE3(name, ...) \ COMPAT_SYSCALL_DEFINEx(3, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINE4(name, ...) \ COMPAT_SYSCALL_DEFINEx(4, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINE5(name, ...) \ COMPAT_SYSCALL_DEFINEx(5, _##name, __VA_ARGS__) #define COMPAT_SYSCALL_DEFINE6(name, ...) \ COMPAT_SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) /* * The asmlinkage stub is aliased to a function named __se_compat_sys_*() which * sign-extends 32-bit ints to longs whenever needed. The actual work is * done within __do_compat_sys_*(). */ #ifndef COMPAT_SYSCALL_DEFINEx #define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ __diag_push(); \ __diag_ignore(GCC, 8, "-Wattribute-alias", \ "Type aliasing is used to sanitize syscall arguments");\ asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \ __attribute__((alias(__stringify(__se_compat_sys##name)))); \ ALLOW_ERROR_INJECTION(compat_sys##name, ERRNO); \ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ asmlinkage long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ { \ long ret = __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\ __MAP(x,__SC_TEST,__VA_ARGS__); \ return ret; \ } \ __diag_pop(); \ static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) #endif /* COMPAT_SYSCALL_DEFINEx */ struct compat_iovec { compat_uptr_t iov_base; compat_size_t iov_len; }; #ifndef compat_user_stack_pointer #define compat_user_stack_pointer() current_user_stack_pointer() #endif #ifndef compat_sigaltstack /* we'll need that for MIPS */ typedef struct compat_sigaltstack { compat_uptr_t ss_sp; int ss_flags; compat_size_t ss_size; } compat_stack_t; #endif #ifndef COMPAT_MINSIGSTKSZ #define COMPAT_MINSIGSTKSZ MINSIGSTKSZ #endif #define compat_jiffies_to_clock_t(x) \ (((unsigned long)(x) * COMPAT_USER_HZ) / HZ) typedef __compat_uid32_t compat_uid_t; typedef __compat_gid32_t compat_gid_t; struct compat_sel_arg_struct; struct rusage; struct old_itimerval32; struct compat_tms { compat_clock_t tms_utime; compat_clock_t tms_stime; compat_clock_t tms_cutime; compat_clock_t tms_cstime; }; #define _COMPAT_NSIG_WORDS (_COMPAT_NSIG / _COMPAT_NSIG_BPW) typedef struct { compat_sigset_word sig[_COMPAT_NSIG_WORDS]; } compat_sigset_t; int set_compat_user_sigmask(const compat_sigset_t __user *umask, size_t sigsetsize); struct compat_sigaction { #ifndef __ARCH_HAS_IRIX_SIGACTION compat_uptr_t sa_handler; compat_ulong_t sa_flags; #else compat_uint_t sa_flags; compat_uptr_t sa_handler; #endif #ifdef __ARCH_HAS_SA_RESTORER compat_uptr_t sa_restorer; #endif compat_sigset_t sa_mask __packed; }; typedef union compat_sigval { compat_int_t sival_int; compat_uptr_t sival_ptr; } compat_sigval_t; typedef struct compat_siginfo { int si_signo; #ifndef __ARCH_HAS_SWAPPED_SIGINFO int si_errno; int si_code; #else int si_code; int si_errno; #endif union { int _pad[128/sizeof(int) - 3]; /* kill() */ struct { compat_pid_t _pid; /* sender's pid */ __compat_uid32_t _uid; /* sender's uid */ } _kill; /* POSIX.1b timers */ struct { compat_timer_t _tid; /* timer id */ int _overrun; /* overrun count */ compat_sigval_t _sigval; /* same as below */ } _timer; /* POSIX.1b signals */ struct { compat_pid_t _pid; /* sender's pid */ __compat_uid32_t _uid; /* sender's uid */ compat_sigval_t _sigval; } _rt; /* SIGCHLD */ struct { compat_pid_t _pid; /* which child */ __compat_uid32_t _uid; /* sender's uid */ int _status; /* exit code */ compat_clock_t _utime; compat_clock_t _stime; } _sigchld; #ifdef CONFIG_X86_X32_ABI /* SIGCHLD (x32 version) */ struct { compat_pid_t _pid; /* which child */ __compat_uid32_t _uid; /* sender's uid */ int _status; /* exit code */ compat_s64 _utime; compat_s64 _stime; } _sigchld_x32; #endif /* SIGILL, SIGFPE, SIGSEGV, SIGBUS, SIGTRAP, SIGEMT */ struct { compat_uptr_t _addr; /* faulting insn/memory ref. */ #define __COMPAT_ADDR_BND_PKEY_PAD (__alignof__(compat_uptr_t) < sizeof(short) ? \ sizeof(short) : __alignof__(compat_uptr_t)) union { /* used on alpha and sparc */ int _trapno; /* TRAP # which caused the signal */ /* * used when si_code=BUS_MCEERR_AR or * used when si_code=BUS_MCEERR_AO */ short int _addr_lsb; /* Valid LSB of the reported address. */ /* used when si_code=SEGV_BNDERR */ struct { char _dummy_bnd[__COMPAT_ADDR_BND_PKEY_PAD]; compat_uptr_t _lower; compat_uptr_t _upper; } _addr_bnd; /* used when si_code=SEGV_PKUERR */ struct { char _dummy_pkey[__COMPAT_ADDR_BND_PKEY_PAD]; u32 _pkey; } _addr_pkey; /* used when si_code=TRAP_PERF */ struct { compat_ulong_t _data; u32 _type; u32 _flags; } _perf; }; } _sigfault; /* SIGPOLL */ struct { compat_long_t _band; /* POLL_IN, POLL_OUT, POLL_MSG */ int _fd; } _sigpoll; struct { compat_uptr_t _call_addr; /* calling user insn */ int _syscall; /* triggering system call number */ unsigned int _arch; /* AUDIT_ARCH_* of syscall */ } _sigsys; } _sifields; } compat_siginfo_t; struct compat_rlimit { compat_ulong_t rlim_cur; compat_ulong_t rlim_max; }; #ifdef __ARCH_NEED_COMPAT_FLOCK64_PACKED #define __ARCH_COMPAT_FLOCK64_PACK __attribute__((packed)) #else #define __ARCH_COMPAT_FLOCK64_PACK #endif struct compat_flock { short l_type; short l_whence; compat_off_t l_start; compat_off_t l_len; #ifdef __ARCH_COMPAT_FLOCK_EXTRA_SYSID __ARCH_COMPAT_FLOCK_EXTRA_SYSID #endif compat_pid_t l_pid; #ifdef __ARCH_COMPAT_FLOCK_PAD __ARCH_COMPAT_FLOCK_PAD #endif }; struct compat_flock64 { short l_type; short l_whence; compat_loff_t l_start; compat_loff_t l_len; compat_pid_t l_pid; #ifdef __ARCH_COMPAT_FLOCK64_PAD __ARCH_COMPAT_FLOCK64_PAD #endif } __ARCH_COMPAT_FLOCK64_PACK; struct compat_rusage { struct old_timeval32 ru_utime; struct old_timeval32 ru_stime; compat_long_t ru_maxrss; compat_long_t ru_ixrss; compat_long_t ru_idrss; compat_long_t ru_isrss; compat_long_t ru_minflt; compat_long_t ru_majflt; compat_long_t ru_nswap; compat_long_t ru_inblock; compat_long_t ru_oublock; compat_long_t ru_msgsnd; compat_long_t ru_msgrcv; compat_long_t ru_nsignals; compat_long_t ru_nvcsw; compat_long_t ru_nivcsw; }; extern int put_compat_rusage(const struct rusage *, struct compat_rusage __user *); struct compat_siginfo; struct __compat_aio_sigset; struct compat_dirent { u32 d_ino; compat_off_t d_off; u16 d_reclen; char d_name[256]; }; struct compat_ustat { compat_daddr_t f_tfree; compat_ino_t f_tinode; char f_fname[6]; char f_fpack[6]; }; #define COMPAT_SIGEV_PAD_SIZE ((SIGEV_MAX_SIZE/sizeof(int)) - 3) typedef struct compat_sigevent { compat_sigval_t sigev_value; compat_int_t sigev_signo; compat_int_t sigev_notify; union { compat_int_t _pad[COMPAT_SIGEV_PAD_SIZE]; compat_int_t _tid; struct { compat_uptr_t _function; compat_uptr_t _attribute; } _sigev_thread; } _sigev_un; } compat_sigevent_t; struct compat_ifmap { compat_ulong_t mem_start; compat_ulong_t mem_end; unsigned short base_addr; unsigned char irq; unsigned char dma; unsigned char port; }; struct compat_if_settings { unsigned int type; /* Type of physical device or protocol */ unsigned int size; /* Size of the data allocated by the caller */ compat_uptr_t ifs_ifsu; /* union of pointers */ }; struct compat_ifreq { union { char ifrn_name[IFNAMSIZ]; /* if name, e.g. "en0" */ } ifr_ifrn; union { struct sockaddr ifru_addr; struct sockaddr ifru_dstaddr; struct sockaddr ifru_broadaddr; struct sockaddr ifru_netmask; struct sockaddr ifru_hwaddr; short ifru_flags; compat_int_t ifru_ivalue; compat_int_t ifru_mtu; struct compat_ifmap ifru_map; char ifru_slave[IFNAMSIZ]; /* Just fits the size */ char ifru_newname[IFNAMSIZ]; compat_caddr_t ifru_data; struct compat_if_settings ifru_settings; } ifr_ifru; }; struct compat_ifconf { compat_int_t ifc_len; /* size of buffer */ compat_caddr_t ifcbuf; }; struct compat_robust_list { compat_uptr_t next; }; struct compat_robust_list_head { struct compat_robust_list list; compat_long_t futex_offset; compat_uptr_t list_op_pending; }; #ifdef CONFIG_COMPAT_OLD_SIGACTION struct compat_old_sigaction { compat_uptr_t sa_handler; compat_old_sigset_t sa_mask; compat_ulong_t sa_flags; compat_uptr_t sa_restorer; }; #endif struct compat_keyctl_kdf_params { compat_uptr_t hashname; compat_uptr_t otherinfo; __u32 otherinfolen; __u32 __spare[8]; }; struct compat_stat; struct compat_statfs; struct compat_statfs64; struct compat_old_linux_dirent; struct compat_linux_dirent; struct linux_dirent64; struct compat_msghdr; struct compat_mmsghdr; struct compat_sysinfo; struct compat_sysctl_args; struct compat_kexec_segment; struct compat_mq_attr; struct compat_msgbuf; void copy_siginfo_to_external32(struct compat_siginfo *to, const struct kernel_siginfo *from); int copy_siginfo_from_user32(kernel_siginfo_t *to, const struct compat_siginfo __user *from); int __copy_siginfo_to_user32(struct compat_siginfo __user *to, const kernel_siginfo_t *from); #ifndef copy_siginfo_to_user32 #define copy_siginfo_to_user32 __copy_siginfo_to_user32 #endif int get_compat_sigevent(struct sigevent *event, const struct compat_sigevent __user *u_event); extern int get_compat_sigset(sigset_t *set, const compat_sigset_t __user *compat); /* * Defined inline such that size can be compile time constant, which avoids * CONFIG_HARDENED_USERCOPY complaining about copies from task_struct */ static inline int put_compat_sigset(compat_sigset_t __user *compat, const sigset_t *set, unsigned int size) { /* size <= sizeof(compat_sigset_t) <= sizeof(sigset_t) */ #if defined(__BIG_ENDIAN) && defined(CONFIG_64BIT) compat_sigset_t v; switch (_NSIG_WORDS) { case 4: v.sig[7] = (set->sig[3] >> 32); v.sig[6] = set->sig[3]; fallthrough; case 3: v.sig[5] = (set->sig[2] >> 32); v.sig[4] = set->sig[2]; fallthrough; case 2: v.sig[3] = (set->sig[1] >> 32); v.sig[2] = set->sig[1]; fallthrough; case 1: v.sig[1] = (set->sig[0] >> 32); v.sig[0] = set->sig[0]; } return copy_to_user(compat, &v, size) ? -EFAULT : 0; #else return copy_to_user(compat, set, size) ? -EFAULT : 0; #endif } #ifdef CONFIG_CPU_BIG_ENDIAN #define unsafe_put_compat_sigset(compat, set, label) do { \ compat_sigset_t __user *__c = compat; \ const sigset_t *__s = set; \ \ switch (_NSIG_WORDS) { \ case 4: \ unsafe_put_user(__s->sig[3] >> 32, &__c->sig[7], label); \ unsafe_put_user(__s->sig[3], &__c->sig[6], label); \ fallthrough; \ case 3: \ unsafe_put_user(__s->sig[2] >> 32, &__c->sig[5], label); \ unsafe_put_user(__s->sig[2], &__c->sig[4], label); \ fallthrough; \ case 2: \ unsafe_put_user(__s->sig[1] >> 32, &__c->sig[3], label); \ unsafe_put_user(__s->sig[1], &__c->sig[2], label); \ fallthrough; \ case 1: \ unsafe_put_user(__s->sig[0] >> 32, &__c->sig[1], label); \ unsafe_put_user(__s->sig[0], &__c->sig[0], label); \ } \ } while (0) #define unsafe_get_compat_sigset(set, compat, label) do { \ const compat_sigset_t __user *__c = compat; \ compat_sigset_word hi, lo; \ sigset_t *__s = set; \ \ switch (_NSIG_WORDS) { \ case 4: \ unsafe_get_user(lo, &__c->sig[7], label); \ unsafe_get_user(hi, &__c->sig[6], label); \ __s->sig[3] = hi | (((long)lo) << 32); \ fallthrough; \ case 3: \ unsafe_get_user(lo, &__c->sig[5], label); \ unsafe_get_user(hi, &__c->sig[4], label); \ __s->sig[2] = hi | (((long)lo) << 32); \ fallthrough; \ case 2: \ unsafe_get_user(lo, &__c->sig[3], label); \ unsafe_get_user(hi, &__c->sig[2], label); \ __s->sig[1] = hi | (((long)lo) << 32); \ fallthrough; \ case 1: \ unsafe_get_user(lo, &__c->sig[1], label); \ unsafe_get_user(hi, &__c->sig[0], label); \ __s->sig[0] = hi | (((long)lo) << 32); \ } \ } while (0) #else #define unsafe_put_compat_sigset(compat, set, label) do { \ compat_sigset_t __user *__c = compat; \ const sigset_t *__s = set; \ \ unsafe_copy_to_user(__c, __s, sizeof(*__c), label); \ } while (0) #define unsafe_get_compat_sigset(set, compat, label) do { \ const compat_sigset_t __user *__c = compat; \ sigset_t *__s = set; \ \ unsafe_copy_from_user(__s, __c, sizeof(*__c), label); \ } while (0) #endif extern int compat_ptrace_request(struct task_struct *child, compat_long_t request, compat_ulong_t addr, compat_ulong_t data); extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t addr, compat_ulong_t data); struct epoll_event; /* fortunately, this one is fixed-layout */ int compat_restore_altstack(const compat_stack_t __user *uss); int __compat_save_altstack(compat_stack_t __user *, unsigned long); #define unsafe_compat_save_altstack(uss, sp, label) do { \ compat_stack_t __user *__uss = uss; \ struct task_struct *t = current; \ unsafe_put_user(ptr_to_compat((void __user *)t->sas_ss_sp), \ &__uss->ss_sp, label); \ unsafe_put_user(t->sas_ss_flags, &__uss->ss_flags, label); \ unsafe_put_user(t->sas_ss_size, &__uss->ss_size, label); \ } while (0); /* * These syscall function prototypes are kept in the same order as * include/uapi/asm-generic/unistd.h. Deprecated or obsolete system calls * go below. * * Please note that these prototypes here are only provided for information * purposes, for static analysis, and for linking from the syscall table. * These functions should not be called elsewhere from kernel code. * * As the syscall calling convention may be different from the default * for architectures overriding the syscall calling convention, do not * include the prototypes if CONFIG_ARCH_HAS_SYSCALL_WRAPPER is enabled. */ #ifndef CONFIG_ARCH_HAS_SYSCALL_WRAPPER asmlinkage long compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p); asmlinkage long compat_sys_io_submit(compat_aio_context_t ctx_id, int nr, u32 __user *iocb); asmlinkage long compat_sys_io_pgetevents(compat_aio_context_t ctx_id, compat_long_t min_nr, compat_long_t nr, struct io_event __user *events, struct old_timespec32 __user *timeout, const struct __compat_aio_sigset __user *usig); asmlinkage long compat_sys_io_pgetevents_time64(compat_aio_context_t ctx_id, compat_long_t min_nr, compat_long_t nr, struct io_event __user *events, struct __kernel_timespec __user *timeout, const struct __compat_aio_sigset __user *usig); asmlinkage long compat_sys_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, int timeout, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); asmlinkage long compat_sys_epoll_pwait2(int epfd, struct epoll_event __user *events, int maxevents, const struct __kernel_timespec __user *timeout, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd, compat_ulong_t arg); asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd, compat_ulong_t arg); asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd, compat_ulong_t arg); asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_statfs __user *buf); asmlinkage long compat_sys_statfs64(const char __user *pathname, compat_size_t sz, struct compat_statfs64 __user *buf); asmlinkage long compat_sys_fstatfs(unsigned int fd, struct compat_statfs __user *buf); asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user *buf); asmlinkage long compat_sys_truncate(const char __user *, compat_off_t); asmlinkage long compat_sys_ftruncate(unsigned int, compat_off_t); /* No generic prototype for truncate64, ftruncate64, fallocate */ asmlinkage long compat_sys_openat(int dfd, const char __user *filename, int flags, umode_t mode); asmlinkage long compat_sys_getdents(unsigned int fd, struct compat_linux_dirent __user *dirent, unsigned int count); asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int); /* No generic prototype for pread64 and pwrite64 */ asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd, const struct iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high); asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd, const struct iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high); #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 asmlinkage long compat_sys_preadv64(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos); #endif #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64 asmlinkage long compat_sys_pwritev64(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos); #endif asmlinkage long compat_sys_sendfile(int out_fd, int in_fd, compat_off_t __user *offset, compat_size_t count); asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd, compat_loff_t __user *offset, compat_size_t count); asmlinkage long compat_sys_pselect6_time32(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct old_timespec32 __user *tsp, void __user *sig); asmlinkage long compat_sys_pselect6_time64(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct __kernel_timespec __user *tsp, void __user *sig); asmlinkage long compat_sys_ppoll_time32(struct pollfd __user *ufds, unsigned int nfds, struct old_timespec32 __user *tsp, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); asmlinkage long compat_sys_ppoll_time64(struct pollfd __user *ufds, unsigned int nfds, struct __kernel_timespec __user *tsp, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); asmlinkage long compat_sys_signalfd4(int ufd, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize, int flags); asmlinkage long compat_sys_newfstatat(unsigned int dfd, const char __user *filename, struct compat_stat __user *statbuf, int flag); asmlinkage long compat_sys_newfstat(unsigned int fd, struct compat_stat __user *statbuf); /* No generic prototype for sync_file_range and sync_file_range2 */ asmlinkage long compat_sys_waitid(int, compat_pid_t, struct compat_siginfo __user *, int, struct compat_rusage __user *); asmlinkage long compat_sys_set_robust_list(struct compat_robust_list_head __user *head, compat_size_t len); asmlinkage long compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, compat_size_t __user *len_ptr); asmlinkage long compat_sys_getitimer(int which, struct old_itimerval32 __user *it); asmlinkage long compat_sys_setitimer(int which, struct old_itimerval32 __user *in, struct old_itimerval32 __user *out); asmlinkage long compat_sys_kexec_load(compat_ulong_t entry, compat_ulong_t nr_segments, struct compat_kexec_segment __user *, compat_ulong_t flags); asmlinkage long compat_sys_timer_create(clockid_t which_clock, struct compat_sigevent __user *timer_event_spec, timer_t __user *created_timer_id); asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, compat_long_t addr, compat_long_t data); asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid, unsigned int len, compat_ulong_t __user *user_mask_ptr); asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len, compat_ulong_t __user *user_mask_ptr); asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr, compat_stack_t __user *uoss_ptr); asmlinkage long compat_sys_rt_sigsuspend(compat_sigset_t __user *unewset, compat_size_t sigsetsize); #ifndef CONFIG_ODD_RT_SIGACTION asmlinkage long compat_sys_rt_sigaction(int, const struct compat_sigaction __user *, struct compat_sigaction __user *, compat_size_t); #endif asmlinkage long compat_sys_rt_sigprocmask(int how, compat_sigset_t __user *set, compat_sigset_t __user *oset, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigpending(compat_sigset_t __user *uset, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigtimedwait_time32(compat_sigset_t __user *uthese, struct compat_siginfo __user *uinfo, struct old_timespec32 __user *uts, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigtimedwait_time64(compat_sigset_t __user *uthese, struct compat_siginfo __user *uinfo, struct __kernel_timespec __user *uts, compat_size_t sigsetsize); asmlinkage long compat_sys_rt_sigqueueinfo(compat_pid_t pid, int sig, struct compat_siginfo __user *uinfo); /* No generic prototype for rt_sigreturn */ asmlinkage long compat_sys_times(struct compat_tms __user *tbuf); asmlinkage long compat_sys_getrlimit(unsigned int resource, struct compat_rlimit __user *rlim); asmlinkage long compat_sys_setrlimit(unsigned int resource, struct compat_rlimit __user *rlim); asmlinkage long compat_sys_getrusage(int who, struct compat_rusage __user *ru); asmlinkage long compat_sys_gettimeofday(struct old_timeval32 __user *tv, struct timezone __user *tz); asmlinkage long compat_sys_settimeofday(struct old_timeval32 __user *tv, struct timezone __user *tz); asmlinkage long compat_sys_sysinfo(struct compat_sysinfo __user *info); asmlinkage long compat_sys_mq_open(const char __user *u_name, int oflag, compat_mode_t mode, struct compat_mq_attr __user *u_attr); asmlinkage long compat_sys_mq_notify(mqd_t mqdes, const struct compat_sigevent __user *u_notification); asmlinkage long compat_sys_mq_getsetattr(mqd_t mqdes, const struct compat_mq_attr __user *u_mqstat, struct compat_mq_attr __user *u_omqstat); asmlinkage long compat_sys_msgctl(int first, int second, void __user *uptr); asmlinkage long compat_sys_msgrcv(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, compat_long_t msgtyp, int msgflg); asmlinkage long compat_sys_msgsnd(int msqid, compat_uptr_t msgp, compat_ssize_t msgsz, int msgflg); asmlinkage long compat_sys_semctl(int semid, int semnum, int cmd, int arg); asmlinkage long compat_sys_shmctl(int first, int second, void __user *uptr); asmlinkage long compat_sys_shmat(int shmid, compat_uptr_t shmaddr, int shmflg); asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, compat_size_t len, unsigned flags, struct sockaddr __user *addr, int __user *addrlen); asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags); asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags); /* No generic prototype for readahead */ asmlinkage long compat_sys_keyctl(u32 option, u32 arg2, u32 arg3, u32 arg4, u32 arg5); asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv, const compat_uptr_t __user *envp); /* No generic prototype for fadvise64_64 */ /* CONFIG_MMU only */ asmlinkage long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, compat_pid_t pid, int sig, struct compat_siginfo __user *uinfo); asmlinkage long compat_sys_recvmmsg_time64(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags, struct __kernel_timespec __user *timeout); asmlinkage long compat_sys_recvmmsg_time32(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags, struct old_timespec32 __user *timeout); asmlinkage long compat_sys_wait4(compat_pid_t pid, compat_uint_t __user *stat_addr, int options, struct compat_rusage __user *ru); asmlinkage long compat_sys_fanotify_mark(int, unsigned int, __u32, __u32, int, const char __user *); asmlinkage long compat_sys_open_by_handle_at(int mountdirfd, struct file_handle __user *handle, int flags); asmlinkage long compat_sys_sendmmsg(int fd, struct compat_mmsghdr __user *mmsg, unsigned vlen, unsigned int flags); asmlinkage long compat_sys_execveat(int dfd, const char __user *filename, const compat_uptr_t __user *argv, const compat_uptr_t __user *envp, int flags); asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd, const struct iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd, const struct iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 asmlinkage long compat_sys_preadv64v2(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags); #endif #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 asmlinkage long compat_sys_pwritev64v2(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags); #endif /* * Deprecated system calls which are still defined in * include/uapi/asm-generic/unistd.h and wanted by >= 1 arch */ /* __ARCH_WANT_SYSCALL_NO_AT */ asmlinkage long compat_sys_open(const char __user *filename, int flags, umode_t mode); /* __ARCH_WANT_SYSCALL_NO_FLAGS */ asmlinkage long compat_sys_signalfd(int ufd, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize); /* __ARCH_WANT_SYSCALL_OFF_T */ asmlinkage long compat_sys_newstat(const char __user *filename, struct compat_stat __user *statbuf); asmlinkage long compat_sys_newlstat(const char __user *filename, struct compat_stat __user *statbuf); /* __ARCH_WANT_SYSCALL_DEPRECATED */ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct old_timeval32 __user *tvp); asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32); asmlinkage long compat_sys_recv(int fd, void __user *buf, compat_size_t len, unsigned flags); /* obsolete */ asmlinkage long compat_sys_old_readdir(unsigned int fd, struct compat_old_linux_dirent __user *, unsigned int count); /* obsolete */ asmlinkage long compat_sys_old_select(struct compat_sel_arg_struct __user *arg); /* obsolete */ asmlinkage long compat_sys_ipc(u32, int, int, u32, compat_uptr_t, u32); /* obsolete */ #ifdef __ARCH_WANT_SYS_SIGPENDING asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set); #endif #ifdef __ARCH_WANT_SYS_SIGPROCMASK asmlinkage long compat_sys_sigprocmask(int how, compat_old_sigset_t __user *nset, compat_old_sigset_t __user *oset); #endif #ifdef CONFIG_COMPAT_OLD_SIGACTION asmlinkage long compat_sys_sigaction(int sig, const struct compat_old_sigaction __user *act, struct compat_old_sigaction __user *oact); #endif /* obsolete */ asmlinkage long compat_sys_socketcall(int call, u32 __user *args); #ifdef __ARCH_WANT_COMPAT_TRUNCATE64 asmlinkage long compat_sys_truncate64(const char __user *pathname, compat_arg_u64(len)); #endif #ifdef __ARCH_WANT_COMPAT_FTRUNCATE64 asmlinkage long compat_sys_ftruncate64(unsigned int fd, compat_arg_u64(len)); #endif #ifdef __ARCH_WANT_COMPAT_FALLOCATE asmlinkage long compat_sys_fallocate(int fd, int mode, compat_arg_u64(offset), compat_arg_u64(len)); #endif #ifdef __ARCH_WANT_COMPAT_PREAD64 asmlinkage long compat_sys_pread64(unsigned int fd, char __user *buf, size_t count, compat_arg_u64(pos)); #endif #ifdef __ARCH_WANT_COMPAT_PWRITE64 asmlinkage long compat_sys_pwrite64(unsigned int fd, const char __user *buf, size_t count, compat_arg_u64(pos)); #endif #ifdef __ARCH_WANT_COMPAT_SYNC_FILE_RANGE asmlinkage long compat_sys_sync_file_range(int fd, compat_arg_u64(pos), compat_arg_u64(nbytes), unsigned int flags); #endif #ifdef __ARCH_WANT_COMPAT_FADVISE64_64 asmlinkage long compat_sys_fadvise64_64(int fd, compat_arg_u64(pos), compat_arg_u64(len), int advice); #endif #ifdef __ARCH_WANT_COMPAT_READAHEAD asmlinkage long compat_sys_readahead(int fd, compat_arg_u64(offset), size_t count); #endif #endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ /** * ns_to_old_timeval32 - Compat version of ns_to_timeval * @nsec: the nanoseconds value to be converted * * Returns the old_timeval32 representation of the nsec parameter. */ static inline struct old_timeval32 ns_to_old_timeval32(s64 nsec) { struct __kernel_old_timeval tv; struct old_timeval32 ctv; tv = ns_to_kernel_old_timeval(nsec); ctv.tv_sec = tv.tv_sec; ctv.tv_usec = tv.tv_usec; return ctv; } /* * Kernel code should not call compat syscalls (i.e., compat_sys_xyzyyz()) * directly. Instead, use one of the functions which work equivalently, such * as the kcompat_sys_xyzyyz() functions prototyped below. */ int kcompat_sys_statfs64(const char __user * pathname, compat_size_t sz, struct compat_statfs64 __user * buf); int kcompat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user * buf); #ifdef CONFIG_COMPAT /* * For most but not all architectures, "am I in a compat syscall?" and * "am I a compat task?" are the same question. For architectures on which * they aren't the same question, arch code can override in_compat_syscall. */ #ifndef in_compat_syscall static inline bool in_compat_syscall(void) { return is_compat_task(); } #endif #else /* !CONFIG_COMPAT */ #define is_compat_task() (0) /* Ensure no one redefines in_compat_syscall() under !CONFIG_COMPAT */ #define in_compat_syscall in_compat_syscall static inline bool in_compat_syscall(void) { return false; } #endif /* CONFIG_COMPAT */ #define BITS_PER_COMPAT_LONG (8*sizeof(compat_long_t)) #define BITS_TO_COMPAT_LONGS(bits) DIV_ROUND_UP(bits, BITS_PER_COMPAT_LONG) long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask, unsigned long bitmap_size); long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask, unsigned long bitmap_size); /* * Some legacy ABIs like the i386 one use less than natural alignment for 64-bit * types, and will need special compat treatment for that. Most architectures * don't need that special handling even for compat syscalls. */ #ifndef compat_need_64bit_alignment_fixup #define compat_need_64bit_alignment_fixup() false #endif /* * A pointer passed in from user mode. This should not * be used for syscall parameters, just declare them * as pointers because the syscall entry code will have * appropriately converted them already. */ #ifndef compat_ptr static inline void __user *compat_ptr(compat_uptr_t uptr) { return (void __user *)(unsigned long)uptr; } #endif static inline compat_uptr_t ptr_to_compat(void __user *uptr) { return (u32)(unsigned long)uptr; } #endif /* _LINUX_COMPAT_H */ |
| 4 4 4 4 4 3 3 8 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* XDP user-space ring structure * Copyright(c) 2018 Intel Corporation. */ #ifndef _LINUX_XSK_QUEUE_H #define _LINUX_XSK_QUEUE_H #include <linux/types.h> #include <linux/if_xdp.h> #include <net/xdp_sock.h> #include <net/xsk_buff_pool.h> #include "xsk.h" struct xdp_ring { u32 producer ____cacheline_aligned_in_smp; /* Hinder the adjacent cache prefetcher to prefetch the consumer * pointer if the producer pointer is touched and vice versa. */ u32 pad1 ____cacheline_aligned_in_smp; u32 consumer ____cacheline_aligned_in_smp; u32 pad2 ____cacheline_aligned_in_smp; u32 flags; u32 pad3 ____cacheline_aligned_in_smp; }; /* Used for the RX and TX queues for packets */ struct xdp_rxtx_ring { struct xdp_ring ptrs; struct xdp_desc desc[] ____cacheline_aligned_in_smp; }; /* Used for the fill and completion queues for buffers */ struct xdp_umem_ring { struct xdp_ring ptrs; u64 desc[] ____cacheline_aligned_in_smp; }; struct xsk_queue { u32 ring_mask; u32 nentries; u32 cached_prod; u32 cached_cons; struct xdp_ring *ring; u64 invalid_descs; u64 queue_empty_descs; size_t ring_vmalloc_size; }; struct parsed_desc { u32 mb; u32 valid; }; /* The structure of the shared state of the rings are a simple * circular buffer, as outlined in * Documentation/core-api/circular-buffers.rst. For the Rx and * completion ring, the kernel is the producer and user space is the * consumer. For the Tx and fill rings, the kernel is the consumer and * user space is the producer. * * producer consumer * * if (LOAD ->consumer) { (A) LOAD.acq ->producer (C) * STORE $data LOAD $data * STORE.rel ->producer (B) STORE.rel ->consumer (D) * } * * (A) pairs with (D), and (B) pairs with (C). * * Starting with (B), it protects the data from being written after * the producer pointer. If this barrier was missing, the consumer * could observe the producer pointer being set and thus load the data * before the producer has written the new data. The consumer would in * this case load the old data. * * (C) protects the consumer from speculatively loading the data before * the producer pointer actually has been read. If we do not have this * barrier, some architectures could load old data as speculative loads * are not discarded as the CPU does not know there is a dependency * between ->producer and data. * * (A) is a control dependency that separates the load of ->consumer * from the stores of $data. In case ->consumer indicates there is no * room in the buffer to store $data we do not. The dependency will * order both of the stores after the loads. So no barrier is needed. * * (D) protects the load of the data to be observed to happen after the * store of the consumer pointer. If we did not have this memory * barrier, the producer could observe the consumer pointer being set * and overwrite the data with a new value before the consumer got the * chance to read the old value. The consumer would thus miss reading * the old entry and very likely read the new entry twice, once right * now and again after circling through the ring. */ /* The operations on the rings are the following: * * producer consumer * * RESERVE entries PEEK in the ring for entries * WRITE data into the ring READ data from the ring * SUBMIT entries RELEASE entries * * The producer reserves one or more entries in the ring. It can then * fill in these entries and finally submit them so that they can be * seen and read by the consumer. * * The consumer peeks into the ring to see if the producer has written * any new entries. If so, the consumer can then read these entries * and when it is done reading them release them back to the producer * so that the producer can use these slots to fill in new entries. * * The function names below reflect these operations. */ /* Functions that read and validate content from consumer rings. */ static inline void __xskq_cons_read_addr_unchecked(struct xsk_queue *q, u32 cached_cons, u64 *addr) { struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; u32 idx = cached_cons & q->ring_mask; *addr = ring->desc[idx]; } static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr) { if (q->cached_cons != q->cached_prod) { __xskq_cons_read_addr_unchecked(q, q->cached_cons, addr); return true; } return false; } static inline bool xp_unused_options_set(u32 options) { return options & ~(XDP_PKT_CONTD | XDP_TX_METADATA); } static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { u64 addr = desc->addr - pool->tx_metadata_len; u64 len = desc->len + pool->tx_metadata_len; u64 offset = addr & (pool->chunk_size - 1); if (!desc->len) return false; if (offset + len > pool->chunk_size) return false; if (addr >= pool->addrs_cnt) return false; if (xp_unused_options_set(desc->options)) return false; return true; } static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { u64 addr = xp_unaligned_add_offset_to_addr(desc->addr) - pool->tx_metadata_len; u64 len = desc->len + pool->tx_metadata_len; if (!desc->len) return false; if (len > pool->chunk_size) return false; if (addr >= pool->addrs_cnt || addr + len > pool->addrs_cnt || xp_desc_crosses_non_contig_pg(pool, addr, len)) return false; if (xp_unused_options_set(desc->options)) return false; return true; } static inline bool xp_validate_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { return pool->unaligned ? xp_unaligned_validate_desc(pool, desc) : xp_aligned_validate_desc(pool, desc); } static inline bool xskq_has_descs(struct xsk_queue *q) { return q->cached_cons != q->cached_prod; } static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d, struct xsk_buff_pool *pool) { if (!xp_validate_desc(pool, d)) { q->invalid_descs++; return false; } return true; } static inline bool xskq_cons_read_desc(struct xsk_queue *q, struct xdp_desc *desc, struct xsk_buff_pool *pool) { if (q->cached_cons != q->cached_prod) { struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; u32 idx = q->cached_cons & q->ring_mask; *desc = ring->desc[idx]; return xskq_cons_is_valid_desc(q, desc, pool); } q->queue_empty_descs++; return false; } static inline void xskq_cons_release_n(struct xsk_queue *q, u32 cnt) { q->cached_cons += cnt; } static inline void parse_desc(struct xsk_queue *q, struct xsk_buff_pool *pool, struct xdp_desc *desc, struct parsed_desc *parsed) { parsed->valid = xskq_cons_is_valid_desc(q, desc, pool); parsed->mb = xp_mb_desc(desc); } static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q, struct xsk_buff_pool *pool, u32 max) { u32 cached_cons = q->cached_cons, nb_entries = 0; struct xdp_desc *descs = pool->tx_descs; u32 total_descs = 0, nr_frags = 0; /* track first entry, if stumble upon *any* invalid descriptor, rewind * current packet that consists of frags and stop the processing */ while (cached_cons != q->cached_prod && nb_entries < max) { struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; u32 idx = cached_cons & q->ring_mask; struct parsed_desc parsed; descs[nb_entries] = ring->desc[idx]; cached_cons++; parse_desc(q, pool, &descs[nb_entries], &parsed); if (unlikely(!parsed.valid)) break; if (likely(!parsed.mb)) { total_descs += (nr_frags + 1); nr_frags = 0; } else { nr_frags++; if (nr_frags == pool->xdp_zc_max_segs) { nr_frags = 0; break; } } nb_entries++; } cached_cons -= nr_frags; /* Release valid plus any invalid entries */ xskq_cons_release_n(q, cached_cons - q->cached_cons); return total_descs; } /* Functions for consumers */ static inline void __xskq_cons_release(struct xsk_queue *q) { smp_store_release(&q->ring->consumer, q->cached_cons); /* D, matchees A */ } static inline void __xskq_cons_peek(struct xsk_queue *q) { /* Refresh the local pointer */ q->cached_prod = smp_load_acquire(&q->ring->producer); /* C, matches B */ } static inline void xskq_cons_get_entries(struct xsk_queue *q) { __xskq_cons_release(q); __xskq_cons_peek(q); } static inline u32 xskq_cons_nb_entries(struct xsk_queue *q, u32 max) { u32 entries = q->cached_prod - q->cached_cons; if (entries >= max) return max; __xskq_cons_peek(q); entries = q->cached_prod - q->cached_cons; return entries >= max ? max : entries; } static inline bool xskq_cons_peek_addr_unchecked(struct xsk_queue *q, u64 *addr) { if (q->cached_prod == q->cached_cons) xskq_cons_get_entries(q); return xskq_cons_read_addr_unchecked(q, addr); } static inline bool xskq_cons_peek_desc(struct xsk_queue *q, struct xdp_desc *desc, struct xsk_buff_pool *pool) { if (q->cached_prod == q->cached_cons) xskq_cons_get_entries(q); return xskq_cons_read_desc(q, desc, pool); } /* To improve performance in the xskq_cons_release functions, only update local state here. * Reflect this to global state when we get new entries from the ring in * xskq_cons_get_entries() and whenever Rx or Tx processing are completed in the NAPI loop. */ static inline void xskq_cons_release(struct xsk_queue *q) { q->cached_cons++; } static inline void xskq_cons_cancel_n(struct xsk_queue *q, u32 cnt) { q->cached_cons -= cnt; } static inline u32 xskq_cons_present_entries(struct xsk_queue *q) { /* No barriers needed since data is not accessed */ return READ_ONCE(q->ring->producer) - READ_ONCE(q->ring->consumer); } /* Functions for producers */ static inline u32 xskq_prod_nb_free(struct xsk_queue *q, u32 max) { u32 free_entries = q->nentries - (q->cached_prod - q->cached_cons); if (free_entries >= max) return max; /* Refresh the local tail pointer */ q->cached_cons = READ_ONCE(q->ring->consumer); free_entries = q->nentries - (q->cached_prod - q->cached_cons); return free_entries >= max ? max : free_entries; } static inline bool xskq_prod_is_full(struct xsk_queue *q) { return xskq_prod_nb_free(q, 1) ? false : true; } static inline void xskq_prod_cancel_n(struct xsk_queue *q, u32 cnt) { q->cached_prod -= cnt; } static inline int xskq_prod_reserve(struct xsk_queue *q) { if (xskq_prod_is_full(q)) return -ENOSPC; /* A, matches D */ q->cached_prod++; return 0; } static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr) { struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; if (xskq_prod_is_full(q)) return -ENOSPC; /* A, matches D */ ring->desc[q->cached_prod++ & q->ring_mask] = addr; return 0; } static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_desc *descs, u32 nb_entries) { struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; u32 i, cached_prod; /* A, matches D */ cached_prod = q->cached_prod; for (i = 0; i < nb_entries; i++) ring->desc[cached_prod++ & q->ring_mask] = descs[i].addr; q->cached_prod = cached_prod; } static inline int xskq_prod_reserve_desc(struct xsk_queue *q, u64 addr, u32 len, u32 flags) { struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; u32 idx; if (xskq_prod_is_full(q)) return -ENOBUFS; /* A, matches D */ idx = q->cached_prod++ & q->ring_mask; ring->desc[idx].addr = addr; ring->desc[idx].len = len; ring->desc[idx].options = flags; return 0; } static inline void __xskq_prod_submit(struct xsk_queue *q, u32 idx) { smp_store_release(&q->ring->producer, idx); /* B, matches C */ } static inline void xskq_prod_submit(struct xsk_queue *q) { __xskq_prod_submit(q, q->cached_prod); } static inline void xskq_prod_submit_n(struct xsk_queue *q, u32 nb_entries) { __xskq_prod_submit(q, q->ring->producer + nb_entries); } static inline bool xskq_prod_is_empty(struct xsk_queue *q) { /* No barriers needed since data is not accessed */ return READ_ONCE(q->ring->consumer) == READ_ONCE(q->ring->producer); } /* For both producers and consumers */ static inline u64 xskq_nb_invalid_descs(struct xsk_queue *q) { return q ? q->invalid_descs : 0; } static inline u64 xskq_nb_queue_empty_descs(struct xsk_queue *q) { return q ? q->queue_empty_descs : 0; } struct xsk_queue *xskq_create(u32 nentries, bool umem_queue); void xskq_destroy(struct xsk_queue *q_ops); #endif /* _LINUX_XSK_QUEUE_H */ |
| 1920 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Dynamic DMA mapping support. * * This implementation is a fallback for platforms that do not support * I/O TLBs (aka DMA address translation hardware). * Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@intel.com> * Copyright (C) 2000 Goutham Rao <goutham.rao@intel.com> * Copyright (C) 2000, 2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> * * 03/05/07 davidm Switch from PCI-DMA to generic device DMA API. * 00/12/13 davidm Rename to swiotlb.c and add mark_clean() to avoid * unnecessary i-cache flushing. * 04/07/.. ak Better overflow handling. Assorted fixes. * 05/09/10 linville Add support for syncing ranges, support syncing for * DMA_BIDIRECTIONAL mappings, miscellaneous cleanup. * 08/12/11 beckyb Add highmem support */ #define pr_fmt(fmt) "software IO TLB: " fmt #include <linux/cache.h> #include <linux/cc_platform.h> #include <linux/ctype.h> #include <linux/debugfs.h> #include <linux/dma-direct.h> #include <linux/dma-map-ops.h> #include <linux/export.h> #include <linux/gfp.h> #include <linux/highmem.h> #include <linux/io.h> #include <linux/iommu-helper.h> #include <linux/init.h> #include <linux/memblock.h> #include <linux/mm.h> #include <linux/pfn.h> #include <linux/rculist.h> #include <linux/scatterlist.h> #include <linux/set_memory.h> #include <linux/spinlock.h> #include <linux/string.h> #include <linux/swiotlb.h> #include <linux/types.h> #ifdef CONFIG_DMA_RESTRICTED_POOL #include <linux/of.h> #include <linux/of_fdt.h> #include <linux/of_reserved_mem.h> #include <linux/slab.h> #endif #define CREATE_TRACE_POINTS #include <trace/events/swiotlb.h> #define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT)) /* * Minimum IO TLB size to bother booting with. Systems with mainly * 64bit capable cards will only lightly use the swiotlb. If we can't * allocate a contiguous 1MB, we're probably in trouble anyway. */ #define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT) #define INVALID_PHYS_ADDR (~(phys_addr_t)0) /** * struct io_tlb_slot - IO TLB slot descriptor * @orig_addr: The original address corresponding to a mapped entry. * @alloc_size: Size of the allocated buffer. * @list: The free list describing the number of free entries available * from each index. * @pad_slots: Number of preceding padding slots. Valid only in the first * allocated non-padding slot. */ struct io_tlb_slot { phys_addr_t orig_addr; size_t alloc_size; unsigned short list; unsigned short pad_slots; }; static bool swiotlb_force_bounce; static bool swiotlb_force_disable; #ifdef CONFIG_SWIOTLB_DYNAMIC static void swiotlb_dyn_alloc(struct work_struct *work); static struct io_tlb_mem io_tlb_default_mem = { .lock = __SPIN_LOCK_UNLOCKED(io_tlb_default_mem.lock), .pools = LIST_HEAD_INIT(io_tlb_default_mem.pools), .dyn_alloc = __WORK_INITIALIZER(io_tlb_default_mem.dyn_alloc, swiotlb_dyn_alloc), }; #else /* !CONFIG_SWIOTLB_DYNAMIC */ static struct io_tlb_mem io_tlb_default_mem; #endif /* CONFIG_SWIOTLB_DYNAMIC */ static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT; static unsigned long default_nareas; /** * struct io_tlb_area - IO TLB memory area descriptor * * This is a single area with a single lock. * * @used: The number of used IO TLB block. * @index: The slot index to start searching in this area for next round. * @lock: The lock to protect the above data structures in the map and * unmap calls. */ struct io_tlb_area { unsigned long used; unsigned int index; spinlock_t lock; }; /* * Round up number of slabs to the next power of 2. The last area is going * be smaller than the rest if default_nslabs is not power of two. * The number of slot in an area should be a multiple of IO_TLB_SEGSIZE, * otherwise a segment may span two or more areas. It conflicts with free * contiguous slots tracking: free slots are treated contiguous no matter * whether they cross an area boundary. * * Return true if default_nslabs is rounded up. */ static bool round_up_default_nslabs(void) { if (!default_nareas) return false; if (default_nslabs < IO_TLB_SEGSIZE * default_nareas) default_nslabs = IO_TLB_SEGSIZE * default_nareas; else if (is_power_of_2(default_nslabs)) return false; default_nslabs = roundup_pow_of_two(default_nslabs); return true; } /** * swiotlb_adjust_nareas() - adjust the number of areas and slots * @nareas: Desired number of areas. Zero is treated as 1. * * Adjust the default number of areas in a memory pool. * The default size of the memory pool may also change to meet minimum area * size requirements. */ static void swiotlb_adjust_nareas(unsigned int nareas) { if (!nareas) nareas = 1; else if (!is_power_of_2(nareas)) nareas = roundup_pow_of_two(nareas); default_nareas = nareas; pr_info("area num %d.\n", nareas); if (round_up_default_nslabs()) pr_info("SWIOTLB bounce buffer size roundup to %luMB", (default_nslabs << IO_TLB_SHIFT) >> 20); } /** * limit_nareas() - get the maximum number of areas for a given memory pool size * @nareas: Desired number of areas. * @nslots: Total number of slots in the memory pool. * * Limit the number of areas to the maximum possible number of areas in * a memory pool of the given size. * * Return: Maximum possible number of areas. */ static unsigned int limit_nareas(unsigned int nareas, unsigned long nslots) { if (nslots < nareas * IO_TLB_SEGSIZE) return nslots / IO_TLB_SEGSIZE; return nareas; } static int __init setup_io_tlb_npages(char *str) { if (isdigit(*str)) { /* avoid tail segment of size < IO_TLB_SEGSIZE */ default_nslabs = ALIGN(simple_strtoul(str, &str, 0), IO_TLB_SEGSIZE); } if (*str == ',') ++str; if (isdigit(*str)) swiotlb_adjust_nareas(simple_strtoul(str, &str, 0)); if (*str == ',') ++str; if (!strcmp(str, "force")) swiotlb_force_bounce = true; else if (!strcmp(str, "noforce")) swiotlb_force_disable = true; return 0; } early_param("swiotlb", setup_io_tlb_npages); unsigned long swiotlb_size_or_default(void) { return default_nslabs << IO_TLB_SHIFT; } void __init swiotlb_adjust_size(unsigned long size) { /* * If swiotlb parameter has not been specified, give a chance to * architectures such as those supporting memory encryption to * adjust/expand SWIOTLB size for their use. */ if (default_nslabs != IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT) return; size = ALIGN(size, IO_TLB_SIZE); default_nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE); if (round_up_default_nslabs()) size = default_nslabs << IO_TLB_SHIFT; pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20); } void swiotlb_print_info(void) { struct io_tlb_pool *mem = &io_tlb_default_mem.defpool; if (!mem->nslabs) { pr_warn("No low mem\n"); return; } pr_info("mapped [mem %pa-%pa] (%luMB)\n", &mem->start, &mem->end, (mem->nslabs << IO_TLB_SHIFT) >> 20); } static inline unsigned long io_tlb_offset(unsigned long val) { return val & (IO_TLB_SEGSIZE - 1); } static inline unsigned long nr_slots(u64 val) { return DIV_ROUND_UP(val, IO_TLB_SIZE); } /* * Early SWIOTLB allocation may be too early to allow an architecture to * perform the desired operations. This function allows the architecture to * call SWIOTLB when the operations are possible. It needs to be called * before the SWIOTLB memory is used. */ void __init swiotlb_update_mem_attributes(void) { struct io_tlb_pool *mem = &io_tlb_default_mem.defpool; unsigned long bytes; if (!mem->nslabs || mem->late_alloc) return; bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT); set_memory_decrypted((unsigned long)mem->vaddr, bytes >> PAGE_SHIFT); } static void swiotlb_init_io_tlb_pool(struct io_tlb_pool *mem, phys_addr_t start, unsigned long nslabs, bool late_alloc, unsigned int nareas) { void *vaddr = phys_to_virt(start); unsigned long bytes = nslabs << IO_TLB_SHIFT, i; mem->nslabs = nslabs; mem->start = start; mem->end = mem->start + bytes; mem->late_alloc = late_alloc; mem->nareas = nareas; mem->area_nslabs = nslabs / mem->nareas; for (i = 0; i < mem->nareas; i++) { spin_lock_init(&mem->areas[i].lock); mem->areas[i].index = 0; mem->areas[i].used = 0; } for (i = 0; i < mem->nslabs; i++) { mem->slots[i].list = min(IO_TLB_SEGSIZE - io_tlb_offset(i), mem->nslabs - i); mem->slots[i].orig_addr = INVALID_PHYS_ADDR; mem->slots[i].alloc_size = 0; mem->slots[i].pad_slots = 0; } memset(vaddr, 0, bytes); mem->vaddr = vaddr; return; } /** * add_mem_pool() - add a memory pool to the allocator * @mem: Software IO TLB allocator. * @pool: Memory pool to be added. */ static void add_mem_pool(struct io_tlb_mem *mem, struct io_tlb_pool *pool) { #ifdef CONFIG_SWIOTLB_DYNAMIC spin_lock(&mem->lock); list_add_rcu(&pool->node, &mem->pools); mem->nslabs += pool->nslabs; spin_unlock(&mem->lock); #else mem->nslabs = pool->nslabs; #endif } static void __init *swiotlb_memblock_alloc(unsigned long nslabs, unsigned int flags, int (*remap)(void *tlb, unsigned long nslabs)) { size_t bytes = PAGE_ALIGN(nslabs << IO_TLB_SHIFT); void *tlb; /* * By default allocate the bounce buffer memory from low memory, but * allow to pick a location everywhere for hypervisors with guest * memory encryption. */ if (flags & SWIOTLB_ANY) tlb = memblock_alloc(bytes, PAGE_SIZE); else tlb = memblock_alloc_low(bytes, PAGE_SIZE); if (!tlb) { pr_warn("%s: Failed to allocate %zu bytes tlb structure\n", __func__, bytes); return NULL; } if (remap && remap(tlb, nslabs) < 0) { memblock_free(tlb, PAGE_ALIGN(bytes)); pr_warn("%s: Failed to remap %zu bytes\n", __func__, bytes); return NULL; } return tlb; } /* * Statically reserve bounce buffer space and initialize bounce buffer data * structures for the software IO TLB used to implement the DMA API. */ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags, int (*remap)(void *tlb, unsigned long nslabs)) { struct io_tlb_pool *mem = &io_tlb_default_mem.defpool; unsigned long nslabs; unsigned int nareas; size_t alloc_size; void *tlb; if (!addressing_limit && !swiotlb_force_bounce) return; if (swiotlb_force_disable) return; io_tlb_default_mem.force_bounce = swiotlb_force_bounce || (flags & SWIOTLB_FORCE); #ifdef CONFIG_SWIOTLB_DYNAMIC if (!remap) io_tlb_default_mem.can_grow = true; if (flags & SWIOTLB_ANY) io_tlb_default_mem.phys_limit = virt_to_phys(high_memory - 1); else io_tlb_default_mem.phys_limit = ARCH_LOW_ADDRESS_LIMIT; #endif if (!default_nareas) swiotlb_adjust_nareas(num_possible_cpus()); nslabs = default_nslabs; nareas = limit_nareas(default_nareas, nslabs); while ((tlb = swiotlb_memblock_alloc(nslabs, flags, remap)) == NULL) { if (nslabs <= IO_TLB_MIN_SLABS) return; nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE); nareas = limit_nareas(nareas, nslabs); } if (default_nslabs != nslabs) { pr_info("SWIOTLB bounce buffer size adjusted %lu -> %lu slabs", default_nslabs, nslabs); default_nslabs = nslabs; } alloc_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), nslabs)); mem->slots = memblock_alloc(alloc_size, PAGE_SIZE); if (!mem->slots) { pr_warn("%s: Failed to allocate %zu bytes align=0x%lx\n", __func__, alloc_size, PAGE_SIZE); return; } mem->areas = memblock_alloc(array_size(sizeof(struct io_tlb_area), nareas), SMP_CACHE_BYTES); if (!mem->areas) { pr_warn("%s: Failed to allocate mem->areas.\n", __func__); return; } swiotlb_init_io_tlb_pool(mem, __pa(tlb), nslabs, false, nareas); add_mem_pool(&io_tlb_default_mem, mem); if (flags & SWIOTLB_VERBOSE) swiotlb_print_info(); } void __init swiotlb_init(bool addressing_limit, unsigned int flags) { swiotlb_init_remap(addressing_limit, flags, NULL); } /* * Systems with larger DMA zones (those that don't support ISA) can * initialize the swiotlb later using the slab allocator if needed. * This should be just like above, but with some error catching. */ int swiotlb_init_late(size_t size, gfp_t gfp_mask, int (*remap)(void *tlb, unsigned long nslabs)) { struct io_tlb_pool *mem = &io_tlb_default_mem.defpool; unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE); unsigned int nareas; unsigned char *vstart = NULL; unsigned int order, area_order; bool retried = false; int rc = 0; if (io_tlb_default_mem.nslabs) return 0; if (swiotlb_force_disable) return 0; io_tlb_default_mem.force_bounce = swiotlb_force_bounce; #ifdef CONFIG_SWIOTLB_DYNAMIC if (!remap) io_tlb_default_mem.can_grow = true; if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp_mask & __GFP_DMA)) io_tlb_default_mem.phys_limit = zone_dma_limit; else if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp_mask & __GFP_DMA32)) io_tlb_default_mem.phys_limit = max(DMA_BIT_MASK(32), zone_dma_limit); else io_tlb_default_mem.phys_limit = virt_to_phys(high_memory - 1); #endif if (!default_nareas) swiotlb_adjust_nareas(num_possible_cpus()); retry: order = get_order(nslabs << IO_TLB_SHIFT); nslabs = SLABS_PER_PAGE << order; while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) { vstart = (void *)__get_free_pages(gfp_mask | __GFP_NOWARN, order); if (vstart) break; order--; nslabs = SLABS_PER_PAGE << order; retried = true; } if (!vstart) return -ENOMEM; if (remap) rc = remap(vstart, nslabs); if (rc) { free_pages((unsigned long)vstart, order); nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE); if (nslabs < IO_TLB_MIN_SLABS) return rc; retried = true; goto retry; } if (retried) { pr_warn("only able to allocate %ld MB\n", (PAGE_SIZE << order) >> 20); } nareas = limit_nareas(default_nareas, nslabs); area_order = get_order(array_size(sizeof(*mem->areas), nareas)); mem->areas = (struct io_tlb_area *) __get_free_pages(GFP_KERNEL | __GFP_ZERO, area_order); if (!mem->areas) goto error_area; mem->slots = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(array_size(sizeof(*mem->slots), nslabs))); if (!mem->slots) goto error_slots; set_memory_decrypted((unsigned long)vstart, (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT); swiotlb_init_io_tlb_pool(mem, virt_to_phys(vstart), nslabs, true, nareas); add_mem_pool(&io_tlb_default_mem, mem); swiotlb_print_info(); return 0; error_slots: free_pages((unsigned long)mem->areas, area_order); error_area: free_pages((unsigned long)vstart, order); return -ENOMEM; } void __init swiotlb_exit(void) { struct io_tlb_pool *mem = &io_tlb_default_mem.defpool; unsigned long tbl_vaddr; size_t tbl_size, slots_size; unsigned int area_order; if (swiotlb_force_bounce) return; if (!mem->nslabs) return; pr_info("tearing down default memory pool\n"); tbl_vaddr = (unsigned long)phys_to_virt(mem->start); tbl_size = PAGE_ALIGN(mem->end - mem->start); slots_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), mem->nslabs)); set_memory_encrypted(tbl_vaddr, tbl_size >> PAGE_SHIFT); if (mem->late_alloc) { area_order = get_order(array_size(sizeof(*mem->areas), mem->nareas)); free_pages((unsigned long)mem->areas, area_order); free_pages(tbl_vaddr, get_order(tbl_size)); free_pages((unsigned long)mem->slots, get_order(slots_size)); } else { memblock_free_late(__pa(mem->areas), array_size(sizeof(*mem->areas), mem->nareas)); memblock_free_late(mem->start, tbl_size); memblock_free_late(__pa(mem->slots), slots_size); } memset(mem, 0, sizeof(*mem)); } #ifdef CONFIG_SWIOTLB_DYNAMIC /** * alloc_dma_pages() - allocate pages to be used for DMA * @gfp: GFP flags for the allocation. * @bytes: Size of the buffer. * @phys_limit: Maximum allowed physical address of the buffer. * * Allocate pages from the buddy allocator. If successful, make the allocated * pages decrypted that they can be used for DMA. * * Return: Decrypted pages, %NULL on allocation failure, or ERR_PTR(-EAGAIN) * if the allocated physical address was above @phys_limit. */ static struct page *alloc_dma_pages(gfp_t gfp, size_t bytes, u64 phys_limit) { unsigned int order = get_order(bytes); struct page *page; phys_addr_t paddr; void *vaddr; page = alloc_pages(gfp, order); if (!page) return NULL; paddr = page_to_phys(page); if (paddr + bytes - 1 > phys_limit) { __free_pages(page, order); return ERR_PTR(-EAGAIN); } vaddr = phys_to_virt(paddr); if (set_memory_decrypted((unsigned long)vaddr, PFN_UP(bytes))) goto error; return page; error: /* Intentional leak if pages cannot be encrypted again. */ if (!set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes))) __free_pages(page, order); return NULL; } /** * swiotlb_alloc_tlb() - allocate a dynamic IO TLB buffer * @dev: Device for which a memory pool is allocated. * @bytes: Size of the buffer. * @phys_limit: Maximum allowed physical address of the buffer. * @gfp: GFP flags for the allocation. * * Return: Allocated pages, or %NULL on allocation failure. */ static struct page *swiotlb_alloc_tlb(struct device *dev, size_t bytes, u64 phys_limit, gfp_t gfp) { struct page *page; /* * Allocate from the atomic pools if memory is encrypted and * the allocation is atomic, because decrypting may block. */ if (!gfpflags_allow_blocking(gfp) && dev && force_dma_unencrypted(dev)) { void *vaddr; if (!IS_ENABLED(CONFIG_DMA_COHERENT_POOL)) return NULL; return dma_alloc_from_pool(dev, bytes, &vaddr, gfp, dma_coherent_ok); } gfp &= ~GFP_ZONEMASK; if (phys_limit <= zone_dma_limit) gfp |= __GFP_DMA; else if (phys_limit <= DMA_BIT_MASK(32)) gfp |= __GFP_DMA32; while (IS_ERR(page = alloc_dma_pages(gfp, bytes, phys_limit))) { if (IS_ENABLED(CONFIG_ZONE_DMA32) && phys_limit < DMA_BIT_MASK(64) && !(gfp & (__GFP_DMA32 | __GFP_DMA))) gfp |= __GFP_DMA32; else if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & __GFP_DMA)) gfp = (gfp & ~__GFP_DMA32) | __GFP_DMA; else return NULL; } return page; } /** * swiotlb_free_tlb() - free a dynamically allocated IO TLB buffer * @vaddr: Virtual address of the buffer. * @bytes: Size of the buffer. */ static void swiotlb_free_tlb(void *vaddr, size_t bytes) { if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) && dma_free_from_pool(NULL, vaddr, bytes)) return; /* Intentional leak if pages cannot be encrypted again. */ if (!set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes))) __free_pages(virt_to_page(vaddr), get_order(bytes)); } /** * swiotlb_alloc_pool() - allocate a new IO TLB memory pool * @dev: Device for which a memory pool is allocated. * @minslabs: Minimum number of slabs. * @nslabs: Desired (maximum) number of slabs. * @nareas: Number of areas. * @phys_limit: Maximum DMA buffer physical address. * @gfp: GFP flags for the allocations. * * Allocate and initialize a new IO TLB memory pool. The actual number of * slabs may be reduced if allocation of @nslabs fails. If even * @minslabs cannot be allocated, this function fails. * * Return: New memory pool, or %NULL on allocation failure. */ static struct io_tlb_pool *swiotlb_alloc_pool(struct device *dev, unsigned long minslabs, unsigned long nslabs, unsigned int nareas, u64 phys_limit, gfp_t gfp) { struct io_tlb_pool *pool; unsigned int slot_order; struct page *tlb; size_t pool_size; size_t tlb_size; if (nslabs > SLABS_PER_PAGE << MAX_PAGE_ORDER) { nslabs = SLABS_PER_PAGE << MAX_PAGE_ORDER; nareas = limit_nareas(nareas, nslabs); } pool_size = sizeof(*pool) + array_size(sizeof(*pool->areas), nareas); pool = kzalloc(pool_size, gfp); if (!pool) goto error; pool->areas = (void *)pool + sizeof(*pool); tlb_size = nslabs << IO_TLB_SHIFT; while (!(tlb = swiotlb_alloc_tlb(dev, tlb_size, phys_limit, gfp))) { if (nslabs <= minslabs) goto error_tlb; nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE); nareas = limit_nareas(nareas, nslabs); tlb_size = nslabs << IO_TLB_SHIFT; } slot_order = get_order(array_size(sizeof(*pool->slots), nslabs)); pool->slots = (struct io_tlb_slot *) __get_free_pages(gfp, slot_order); if (!pool->slots) goto error_slots; swiotlb_init_io_tlb_pool(pool, page_to_phys(tlb), nslabs, true, nareas); return pool; error_slots: swiotlb_free_tlb(page_address(tlb), tlb_size); error_tlb: kfree(pool); error: return NULL; } /** * swiotlb_dyn_alloc() - dynamic memory pool allocation worker * @work: Pointer to dyn_alloc in struct io_tlb_mem. */ static void swiotlb_dyn_alloc(struct work_struct *work) { struct io_tlb_mem *mem = container_of(work, struct io_tlb_mem, dyn_alloc); struct io_tlb_pool *pool; pool = swiotlb_alloc_pool(NULL, IO_TLB_MIN_SLABS, default_nslabs, default_nareas, mem->phys_limit, GFP_KERNEL); if (!pool) { pr_warn_ratelimited("Failed to allocate new pool"); return; } add_mem_pool(mem, pool); } /** * swiotlb_dyn_free() - RCU callback to free a memory pool * @rcu: RCU head in the corresponding struct io_tlb_pool. */ static void swiotlb_dyn_free(struct rcu_head *rcu) { struct io_tlb_pool *pool = container_of(rcu, struct io_tlb_pool, rcu); size_t slots_size = array_size(sizeof(*pool->slots), pool->nslabs); size_t tlb_size = pool->end - pool->start; free_pages((unsigned long)pool->slots, get_order(slots_size)); swiotlb_free_tlb(pool->vaddr, tlb_size); kfree(pool); } /** * __swiotlb_find_pool() - find the IO TLB pool for a physical address * @dev: Device which has mapped the DMA buffer. * @paddr: Physical address within the DMA buffer. * * Find the IO TLB memory pool descriptor which contains the given physical * address, if any. This function is for use only when the dev is known to * be using swiotlb. Use swiotlb_find_pool() for the more general case * when this condition is not met. * * Return: Memory pool which contains @paddr, or %NULL if none. */ struct io_tlb_pool *__swiotlb_find_pool(struct device *dev, phys_addr_t paddr) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; struct io_tlb_pool *pool; rcu_read_lock(); list_for_each_entry_rcu(pool, &mem->pools, node) { if (paddr >= pool->start && paddr < pool->end) goto out; } list_for_each_entry_rcu(pool, &dev->dma_io_tlb_pools, node) { if (paddr >= pool->start && paddr < pool->end) goto out; } pool = NULL; out: rcu_read_unlock(); return pool; } /** * swiotlb_del_pool() - remove an IO TLB pool from a device * @dev: Owning device. * @pool: Memory pool to be removed. */ static void swiotlb_del_pool(struct device *dev, struct io_tlb_pool *pool) { unsigned long flags; spin_lock_irqsave(&dev->dma_io_tlb_lock, flags); list_del_rcu(&pool->node); spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags); call_rcu(&pool->rcu, swiotlb_dyn_free); } #endif /* CONFIG_SWIOTLB_DYNAMIC */ /** * swiotlb_dev_init() - initialize swiotlb fields in &struct device * @dev: Device to be initialized. */ void swiotlb_dev_init(struct device *dev) { dev->dma_io_tlb_mem = &io_tlb_default_mem; #ifdef CONFIG_SWIOTLB_DYNAMIC INIT_LIST_HEAD(&dev->dma_io_tlb_pools); spin_lock_init(&dev->dma_io_tlb_lock); dev->dma_uses_io_tlb = false; #endif } /** * swiotlb_align_offset() - Get required offset into an IO TLB allocation. * @dev: Owning device. * @align_mask: Allocation alignment mask. * @addr: DMA address. * * Return the minimum offset from the start of an IO TLB allocation which is * required for a given buffer address and allocation alignment to keep the * device happy. * * First, the address bits covered by min_align_mask must be identical in the * original address and the bounce buffer address. High bits are preserved by * choosing a suitable IO TLB slot, but bits below IO_TLB_SHIFT require extra * padding bytes before the bounce buffer. * * Second, @align_mask specifies which bits of the first allocated slot must * be zero. This may require allocating additional padding slots, and then the * offset (in bytes) from the first such padding slot is returned. */ static unsigned int swiotlb_align_offset(struct device *dev, unsigned int align_mask, u64 addr) { return addr & dma_get_min_align_mask(dev) & (align_mask | (IO_TLB_SIZE - 1)); } /* * Bounce: copy the swiotlb buffer from or back to the original dma location */ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size, enum dma_data_direction dir, struct io_tlb_pool *mem) { int index = (tlb_addr - mem->start) >> IO_TLB_SHIFT; phys_addr_t orig_addr = mem->slots[index].orig_addr; size_t alloc_size = mem->slots[index].alloc_size; unsigned long pfn = PFN_DOWN(orig_addr); unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start; int tlb_offset; if (orig_addr == INVALID_PHYS_ADDR) return; /* * It's valid for tlb_offset to be negative. This can happen when the * "offset" returned by swiotlb_align_offset() is non-zero, and the * tlb_addr is pointing within the first "offset" bytes of the second * or subsequent slots of the allocated swiotlb area. While it's not * valid for tlb_addr to be pointing within the first "offset" bytes * of the first slot, there's no way to check for such an error since * this function can't distinguish the first slot from the second and * subsequent slots. */ tlb_offset = (tlb_addr & (IO_TLB_SIZE - 1)) - swiotlb_align_offset(dev, 0, orig_addr); orig_addr += tlb_offset; alloc_size -= tlb_offset; if (size > alloc_size) { dev_WARN_ONCE(dev, 1, "Buffer overflow detected. Allocation size: %zu. Mapping size: %zu.\n", alloc_size, size); size = alloc_size; } if (PageHighMem(pfn_to_page(pfn))) { unsigned int offset = orig_addr & ~PAGE_MASK; struct page *page; unsigned int sz = 0; unsigned long flags; while (size) { sz = min_t(size_t, PAGE_SIZE - offset, size); local_irq_save(flags); page = pfn_to_page(pfn); if (dir == DMA_TO_DEVICE) memcpy_from_page(vaddr, page, offset, sz); else memcpy_to_page(page, offset, vaddr, sz); local_irq_restore(flags); size -= sz; pfn++; vaddr += sz; offset = 0; } } else if (dir == DMA_TO_DEVICE) { memcpy(vaddr, phys_to_virt(orig_addr), size); } else { memcpy(phys_to_virt(orig_addr), vaddr, size); } } static inline phys_addr_t slot_addr(phys_addr_t start, phys_addr_t idx) { return start + (idx << IO_TLB_SHIFT); } /* * Carefully handle integer overflow which can occur when boundary_mask == ~0UL. */ static inline unsigned long get_max_slots(unsigned long boundary_mask) { return (boundary_mask >> IO_TLB_SHIFT) + 1; } static unsigned int wrap_area_index(struct io_tlb_pool *mem, unsigned int index) { if (index >= mem->area_nslabs) return 0; return index; } /* * Track the total used slots with a global atomic value in order to have * correct information to determine the high water mark. The mem_used() * function gives imprecise results because there's no locking across * multiple areas. */ #ifdef CONFIG_DEBUG_FS static void inc_used_and_hiwater(struct io_tlb_mem *mem, unsigned int nslots) { unsigned long old_hiwater, new_used; new_used = atomic_long_add_return(nslots, &mem->total_used); old_hiwater = atomic_long_read(&mem->used_hiwater); do { if (new_used <= old_hiwater) break; } while (!atomic_long_try_cmpxchg(&mem->used_hiwater, &old_hiwater, new_used)); } static void dec_used(struct io_tlb_mem *mem, unsigned int nslots) { atomic_long_sub(nslots, &mem->total_used); } #else /* !CONFIG_DEBUG_FS */ static void inc_used_and_hiwater(struct io_tlb_mem *mem, unsigned int nslots) { } static void dec_used(struct io_tlb_mem *mem, unsigned int nslots) { } #endif /* CONFIG_DEBUG_FS */ #ifdef CONFIG_SWIOTLB_DYNAMIC #ifdef CONFIG_DEBUG_FS static void inc_transient_used(struct io_tlb_mem *mem, unsigned int nslots) { atomic_long_add(nslots, &mem->transient_nslabs); } static void dec_transient_used(struct io_tlb_mem *mem, unsigned int nslots) { atomic_long_sub(nslots, &mem->transient_nslabs); } #else /* !CONFIG_DEBUG_FS */ static void inc_transient_used(struct io_tlb_mem *mem, unsigned int nslots) { } static void dec_transient_used(struct io_tlb_mem *mem, unsigned int nslots) { } #endif /* CONFIG_DEBUG_FS */ #endif /* CONFIG_SWIOTLB_DYNAMIC */ /** * swiotlb_search_pool_area() - search one memory area in one pool * @dev: Device which maps the buffer. * @pool: Memory pool to be searched. * @area_index: Index of the IO TLB memory area to be searched. * @orig_addr: Original (non-bounced) IO buffer address. * @alloc_size: Total requested size of the bounce buffer, * including initial alignment padding. * @alloc_align_mask: Required alignment of the allocated buffer. * * Find a suitable sequence of IO TLB entries for the request and allocate * a buffer from the given IO TLB memory area. * This function takes care of locking. * * Return: Index of the first allocated slot, or -1 on error. */ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool, int area_index, phys_addr_t orig_addr, size_t alloc_size, unsigned int alloc_align_mask) { struct io_tlb_area *area = pool->areas + area_index; unsigned long boundary_mask = dma_get_seg_boundary(dev); dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(dev, pool->start) & boundary_mask; unsigned long max_slots = get_max_slots(boundary_mask); unsigned int iotlb_align_mask = dma_get_min_align_mask(dev); unsigned int nslots = nr_slots(alloc_size), stride; unsigned int offset = swiotlb_align_offset(dev, 0, orig_addr); unsigned int index, slots_checked, count = 0, i; unsigned long flags; unsigned int slot_base; unsigned int slot_index; BUG_ON(!nslots); BUG_ON(area_index >= pool->nareas); /* * Historically, swiotlb allocations >= PAGE_SIZE were guaranteed to be * page-aligned in the absence of any other alignment requirements. * 'alloc_align_mask' was later introduced to specify the alignment * explicitly, however this is passed as zero for streaming mappings * and so we preserve the old behaviour there in case any drivers are * relying on it. */ if (!alloc_align_mask && !iotlb_align_mask && alloc_size >= PAGE_SIZE) alloc_align_mask = PAGE_SIZE - 1; /* * Ensure that the allocation is at least slot-aligned and update * 'iotlb_align_mask' to ignore bits that will be preserved when * offsetting into the allocation. */ alloc_align_mask |= (IO_TLB_SIZE - 1); iotlb_align_mask &= ~alloc_align_mask; /* * For mappings with an alignment requirement don't bother looping to * unaligned slots once we found an aligned one. */ stride = get_max_slots(max(alloc_align_mask, iotlb_align_mask)); spin_lock_irqsave(&area->lock, flags); if (unlikely(nslots > pool->area_nslabs - area->used)) goto not_found; slot_base = area_index * pool->area_nslabs; index = area->index; for (slots_checked = 0; slots_checked < pool->area_nslabs; ) { phys_addr_t tlb_addr; slot_index = slot_base + index; tlb_addr = slot_addr(tbl_dma_addr, slot_index); if ((tlb_addr & alloc_align_mask) || (orig_addr && (tlb_addr & iotlb_align_mask) != (orig_addr & iotlb_align_mask))) { index = wrap_area_index(pool, index + 1); slots_checked++; continue; } if (!iommu_is_span_boundary(slot_index, nslots, nr_slots(tbl_dma_addr), max_slots)) { if (pool->slots[slot_index].list >= nslots) goto found; } index = wrap_area_index(pool, index + stride); slots_checked += stride; } not_found: spin_unlock_irqrestore(&area->lock, flags); return -1; found: /* * If we find a slot that indicates we have 'nslots' number of * contiguous buffers, we allocate the buffers from that slot onwards * and set the list of free entries to '0' indicating unavailable. */ for (i = slot_index; i < slot_index + nslots; i++) { pool->slots[i].list = 0; pool->slots[i].alloc_size = alloc_size - (offset + ((i - slot_index) << IO_TLB_SHIFT)); } for (i = slot_index - 1; io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && pool->slots[i].list; i--) pool->slots[i].list = ++count; /* * Update the indices to avoid searching in the next round. */ area->index = wrap_area_index(pool, index + nslots); area->used += nslots; spin_unlock_irqrestore(&area->lock, flags); inc_used_and_hiwater(dev->dma_io_tlb_mem, nslots); return slot_index; } #ifdef CONFIG_SWIOTLB_DYNAMIC /** * swiotlb_search_area() - search one memory area in all pools * @dev: Device which maps the buffer. * @start_cpu: Start CPU number. * @cpu_offset: Offset from @start_cpu. * @orig_addr: Original (non-bounced) IO buffer address. * @alloc_size: Total requested size of the bounce buffer, * including initial alignment padding. * @alloc_align_mask: Required alignment of the allocated buffer. * @retpool: Used memory pool, updated on return. * * Search one memory area in all pools for a sequence of slots that match the * allocation constraints. * * Return: Index of the first allocated slot, or -1 on error. */ static int swiotlb_search_area(struct device *dev, int start_cpu, int cpu_offset, phys_addr_t orig_addr, size_t alloc_size, unsigned int alloc_align_mask, struct io_tlb_pool **retpool) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; struct io_tlb_pool *pool; int area_index; int index = -1; rcu_read_lock(); list_for_each_entry_rcu(pool, &mem->pools, node) { if (cpu_offset >= pool->nareas) continue; area_index = (start_cpu + cpu_offset) & (pool->nareas - 1); index = swiotlb_search_pool_area(dev, pool, area_index, orig_addr, alloc_size, alloc_align_mask); if (index >= 0) { *retpool = pool; break; } } rcu_read_unlock(); return index; } /** * swiotlb_find_slots() - search for slots in the whole swiotlb * @dev: Device which maps the buffer. * @orig_addr: Original (non-bounced) IO buffer address. * @alloc_size: Total requested size of the bounce buffer, * including initial alignment padding. * @alloc_align_mask: Required alignment of the allocated buffer. * @retpool: Used memory pool, updated on return. * * Search through the whole software IO TLB to find a sequence of slots that * match the allocation constraints. * * Return: Index of the first allocated slot, or -1 on error. */ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, size_t alloc_size, unsigned int alloc_align_mask, struct io_tlb_pool **retpool) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; struct io_tlb_pool *pool; unsigned long nslabs; unsigned long flags; u64 phys_limit; int cpu, i; int index; if (alloc_size > IO_TLB_SEGSIZE * IO_TLB_SIZE) return -1; cpu = raw_smp_processor_id(); for (i = 0; i < default_nareas; ++i) { index = swiotlb_search_area(dev, cpu, i, orig_addr, alloc_size, alloc_align_mask, &pool); if (index >= 0) goto found; } if (!mem->can_grow) return -1; schedule_work(&mem->dyn_alloc); nslabs = nr_slots(alloc_size); phys_limit = min_not_zero(*dev->dma_mask, dev->bus_dma_limit); pool = swiotlb_alloc_pool(dev, nslabs, nslabs, 1, phys_limit, GFP_NOWAIT | __GFP_NOWARN); if (!pool) return -1; index = swiotlb_search_pool_area(dev, pool, 0, orig_addr, alloc_size, alloc_align_mask); if (index < 0) { swiotlb_dyn_free(&pool->rcu); return -1; } pool->transient = true; spin_lock_irqsave(&dev->dma_io_tlb_lock, flags); list_add_rcu(&pool->node, &dev->dma_io_tlb_pools); spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags); inc_transient_used(mem, pool->nslabs); found: WRITE_ONCE(dev->dma_uses_io_tlb, true); /* * The general barrier orders reads and writes against a presumed store * of the SWIOTLB buffer address by a device driver (to a driver private * data structure). It serves two purposes. * * First, the store to dev->dma_uses_io_tlb must be ordered before the * presumed store. This guarantees that the returned buffer address * cannot be passed to another CPU before updating dev->dma_uses_io_tlb. * * Second, the load from mem->pools must be ordered before the same * presumed store. This guarantees that the returned buffer address * cannot be observed by another CPU before an update of the RCU list * that was made by swiotlb_dyn_alloc() on a third CPU (cf. multicopy * atomicity). * * See also the comment in swiotlb_find_pool(). */ smp_mb(); *retpool = pool; return index; } #else /* !CONFIG_SWIOTLB_DYNAMIC */ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, size_t alloc_size, unsigned int alloc_align_mask, struct io_tlb_pool **retpool) { struct io_tlb_pool *pool; int start, i; int index; *retpool = pool = &dev->dma_io_tlb_mem->defpool; i = start = raw_smp_processor_id() & (pool->nareas - 1); do { index = swiotlb_search_pool_area(dev, pool, i, orig_addr, alloc_size, alloc_align_mask); if (index >= 0) return index; if (++i >= pool->nareas) i = 0; } while (i != start); return -1; } #endif /* CONFIG_SWIOTLB_DYNAMIC */ #ifdef CONFIG_DEBUG_FS /** * mem_used() - get number of used slots in an allocator * @mem: Software IO TLB allocator. * * The result is accurate in this version of the function, because an atomic * counter is available if CONFIG_DEBUG_FS is set. * * Return: Number of used slots. */ static unsigned long mem_used(struct io_tlb_mem *mem) { return atomic_long_read(&mem->total_used); } #else /* !CONFIG_DEBUG_FS */ /** * mem_pool_used() - get number of used slots in a memory pool * @pool: Software IO TLB memory pool. * * The result is not accurate, see mem_used(). * * Return: Approximate number of used slots. */ static unsigned long mem_pool_used(struct io_tlb_pool *pool) { int i; unsigned long used = 0; for (i = 0; i < pool->nareas; i++) used += pool->areas[i].used; return used; } /** * mem_used() - get number of used slots in an allocator * @mem: Software IO TLB allocator. * * The result is not accurate, because there is no locking of individual * areas. * * Return: Approximate number of used slots. */ static unsigned long mem_used(struct io_tlb_mem *mem) { #ifdef CONFIG_SWIOTLB_DYNAMIC struct io_tlb_pool *pool; unsigned long used = 0; rcu_read_lock(); list_for_each_entry_rcu(pool, &mem->pools, node) used += mem_pool_used(pool); rcu_read_unlock(); return used; #else return mem_pool_used(&mem->defpool); #endif } #endif /* CONFIG_DEBUG_FS */ /** * swiotlb_tbl_map_single() - bounce buffer map a single contiguous physical area * @dev: Device which maps the buffer. * @orig_addr: Original (non-bounced) physical IO buffer address * @mapping_size: Requested size of the actual bounce buffer, excluding * any pre- or post-padding for alignment * @alloc_align_mask: Required start and end alignment of the allocated buffer * @dir: DMA direction * @attrs: Optional DMA attributes for the map operation * * Find and allocate a suitable sequence of IO TLB slots for the request. * The allocated space starts at an alignment specified by alloc_align_mask, * and the size of the allocated space is rounded up so that the total amount * of allocated space is a multiple of (alloc_align_mask + 1). If * alloc_align_mask is zero, the allocated space may be at any alignment and * the size is not rounded up. * * The returned address is within the allocated space and matches the bits * of orig_addr that are specified in the DMA min_align_mask for the device. As * such, this returned address may be offset from the beginning of the allocated * space. The bounce buffer space starting at the returned address for * mapping_size bytes is initialized to the contents of the original IO buffer * area. Any pre-padding (due to an offset) and any post-padding (due to * rounding-up the size) is not initialized. */ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, size_t mapping_size, unsigned int alloc_align_mask, enum dma_data_direction dir, unsigned long attrs) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; unsigned int offset; struct io_tlb_pool *pool; unsigned int i; size_t size; int index; phys_addr_t tlb_addr; unsigned short pad_slots; if (!mem || !mem->nslabs) { dev_warn_ratelimited(dev, "Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer"); return (phys_addr_t)DMA_MAPPING_ERROR; } if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n"); /* * The default swiotlb memory pool is allocated with PAGE_SIZE * alignment. If a mapping is requested with larger alignment, * the mapping may be unable to use the initial slot(s) in all * sets of IO_TLB_SEGSIZE slots. In such case, a mapping request * of or near the maximum mapping size would always fail. */ dev_WARN_ONCE(dev, alloc_align_mask > ~PAGE_MASK, "Alloc alignment may prevent fulfilling requests with max mapping_size\n"); offset = swiotlb_align_offset(dev, alloc_align_mask, orig_addr); size = ALIGN(mapping_size + offset, alloc_align_mask + 1); index = swiotlb_find_slots(dev, orig_addr, size, alloc_align_mask, &pool); if (index == -1) { if (!(attrs & DMA_ATTR_NO_WARN)) dev_warn_ratelimited(dev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n", size, mem->nslabs, mem_used(mem)); return (phys_addr_t)DMA_MAPPING_ERROR; } /* * If dma_skip_sync was set, reset it on first SWIOTLB buffer * mapping to always sync SWIOTLB buffers. */ dma_reset_need_sync(dev); /* * Save away the mapping from the original address to the DMA address. * This is needed when we sync the memory. Then we sync the buffer if * needed. */ pad_slots = offset >> IO_TLB_SHIFT; offset &= (IO_TLB_SIZE - 1); index += pad_slots; pool->slots[index].pad_slots = pad_slots; for (i = 0; i < (nr_slots(size) - pad_slots); i++) pool->slots[index + i].orig_addr = slot_addr(orig_addr, i); tlb_addr = slot_addr(pool->start, index) + offset; /* * When the device is writing memory, i.e. dir == DMA_FROM_DEVICE, copy * the original buffer to the TLB buffer before initiating DMA in order * to preserve the original's data if the device does a partial write, * i.e. if the device doesn't overwrite the entire buffer. Preserving * the original data, even if it's garbage, is necessary to match * hardware behavior. Use of swiotlb is supposed to be transparent, * i.e. swiotlb must not corrupt memory by clobbering unwritten bytes. */ swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE, pool); return tlb_addr; } static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr, struct io_tlb_pool *mem) { unsigned long flags; unsigned int offset = swiotlb_align_offset(dev, 0, tlb_addr); int index, nslots, aindex; struct io_tlb_area *area; int count, i; index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT; index -= mem->slots[index].pad_slots; nslots = nr_slots(mem->slots[index].alloc_size + offset); aindex = index / mem->area_nslabs; area = &mem->areas[aindex]; /* * Return the buffer to the free list by setting the corresponding * entries to indicate the number of contiguous entries available. * While returning the entries to the free list, we merge the entries * with slots below and above the pool being returned. */ BUG_ON(aindex >= mem->nareas); spin_lock_irqsave(&area->lock, flags); if (index + nslots < ALIGN(index + 1, IO_TLB_SEGSIZE)) count = mem->slots[index + nslots].list; else count = 0; /* * Step 1: return the slots to the free list, merging the slots with * superceeding slots */ for (i = index + nslots - 1; i >= index; i--) { mem->slots[i].list = ++count; mem->slots[i].orig_addr = INVALID_PHYS_ADDR; mem->slots[i].alloc_size = 0; mem->slots[i].pad_slots = 0; } /* * Step 2: merge the returned slots with the preceding slots, if * available (non zero) */ for (i = index - 1; io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && mem->slots[i].list; i--) mem->slots[i].list = ++count; area->used -= nslots; spin_unlock_irqrestore(&area->lock, flags); dec_used(dev->dma_io_tlb_mem, nslots); } #ifdef CONFIG_SWIOTLB_DYNAMIC /** * swiotlb_del_transient() - delete a transient memory pool * @dev: Device which mapped the buffer. * @tlb_addr: Physical address within a bounce buffer. * @pool: Pointer to the transient memory pool to be checked and deleted. * * Check whether the address belongs to a transient SWIOTLB memory pool. * If yes, then delete the pool. * * Return: %true if @tlb_addr belonged to a transient pool that was released. */ static bool swiotlb_del_transient(struct device *dev, phys_addr_t tlb_addr, struct io_tlb_pool *pool) { if (!pool->transient) return false; dec_used(dev->dma_io_tlb_mem, pool->nslabs); swiotlb_del_pool(dev, pool); dec_transient_used(dev->dma_io_tlb_mem, pool->nslabs); return true; } #else /* !CONFIG_SWIOTLB_DYNAMIC */ static inline bool swiotlb_del_transient(struct device *dev, phys_addr_t tlb_addr, struct io_tlb_pool *pool) { return false; } #endif /* CONFIG_SWIOTLB_DYNAMIC */ /* * tlb_addr is the physical address of the bounce buffer to unmap. */ void __swiotlb_tbl_unmap_single(struct device *dev, phys_addr_t tlb_addr, size_t mapping_size, enum dma_data_direction dir, unsigned long attrs, struct io_tlb_pool *pool) { /* * First, sync the memory before unmapping the entry */ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_FROM_DEVICE, pool); if (swiotlb_del_transient(dev, tlb_addr, pool)) return; swiotlb_release_slots(dev, tlb_addr, pool); } void __swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr, size_t size, enum dma_data_direction dir, struct io_tlb_pool *pool) { if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) swiotlb_bounce(dev, tlb_addr, size, DMA_TO_DEVICE, pool); else BUG_ON(dir != DMA_FROM_DEVICE); } void __swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr, size_t size, enum dma_data_direction dir, struct io_tlb_pool *pool) { if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) swiotlb_bounce(dev, tlb_addr, size, DMA_FROM_DEVICE, pool); else BUG_ON(dir != DMA_TO_DEVICE); } /* * Create a swiotlb mapping for the buffer at @paddr, and in case of DMAing * to the device copy the data into it as well. */ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, enum dma_data_direction dir, unsigned long attrs) { phys_addr_t swiotlb_addr; dma_addr_t dma_addr; trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size); swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, 0, dir, attrs); if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; /* Ensure that the address returned is DMA'ble */ dma_addr = phys_to_dma_unencrypted(dev, swiotlb_addr); if (unlikely(!dma_capable(dev, dma_addr, size, true))) { __swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC, swiotlb_find_pool(dev, swiotlb_addr)); dev_WARN_ONCE(dev, 1, "swiotlb addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); return DMA_MAPPING_ERROR; } if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) arch_sync_dma_for_device(swiotlb_addr, size, dir); return dma_addr; } size_t swiotlb_max_mapping_size(struct device *dev) { int min_align_mask = dma_get_min_align_mask(dev); int min_align = 0; /* * swiotlb_find_slots() skips slots according to * min align mask. This affects max mapping size. * Take it into acount here. */ if (min_align_mask) min_align = roundup(min_align_mask, IO_TLB_SIZE); return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE - min_align; } /** * is_swiotlb_allocated() - check if the default software IO TLB is initialized */ bool is_swiotlb_allocated(void) { return io_tlb_default_mem.nslabs; } bool is_swiotlb_active(struct device *dev) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; return mem && mem->nslabs; } /** * default_swiotlb_base() - get the base address of the default SWIOTLB * * Get the lowest physical address used by the default software IO TLB pool. */ phys_addr_t default_swiotlb_base(void) { #ifdef CONFIG_SWIOTLB_DYNAMIC io_tlb_default_mem.can_grow = false; #endif return io_tlb_default_mem.defpool.start; } /** * default_swiotlb_limit() - get the address limit of the default SWIOTLB * * Get the highest physical address used by the default software IO TLB pool. */ phys_addr_t default_swiotlb_limit(void) { #ifdef CONFIG_SWIOTLB_DYNAMIC return io_tlb_default_mem.phys_limit; #else return io_tlb_default_mem.defpool.end - 1; #endif } #ifdef CONFIG_DEBUG_FS #ifdef CONFIG_SWIOTLB_DYNAMIC static unsigned long mem_transient_used(struct io_tlb_mem *mem) { return atomic_long_read(&mem->transient_nslabs); } static int io_tlb_transient_used_get(void *data, u64 *val) { struct io_tlb_mem *mem = data; *val = mem_transient_used(mem); return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_transient_used, io_tlb_transient_used_get, NULL, "%llu\n"); #endif /* CONFIG_SWIOTLB_DYNAMIC */ static int io_tlb_used_get(void *data, u64 *val) { struct io_tlb_mem *mem = data; *val = mem_used(mem); return 0; } static int io_tlb_hiwater_get(void *data, u64 *val) { struct io_tlb_mem *mem = data; *val = atomic_long_read(&mem->used_hiwater); return 0; } static int io_tlb_hiwater_set(void *data, u64 val) { struct io_tlb_mem *mem = data; /* Only allow setting to zero */ if (val != 0) return -EINVAL; atomic_long_set(&mem->used_hiwater, val); return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_used, io_tlb_used_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_hiwater, io_tlb_hiwater_get, io_tlb_hiwater_set, "%llu\n"); static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, const char *dirname) { mem->debugfs = debugfs_create_dir(dirname, io_tlb_default_mem.debugfs); if (!mem->nslabs) return; debugfs_create_ulong("io_tlb_nslabs", 0400, mem->debugfs, &mem->nslabs); debugfs_create_file("io_tlb_used", 0400, mem->debugfs, mem, &fops_io_tlb_used); debugfs_create_file("io_tlb_used_hiwater", 0600, mem->debugfs, mem, &fops_io_tlb_hiwater); #ifdef CONFIG_SWIOTLB_DYNAMIC debugfs_create_file("io_tlb_transient_nslabs", 0400, mem->debugfs, mem, &fops_io_tlb_transient_used); #endif } static int __init swiotlb_create_default_debugfs(void) { swiotlb_create_debugfs_files(&io_tlb_default_mem, "swiotlb"); return 0; } late_initcall(swiotlb_create_default_debugfs); #else /* !CONFIG_DEBUG_FS */ static inline void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, const char *dirname) { } #endif /* CONFIG_DEBUG_FS */ #ifdef CONFIG_DMA_RESTRICTED_POOL struct page *swiotlb_alloc(struct device *dev, size_t size) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; struct io_tlb_pool *pool; phys_addr_t tlb_addr; unsigned int align; int index; if (!mem) return NULL; align = (1 << (get_order(size) + PAGE_SHIFT)) - 1; index = swiotlb_find_slots(dev, 0, size, align, &pool); if (index == -1) return NULL; tlb_addr = slot_addr(pool->start, index); if (unlikely(!PAGE_ALIGNED(tlb_addr))) { dev_WARN_ONCE(dev, 1, "Cannot allocate pages from non page-aligned swiotlb addr 0x%pa.\n", &tlb_addr); swiotlb_release_slots(dev, tlb_addr, pool); return NULL; } return pfn_to_page(PFN_DOWN(tlb_addr)); } bool swiotlb_free(struct device *dev, struct page *page, size_t size) { phys_addr_t tlb_addr = page_to_phys(page); struct io_tlb_pool *pool; pool = swiotlb_find_pool(dev, tlb_addr); if (!pool) return false; swiotlb_release_slots(dev, tlb_addr, pool); return true; } static int rmem_swiotlb_device_init(struct reserved_mem *rmem, struct device *dev) { struct io_tlb_mem *mem = rmem->priv; unsigned long nslabs = rmem->size >> IO_TLB_SHIFT; /* Set Per-device io tlb area to one */ unsigned int nareas = 1; if (PageHighMem(pfn_to_page(PHYS_PFN(rmem->base)))) { dev_err(dev, "Restricted DMA pool must be accessible within the linear mapping."); return -EINVAL; } /* * Since multiple devices can share the same pool, the private data, * io_tlb_mem struct, will be initialized by the first device attached * to it. */ if (!mem) { struct io_tlb_pool *pool; mem = kzalloc(sizeof(*mem), GFP_KERNEL); if (!mem) return -ENOMEM; pool = &mem->defpool; pool->slots = kcalloc(nslabs, sizeof(*pool->slots), GFP_KERNEL); if (!pool->slots) { kfree(mem); return -ENOMEM; } pool->areas = kcalloc(nareas, sizeof(*pool->areas), GFP_KERNEL); if (!pool->areas) { kfree(pool->slots); kfree(mem); return -ENOMEM; } set_memory_decrypted((unsigned long)phys_to_virt(rmem->base), rmem->size >> PAGE_SHIFT); swiotlb_init_io_tlb_pool(pool, rmem->base, nslabs, false, nareas); mem->force_bounce = true; mem->for_alloc = true; #ifdef CONFIG_SWIOTLB_DYNAMIC spin_lock_init(&mem->lock); INIT_LIST_HEAD_RCU(&mem->pools); #endif add_mem_pool(mem, pool); rmem->priv = mem; swiotlb_create_debugfs_files(mem, rmem->name); } dev->dma_io_tlb_mem = mem; return 0; } static void rmem_swiotlb_device_release(struct reserved_mem *rmem, struct device *dev) { dev->dma_io_tlb_mem = &io_tlb_default_mem; } static const struct reserved_mem_ops rmem_swiotlb_ops = { .device_init = rmem_swiotlb_device_init, .device_release = rmem_swiotlb_device_release, }; static int __init rmem_swiotlb_setup(struct reserved_mem *rmem) { unsigned long node = rmem->fdt_node; if (of_get_flat_dt_prop(node, "reusable", NULL) || of_get_flat_dt_prop(node, "linux,cma-default", NULL) || of_get_flat_dt_prop(node, "linux,dma-default", NULL) || of_get_flat_dt_prop(node, "no-map", NULL)) return -EINVAL; rmem->ops = &rmem_swiotlb_ops; pr_info("Reserved memory: created restricted DMA pool at %pa, size %ld MiB\n", &rmem->base, (unsigned long)rmem->size / SZ_1M); return 0; } RESERVEDMEM_OF_DECLARE(dma, "restricted-dma-pool", rmem_swiotlb_setup); #endif /* CONFIG_DMA_RESTRICTED_POOL */ |
| 23 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __VDSO_HELPERS_H #define __VDSO_HELPERS_H #ifndef __ASSEMBLY__ #include <asm/barrier.h> #include <vdso/datapage.h> static __always_inline u32 vdso_read_begin(const struct vdso_data *vd) { u32 seq; while (unlikely((seq = READ_ONCE(vd->seq)) & 1)) cpu_relax(); smp_rmb(); return seq; } static __always_inline u32 vdso_read_retry(const struct vdso_data *vd, u32 start) { u32 seq; smp_rmb(); seq = READ_ONCE(vd->seq); return seq != start; } static __always_inline void vdso_write_begin(struct vdso_data *vd) { /* * WRITE_ONCE() is required otherwise the compiler can validly tear * updates to vd[x].seq and it is possible that the value seen by the * reader is inconsistent. */ WRITE_ONCE(vd[CS_HRES_COARSE].seq, vd[CS_HRES_COARSE].seq + 1); WRITE_ONCE(vd[CS_RAW].seq, vd[CS_RAW].seq + 1); smp_wmb(); } static __always_inline void vdso_write_end(struct vdso_data *vd) { smp_wmb(); /* * WRITE_ONCE() is required otherwise the compiler can validly tear * updates to vd[x].seq and it is possible that the value seen by the * reader is inconsistent. */ WRITE_ONCE(vd[CS_HRES_COARSE].seq, vd[CS_HRES_COARSE].seq + 1); WRITE_ONCE(vd[CS_RAW].seq, vd[CS_RAW].seq + 1); } #endif /* !__ASSEMBLY__ */ #endif /* __VDSO_HELPERS_H */ |
| 11457 9687 9695 66 66 1 10 10 66 66 819 817 818 818 9 8 8 4 3 809 809 811 812 811 3 809 809 809 808 808 809 807 806 2 11 3 11 5 11 3 709 151 779 10977 9777 784 32 33 33 30 33 30 30 33 32 30 30 4 4 1949 1915 1906 1872 1953 563 557 447 239 239 232 239 1147 1147 1146 1219 1215 1193 1219 47 47 47 11638 11511 11515 362 9637 10099 10058 9123 10102 10102 11986 7 27 14 14 14 24 11 12 12 11 23 18 17 18 20 19 18 18 3 3 2 1 1 3 3 3 3 2 1 3 6 5 4 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic pidhash and scalable, time-bounded PID allocator * * (C) 2002-2003 Nadia Yvette Chambers, IBM * (C) 2004 Nadia Yvette Chambers, Oracle * (C) 2002-2004 Ingo Molnar, Red Hat * * pid-structures are backing objects for tasks sharing a given ID to chain * against. There is very little to them aside from hashing them and * parking tasks using given ID's on a list. * * The hash is always changed with the tasklist_lock write-acquired, * and the hash is only accessed with the tasklist_lock at least * read-acquired, so there's no additional SMP locking needed here. * * We have a list of bitmap pages, which bitmaps represent the PID space. * Allocating and freeing PIDs is completely lockless. The worst-case * allocation scenario when all but one out of 1 million PIDs possible are * allocated already: the scanning of 32 list entries and at most PAGE_SIZE * bytes. The typical fastpath is a single successful setbit. Freeing is O(1). * * Pid namespaces: * (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc. * (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM * Many thanks to Oleg Nesterov for comments and help * */ #include <linux/mm.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/rculist.h> #include <linux/memblock.h> #include <linux/pid_namespace.h> #include <linux/init_task.h> #include <linux/syscalls.h> #include <linux/proc_ns.h> #include <linux/refcount.h> #include <linux/anon_inodes.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/idr.h> #include <linux/pidfs.h> #include <net/sock.h> #include <uapi/linux/pidfd.h> struct pid init_struct_pid = { .count = REFCOUNT_INIT(1), .tasks = { { .first = NULL }, { .first = NULL }, { .first = NULL }, }, .level = 0, .numbers = { { .nr = 0, .ns = &init_pid_ns, }, } }; int pid_max = PID_MAX_DEFAULT; int pid_max_min = RESERVED_PIDS + 1; int pid_max_max = PID_MAX_LIMIT; /* * Pseudo filesystems start inode numbering after one. We use Reserved * PIDs as a natural offset. */ static u64 pidfs_ino = RESERVED_PIDS; /* * PID-map pages start out as NULL, they get allocated upon * first use and are never deallocated. This way a low pid_max * value does not cause lots of bitmaps to be allocated, but * the scheme scales to up to 4 million PIDs, runtime. */ struct pid_namespace init_pid_ns = { .ns.count = REFCOUNT_INIT(2), .idr = IDR_INIT(init_pid_ns.idr), .pid_allocated = PIDNS_ADDING, .level = 0, .child_reaper = &init_task, .user_ns = &init_user_ns, .ns.inum = PROC_PID_INIT_INO, #ifdef CONFIG_PID_NS .ns.ops = &pidns_operations, #endif #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) .memfd_noexec_scope = MEMFD_NOEXEC_SCOPE_EXEC, #endif }; EXPORT_SYMBOL_GPL(init_pid_ns); /* * Note: disable interrupts while the pidmap_lock is held as an * interrupt might come in and do read_lock(&tasklist_lock). * * If we don't disable interrupts there is a nasty deadlock between * detach_pid()->free_pid() and another cpu that does * spin_lock(&pidmap_lock) followed by an interrupt routine that does * read_lock(&tasklist_lock); * * After we clean up the tasklist_lock and know there are no * irq handlers that take it we can leave the interrupts enabled. * For now it is easier to be safe than to prove it can't happen. */ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock); void put_pid(struct pid *pid) { struct pid_namespace *ns; if (!pid) return; ns = pid->numbers[pid->level].ns; if (refcount_dec_and_test(&pid->count)) { kmem_cache_free(ns->pid_cachep, pid); put_pid_ns(ns); } } EXPORT_SYMBOL_GPL(put_pid); static void delayed_put_pid(struct rcu_head *rhp) { struct pid *pid = container_of(rhp, struct pid, rcu); put_pid(pid); } void free_pid(struct pid *pid) { /* We can be called with write_lock_irq(&tasklist_lock) held */ int i; unsigned long flags; spin_lock_irqsave(&pidmap_lock, flags); for (i = 0; i <= pid->level; i++) { struct upid *upid = pid->numbers + i; struct pid_namespace *ns = upid->ns; switch (--ns->pid_allocated) { case 2: case 1: /* When all that is left in the pid namespace * is the reaper wake up the reaper. The reaper * may be sleeping in zap_pid_ns_processes(). */ wake_up_process(ns->child_reaper); break; case PIDNS_ADDING: /* Handle a fork failure of the first process */ WARN_ON(ns->child_reaper); ns->pid_allocated = 0; break; } idr_remove(&ns->idr, upid->nr); } spin_unlock_irqrestore(&pidmap_lock, flags); call_rcu(&pid->rcu, delayed_put_pid); } struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, size_t set_tid_size) { struct pid *pid; enum pid_type type; int i, nr; struct pid_namespace *tmp; struct upid *upid; int retval = -ENOMEM; /* * set_tid_size contains the size of the set_tid array. Starting at * the most nested currently active PID namespace it tells alloc_pid() * which PID to set for a process in that most nested PID namespace * up to set_tid_size PID namespaces. It does not have to set the PID * for a process in all nested PID namespaces but set_tid_size must * never be greater than the current ns->level + 1. */ if (set_tid_size > ns->level + 1) return ERR_PTR(-EINVAL); pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL); if (!pid) return ERR_PTR(retval); tmp = ns; pid->level = ns->level; for (i = ns->level; i >= 0; i--) { int tid = 0; if (set_tid_size) { tid = set_tid[ns->level - i]; retval = -EINVAL; if (tid < 1 || tid >= pid_max) goto out_free; /* * Also fail if a PID != 1 is requested and * no PID 1 exists. */ if (tid != 1 && !tmp->child_reaper) goto out_free; retval = -EPERM; if (!checkpoint_restore_ns_capable(tmp->user_ns)) goto out_free; set_tid_size--; } idr_preload(GFP_KERNEL); spin_lock_irq(&pidmap_lock); if (tid) { nr = idr_alloc(&tmp->idr, NULL, tid, tid + 1, GFP_ATOMIC); /* * If ENOSPC is returned it means that the PID is * alreay in use. Return EEXIST in that case. */ if (nr == -ENOSPC) nr = -EEXIST; } else { int pid_min = 1; /* * init really needs pid 1, but after reaching the * maximum wrap back to RESERVED_PIDS */ if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS) pid_min = RESERVED_PIDS; /* * Store a null pointer so find_pid_ns does not find * a partially initialized PID (see below). */ nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min, pid_max, GFP_ATOMIC); } spin_unlock_irq(&pidmap_lock); idr_preload_end(); if (nr < 0) { retval = (nr == -ENOSPC) ? -EAGAIN : nr; goto out_free; } pid->numbers[i].nr = nr; pid->numbers[i].ns = tmp; tmp = tmp->parent; } /* * ENOMEM is not the most obvious choice especially for the case * where the child subreaper has already exited and the pid * namespace denies the creation of any new processes. But ENOMEM * is what we have exposed to userspace for a long time and it is * documented behavior for pid namespaces. So we can't easily * change it even if there were an error code better suited. */ retval = -ENOMEM; get_pid_ns(ns); refcount_set(&pid->count, 1); spin_lock_init(&pid->lock); for (type = 0; type < PIDTYPE_MAX; ++type) INIT_HLIST_HEAD(&pid->tasks[type]); init_waitqueue_head(&pid->wait_pidfd); INIT_HLIST_HEAD(&pid->inodes); upid = pid->numbers + ns->level; spin_lock_irq(&pidmap_lock); if (!(ns->pid_allocated & PIDNS_ADDING)) goto out_unlock; pid->stashed = NULL; pid->ino = ++pidfs_ino; for ( ; upid >= pid->numbers; --upid) { /* Make the PID visible to find_pid_ns. */ idr_replace(&upid->ns->idr, pid, upid->nr); upid->ns->pid_allocated++; } spin_unlock_irq(&pidmap_lock); return pid; out_unlock: spin_unlock_irq(&pidmap_lock); put_pid_ns(ns); out_free: spin_lock_irq(&pidmap_lock); while (++i <= ns->level) { upid = pid->numbers + i; idr_remove(&upid->ns->idr, upid->nr); } /* On failure to allocate the first pid, reset the state */ if (ns->pid_allocated == PIDNS_ADDING) idr_set_cursor(&ns->idr, 0); spin_unlock_irq(&pidmap_lock); kmem_cache_free(ns->pid_cachep, pid); return ERR_PTR(retval); } void disable_pid_allocation(struct pid_namespace *ns) { spin_lock_irq(&pidmap_lock); ns->pid_allocated &= ~PIDNS_ADDING; spin_unlock_irq(&pidmap_lock); } struct pid *find_pid_ns(int nr, struct pid_namespace *ns) { return idr_find(&ns->idr, nr); } EXPORT_SYMBOL_GPL(find_pid_ns); struct pid *find_vpid(int nr) { return find_pid_ns(nr, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(find_vpid); static struct pid **task_pid_ptr(struct task_struct *task, enum pid_type type) { return (type == PIDTYPE_PID) ? &task->thread_pid : &task->signal->pids[type]; } /* * attach_pid() must be called with the tasklist_lock write-held. */ void attach_pid(struct task_struct *task, enum pid_type type) { struct pid *pid = *task_pid_ptr(task, type); hlist_add_head_rcu(&task->pid_links[type], &pid->tasks[type]); } static void __change_pid(struct task_struct *task, enum pid_type type, struct pid *new) { struct pid **pid_ptr = task_pid_ptr(task, type); struct pid *pid; int tmp; pid = *pid_ptr; hlist_del_rcu(&task->pid_links[type]); *pid_ptr = new; if (type == PIDTYPE_PID) { WARN_ON_ONCE(pid_has_task(pid, PIDTYPE_PID)); wake_up_all(&pid->wait_pidfd); } for (tmp = PIDTYPE_MAX; --tmp >= 0; ) if (pid_has_task(pid, tmp)) return; free_pid(pid); } void detach_pid(struct task_struct *task, enum pid_type type) { __change_pid(task, type, NULL); } void change_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { __change_pid(task, type, pid); attach_pid(task, type); } void exchange_tids(struct task_struct *left, struct task_struct *right) { struct pid *pid1 = left->thread_pid; struct pid *pid2 = right->thread_pid; struct hlist_head *head1 = &pid1->tasks[PIDTYPE_PID]; struct hlist_head *head2 = &pid2->tasks[PIDTYPE_PID]; /* Swap the single entry tid lists */ hlists_swap_heads_rcu(head1, head2); /* Swap the per task_struct pid */ rcu_assign_pointer(left->thread_pid, pid2); rcu_assign_pointer(right->thread_pid, pid1); /* Swap the cached value */ WRITE_ONCE(left->pid, pid_nr(pid2)); WRITE_ONCE(right->pid, pid_nr(pid1)); } /* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */ void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type type) { WARN_ON_ONCE(type == PIDTYPE_PID); hlist_replace_rcu(&old->pid_links[type], &new->pid_links[type]); } struct task_struct *pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result = NULL; if (pid) { struct hlist_node *first; first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]), lockdep_tasklist_lock_is_held()); if (first) result = hlist_entry(first, struct task_struct, pid_links[(type)]); } return result; } EXPORT_SYMBOL(pid_task); /* * Must be called under rcu_read_lock(). */ struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) { RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "find_task_by_pid_ns() needs rcu_read_lock() protection"); return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID); } struct task_struct *find_task_by_vpid(pid_t vnr) { return find_task_by_pid_ns(vnr, task_active_pid_ns(current)); } struct task_struct *find_get_task_by_vpid(pid_t nr) { struct task_struct *task; rcu_read_lock(); task = find_task_by_vpid(nr); if (task) get_task_struct(task); rcu_read_unlock(); return task; } struct pid *get_task_pid(struct task_struct *task, enum pid_type type) { struct pid *pid; rcu_read_lock(); pid = get_pid(rcu_dereference(*task_pid_ptr(task, type))); rcu_read_unlock(); return pid; } EXPORT_SYMBOL_GPL(get_task_pid); struct task_struct *get_pid_task(struct pid *pid, enum pid_type type) { struct task_struct *result; rcu_read_lock(); result = pid_task(pid, type); if (result) get_task_struct(result); rcu_read_unlock(); return result; } EXPORT_SYMBOL_GPL(get_pid_task); struct pid *find_get_pid(pid_t nr) { struct pid *pid; rcu_read_lock(); pid = get_pid(find_vpid(nr)); rcu_read_unlock(); return pid; } EXPORT_SYMBOL_GPL(find_get_pid); pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns) { struct upid *upid; pid_t nr = 0; if (pid && ns->level <= pid->level) { upid = &pid->numbers[ns->level]; if (upid->ns == ns) nr = upid->nr; } return nr; } EXPORT_SYMBOL_GPL(pid_nr_ns); pid_t pid_vnr(struct pid *pid) { return pid_nr_ns(pid, task_active_pid_ns(current)); } EXPORT_SYMBOL_GPL(pid_vnr); pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, struct pid_namespace *ns) { pid_t nr = 0; rcu_read_lock(); if (!ns) ns = task_active_pid_ns(current); nr = pid_nr_ns(rcu_dereference(*task_pid_ptr(task, type)), ns); rcu_read_unlock(); return nr; } EXPORT_SYMBOL(__task_pid_nr_ns); struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) { return ns_of_pid(task_pid(tsk)); } EXPORT_SYMBOL_GPL(task_active_pid_ns); /* * Used by proc to find the first pid that is greater than or equal to nr. * * If there is a pid at nr this function is exactly the same as find_pid_ns. */ struct pid *find_ge_pid(int nr, struct pid_namespace *ns) { return idr_get_next(&ns->idr, &nr); } EXPORT_SYMBOL_GPL(find_ge_pid); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) { CLASS(fd, f)(fd); struct pid *pid; if (fd_empty(f)) return ERR_PTR(-EBADF); pid = pidfd_pid(fd_file(f)); if (!IS_ERR(pid)) { get_pid(pid); *flags = fd_file(f)->f_flags; } return pid; } /** * pidfd_get_task() - Get the task associated with a pidfd * * @pidfd: pidfd for which to get the task * @flags: flags associated with this pidfd * * Return the task associated with @pidfd. The function takes a reference on * the returned task. The caller is responsible for releasing that reference. * * Return: On success, the task_struct associated with the pidfd. * On error, a negative errno number will be returned. */ struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags) { unsigned int f_flags; struct pid *pid; struct task_struct *task; pid = pidfd_get_pid(pidfd, &f_flags); if (IS_ERR(pid)) return ERR_CAST(pid); task = get_pid_task(pid, PIDTYPE_TGID); put_pid(pid); if (!task) return ERR_PTR(-ESRCH); *flags = f_flags; return task; } /** * pidfd_create() - Create a new pid file descriptor. * * @pid: struct pid that the pidfd will reference * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set. * * Note, that this function can only be called after the fd table has * been unshared to avoid leaking the pidfd to the new process. * * This symbol should not be explicitly exported to loadable modules. * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ static int pidfd_create(struct pid *pid, unsigned int flags) { int pidfd; struct file *pidfd_file; pidfd = pidfd_prepare(pid, flags, &pidfd_file); if (pidfd < 0) return pidfd; fd_install(pidfd, pidfd_file); return pidfd; } /** * sys_pidfd_open() - Open new pid file descriptor. * * @pid: pid for which to retrieve a pidfd * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set for * the task identified by @pid. Without PIDFD_THREAD flag the target task * must be a thread-group leader. * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) { int fd; struct pid *p; if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) return -EINVAL; if (pid <= 0) return -EINVAL; p = find_get_pid(pid); if (!p) return -ESRCH; fd = pidfd_create(p, flags); put_pid(p); return fd; } void __init pid_idr_init(void) { /* Verify no one has done anything silly: */ BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING); /* bump default and minimum pid_max based on number of cpus */ pid_max = min(pid_max_max, max_t(int, pid_max, PIDS_PER_CPU_DEFAULT * num_possible_cpus())); pid_max_min = max_t(int, pid_max_min, PIDS_PER_CPU_MIN * num_possible_cpus()); pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min); idr_init(&init_pid_ns.idr); init_pid_ns.pid_cachep = kmem_cache_create("pid", struct_size_t(struct pid, numbers, 1), __alignof__(struct pid), SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); } static struct file *__pidfd_fget(struct task_struct *task, int fd) { struct file *file; int ret; ret = down_read_killable(&task->signal->exec_update_lock); if (ret) return ERR_PTR(ret); if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS)) file = fget_task(task, fd); else file = ERR_PTR(-EPERM); up_read(&task->signal->exec_update_lock); if (!file) { /* * It is possible that the target thread is exiting; it can be * either: * 1. before exit_signals(), which gives a real fd * 2. before exit_files() takes the task_lock() gives a real fd * 3. after exit_files() releases task_lock(), ->files is NULL; * this has PF_EXITING, since it was set in exit_signals(), * __pidfd_fget() returns EBADF. * In case 3 we get EBADF, but that really means ESRCH, since * the task is currently exiting and has freed its files * struct, so we fix it up. */ if (task->flags & PF_EXITING) file = ERR_PTR(-ESRCH); else file = ERR_PTR(-EBADF); } return file; } static int pidfd_getfd(struct pid *pid, int fd) { struct task_struct *task; struct file *file; int ret; task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; file = __pidfd_fget(task, fd); put_task_struct(task); if (IS_ERR(file)) return PTR_ERR(file); ret = receive_fd(file, NULL, O_CLOEXEC); fput(file); return ret; } /** * sys_pidfd_getfd() - Get a file descriptor from another process * * @pidfd: the pidfd file descriptor of the process * @fd: the file descriptor number to get * @flags: flags on how to get the fd (reserved) * * This syscall gets a copy of a file descriptor from another process * based on the pidfd, and file descriptor number. It requires that * the calling process has the ability to ptrace the process represented * by the pidfd. The process which is having its file descriptor copied * is otherwise unaffected. * * Return: On success, a cloexec file descriptor is returned. * On error, a negative errno number will be returned. */ SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd, unsigned int, flags) { struct pid *pid; /* flags is currently unused - make sure it's unset */ if (flags) return -EINVAL; CLASS(fd, f)(pidfd); if (fd_empty(f)) return -EBADF; pid = pidfd_pid(fd_file(f)); if (IS_ERR(pid)) return PTR_ERR(pid); return pidfd_getfd(pid, fd); } |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 | // SPDX-License-Identifier: GPL-2.0-only /* * hosts.c Copyright (C) 1992 Drew Eckhardt * Copyright (C) 1993, 1994, 1995 Eric Youngdale * Copyright (C) 2002-2003 Christoph Hellwig * * mid to lowlevel SCSI driver interface * Initial versions: Drew Eckhardt * Subsequent revisions: Eric Youngdale * * <drew@colorado.edu> * * Jiffies wrap fixes (host->resetting), 3 Dec 1998 Andrea Arcangeli * Added QLOGIC QLA1280 SCSI controller kernel host support. * August 4, 1999 Fred Lewis, Intel DuPont * * Updated to reflect the new initialization scheme for the higher * level of scsi drivers (sd/sr/st) * September 17, 2000 Torben Mathiasen <tmm@image.dk> * * Restructured scsi_host lists and associated functions. * September 04, 2002 Mike Anderson (andmike@us.ibm.com) */ #include <linux/module.h> #include <linux/blkdev.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/kthread.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/init.h> #include <linux/completion.h> #include <linux/transport_class.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/idr.h> #include <scsi/scsi_device.h> #include <scsi/scsi_host.h> #include <scsi/scsi_transport.h> #include <scsi/scsi_cmnd.h> #include "scsi_priv.h" #include "scsi_logging.h" static int shost_eh_deadline = -1; module_param_named(eh_deadline, shost_eh_deadline, int, S_IRUGO|S_IWUSR); MODULE_PARM_DESC(eh_deadline, "SCSI EH timeout in seconds (should be between 0 and 2^31-1)"); static DEFINE_IDA(host_index_ida); static void scsi_host_cls_release(struct device *dev) { put_device(&class_to_shost(dev)->shost_gendev); } static struct class shost_class = { .name = "scsi_host", .dev_release = scsi_host_cls_release, .dev_groups = scsi_shost_groups, }; /** * scsi_host_set_state - Take the given host through the host state model. * @shost: scsi host to change the state of. * @state: state to change to. * * Returns zero if unsuccessful or an error if the requested * transition is illegal. **/ int scsi_host_set_state(struct Scsi_Host *shost, enum scsi_host_state state) { enum scsi_host_state oldstate = shost->shost_state; if (state == oldstate) return 0; switch (state) { case SHOST_CREATED: /* There are no legal states that come back to * created. This is the manually initialised start * state */ goto illegal; case SHOST_RUNNING: switch (oldstate) { case SHOST_CREATED: case SHOST_RECOVERY: break; default: goto illegal; } break; case SHOST_RECOVERY: switch (oldstate) { case SHOST_RUNNING: break; default: goto illegal; } break; case SHOST_CANCEL: switch (oldstate) { case SHOST_CREATED: case SHOST_RUNNING: case SHOST_CANCEL_RECOVERY: break; default: goto illegal; } break; case SHOST_DEL: switch (oldstate) { case SHOST_CANCEL: case SHOST_DEL_RECOVERY: break; default: goto illegal; } break; case SHOST_CANCEL_RECOVERY: switch (oldstate) { case SHOST_CANCEL: case SHOST_RECOVERY: break; default: goto illegal; } break; case SHOST_DEL_RECOVERY: switch (oldstate) { case SHOST_CANCEL_RECOVERY: break; default: goto illegal; } break; } shost->shost_state = state; return 0; illegal: SCSI_LOG_ERROR_RECOVERY(1, shost_printk(KERN_ERR, shost, "Illegal host state transition" "%s->%s\n", scsi_host_state_name(oldstate), scsi_host_state_name(state))); return -EINVAL; } /** * scsi_remove_host - remove a scsi host * @shost: a pointer to a scsi host to remove **/ void scsi_remove_host(struct Scsi_Host *shost) { unsigned long flags; mutex_lock(&shost->scan_mutex); spin_lock_irqsave(shost->host_lock, flags); if (scsi_host_set_state(shost, SHOST_CANCEL)) if (scsi_host_set_state(shost, SHOST_CANCEL_RECOVERY)) { spin_unlock_irqrestore(shost->host_lock, flags); mutex_unlock(&shost->scan_mutex); return; } spin_unlock_irqrestore(shost->host_lock, flags); scsi_autopm_get_host(shost); flush_workqueue(shost->tmf_work_q); scsi_forget_host(shost); mutex_unlock(&shost->scan_mutex); scsi_proc_host_rm(shost); scsi_proc_hostdir_rm(shost->hostt); /* * New SCSI devices cannot be attached anymore because of the SCSI host * state so drop the tag set refcnt. Wait until the tag set refcnt drops * to zero because .exit_cmd_priv implementations may need the host * pointer. */ kref_put(&shost->tagset_refcnt, scsi_mq_free_tags); wait_for_completion(&shost->tagset_freed); spin_lock_irqsave(shost->host_lock, flags); if (scsi_host_set_state(shost, SHOST_DEL)) BUG_ON(scsi_host_set_state(shost, SHOST_DEL_RECOVERY)); spin_unlock_irqrestore(shost->host_lock, flags); transport_unregister_device(&shost->shost_gendev); device_unregister(&shost->shost_dev); device_del(&shost->shost_gendev); } EXPORT_SYMBOL(scsi_remove_host); /** * scsi_add_host_with_dma - add a scsi host with dma device * @shost: scsi host pointer to add * @dev: a struct device of type scsi class * @dma_dev: dma device for the host * * Note: You rarely need to worry about this unless you're in a * virtualised host environments, so use the simpler scsi_add_host() * function instead. * * Return value: * 0 on success / != 0 for error **/ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev, struct device *dma_dev) { const struct scsi_host_template *sht = shost->hostt; int error = -EINVAL; shost_printk(KERN_INFO, shost, "%s\n", sht->info ? sht->info(shost) : sht->name); if (!shost->can_queue) { shost_printk(KERN_ERR, shost, "can_queue = 0 no longer supported\n"); goto fail; } /* Use min_t(int, ...) in case shost->can_queue exceeds SHRT_MAX */ shost->cmd_per_lun = min_t(int, shost->cmd_per_lun, shost->can_queue); error = scsi_init_sense_cache(shost); if (error) goto fail; if (!shost->shost_gendev.parent) shost->shost_gendev.parent = dev ? dev : &platform_bus; if (!dma_dev) dma_dev = shost->shost_gendev.parent; shost->dma_dev = dma_dev; if (dma_dev->dma_mask) { shost->max_sectors = min_t(unsigned int, shost->max_sectors, dma_max_mapping_size(dma_dev) >> SECTOR_SHIFT); } error = scsi_mq_setup_tags(shost); if (error) goto fail; kref_init(&shost->tagset_refcnt); init_completion(&shost->tagset_freed); /* * Increase usage count temporarily here so that calling * scsi_autopm_put_host() will trigger runtime idle if there is * nothing else preventing suspending the device. */ pm_runtime_get_noresume(&shost->shost_gendev); pm_runtime_set_active(&shost->shost_gendev); pm_runtime_enable(&shost->shost_gendev); device_enable_async_suspend(&shost->shost_gendev); error = device_add(&shost->shost_gendev); if (error) goto out_disable_runtime_pm; scsi_host_set_state(shost, SHOST_RUNNING); get_device(shost->shost_gendev.parent); device_enable_async_suspend(&shost->shost_dev); get_device(&shost->shost_gendev); error = device_add(&shost->shost_dev); if (error) goto out_del_gendev; if (shost->transportt->host_size) { shost->shost_data = kzalloc(shost->transportt->host_size, GFP_KERNEL); if (shost->shost_data == NULL) { error = -ENOMEM; goto out_del_dev; } } if (shost->transportt->create_work_queue) { shost->work_q = alloc_workqueue( "scsi_wq_%d", WQ_SYSFS | __WQ_LEGACY | WQ_MEM_RECLAIM | WQ_UNBOUND, 1, shost->host_no); if (!shost->work_q) { error = -EINVAL; goto out_del_dev; } } error = scsi_sysfs_add_host(shost); if (error) goto out_del_dev; scsi_proc_host_add(shost); scsi_autopm_put_host(shost); return error; /* * Any host allocation in this function will be freed in * scsi_host_dev_release(). */ out_del_dev: device_del(&shost->shost_dev); out_del_gendev: /* * Host state is SHOST_RUNNING so we have to explicitly release * ->shost_dev. */ put_device(&shost->shost_dev); device_del(&shost->shost_gendev); out_disable_runtime_pm: device_disable_async_suspend(&shost->shost_gendev); pm_runtime_disable(&shost->shost_gendev); pm_runtime_set_suspended(&shost->shost_gendev); pm_runtime_put_noidle(&shost->shost_gendev); kref_put(&shost->tagset_refcnt, scsi_mq_free_tags); fail: return error; } EXPORT_SYMBOL(scsi_add_host_with_dma); static void scsi_host_dev_release(struct device *dev) { struct Scsi_Host *shost = dev_to_shost(dev); struct device *parent = dev->parent; /* Wait for functions invoked through call_rcu(&scmd->rcu, ...) */ rcu_barrier(); if (shost->tmf_work_q) destroy_workqueue(shost->tmf_work_q); if (shost->ehandler) kthread_stop(shost->ehandler); if (shost->work_q) destroy_workqueue(shost->work_q); if (shost->shost_state == SHOST_CREATED) { /* * Free the shost_dev device name and remove the proc host dir * here if scsi_host_{alloc,put}() have been called but neither * scsi_host_add() nor scsi_remove_host() has been called. * This avoids that the memory allocated for the shost_dev * name as well as the proc dir structure are leaked. */ scsi_proc_hostdir_rm(shost->hostt); kfree(dev_name(&shost->shost_dev)); } kfree(shost->shost_data); ida_free(&host_index_ida, shost->host_no); if (shost->shost_state != SHOST_CREATED) put_device(parent); kfree(shost); } static const struct device_type scsi_host_type = { .name = "scsi_host", .release = scsi_host_dev_release, }; /** * scsi_host_alloc - register a scsi host adapter instance. * @sht: pointer to scsi host template * @privsize: extra bytes to allocate for driver * * Note: * Allocate a new Scsi_Host and perform basic initialization. * The host is not published to the scsi midlayer until scsi_add_host * is called. * * Return value: * Pointer to a new Scsi_Host **/ struct Scsi_Host *scsi_host_alloc(const struct scsi_host_template *sht, int privsize) { struct Scsi_Host *shost; int index; shost = kzalloc(sizeof(struct Scsi_Host) + privsize, GFP_KERNEL); if (!shost) return NULL; shost->host_lock = &shost->default_lock; spin_lock_init(shost->host_lock); shost->shost_state = SHOST_CREATED; INIT_LIST_HEAD(&shost->__devices); INIT_LIST_HEAD(&shost->__targets); INIT_LIST_HEAD(&shost->eh_abort_list); INIT_LIST_HEAD(&shost->eh_cmd_q); INIT_LIST_HEAD(&shost->starved_list); init_waitqueue_head(&shost->host_wait); mutex_init(&shost->scan_mutex); index = ida_alloc(&host_index_ida, GFP_KERNEL); if (index < 0) { kfree(shost); return NULL; } shost->host_no = index; shost->dma_channel = 0xff; /* These three are default values which can be overridden */ shost->max_channel = 0; shost->max_id = 8; shost->max_lun = 8; /* Give each shost a default transportt */ shost->transportt = &blank_transport_template; /* * All drivers right now should be able to handle 12 byte * commands. Every so often there are requests for 16 byte * commands, but individual low-level drivers need to certify that * they actually do something sensible with such commands. */ shost->max_cmd_len = 12; shost->hostt = sht; shost->this_id = sht->this_id; shost->can_queue = sht->can_queue; shost->sg_tablesize = sht->sg_tablesize; shost->sg_prot_tablesize = sht->sg_prot_tablesize; shost->cmd_per_lun = sht->cmd_per_lun; shost->no_write_same = sht->no_write_same; shost->host_tagset = sht->host_tagset; shost->queuecommand_may_block = sht->queuecommand_may_block; if (shost_eh_deadline == -1 || !sht->eh_host_reset_handler) shost->eh_deadline = -1; else if ((ulong) shost_eh_deadline * HZ > INT_MAX) { shost_printk(KERN_WARNING, shost, "eh_deadline %u too large, setting to %u\n", shost_eh_deadline, INT_MAX / HZ); shost->eh_deadline = INT_MAX; } else shost->eh_deadline = shost_eh_deadline * HZ; if (sht->supported_mode == MODE_UNKNOWN) /* means we didn't set it ... default to INITIATOR */ shost->active_mode = MODE_INITIATOR; else shost->active_mode = sht->supported_mode; if (sht->max_host_blocked) shost->max_host_blocked = sht->max_host_blocked; else shost->max_host_blocked = SCSI_DEFAULT_HOST_BLOCKED; /* * If the driver imposes no hard sector transfer limit, start at * machine infinity initially. */ if (sht->max_sectors) shost->max_sectors = sht->max_sectors; else shost->max_sectors = SCSI_DEFAULT_MAX_SECTORS; if (sht->max_segment_size) shost->max_segment_size = sht->max_segment_size; else shost->max_segment_size = BLK_MAX_SEGMENT_SIZE; /* 32-byte (dword) is a common minimum for HBAs. */ if (sht->dma_alignment) shost->dma_alignment = sht->dma_alignment; else shost->dma_alignment = 3; /* * assume a 4GB boundary, if not set */ if (sht->dma_boundary) shost->dma_boundary = sht->dma_boundary; else shost->dma_boundary = 0xffffffff; if (sht->virt_boundary_mask) shost->virt_boundary_mask = sht->virt_boundary_mask; device_initialize(&shost->shost_gendev); dev_set_name(&shost->shost_gendev, "host%d", shost->host_no); shost->shost_gendev.bus = &scsi_bus_type; shost->shost_gendev.type = &scsi_host_type; scsi_enable_async_suspend(&shost->shost_gendev); device_initialize(&shost->shost_dev); shost->shost_dev.parent = &shost->shost_gendev; shost->shost_dev.class = &shost_class; dev_set_name(&shost->shost_dev, "host%d", shost->host_no); shost->shost_dev.groups = sht->shost_groups; shost->ehandler = kthread_run(scsi_error_handler, shost, "scsi_eh_%d", shost->host_no); if (IS_ERR(shost->ehandler)) { shost_printk(KERN_WARNING, shost, "error handler thread failed to spawn, error = %ld\n", PTR_ERR(shost->ehandler)); shost->ehandler = NULL; goto fail; } shost->tmf_work_q = alloc_workqueue("scsi_tmf_%d", WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 1, shost->host_no); if (!shost->tmf_work_q) { shost_printk(KERN_WARNING, shost, "failed to create tmf workq\n"); goto fail; } if (scsi_proc_hostdir_add(shost->hostt) < 0) goto fail; return shost; fail: /* * Host state is still SHOST_CREATED and that is enough to release * ->shost_gendev. scsi_host_dev_release() will free * dev_name(&shost->shost_dev). */ put_device(&shost->shost_gendev); return NULL; } EXPORT_SYMBOL(scsi_host_alloc); static int __scsi_host_match(struct device *dev, const void *data) { struct Scsi_Host *p; const unsigned int *hostnum = data; p = class_to_shost(dev); return p->host_no == *hostnum; } /** * scsi_host_lookup - get a reference to a Scsi_Host by host no * @hostnum: host number to locate * * Return value: * A pointer to located Scsi_Host or NULL. * * The caller must do a scsi_host_put() to drop the reference * that scsi_host_get() took. The put_device() below dropped * the reference from class_find_device(). **/ struct Scsi_Host *scsi_host_lookup(unsigned int hostnum) { struct device *cdev; struct Scsi_Host *shost = NULL; cdev = class_find_device(&shost_class, NULL, &hostnum, __scsi_host_match); if (cdev) { shost = scsi_host_get(class_to_shost(cdev)); put_device(cdev); } return shost; } EXPORT_SYMBOL(scsi_host_lookup); /** * scsi_host_get - inc a Scsi_Host ref count * @shost: Pointer to Scsi_Host to inc. **/ struct Scsi_Host *scsi_host_get(struct Scsi_Host *shost) { if ((shost->shost_state == SHOST_DEL) || !get_device(&shost->shost_gendev)) return NULL; return shost; } EXPORT_SYMBOL(scsi_host_get); static bool scsi_host_check_in_flight(struct request *rq, void *data) { int *count = data; struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq); if (test_bit(SCMD_STATE_INFLIGHT, &cmd->state)) (*count)++; return true; } /** * scsi_host_busy - Return the host busy counter * @shost: Pointer to Scsi_Host to inc. **/ int scsi_host_busy(struct Scsi_Host *shost) { int cnt = 0; blk_mq_tagset_busy_iter(&shost->tag_set, scsi_host_check_in_flight, &cnt); return cnt; } EXPORT_SYMBOL(scsi_host_busy); /** * scsi_host_put - dec a Scsi_Host ref count * @shost: Pointer to Scsi_Host to dec. **/ void scsi_host_put(struct Scsi_Host *shost) { put_device(&shost->shost_gendev); } EXPORT_SYMBOL(scsi_host_put); int scsi_init_hosts(void) { return class_register(&shost_class); } void scsi_exit_hosts(void) { class_unregister(&shost_class); ida_destroy(&host_index_ida); } int scsi_is_host_device(const struct device *dev) { return dev->type == &scsi_host_type; } EXPORT_SYMBOL(scsi_is_host_device); /** * scsi_queue_work - Queue work to the Scsi_Host workqueue. * @shost: Pointer to Scsi_Host. * @work: Work to queue for execution. * * Return value: * 1 - work queued for execution * 0 - work is already queued * -EINVAL - work queue doesn't exist **/ int scsi_queue_work(struct Scsi_Host *shost, struct work_struct *work) { if (unlikely(!shost->work_q)) { shost_printk(KERN_ERR, shost, "ERROR: Scsi host '%s' attempted to queue scsi-work, " "when no workqueue created.\n", shost->hostt->name); dump_stack(); return -EINVAL; } return queue_work(shost->work_q, work); } EXPORT_SYMBOL_GPL(scsi_queue_work); /** * scsi_flush_work - Flush a Scsi_Host's workqueue. * @shost: Pointer to Scsi_Host. **/ void scsi_flush_work(struct Scsi_Host *shost) { if (!shost->work_q) { shost_printk(KERN_ERR, shost, "ERROR: Scsi host '%s' attempted to flush scsi-work, " "when no workqueue created.\n", shost->hostt->name); dump_stack(); return; } flush_workqueue(shost->work_q); } EXPORT_SYMBOL_GPL(scsi_flush_work); static bool complete_all_cmds_iter(struct request *rq, void *data) { struct scsi_cmnd *scmd = blk_mq_rq_to_pdu(rq); enum scsi_host_status status = *(enum scsi_host_status *)data; scsi_dma_unmap(scmd); scmd->result = 0; set_host_byte(scmd, status); scsi_done(scmd); return true; } /** * scsi_host_complete_all_commands - Terminate all running commands * @shost: Scsi Host on which commands should be terminated * @status: Status to be set for the terminated commands * * There is no protection against modification of the number * of outstanding commands. It is the responsibility of the * caller to ensure that concurrent I/O submission and/or * completion is stopped when calling this function. */ void scsi_host_complete_all_commands(struct Scsi_Host *shost, enum scsi_host_status status) { blk_mq_tagset_busy_iter(&shost->tag_set, complete_all_cmds_iter, &status); } EXPORT_SYMBOL_GPL(scsi_host_complete_all_commands); struct scsi_host_busy_iter_data { bool (*fn)(struct scsi_cmnd *, void *); void *priv; }; static bool __scsi_host_busy_iter_fn(struct request *req, void *priv) { struct scsi_host_busy_iter_data *iter_data = priv; struct scsi_cmnd *sc = blk_mq_rq_to_pdu(req); return iter_data->fn(sc, iter_data->priv); } /** * scsi_host_busy_iter - Iterate over all busy commands * @shost: Pointer to Scsi_Host. * @fn: Function to call on each busy command * @priv: Data pointer passed to @fn * * If locking against concurrent command completions is required * ithas to be provided by the caller **/ void scsi_host_busy_iter(struct Scsi_Host *shost, bool (*fn)(struct scsi_cmnd *, void *), void *priv) { struct scsi_host_busy_iter_data iter_data = { .fn = fn, .priv = priv, }; blk_mq_tagset_busy_iter(&shost->tag_set, __scsi_host_busy_iter_fn, &iter_data); } EXPORT_SYMBOL_GPL(scsi_host_busy_iter); |
| 290 88 17 2 17 1 1 17 17 43 41 4 3 360 359 359 360 358 4 3 2 307 307 1 34 43 43 40 335 360 5 355 502 14 502 501 502 502 403 403 14 403 501 502 502 502 501 502 502 502 365 325 502 502 501 502 403 406 403 403 403 403 97 97 97 97 340 339 339 339 339 339 339 339 340 340 28 340 339 138 38 37 28 11 340 100 100 505 505 504 502 501 502 502 501 500 497 496 17 498 37 37 37 496 141 112 113 400 16 126 335 254 405 64 64 63 3 64 64 64 3 3 64 64 300 300 300 299 300 300 239 365 324 37 4 269 74 198 2 196 193 70 28 193 44 151 408 408 408 403 98 404 365 1 365 365 193 193 78 140 146 321 97 97 97 97 1 97 81 5 253 253 253 15 241 1 240 253 16 158 157 158 64 151 2 148 144 129 144 8 8 64 64 106 106 69 37 106 4 106 2 104 106 21 21 21 21 21 22 22 22 1 21 22 1 1 1 1 2 2 2 149 32 123 149 150 150 2 1 1 2 2 3 3 3 74 71 54 55 75 71 71 6 71 66 49 36 5 68 67 68 33 32 49 67 71 39 35 35 33 9 35 26 19 27 35 9 9 34 34 1 34 39 86 86 10 80 7 74 86 17 168 168 5 166 16 151 168 20 8 31 31 31 8 31 23 31 31 6 26 30 30 1 29 30 18 1 18 18 18 5 5 5 90 91 89 13 1 12 91 1 90 5 5 5 6 6 6 6 6 6 6 6 6 6 6 6 3 1 2 2 3 3 1 2 2 3 5 5 5 5 2 2 2 2 2 2 2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * 9P Client * * Copyright (C) 2008 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/poll.h> #include <linux/idr.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/uio.h> #include <linux/netfs.h> #include <net/9p/9p.h> #include <linux/parser.h> #include <linux/seq_file.h> #include <net/9p/client.h> #include <net/9p/transport.h> #include "protocol.h" #define CREATE_TRACE_POINTS #include <trace/events/9p.h> /* DEFAULT MSIZE = 32 pages worth of payload + P9_HDRSZ + * room for write (16 extra) or read (11 extra) operands. */ #define DEFAULT_MSIZE ((128 * 1024) + P9_IOHDRSZ) /* Client Option Parsing (code inspired by NFS code) * - a little lazy - parse all client options */ enum { Opt_msize, Opt_trans, Opt_legacy, Opt_version, Opt_err, }; static const match_table_t tokens = { {Opt_msize, "msize=%u"}, {Opt_legacy, "noextend"}, {Opt_trans, "trans=%s"}, {Opt_version, "version=%s"}, {Opt_err, NULL}, }; inline int p9_is_proto_dotl(struct p9_client *clnt) { return clnt->proto_version == p9_proto_2000L; } EXPORT_SYMBOL(p9_is_proto_dotl); inline int p9_is_proto_dotu(struct p9_client *clnt) { return clnt->proto_version == p9_proto_2000u; } EXPORT_SYMBOL(p9_is_proto_dotu); int p9_show_client_options(struct seq_file *m, struct p9_client *clnt) { if (clnt->msize != DEFAULT_MSIZE) seq_printf(m, ",msize=%u", clnt->msize); seq_printf(m, ",trans=%s", clnt->trans_mod->name); switch (clnt->proto_version) { case p9_proto_legacy: seq_puts(m, ",noextend"); break; case p9_proto_2000u: seq_puts(m, ",version=9p2000.u"); break; case p9_proto_2000L: /* Default */ break; } if (clnt->trans_mod->show_options) return clnt->trans_mod->show_options(m, clnt); return 0; } EXPORT_SYMBOL(p9_show_client_options); /* Some error codes are taken directly from the server replies, * make sure they are valid. */ static int safe_errno(int err) { if (err > 0 || err < -MAX_ERRNO) { p9_debug(P9_DEBUG_ERROR, "Invalid error code %d\n", err); return -EPROTO; } return err; } /* Interpret mount option for protocol version */ static int get_protocol_version(char *s) { int version = -EINVAL; if (!strcmp(s, "9p2000")) { version = p9_proto_legacy; p9_debug(P9_DEBUG_9P, "Protocol version: Legacy\n"); } else if (!strcmp(s, "9p2000.u")) { version = p9_proto_2000u; p9_debug(P9_DEBUG_9P, "Protocol version: 9P2000.u\n"); } else if (!strcmp(s, "9p2000.L")) { version = p9_proto_2000L; p9_debug(P9_DEBUG_9P, "Protocol version: 9P2000.L\n"); } else { pr_info("Unknown protocol version %s\n", s); } return version; } /** * parse_opts - parse mount options into client structure * @opts: options string passed from mount * @clnt: existing v9fs client information * * Return 0 upon success, -ERRNO upon failure */ static int parse_opts(char *opts, struct p9_client *clnt) { char *options, *tmp_options; char *p; substring_t args[MAX_OPT_ARGS]; int option; char *s; int ret = 0; clnt->proto_version = p9_proto_2000L; clnt->msize = DEFAULT_MSIZE; if (!opts) return 0; tmp_options = kstrdup(opts, GFP_KERNEL); if (!tmp_options) return -ENOMEM; options = tmp_options; while ((p = strsep(&options, ",")) != NULL) { int token, r; if (!*p) continue; token = match_token(p, tokens, args); switch (token) { case Opt_msize: r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); ret = r; continue; } if (option < 4096) { p9_debug(P9_DEBUG_ERROR, "msize should be at least 4k\n"); ret = -EINVAL; continue; } clnt->msize = option; break; case Opt_trans: s = match_strdup(&args[0]); if (!s) { ret = -ENOMEM; p9_debug(P9_DEBUG_ERROR, "problem allocating copy of trans arg\n"); goto free_and_return; } v9fs_put_trans(clnt->trans_mod); clnt->trans_mod = v9fs_get_trans_by_name(s); if (!clnt->trans_mod) { pr_info("Could not find request transport: %s\n", s); ret = -EINVAL; } kfree(s); break; case Opt_legacy: clnt->proto_version = p9_proto_legacy; break; case Opt_version: s = match_strdup(&args[0]); if (!s) { ret = -ENOMEM; p9_debug(P9_DEBUG_ERROR, "problem allocating copy of version arg\n"); goto free_and_return; } r = get_protocol_version(s); if (r < 0) ret = r; else clnt->proto_version = r; kfree(s); break; default: continue; } } free_and_return: if (ret) v9fs_put_trans(clnt->trans_mod); kfree(tmp_options); return ret; } static int p9_fcall_init(struct p9_client *c, struct p9_fcall *fc, int alloc_msize) { if (likely(c->fcall_cache) && alloc_msize == c->msize) { fc->sdata = kmem_cache_alloc(c->fcall_cache, GFP_NOFS); fc->cache = c->fcall_cache; } else { fc->sdata = kmalloc(alloc_msize, GFP_NOFS); fc->cache = NULL; } if (!fc->sdata) return -ENOMEM; fc->capacity = alloc_msize; fc->id = 0; fc->tag = P9_NOTAG; return 0; } void p9_fcall_fini(struct p9_fcall *fc) { /* sdata can be NULL for interrupted requests in trans_rdma, * and kmem_cache_free does not do NULL-check for us */ if (unlikely(!fc->sdata)) return; if (fc->cache) kmem_cache_free(fc->cache, fc->sdata); else kfree(fc->sdata); } EXPORT_SYMBOL(p9_fcall_fini); static struct kmem_cache *p9_req_cache; /** * p9_tag_alloc - Allocate a new request. * @c: Client session. * @type: Transaction type. * @t_size: Buffer size for holding this request * (automatic calculation by format template if 0). * @r_size: Buffer size for holding server's reply on this request * (automatic calculation by format template if 0). * @fmt: Format template for assembling 9p request message * (see p9pdu_vwritef). * @ap: Variable arguments to be fed to passed format template * (see p9pdu_vwritef). * * Context: Process context. * Return: Pointer to new request. */ static struct p9_req_t * p9_tag_alloc(struct p9_client *c, int8_t type, uint t_size, uint r_size, const char *fmt, va_list ap) { struct p9_req_t *req = kmem_cache_alloc(p9_req_cache, GFP_NOFS); int alloc_tsize; int alloc_rsize; int tag; va_list apc; va_copy(apc, ap); alloc_tsize = min_t(size_t, c->msize, t_size ?: p9_msg_buf_size(c, type, fmt, apc)); va_end(apc); alloc_rsize = min_t(size_t, c->msize, r_size ?: p9_msg_buf_size(c, type + 1, fmt, ap)); if (!req) return ERR_PTR(-ENOMEM); if (p9_fcall_init(c, &req->tc, alloc_tsize)) goto free_req; if (p9_fcall_init(c, &req->rc, alloc_rsize)) goto free; p9pdu_reset(&req->tc); p9pdu_reset(&req->rc); req->t_err = 0; req->status = REQ_STATUS_ALLOC; /* refcount needs to be set to 0 before inserting into the idr * so p9_tag_lookup does not accept a request that is not fully * initialized. refcount_set to 2 below will mark request ready. */ refcount_set(&req->refcount, 0); init_waitqueue_head(&req->wq); INIT_LIST_HEAD(&req->req_list); idr_preload(GFP_NOFS); spin_lock_irq(&c->lock); if (type == P9_TVERSION) tag = idr_alloc(&c->reqs, req, P9_NOTAG, P9_NOTAG + 1, GFP_NOWAIT); else tag = idr_alloc(&c->reqs, req, 0, P9_NOTAG, GFP_NOWAIT); req->tc.tag = tag; spin_unlock_irq(&c->lock); idr_preload_end(); if (tag < 0) goto free; /* Init ref to two because in the general case there is one ref * that is put asynchronously by a writer thread, one ref * temporarily given by p9_tag_lookup and put by p9_client_cb * in the recv thread, and one ref put by p9_req_put in the * main thread. The only exception is virtio that does not use * p9_tag_lookup but does not have a writer thread either * (the write happens synchronously in the request/zc_request * callback), so p9_client_cb eats the second ref there * as the pointer is duplicated directly by virtqueue_add_sgs() */ refcount_set(&req->refcount, 2); return req; free: p9_fcall_fini(&req->tc); p9_fcall_fini(&req->rc); free_req: kmem_cache_free(p9_req_cache, req); return ERR_PTR(-ENOMEM); } /** * p9_tag_lookup - Look up a request by tag. * @c: Client session. * @tag: Transaction ID. * * Context: Any context. * Return: A request, or %NULL if there is no request with that tag. */ struct p9_req_t *p9_tag_lookup(struct p9_client *c, u16 tag) { struct p9_req_t *req; rcu_read_lock(); again: req = idr_find(&c->reqs, tag); if (req) { /* We have to be careful with the req found under rcu_read_lock * Thanks to SLAB_TYPESAFE_BY_RCU we can safely try to get the * ref again without corrupting other data, then check again * that the tag matches once we have the ref */ if (!p9_req_try_get(req)) goto again; if (req->tc.tag != tag) { p9_req_put(c, req); goto again; } } rcu_read_unlock(); return req; } EXPORT_SYMBOL(p9_tag_lookup); /** * p9_tag_remove - Remove a tag. * @c: Client session. * @r: Request of reference. * * Context: Any context. */ static void p9_tag_remove(struct p9_client *c, struct p9_req_t *r) { unsigned long flags; u16 tag = r->tc.tag; p9_debug(P9_DEBUG_MUX, "freeing clnt %p req %p tag: %d\n", c, r, tag); spin_lock_irqsave(&c->lock, flags); idr_remove(&c->reqs, tag); spin_unlock_irqrestore(&c->lock, flags); } int p9_req_put(struct p9_client *c, struct p9_req_t *r) { if (refcount_dec_and_test(&r->refcount)) { p9_tag_remove(c, r); p9_fcall_fini(&r->tc); p9_fcall_fini(&r->rc); kmem_cache_free(p9_req_cache, r); return 1; } return 0; } EXPORT_SYMBOL(p9_req_put); /** * p9_tag_cleanup - cleans up tags structure and reclaims resources * @c: v9fs client struct * * This frees resources associated with the tags structure * */ static void p9_tag_cleanup(struct p9_client *c) { struct p9_req_t *req; int id; rcu_read_lock(); idr_for_each_entry(&c->reqs, req, id) { pr_info("Tag %d still in use\n", id); if (p9_req_put(c, req) == 0) pr_warn("Packet with tag %d has still references", req->tc.tag); } rcu_read_unlock(); } /** * p9_client_cb - call back from transport to client * @c: client state * @req: request received * @status: request status, one of REQ_STATUS_* * */ void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status) { p9_debug(P9_DEBUG_MUX, " tag %d\n", req->tc.tag); /* This barrier is needed to make sure any change made to req before * the status change is visible to another thread */ smp_wmb(); WRITE_ONCE(req->status, status); wake_up(&req->wq); p9_debug(P9_DEBUG_MUX, "wakeup: %d\n", req->tc.tag); p9_req_put(c, req); } EXPORT_SYMBOL(p9_client_cb); /** * p9_parse_header - parse header arguments out of a packet * @pdu: packet to parse * @size: size of packet * @type: type of request * @tag: tag of packet * @rewind: set if we need to rewind offset afterwards */ int p9_parse_header(struct p9_fcall *pdu, int32_t *size, int8_t *type, int16_t *tag, int rewind) { s8 r_type; s16 r_tag; s32 r_size; int offset = pdu->offset; int err; pdu->offset = 0; err = p9pdu_readf(pdu, 0, "dbw", &r_size, &r_type, &r_tag); if (err) goto rewind_and_exit; if (type) *type = r_type; if (tag) *tag = r_tag; if (size) *size = r_size; if (pdu->size != r_size || r_size < 7) { err = -EINVAL; goto rewind_and_exit; } pdu->id = r_type; pdu->tag = r_tag; p9_debug(P9_DEBUG_9P, "<<< size=%d type: %d tag: %d\n", pdu->size, pdu->id, pdu->tag); rewind_and_exit: if (rewind) pdu->offset = offset; return err; } EXPORT_SYMBOL(p9_parse_header); /** * p9_check_errors - check 9p packet for error return and process it * @c: current client instance * @req: request to parse and check for error conditions * * returns error code if one is discovered, otherwise returns 0 * * this will have to be more complicated if we have multiple * error packet types */ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req) { s8 type; int err; int ecode; err = p9_parse_header(&req->rc, NULL, &type, NULL, 0); if (req->rc.size > req->rc.capacity && !req->rc.zc) { pr_err("requested packet size too big: %d does not fit %zu (type=%d)\n", req->rc.size, req->rc.capacity, req->rc.id); return -EIO; } /* dump the response from server * This should be after check errors which poplulate pdu_fcall. */ trace_9p_protocol_dump(c, &req->rc); if (err) { p9_debug(P9_DEBUG_ERROR, "couldn't parse header %d\n", err); return err; } if (type != P9_RERROR && type != P9_RLERROR) return 0; if (!p9_is_proto_dotl(c)) { char *ename = NULL; err = p9pdu_readf(&req->rc, c->proto_version, "s?d", &ename, &ecode); if (err) { kfree(ename); goto out_err; } if (p9_is_proto_dotu(c) && ecode < 512) err = -ecode; if (!err) { err = p9_errstr2errno(ename, strlen(ename)); p9_debug(P9_DEBUG_9P, "<<< RERROR (%d) %s\n", -ecode, ename); } kfree(ename); } else { err = p9pdu_readf(&req->rc, c->proto_version, "d", &ecode); if (err) goto out_err; err = -ecode; p9_debug(P9_DEBUG_9P, "<<< RLERROR (%d)\n", -ecode); } return err; out_err: p9_debug(P9_DEBUG_ERROR, "couldn't parse error%d\n", err); return err; } static struct p9_req_t * p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...); /** * p9_client_flush - flush (cancel) a request * @c: client state * @oldreq: request to cancel * * This sents a flush for a particular request and links * the flush request to the original request. The current * code only supports a single flush request although the protocol * allows for multiple flush requests to be sent for a single request. * */ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq) { struct p9_req_t *req; s16 oldtag; int err; err = p9_parse_header(&oldreq->tc, NULL, NULL, &oldtag, 1); if (err) return err; p9_debug(P9_DEBUG_9P, ">>> TFLUSH tag %d\n", oldtag); req = p9_client_rpc(c, P9_TFLUSH, "w", oldtag); if (IS_ERR(req)) return PTR_ERR(req); /* if we haven't received a response for oldreq, * remove it from the list */ if (READ_ONCE(oldreq->status) == REQ_STATUS_SENT) { if (c->trans_mod->cancelled) c->trans_mod->cancelled(c, oldreq); } p9_req_put(c, req); return 0; } static struct p9_req_t *p9_client_prepare_req(struct p9_client *c, int8_t type, uint t_size, uint r_size, const char *fmt, va_list ap) { int err; struct p9_req_t *req; va_list apc; p9_debug(P9_DEBUG_MUX, "client %p op %d\n", c, type); /* we allow for any status other than disconnected */ if (c->status == Disconnected) return ERR_PTR(-EIO); /* if status is begin_disconnected we allow only clunk request */ if (c->status == BeginDisconnect && type != P9_TCLUNK) return ERR_PTR(-EIO); va_copy(apc, ap); req = p9_tag_alloc(c, type, t_size, r_size, fmt, apc); va_end(apc); if (IS_ERR(req)) return req; /* marshall the data */ p9pdu_prepare(&req->tc, req->tc.tag, type); err = p9pdu_vwritef(&req->tc, c->proto_version, fmt, ap); if (err) goto reterr; p9pdu_finalize(c, &req->tc); trace_9p_client_req(c, type, req->tc.tag); return req; reterr: p9_req_put(c, req); /* We have to put also the 2nd reference as it won't be used */ p9_req_put(c, req); return ERR_PTR(err); } /** * p9_client_rpc - issue a request and wait for a response * @c: client session * @type: type of request * @fmt: protocol format string (see protocol.c) * * Returns request structure (which client must free using p9_req_put) */ static struct p9_req_t * p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...) { va_list ap; int sigpending, err; unsigned long flags; struct p9_req_t *req; /* Passing zero for tsize/rsize to p9_client_prepare_req() tells it to * auto determine an appropriate (small) request/response size * according to actual message data being sent. Currently RDMA * transport is excluded from this response message size optimization, * as it would not cope with it, due to its pooled response buffers * (using an optimized request size for RDMA as well though). */ const uint tsize = 0; const uint rsize = c->trans_mod->pooled_rbuffers ? c->msize : 0; va_start(ap, fmt); req = p9_client_prepare_req(c, type, tsize, rsize, fmt, ap); va_end(ap); if (IS_ERR(req)) return req; req->tc.zc = false; req->rc.zc = false; if (signal_pending(current)) { sigpending = 1; clear_thread_flag(TIF_SIGPENDING); } else { sigpending = 0; } err = c->trans_mod->request(c, req); if (err < 0) { /* write won't happen */ p9_req_put(c, req); if (err != -ERESTARTSYS && err != -EFAULT) c->status = Disconnected; goto recalc_sigpending; } again: /* Wait for the response */ err = wait_event_killable(req->wq, READ_ONCE(req->status) >= REQ_STATUS_RCVD); /* Make sure our req is coherent with regard to updates in other * threads - echoes to wmb() in the callback */ smp_rmb(); if (err == -ERESTARTSYS && c->status == Connected && type == P9_TFLUSH) { sigpending = 1; clear_thread_flag(TIF_SIGPENDING); goto again; } if (READ_ONCE(req->status) == REQ_STATUS_ERROR) { p9_debug(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err); err = req->t_err; } if (err == -ERESTARTSYS && c->status == Connected) { p9_debug(P9_DEBUG_MUX, "flushing\n"); sigpending = 1; clear_thread_flag(TIF_SIGPENDING); if (c->trans_mod->cancel(c, req)) p9_client_flush(c, req); /* if we received the response anyway, don't signal error */ if (READ_ONCE(req->status) == REQ_STATUS_RCVD) err = 0; } recalc_sigpending: if (sigpending) { spin_lock_irqsave(¤t->sighand->siglock, flags); recalc_sigpending(); spin_unlock_irqrestore(¤t->sighand->siglock, flags); } if (err < 0) goto reterr; err = p9_check_errors(c, req); trace_9p_client_res(c, type, req->rc.tag, err); if (!err) return req; reterr: p9_req_put(c, req); return ERR_PTR(safe_errno(err)); } /** * p9_client_zc_rpc - issue a request and wait for a response * @c: client session * @type: type of request * @uidata: destination for zero copy read * @uodata: source for zero copy write * @inlen: read buffer size * @olen: write buffer size * @in_hdrlen: reader header size, This is the size of response protocol data * @fmt: protocol format string (see protocol.c) * * Returns request structure (which client must free using p9_req_put) */ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type, struct iov_iter *uidata, struct iov_iter *uodata, int inlen, int olen, int in_hdrlen, const char *fmt, ...) { va_list ap; int sigpending, err; unsigned long flags; struct p9_req_t *req; va_start(ap, fmt); /* We allocate a inline protocol data of only 4k bytes. * The actual content is passed in zero-copy fashion. */ req = p9_client_prepare_req(c, type, P9_ZC_HDR_SZ, P9_ZC_HDR_SZ, fmt, ap); va_end(ap); if (IS_ERR(req)) return req; req->tc.zc = true; req->rc.zc = true; if (signal_pending(current)) { sigpending = 1; clear_thread_flag(TIF_SIGPENDING); } else { sigpending = 0; } err = c->trans_mod->zc_request(c, req, uidata, uodata, inlen, olen, in_hdrlen); if (err < 0) { if (err == -EIO) c->status = Disconnected; if (err != -ERESTARTSYS) goto recalc_sigpending; } if (READ_ONCE(req->status) == REQ_STATUS_ERROR) { p9_debug(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err); err = req->t_err; } if (err == -ERESTARTSYS && c->status == Connected) { p9_debug(P9_DEBUG_MUX, "flushing\n"); sigpending = 1; clear_thread_flag(TIF_SIGPENDING); if (c->trans_mod->cancel(c, req)) p9_client_flush(c, req); /* if we received the response anyway, don't signal error */ if (READ_ONCE(req->status) == REQ_STATUS_RCVD) err = 0; } recalc_sigpending: if (sigpending) { spin_lock_irqsave(¤t->sighand->siglock, flags); recalc_sigpending(); spin_unlock_irqrestore(¤t->sighand->siglock, flags); } if (err < 0) goto reterr; err = p9_check_errors(c, req); trace_9p_client_res(c, type, req->rc.tag, err); if (!err) return req; reterr: p9_req_put(c, req); return ERR_PTR(safe_errno(err)); } static struct p9_fid *p9_fid_create(struct p9_client *clnt) { int ret; struct p9_fid *fid; p9_debug(P9_DEBUG_FID, "clnt %p\n", clnt); fid = kzalloc(sizeof(*fid), GFP_KERNEL); if (!fid) return NULL; fid->mode = -1; fid->uid = current_fsuid(); fid->clnt = clnt; refcount_set(&fid->count, 1); idr_preload(GFP_KERNEL); spin_lock_irq(&clnt->lock); ret = idr_alloc_u32(&clnt->fids, fid, &fid->fid, P9_NOFID - 1, GFP_NOWAIT); spin_unlock_irq(&clnt->lock); idr_preload_end(); if (!ret) { trace_9p_fid_ref(fid, P9_FID_REF_CREATE); return fid; } kfree(fid); return NULL; } static void p9_fid_destroy(struct p9_fid *fid) { struct p9_client *clnt; unsigned long flags; p9_debug(P9_DEBUG_FID, "fid %d\n", fid->fid); trace_9p_fid_ref(fid, P9_FID_REF_DESTROY); clnt = fid->clnt; spin_lock_irqsave(&clnt->lock, flags); idr_remove(&clnt->fids, fid->fid); spin_unlock_irqrestore(&clnt->lock, flags); kfree(fid->rdir); kfree(fid); } /* We also need to export tracepoint symbols for tracepoint_enabled() */ EXPORT_TRACEPOINT_SYMBOL(9p_fid_ref); void do_trace_9p_fid_get(struct p9_fid *fid) { trace_9p_fid_ref(fid, P9_FID_REF_GET); } EXPORT_SYMBOL(do_trace_9p_fid_get); void do_trace_9p_fid_put(struct p9_fid *fid) { trace_9p_fid_ref(fid, P9_FID_REF_PUT); } EXPORT_SYMBOL(do_trace_9p_fid_put); static int p9_client_version(struct p9_client *c) { int err; struct p9_req_t *req; char *version = NULL; int msize; p9_debug(P9_DEBUG_9P, ">>> TVERSION msize %d protocol %d\n", c->msize, c->proto_version); switch (c->proto_version) { case p9_proto_2000L: req = p9_client_rpc(c, P9_TVERSION, "ds", c->msize, "9P2000.L"); break; case p9_proto_2000u: req = p9_client_rpc(c, P9_TVERSION, "ds", c->msize, "9P2000.u"); break; case p9_proto_legacy: req = p9_client_rpc(c, P9_TVERSION, "ds", c->msize, "9P2000"); break; default: return -EINVAL; } if (IS_ERR(req)) return PTR_ERR(req); err = p9pdu_readf(&req->rc, c->proto_version, "ds", &msize, &version); if (err) { p9_debug(P9_DEBUG_9P, "version error %d\n", err); trace_9p_protocol_dump(c, &req->rc); goto error; } p9_debug(P9_DEBUG_9P, "<<< RVERSION msize %d %s\n", msize, version); if (!strncmp(version, "9P2000.L", 8)) { c->proto_version = p9_proto_2000L; } else if (!strncmp(version, "9P2000.u", 8)) { c->proto_version = p9_proto_2000u; } else if (!strncmp(version, "9P2000", 6)) { c->proto_version = p9_proto_legacy; } else { p9_debug(P9_DEBUG_ERROR, "server returned an unknown version: %s\n", version); err = -EREMOTEIO; goto error; } if (msize < 4096) { p9_debug(P9_DEBUG_ERROR, "server returned a msize < 4096: %d\n", msize); err = -EREMOTEIO; goto error; } if (msize < c->msize) c->msize = msize; error: kfree(version); p9_req_put(c, req); return err; } struct p9_client *p9_client_create(const char *dev_name, char *options) { int err; static atomic_t seqno = ATOMIC_INIT(0); struct p9_client *clnt; char *client_id; char *cache_name; clnt = kmalloc(sizeof(*clnt), GFP_KERNEL); if (!clnt) return ERR_PTR(-ENOMEM); clnt->trans_mod = NULL; clnt->trans = NULL; clnt->fcall_cache = NULL; client_id = utsname()->nodename; memcpy(clnt->name, client_id, strlen(client_id) + 1); spin_lock_init(&clnt->lock); idr_init(&clnt->fids); idr_init(&clnt->reqs); err = parse_opts(options, clnt); if (err < 0) goto free_client; if (!clnt->trans_mod) clnt->trans_mod = v9fs_get_default_trans(); if (!clnt->trans_mod) { err = -EPROTONOSUPPORT; p9_debug(P9_DEBUG_ERROR, "No transport defined or default transport\n"); goto free_client; } p9_debug(P9_DEBUG_MUX, "clnt %p trans %p msize %d protocol %d\n", clnt, clnt->trans_mod, clnt->msize, clnt->proto_version); err = clnt->trans_mod->create(clnt, dev_name, options); if (err) goto put_trans; if (clnt->msize > clnt->trans_mod->maxsize) { clnt->msize = clnt->trans_mod->maxsize; pr_info("Limiting 'msize' to %d as this is the maximum " "supported by transport %s\n", clnt->msize, clnt->trans_mod->name ); } if (clnt->msize < 4096) { p9_debug(P9_DEBUG_ERROR, "Please specify a msize of at least 4k\n"); err = -EINVAL; goto close_trans; } err = p9_client_version(clnt); if (err) goto close_trans; cache_name = kasprintf(GFP_KERNEL, "9p-fcall-cache-%u", atomic_inc_return(&seqno)); if (!cache_name) { err = -ENOMEM; goto close_trans; } /* P9_HDRSZ + 4 is the smallest packet header we can have that is * followed by data accessed from userspace by read */ clnt->fcall_cache = kmem_cache_create_usercopy(cache_name, clnt->msize, 0, 0, P9_HDRSZ + 4, clnt->msize - (P9_HDRSZ + 4), NULL); kfree(cache_name); return clnt; close_trans: clnt->trans_mod->close(clnt); put_trans: v9fs_put_trans(clnt->trans_mod); free_client: kfree(clnt); return ERR_PTR(err); } EXPORT_SYMBOL(p9_client_create); void p9_client_destroy(struct p9_client *clnt) { struct p9_fid *fid; int id; p9_debug(P9_DEBUG_MUX, "clnt %p\n", clnt); if (clnt->trans_mod) clnt->trans_mod->close(clnt); v9fs_put_trans(clnt->trans_mod); idr_for_each_entry(&clnt->fids, fid, id) { pr_info("Found fid %d not clunked\n", fid->fid); p9_fid_destroy(fid); } p9_tag_cleanup(clnt); kmem_cache_destroy(clnt->fcall_cache); kfree(clnt); } EXPORT_SYMBOL(p9_client_destroy); void p9_client_disconnect(struct p9_client *clnt) { p9_debug(P9_DEBUG_9P, "clnt %p\n", clnt); clnt->status = Disconnected; } EXPORT_SYMBOL(p9_client_disconnect); void p9_client_begin_disconnect(struct p9_client *clnt) { p9_debug(P9_DEBUG_9P, "clnt %p\n", clnt); clnt->status = BeginDisconnect; } EXPORT_SYMBOL(p9_client_begin_disconnect); struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid, const char *uname, kuid_t n_uname, const char *aname) { int err; struct p9_req_t *req; struct p9_fid *fid; struct p9_qid qid; p9_debug(P9_DEBUG_9P, ">>> TATTACH afid %d uname %s aname %s\n", afid ? afid->fid : -1, uname, aname); fid = p9_fid_create(clnt); if (!fid) { err = -ENOMEM; goto error; } fid->uid = n_uname; req = p9_client_rpc(clnt, P9_TATTACH, "ddss?u", fid->fid, afid ? afid->fid : P9_NOFID, uname, aname, n_uname); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", &qid); if (err) { trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RATTACH qid %x.%llx.%x\n", qid.type, qid.path, qid.version); memmove(&fid->qid, &qid, sizeof(struct p9_qid)); p9_req_put(clnt, req); return fid; error: if (fid) p9_fid_destroy(fid); return ERR_PTR(err); } EXPORT_SYMBOL(p9_client_attach); struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname, const unsigned char * const *wnames, int clone) { int err; struct p9_client *clnt; struct p9_fid *fid; struct p9_qid *wqids; struct p9_req_t *req; u16 nwqids, count; wqids = NULL; clnt = oldfid->clnt; if (clone) { fid = p9_fid_create(clnt); if (!fid) { err = -ENOMEM; goto error; } fid->uid = oldfid->uid; } else { fid = oldfid; } p9_debug(P9_DEBUG_9P, ">>> TWALK fids %d,%d nwname %ud wname[0] %s\n", oldfid->fid, fid->fid, nwname, wnames ? wnames[0] : NULL); req = p9_client_rpc(clnt, P9_TWALK, "ddT", oldfid->fid, fid->fid, nwname, wnames); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "R", &nwqids, &wqids); if (err) { trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); goto clunk_fid; } p9_req_put(clnt, req); p9_debug(P9_DEBUG_9P, "<<< RWALK nwqid %d:\n", nwqids); if (nwqids != nwname) { err = -ENOENT; goto clunk_fid; } for (count = 0; count < nwqids; count++) p9_debug(P9_DEBUG_9P, "<<< [%d] %x.%llx.%x\n", count, wqids[count].type, wqids[count].path, wqids[count].version); if (nwname) memmove(&fid->qid, &wqids[nwqids - 1], sizeof(struct p9_qid)); else memmove(&fid->qid, &oldfid->qid, sizeof(struct p9_qid)); kfree(wqids); return fid; clunk_fid: kfree(wqids); p9_fid_put(fid); fid = NULL; error: if (fid && fid != oldfid) p9_fid_destroy(fid); return ERR_PTR(err); } EXPORT_SYMBOL(p9_client_walk); int p9_client_open(struct p9_fid *fid, int mode) { int err; struct p9_client *clnt; struct p9_req_t *req; struct p9_qid qid; int iounit; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> %s fid %d mode %d\n", p9_is_proto_dotl(clnt) ? "TLOPEN" : "TOPEN", fid->fid, mode); if (fid->mode != -1) return -EINVAL; if (p9_is_proto_dotl(clnt)) req = p9_client_rpc(clnt, P9_TLOPEN, "dd", fid->fid, mode & P9L_MODE_MASK); else req = p9_client_rpc(clnt, P9_TOPEN, "db", fid->fid, mode & P9L_MODE_MASK); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "Qd", &qid, &iounit); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto free_and_error; } p9_debug(P9_DEBUG_9P, "<<< %s qid %x.%llx.%x iounit %x\n", p9_is_proto_dotl(clnt) ? "RLOPEN" : "ROPEN", qid.type, qid.path, qid.version, iounit); memmove(&fid->qid, &qid, sizeof(struct p9_qid)); fid->mode = mode; fid->iounit = iounit; free_and_error: p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_open); int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32 mode, kgid_t gid, struct p9_qid *qid) { int err; struct p9_client *clnt; struct p9_req_t *req; int iounit; p9_debug(P9_DEBUG_9P, ">>> TLCREATE fid %d name %s flags %d mode %d gid %d\n", ofid->fid, name, flags, mode, from_kgid(&init_user_ns, gid)); clnt = ofid->clnt; if (ofid->mode != -1) return -EINVAL; req = p9_client_rpc(clnt, P9_TLCREATE, "dsddg", ofid->fid, name, flags, mode & P9L_MODE_MASK, gid); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "Qd", qid, &iounit); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto free_and_error; } p9_debug(P9_DEBUG_9P, "<<< RLCREATE qid %x.%llx.%x iounit %x\n", qid->type, qid->path, qid->version, iounit); memmove(&ofid->qid, qid, sizeof(struct p9_qid)); ofid->mode = flags; ofid->iounit = iounit; free_and_error: p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_create_dotl); int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode, char *extension) { int err; struct p9_client *clnt; struct p9_req_t *req; struct p9_qid qid; int iounit; p9_debug(P9_DEBUG_9P, ">>> TCREATE fid %d name %s perm %d mode %d\n", fid->fid, name, perm, mode); clnt = fid->clnt; if (fid->mode != -1) return -EINVAL; req = p9_client_rpc(clnt, P9_TCREATE, "dsdb?s", fid->fid, name, perm, mode & P9L_MODE_MASK, extension); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "Qd", &qid, &iounit); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto free_and_error; } p9_debug(P9_DEBUG_9P, "<<< RCREATE qid %x.%llx.%x iounit %x\n", qid.type, qid.path, qid.version, iounit); memmove(&fid->qid, &qid, sizeof(struct p9_qid)); fid->mode = mode; fid->iounit = iounit; free_and_error: p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_fcreate); int p9_client_symlink(struct p9_fid *dfid, const char *name, const char *symtgt, kgid_t gid, struct p9_qid *qid) { int err; struct p9_client *clnt; struct p9_req_t *req; p9_debug(P9_DEBUG_9P, ">>> TSYMLINK dfid %d name %s symtgt %s\n", dfid->fid, name, symtgt); clnt = dfid->clnt; req = p9_client_rpc(clnt, P9_TSYMLINK, "dssg", dfid->fid, name, symtgt, gid); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", qid); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto free_and_error; } p9_debug(P9_DEBUG_9P, "<<< RSYMLINK qid %x.%llx.%x\n", qid->type, qid->path, qid->version); free_and_error: p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_symlink); int p9_client_link(struct p9_fid *dfid, struct p9_fid *oldfid, const char *newname) { struct p9_client *clnt; struct p9_req_t *req; p9_debug(P9_DEBUG_9P, ">>> TLINK dfid %d oldfid %d newname %s\n", dfid->fid, oldfid->fid, newname); clnt = dfid->clnt; req = p9_client_rpc(clnt, P9_TLINK, "dds", dfid->fid, oldfid->fid, newname); if (IS_ERR(req)) return PTR_ERR(req); p9_debug(P9_DEBUG_9P, "<<< RLINK\n"); p9_req_put(clnt, req); return 0; } EXPORT_SYMBOL(p9_client_link); int p9_client_fsync(struct p9_fid *fid, int datasync) { int err = 0; struct p9_client *clnt; struct p9_req_t *req; p9_debug(P9_DEBUG_9P, ">>> TFSYNC fid %d datasync:%d\n", fid->fid, datasync); clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TFSYNC, "dd", fid->fid, datasync); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RFSYNC fid %d\n", fid->fid); p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_fsync); int p9_client_clunk(struct p9_fid *fid) { int err = 0; struct p9_client *clnt; struct p9_req_t *req; int retries = 0; again: p9_debug(P9_DEBUG_9P, ">>> TCLUNK fid %d (try %d)\n", fid->fid, retries); clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TCLUNK, "d", fid->fid); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RCLUNK fid %d\n", fid->fid); p9_req_put(clnt, req); error: /* Fid is not valid even after a failed clunk * If interrupted, retry once then give up and * leak fid until umount. */ if (err == -ERESTARTSYS) { if (retries++ == 0) goto again; } else { p9_fid_destroy(fid); } return err; } EXPORT_SYMBOL(p9_client_clunk); int p9_client_remove(struct p9_fid *fid) { int err = 0; struct p9_client *clnt; struct p9_req_t *req; p9_debug(P9_DEBUG_9P, ">>> TREMOVE fid %d\n", fid->fid); clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TREMOVE, "d", fid->fid); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RREMOVE fid %d\n", fid->fid); p9_req_put(clnt, req); error: if (err == -ERESTARTSYS) p9_fid_put(fid); else p9_fid_destroy(fid); return err; } EXPORT_SYMBOL(p9_client_remove); int p9_client_unlinkat(struct p9_fid *dfid, const char *name, int flags) { int err = 0; struct p9_req_t *req; struct p9_client *clnt; p9_debug(P9_DEBUG_9P, ">>> TUNLINKAT fid %d %s %d\n", dfid->fid, name, flags); clnt = dfid->clnt; req = p9_client_rpc(clnt, P9_TUNLINKAT, "dsd", dfid->fid, name, flags); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RUNLINKAT fid %d %s\n", dfid->fid, name); p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_unlinkat); int p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err) { int total = 0; *err = 0; while (iov_iter_count(to)) { int count; count = p9_client_read_once(fid, offset, to, err); if (!count || *err) break; offset += count; total += count; } return total; } EXPORT_SYMBOL(p9_client_read); int p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err) { struct p9_client *clnt = fid->clnt; struct p9_req_t *req; int count = iov_iter_count(to); int rsize, received, non_zc = 0; char *dataptr; *err = 0; p9_debug(P9_DEBUG_9P, ">>> TREAD fid %d offset %llu %zu\n", fid->fid, offset, iov_iter_count(to)); rsize = fid->iounit; if (!rsize || rsize > clnt->msize - P9_IOHDRSZ) rsize = clnt->msize - P9_IOHDRSZ; if (count < rsize) rsize = count; /* Don't bother zerocopy for small IO (< 1024) */ if (clnt->trans_mod->zc_request && rsize > 1024) { /* response header len is 11 * PDU Header(7) + IO Size (4) */ req = p9_client_zc_rpc(clnt, P9_TREAD, to, NULL, rsize, 0, 11, "dqd", fid->fid, offset, rsize); } else { non_zc = 1; req = p9_client_rpc(clnt, P9_TREAD, "dqd", fid->fid, offset, rsize); } if (IS_ERR(req)) { *err = PTR_ERR(req); if (!non_zc) iov_iter_revert(to, count - iov_iter_count(to)); return 0; } *err = p9pdu_readf(&req->rc, clnt->proto_version, "D", &received, &dataptr); if (*err) { if (!non_zc) iov_iter_revert(to, count - iov_iter_count(to)); trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); return 0; } if (rsize < received) { pr_err("bogus RREAD count (%d > %d)\n", received, rsize); received = rsize; } p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", received); if (non_zc) { int n = copy_to_iter(dataptr, received, to); if (n != received) { *err = -EFAULT; p9_req_put(clnt, req); return n; } } else { iov_iter_revert(to, count - received - iov_iter_count(to)); } p9_req_put(clnt, req); return received; } EXPORT_SYMBOL(p9_client_read_once); int p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err) { struct p9_client *clnt = fid->clnt; struct p9_req_t *req; int total = 0; *err = 0; while (iov_iter_count(from)) { int count = iov_iter_count(from); int rsize = fid->iounit; int written; if (!rsize || rsize > clnt->msize - P9_IOHDRSZ) rsize = clnt->msize - P9_IOHDRSZ; if (count < rsize) rsize = count; p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %d (/%d)\n", fid->fid, offset, rsize, count); /* Don't bother zerocopy for small IO (< 1024) */ if (clnt->trans_mod->zc_request && rsize > 1024) { req = p9_client_zc_rpc(clnt, P9_TWRITE, NULL, from, 0, rsize, P9_ZC_HDR_SZ, "dqd", fid->fid, offset, rsize); } else { req = p9_client_rpc(clnt, P9_TWRITE, "dqV", fid->fid, offset, rsize, from); } if (IS_ERR(req)) { iov_iter_revert(from, count - iov_iter_count(from)); *err = PTR_ERR(req); break; } *err = p9pdu_readf(&req->rc, clnt->proto_version, "d", &written); if (*err) { iov_iter_revert(from, count - iov_iter_count(from)); trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); break; } if (rsize < written) { pr_err("bogus RWRITE count (%d > %d)\n", written, rsize); written = rsize; } p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", written); p9_req_put(clnt, req); iov_iter_revert(from, count - written - iov_iter_count(from)); total += written; offset += written; } return total; } EXPORT_SYMBOL(p9_client_write); void p9_client_write_subreq(struct netfs_io_subrequest *subreq) { struct netfs_io_request *wreq = subreq->rreq; struct p9_fid *fid = wreq->netfs_priv; struct p9_client *clnt = fid->clnt; struct p9_req_t *req; unsigned long long start = subreq->start + subreq->transferred; int written, len = subreq->len - subreq->transferred; int err; p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu len %d\n", fid->fid, start, len); /* Don't bother zerocopy for small IO (< 1024) */ if (clnt->trans_mod->zc_request && len > 1024) { req = p9_client_zc_rpc(clnt, P9_TWRITE, NULL, &subreq->io_iter, 0, wreq->len, P9_ZC_HDR_SZ, "dqd", fid->fid, start, len); } else { req = p9_client_rpc(clnt, P9_TWRITE, "dqV", fid->fid, start, len, &subreq->io_iter); } if (IS_ERR(req)) { netfs_write_subrequest_terminated(subreq, PTR_ERR(req), false); return; } err = p9pdu_readf(&req->rc, clnt->proto_version, "d", &written); if (err) { trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); netfs_write_subrequest_terminated(subreq, err, false); return; } if (written > len) { pr_err("bogus RWRITE count (%d > %u)\n", written, len); written = len; } p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", len); p9_req_put(clnt, req); netfs_write_subrequest_terminated(subreq, written, false); } EXPORT_SYMBOL(p9_client_write_subreq); struct p9_wstat *p9_client_stat(struct p9_fid *fid) { int err; struct p9_client *clnt; struct p9_wstat *ret; struct p9_req_t *req; u16 ignored; p9_debug(P9_DEBUG_9P, ">>> TSTAT fid %d\n", fid->fid); ret = kmalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return ERR_PTR(-ENOMEM); clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TSTAT, "d", fid->fid); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "wS", &ignored, ret); if (err) { trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RSTAT sz=%x type=%x dev=%x qid=%x.%llx.%x\n" "<<< mode=%8.8x atime=%8.8x mtime=%8.8x length=%llx\n" "<<< name=%s uid=%s gid=%s muid=%s extension=(%s)\n" "<<< uid=%d gid=%d n_muid=%d\n", ret->size, ret->type, ret->dev, ret->qid.type, ret->qid.path, ret->qid.version, ret->mode, ret->atime, ret->mtime, ret->length, ret->name, ret->uid, ret->gid, ret->muid, ret->extension, from_kuid(&init_user_ns, ret->n_uid), from_kgid(&init_user_ns, ret->n_gid), from_kuid(&init_user_ns, ret->n_muid)); p9_req_put(clnt, req); return ret; error: kfree(ret); return ERR_PTR(err); } EXPORT_SYMBOL(p9_client_stat); struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid, u64 request_mask) { int err; struct p9_client *clnt; struct p9_stat_dotl *ret; struct p9_req_t *req; p9_debug(P9_DEBUG_9P, ">>> TGETATTR fid %d, request_mask %lld\n", fid->fid, request_mask); ret = kmalloc(sizeof(*ret), GFP_KERNEL); if (!ret) return ERR_PTR(-ENOMEM); clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TGETATTR, "dq", fid->fid, request_mask); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "A", ret); if (err) { trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RGETATTR st_result_mask=%lld\n" "<<< qid=%x.%llx.%x\n" "<<< st_mode=%8.8x st_nlink=%llu\n" "<<< st_uid=%d st_gid=%d\n" "<<< st_rdev=%llx st_size=%llx st_blksize=%llu st_blocks=%llu\n" "<<< st_atime_sec=%lld st_atime_nsec=%lld\n" "<<< st_mtime_sec=%lld st_mtime_nsec=%lld\n" "<<< st_ctime_sec=%lld st_ctime_nsec=%lld\n" "<<< st_btime_sec=%lld st_btime_nsec=%lld\n" "<<< st_gen=%lld st_data_version=%lld\n", ret->st_result_mask, ret->qid.type, ret->qid.path, ret->qid.version, ret->st_mode, ret->st_nlink, from_kuid(&init_user_ns, ret->st_uid), from_kgid(&init_user_ns, ret->st_gid), ret->st_rdev, ret->st_size, ret->st_blksize, ret->st_blocks, ret->st_atime_sec, ret->st_atime_nsec, ret->st_mtime_sec, ret->st_mtime_nsec, ret->st_ctime_sec, ret->st_ctime_nsec, ret->st_btime_sec, ret->st_btime_nsec, ret->st_gen, ret->st_data_version); p9_req_put(clnt, req); return ret; error: kfree(ret); return ERR_PTR(err); } EXPORT_SYMBOL(p9_client_getattr_dotl); static int p9_client_statsize(struct p9_wstat *wst, int proto_version) { int ret; /* NOTE: size shouldn't include its own length */ /* size[2] type[2] dev[4] qid[13] */ /* mode[4] atime[4] mtime[4] length[8]*/ /* name[s] uid[s] gid[s] muid[s] */ ret = 2 + 4 + 13 + 4 + 4 + 4 + 8 + 2 + 2 + 2 + 2; if (wst->name) ret += strlen(wst->name); if (wst->uid) ret += strlen(wst->uid); if (wst->gid) ret += strlen(wst->gid); if (wst->muid) ret += strlen(wst->muid); if (proto_version == p9_proto_2000u || proto_version == p9_proto_2000L) { /* extension[s] n_uid[4] n_gid[4] n_muid[4] */ ret += 2 + 4 + 4 + 4; if (wst->extension) ret += strlen(wst->extension); } return ret; } int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst) { int err = 0; struct p9_req_t *req; struct p9_client *clnt; clnt = fid->clnt; wst->size = p9_client_statsize(wst, clnt->proto_version); p9_debug(P9_DEBUG_9P, ">>> TWSTAT fid %d\n", fid->fid); p9_debug(P9_DEBUG_9P, " sz=%x type=%x dev=%x qid=%x.%llx.%x\n" " mode=%8.8x atime=%8.8x mtime=%8.8x length=%llx\n" " name=%s uid=%s gid=%s muid=%s extension=(%s)\n" " uid=%d gid=%d n_muid=%d\n", wst->size, wst->type, wst->dev, wst->qid.type, wst->qid.path, wst->qid.version, wst->mode, wst->atime, wst->mtime, wst->length, wst->name, wst->uid, wst->gid, wst->muid, wst->extension, from_kuid(&init_user_ns, wst->n_uid), from_kgid(&init_user_ns, wst->n_gid), from_kuid(&init_user_ns, wst->n_muid)); req = p9_client_rpc(clnt, P9_TWSTAT, "dwS", fid->fid, wst->size + 2, wst); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RWSTAT fid %d\n", fid->fid); p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_wstat); int p9_client_setattr(struct p9_fid *fid, struct p9_iattr_dotl *p9attr) { int err = 0; struct p9_req_t *req; struct p9_client *clnt; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TSETATTR fid %d\n", fid->fid); p9_debug(P9_DEBUG_9P, " valid=%x mode=%x uid=%d gid=%d size=%lld\n", p9attr->valid, p9attr->mode, from_kuid(&init_user_ns, p9attr->uid), from_kgid(&init_user_ns, p9attr->gid), p9attr->size); p9_debug(P9_DEBUG_9P, " atime_sec=%lld atime_nsec=%lld\n", p9attr->atime_sec, p9attr->atime_nsec); p9_debug(P9_DEBUG_9P, " mtime_sec=%lld mtime_nsec=%lld\n", p9attr->mtime_sec, p9attr->mtime_nsec); req = p9_client_rpc(clnt, P9_TSETATTR, "dI", fid->fid, p9attr); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RSETATTR fid %d\n", fid->fid); p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_setattr); int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb) { int err; struct p9_req_t *req; struct p9_client *clnt; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TSTATFS fid %d\n", fid->fid); req = p9_client_rpc(clnt, P9_TSTATFS, "d", fid->fid); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "ddqqqqqqd", &sb->type, &sb->bsize, &sb->blocks, &sb->bfree, &sb->bavail, &sb->files, &sb->ffree, &sb->fsid, &sb->namelen); if (err) { trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RSTATFS fid %d type 0x%x bsize %u blocks %llu bfree %llu bavail %llu files %llu ffree %llu fsid %llu namelen %u\n", fid->fid, sb->type, sb->bsize, sb->blocks, sb->bfree, sb->bavail, sb->files, sb->ffree, sb->fsid, sb->namelen); p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_statfs); int p9_client_rename(struct p9_fid *fid, struct p9_fid *newdirfid, const char *name) { int err = 0; struct p9_req_t *req; struct p9_client *clnt; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TRENAME fid %d newdirfid %d name %s\n", fid->fid, newdirfid->fid, name); req = p9_client_rpc(clnt, P9_TRENAME, "dds", fid->fid, newdirfid->fid, name); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RRENAME fid %d\n", fid->fid); p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_rename); int p9_client_renameat(struct p9_fid *olddirfid, const char *old_name, struct p9_fid *newdirfid, const char *new_name) { int err = 0; struct p9_req_t *req; struct p9_client *clnt; clnt = olddirfid->clnt; p9_debug(P9_DEBUG_9P, ">>> TRENAMEAT olddirfid %d old name %s newdirfid %d new name %s\n", olddirfid->fid, old_name, newdirfid->fid, new_name); req = p9_client_rpc(clnt, P9_TRENAMEAT, "dsds", olddirfid->fid, old_name, newdirfid->fid, new_name); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RRENAMEAT newdirfid %d new name %s\n", newdirfid->fid, new_name); p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_renameat); /* An xattrwalk without @attr_name gives the fid for the lisxattr namespace */ struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid, const char *attr_name, u64 *attr_size) { int err; struct p9_req_t *req; struct p9_client *clnt; struct p9_fid *attr_fid; clnt = file_fid->clnt; attr_fid = p9_fid_create(clnt); if (!attr_fid) { err = -ENOMEM; goto error; } p9_debug(P9_DEBUG_9P, ">>> TXATTRWALK file_fid %d, attr_fid %d name '%s'\n", file_fid->fid, attr_fid->fid, attr_name); req = p9_client_rpc(clnt, P9_TXATTRWALK, "dds", file_fid->fid, attr_fid->fid, attr_name); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "q", attr_size); if (err) { trace_9p_protocol_dump(clnt, &req->rc); p9_req_put(clnt, req); goto clunk_fid; } p9_req_put(clnt, req); p9_debug(P9_DEBUG_9P, "<<< RXATTRWALK fid %d size %llu\n", attr_fid->fid, *attr_size); return attr_fid; clunk_fid: p9_fid_put(attr_fid); attr_fid = NULL; error: if (attr_fid && attr_fid != file_fid) p9_fid_destroy(attr_fid); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(p9_client_xattrwalk); int p9_client_xattrcreate(struct p9_fid *fid, const char *name, u64 attr_size, int flags) { int err = 0; struct p9_req_t *req; struct p9_client *clnt; p9_debug(P9_DEBUG_9P, ">>> TXATTRCREATE fid %d name %s size %llu flag %d\n", fid->fid, name, attr_size, flags); clnt = fid->clnt; req = p9_client_rpc(clnt, P9_TXATTRCREATE, "dsqd", fid->fid, name, attr_size, flags); if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } p9_debug(P9_DEBUG_9P, "<<< RXATTRCREATE fid %d\n", fid->fid); p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL_GPL(p9_client_xattrcreate); int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) { int err, rsize, non_zc = 0; struct p9_client *clnt; struct p9_req_t *req; char *dataptr; struct kvec kv = {.iov_base = data, .iov_len = count}; struct iov_iter to; iov_iter_kvec(&to, ITER_DEST, &kv, 1, count); p9_debug(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %d\n", fid->fid, offset, count); clnt = fid->clnt; rsize = fid->iounit; if (!rsize || rsize > clnt->msize - P9_READDIRHDRSZ) rsize = clnt->msize - P9_READDIRHDRSZ; if (count < rsize) rsize = count; /* Don't bother zerocopy for small IO (< 1024) */ if (clnt->trans_mod->zc_request && rsize > 1024) { /* response header len is 11 * PDU Header(7) + IO Size (4) */ req = p9_client_zc_rpc(clnt, P9_TREADDIR, &to, NULL, rsize, 0, 11, "dqd", fid->fid, offset, rsize); } else { non_zc = 1; req = p9_client_rpc(clnt, P9_TREADDIR, "dqd", fid->fid, offset, rsize); } if (IS_ERR(req)) { err = PTR_ERR(req); goto error; } err = p9pdu_readf(&req->rc, clnt->proto_version, "D", &count, &dataptr); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto free_and_error; } if (rsize < count) { pr_err("bogus RREADDIR count (%d > %d)\n", count, rsize); count = rsize; } p9_debug(P9_DEBUG_9P, "<<< RREADDIR count %d\n", count); if (non_zc) memmove(data, dataptr, count); p9_req_put(clnt, req); return count; free_and_error: p9_req_put(clnt, req); error: return err; } EXPORT_SYMBOL(p9_client_readdir); int p9_client_mknod_dotl(struct p9_fid *fid, const char *name, int mode, dev_t rdev, kgid_t gid, struct p9_qid *qid) { int err; struct p9_client *clnt; struct p9_req_t *req; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TMKNOD fid %d name %s mode %d major %d minor %d\n", fid->fid, name, mode, MAJOR(rdev), MINOR(rdev)); req = p9_client_rpc(clnt, P9_TMKNOD, "dsdddg", fid->fid, name, mode, MAJOR(rdev), MINOR(rdev), gid); if (IS_ERR(req)) return PTR_ERR(req); err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", qid); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto error; } p9_debug(P9_DEBUG_9P, "<<< RMKNOD qid %x.%llx.%x\n", qid->type, qid->path, qid->version); error: p9_req_put(clnt, req); return err; } EXPORT_SYMBOL(p9_client_mknod_dotl); int p9_client_mkdir_dotl(struct p9_fid *fid, const char *name, int mode, kgid_t gid, struct p9_qid *qid) { int err; struct p9_client *clnt; struct p9_req_t *req; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TMKDIR fid %d name %s mode %d gid %d\n", fid->fid, name, mode, from_kgid(&init_user_ns, gid)); req = p9_client_rpc(clnt, P9_TMKDIR, "dsdg", fid->fid, name, mode, gid); if (IS_ERR(req)) return PTR_ERR(req); err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", qid); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto error; } p9_debug(P9_DEBUG_9P, "<<< RMKDIR qid %x.%llx.%x\n", qid->type, qid->path, qid->version); error: p9_req_put(clnt, req); return err; } EXPORT_SYMBOL(p9_client_mkdir_dotl); int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status) { int err; struct p9_client *clnt; struct p9_req_t *req; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TLOCK fid %d type %i flags %d start %lld length %lld proc_id %d client_id %s\n", fid->fid, flock->type, flock->flags, flock->start, flock->length, flock->proc_id, flock->client_id); req = p9_client_rpc(clnt, P9_TLOCK, "dbdqqds", fid->fid, flock->type, flock->flags, flock->start, flock->length, flock->proc_id, flock->client_id); if (IS_ERR(req)) return PTR_ERR(req); err = p9pdu_readf(&req->rc, clnt->proto_version, "b", status); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto error; } p9_debug(P9_DEBUG_9P, "<<< RLOCK status %i\n", *status); error: p9_req_put(clnt, req); return err; } EXPORT_SYMBOL(p9_client_lock_dotl); int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *glock) { int err; struct p9_client *clnt; struct p9_req_t *req; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TGETLOCK fid %d, type %i start %lld length %lld proc_id %d client_id %s\n", fid->fid, glock->type, glock->start, glock->length, glock->proc_id, glock->client_id); req = p9_client_rpc(clnt, P9_TGETLOCK, "dbqqds", fid->fid, glock->type, glock->start, glock->length, glock->proc_id, glock->client_id); if (IS_ERR(req)) return PTR_ERR(req); err = p9pdu_readf(&req->rc, clnt->proto_version, "bqqds", &glock->type, &glock->start, &glock->length, &glock->proc_id, &glock->client_id); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto error; } p9_debug(P9_DEBUG_9P, "<<< RGETLOCK type %i start %lld length %lld proc_id %d client_id %s\n", glock->type, glock->start, glock->length, glock->proc_id, glock->client_id); error: p9_req_put(clnt, req); return err; } EXPORT_SYMBOL(p9_client_getlock_dotl); int p9_client_readlink(struct p9_fid *fid, char **target) { int err; struct p9_client *clnt; struct p9_req_t *req; clnt = fid->clnt; p9_debug(P9_DEBUG_9P, ">>> TREADLINK fid %d\n", fid->fid); req = p9_client_rpc(clnt, P9_TREADLINK, "d", fid->fid); if (IS_ERR(req)) return PTR_ERR(req); err = p9pdu_readf(&req->rc, clnt->proto_version, "s", target); if (err) { trace_9p_protocol_dump(clnt, &req->rc); goto error; } p9_debug(P9_DEBUG_9P, "<<< RREADLINK target %s\n", *target); error: p9_req_put(clnt, req); return err; } EXPORT_SYMBOL(p9_client_readlink); int __init p9_client_init(void) { p9_req_cache = KMEM_CACHE(p9_req_t, SLAB_TYPESAFE_BY_RCU); return p9_req_cache ? 0 : -ENOMEM; } void __exit p9_client_exit(void) { kmem_cache_destroy(p9_req_cache); } |
| 41 46 46 46 46 15 2 15 46 36 36 36 5 1 3 3 3 2 1 1 1 1 3 11 6 6 6 6 5 2 3 3 3 17 17 17 17 15 12 3 15 3 12 17 12 17 17 17 15 2 17 16 12 17 12 17 3 3 17 17 17 7 7 5 5 5 4 4 1 7 2 1 3 2 1 2 5 1 8 2 3 5 8 9 9 8 46 45 3 43 4 50 48 48 47 46 43 41 41 17 17 17 24 24 24 24 17 41 17 24 7 53 3 1 1 5 4 4 3 3 2 1 1 1 5 50 50 3 53 5 61 61 59 23 23 23 23 22 11 11 11 2 2 2 2 13 23 23 23 23 23 23 23 23 3 3 3 3 3 3 3 3 2 3 2 3 3 3 3 3 3 1 1 111 111 111 | 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 | /* * Copyright (c) 2016-2017, Mellanox Technologies. All rights reserved. * Copyright (c) 2016-2017, Dave Watson <davejwatson@fb.com>. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include <linux/module.h> #include <net/tcp.h> #include <net/inet_common.h> #include <linux/highmem.h> #include <linux/netdevice.h> #include <linux/sched/signal.h> #include <linux/inetdevice.h> #include <linux/inet_diag.h> #include <net/snmp.h> #include <net/tls.h> #include <net/tls_toe.h> #include "tls.h" MODULE_AUTHOR("Mellanox Technologies"); MODULE_DESCRIPTION("Transport Layer Security Support"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS_TCP_ULP("tls"); enum { TLSV4, TLSV6, TLS_NUM_PROTS, }; #define CHECK_CIPHER_DESC(cipher,ci) \ static_assert(cipher ## _IV_SIZE <= TLS_MAX_IV_SIZE); \ static_assert(cipher ## _SALT_SIZE <= TLS_MAX_SALT_SIZE); \ static_assert(cipher ## _REC_SEQ_SIZE <= TLS_MAX_REC_SEQ_SIZE); \ static_assert(cipher ## _TAG_SIZE == TLS_TAG_SIZE); \ static_assert(sizeof_field(struct ci, iv) == cipher ## _IV_SIZE); \ static_assert(sizeof_field(struct ci, key) == cipher ## _KEY_SIZE); \ static_assert(sizeof_field(struct ci, salt) == cipher ## _SALT_SIZE); \ static_assert(sizeof_field(struct ci, rec_seq) == cipher ## _REC_SEQ_SIZE); #define __CIPHER_DESC(ci) \ .iv_offset = offsetof(struct ci, iv), \ .key_offset = offsetof(struct ci, key), \ .salt_offset = offsetof(struct ci, salt), \ .rec_seq_offset = offsetof(struct ci, rec_seq), \ .crypto_info = sizeof(struct ci) #define CIPHER_DESC(cipher,ci,algname,_offloadable) [cipher - TLS_CIPHER_MIN] = { \ .nonce = cipher ## _IV_SIZE, \ .iv = cipher ## _IV_SIZE, \ .key = cipher ## _KEY_SIZE, \ .salt = cipher ## _SALT_SIZE, \ .tag = cipher ## _TAG_SIZE, \ .rec_seq = cipher ## _REC_SEQ_SIZE, \ .cipher_name = algname, \ .offloadable = _offloadable, \ __CIPHER_DESC(ci), \ } #define CIPHER_DESC_NONCE0(cipher,ci,algname,_offloadable) [cipher - TLS_CIPHER_MIN] = { \ .nonce = 0, \ .iv = cipher ## _IV_SIZE, \ .key = cipher ## _KEY_SIZE, \ .salt = cipher ## _SALT_SIZE, \ .tag = cipher ## _TAG_SIZE, \ .rec_seq = cipher ## _REC_SEQ_SIZE, \ .cipher_name = algname, \ .offloadable = _offloadable, \ __CIPHER_DESC(ci), \ } const struct tls_cipher_desc tls_cipher_desc[TLS_CIPHER_MAX + 1 - TLS_CIPHER_MIN] = { CIPHER_DESC(TLS_CIPHER_AES_GCM_128, tls12_crypto_info_aes_gcm_128, "gcm(aes)", true), CIPHER_DESC(TLS_CIPHER_AES_GCM_256, tls12_crypto_info_aes_gcm_256, "gcm(aes)", true), CIPHER_DESC(TLS_CIPHER_AES_CCM_128, tls12_crypto_info_aes_ccm_128, "ccm(aes)", false), CIPHER_DESC_NONCE0(TLS_CIPHER_CHACHA20_POLY1305, tls12_crypto_info_chacha20_poly1305, "rfc7539(chacha20,poly1305)", false), CIPHER_DESC(TLS_CIPHER_SM4_GCM, tls12_crypto_info_sm4_gcm, "gcm(sm4)", false), CIPHER_DESC(TLS_CIPHER_SM4_CCM, tls12_crypto_info_sm4_ccm, "ccm(sm4)", false), CIPHER_DESC(TLS_CIPHER_ARIA_GCM_128, tls12_crypto_info_aria_gcm_128, "gcm(aria)", false), CIPHER_DESC(TLS_CIPHER_ARIA_GCM_256, tls12_crypto_info_aria_gcm_256, "gcm(aria)", false), }; CHECK_CIPHER_DESC(TLS_CIPHER_AES_GCM_128, tls12_crypto_info_aes_gcm_128); CHECK_CIPHER_DESC(TLS_CIPHER_AES_GCM_256, tls12_crypto_info_aes_gcm_256); CHECK_CIPHER_DESC(TLS_CIPHER_AES_CCM_128, tls12_crypto_info_aes_ccm_128); CHECK_CIPHER_DESC(TLS_CIPHER_CHACHA20_POLY1305, tls12_crypto_info_chacha20_poly1305); CHECK_CIPHER_DESC(TLS_CIPHER_SM4_GCM, tls12_crypto_info_sm4_gcm); CHECK_CIPHER_DESC(TLS_CIPHER_SM4_CCM, tls12_crypto_info_sm4_ccm); CHECK_CIPHER_DESC(TLS_CIPHER_ARIA_GCM_128, tls12_crypto_info_aria_gcm_128); CHECK_CIPHER_DESC(TLS_CIPHER_ARIA_GCM_256, tls12_crypto_info_aria_gcm_256); static const struct proto *saved_tcpv6_prot; static DEFINE_MUTEX(tcpv6_prot_mutex); static const struct proto *saved_tcpv4_prot; static DEFINE_MUTEX(tcpv4_prot_mutex); static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; static struct proto_ops tls_proto_ops[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], const struct proto *base); void update_sk_prot(struct sock *sk, struct tls_context *ctx) { int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; WRITE_ONCE(sk->sk_prot, &tls_prots[ip_ver][ctx->tx_conf][ctx->rx_conf]); WRITE_ONCE(sk->sk_socket->ops, &tls_proto_ops[ip_ver][ctx->tx_conf][ctx->rx_conf]); } int wait_on_pending_writer(struct sock *sk, long *timeo) { DEFINE_WAIT_FUNC(wait, woken_wake_function); int ret, rc = 0; add_wait_queue(sk_sleep(sk), &wait); while (1) { if (!*timeo) { rc = -EAGAIN; break; } if (signal_pending(current)) { rc = sock_intr_errno(*timeo); break; } ret = sk_wait_event(sk, timeo, !READ_ONCE(sk->sk_write_pending), &wait); if (ret) { if (ret < 0) rc = ret; break; } } remove_wait_queue(sk_sleep(sk), &wait); return rc; } int tls_push_sg(struct sock *sk, struct tls_context *ctx, struct scatterlist *sg, u16 first_offset, int flags) { struct bio_vec bvec; struct msghdr msg = { .msg_flags = MSG_SPLICE_PAGES | flags, }; int ret = 0; struct page *p; size_t size; int offset = first_offset; size = sg->length - offset; offset += sg->offset; ctx->splicing_pages = true; while (1) { /* is sending application-limited? */ tcp_rate_check_app_limited(sk); p = sg_page(sg); retry: bvec_set_page(&bvec, p, size, offset); iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); ret = tcp_sendmsg_locked(sk, &msg, size); if (ret != size) { if (ret > 0) { offset += ret; size -= ret; goto retry; } offset -= sg->offset; ctx->partially_sent_offset = offset; ctx->partially_sent_record = (void *)sg; ctx->splicing_pages = false; return ret; } put_page(p); sk_mem_uncharge(sk, sg->length); sg = sg_next(sg); if (!sg) break; offset = sg->offset; size = sg->length; } ctx->splicing_pages = false; return 0; } static int tls_handle_open_record(struct sock *sk, int flags) { struct tls_context *ctx = tls_get_ctx(sk); if (tls_is_pending_open_record(ctx)) return ctx->push_pending_record(sk, flags); return 0; } int tls_process_cmsg(struct sock *sk, struct msghdr *msg, unsigned char *record_type) { struct cmsghdr *cmsg; int rc = -EINVAL; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_TLS) continue; switch (cmsg->cmsg_type) { case TLS_SET_RECORD_TYPE: if (cmsg->cmsg_len < CMSG_LEN(sizeof(*record_type))) return -EINVAL; if (msg->msg_flags & MSG_MORE) return -EINVAL; rc = tls_handle_open_record(sk, msg->msg_flags); if (rc) return rc; *record_type = *(unsigned char *)CMSG_DATA(cmsg); rc = 0; break; default: return -EINVAL; } } return rc; } int tls_push_partial_record(struct sock *sk, struct tls_context *ctx, int flags) { struct scatterlist *sg; u16 offset; sg = ctx->partially_sent_record; offset = ctx->partially_sent_offset; ctx->partially_sent_record = NULL; return tls_push_sg(sk, ctx, sg, offset, flags); } void tls_free_partial_record(struct sock *sk, struct tls_context *ctx) { struct scatterlist *sg; for (sg = ctx->partially_sent_record; sg; sg = sg_next(sg)) { put_page(sg_page(sg)); sk_mem_uncharge(sk, sg->length); } ctx->partially_sent_record = NULL; } static void tls_write_space(struct sock *sk) { struct tls_context *ctx = tls_get_ctx(sk); /* If splicing_pages call lower protocol write space handler * to ensure we wake up any waiting operations there. For example * if splicing pages where to call sk_wait_event. */ if (ctx->splicing_pages) { ctx->sk_write_space(sk); return; } #ifdef CONFIG_TLS_DEVICE if (ctx->tx_conf == TLS_HW) tls_device_write_space(sk, ctx); else #endif tls_sw_write_space(sk, ctx); ctx->sk_write_space(sk); } /** * tls_ctx_free() - free TLS ULP context * @sk: socket to with @ctx is attached * @ctx: TLS context structure * * Free TLS context. If @sk is %NULL caller guarantees that the socket * to which @ctx was attached has no outstanding references. */ void tls_ctx_free(struct sock *sk, struct tls_context *ctx) { if (!ctx) return; memzero_explicit(&ctx->crypto_send, sizeof(ctx->crypto_send)); memzero_explicit(&ctx->crypto_recv, sizeof(ctx->crypto_recv)); mutex_destroy(&ctx->tx_lock); if (sk) kfree_rcu(ctx, rcu); else kfree(ctx); } static void tls_sk_proto_cleanup(struct sock *sk, struct tls_context *ctx, long timeo) { if (unlikely(sk->sk_write_pending) && !wait_on_pending_writer(sk, &timeo)) tls_handle_open_record(sk, 0); /* We need these for tls_sw_fallback handling of other packets */ if (ctx->tx_conf == TLS_SW) { tls_sw_release_resources_tx(sk); TLS_DEC_STATS(sock_net(sk), LINUX_MIB_TLSCURRTXSW); } else if (ctx->tx_conf == TLS_HW) { tls_device_free_resources_tx(sk); TLS_DEC_STATS(sock_net(sk), LINUX_MIB_TLSCURRTXDEVICE); } if (ctx->rx_conf == TLS_SW) { tls_sw_release_resources_rx(sk); TLS_DEC_STATS(sock_net(sk), LINUX_MIB_TLSCURRRXSW); } else if (ctx->rx_conf == TLS_HW) { tls_device_offload_cleanup_rx(sk); TLS_DEC_STATS(sock_net(sk), LINUX_MIB_TLSCURRRXDEVICE); } } static void tls_sk_proto_close(struct sock *sk, long timeout) { struct inet_connection_sock *icsk = inet_csk(sk); struct tls_context *ctx = tls_get_ctx(sk); long timeo = sock_sndtimeo(sk, 0); bool free_ctx; if (ctx->tx_conf == TLS_SW) tls_sw_cancel_work_tx(ctx); lock_sock(sk); free_ctx = ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW; if (ctx->tx_conf != TLS_BASE || ctx->rx_conf != TLS_BASE) tls_sk_proto_cleanup(sk, ctx, timeo); write_lock_bh(&sk->sk_callback_lock); if (free_ctx) rcu_assign_pointer(icsk->icsk_ulp_data, NULL); WRITE_ONCE(sk->sk_prot, ctx->sk_proto); if (sk->sk_write_space == tls_write_space) sk->sk_write_space = ctx->sk_write_space; write_unlock_bh(&sk->sk_callback_lock); release_sock(sk); if (ctx->tx_conf == TLS_SW) tls_sw_free_ctx_tx(ctx); if (ctx->rx_conf == TLS_SW || ctx->rx_conf == TLS_HW) tls_sw_strparser_done(ctx); if (ctx->rx_conf == TLS_SW) tls_sw_free_ctx_rx(ctx); ctx->sk_proto->close(sk, timeout); if (free_ctx) tls_ctx_free(sk, ctx); } static __poll_t tls_sk_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait) { struct tls_sw_context_rx *ctx; struct tls_context *tls_ctx; struct sock *sk = sock->sk; struct sk_psock *psock; __poll_t mask = 0; u8 shutdown; int state; mask = tcp_poll(file, sock, wait); state = inet_sk_state_load(sk); shutdown = READ_ONCE(sk->sk_shutdown); if (unlikely(state != TCP_ESTABLISHED || shutdown & RCV_SHUTDOWN)) return mask; tls_ctx = tls_get_ctx(sk); ctx = tls_sw_ctx_rx(tls_ctx); psock = sk_psock_get(sk); if (skb_queue_empty_lockless(&ctx->rx_list) && !tls_strp_msg_ready(ctx) && sk_psock_queue_empty(psock)) mask &= ~(EPOLLIN | EPOLLRDNORM); if (psock) sk_psock_put(sk, psock); return mask; } static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, int __user *optlen, int tx) { int rc = 0; const struct tls_cipher_desc *cipher_desc; struct tls_context *ctx = tls_get_ctx(sk); struct tls_crypto_info *crypto_info; struct cipher_context *cctx; int len; if (get_user(len, optlen)) return -EFAULT; if (!optval || (len < sizeof(*crypto_info))) { rc = -EINVAL; goto out; } if (!ctx) { rc = -EBUSY; goto out; } /* get user crypto info */ if (tx) { crypto_info = &ctx->crypto_send.info; cctx = &ctx->tx; } else { crypto_info = &ctx->crypto_recv.info; cctx = &ctx->rx; } if (!TLS_CRYPTO_INFO_READY(crypto_info)) { rc = -EBUSY; goto out; } if (len == sizeof(*crypto_info)) { if (copy_to_user(optval, crypto_info, sizeof(*crypto_info))) rc = -EFAULT; goto out; } cipher_desc = get_cipher_desc(crypto_info->cipher_type); if (!cipher_desc || len != cipher_desc->crypto_info) { rc = -EINVAL; goto out; } memcpy(crypto_info_iv(crypto_info, cipher_desc), cctx->iv + cipher_desc->salt, cipher_desc->iv); memcpy(crypto_info_rec_seq(crypto_info, cipher_desc), cctx->rec_seq, cipher_desc->rec_seq); if (copy_to_user(optval, crypto_info, cipher_desc->crypto_info)) rc = -EFAULT; out: return rc; } static int do_tls_getsockopt_tx_zc(struct sock *sk, char __user *optval, int __user *optlen) { struct tls_context *ctx = tls_get_ctx(sk); unsigned int value; int len; if (get_user(len, optlen)) return -EFAULT; if (len != sizeof(value)) return -EINVAL; value = ctx->zerocopy_sendfile; if (copy_to_user(optval, &value, sizeof(value))) return -EFAULT; return 0; } static int do_tls_getsockopt_no_pad(struct sock *sk, char __user *optval, int __user *optlen) { struct tls_context *ctx = tls_get_ctx(sk); int value, len; if (ctx->prot_info.version != TLS_1_3_VERSION) return -EINVAL; if (get_user(len, optlen)) return -EFAULT; if (len < sizeof(value)) return -EINVAL; value = -EINVAL; if (ctx->rx_conf == TLS_SW || ctx->rx_conf == TLS_HW) value = ctx->rx_no_pad; if (value < 0) return value; if (put_user(sizeof(value), optlen)) return -EFAULT; if (copy_to_user(optval, &value, sizeof(value))) return -EFAULT; return 0; } static int do_tls_getsockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen) { int rc = 0; lock_sock(sk); switch (optname) { case TLS_TX: case TLS_RX: rc = do_tls_getsockopt_conf(sk, optval, optlen, optname == TLS_TX); break; case TLS_TX_ZEROCOPY_RO: rc = do_tls_getsockopt_tx_zc(sk, optval, optlen); break; case TLS_RX_EXPECT_NO_PAD: rc = do_tls_getsockopt_no_pad(sk, optval, optlen); break; default: rc = -ENOPROTOOPT; break; } release_sock(sk); return rc; } static int tls_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct tls_context *ctx = tls_get_ctx(sk); if (level != SOL_TLS) return ctx->sk_proto->getsockopt(sk, level, optname, optval, optlen); return do_tls_getsockopt(sk, optname, optval, optlen); } static int validate_crypto_info(const struct tls_crypto_info *crypto_info, const struct tls_crypto_info *alt_crypto_info) { if (crypto_info->version != TLS_1_2_VERSION && crypto_info->version != TLS_1_3_VERSION) return -EINVAL; switch (crypto_info->cipher_type) { case TLS_CIPHER_ARIA_GCM_128: case TLS_CIPHER_ARIA_GCM_256: if (crypto_info->version != TLS_1_2_VERSION) return -EINVAL; break; } /* Ensure that TLS version and ciphers are same in both directions */ if (TLS_CRYPTO_INFO_READY(alt_crypto_info)) { if (alt_crypto_info->version != crypto_info->version || alt_crypto_info->cipher_type != crypto_info->cipher_type) return -EINVAL; } return 0; } static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, unsigned int optlen, int tx) { struct tls_crypto_info *crypto_info; struct tls_crypto_info *alt_crypto_info; struct tls_context *ctx = tls_get_ctx(sk); const struct tls_cipher_desc *cipher_desc; union tls_crypto_context *crypto_ctx; int rc = 0; int conf; if (sockptr_is_null(optval) || (optlen < sizeof(*crypto_info))) return -EINVAL; if (tx) { crypto_ctx = &ctx->crypto_send; alt_crypto_info = &ctx->crypto_recv.info; } else { crypto_ctx = &ctx->crypto_recv; alt_crypto_info = &ctx->crypto_send.info; } crypto_info = &crypto_ctx->info; /* Currently we don't support set crypto info more than one time */ if (TLS_CRYPTO_INFO_READY(crypto_info)) return -EBUSY; rc = copy_from_sockptr(crypto_info, optval, sizeof(*crypto_info)); if (rc) { rc = -EFAULT; goto err_crypto_info; } rc = validate_crypto_info(crypto_info, alt_crypto_info); if (rc) goto err_crypto_info; cipher_desc = get_cipher_desc(crypto_info->cipher_type); if (!cipher_desc) { rc = -EINVAL; goto err_crypto_info; } if (optlen != cipher_desc->crypto_info) { rc = -EINVAL; goto err_crypto_info; } rc = copy_from_sockptr_offset(crypto_info + 1, optval, sizeof(*crypto_info), optlen - sizeof(*crypto_info)); if (rc) { rc = -EFAULT; goto err_crypto_info; } if (tx) { rc = tls_set_device_offload(sk); conf = TLS_HW; if (!rc) { TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSTXDEVICE); TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSCURRTXDEVICE); } else { rc = tls_set_sw_offload(sk, 1); if (rc) goto err_crypto_info; TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSTXSW); TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSCURRTXSW); conf = TLS_SW; } } else { rc = tls_set_device_offload_rx(sk, ctx); conf = TLS_HW; if (!rc) { TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXDEVICE); TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSCURRRXDEVICE); } else { rc = tls_set_sw_offload(sk, 0); if (rc) goto err_crypto_info; TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXSW); TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSCURRRXSW); conf = TLS_SW; } tls_sw_strparser_arm(sk, ctx); } if (tx) ctx->tx_conf = conf; else ctx->rx_conf = conf; update_sk_prot(sk, ctx); if (tx) { ctx->sk_write_space = sk->sk_write_space; sk->sk_write_space = tls_write_space; } else { struct tls_sw_context_rx *rx_ctx = tls_sw_ctx_rx(ctx); tls_strp_check_rcv(&rx_ctx->strp); } return 0; err_crypto_info: memzero_explicit(crypto_ctx, sizeof(*crypto_ctx)); return rc; } static int do_tls_setsockopt_tx_zc(struct sock *sk, sockptr_t optval, unsigned int optlen) { struct tls_context *ctx = tls_get_ctx(sk); unsigned int value; if (sockptr_is_null(optval) || optlen != sizeof(value)) return -EINVAL; if (copy_from_sockptr(&value, optval, sizeof(value))) return -EFAULT; if (value > 1) return -EINVAL; ctx->zerocopy_sendfile = value; return 0; } static int do_tls_setsockopt_no_pad(struct sock *sk, sockptr_t optval, unsigned int optlen) { struct tls_context *ctx = tls_get_ctx(sk); u32 val; int rc; if (ctx->prot_info.version != TLS_1_3_VERSION || sockptr_is_null(optval) || optlen < sizeof(val)) return -EINVAL; rc = copy_from_sockptr(&val, optval, sizeof(val)); if (rc) return -EFAULT; if (val > 1) return -EINVAL; rc = check_zeroed_sockptr(optval, sizeof(val), optlen - sizeof(val)); if (rc < 1) return rc == 0 ? -EINVAL : rc; lock_sock(sk); rc = -EINVAL; if (ctx->rx_conf == TLS_SW || ctx->rx_conf == TLS_HW) { ctx->rx_no_pad = val; tls_update_rx_zc_capable(ctx); rc = 0; } release_sock(sk); return rc; } static int do_tls_setsockopt(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen) { int rc = 0; switch (optname) { case TLS_TX: case TLS_RX: lock_sock(sk); rc = do_tls_setsockopt_conf(sk, optval, optlen, optname == TLS_TX); release_sock(sk); break; case TLS_TX_ZEROCOPY_RO: lock_sock(sk); rc = do_tls_setsockopt_tx_zc(sk, optval, optlen); release_sock(sk); break; case TLS_RX_EXPECT_NO_PAD: rc = do_tls_setsockopt_no_pad(sk, optval, optlen); break; default: rc = -ENOPROTOOPT; break; } return rc; } static int tls_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct tls_context *ctx = tls_get_ctx(sk); if (level != SOL_TLS) return ctx->sk_proto->setsockopt(sk, level, optname, optval, optlen); return do_tls_setsockopt(sk, optname, optval, optlen); } struct tls_context *tls_ctx_create(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tls_context *ctx; ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); if (!ctx) return NULL; mutex_init(&ctx->tx_lock); ctx->sk_proto = READ_ONCE(sk->sk_prot); ctx->sk = sk; /* Release semantic of rcu_assign_pointer() ensures that * ctx->sk_proto is visible before changing sk->sk_prot in * update_sk_prot(), and prevents reading uninitialized value in * tls_{getsockopt, setsockopt}. Note that we do not need a * read barrier in tls_{getsockopt,setsockopt} as there is an * address dependency between sk->sk_proto->{getsockopt,setsockopt} * and ctx->sk_proto. */ rcu_assign_pointer(icsk->icsk_ulp_data, ctx); return ctx; } static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG], const struct proto_ops *base) { ops[TLS_BASE][TLS_BASE] = *base; ops[TLS_SW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; ops[TLS_SW ][TLS_BASE].splice_eof = tls_sw_splice_eof; ops[TLS_BASE][TLS_SW ] = ops[TLS_BASE][TLS_BASE]; ops[TLS_BASE][TLS_SW ].splice_read = tls_sw_splice_read; ops[TLS_BASE][TLS_SW ].poll = tls_sk_poll; ops[TLS_BASE][TLS_SW ].read_sock = tls_sw_read_sock; ops[TLS_SW ][TLS_SW ] = ops[TLS_SW ][TLS_BASE]; ops[TLS_SW ][TLS_SW ].splice_read = tls_sw_splice_read; ops[TLS_SW ][TLS_SW ].poll = tls_sk_poll; ops[TLS_SW ][TLS_SW ].read_sock = tls_sw_read_sock; #ifdef CONFIG_TLS_DEVICE ops[TLS_HW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; ops[TLS_HW ][TLS_SW ] = ops[TLS_BASE][TLS_SW ]; ops[TLS_BASE][TLS_HW ] = ops[TLS_BASE][TLS_SW ]; ops[TLS_SW ][TLS_HW ] = ops[TLS_SW ][TLS_SW ]; ops[TLS_HW ][TLS_HW ] = ops[TLS_HW ][TLS_SW ]; #endif #ifdef CONFIG_TLS_TOE ops[TLS_HW_RECORD][TLS_HW_RECORD] = *base; #endif } static void tls_build_proto(struct sock *sk) { int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; struct proto *prot = READ_ONCE(sk->sk_prot); /* Build IPv6 TLS whenever the address of tcpv6 _prot changes */ if (ip_ver == TLSV6 && unlikely(prot != smp_load_acquire(&saved_tcpv6_prot))) { mutex_lock(&tcpv6_prot_mutex); if (likely(prot != saved_tcpv6_prot)) { build_protos(tls_prots[TLSV6], prot); build_proto_ops(tls_proto_ops[TLSV6], sk->sk_socket->ops); smp_store_release(&saved_tcpv6_prot, prot); } mutex_unlock(&tcpv6_prot_mutex); } if (ip_ver == TLSV4 && unlikely(prot != smp_load_acquire(&saved_tcpv4_prot))) { mutex_lock(&tcpv4_prot_mutex); if (likely(prot != saved_tcpv4_prot)) { build_protos(tls_prots[TLSV4], prot); build_proto_ops(tls_proto_ops[TLSV4], sk->sk_socket->ops); smp_store_release(&saved_tcpv4_prot, prot); } mutex_unlock(&tcpv4_prot_mutex); } } static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], const struct proto *base) { prot[TLS_BASE][TLS_BASE] = *base; prot[TLS_BASE][TLS_BASE].setsockopt = tls_setsockopt; prot[TLS_BASE][TLS_BASE].getsockopt = tls_getsockopt; prot[TLS_BASE][TLS_BASE].close = tls_sk_proto_close; prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; prot[TLS_SW][TLS_BASE].sendmsg = tls_sw_sendmsg; prot[TLS_SW][TLS_BASE].splice_eof = tls_sw_splice_eof; prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE]; prot[TLS_BASE][TLS_SW].recvmsg = tls_sw_recvmsg; prot[TLS_BASE][TLS_SW].sock_is_readable = tls_sw_sock_is_readable; prot[TLS_BASE][TLS_SW].close = tls_sk_proto_close; prot[TLS_SW][TLS_SW] = prot[TLS_SW][TLS_BASE]; prot[TLS_SW][TLS_SW].recvmsg = tls_sw_recvmsg; prot[TLS_SW][TLS_SW].sock_is_readable = tls_sw_sock_is_readable; prot[TLS_SW][TLS_SW].close = tls_sk_proto_close; #ifdef CONFIG_TLS_DEVICE prot[TLS_HW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; prot[TLS_HW][TLS_BASE].sendmsg = tls_device_sendmsg; prot[TLS_HW][TLS_BASE].splice_eof = tls_device_splice_eof; prot[TLS_HW][TLS_SW] = prot[TLS_BASE][TLS_SW]; prot[TLS_HW][TLS_SW].sendmsg = tls_device_sendmsg; prot[TLS_HW][TLS_SW].splice_eof = tls_device_splice_eof; prot[TLS_BASE][TLS_HW] = prot[TLS_BASE][TLS_SW]; prot[TLS_SW][TLS_HW] = prot[TLS_SW][TLS_SW]; prot[TLS_HW][TLS_HW] = prot[TLS_HW][TLS_SW]; #endif #ifdef CONFIG_TLS_TOE prot[TLS_HW_RECORD][TLS_HW_RECORD] = *base; prot[TLS_HW_RECORD][TLS_HW_RECORD].hash = tls_toe_hash; prot[TLS_HW_RECORD][TLS_HW_RECORD].unhash = tls_toe_unhash; #endif } static int tls_init(struct sock *sk) { struct tls_context *ctx; int rc = 0; tls_build_proto(sk); #ifdef CONFIG_TLS_TOE if (tls_toe_bypass(sk)) return 0; #endif /* The TLS ulp is currently supported only for TCP sockets * in ESTABLISHED state. * Supporting sockets in LISTEN state will require us * to modify the accept implementation to clone rather then * share the ulp context. */ if (sk->sk_state != TCP_ESTABLISHED) return -ENOTCONN; /* allocate tls context */ write_lock_bh(&sk->sk_callback_lock); ctx = tls_ctx_create(sk); if (!ctx) { rc = -ENOMEM; goto out; } ctx->tx_conf = TLS_BASE; ctx->rx_conf = TLS_BASE; update_sk_prot(sk, ctx); out: write_unlock_bh(&sk->sk_callback_lock); return rc; } static void tls_update(struct sock *sk, struct proto *p, void (*write_space)(struct sock *sk)) { struct tls_context *ctx; WARN_ON_ONCE(sk->sk_prot == p); ctx = tls_get_ctx(sk); if (likely(ctx)) { ctx->sk_write_space = write_space; ctx->sk_proto = p; } else { /* Pairs with lockless read in sk_clone_lock(). */ WRITE_ONCE(sk->sk_prot, p); sk->sk_write_space = write_space; } } static u16 tls_user_config(struct tls_context *ctx, bool tx) { u16 config = tx ? ctx->tx_conf : ctx->rx_conf; switch (config) { case TLS_BASE: return TLS_CONF_BASE; case TLS_SW: return TLS_CONF_SW; case TLS_HW: return TLS_CONF_HW; case TLS_HW_RECORD: return TLS_CONF_HW_RECORD; } return 0; } static int tls_get_info(struct sock *sk, struct sk_buff *skb) { u16 version, cipher_type; struct tls_context *ctx; struct nlattr *start; int err; start = nla_nest_start_noflag(skb, INET_ULP_INFO_TLS); if (!start) return -EMSGSIZE; rcu_read_lock(); ctx = rcu_dereference(inet_csk(sk)->icsk_ulp_data); if (!ctx) { err = 0; goto nla_failure; } version = ctx->prot_info.version; if (version) { err = nla_put_u16(skb, TLS_INFO_VERSION, version); if (err) goto nla_failure; } cipher_type = ctx->prot_info.cipher_type; if (cipher_type) { err = nla_put_u16(skb, TLS_INFO_CIPHER, cipher_type); if (err) goto nla_failure; } err = nla_put_u16(skb, TLS_INFO_TXCONF, tls_user_config(ctx, true)); if (err) goto nla_failure; err = nla_put_u16(skb, TLS_INFO_RXCONF, tls_user_config(ctx, false)); if (err) goto nla_failure; if (ctx->tx_conf == TLS_HW && ctx->zerocopy_sendfile) { err = nla_put_flag(skb, TLS_INFO_ZC_RO_TX); if (err) goto nla_failure; } if (ctx->rx_no_pad) { err = nla_put_flag(skb, TLS_INFO_RX_NO_PAD); if (err) goto nla_failure; } rcu_read_unlock(); nla_nest_end(skb, start); return 0; nla_failure: rcu_read_unlock(); nla_nest_cancel(skb, start); return err; } static size_t tls_get_info_size(const struct sock *sk) { size_t size = 0; size += nla_total_size(0) + /* INET_ULP_INFO_TLS */ nla_total_size(sizeof(u16)) + /* TLS_INFO_VERSION */ nla_total_size(sizeof(u16)) + /* TLS_INFO_CIPHER */ nla_total_size(sizeof(u16)) + /* TLS_INFO_RXCONF */ nla_total_size(sizeof(u16)) + /* TLS_INFO_TXCONF */ nla_total_size(0) + /* TLS_INFO_ZC_RO_TX */ nla_total_size(0) + /* TLS_INFO_RX_NO_PAD */ 0; return size; } static int __net_init tls_init_net(struct net *net) { int err; net->mib.tls_statistics = alloc_percpu(struct linux_tls_mib); if (!net->mib.tls_statistics) return -ENOMEM; err = tls_proc_init(net); if (err) goto err_free_stats; return 0; err_free_stats: free_percpu(net->mib.tls_statistics); return err; } static void __net_exit tls_exit_net(struct net *net) { tls_proc_fini(net); free_percpu(net->mib.tls_statistics); } static struct pernet_operations tls_proc_ops = { .init = tls_init_net, .exit = tls_exit_net, }; static struct tcp_ulp_ops tcp_tls_ulp_ops __read_mostly = { .name = "tls", .owner = THIS_MODULE, .init = tls_init, .update = tls_update, .get_info = tls_get_info, .get_info_size = tls_get_info_size, }; static int __init tls_register(void) { int err; err = register_pernet_subsys(&tls_proc_ops); if (err) return err; err = tls_strp_dev_init(); if (err) goto err_pernet; err = tls_device_init(); if (err) goto err_strp; tcp_register_ulp(&tcp_tls_ulp_ops); return 0; err_strp: tls_strp_dev_exit(); err_pernet: unregister_pernet_subsys(&tls_proc_ops); return err; } static void __exit tls_unregister(void) { tcp_unregister_ulp(&tcp_tls_ulp_ops); tls_strp_dev_exit(); tls_device_cleanup(); unregister_pernet_subsys(&tls_proc_ops); } module_init(tls_register); module_exit(tls_unregister); |
| 27 27 27 2 23 7 27 27 24 9 26 23 3 23 9 27 27 27 27 26 26 21 26 26 1 9 1 9 9 4 4 4 4 2 4 4 6 1 1 6 27 27 27 12 12 12 12 12 14 9 14 6 14 14 14 9 9 9 7 7 7 4 4 1 1 1 1 1 1 26 1713 13 13 1 13 13 13 4 1 13 12 8 5 1 4 9 13 8 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * This file contains device methods for creating, using and destroying * virtual HSR or PRP devices. */ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> #include "hsr_device.h" #include "hsr_slave.h" #include "hsr_framereg.h" #include "hsr_main.h" #include "hsr_forward.h" static bool is_admin_up(struct net_device *dev) { return dev && (dev->flags & IFF_UP); } static bool is_slave_up(struct net_device *dev) { return dev && is_admin_up(dev) && netif_oper_up(dev); } static void hsr_set_operstate(struct hsr_port *master, bool has_carrier) { struct net_device *dev = master->dev; if (!is_admin_up(dev)) { netdev_set_operstate(dev, IF_OPER_DOWN); return; } if (has_carrier) netdev_set_operstate(dev, IF_OPER_UP); else netdev_set_operstate(dev, IF_OPER_LOWERLAYERDOWN); } static bool hsr_check_carrier(struct hsr_port *master) { struct hsr_port *port; ASSERT_RTNL(); hsr_for_each_port(master->hsr, port) { if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) { netif_carrier_on(master->dev); return true; } } netif_carrier_off(master->dev); return false; } static void hsr_check_announce(struct net_device *hsr_dev) { struct hsr_priv *hsr; hsr = netdev_priv(hsr_dev); if (netif_running(hsr_dev) && netif_oper_up(hsr_dev)) { /* Enable announce timer and start sending supervisory frames */ if (!timer_pending(&hsr->announce_timer)) { hsr->announce_count = 0; mod_timer(&hsr->announce_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); } if (hsr->redbox && !timer_pending(&hsr->announce_proxy_timer)) mod_timer(&hsr->announce_proxy_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL) / 2); } else { /* Deactivate the announce timer */ timer_delete(&hsr->announce_timer); if (hsr->redbox) timer_delete(&hsr->announce_proxy_timer); } } void hsr_check_carrier_and_operstate(struct hsr_priv *hsr) { struct hsr_port *master; bool has_carrier; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); /* netif_stacked_transfer_operstate() cannot be used here since * it doesn't set IF_OPER_LOWERLAYERDOWN (?) */ has_carrier = hsr_check_carrier(master); hsr_set_operstate(master, has_carrier); hsr_check_announce(master->dev); } int hsr_get_max_mtu(struct hsr_priv *hsr) { unsigned int mtu_max; struct hsr_port *port; mtu_max = ETH_DATA_LEN; hsr_for_each_port(hsr, port) if (port->type != HSR_PT_MASTER) mtu_max = min(port->dev->mtu, mtu_max); if (mtu_max < HSR_HLEN) return 0; return mtu_max - HSR_HLEN; } static int hsr_dev_change_mtu(struct net_device *dev, int new_mtu) { struct hsr_priv *hsr; hsr = netdev_priv(dev); if (new_mtu > hsr_get_max_mtu(hsr)) { netdev_info(dev, "A HSR master's MTU cannot be greater than the smallest MTU of its slaves minus the HSR Tag length (%d octets).\n", HSR_HLEN); return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int hsr_dev_open(struct net_device *dev) { struct hsr_priv *hsr; struct hsr_port *port; const char *designation = NULL; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: designation = "Slave A"; break; case HSR_PT_SLAVE_B: designation = "Slave B"; break; case HSR_PT_INTERLINK: designation = "Interlink"; break; default: designation = "Unknown"; } if (!is_slave_up(port->dev)) netdev_warn(dev, "%s (%s) is not up; please bring it up to get a fully working HSR network\n", designation, port->dev->name); } if (!designation) netdev_warn(dev, "No slave devices configured\n"); return 0; } static int hsr_dev_close(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_uc_unsync(port->dev, dev); dev_mc_unsync(port->dev, dev); break; default: break; } } return 0; } static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr, netdev_features_t features) { netdev_features_t mask; struct hsr_port *port; mask = features; /* Mask out all features that, if supported by one device, should be * enabled for all devices (see NETIF_F_ONE_FOR_ALL). * * Anything that's off in mask will not be enabled - so only things * that were in features originally, and also is in NETIF_F_ONE_FOR_ALL, * may become enabled. */ features &= ~NETIF_F_ONE_FOR_ALL; hsr_for_each_port(hsr, port) features = netdev_increment_features(features, port->dev->features, mask); return features; } static netdev_features_t hsr_fix_features(struct net_device *dev, netdev_features_t features) { struct hsr_priv *hsr = netdev_priv(dev); return hsr_features_recompute(hsr, features); } static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct hsr_priv *hsr = netdev_priv(dev); struct hsr_port *master; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (master) { skb->dev = master->dev; skb_reset_mac_header(skb); skb_reset_mac_len(skb); spin_lock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } else { dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); } return NETDEV_TX_OK; } static const struct header_ops hsr_header_ops = { .create = eth_header, .parse = eth_header_parse, }; static struct sk_buff *hsr_init_skb(struct hsr_port *master, int extra) { struct hsr_priv *hsr = master->hsr; struct sk_buff *skb; int hlen, tlen; int len; hlen = LL_RESERVED_SPACE(master->dev); tlen = master->dev->needed_tailroom; len = sizeof(struct hsr_sup_tag) + sizeof(struct hsr_sup_payload); /* skb size is same for PRP/HSR frames, only difference * being, for PRP it is a trailer and for HSR it is a * header. * RedBox might use @extra more bytes. */ skb = dev_alloc_skb(len + extra + hlen + tlen); if (!skb) return skb; skb_reserve(skb, hlen); skb->dev = master->dev; skb->priority = TC_PRIO_CONTROL; skb_reset_network_header(skb); skb_reset_transport_header(skb); if (dev_hard_header(skb, skb->dev, ETH_P_PRP, hsr->sup_multicast_addr, skb->dev->dev_addr, skb->len) <= 0) goto out; skb_reset_mac_header(skb); skb_reset_mac_len(skb); return skb; out: kfree_skb(skb); return NULL; } static void send_hsr_supervision_frame(struct hsr_port *port, unsigned long *interval, const unsigned char *addr) { struct hsr_priv *hsr = port->hsr; __u8 type = HSR_TLV_LIFE_CHECK; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tlv *hsr_stlv; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; int extra = 0; *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); if (hsr->announce_count < 3 && hsr->prot_version == 0) { type = HSR_TLV_ANNOUNCE; *interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); hsr->announce_count++; } if (hsr->redbox) extra = sizeof(struct hsr_sup_tlv) + sizeof(struct hsr_sup_payload); skb = hsr_init_skb(port, extra); if (!skb) { netdev_warn_once(port->dev, "HSR: Could not send supervision frame\n"); return; } hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); if (hsr->prot_version > 0) { hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; } else { hsr_stag->sequence_nr = htons(hsr->sequence_nr); hsr->sequence_nr++; } hsr_stag->tlv.HSR_TLV_type = type; /* TODO: Why 12 in HSRv0? */ hsr_stag->tlv.HSR_TLV_length = hsr->prot_version ? sizeof(struct hsr_sup_payload) : 12; /* Payload: MacAddressA / SAN MAC from ProxyNodeTable */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, addr); if (hsr->redbox && hsr_is_node_in_db(&hsr->proxy_node_db, addr)) { hsr_stlv = skb_put(skb, sizeof(struct hsr_sup_tlv)); hsr_stlv->HSR_TLV_type = PRP_TLV_REDBOX_MAC; hsr_stlv->HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressRedBox */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, hsr->macaddress_redbox); } if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, port); spin_unlock_bh(&hsr->seqnr_lock); return; } static void send_prp_supervision_frame(struct hsr_port *master, unsigned long *interval, const unsigned char *addr) { struct hsr_priv *hsr = master->hsr; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; skb = hsr_init_skb(master, 0); if (!skb) { netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, (hsr->prot_version ? 1 : 0)); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; hsr_stag->tlv.HSR_TLV_type = PRP_TLV_LIFE_CHECK_DD; hsr_stag->tlv.HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressA */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } /* Announce (supervision frame) timer function */ static void hsr_announce(struct timer_list *t) { struct hsr_priv *hsr; struct hsr_port *master; unsigned long interval; hsr = from_timer(hsr, t, announce_timer); rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); hsr->proto_ops->send_sv_frame(master, &interval, master->dev->dev_addr); if (is_admin_up(master->dev)) mod_timer(&hsr->announce_timer, jiffies + interval); rcu_read_unlock(); } /* Announce (supervision frame) timer function for RedBox */ static void hsr_proxy_announce(struct timer_list *t) { struct hsr_priv *hsr = from_timer(hsr, t, announce_proxy_timer); struct hsr_port *interlink; unsigned long interval = 0; struct hsr_node *node; rcu_read_lock(); /* RedBOX sends supervisory frames to HSR network with MAC addresses * of SAN nodes stored in ProxyNodeTable. */ interlink = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); if (!interlink) goto done; list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) { if (hsr_addr_is_redbox(hsr, node->macaddress_A)) continue; hsr->proto_ops->send_sv_frame(interlink, &interval, node->macaddress_A); } if (is_admin_up(interlink->dev)) { if (!interval) interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); mod_timer(&hsr->announce_proxy_timer, jiffies + interval); } done: rcu_read_unlock(); } void hsr_del_ports(struct hsr_priv *hsr) { struct hsr_port *port; port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (port) hsr_del_port(port); } static void hsr_set_rx_mode(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_mc_sync_multiple(port->dev, dev); dev_uc_sync_multiple(port->dev, dev); break; default: break; } } } static void hsr_change_rx_flags(struct net_device *dev, int change) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: if (change & IFF_ALLMULTI) dev_set_allmulti(port->dev, dev->flags & IFF_ALLMULTI ? 1 : -1); break; default: break; } } } static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { bool is_slave_a_added = false; bool is_slave_b_added = false; struct hsr_port *port; struct hsr_priv *hsr; int ret = 0; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER || port->type == HSR_PT_INTERLINK) continue; ret = vlan_vid_add(port->dev, proto, vid); switch (port->type) { case HSR_PT_SLAVE_A: if (ret) { /* clean up Slave-B */ netdev_err(dev, "add vid failed for Slave-A\n"); if (is_slave_b_added) vlan_vid_del(port->dev, proto, vid); return ret; } is_slave_a_added = true; break; case HSR_PT_SLAVE_B: if (ret) { /* clean up Slave-A */ netdev_err(dev, "add vid failed for Slave-B\n"); if (is_slave_a_added) vlan_vid_del(port->dev, proto, vid); return ret; } is_slave_b_added = true; break; default: break; } } return 0; } static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: vlan_vid_del(port->dev, proto, vid); break; default: break; } } return 0; } static const struct net_device_ops hsr_device_ops = { .ndo_change_mtu = hsr_dev_change_mtu, .ndo_open = hsr_dev_open, .ndo_stop = hsr_dev_close, .ndo_start_xmit = hsr_dev_xmit, .ndo_change_rx_flags = hsr_change_rx_flags, .ndo_fix_features = hsr_fix_features, .ndo_set_rx_mode = hsr_set_rx_mode, .ndo_vlan_rx_add_vid = hsr_ndo_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = hsr_ndo_vlan_rx_kill_vid, }; static const struct device_type hsr_type = { .name = "hsr", }; static struct hsr_proto_ops hsr_ops = { .send_sv_frame = send_hsr_supervision_frame, .create_tagged_frame = hsr_create_tagged_frame, .get_untagged_frame = hsr_get_untagged_frame, .drop_frame = hsr_drop_frame, .fill_frame_info = hsr_fill_frame_info, .invalid_dan_ingress_frame = hsr_invalid_dan_ingress_frame, }; static struct hsr_proto_ops prp_ops = { .send_sv_frame = send_prp_supervision_frame, .create_tagged_frame = prp_create_tagged_frame, .get_untagged_frame = prp_get_untagged_frame, .drop_frame = prp_drop_frame, .fill_frame_info = prp_fill_frame_info, .handle_san_frame = prp_handle_san_frame, .update_san_info = prp_update_san_info, }; void hsr_dev_setup(struct net_device *dev) { eth_hw_addr_random(dev); ether_setup(dev); dev->min_mtu = 0; dev->header_ops = &hsr_header_ops; dev->netdev_ops = &hsr_device_ops; SET_NETDEV_DEVTYPE(dev, &hsr_type); dev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; /* Prevent recursive tx locking */ dev->lltx = true; /* Not sure about this. Taken from bridge code. netdevice.h says * it means "Does not change network namespaces". */ dev->netns_local = true; dev->needs_free_netdev = true; dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_FILTER; dev->features = dev->hw_features; } /* Return true if dev is a HSR master; return false otherwise. */ bool is_hsr_master(struct net_device *dev) { return (dev->netdev_ops->ndo_start_xmit == hsr_dev_xmit); } EXPORT_SYMBOL(is_hsr_master); /* Default multicast address for HSR Supervision frames */ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x15, 0x4e, 0x00, 0x01, 0x00 }; int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], struct net_device *interlink, unsigned char multicast_spec, u8 protocol_version, struct netlink_ext_ack *extack) { bool unregister = false; struct hsr_priv *hsr; int res; hsr = netdev_priv(hsr_dev); INIT_LIST_HEAD(&hsr->ports); INIT_LIST_HEAD(&hsr->node_db); INIT_LIST_HEAD(&hsr->proxy_node_db); spin_lock_init(&hsr->list_lock); eth_hw_addr_set(hsr_dev, slave[0]->dev_addr); /* initialize protocol specific functions */ if (protocol_version == PRP_V1) { /* For PRP, lan_id has most significant 3 bits holding * the net_id of PRP_LAN_ID */ hsr->net_id = PRP_LAN_ID << 1; hsr->proto_ops = &prp_ops; } else { hsr->proto_ops = &hsr_ops; } /* Make sure we recognize frames from ourselves in hsr_rcv() */ res = hsr_create_self_node(hsr, hsr_dev->dev_addr, slave[1]->dev_addr); if (res < 0) return res; spin_lock_init(&hsr->seqnr_lock); /* Overflow soon to find bugs easier: */ hsr->sequence_nr = HSR_SEQNR_START; hsr->sup_sequence_nr = HSR_SUP_SEQNR_START; timer_setup(&hsr->announce_timer, hsr_announce, 0); timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0); timer_setup(&hsr->prune_proxy_timer, hsr_prune_proxy_nodes, 0); timer_setup(&hsr->announce_proxy_timer, hsr_proxy_announce, 0); ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr); hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; hsr->prot_version = protocol_version; /* Make sure the 1st call to netif_carrier_on() gets through */ netif_carrier_off(hsr_dev); res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER, extack); if (res) goto err_add_master; /* HSR forwarding offload supported in lower device? */ if ((slave[0]->features & NETIF_F_HW_HSR_FWD) && (slave[1]->features & NETIF_F_HW_HSR_FWD)) hsr->fwd_offloaded = true; if ((slave[0]->features & NETIF_F_HW_VLAN_CTAG_FILTER) && (slave[1]->features & NETIF_F_HW_VLAN_CTAG_FILTER)) hsr_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; res = register_netdevice(hsr_dev); if (res) goto err_unregister; unregister = true; res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A, extack); if (res) goto err_unregister; res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B, extack); if (res) goto err_unregister; if (interlink) { res = hsr_add_port(hsr, interlink, HSR_PT_INTERLINK, extack); if (res) goto err_unregister; hsr->redbox = true; ether_addr_copy(hsr->macaddress_redbox, interlink->dev_addr); mod_timer(&hsr->prune_proxy_timer, jiffies + msecs_to_jiffies(PRUNE_PROXY_PERIOD)); } hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); return 0; err_unregister: hsr_del_ports(hsr); err_add_master: hsr_del_self_node(hsr); if (unregister) unregister_netdevice(hsr_dev); return res; } |
| 4 3 3 1 2 1 1 1 1 1 3 4 5 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * super.c * * Copyright (c) 1999 Al Smith * * Portions derived from work (c) 1995,1996 Christian Vogelgsang. */ #include <linux/init.h> #include <linux/module.h> #include <linux/exportfs.h> #include <linux/slab.h> #include <linux/buffer_head.h> #include <linux/vfs.h> #include <linux/blkdev.h> #include <linux/fs_context.h> #include "efs.h" #include <linux/efs_vh.h> #include <linux/efs_fs_sb.h> static int efs_statfs(struct dentry *dentry, struct kstatfs *buf); static int efs_init_fs_context(struct fs_context *fc); static void efs_kill_sb(struct super_block *s) { struct efs_sb_info *sbi = SUPER_INFO(s); kill_block_super(s); kfree(sbi); } static struct pt_types sgi_pt_types[] = { {0x00, "SGI vh"}, {0x01, "SGI trkrepl"}, {0x02, "SGI secrepl"}, {0x03, "SGI raw"}, {0x04, "SGI bsd"}, {SGI_SYSV, "SGI sysv"}, {0x06, "SGI vol"}, {SGI_EFS, "SGI efs"}, {0x08, "SGI lv"}, {0x09, "SGI rlv"}, {0x0A, "SGI xfs"}, {0x0B, "SGI xfslog"}, {0x0C, "SGI xlv"}, {0x82, "Linux swap"}, {0x83, "Linux native"}, {0, NULL} }; /* * File system definition and registration. */ static struct file_system_type efs_fs_type = { .owner = THIS_MODULE, .name = "efs", .kill_sb = efs_kill_sb, .fs_flags = FS_REQUIRES_DEV, .init_fs_context = efs_init_fs_context, }; MODULE_ALIAS_FS("efs"); static struct kmem_cache * efs_inode_cachep; static struct inode *efs_alloc_inode(struct super_block *sb) { struct efs_inode_info *ei; ei = alloc_inode_sb(sb, efs_inode_cachep, GFP_KERNEL); if (!ei) return NULL; return &ei->vfs_inode; } static void efs_free_inode(struct inode *inode) { kmem_cache_free(efs_inode_cachep, INODE_INFO(inode)); } static void init_once(void *foo) { struct efs_inode_info *ei = (struct efs_inode_info *) foo; inode_init_once(&ei->vfs_inode); } static int __init init_inodecache(void) { efs_inode_cachep = kmem_cache_create("efs_inode_cache", sizeof(struct efs_inode_info), 0, SLAB_RECLAIM_ACCOUNT|SLAB_ACCOUNT, init_once); if (efs_inode_cachep == NULL) return -ENOMEM; return 0; } static void destroy_inodecache(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(efs_inode_cachep); } static const struct super_operations efs_superblock_operations = { .alloc_inode = efs_alloc_inode, .free_inode = efs_free_inode, .statfs = efs_statfs, }; static const struct export_operations efs_export_ops = { .encode_fh = generic_encode_ino32_fh, .fh_to_dentry = efs_fh_to_dentry, .fh_to_parent = efs_fh_to_parent, .get_parent = efs_get_parent, }; static int __init init_efs_fs(void) { int err; pr_info(EFS_VERSION" - http://aeschi.ch.eu.org/efs/\n"); err = init_inodecache(); if (err) goto out1; err = register_filesystem(&efs_fs_type); if (err) goto out; return 0; out: destroy_inodecache(); out1: return err; } static void __exit exit_efs_fs(void) { unregister_filesystem(&efs_fs_type); destroy_inodecache(); } module_init(init_efs_fs) module_exit(exit_efs_fs) static efs_block_t efs_validate_vh(struct volume_header *vh) { int i; __be32 cs, *ui; int csum; efs_block_t sblock = 0; /* shuts up gcc */ struct pt_types *pt_entry; int pt_type, slice = -1; if (be32_to_cpu(vh->vh_magic) != VHMAGIC) { /* * assume that we're dealing with a partition and allow * read_super() to try and detect a valid superblock * on the next block. */ return 0; } ui = ((__be32 *) (vh + 1)) - 1; for(csum = 0; ui >= ((__be32 *) vh);) { cs = *ui--; csum += be32_to_cpu(cs); } if (csum) { pr_warn("SGI disklabel: checksum bad, label corrupted\n"); return 0; } #ifdef DEBUG pr_debug("bf: \"%16s\"\n", vh->vh_bootfile); for(i = 0; i < NVDIR; i++) { int j; char name[VDNAMESIZE+1]; for(j = 0; j < VDNAMESIZE; j++) { name[j] = vh->vh_vd[i].vd_name[j]; } name[j] = (char) 0; if (name[0]) { pr_debug("vh: %8s block: 0x%08x size: 0x%08x\n", name, (int) be32_to_cpu(vh->vh_vd[i].vd_lbn), (int) be32_to_cpu(vh->vh_vd[i].vd_nbytes)); } } #endif for(i = 0; i < NPARTAB; i++) { pt_type = (int) be32_to_cpu(vh->vh_pt[i].pt_type); for(pt_entry = sgi_pt_types; pt_entry->pt_name; pt_entry++) { if (pt_type == pt_entry->pt_type) break; } #ifdef DEBUG if (be32_to_cpu(vh->vh_pt[i].pt_nblks)) { pr_debug("pt %2d: start: %08d size: %08d type: 0x%02x (%s)\n", i, (int)be32_to_cpu(vh->vh_pt[i].pt_firstlbn), (int)be32_to_cpu(vh->vh_pt[i].pt_nblks), pt_type, (pt_entry->pt_name) ? pt_entry->pt_name : "unknown"); } #endif if (IS_EFS(pt_type)) { sblock = be32_to_cpu(vh->vh_pt[i].pt_firstlbn); slice = i; } } if (slice == -1) { pr_notice("partition table contained no EFS partitions\n"); #ifdef DEBUG } else { pr_info("using slice %d (type %s, offset 0x%x)\n", slice, (pt_entry->pt_name) ? pt_entry->pt_name : "unknown", sblock); #endif } return sblock; } static int efs_validate_super(struct efs_sb_info *sb, struct efs_super *super) { if (!IS_EFS_MAGIC(be32_to_cpu(super->fs_magic))) return -1; sb->fs_magic = be32_to_cpu(super->fs_magic); sb->total_blocks = be32_to_cpu(super->fs_size); sb->first_block = be32_to_cpu(super->fs_firstcg); sb->group_size = be32_to_cpu(super->fs_cgfsize); sb->data_free = be32_to_cpu(super->fs_tfree); sb->inode_free = be32_to_cpu(super->fs_tinode); sb->inode_blocks = be16_to_cpu(super->fs_cgisize); sb->total_groups = be16_to_cpu(super->fs_ncg); return 0; } static int efs_fill_super(struct super_block *s, struct fs_context *fc) { struct efs_sb_info *sb; struct buffer_head *bh; struct inode *root; sb = kzalloc(sizeof(struct efs_sb_info), GFP_KERNEL); if (!sb) return -ENOMEM; s->s_fs_info = sb; s->s_time_min = 0; s->s_time_max = U32_MAX; s->s_magic = EFS_SUPER_MAGIC; if (!sb_set_blocksize(s, EFS_BLOCKSIZE)) { pr_err("device does not support %d byte blocks\n", EFS_BLOCKSIZE); return invalf(fc, "device does not support %d byte blocks\n", EFS_BLOCKSIZE); } /* read the vh (volume header) block */ bh = sb_bread(s, 0); if (!bh) { pr_err("cannot read volume header\n"); return -EIO; } /* * if this returns zero then we didn't find any partition table. * this isn't (yet) an error - just assume for the moment that * the device is valid and go on to search for a superblock. */ sb->fs_start = efs_validate_vh((struct volume_header *) bh->b_data); brelse(bh); if (sb->fs_start == -1) { return -EINVAL; } bh = sb_bread(s, sb->fs_start + EFS_SUPER); if (!bh) { pr_err("cannot read superblock\n"); return -EIO; } if (efs_validate_super(sb, (struct efs_super *) bh->b_data)) { #ifdef DEBUG pr_warn("invalid superblock at block %u\n", sb->fs_start + EFS_SUPER); #endif brelse(bh); return -EINVAL; } brelse(bh); if (!sb_rdonly(s)) { #ifdef DEBUG pr_info("forcing read-only mode\n"); #endif s->s_flags |= SB_RDONLY; } s->s_op = &efs_superblock_operations; s->s_export_op = &efs_export_ops; root = efs_iget(s, EFS_ROOTINODE); if (IS_ERR(root)) { pr_err("get root inode failed\n"); return PTR_ERR(root); } s->s_root = d_make_root(root); if (!(s->s_root)) { pr_err("get root dentry failed\n"); return -ENOMEM; } return 0; } static int efs_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, efs_fill_super); } static int efs_reconfigure(struct fs_context *fc) { sync_filesystem(fc->root->d_sb); fc->sb_flags |= SB_RDONLY; return 0; } static const struct fs_context_operations efs_context_opts = { .get_tree = efs_get_tree, .reconfigure = efs_reconfigure, }; /* * Set up the filesystem mount context. */ static int efs_init_fs_context(struct fs_context *fc) { fc->ops = &efs_context_opts; return 0; } static int efs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct efs_sb_info *sbi = SUPER_INFO(sb); u64 id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = EFS_SUPER_MAGIC; /* efs magic number */ buf->f_bsize = EFS_BLOCKSIZE; /* blocksize */ buf->f_blocks = sbi->total_groups * /* total data blocks */ (sbi->group_size - sbi->inode_blocks); buf->f_bfree = sbi->data_free; /* free data blocks */ buf->f_bavail = sbi->data_free; /* free blocks for non-root */ buf->f_files = sbi->total_groups * /* total inodes */ sbi->inode_blocks * (EFS_BLOCKSIZE / sizeof(struct efs_dinode)); buf->f_ffree = sbi->inode_free; /* free inodes */ buf->f_fsid = u64_to_fsid(id); buf->f_namelen = EFS_MAXNAMELEN; /* max filename length */ return 0; } |
| 18 36 1 35 40 38 40 37 36 35 36 19 1 18 18 2 16 1 1 3 3 8 6 4 2 6 6 3 1 1 4 4 1 6 5 1 4 6 1 1 1 1 4 4 1 3 3 3 3 2 3 4 1 1 1 1 2 1 2 10 3 7 4 3 3 2 3 6 1 5 10 31 43 42 41 25 40 43 36 31 31 23 8 15 1 14 11 29 29 35 1 42 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright 2008 Red Hat, Inc. All rights reserved. * Copyright 2008 Ian Kent <raven@themaw.net> */ #include <linux/module.h> #include <linux/miscdevice.h> #include <linux/compat.h> #include <linux/fdtable.h> #include <linux/magic.h> #include <linux/nospec.h> #include "autofs_i.h" /* * This module implements an interface for routing autofs ioctl control * commands via a miscellaneous device file. * * The alternate interface is needed because we need to be able open * an ioctl file descriptor on an autofs mount that may be covered by * another mount. This situation arises when starting automount(8) * or other user space daemon which uses direct mounts or offset * mounts (used for autofs lazy mount/umount of nested mount trees), * which have been left busy at service shutdown. */ typedef int (*ioctl_fn)(struct file *, struct autofs_sb_info *, struct autofs_dev_ioctl *); static int check_name(const char *name) { if (!strchr(name, '/')) return -EINVAL; return 0; } /* * Check a string doesn't overrun the chunk of * memory we copied from user land. */ static int invalid_str(char *str, size_t size) { if (memchr(str, 0, size)) return 0; return -EINVAL; } /* * Check that the user compiled against correct version of autofs * misc device code. * * As well as checking the version compatibility this always copies * the kernel interface version out. */ static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param) { int err = 0; if ((param->ver_major != AUTOFS_DEV_IOCTL_VERSION_MAJOR) || (param->ver_minor > AUTOFS_DEV_IOCTL_VERSION_MINOR)) { pr_warn("ioctl control interface version mismatch: " "kernel(%u.%u), user(%u.%u), cmd(0x%08x)\n", AUTOFS_DEV_IOCTL_VERSION_MAJOR, AUTOFS_DEV_IOCTL_VERSION_MINOR, param->ver_major, param->ver_minor, cmd); err = -EINVAL; } /* Fill in the kernel version. */ param->ver_major = AUTOFS_DEV_IOCTL_VERSION_MAJOR; param->ver_minor = AUTOFS_DEV_IOCTL_VERSION_MINOR; return err; } /* * Copy parameter control struct, including a possible path allocated * at the end of the struct. */ static struct autofs_dev_ioctl * copy_dev_ioctl(struct autofs_dev_ioctl __user *in) { struct autofs_dev_ioctl tmp, *res; if (copy_from_user(&tmp, in, AUTOFS_DEV_IOCTL_SIZE)) return ERR_PTR(-EFAULT); if (tmp.size < AUTOFS_DEV_IOCTL_SIZE) return ERR_PTR(-EINVAL); if (tmp.size > AUTOFS_DEV_IOCTL_SIZE + PATH_MAX) return ERR_PTR(-ENAMETOOLONG); res = memdup_user(in, tmp.size); if (!IS_ERR(res)) res->size = tmp.size; return res; } static inline void free_dev_ioctl(struct autofs_dev_ioctl *param) { kfree(param); } /* * Check sanity of parameter control fields and if a path is present * check that it is terminated and contains at least one "/". */ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param) { unsigned int inr = _IOC_NR(cmd); int err; err = check_dev_ioctl_version(cmd, param); if (err) { pr_warn("invalid device control module version " "supplied for cmd(0x%08x)\n", cmd); goto out; } if (param->size > AUTOFS_DEV_IOCTL_SIZE) { err = invalid_str(param->path, param->size - AUTOFS_DEV_IOCTL_SIZE); if (err) { pr_warn( "path string terminator missing for cmd(0x%08x)\n", cmd); goto out; } /* Setting the per-dentry expire timeout requires a trailing * path component, ie. no '/', so invert the logic of the * check_name() return for AUTOFS_DEV_IOCTL_TIMEOUT_CMD. */ err = check_name(param->path); if (inr == AUTOFS_DEV_IOCTL_TIMEOUT_CMD) err = err ? 0 : -EINVAL; if (err) { pr_warn("invalid path supplied for cmd(0x%08x)\n", cmd); goto out; } } else { if (inr == AUTOFS_DEV_IOCTL_OPENMOUNT_CMD || inr == AUTOFS_DEV_IOCTL_REQUESTER_CMD || inr == AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD) { err = -EINVAL; goto out; } } err = 0; out: return err; } /* Return autofs dev ioctl version */ static int autofs_dev_ioctl_version(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { /* This should have already been set. */ param->ver_major = AUTOFS_DEV_IOCTL_VERSION_MAJOR; param->ver_minor = AUTOFS_DEV_IOCTL_VERSION_MINOR; return 0; } /* Return autofs module protocol version */ static int autofs_dev_ioctl_protover(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { param->protover.version = sbi->version; return 0; } /* Return autofs module protocol sub version */ static int autofs_dev_ioctl_protosubver(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { param->protosubver.sub_version = sbi->sub_version; return 0; } /* Find the topmost mount satisfying test() */ static int find_autofs_mount(const char *pathname, struct path *res, int test(const struct path *path, void *data), void *data) { struct path path; int err; err = kern_path(pathname, LOOKUP_MOUNTPOINT, &path); if (err) return err; err = -ENOENT; while (path.dentry == path.mnt->mnt_root) { if (path.dentry->d_sb->s_magic == AUTOFS_SUPER_MAGIC) { if (test(&path, data)) { path_get(&path); *res = path; err = 0; break; } } if (!follow_up(&path)) break; } path_put(&path); return err; } static int test_by_dev(const struct path *path, void *p) { return path->dentry->d_sb->s_dev == *(dev_t *)p; } static int test_by_type(const struct path *path, void *p) { struct autofs_info *ino = autofs_dentry_ino(path->dentry); return ino && ino->sbi->type & *(unsigned *)p; } /* * Open a file descriptor on the autofs mount point corresponding * to the given path and device number (aka. new_encode_dev(sb->s_dev)). */ static int autofs_dev_ioctl_open_mountpoint(const char *name, dev_t devid) { int err, fd; fd = get_unused_fd_flags(O_CLOEXEC); if (likely(fd >= 0)) { struct file *filp; struct path path; err = find_autofs_mount(name, &path, test_by_dev, &devid); if (err) goto out; filp = dentry_open(&path, O_RDONLY, current_cred()); path_put(&path); if (IS_ERR(filp)) { err = PTR_ERR(filp); goto out; } fd_install(fd, filp); } return fd; out: put_unused_fd(fd); return err; } /* Open a file descriptor on an autofs mount point */ static int autofs_dev_ioctl_openmount(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { const char *path; dev_t devid; int err, fd; /* param->path has been checked in validate_dev_ioctl() */ if (!param->openmount.devid) return -EINVAL; param->ioctlfd = -1; path = param->path; devid = new_decode_dev(param->openmount.devid); err = 0; fd = autofs_dev_ioctl_open_mountpoint(path, devid); if (unlikely(fd < 0)) { err = fd; goto out; } param->ioctlfd = fd; out: return err; } /* Close file descriptor allocated above (user can also use close(2)). */ static int autofs_dev_ioctl_closemount(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { return close_fd(param->ioctlfd); } /* * Send "ready" status for an existing wait (either a mount or an expire * request). */ static int autofs_dev_ioctl_ready(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { autofs_wqt_t token; token = (autofs_wqt_t) param->ready.token; return autofs_wait_release(sbi, token, 0); } /* * Send "fail" status for an existing wait (either a mount or an expire * request). */ static int autofs_dev_ioctl_fail(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { autofs_wqt_t token; int status; token = (autofs_wqt_t) param->fail.token; status = param->fail.status < 0 ? param->fail.status : -ENOENT; return autofs_wait_release(sbi, token, status); } /* * Set the pipe fd for kernel communication to the daemon. * * Normally this is set at mount using an option but if we * are reconnecting to a busy mount then we need to use this * to tell the autofs mount about the new kernel pipe fd. In * order to protect mounts against incorrectly setting the * pipefd we also require that the autofs mount be catatonic. * * This also sets the process group id used to identify the * controlling process (eg. the owning automount(8) daemon). */ static int autofs_dev_ioctl_setpipefd(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { int pipefd; int err = 0; struct pid *new_pid = NULL; if (param->setpipefd.pipefd == -1) return -EINVAL; pipefd = param->setpipefd.pipefd; mutex_lock(&sbi->wq_mutex); if (!(sbi->flags & AUTOFS_SBI_CATATONIC)) { mutex_unlock(&sbi->wq_mutex); return -EBUSY; } else { struct file *pipe; new_pid = get_task_pid(current, PIDTYPE_PGID); if (ns_of_pid(new_pid) != ns_of_pid(sbi->oz_pgrp)) { pr_warn("not allowed to change PID namespace\n"); err = -EINVAL; goto out; } pipe = fget(pipefd); if (!pipe) { err = -EBADF; goto out; } if (autofs_prepare_pipe(pipe) < 0) { err = -EPIPE; fput(pipe); goto out; } swap(sbi->oz_pgrp, new_pid); sbi->pipefd = pipefd; sbi->pipe = pipe; sbi->flags &= ~AUTOFS_SBI_CATATONIC; } out: put_pid(new_pid); mutex_unlock(&sbi->wq_mutex); return err; } /* * Make the autofs mount point catatonic, no longer responsive to * mount requests. Also closes the kernel pipe file descriptor. */ static int autofs_dev_ioctl_catatonic(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { autofs_catatonic_mode(sbi); return 0; } /* * Set the autofs mount expire timeout. * * There are two places an expire timeout can be set, in the autofs * super block info. (this is all that's needed for direct and offset * mounts because there's a distinct mount corresponding to each of * these) and per-dentry within within the dentry info. If a per-dentry * timeout is set it will override the expire timeout set in the parent * autofs super block info. * * If setting the autofs super block expire timeout the autofs_dev_ioctl * size field will be equal to the autofs_dev_ioctl structure size. If * setting the per-dentry expire timeout the mount point name is passed * in the autofs_dev_ioctl path field and the size field updated to * reflect this. * * Setting the autofs mount expire timeout sets the timeout in the super * block info. struct. Setting the per-dentry timeout does a little more. * If the timeout is equal to -1 the per-dentry timeout (and flag) is * cleared which reverts to using the super block timeout, otherwise if * timeout is 0 the timeout is set to this value and the flag is left * set which disables expiration for the mount point, lastly the flag * and the timeout are set enabling the dentry to use this timeout. */ static int autofs_dev_ioctl_timeout(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { unsigned long timeout = param->timeout.timeout; /* If setting the expire timeout for an individual indirect * mount point dentry the mount trailing component path is * placed in param->path and param->size adjusted to account * for it otherwise param->size it is set to the structure * size. */ if (param->size == AUTOFS_DEV_IOCTL_SIZE) { param->timeout.timeout = sbi->exp_timeout / HZ; sbi->exp_timeout = timeout * HZ; } else { struct dentry *base = fp->f_path.dentry; struct inode *inode = base->d_inode; int path_len = param->size - AUTOFS_DEV_IOCTL_SIZE - 1; struct dentry *dentry; struct autofs_info *ino; if (!autofs_type_indirect(sbi->type)) return -EINVAL; /* An expire timeout greater than the superblock timeout * could be a problem at shutdown but the super block * timeout itself can change so all we can really do is * warn the user. */ if (timeout >= sbi->exp_timeout) pr_warn("per-mount expire timeout is greater than " "the parent autofs mount timeout which could " "prevent shutdown\n"); inode_lock_shared(inode); dentry = try_lookup_one_len(param->path, base, path_len); inode_unlock_shared(inode); if (IS_ERR_OR_NULL(dentry)) return dentry ? PTR_ERR(dentry) : -ENOENT; ino = autofs_dentry_ino(dentry); if (!ino) { dput(dentry); return -ENOENT; } if (ino->exp_timeout && ino->flags & AUTOFS_INF_EXPIRE_SET) param->timeout.timeout = ino->exp_timeout / HZ; else param->timeout.timeout = sbi->exp_timeout / HZ; if (timeout == -1) { /* Revert to using the super block timeout */ ino->flags &= ~AUTOFS_INF_EXPIRE_SET; ino->exp_timeout = 0; } else { /* Set the dentry expire flag and timeout. * * If timeout is 0 it will prevent the expire * of this particular automount. */ ino->flags |= AUTOFS_INF_EXPIRE_SET; ino->exp_timeout = timeout * HZ; } dput(dentry); } return 0; } /* * Return the uid and gid of the last request for the mount * * When reconstructing an autofs mount tree with active mounts * we need to re-connect to mounts that may have used the original * process uid and gid (or string variations of them) for mount * lookups within the map entry. */ static int autofs_dev_ioctl_requester(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { struct autofs_info *ino; struct path path; dev_t devid; int err = -ENOENT; /* param->path has been checked in validate_dev_ioctl() */ devid = sbi->sb->s_dev; param->requester.uid = param->requester.gid = -1; err = find_autofs_mount(param->path, &path, test_by_dev, &devid); if (err) goto out; ino = autofs_dentry_ino(path.dentry); if (ino) { err = 0; autofs_expire_wait(&path, 0); spin_lock(&sbi->fs_lock); param->requester.uid = from_kuid_munged(current_user_ns(), ino->uid); param->requester.gid = from_kgid_munged(current_user_ns(), ino->gid); spin_unlock(&sbi->fs_lock); } path_put(&path); out: return err; } /* * Call repeatedly until it returns -EAGAIN, meaning there's nothing * more that can be done. */ static int autofs_dev_ioctl_expire(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { struct vfsmount *mnt; int how; how = param->expire.how; mnt = fp->f_path.mnt; return autofs_do_expire_multi(sbi->sb, mnt, sbi, how); } /* Check if autofs mount point is in use */ static int autofs_dev_ioctl_askumount(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { param->askumount.may_umount = 0; if (may_umount(fp->f_path.mnt)) param->askumount.may_umount = 1; return 0; } /* * Check if the given path is a mountpoint. * * If we are supplied with the file descriptor of an autofs * mount we're looking for a specific mount. In this case * the path is considered a mountpoint if it is itself a * mountpoint or contains a mount, such as a multi-mount * without a root mount. In this case we return 1 if the * path is a mount point and the super magic of the covering * mount if there is one or 0 if it isn't a mountpoint. * * If we aren't supplied with a file descriptor then we * lookup the path and check if it is the root of a mount. * If a type is given we are looking for a particular autofs * mount and if we don't find a match we return fail. If the * located path is the root of a mount we return 1 along with * the super magic of the mount or 0 otherwise. * * In both cases the device number (as returned by * new_encode_dev()) is also returned. */ static int autofs_dev_ioctl_ismountpoint(struct file *fp, struct autofs_sb_info *sbi, struct autofs_dev_ioctl *param) { struct path path; const char *name; unsigned int type; unsigned int devid, magic; int err = -ENOENT; /* param->path has been checked in validate_dev_ioctl() */ name = param->path; type = param->ismountpoint.in.type; param->ismountpoint.out.devid = devid = 0; param->ismountpoint.out.magic = magic = 0; if (!fp || param->ioctlfd == -1) { if (autofs_type_any(type)) err = kern_path(name, LOOKUP_FOLLOW | LOOKUP_MOUNTPOINT, &path); else err = find_autofs_mount(name, &path, test_by_type, &type); if (err) goto out; devid = new_encode_dev(path.dentry->d_sb->s_dev); err = 0; if (path.mnt->mnt_root == path.dentry) { err = 1; magic = path.dentry->d_sb->s_magic; } } else { dev_t dev = sbi->sb->s_dev; err = find_autofs_mount(name, &path, test_by_dev, &dev); if (err) goto out; devid = new_encode_dev(dev); err = path_has_submounts(&path); if (follow_down_one(&path)) magic = path.dentry->d_sb->s_magic; } param->ismountpoint.out.devid = devid; param->ismountpoint.out.magic = magic; path_put(&path); out: return err; } /* * Our range of ioctl numbers isn't 0 based so we need to shift * the array index by _IOC_NR(AUTOFS_CTL_IOC_FIRST) for the table * lookup. */ #define cmd_idx(cmd) (cmd - _IOC_NR(AUTOFS_DEV_IOCTL_IOC_FIRST)) static ioctl_fn lookup_dev_ioctl(unsigned int cmd) { static const ioctl_fn _ioctls[] = { autofs_dev_ioctl_version, autofs_dev_ioctl_protover, autofs_dev_ioctl_protosubver, autofs_dev_ioctl_openmount, autofs_dev_ioctl_closemount, autofs_dev_ioctl_ready, autofs_dev_ioctl_fail, autofs_dev_ioctl_setpipefd, autofs_dev_ioctl_catatonic, autofs_dev_ioctl_timeout, autofs_dev_ioctl_requester, autofs_dev_ioctl_expire, autofs_dev_ioctl_askumount, autofs_dev_ioctl_ismountpoint, }; unsigned int idx = cmd_idx(cmd); if (idx >= ARRAY_SIZE(_ioctls)) return NULL; idx = array_index_nospec(idx, ARRAY_SIZE(_ioctls)); return _ioctls[idx]; } /* ioctl dispatcher */ static int _autofs_dev_ioctl(unsigned int command, struct autofs_dev_ioctl __user *user) { struct autofs_dev_ioctl *param; struct file *fp; struct autofs_sb_info *sbi; unsigned int cmd_first, cmd; ioctl_fn fn = NULL; int err = 0; cmd_first = _IOC_NR(AUTOFS_DEV_IOCTL_IOC_FIRST); cmd = _IOC_NR(command); if (_IOC_TYPE(command) != _IOC_TYPE(AUTOFS_DEV_IOCTL_IOC_FIRST) || cmd - cmd_first > AUTOFS_DEV_IOCTL_IOC_COUNT) { return -ENOTTY; } /* Only root can use ioctls other than AUTOFS_DEV_IOCTL_VERSION_CMD * and AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD */ if (cmd != AUTOFS_DEV_IOCTL_VERSION_CMD && cmd != AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD && !capable(CAP_SYS_ADMIN)) return -EPERM; /* Copy the parameters into kernel space. */ param = copy_dev_ioctl(user); if (IS_ERR(param)) return PTR_ERR(param); err = validate_dev_ioctl(command, param); if (err) goto out; fn = lookup_dev_ioctl(cmd); if (!fn) { pr_warn("unknown command 0x%08x\n", command); err = -ENOTTY; goto out; } fp = NULL; sbi = NULL; /* * For obvious reasons the openmount can't have a file * descriptor yet. We don't take a reference to the * file during close to allow for immediate release, * and the same for retrieving ioctl version. */ if (cmd != AUTOFS_DEV_IOCTL_VERSION_CMD && cmd != AUTOFS_DEV_IOCTL_OPENMOUNT_CMD && cmd != AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD) { struct super_block *sb; fp = fget(param->ioctlfd); if (!fp) { if (cmd == AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD) goto cont; err = -EBADF; goto out; } sb = file_inode(fp)->i_sb; if (sb->s_type != &autofs_fs_type) { err = -EINVAL; fput(fp); goto out; } sbi = autofs_sbi(sb); /* * Admin needs to be able to set the mount catatonic in * order to be able to perform the re-open. */ if (!autofs_oz_mode(sbi) && cmd != AUTOFS_DEV_IOCTL_CATATONIC_CMD) { err = -EACCES; fput(fp); goto out; } } cont: err = fn(fp, sbi, param); if (fp) fput(fp); if (err >= 0 && copy_to_user(user, param, AUTOFS_DEV_IOCTL_SIZE)) err = -EFAULT; out: free_dev_ioctl(param); return err; } static long autofs_dev_ioctl(struct file *file, unsigned int command, unsigned long u) { int err; err = _autofs_dev_ioctl(command, (struct autofs_dev_ioctl __user *) u); return (long) err; } #ifdef CONFIG_COMPAT static long autofs_dev_ioctl_compat(struct file *file, unsigned int command, unsigned long u) { return autofs_dev_ioctl(file, command, (unsigned long) compat_ptr(u)); } #else #define autofs_dev_ioctl_compat NULL #endif static const struct file_operations _dev_ioctl_fops = { .unlocked_ioctl = autofs_dev_ioctl, .compat_ioctl = autofs_dev_ioctl_compat, .owner = THIS_MODULE, .llseek = noop_llseek, }; static struct miscdevice _autofs_dev_ioctl_misc = { .minor = AUTOFS_MINOR, .name = AUTOFS_DEVICE_NAME, .fops = &_dev_ioctl_fops, .mode = 0644, }; MODULE_ALIAS_MISCDEV(AUTOFS_MINOR); MODULE_ALIAS("devname:autofs"); /* Register/deregister misc character device */ int __init autofs_dev_ioctl_init(void) { int r; r = misc_register(&_autofs_dev_ioctl_misc); if (r) { pr_err("misc_register failed for control device\n"); return r; } return 0; } void autofs_dev_ioctl_exit(void) { misc_deregister(&_autofs_dev_ioctl_misc); } |
| 3 3 3 3 3 3 3 3 10 10 10 82 5 1 1 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 2 4 2 2 67 67 67 67 67 14 14 14 14 14 14 14 14 14 14 14 14 36 35 36 36 36 36 36 35 5 5 5 5 5 9 9 9 12 12 9 9 9 9 9 9 12 9 9 9 9 9 9 12 12 12 12 12 12 12 12 12 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 | /* * Copyright (C) 2017 Netronome Systems, Inc. * * This software is licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this * source tree. * * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. */ #include <linux/debugfs.h> #include <linux/etherdevice.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <net/netdev_queues.h> #include <net/page_pool/helpers.h> #include <net/netlink.h> #include <net/net_shaper.h> #include <net/pkt_cls.h> #include <net/rtnetlink.h> #include <net/udp_tunnel.h> #include "netdevsim.h" #define NSIM_RING_SIZE 256 static int nsim_napi_rx(struct nsim_rq *rq, struct sk_buff *skb) { if (skb_queue_len(&rq->skb_queue) > NSIM_RING_SIZE) { dev_kfree_skb_any(skb); return NET_RX_DROP; } skb_queue_tail(&rq->skb_queue, skb); return NET_RX_SUCCESS; } static int nsim_forward_skb(struct net_device *dev, struct sk_buff *skb, struct nsim_rq *rq) { return __dev_forward_skb(dev, skb) ?: nsim_napi_rx(rq, skb); } static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct netdevsim *ns = netdev_priv(dev); struct net_device *peer_dev; unsigned int len = skb->len; struct netdevsim *peer_ns; struct nsim_rq *rq; int rxq; rcu_read_lock(); if (!nsim_ipsec_tx(ns, skb)) goto out_drop_free; peer_ns = rcu_dereference(ns->peer); if (!peer_ns) goto out_drop_free; peer_dev = peer_ns->netdev; rxq = skb_get_queue_mapping(skb); if (rxq >= peer_dev->num_rx_queues) rxq = rxq % peer_dev->num_rx_queues; rq = &peer_ns->rq[rxq]; skb_tx_timestamp(skb); if (unlikely(nsim_forward_skb(peer_dev, skb, rq) == NET_RX_DROP)) goto out_drop_cnt; napi_schedule(&rq->napi); rcu_read_unlock(); u64_stats_update_begin(&ns->syncp); ns->tx_packets++; ns->tx_bytes += len; u64_stats_update_end(&ns->syncp); return NETDEV_TX_OK; out_drop_free: dev_kfree_skb(skb); out_drop_cnt: rcu_read_unlock(); u64_stats_update_begin(&ns->syncp); ns->tx_dropped++; u64_stats_update_end(&ns->syncp); return NETDEV_TX_OK; } static void nsim_set_rx_mode(struct net_device *dev) { } static int nsim_change_mtu(struct net_device *dev, int new_mtu) { struct netdevsim *ns = netdev_priv(dev); if (ns->xdp.prog && new_mtu > NSIM_XDP_MAX_MTU) return -EBUSY; WRITE_ONCE(dev->mtu, new_mtu); return 0; } static void nsim_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct netdevsim *ns = netdev_priv(dev); unsigned int start; do { start = u64_stats_fetch_begin(&ns->syncp); stats->tx_bytes = ns->tx_bytes; stats->tx_packets = ns->tx_packets; stats->tx_dropped = ns->tx_dropped; } while (u64_stats_fetch_retry(&ns->syncp, start)); } static int nsim_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { return nsim_bpf_setup_tc_block_cb(type, type_data, cb_priv); } static int nsim_set_vf_mac(struct net_device *dev, int vf, u8 *mac) { struct netdevsim *ns = netdev_priv(dev); struct nsim_dev *nsim_dev = ns->nsim_dev; /* Only refuse multicast addresses, zero address can mean unset/any. */ if (vf >= nsim_dev_get_vfs(nsim_dev) || is_multicast_ether_addr(mac)) return -EINVAL; memcpy(nsim_dev->vfconfigs[vf].vf_mac, mac, ETH_ALEN); return 0; } static int nsim_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos, __be16 vlan_proto) { struct netdevsim *ns = netdev_priv(dev); struct nsim_dev *nsim_dev = ns->nsim_dev; if (vf >= nsim_dev_get_vfs(nsim_dev) || vlan > 4095 || qos > 7) return -EINVAL; nsim_dev->vfconfigs[vf].vlan = vlan; nsim_dev->vfconfigs[vf].qos = qos; nsim_dev->vfconfigs[vf].vlan_proto = vlan_proto; return 0; } static int nsim_set_vf_rate(struct net_device *dev, int vf, int min, int max) { struct netdevsim *ns = netdev_priv(dev); struct nsim_dev *nsim_dev = ns->nsim_dev; if (nsim_esw_mode_is_switchdev(ns->nsim_dev)) { pr_err("Not supported in switchdev mode. Please use devlink API.\n"); return -EOPNOTSUPP; } if (vf >= nsim_dev_get_vfs(nsim_dev)) return -EINVAL; nsim_dev->vfconfigs[vf].min_tx_rate = min; nsim_dev->vfconfigs[vf].max_tx_rate = max; return 0; } static int nsim_set_vf_spoofchk(struct net_device *dev, int vf, bool val) { struct netdevsim *ns = netdev_priv(dev); struct nsim_dev *nsim_dev = ns->nsim_dev; if (vf >= nsim_dev_get_vfs(nsim_dev)) return -EINVAL; nsim_dev->vfconfigs[vf].spoofchk_enabled = val; return 0; } static int nsim_set_vf_rss_query_en(struct net_device *dev, int vf, bool val) { struct netdevsim *ns = netdev_priv(dev); struct nsim_dev *nsim_dev = ns->nsim_dev; if (vf >= nsim_dev_get_vfs(nsim_dev)) return -EINVAL; nsim_dev->vfconfigs[vf].rss_query_enabled = val; return 0; } static int nsim_set_vf_trust(struct net_device *dev, int vf, bool val) { struct netdevsim *ns = netdev_priv(dev); struct nsim_dev *nsim_dev = ns->nsim_dev; if (vf >= nsim_dev_get_vfs(nsim_dev)) return -EINVAL; nsim_dev->vfconfigs[vf].trusted = val; return 0; } static int nsim_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi) { struct netdevsim *ns = netdev_priv(dev); struct nsim_dev *nsim_dev = ns->nsim_dev; if (vf >= nsim_dev_get_vfs(nsim_dev)) return -EINVAL; ivi->vf = vf; ivi->linkstate = nsim_dev->vfconfigs[vf].link_state; ivi->min_tx_rate = nsim_dev->vfconfigs[vf].min_tx_rate; ivi->max_tx_rate = nsim_dev->vfconfigs[vf].max_tx_rate; ivi->vlan = nsim_dev->vfconfigs[vf].vlan; ivi->vlan_proto = nsim_dev->vfconfigs[vf].vlan_proto; ivi->qos = nsim_dev->vfconfigs[vf].qos; memcpy(&ivi->mac, nsim_dev->vfconfigs[vf].vf_mac, ETH_ALEN); ivi->spoofchk = nsim_dev->vfconfigs[vf].spoofchk_enabled; ivi->trusted = nsim_dev->vfconfigs[vf].trusted; ivi->rss_query_en = nsim_dev->vfconfigs[vf].rss_query_enabled; return 0; } static int nsim_set_vf_link_state(struct net_device *dev, int vf, int state) { struct netdevsim *ns = netdev_priv(dev); struct nsim_dev *nsim_dev = ns->nsim_dev; if (vf >= nsim_dev_get_vfs(nsim_dev)) return -EINVAL; switch (state) { case IFLA_VF_LINK_STATE_AUTO: case IFLA_VF_LINK_STATE_ENABLE: case IFLA_VF_LINK_STATE_DISABLE: break; default: return -EINVAL; } nsim_dev->vfconfigs[vf].link_state = state; return 0; } static void nsim_taprio_stats(struct tc_taprio_qopt_stats *stats) { stats->window_drops = 0; stats->tx_overruns = 0; } static int nsim_setup_tc_taprio(struct net_device *dev, struct tc_taprio_qopt_offload *offload) { int err = 0; switch (offload->cmd) { case TAPRIO_CMD_REPLACE: case TAPRIO_CMD_DESTROY: break; case TAPRIO_CMD_STATS: nsim_taprio_stats(&offload->stats); break; default: err = -EOPNOTSUPP; } return err; } static LIST_HEAD(nsim_block_cb_list); static int nsim_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { struct netdevsim *ns = netdev_priv(dev); switch (type) { case TC_SETUP_QDISC_TAPRIO: return nsim_setup_tc_taprio(dev, type_data); case TC_SETUP_BLOCK: return flow_block_cb_setup_simple(type_data, &nsim_block_cb_list, nsim_setup_tc_block_cb, ns, ns, true); default: return -EOPNOTSUPP; } } static int nsim_set_features(struct net_device *dev, netdev_features_t features) { struct netdevsim *ns = netdev_priv(dev); if ((dev->features & NETIF_F_HW_TC) > (features & NETIF_F_HW_TC)) return nsim_bpf_disable_tc(ns); return 0; } static int nsim_get_iflink(const struct net_device *dev) { struct netdevsim *nsim, *peer; int iflink; nsim = netdev_priv(dev); rcu_read_lock(); peer = rcu_dereference(nsim->peer); iflink = peer ? READ_ONCE(peer->netdev->ifindex) : READ_ONCE(dev->ifindex); rcu_read_unlock(); return iflink; } static int nsim_rcv(struct nsim_rq *rq, int budget) { struct sk_buff *skb; int i; for (i = 0; i < budget; i++) { if (skb_queue_empty(&rq->skb_queue)) break; skb = skb_dequeue(&rq->skb_queue); netif_receive_skb(skb); } return i; } static int nsim_poll(struct napi_struct *napi, int budget) { struct nsim_rq *rq = container_of(napi, struct nsim_rq, napi); int done; done = nsim_rcv(rq, budget); napi_complete(napi); return done; } static int nsim_create_page_pool(struct nsim_rq *rq) { struct page_pool_params p = { .order = 0, .pool_size = NSIM_RING_SIZE, .nid = NUMA_NO_NODE, .dev = &rq->napi.dev->dev, .napi = &rq->napi, .dma_dir = DMA_BIDIRECTIONAL, .netdev = rq->napi.dev, }; rq->page_pool = page_pool_create(&p); if (IS_ERR(rq->page_pool)) { int err = PTR_ERR(rq->page_pool); rq->page_pool = NULL; return err; } return 0; } static int nsim_init_napi(struct netdevsim *ns) { struct net_device *dev = ns->netdev; struct nsim_rq *rq; int err, i; for (i = 0; i < dev->num_rx_queues; i++) { rq = &ns->rq[i]; netif_napi_add(dev, &rq->napi, nsim_poll); } for (i = 0; i < dev->num_rx_queues; i++) { rq = &ns->rq[i]; err = nsim_create_page_pool(rq); if (err) goto err_pp_destroy; } return 0; err_pp_destroy: while (i--) { page_pool_destroy(ns->rq[i].page_pool); ns->rq[i].page_pool = NULL; } for (i = 0; i < dev->num_rx_queues; i++) __netif_napi_del(&ns->rq[i].napi); return err; } static void nsim_enable_napi(struct netdevsim *ns) { struct net_device *dev = ns->netdev; int i; for (i = 0; i < dev->num_rx_queues; i++) { struct nsim_rq *rq = &ns->rq[i]; netif_queue_set_napi(dev, i, NETDEV_QUEUE_TYPE_RX, &rq->napi); napi_enable(&rq->napi); } } static int nsim_open(struct net_device *dev) { struct netdevsim *ns = netdev_priv(dev); int err; err = nsim_init_napi(ns); if (err) return err; nsim_enable_napi(ns); return 0; } static void nsim_del_napi(struct netdevsim *ns) { struct net_device *dev = ns->netdev; int i; for (i = 0; i < dev->num_rx_queues; i++) { struct nsim_rq *rq = &ns->rq[i]; napi_disable(&rq->napi); __netif_napi_del(&rq->napi); } synchronize_net(); for (i = 0; i < dev->num_rx_queues; i++) { page_pool_destroy(ns->rq[i].page_pool); ns->rq[i].page_pool = NULL; } } static int nsim_stop(struct net_device *dev) { struct netdevsim *ns = netdev_priv(dev); struct netdevsim *peer; netif_carrier_off(dev); peer = rtnl_dereference(ns->peer); if (peer) netif_carrier_off(peer->netdev); nsim_del_napi(ns); return 0; } static int nsim_shaper_set(struct net_shaper_binding *binding, const struct net_shaper *shaper, struct netlink_ext_ack *extack) { return 0; } static int nsim_shaper_del(struct net_shaper_binding *binding, const struct net_shaper_handle *handle, struct netlink_ext_ack *extack) { return 0; } static int nsim_shaper_group(struct net_shaper_binding *binding, int leaves_count, const struct net_shaper *leaves, const struct net_shaper *root, struct netlink_ext_ack *extack) { return 0; } static void nsim_shaper_cap(struct net_shaper_binding *binding, enum net_shaper_scope scope, unsigned long *flags) { *flags = ULONG_MAX; } static const struct net_shaper_ops nsim_shaper_ops = { .set = nsim_shaper_set, .delete = nsim_shaper_del, .group = nsim_shaper_group, .capabilities = nsim_shaper_cap, }; static const struct net_device_ops nsim_netdev_ops = { .ndo_start_xmit = nsim_start_xmit, .ndo_set_rx_mode = nsim_set_rx_mode, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = nsim_change_mtu, .ndo_get_stats64 = nsim_get_stats64, .ndo_set_vf_mac = nsim_set_vf_mac, .ndo_set_vf_vlan = nsim_set_vf_vlan, .ndo_set_vf_rate = nsim_set_vf_rate, .ndo_set_vf_spoofchk = nsim_set_vf_spoofchk, .ndo_set_vf_trust = nsim_set_vf_trust, .ndo_get_vf_config = nsim_get_vf_config, .ndo_set_vf_link_state = nsim_set_vf_link_state, .ndo_set_vf_rss_query_en = nsim_set_vf_rss_query_en, .ndo_setup_tc = nsim_setup_tc, .ndo_set_features = nsim_set_features, .ndo_get_iflink = nsim_get_iflink, .ndo_bpf = nsim_bpf, .ndo_open = nsim_open, .ndo_stop = nsim_stop, .net_shaper_ops = &nsim_shaper_ops, }; static const struct net_device_ops nsim_vf_netdev_ops = { .ndo_start_xmit = nsim_start_xmit, .ndo_set_rx_mode = nsim_set_rx_mode, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = nsim_change_mtu, .ndo_get_stats64 = nsim_get_stats64, .ndo_setup_tc = nsim_setup_tc, .ndo_set_features = nsim_set_features, }; /* We don't have true per-queue stats, yet, so do some random fakery here. * Only report stuff for queue 0. */ static void nsim_get_queue_stats_rx(struct net_device *dev, int idx, struct netdev_queue_stats_rx *stats) { struct rtnl_link_stats64 rtstats = {}; if (!idx) nsim_get_stats64(dev, &rtstats); stats->packets = rtstats.rx_packets - !!rtstats.rx_packets; stats->bytes = rtstats.rx_bytes; } static void nsim_get_queue_stats_tx(struct net_device *dev, int idx, struct netdev_queue_stats_tx *stats) { struct rtnl_link_stats64 rtstats = {}; if (!idx) nsim_get_stats64(dev, &rtstats); stats->packets = rtstats.tx_packets - !!rtstats.tx_packets; stats->bytes = rtstats.tx_bytes; } static void nsim_get_base_stats(struct net_device *dev, struct netdev_queue_stats_rx *rx, struct netdev_queue_stats_tx *tx) { struct rtnl_link_stats64 rtstats = {}; nsim_get_stats64(dev, &rtstats); rx->packets = !!rtstats.rx_packets; rx->bytes = 0; tx->packets = !!rtstats.tx_packets; tx->bytes = 0; } static const struct netdev_stat_ops nsim_stat_ops = { .get_queue_stats_tx = nsim_get_queue_stats_tx, .get_queue_stats_rx = nsim_get_queue_stats_rx, .get_base_stats = nsim_get_base_stats, }; static ssize_t nsim_pp_hold_read(struct file *file, char __user *data, size_t count, loff_t *ppos) { struct netdevsim *ns = file->private_data; char buf[3] = "n\n"; if (ns->page) buf[0] = 'y'; return simple_read_from_buffer(data, count, ppos, buf, 2); } static ssize_t nsim_pp_hold_write(struct file *file, const char __user *data, size_t count, loff_t *ppos) { struct netdevsim *ns = file->private_data; ssize_t ret; bool val; ret = kstrtobool_from_user(data, count, &val); if (ret) return ret; rtnl_lock(); ret = count; if (val == !!ns->page) goto exit; if (!netif_running(ns->netdev) && val) { ret = -ENETDOWN; } else if (val) { ns->page = page_pool_dev_alloc_pages(ns->rq[0].page_pool); if (!ns->page) ret = -ENOMEM; } else { page_pool_put_full_page(ns->page->pp, ns->page, false); ns->page = NULL; } exit: rtnl_unlock(); return ret; } static const struct file_operations nsim_pp_hold_fops = { .open = simple_open, .read = nsim_pp_hold_read, .write = nsim_pp_hold_write, .llseek = generic_file_llseek, .owner = THIS_MODULE, }; static void nsim_setup(struct net_device *dev) { ether_setup(dev); eth_hw_addr_random(dev); dev->tx_queue_len = 0; dev->flags &= ~IFF_MULTICAST; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; dev->features |= NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | NETIF_F_TSO; dev->hw_features |= NETIF_F_HW_TC | NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | NETIF_F_TSO; dev->max_mtu = ETH_MAX_MTU; dev->xdp_features = NETDEV_XDP_ACT_HW_OFFLOAD; } static int nsim_queue_init(struct netdevsim *ns) { struct net_device *dev = ns->netdev; int i; ns->rq = kvcalloc(dev->num_rx_queues, sizeof(*ns->rq), GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!ns->rq) return -ENOMEM; for (i = 0; i < dev->num_rx_queues; i++) skb_queue_head_init(&ns->rq[i].skb_queue); return 0; } static void nsim_queue_free(struct netdevsim *ns) { struct net_device *dev = ns->netdev; int i; for (i = 0; i < dev->num_rx_queues; i++) skb_queue_purge_reason(&ns->rq[i].skb_queue, SKB_DROP_REASON_QUEUE_PURGE); kvfree(ns->rq); ns->rq = NULL; } static int nsim_init_netdevsim(struct netdevsim *ns) { struct mock_phc *phc; int err; phc = mock_phc_create(&ns->nsim_bus_dev->dev); if (IS_ERR(phc)) return PTR_ERR(phc); ns->phc = phc; ns->netdev->netdev_ops = &nsim_netdev_ops; ns->netdev->stat_ops = &nsim_stat_ops; err = nsim_udp_tunnels_info_create(ns->nsim_dev, ns->netdev); if (err) goto err_phc_destroy; rtnl_lock(); err = nsim_queue_init(ns); if (err) goto err_utn_destroy; err = nsim_bpf_init(ns); if (err) goto err_rq_destroy; nsim_macsec_init(ns); nsim_ipsec_init(ns); err = register_netdevice(ns->netdev); if (err) goto err_ipsec_teardown; rtnl_unlock(); return 0; err_ipsec_teardown: nsim_ipsec_teardown(ns); nsim_macsec_teardown(ns); nsim_bpf_uninit(ns); err_rq_destroy: nsim_queue_free(ns); err_utn_destroy: rtnl_unlock(); nsim_udp_tunnels_info_destroy(ns->netdev); err_phc_destroy: mock_phc_destroy(ns->phc); return err; } static int nsim_init_netdevsim_vf(struct netdevsim *ns) { int err; ns->netdev->netdev_ops = &nsim_vf_netdev_ops; rtnl_lock(); err = register_netdevice(ns->netdev); rtnl_unlock(); return err; } static void nsim_exit_netdevsim(struct netdevsim *ns) { nsim_udp_tunnels_info_destroy(ns->netdev); mock_phc_destroy(ns->phc); } struct netdevsim * nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port) { struct net_device *dev; struct netdevsim *ns; int err; dev = alloc_netdev_mq(sizeof(*ns), "eth%d", NET_NAME_UNKNOWN, nsim_setup, nsim_dev->nsim_bus_dev->num_queues); if (!dev) return ERR_PTR(-ENOMEM); dev_net_set(dev, nsim_dev_net(nsim_dev)); ns = netdev_priv(dev); ns->netdev = dev; u64_stats_init(&ns->syncp); ns->nsim_dev = nsim_dev; ns->nsim_dev_port = nsim_dev_port; ns->nsim_bus_dev = nsim_dev->nsim_bus_dev; SET_NETDEV_DEV(dev, &ns->nsim_bus_dev->dev); SET_NETDEV_DEVLINK_PORT(dev, &nsim_dev_port->devlink_port); nsim_ethtool_init(ns); if (nsim_dev_port_is_pf(nsim_dev_port)) err = nsim_init_netdevsim(ns); else err = nsim_init_netdevsim_vf(ns); if (err) goto err_free_netdev; ns->pp_dfs = debugfs_create_file("pp_hold", 0600, nsim_dev_port->ddir, ns, &nsim_pp_hold_fops); return ns; err_free_netdev: free_netdev(dev); return ERR_PTR(err); } void nsim_destroy(struct netdevsim *ns) { struct net_device *dev = ns->netdev; struct netdevsim *peer; debugfs_remove(ns->pp_dfs); rtnl_lock(); peer = rtnl_dereference(ns->peer); if (peer) RCU_INIT_POINTER(peer->peer, NULL); RCU_INIT_POINTER(ns->peer, NULL); unregister_netdevice(dev); if (nsim_dev_port_is_pf(ns->nsim_dev_port)) { nsim_macsec_teardown(ns); nsim_ipsec_teardown(ns); nsim_bpf_uninit(ns); nsim_queue_free(ns); } rtnl_unlock(); if (nsim_dev_port_is_pf(ns->nsim_dev_port)) nsim_exit_netdevsim(ns); /* Put this intentionally late to exercise the orphaning path */ if (ns->page) { page_pool_put_full_page(ns->page->pp, ns->page, false); ns->page = NULL; } free_netdev(dev); } bool netdev_is_nsim(struct net_device *dev) { return dev->netdev_ops == &nsim_netdev_ops; } static int nsim_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { NL_SET_ERR_MSG_MOD(extack, "Please use: echo \"[ID] [PORT_COUNT] [NUM_QUEUES]\" > /sys/bus/netdevsim/new_device"); return -EOPNOTSUPP; } static struct rtnl_link_ops nsim_link_ops __read_mostly = { .kind = DRV_NAME, .validate = nsim_validate, }; static int __init nsim_module_init(void) { int err; err = nsim_dev_init(); if (err) return err; err = nsim_bus_init(); if (err) goto err_dev_exit; err = rtnl_link_register(&nsim_link_ops); if (err) goto err_bus_exit; return 0; err_bus_exit: nsim_bus_exit(); err_dev_exit: nsim_dev_exit(); return err; } static void __exit nsim_module_exit(void) { rtnl_link_unregister(&nsim_link_ops); nsim_bus_exit(); nsim_dev_exit(); } module_init(nsim_module_init); module_exit(nsim_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Simulated networking device for testing"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); |
| 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 27 27 27 27 27 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 6 6 6 22 22 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2017, Mellanox Technologies inc. All rights reserved. */ #include <rdma/uverbs_ioctl.h> #include <rdma/rdma_user_ioctl.h> #include <linux/bitops.h> #include "rdma_core.h" #include "uverbs.h" static int ib_uverbs_notsupp(struct uverbs_attr_bundle *attrs) { return -EOPNOTSUPP; } static void *uapi_add_elm(struct uverbs_api *uapi, u32 key, size_t alloc_size) { void *elm; int rc; if (key == UVERBS_API_KEY_ERR) return ERR_PTR(-EOVERFLOW); elm = kzalloc(alloc_size, GFP_KERNEL); if (!elm) return ERR_PTR(-ENOMEM); rc = radix_tree_insert(&uapi->radix, key, elm); if (rc) { kfree(elm); return ERR_PTR(rc); } return elm; } static void *uapi_add_get_elm(struct uverbs_api *uapi, u32 key, size_t alloc_size, bool *exists) { void *elm; elm = uapi_add_elm(uapi, key, alloc_size); if (!IS_ERR(elm)) { *exists = false; return elm; } if (elm != ERR_PTR(-EEXIST)) return elm; elm = radix_tree_lookup(&uapi->radix, key); if (WARN_ON(!elm)) return ERR_PTR(-EINVAL); *exists = true; return elm; } static int uapi_create_write(struct uverbs_api *uapi, struct ib_device *ibdev, const struct uapi_definition *def, u32 obj_key, u32 *cur_method_key) { struct uverbs_api_write_method *method_elm; u32 method_key = obj_key; bool exists; if (def->write.is_ex) method_key |= uapi_key_write_ex_method(def->write.command_num); else method_key |= uapi_key_write_method(def->write.command_num); method_elm = uapi_add_get_elm(uapi, method_key, sizeof(*method_elm), &exists); if (IS_ERR(method_elm)) return PTR_ERR(method_elm); if (WARN_ON(exists && (def->write.is_ex != method_elm->is_ex))) return -EINVAL; method_elm->is_ex = def->write.is_ex; method_elm->handler = def->func_write; if (!def->write.is_ex) method_elm->disabled = !(ibdev->uverbs_cmd_mask & BIT_ULL(def->write.command_num)); if (!def->write.is_ex && def->func_write) { method_elm->has_udata = def->write.has_udata; method_elm->has_resp = def->write.has_resp; method_elm->req_size = def->write.req_size; method_elm->resp_size = def->write.resp_size; } *cur_method_key = method_key; return 0; } static int uapi_merge_method(struct uverbs_api *uapi, struct uverbs_api_object *obj_elm, u32 obj_key, const struct uverbs_method_def *method, bool is_driver) { u32 method_key = obj_key | uapi_key_ioctl_method(method->id); struct uverbs_api_ioctl_method *method_elm; unsigned int i; bool exists; if (!method->attrs) return 0; method_elm = uapi_add_get_elm(uapi, method_key, sizeof(*method_elm), &exists); if (IS_ERR(method_elm)) return PTR_ERR(method_elm); if (exists) { /* * This occurs when a driver uses ADD_UVERBS_ATTRIBUTES_SIMPLE */ if (WARN_ON(method->handler)) return -EINVAL; } else { WARN_ON(!method->handler); rcu_assign_pointer(method_elm->handler, method->handler); if (method->handler != uverbs_destroy_def_handler) method_elm->driver_method = is_driver; } for (i = 0; i != method->num_attrs; i++) { const struct uverbs_attr_def *attr = (*method->attrs)[i]; struct uverbs_api_attr *attr_slot; if (!attr) continue; /* * ENUM_IN contains the 'ids' pointer to the driver's .rodata, * so if it is specified by a driver then it always makes this * into a driver method. */ if (attr->attr.type == UVERBS_ATTR_TYPE_ENUM_IN) method_elm->driver_method |= is_driver; /* * Like other uobject based things we only support a single * uobject being NEW'd or DESTROY'd */ if (attr->attr.type == UVERBS_ATTR_TYPE_IDRS_ARRAY) { u8 access = attr->attr.u2.objs_arr.access; if (WARN_ON(access == UVERBS_ACCESS_NEW || access == UVERBS_ACCESS_DESTROY)) return -EINVAL; } attr_slot = uapi_add_elm(uapi, method_key | uapi_key_attr(attr->id), sizeof(*attr_slot)); /* Attributes are not allowed to be modified by drivers */ if (IS_ERR(attr_slot)) return PTR_ERR(attr_slot); attr_slot->spec = attr->attr; } return 0; } static int uapi_merge_obj_tree(struct uverbs_api *uapi, const struct uverbs_object_def *obj, bool is_driver) { struct uverbs_api_object *obj_elm; unsigned int i; u32 obj_key; bool exists; int rc; obj_key = uapi_key_obj(obj->id); obj_elm = uapi_add_get_elm(uapi, obj_key, sizeof(*obj_elm), &exists); if (IS_ERR(obj_elm)) return PTR_ERR(obj_elm); if (obj->type_attrs) { if (WARN_ON(obj_elm->type_attrs)) return -EINVAL; obj_elm->id = obj->id; obj_elm->type_attrs = obj->type_attrs; obj_elm->type_class = obj->type_attrs->type_class; /* * Today drivers are only permitted to use idr_class and * fd_class types. We can revoke the IDR types during * disassociation, and the FD types require the driver to use * struct file_operations.owner to prevent the driver module * code from unloading while the file is open. This provides * enough safety that uverbs_uobject_fd_release() will * continue to work. Drivers using FD are responsible to * handle disassociation of the device on their own. */ if (WARN_ON(is_driver && obj->type_attrs->type_class != &uverbs_idr_class && obj->type_attrs->type_class != &uverbs_fd_class)) return -EINVAL; } if (!obj->methods) return 0; for (i = 0; i != obj->num_methods; i++) { const struct uverbs_method_def *method = (*obj->methods)[i]; if (!method) continue; rc = uapi_merge_method(uapi, obj_elm, obj_key, method, is_driver); if (rc) return rc; } return 0; } static int uapi_disable_elm(struct uverbs_api *uapi, const struct uapi_definition *def, u32 obj_key, u32 method_key) { bool exists; if (def->scope == UAPI_SCOPE_OBJECT) { struct uverbs_api_object *obj_elm; obj_elm = uapi_add_get_elm( uapi, obj_key, sizeof(*obj_elm), &exists); if (IS_ERR(obj_elm)) return PTR_ERR(obj_elm); obj_elm->disabled = 1; return 0; } if (def->scope == UAPI_SCOPE_METHOD && uapi_key_is_ioctl_method(method_key)) { struct uverbs_api_ioctl_method *method_elm; method_elm = uapi_add_get_elm(uapi, method_key, sizeof(*method_elm), &exists); if (IS_ERR(method_elm)) return PTR_ERR(method_elm); method_elm->disabled = 1; return 0; } if (def->scope == UAPI_SCOPE_METHOD && (uapi_key_is_write_method(method_key) || uapi_key_is_write_ex_method(method_key))) { struct uverbs_api_write_method *write_elm; write_elm = uapi_add_get_elm(uapi, method_key, sizeof(*write_elm), &exists); if (IS_ERR(write_elm)) return PTR_ERR(write_elm); write_elm->disabled = 1; return 0; } WARN_ON(true); return -EINVAL; } static int uapi_merge_def(struct uverbs_api *uapi, struct ib_device *ibdev, const struct uapi_definition *def_list, bool is_driver) { const struct uapi_definition *def = def_list; u32 cur_obj_key = UVERBS_API_KEY_ERR; u32 cur_method_key = UVERBS_API_KEY_ERR; bool exists; int rc; if (!def_list) return 0; for (;; def++) { switch ((enum uapi_definition_kind)def->kind) { case UAPI_DEF_CHAIN: rc = uapi_merge_def(uapi, ibdev, def->chain, is_driver); if (rc) return rc; continue; case UAPI_DEF_CHAIN_OBJ_TREE: if (WARN_ON(def->object_start.object_id != def->chain_obj_tree->id)) return -EINVAL; cur_obj_key = uapi_key_obj(def->object_start.object_id); rc = uapi_merge_obj_tree(uapi, def->chain_obj_tree, is_driver); if (rc) return rc; continue; case UAPI_DEF_END: return 0; case UAPI_DEF_IS_SUPPORTED_DEV_FN: { void **ibdev_fn = (void *)(&ibdev->ops) + def->needs_fn_offset; if (*ibdev_fn) continue; rc = uapi_disable_elm( uapi, def, cur_obj_key, cur_method_key); if (rc) return rc; continue; } case UAPI_DEF_IS_SUPPORTED_FUNC: if (def->func_is_supported(ibdev)) continue; rc = uapi_disable_elm( uapi, def, cur_obj_key, cur_method_key); if (rc) return rc; continue; case UAPI_DEF_OBJECT_START: { struct uverbs_api_object *obj_elm; cur_obj_key = uapi_key_obj(def->object_start.object_id); obj_elm = uapi_add_get_elm(uapi, cur_obj_key, sizeof(*obj_elm), &exists); if (IS_ERR(obj_elm)) return PTR_ERR(obj_elm); continue; } case UAPI_DEF_WRITE: rc = uapi_create_write( uapi, ibdev, def, cur_obj_key, &cur_method_key); if (rc) return rc; continue; } WARN_ON(true); return -EINVAL; } } static int uapi_finalize_ioctl_method(struct uverbs_api *uapi, struct uverbs_api_ioctl_method *method_elm, u32 method_key) { struct radix_tree_iter iter; unsigned int num_attrs = 0; unsigned int max_bkey = 0; bool single_uobj = false; void __rcu **slot; method_elm->destroy_bkey = UVERBS_API_ATTR_BKEY_LEN; radix_tree_for_each_slot (slot, &uapi->radix, &iter, uapi_key_attrs_start(method_key)) { struct uverbs_api_attr *elm = rcu_dereference_protected(*slot, true); u32 attr_key = iter.index & UVERBS_API_ATTR_KEY_MASK; u32 attr_bkey = uapi_bkey_attr(attr_key); u8 type = elm->spec.type; if (uapi_key_attr_to_ioctl_method(iter.index) != uapi_key_attr_to_ioctl_method(method_key)) break; if (elm->spec.mandatory) __set_bit(attr_bkey, method_elm->attr_mandatory); if (elm->spec.is_udata) method_elm->has_udata = true; if (type == UVERBS_ATTR_TYPE_IDR || type == UVERBS_ATTR_TYPE_FD) { u8 access = elm->spec.u.obj.access; /* * Verbs specs may only have one NEW/DESTROY, we don't * have the infrastructure to abort multiple NEW's or * cope with multiple DESTROY failure. */ if (access == UVERBS_ACCESS_NEW || access == UVERBS_ACCESS_DESTROY) { if (WARN_ON(single_uobj)) return -EINVAL; single_uobj = true; if (WARN_ON(!elm->spec.mandatory)) return -EINVAL; } if (access == UVERBS_ACCESS_DESTROY) method_elm->destroy_bkey = attr_bkey; } max_bkey = max(max_bkey, attr_bkey); num_attrs++; } method_elm->key_bitmap_len = max_bkey + 1; WARN_ON(method_elm->key_bitmap_len > UVERBS_API_ATTR_BKEY_LEN); uapi_compute_bundle_size(method_elm, num_attrs); return 0; } static int uapi_finalize(struct uverbs_api *uapi) { const struct uverbs_api_write_method **data; unsigned long max_write_ex = 0; unsigned long max_write = 0; struct radix_tree_iter iter; void __rcu **slot; int rc; int i; radix_tree_for_each_slot (slot, &uapi->radix, &iter, 0) { struct uverbs_api_ioctl_method *method_elm = rcu_dereference_protected(*slot, true); if (uapi_key_is_ioctl_method(iter.index)) { rc = uapi_finalize_ioctl_method(uapi, method_elm, iter.index); if (rc) return rc; } if (uapi_key_is_write_method(iter.index)) max_write = max(max_write, iter.index & UVERBS_API_ATTR_KEY_MASK); if (uapi_key_is_write_ex_method(iter.index)) max_write_ex = max(max_write_ex, iter.index & UVERBS_API_ATTR_KEY_MASK); } uapi->notsupp_method.handler = ib_uverbs_notsupp; uapi->num_write = max_write + 1; uapi->num_write_ex = max_write_ex + 1; data = kmalloc_array(uapi->num_write + uapi->num_write_ex, sizeof(*uapi->write_methods), GFP_KERNEL); if (!data) return -ENOMEM; for (i = 0; i != uapi->num_write + uapi->num_write_ex; i++) data[i] = &uapi->notsupp_method; uapi->write_methods = data; uapi->write_ex_methods = data + uapi->num_write; radix_tree_for_each_slot (slot, &uapi->radix, &iter, 0) { if (uapi_key_is_write_method(iter.index)) uapi->write_methods[iter.index & UVERBS_API_ATTR_KEY_MASK] = rcu_dereference_protected(*slot, true); if (uapi_key_is_write_ex_method(iter.index)) uapi->write_ex_methods[iter.index & UVERBS_API_ATTR_KEY_MASK] = rcu_dereference_protected(*slot, true); } return 0; } static void uapi_remove_range(struct uverbs_api *uapi, u32 start, u32 last) { struct radix_tree_iter iter; void __rcu **slot; radix_tree_for_each_slot (slot, &uapi->radix, &iter, start) { if (iter.index > last) return; kfree(rcu_dereference_protected(*slot, true)); radix_tree_iter_delete(&uapi->radix, &iter, slot); } } static void uapi_remove_object(struct uverbs_api *uapi, u32 obj_key) { uapi_remove_range(uapi, obj_key, obj_key | UVERBS_API_METHOD_KEY_MASK | UVERBS_API_ATTR_KEY_MASK); } static void uapi_remove_method(struct uverbs_api *uapi, u32 method_key) { uapi_remove_range(uapi, method_key, method_key | UVERBS_API_ATTR_KEY_MASK); } static u32 uapi_get_obj_id(struct uverbs_attr_spec *spec) { if (spec->type == UVERBS_ATTR_TYPE_IDR || spec->type == UVERBS_ATTR_TYPE_FD) return spec->u.obj.obj_type; if (spec->type == UVERBS_ATTR_TYPE_IDRS_ARRAY) return spec->u2.objs_arr.obj_type; return UVERBS_API_KEY_ERR; } static void uapi_key_okay(u32 key) { unsigned int count = 0; if (uapi_key_is_object(key)) count++; if (uapi_key_is_ioctl_method(key)) count++; if (uapi_key_is_write_method(key)) count++; if (uapi_key_is_write_ex_method(key)) count++; if (uapi_key_is_attr(key)) count++; WARN(count != 1, "Bad count %u key=%x", count, key); } static void uapi_finalize_disable(struct uverbs_api *uapi) { struct radix_tree_iter iter; u32 starting_key = 0; bool scan_again = false; void __rcu **slot; again: radix_tree_for_each_slot (slot, &uapi->radix, &iter, starting_key) { uapi_key_okay(iter.index); if (uapi_key_is_object(iter.index)) { struct uverbs_api_object *obj_elm = rcu_dereference_protected(*slot, true); if (obj_elm->disabled) { /* Have to check all the attrs again */ scan_again = true; starting_key = iter.index; uapi_remove_object(uapi, iter.index); goto again; } continue; } if (uapi_key_is_ioctl_method(iter.index)) { struct uverbs_api_ioctl_method *method_elm = rcu_dereference_protected(*slot, true); if (method_elm->disabled) { starting_key = iter.index; uapi_remove_method(uapi, iter.index); goto again; } continue; } if (uapi_key_is_write_method(iter.index) || uapi_key_is_write_ex_method(iter.index)) { struct uverbs_api_write_method *method_elm = rcu_dereference_protected(*slot, true); if (method_elm->disabled) { kfree(method_elm); radix_tree_iter_delete(&uapi->radix, &iter, slot); } continue; } if (uapi_key_is_attr(iter.index)) { struct uverbs_api_attr *attr_elm = rcu_dereference_protected(*slot, true); const struct uverbs_api_object *tmp_obj; u32 obj_key; /* * If the method has a mandatory object handle * attribute which relies on an object which is not * present then the entire method is uncallable. */ if (!attr_elm->spec.mandatory) continue; obj_key = uapi_get_obj_id(&attr_elm->spec); if (obj_key == UVERBS_API_KEY_ERR) continue; tmp_obj = uapi_get_object(uapi, obj_key); if (IS_ERR(tmp_obj)) { if (PTR_ERR(tmp_obj) == -ENOMSG) continue; } else { if (!tmp_obj->disabled) continue; } starting_key = iter.index; uapi_remove_method( uapi, iter.index & (UVERBS_API_OBJ_KEY_MASK | UVERBS_API_METHOD_KEY_MASK)); goto again; } WARN_ON(false); } if (!scan_again) return; scan_again = false; starting_key = 0; goto again; } void uverbs_destroy_api(struct uverbs_api *uapi) { if (!uapi) return; uapi_remove_range(uapi, 0, U32_MAX); kfree(uapi->write_methods); kfree(uapi); } static const struct uapi_definition uverbs_core_api[] = { UAPI_DEF_CHAIN(uverbs_def_obj_async_fd), UAPI_DEF_CHAIN(uverbs_def_obj_counters), UAPI_DEF_CHAIN(uverbs_def_obj_cq), UAPI_DEF_CHAIN(uverbs_def_obj_device), UAPI_DEF_CHAIN(uverbs_def_obj_dm), UAPI_DEF_CHAIN(uverbs_def_obj_flow_action), UAPI_DEF_CHAIN(uverbs_def_obj_intf), UAPI_DEF_CHAIN(uverbs_def_obj_mr), UAPI_DEF_CHAIN(uverbs_def_obj_qp), UAPI_DEF_CHAIN(uverbs_def_obj_srq), UAPI_DEF_CHAIN(uverbs_def_obj_wq), UAPI_DEF_CHAIN(uverbs_def_write_intf), {}, }; struct uverbs_api *uverbs_alloc_api(struct ib_device *ibdev) { struct uverbs_api *uapi; int rc; uapi = kzalloc(sizeof(*uapi), GFP_KERNEL); if (!uapi) return ERR_PTR(-ENOMEM); INIT_RADIX_TREE(&uapi->radix, GFP_KERNEL); uapi->driver_id = ibdev->ops.driver_id; rc = uapi_merge_def(uapi, ibdev, uverbs_core_api, false); if (rc) goto err; rc = uapi_merge_def(uapi, ibdev, ibdev->driver_def, true); if (rc) goto err; uapi_finalize_disable(uapi); rc = uapi_finalize(uapi); if (rc) goto err; return uapi; err: if (rc != -ENOMEM) dev_err(&ibdev->dev, "Setup of uverbs_api failed, kernel parsing tree description is not valid (%d)??\n", rc); uverbs_destroy_api(uapi); return ERR_PTR(rc); } /* * The pre version is done before destroying the HW objects, it only blocks * off method access. All methods that require the ib_dev or the module data * must test one of these assignments prior to continuing. */ void uverbs_disassociate_api_pre(struct ib_uverbs_device *uverbs_dev) { struct uverbs_api *uapi = uverbs_dev->uapi; struct radix_tree_iter iter; void __rcu **slot; rcu_assign_pointer(uverbs_dev->ib_dev, NULL); radix_tree_for_each_slot (slot, &uapi->radix, &iter, 0) { if (uapi_key_is_ioctl_method(iter.index)) { struct uverbs_api_ioctl_method *method_elm = rcu_dereference_protected(*slot, true); if (method_elm->driver_method) rcu_assign_pointer(method_elm->handler, NULL); } } synchronize_srcu(&uverbs_dev->disassociate_srcu); } /* * Called when a driver disassociates from the ib_uverbs_device. The * assumption is that the driver module will unload after. Replace everything * related to the driver with NULL as a safety measure. */ void uverbs_disassociate_api(struct uverbs_api *uapi) { struct radix_tree_iter iter; void __rcu **slot; radix_tree_for_each_slot (slot, &uapi->radix, &iter, 0) { if (uapi_key_is_object(iter.index)) { struct uverbs_api_object *object_elm = rcu_dereference_protected(*slot, true); /* * Some type_attrs are in the driver module. We don't * bother to keep track of which since there should be * no use of this after disassociate. */ object_elm->type_attrs = NULL; } else if (uapi_key_is_attr(iter.index)) { struct uverbs_api_attr *elm = rcu_dereference_protected(*slot, true); if (elm->spec.type == UVERBS_ATTR_TYPE_ENUM_IN) elm->spec.u2.enum_def.ids = NULL; } } } |
| 19 | 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 | /* 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> */ #ifndef __LINUX_DMA_FENCE_CHAIN_H #define __LINUX_DMA_FENCE_CHAIN_H #include <linux/dma-fence.h> #include <linux/irq_work.h> #include <linux/slab.h> /** * struct dma_fence_chain - fence to represent an node of a fence chain * @base: fence base class * @prev: previous fence of the chain * @prev_seqno: original previous seqno before garbage collection * @fence: encapsulated fence * @lock: spinlock for fence handling */ struct dma_fence_chain { struct dma_fence base; struct dma_fence __rcu *prev; u64 prev_seqno; struct dma_fence *fence; union { /** * @cb: callback for signaling * * This is used to add the callback for signaling the * complection of the fence chain. Never used at the same time * as the irq work. */ struct dma_fence_cb cb; /** * @work: irq work item for signaling * * Irq work structure to allow us to add the callback without * running into lock inversion. Never used at the same time as * the callback. */ struct irq_work work; }; spinlock_t lock; }; /** * to_dma_fence_chain - cast a fence to a dma_fence_chain * @fence: fence to cast to a dma_fence_array * * Returns NULL if the fence is not a dma_fence_chain, * or the dma_fence_chain otherwise. */ static inline struct dma_fence_chain * to_dma_fence_chain(struct dma_fence *fence) { if (!fence || !dma_fence_is_chain(fence)) return NULL; return container_of(fence, struct dma_fence_chain, base); } /** * dma_fence_chain_contained - return the contained fence * @fence: the fence to test * * If the fence is a dma_fence_chain the function returns the fence contained * inside the chain object, otherwise it returns the fence itself. */ static inline struct dma_fence * dma_fence_chain_contained(struct dma_fence *fence) { struct dma_fence_chain *chain = to_dma_fence_chain(fence); return chain ? chain->fence : fence; } /** * dma_fence_chain_alloc * * Returns a new struct dma_fence_chain object or NULL on failure. * * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). The typecast is * intentional to enforce typesafety. */ #define dma_fence_chain_alloc() \ ((struct dma_fence_chain *)kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL)) /** * dma_fence_chain_free * @chain: chain node to free * * Frees up an allocated but not used struct dma_fence_chain object. This * doesn't need an RCU grace period since the fence was never initialized nor * published. After dma_fence_chain_init() has been called the fence must be * released by calling dma_fence_put(), and not through this function. */ static inline void dma_fence_chain_free(struct dma_fence_chain *chain) { kfree(chain); }; /** * dma_fence_chain_for_each - iterate over all fences in chain * @iter: current fence * @head: starting point * * Iterate over all fences in the chain. We keep a reference to the current * fence while inside the loop which must be dropped when breaking out. * * For a deep dive iterator see dma_fence_unwrap_for_each(). */ #define dma_fence_chain_for_each(iter, head) \ for (iter = dma_fence_get(head); iter; \ iter = dma_fence_chain_walk(iter)) struct dma_fence *dma_fence_chain_walk(struct dma_fence *fence); int dma_fence_chain_find_seqno(struct dma_fence **pfence, uint64_t seqno); void dma_fence_chain_init(struct dma_fence_chain *chain, struct dma_fence *prev, struct dma_fence *fence, uint64_t seqno); #endif /* __LINUX_DMA_FENCE_CHAIN_H */ |
| 5 5 5 5 5 | 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 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2016 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2015 System Fabric Works, Inc. All rights reserved. */ #include "rxe.h" static struct workqueue_struct *rxe_wq; int rxe_alloc_wq(void) { rxe_wq = alloc_workqueue("rxe_wq", WQ_UNBOUND, WQ_MAX_ACTIVE); if (!rxe_wq) return -ENOMEM; return 0; } void rxe_destroy_wq(void) { destroy_workqueue(rxe_wq); } /* Check if task is idle i.e. not running, not scheduled in * work queue and not draining. If so move to busy to * reserve a slot in do_task() by setting to busy and taking * a qp reference to cover the gap from now until the task finishes. * state will move out of busy if task returns a non zero value * in do_task(). If state is already busy it is raised to armed * to indicate to do_task that additional pass should be made * over the task. * Context: caller should hold task->lock. * Returns: true if state transitioned from idle to busy else false. */ static bool __reserve_if_idle(struct rxe_task *task) { WARN_ON(rxe_read(task->qp) <= 0); if (task->state == TASK_STATE_IDLE) { rxe_get(task->qp); task->state = TASK_STATE_BUSY; task->num_sched++; return true; } if (task->state == TASK_STATE_BUSY) task->state = TASK_STATE_ARMED; return false; } /* check if task is idle or drained and not currently * scheduled in the work queue. This routine is * called by rxe_cleanup_task or rxe_disable_task to * see if the queue is empty. * Context: caller should hold task->lock. * Returns true if done else false. */ static bool __is_done(struct rxe_task *task) { if (work_pending(&task->work)) return false; if (task->state == TASK_STATE_IDLE || task->state == TASK_STATE_DRAINED) { return true; } return false; } /* a locked version of __is_done */ static bool is_done(struct rxe_task *task) { unsigned long flags; int done; spin_lock_irqsave(&task->lock, flags); done = __is_done(task); spin_unlock_irqrestore(&task->lock, flags); return done; } /* do_task is a wrapper for the three tasks (requester, * completer, responder) and calls them in a loop until * they return a non-zero value. It is called either * directly by rxe_run_task or indirectly if rxe_sched_task * schedules the task. They must call __reserve_if_idle to * move the task to busy before calling or scheduling. * The task can also be moved to drained or invalid * by calls to rxe_cleanup_task or rxe_disable_task. * In that case tasks which get here are not executed but * just flushed. The tasks are designed to look to see if * there is work to do and then do part of it before returning * here with a return value of zero until all the work * has been consumed then it returns a non-zero value. * The number of times the task can be run is limited by * max iterations so one task cannot hold the cpu forever. * If the limit is hit and work remains the task is rescheduled. */ static void do_task(struct rxe_task *task) { unsigned int iterations; unsigned long flags; int resched = 0; int cont; int ret; WARN_ON(rxe_read(task->qp) <= 0); spin_lock_irqsave(&task->lock, flags); if (task->state >= TASK_STATE_DRAINED) { rxe_put(task->qp); task->num_done++; spin_unlock_irqrestore(&task->lock, flags); return; } spin_unlock_irqrestore(&task->lock, flags); do { iterations = RXE_MAX_ITERATIONS; cont = 0; do { ret = task->func(task->qp); } while (ret == 0 && iterations-- > 0); spin_lock_irqsave(&task->lock, flags); /* we're not done yet but we ran out of iterations. * yield the cpu and reschedule the task */ if (!ret) { task->state = TASK_STATE_IDLE; resched = 1; goto exit; } switch (task->state) { case TASK_STATE_BUSY: task->state = TASK_STATE_IDLE; break; /* someone tried to schedule the task while we * were running, keep going */ case TASK_STATE_ARMED: task->state = TASK_STATE_BUSY; cont = 1; break; case TASK_STATE_DRAINING: task->state = TASK_STATE_DRAINED; break; default: WARN_ON(1); rxe_dbg_qp(task->qp, "unexpected task state = %d\n", task->state); task->state = TASK_STATE_IDLE; } exit: if (!cont) { task->num_done++; if (WARN_ON(task->num_done != task->num_sched)) rxe_dbg_qp( task->qp, "%ld tasks scheduled, %ld tasks done\n", task->num_sched, task->num_done); } spin_unlock_irqrestore(&task->lock, flags); } while (cont); task->ret = ret; if (resched) rxe_sched_task(task); rxe_put(task->qp); } /* wrapper around do_task to fix argument for work queue */ static void do_work(struct work_struct *work) { do_task(container_of(work, struct rxe_task, work)); } int rxe_init_task(struct rxe_task *task, struct rxe_qp *qp, int (*func)(struct rxe_qp *)) { WARN_ON(rxe_read(qp) <= 0); task->qp = qp; task->func = func; task->state = TASK_STATE_IDLE; spin_lock_init(&task->lock); INIT_WORK(&task->work, do_work); return 0; } /* rxe_cleanup_task is only called from rxe_do_qp_cleanup in * process context. The qp is already completed with no * remaining references. Once the queue is drained the * task is moved to invalid and returns. The qp cleanup * code then calls the task functions directly without * using the task struct to drain any late arriving packets * or work requests. */ void rxe_cleanup_task(struct rxe_task *task) { unsigned long flags; spin_lock_irqsave(&task->lock, flags); if (!__is_done(task) && task->state < TASK_STATE_DRAINED) { task->state = TASK_STATE_DRAINING; } else { task->state = TASK_STATE_INVALID; spin_unlock_irqrestore(&task->lock, flags); return; } spin_unlock_irqrestore(&task->lock, flags); /* now the task cannot be scheduled or run just wait * for the previously scheduled tasks to finish. */ while (!is_done(task)) cond_resched(); spin_lock_irqsave(&task->lock, flags); task->state = TASK_STATE_INVALID; spin_unlock_irqrestore(&task->lock, flags); } /* run the task inline if it is currently idle * cannot call do_task holding the lock */ void rxe_run_task(struct rxe_task *task) { unsigned long flags; bool run; WARN_ON(rxe_read(task->qp) <= 0); spin_lock_irqsave(&task->lock, flags); run = __reserve_if_idle(task); spin_unlock_irqrestore(&task->lock, flags); if (run) do_task(task); } /* schedule the task to run later as a work queue entry. * the queue_work call can be called holding * the lock. */ void rxe_sched_task(struct rxe_task *task) { unsigned long flags; WARN_ON(rxe_read(task->qp) <= 0); spin_lock_irqsave(&task->lock, flags); if (__reserve_if_idle(task)) queue_work(rxe_wq, &task->work); spin_unlock_irqrestore(&task->lock, flags); } /* rxe_disable/enable_task are only called from * rxe_modify_qp in process context. Task is moved * to the drained state by do_task. */ void rxe_disable_task(struct rxe_task *task) { unsigned long flags; WARN_ON(rxe_read(task->qp) <= 0); spin_lock_irqsave(&task->lock, flags); if (!__is_done(task) && task->state < TASK_STATE_DRAINED) { task->state = TASK_STATE_DRAINING; } else { task->state = TASK_STATE_DRAINED; spin_unlock_irqrestore(&task->lock, flags); return; } spin_unlock_irqrestore(&task->lock, flags); while (!is_done(task)) cond_resched(); spin_lock_irqsave(&task->lock, flags); task->state = TASK_STATE_DRAINED; spin_unlock_irqrestore(&task->lock, flags); } void rxe_enable_task(struct rxe_task *task) { unsigned long flags; WARN_ON(rxe_read(task->qp) <= 0); spin_lock_irqsave(&task->lock, flags); if (task->state == TASK_STATE_INVALID) { spin_unlock_irqrestore(&task->lock, flags); return; } task->state = TASK_STATE_IDLE; spin_unlock_irqrestore(&task->lock, flags); } |
| 3 3 18 18 18 18 1 3 11 11 3 3 3 3 3 3 3 3 3 2 3 2 1 1 1 3 3 3 3 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 18 1 18 2 2 18 17 17 17 17 17 18 18 1 1 1 4 1 2 2 1 1 1 1 1 1 4 33 32 16 13 14 13 12 11 10 10 7 6 4 3 3 3 33 33 1 1 1 33 33 1 1 1 1 1 1 33 29 29 2 9 9 8 6 6 6 5 3 40 9 3 2 2 1 1 1 1 39 40 40 6 40 40 40 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Antonio Quartulli */ #include "distributed-arp-table.h" #include "main.h" #include <linux/unaligned.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/byteorder/generic.h> #include <linux/container_of.h> #include <linux/errno.h> #include <linux/etherdevice.h> #include <linux/gfp.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/jiffies.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/netlink.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/udp.h> #include <linux/workqueue.h> #include <net/arp.h> #include <net/genetlink.h> #include <net/netlink.h> #include <net/sock.h> #include <uapi/linux/batman_adv.h> #include "bridge_loop_avoidance.h" #include "hard-interface.h" #include "hash.h" #include "log.h" #include "netlink.h" #include "originator.h" #include "send.h" #include "soft-interface.h" #include "translation-table.h" #include "tvlv.h" enum batadv_bootpop { BATADV_BOOTREPLY = 2, }; enum batadv_boothtype { BATADV_HTYPE_ETHERNET = 1, }; enum batadv_dhcpoptioncode { BATADV_DHCP_OPT_PAD = 0, BATADV_DHCP_OPT_MSG_TYPE = 53, BATADV_DHCP_OPT_END = 255, }; enum batadv_dhcptype { BATADV_DHCPACK = 5, }; /* { 99, 130, 83, 99 } */ #define BATADV_DHCP_MAGIC 1669485411 struct batadv_dhcp_packet { __u8 op; __u8 htype; __u8 hlen; __u8 hops; __be32 xid; __be16 secs; __be16 flags; __be32 ciaddr; __be32 yiaddr; __be32 siaddr; __be32 giaddr; __u8 chaddr[16]; __u8 sname[64]; __u8 file[128]; __be32 magic; /* __u8 options[]; */ }; #define BATADV_DHCP_YIADDR_LEN sizeof(((struct batadv_dhcp_packet *)0)->yiaddr) #define BATADV_DHCP_CHADDR_LEN sizeof(((struct batadv_dhcp_packet *)0)->chaddr) static void batadv_dat_purge(struct work_struct *work); /** * batadv_dat_start_timer() - initialise the DAT periodic worker * @bat_priv: the bat priv with all the soft interface information */ static void batadv_dat_start_timer(struct batadv_priv *bat_priv) { queue_delayed_work(batadv_event_workqueue, &bat_priv->dat.work, msecs_to_jiffies(10000)); } /** * batadv_dat_entry_release() - release dat_entry from lists and queue for free * after rcu grace period * @ref: kref pointer of the dat_entry */ static void batadv_dat_entry_release(struct kref *ref) { struct batadv_dat_entry *dat_entry; dat_entry = container_of(ref, struct batadv_dat_entry, refcount); kfree_rcu(dat_entry, rcu); } /** * batadv_dat_entry_put() - decrement the dat_entry refcounter and possibly * release it * @dat_entry: dat_entry to be free'd */ static void batadv_dat_entry_put(struct batadv_dat_entry *dat_entry) { if (!dat_entry) return; kref_put(&dat_entry->refcount, batadv_dat_entry_release); } /** * batadv_dat_to_purge() - check whether a dat_entry has to be purged or not * @dat_entry: the entry to check * * Return: true if the entry has to be purged now, false otherwise. */ static bool batadv_dat_to_purge(struct batadv_dat_entry *dat_entry) { return batadv_has_timed_out(dat_entry->last_update, BATADV_DAT_ENTRY_TIMEOUT); } /** * __batadv_dat_purge() - delete entries from the DAT local storage * @bat_priv: the bat priv with all the soft interface information * @to_purge: function in charge to decide whether an entry has to be purged or * not. This function takes the dat_entry as argument and has to * returns a boolean value: true is the entry has to be deleted, * false otherwise * * Loops over each entry in the DAT local storage and deletes it if and only if * the to_purge function passed as argument returns true. */ static void __batadv_dat_purge(struct batadv_priv *bat_priv, bool (*to_purge)(struct batadv_dat_entry *)) { spinlock_t *list_lock; /* protects write access to the hash lists */ struct batadv_dat_entry *dat_entry; struct hlist_node *node_tmp; struct hlist_head *head; u32 i; if (!bat_priv->dat.hash) return; for (i = 0; i < bat_priv->dat.hash->size; i++) { head = &bat_priv->dat.hash->table[i]; list_lock = &bat_priv->dat.hash->list_locks[i]; spin_lock_bh(list_lock); hlist_for_each_entry_safe(dat_entry, node_tmp, head, hash_entry) { /* if a helper function has been passed as parameter, * ask it if the entry has to be purged or not */ if (to_purge && !to_purge(dat_entry)) continue; hlist_del_rcu(&dat_entry->hash_entry); batadv_dat_entry_put(dat_entry); } spin_unlock_bh(list_lock); } } /** * batadv_dat_purge() - periodic task that deletes old entries from the local * DAT hash table * @work: kernel work struct */ static void batadv_dat_purge(struct work_struct *work) { struct delayed_work *delayed_work; struct batadv_priv_dat *priv_dat; struct batadv_priv *bat_priv; delayed_work = to_delayed_work(work); priv_dat = container_of(delayed_work, struct batadv_priv_dat, work); bat_priv = container_of(priv_dat, struct batadv_priv, dat); __batadv_dat_purge(bat_priv, batadv_dat_to_purge); batadv_dat_start_timer(bat_priv); } /** * batadv_compare_dat() - comparing function used in the local DAT hash table * @node: node in the local table * @data2: second object to compare the node to * * Return: true if the two entries are the same, false otherwise. */ static bool batadv_compare_dat(const struct hlist_node *node, const void *data2) { const void *data1 = container_of(node, struct batadv_dat_entry, hash_entry); return memcmp(data1, data2, sizeof(__be32)) == 0; } /** * batadv_arp_hw_src() - extract the hw_src field from an ARP packet * @skb: ARP packet * @hdr_size: size of the possible header before the ARP packet * * Return: the value of the hw_src field in the ARP packet. */ static u8 *batadv_arp_hw_src(struct sk_buff *skb, int hdr_size) { u8 *addr; addr = (u8 *)(skb->data + hdr_size); addr += ETH_HLEN + sizeof(struct arphdr); return addr; } /** * batadv_arp_ip_src() - extract the ip_src field from an ARP packet * @skb: ARP packet * @hdr_size: size of the possible header before the ARP packet * * Return: the value of the ip_src field in the ARP packet. */ static __be32 batadv_arp_ip_src(struct sk_buff *skb, int hdr_size) { return *(__force __be32 *)(batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN); } /** * batadv_arp_hw_dst() - extract the hw_dst field from an ARP packet * @skb: ARP packet * @hdr_size: size of the possible header before the ARP packet * * Return: the value of the hw_dst field in the ARP packet. */ static u8 *batadv_arp_hw_dst(struct sk_buff *skb, int hdr_size) { return batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN + 4; } /** * batadv_arp_ip_dst() - extract the ip_dst field from an ARP packet * @skb: ARP packet * @hdr_size: size of the possible header before the ARP packet * * Return: the value of the ip_dst field in the ARP packet. */ static __be32 batadv_arp_ip_dst(struct sk_buff *skb, int hdr_size) { u8 *dst = batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN * 2 + 4; return *(__force __be32 *)dst; } /** * batadv_hash_dat() - compute the hash value for an IP address * @data: data to hash * @size: size of the hash table * * Return: the selected index in the hash table for the given data. */ static u32 batadv_hash_dat(const void *data, u32 size) { u32 hash = 0; const struct batadv_dat_entry *dat = data; const unsigned char *key; __be16 vid; u32 i; key = (__force const unsigned char *)&dat->ip; for (i = 0; i < sizeof(dat->ip); i++) { hash += key[i]; hash += (hash << 10); hash ^= (hash >> 6); } vid = htons(dat->vid); key = (__force const unsigned char *)&vid; for (i = 0; i < sizeof(dat->vid); i++) { hash += key[i]; hash += (hash << 10); hash ^= (hash >> 6); } hash += (hash << 3); hash ^= (hash >> 11); hash += (hash << 15); return hash % size; } /** * batadv_dat_entry_hash_find() - look for a given dat_entry in the local hash * table * @bat_priv: the bat priv with all the soft interface information * @ip: search key * @vid: VLAN identifier * * Return: the dat_entry if found, NULL otherwise. */ static struct batadv_dat_entry * batadv_dat_entry_hash_find(struct batadv_priv *bat_priv, __be32 ip, unsigned short vid) { struct hlist_head *head; struct batadv_dat_entry to_find, *dat_entry, *dat_entry_tmp = NULL; struct batadv_hashtable *hash = bat_priv->dat.hash; u32 index; if (!hash) return NULL; to_find.ip = ip; to_find.vid = vid; index = batadv_hash_dat(&to_find, hash->size); head = &hash->table[index]; rcu_read_lock(); hlist_for_each_entry_rcu(dat_entry, head, hash_entry) { if (dat_entry->ip != ip) continue; if (!kref_get_unless_zero(&dat_entry->refcount)) continue; dat_entry_tmp = dat_entry; break; } rcu_read_unlock(); return dat_entry_tmp; } /** * batadv_dat_entry_add() - add a new dat entry or update it if already exists * @bat_priv: the bat priv with all the soft interface information * @ip: ipv4 to add/edit * @mac_addr: mac address to assign to the given ipv4 * @vid: VLAN identifier */ static void batadv_dat_entry_add(struct batadv_priv *bat_priv, __be32 ip, u8 *mac_addr, unsigned short vid) { struct batadv_dat_entry *dat_entry; int hash_added; dat_entry = batadv_dat_entry_hash_find(bat_priv, ip, vid); /* if this entry is already known, just update it */ if (dat_entry) { if (!batadv_compare_eth(dat_entry->mac_addr, mac_addr)) ether_addr_copy(dat_entry->mac_addr, mac_addr); dat_entry->last_update = jiffies; batadv_dbg(BATADV_DBG_DAT, bat_priv, "Entry updated: %pI4 %pM (vid: %d)\n", &dat_entry->ip, dat_entry->mac_addr, batadv_print_vid(vid)); goto out; } dat_entry = kmalloc(sizeof(*dat_entry), GFP_ATOMIC); if (!dat_entry) goto out; dat_entry->ip = ip; dat_entry->vid = vid; ether_addr_copy(dat_entry->mac_addr, mac_addr); dat_entry->last_update = jiffies; kref_init(&dat_entry->refcount); kref_get(&dat_entry->refcount); hash_added = batadv_hash_add(bat_priv->dat.hash, batadv_compare_dat, batadv_hash_dat, dat_entry, &dat_entry->hash_entry); if (unlikely(hash_added != 0)) { /* remove the reference for the hash */ batadv_dat_entry_put(dat_entry); goto out; } batadv_dbg(BATADV_DBG_DAT, bat_priv, "New entry added: %pI4 %pM (vid: %d)\n", &dat_entry->ip, dat_entry->mac_addr, batadv_print_vid(vid)); out: batadv_dat_entry_put(dat_entry); } #ifdef CONFIG_BATMAN_ADV_DEBUG /** * batadv_dbg_arp() - print a debug message containing all the ARP packet * details * @bat_priv: the bat priv with all the soft interface information * @skb: ARP packet * @hdr_size: size of the possible header before the ARP packet * @msg: message to print together with the debugging information */ static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb, int hdr_size, char *msg) { struct batadv_unicast_4addr_packet *unicast_4addr_packet; struct batadv_bcast_packet *bcast_pkt; u8 *orig_addr; __be32 ip_src, ip_dst; if (msg) batadv_dbg(BATADV_DBG_DAT, bat_priv, "%s\n", msg); ip_src = batadv_arp_ip_src(skb, hdr_size); ip_dst = batadv_arp_ip_dst(skb, hdr_size); batadv_dbg(BATADV_DBG_DAT, bat_priv, "ARP MSG = [src: %pM-%pI4 dst: %pM-%pI4]\n", batadv_arp_hw_src(skb, hdr_size), &ip_src, batadv_arp_hw_dst(skb, hdr_size), &ip_dst); if (hdr_size < sizeof(struct batadv_unicast_packet)) return; unicast_4addr_packet = (struct batadv_unicast_4addr_packet *)skb->data; switch (unicast_4addr_packet->u.packet_type) { case BATADV_UNICAST: batadv_dbg(BATADV_DBG_DAT, bat_priv, "* encapsulated within a UNICAST packet\n"); break; case BATADV_UNICAST_4ADDR: batadv_dbg(BATADV_DBG_DAT, bat_priv, "* encapsulated within a UNICAST_4ADDR packet (src: %pM)\n", unicast_4addr_packet->src); switch (unicast_4addr_packet->subtype) { case BATADV_P_DAT_DHT_PUT: batadv_dbg(BATADV_DBG_DAT, bat_priv, "* type: DAT_DHT_PUT\n"); break; case BATADV_P_DAT_DHT_GET: batadv_dbg(BATADV_DBG_DAT, bat_priv, "* type: DAT_DHT_GET\n"); break; case BATADV_P_DAT_CACHE_REPLY: batadv_dbg(BATADV_DBG_DAT, bat_priv, "* type: DAT_CACHE_REPLY\n"); break; case BATADV_P_DATA: batadv_dbg(BATADV_DBG_DAT, bat_priv, "* type: DATA\n"); break; default: batadv_dbg(BATADV_DBG_DAT, bat_priv, "* type: Unknown (%u)!\n", unicast_4addr_packet->u.packet_type); } break; case BATADV_BCAST: bcast_pkt = (struct batadv_bcast_packet *)unicast_4addr_packet; orig_addr = bcast_pkt->orig; batadv_dbg(BATADV_DBG_DAT, bat_priv, "* encapsulated within a BCAST packet (src: %pM)\n", orig_addr); break; default: batadv_dbg(BATADV_DBG_DAT, bat_priv, "* encapsulated within an unknown packet type (0x%x)\n", unicast_4addr_packet->u.packet_type); } } #else static void batadv_dbg_arp(struct batadv_priv *bat_priv, struct sk_buff *skb, int hdr_size, char *msg) { } #endif /* CONFIG_BATMAN_ADV_DEBUG */ /** * batadv_is_orig_node_eligible() - check whether a node can be a DHT candidate * @res: the array with the already selected candidates * @select: number of already selected candidates * @tmp_max: address of the currently evaluated node * @max: current round max address * @last_max: address of the last selected candidate * @candidate: orig_node under evaluation * @max_orig_node: last selected candidate * * Return: true if the node has been elected as next candidate or false * otherwise. */ static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res, int select, batadv_dat_addr_t tmp_max, batadv_dat_addr_t max, batadv_dat_addr_t last_max, struct batadv_orig_node *candidate, struct batadv_orig_node *max_orig_node) { bool ret = false; int j; /* check if orig node candidate is running DAT */ if (!test_bit(BATADV_ORIG_CAPA_HAS_DAT, &candidate->capabilities)) goto out; /* Check if this node has already been selected... */ for (j = 0; j < select; j++) if (res[j].orig_node == candidate) break; /* ..and possibly skip it */ if (j < select) goto out; /* sanity check: has it already been selected? This should not happen */ if (tmp_max > last_max) goto out; /* check if during this iteration an originator with a closer dht * address has already been found */ if (tmp_max < max) goto out; /* this is an hash collision with the temporary selected node. Choose * the one with the lowest address */ if (tmp_max == max && max_orig_node && batadv_compare_eth(candidate->orig, max_orig_node->orig)) goto out; ret = true; out: return ret; } /** * batadv_choose_next_candidate() - select the next DHT candidate * @bat_priv: the bat priv with all the soft interface information * @cands: candidates array * @select: number of candidates already present in the array * @ip_key: key to look up in the DHT * @last_max: pointer where the address of the selected candidate will be saved */ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv, struct batadv_dat_candidate *cands, int select, batadv_dat_addr_t ip_key, batadv_dat_addr_t *last_max) { batadv_dat_addr_t max = 0; batadv_dat_addr_t tmp_max = 0; struct batadv_orig_node *orig_node, *max_orig_node = NULL; struct batadv_hashtable *hash = bat_priv->orig_hash; struct hlist_head *head; int i; /* if no node is eligible as candidate, leave the candidate type as * NOT_FOUND */ cands[select].type = BATADV_DAT_CANDIDATE_NOT_FOUND; /* iterate over the originator list and find the node with the closest * dat_address which has not been selected yet */ for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(orig_node, head, hash_entry) { /* the dht space is a ring using unsigned addresses */ tmp_max = BATADV_DAT_ADDR_MAX - orig_node->dat_addr + ip_key; if (!batadv_is_orig_node_eligible(cands, select, tmp_max, max, *last_max, orig_node, max_orig_node)) continue; if (!kref_get_unless_zero(&orig_node->refcount)) continue; max = tmp_max; batadv_orig_node_put(max_orig_node); max_orig_node = orig_node; } rcu_read_unlock(); } if (max_orig_node) { cands[select].type = BATADV_DAT_CANDIDATE_ORIG; cands[select].orig_node = max_orig_node; batadv_dbg(BATADV_DBG_DAT, bat_priv, "dat_select_candidates() %d: selected %pM addr=%u dist=%u\n", select, max_orig_node->orig, max_orig_node->dat_addr, max); } *last_max = max; } /** * batadv_dat_select_candidates() - select the nodes which the DHT message has * to be sent to * @bat_priv: the bat priv with all the soft interface information * @ip_dst: ipv4 to look up in the DHT * @vid: VLAN identifier * * An originator O is selected if and only if its DHT_ID value is one of three * closest values (from the LEFT, with wrap around if needed) then the hash * value of the key. ip_dst is the key. * * Return: the candidate array of size BATADV_DAT_CANDIDATE_NUM. */ static struct batadv_dat_candidate * batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst, unsigned short vid) { int select; batadv_dat_addr_t last_max = BATADV_DAT_ADDR_MAX, ip_key; struct batadv_dat_candidate *res; struct batadv_dat_entry dat; if (!bat_priv->orig_hash) return NULL; res = kmalloc_array(BATADV_DAT_CANDIDATES_NUM, sizeof(*res), GFP_ATOMIC); if (!res) return NULL; dat.ip = ip_dst; dat.vid = vid; ip_key = (batadv_dat_addr_t)batadv_hash_dat(&dat, BATADV_DAT_ADDR_MAX); batadv_dbg(BATADV_DBG_DAT, bat_priv, "%s(): IP=%pI4 hash(IP)=%u\n", __func__, &ip_dst, ip_key); for (select = 0; select < BATADV_DAT_CANDIDATES_NUM; select++) batadv_choose_next_candidate(bat_priv, res, select, ip_key, &last_max); return res; } /** * batadv_dat_forward_data() - copy and send payload to the selected candidates * @bat_priv: the bat priv with all the soft interface information * @skb: payload to send * @ip: the DHT key * @vid: VLAN identifier * @packet_subtype: unicast4addr packet subtype to use * * This function copies the skb with pskb_copy() and is sent as a unicast packet * to each of the selected candidates. * * Return: true if the packet is sent to at least one candidate, false * otherwise. */ static bool batadv_dat_forward_data(struct batadv_priv *bat_priv, struct sk_buff *skb, __be32 ip, unsigned short vid, int packet_subtype) { int i; bool ret = false; int send_status; struct batadv_neigh_node *neigh_node = NULL; struct sk_buff *tmp_skb; struct batadv_dat_candidate *cand; cand = batadv_dat_select_candidates(bat_priv, ip, vid); if (!cand) return ret; batadv_dbg(BATADV_DBG_DAT, bat_priv, "DHT_SEND for %pI4\n", &ip); for (i = 0; i < BATADV_DAT_CANDIDATES_NUM; i++) { if (cand[i].type == BATADV_DAT_CANDIDATE_NOT_FOUND) continue; neigh_node = batadv_orig_router_get(cand[i].orig_node, BATADV_IF_DEFAULT); if (!neigh_node) goto free_orig; tmp_skb = pskb_copy_for_clone(skb, GFP_ATOMIC); if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, tmp_skb, cand[i].orig_node, packet_subtype)) { kfree_skb(tmp_skb); goto free_neigh; } send_status = batadv_send_unicast_skb(tmp_skb, neigh_node); if (send_status == NET_XMIT_SUCCESS) { /* count the sent packet */ switch (packet_subtype) { case BATADV_P_DAT_DHT_GET: batadv_inc_counter(bat_priv, BATADV_CNT_DAT_GET_TX); break; case BATADV_P_DAT_DHT_PUT: batadv_inc_counter(bat_priv, BATADV_CNT_DAT_PUT_TX); break; } /* packet sent to a candidate: return true */ ret = true; } free_neigh: batadv_neigh_node_put(neigh_node); free_orig: batadv_orig_node_put(cand[i].orig_node); } kfree(cand); return ret; } /** * batadv_dat_tvlv_container_update() - update the dat tvlv container after dat * setting change * @bat_priv: the bat priv with all the soft interface information */ static void batadv_dat_tvlv_container_update(struct batadv_priv *bat_priv) { char dat_mode; dat_mode = atomic_read(&bat_priv->distributed_arp_table); switch (dat_mode) { case 0: batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_DAT, 1); break; case 1: batadv_tvlv_container_register(bat_priv, BATADV_TVLV_DAT, 1, NULL, 0); break; } } /** * batadv_dat_status_update() - update the dat tvlv container after dat * setting change * @net_dev: the soft interface net device */ void batadv_dat_status_update(struct net_device *net_dev) { struct batadv_priv *bat_priv = netdev_priv(net_dev); batadv_dat_tvlv_container_update(bat_priv); } /** * batadv_dat_tvlv_ogm_handler_v1() - process incoming dat tvlv container * @bat_priv: the bat priv with all the soft interface information * @orig: the orig_node of the ogm * @flags: flags indicating the tvlv state (see batadv_tvlv_handler_flags) * @tvlv_value: tvlv buffer containing the gateway data * @tvlv_value_len: tvlv buffer length */ static void batadv_dat_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 flags, void *tvlv_value, u16 tvlv_value_len) { if (flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) clear_bit(BATADV_ORIG_CAPA_HAS_DAT, &orig->capabilities); else set_bit(BATADV_ORIG_CAPA_HAS_DAT, &orig->capabilities); } /** * batadv_dat_hash_free() - free the local DAT hash table * @bat_priv: the bat priv with all the soft interface information */ static void batadv_dat_hash_free(struct batadv_priv *bat_priv) { if (!bat_priv->dat.hash) return; __batadv_dat_purge(bat_priv, NULL); batadv_hash_destroy(bat_priv->dat.hash); bat_priv->dat.hash = NULL; } /** * batadv_dat_init() - initialise the DAT internals * @bat_priv: the bat priv with all the soft interface information * * Return: 0 in case of success, a negative error code otherwise */ int batadv_dat_init(struct batadv_priv *bat_priv) { if (bat_priv->dat.hash) return 0; bat_priv->dat.hash = batadv_hash_new(1024); if (!bat_priv->dat.hash) return -ENOMEM; INIT_DELAYED_WORK(&bat_priv->dat.work, batadv_dat_purge); batadv_dat_start_timer(bat_priv); batadv_tvlv_handler_register(bat_priv, batadv_dat_tvlv_ogm_handler_v1, NULL, NULL, BATADV_TVLV_DAT, 1, BATADV_TVLV_HANDLER_OGM_CIFNOTFND); batadv_dat_tvlv_container_update(bat_priv); return 0; } /** * batadv_dat_free() - free the DAT internals * @bat_priv: the bat priv with all the soft interface information */ void batadv_dat_free(struct batadv_priv *bat_priv) { batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_DAT, 1); batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_DAT, 1); cancel_delayed_work_sync(&bat_priv->dat.work); batadv_dat_hash_free(bat_priv); } /** * batadv_dat_cache_dump_entry() - dump one entry of the DAT cache table to a * netlink socket * @msg: buffer for the message * @portid: netlink port * @cb: Control block containing additional options * @dat_entry: entry to dump * * Return: 0 or error code. */ static int batadv_dat_cache_dump_entry(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_dat_entry *dat_entry) { int msecs; void *hdr; hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq, &batadv_netlink_family, NLM_F_MULTI, BATADV_CMD_GET_DAT_CACHE); if (!hdr) return -ENOBUFS; genl_dump_check_consistent(cb, hdr); msecs = jiffies_to_msecs(jiffies - dat_entry->last_update); if (nla_put_in_addr(msg, BATADV_ATTR_DAT_CACHE_IP4ADDRESS, dat_entry->ip) || nla_put(msg, BATADV_ATTR_DAT_CACHE_HWADDRESS, ETH_ALEN, dat_entry->mac_addr) || nla_put_u16(msg, BATADV_ATTR_DAT_CACHE_VID, dat_entry->vid) || nla_put_u32(msg, BATADV_ATTR_LAST_SEEN_MSECS, msecs)) { genlmsg_cancel(msg, hdr); return -EMSGSIZE; } genlmsg_end(msg, hdr); return 0; } /** * batadv_dat_cache_dump_bucket() - dump one bucket of the DAT cache table to * a netlink socket * @msg: buffer for the message * @portid: netlink port * @cb: Control block containing additional options * @hash: hash to dump * @bucket: bucket index to dump * @idx_skip: How many entries to skip * * Return: 0 or error code. */ static int batadv_dat_cache_dump_bucket(struct sk_buff *msg, u32 portid, struct netlink_callback *cb, struct batadv_hashtable *hash, unsigned int bucket, int *idx_skip) { struct batadv_dat_entry *dat_entry; int idx = 0; spin_lock_bh(&hash->list_locks[bucket]); cb->seq = atomic_read(&hash->generation) << 1 | 1; hlist_for_each_entry(dat_entry, &hash->table[bucket], hash_entry) { if (idx < *idx_skip) goto skip; if (batadv_dat_cache_dump_entry(msg, portid, cb, dat_entry)) { spin_unlock_bh(&hash->list_locks[bucket]); *idx_skip = idx; return -EMSGSIZE; } skip: idx++; } spin_unlock_bh(&hash->list_locks[bucket]); return 0; } /** * batadv_dat_cache_dump() - dump DAT cache table to a netlink socket * @msg: buffer for the message * @cb: callback structure containing arguments * * Return: message length. */ int batadv_dat_cache_dump(struct sk_buff *msg, struct netlink_callback *cb) { struct batadv_hard_iface *primary_if = NULL; int portid = NETLINK_CB(cb->skb).portid; struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_hashtable *hash; struct batadv_priv *bat_priv; int bucket = cb->args[0]; int idx = cb->args[1]; int ifindex; int ret = 0; ifindex = batadv_netlink_get_ifindex(cb->nlh, BATADV_ATTR_MESH_IFINDEX); if (!ifindex) return -EINVAL; soft_iface = dev_get_by_index(net, ifindex); if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { ret = -ENODEV; goto out; } bat_priv = netdev_priv(soft_iface); hash = bat_priv->dat.hash; primary_if = batadv_primary_if_get_selected(bat_priv); if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) { ret = -ENOENT; goto out; } while (bucket < hash->size) { if (batadv_dat_cache_dump_bucket(msg, portid, cb, hash, bucket, &idx)) break; bucket++; idx = 0; } cb->args[0] = bucket; cb->args[1] = idx; ret = msg->len; out: batadv_hardif_put(primary_if); dev_put(soft_iface); return ret; } /** * batadv_arp_get_type() - parse an ARP packet and gets the type * @bat_priv: the bat priv with all the soft interface information * @skb: packet to analyse * @hdr_size: size of the possible header before the ARP packet in the skb * * Return: the ARP type if the skb contains a valid ARP packet, 0 otherwise. */ static u16 batadv_arp_get_type(struct batadv_priv *bat_priv, struct sk_buff *skb, int hdr_size) { struct arphdr *arphdr; struct ethhdr *ethhdr; __be32 ip_src, ip_dst; u8 *hw_src, *hw_dst; u16 type = 0; /* pull the ethernet header */ if (unlikely(!pskb_may_pull(skb, hdr_size + ETH_HLEN))) goto out; ethhdr = (struct ethhdr *)(skb->data + hdr_size); if (ethhdr->h_proto != htons(ETH_P_ARP)) goto out; /* pull the ARP payload */ if (unlikely(!pskb_may_pull(skb, hdr_size + ETH_HLEN + arp_hdr_len(skb->dev)))) goto out; arphdr = (struct arphdr *)(skb->data + hdr_size + ETH_HLEN); /* check whether the ARP packet carries a valid IP information */ if (arphdr->ar_hrd != htons(ARPHRD_ETHER)) goto out; if (arphdr->ar_pro != htons(ETH_P_IP)) goto out; if (arphdr->ar_hln != ETH_ALEN) goto out; if (arphdr->ar_pln != 4) goto out; /* Check for bad reply/request. If the ARP message is not sane, DAT * will simply ignore it */ ip_src = batadv_arp_ip_src(skb, hdr_size); ip_dst = batadv_arp_ip_dst(skb, hdr_size); if (ipv4_is_loopback(ip_src) || ipv4_is_multicast(ip_src) || ipv4_is_loopback(ip_dst) || ipv4_is_multicast(ip_dst) || ipv4_is_zeronet(ip_src) || ipv4_is_lbcast(ip_src) || ipv4_is_zeronet(ip_dst) || ipv4_is_lbcast(ip_dst)) goto out; hw_src = batadv_arp_hw_src(skb, hdr_size); if (is_zero_ether_addr(hw_src) || is_multicast_ether_addr(hw_src)) goto out; /* don't care about the destination MAC address in ARP requests */ if (arphdr->ar_op != htons(ARPOP_REQUEST)) { hw_dst = batadv_arp_hw_dst(skb, hdr_size); if (is_zero_ether_addr(hw_dst) || is_multicast_ether_addr(hw_dst)) goto out; } type = ntohs(arphdr->ar_op); out: return type; } /** * batadv_dat_get_vid() - extract the VLAN identifier from skb if any * @skb: the buffer containing the packet to extract the VID from * @hdr_size: the size of the batman-adv header encapsulating the packet * * Return: If the packet embedded in the skb is vlan tagged this function * returns the VID with the BATADV_VLAN_HAS_TAG flag. Otherwise BATADV_NO_FLAGS * is returned. */ static unsigned short batadv_dat_get_vid(struct sk_buff *skb, int *hdr_size) { unsigned short vid; vid = batadv_get_vid(skb, *hdr_size); /* ARP parsing functions jump forward of hdr_size + ETH_HLEN. * If the header contained in the packet is a VLAN one (which is longer) * hdr_size is updated so that the functions will still skip the * correct amount of bytes. */ if (vid & BATADV_VLAN_HAS_TAG) *hdr_size += VLAN_HLEN; return vid; } /** * batadv_dat_arp_create_reply() - create an ARP Reply * @bat_priv: the bat priv with all the soft interface information * @ip_src: ARP sender IP * @ip_dst: ARP target IP * @hw_src: Ethernet source and ARP sender MAC * @hw_dst: Ethernet destination and ARP target MAC * @vid: VLAN identifier (optional, set to zero otherwise) * * Creates an ARP Reply from the given values, optionally encapsulated in a * VLAN header. * * Return: An skb containing an ARP Reply. */ static struct sk_buff * batadv_dat_arp_create_reply(struct batadv_priv *bat_priv, __be32 ip_src, __be32 ip_dst, u8 *hw_src, u8 *hw_dst, unsigned short vid) { struct sk_buff *skb; skb = arp_create(ARPOP_REPLY, ETH_P_ARP, ip_dst, bat_priv->soft_iface, ip_src, hw_dst, hw_src, hw_dst); if (!skb) return NULL; skb_reset_mac_header(skb); if (vid & BATADV_VLAN_HAS_TAG) skb = vlan_insert_tag(skb, htons(ETH_P_8021Q), vid & VLAN_VID_MASK); return skb; } /** * batadv_dat_snoop_outgoing_arp_request() - snoop the ARP request and try to * answer using DAT * @bat_priv: the bat priv with all the soft interface information * @skb: packet to check * * Return: true if the message has been sent to the dht candidates, false * otherwise. In case of a positive return value the message has to be enqueued * to permit the fallback. */ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv, struct sk_buff *skb) { u16 type = 0; __be32 ip_dst, ip_src; u8 *hw_src; bool ret = false; struct batadv_dat_entry *dat_entry = NULL; struct sk_buff *skb_new; struct net_device *soft_iface = bat_priv->soft_iface; int hdr_size = 0; unsigned short vid; if (!atomic_read(&bat_priv->distributed_arp_table)) goto out; vid = batadv_dat_get_vid(skb, &hdr_size); type = batadv_arp_get_type(bat_priv, skb, hdr_size); /* If the node gets an ARP_REQUEST it has to send a DHT_GET unicast * message to the selected DHT candidates */ if (type != ARPOP_REQUEST) goto out; batadv_dbg_arp(bat_priv, skb, hdr_size, "Parsing outgoing ARP REQUEST"); ip_src = batadv_arp_ip_src(skb, hdr_size); hw_src = batadv_arp_hw_src(skb, hdr_size); ip_dst = batadv_arp_ip_dst(skb, hdr_size); batadv_dat_entry_add(bat_priv, ip_src, hw_src, vid); dat_entry = batadv_dat_entry_hash_find(bat_priv, ip_dst, vid); if (dat_entry) { /* If the ARP request is destined for a local client the local * client will answer itself. DAT would only generate a * duplicate packet. * * Moreover, if the soft-interface is enslaved into a bridge, an * additional DAT answer may trigger kernel warnings about * a packet coming from the wrong port. */ if (batadv_is_my_client(bat_priv, dat_entry->mac_addr, vid)) { ret = true; goto out; } /* If BLA is enabled, only send ARP replies if we have claimed * the destination for the ARP request or if no one else of * the backbone gws belonging to our backbone has claimed the * destination. */ if (!batadv_bla_check_claim(bat_priv, dat_entry->mac_addr, vid)) { batadv_dbg(BATADV_DBG_DAT, bat_priv, "Device %pM claimed by another backbone gw. Don't send ARP reply!", dat_entry->mac_addr); ret = true; goto out; } skb_new = batadv_dat_arp_create_reply(bat_priv, ip_dst, ip_src, dat_entry->mac_addr, hw_src, vid); if (!skb_new) goto out; skb_new->protocol = eth_type_trans(skb_new, soft_iface); batadv_inc_counter(bat_priv, BATADV_CNT_RX); batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES, skb->len + ETH_HLEN + hdr_size); netif_rx(skb_new); batadv_dbg(BATADV_DBG_DAT, bat_priv, "ARP request replied locally\n"); ret = true; } else { /* Send the request to the DHT */ ret = batadv_dat_forward_data(bat_priv, skb, ip_dst, vid, BATADV_P_DAT_DHT_GET); } out: batadv_dat_entry_put(dat_entry); return ret; } /** * batadv_dat_snoop_incoming_arp_request() - snoop the ARP request and try to * answer using the local DAT storage * @bat_priv: the bat priv with all the soft interface information * @skb: packet to check * @hdr_size: size of the encapsulation header * * Return: true if the request has been answered, false otherwise. */ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv, struct sk_buff *skb, int hdr_size) { u16 type; __be32 ip_src, ip_dst; u8 *hw_src; struct sk_buff *skb_new; struct batadv_dat_entry *dat_entry = NULL; bool ret = false; unsigned short vid; int err; if (!atomic_read(&bat_priv->distributed_arp_table)) goto out; vid = batadv_dat_get_vid(skb, &hdr_size); type = batadv_arp_get_type(bat_priv, skb, hdr_size); if (type != ARPOP_REQUEST) goto out; hw_src = batadv_arp_hw_src(skb, hdr_size); ip_src = batadv_arp_ip_src(skb, hdr_size); ip_dst = batadv_arp_ip_dst(skb, hdr_size); batadv_dbg_arp(bat_priv, skb, hdr_size, "Parsing incoming ARP REQUEST"); batadv_dat_entry_add(bat_priv, ip_src, hw_src, vid); dat_entry = batadv_dat_entry_hash_find(bat_priv, ip_dst, vid); if (!dat_entry) goto out; skb_new = batadv_dat_arp_create_reply(bat_priv, ip_dst, ip_src, dat_entry->mac_addr, hw_src, vid); if (!skb_new) goto out; /* To preserve backwards compatibility, the node has choose the outgoing * format based on the incoming request packet type. The assumption is * that a node not using the 4addr packet format doesn't support it. */ if (hdr_size == sizeof(struct batadv_unicast_4addr_packet)) err = batadv_send_skb_via_tt_4addr(bat_priv, skb_new, BATADV_P_DAT_CACHE_REPLY, NULL, vid); else err = batadv_send_skb_via_tt(bat_priv, skb_new, NULL, vid); if (err != NET_XMIT_DROP) { batadv_inc_counter(bat_priv, BATADV_CNT_DAT_CACHED_REPLY_TX); ret = true; } out: batadv_dat_entry_put(dat_entry); if (ret) kfree_skb(skb); return ret; } /** * batadv_dat_snoop_outgoing_arp_reply() - snoop the ARP reply and fill the DHT * @bat_priv: the bat priv with all the soft interface information * @skb: packet to check */ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv, struct sk_buff *skb) { u16 type; __be32 ip_src, ip_dst; u8 *hw_src, *hw_dst; int hdr_size = 0; unsigned short vid; if (!atomic_read(&bat_priv->distributed_arp_table)) return; vid = batadv_dat_get_vid(skb, &hdr_size); type = batadv_arp_get_type(bat_priv, skb, hdr_size); if (type != ARPOP_REPLY) return; batadv_dbg_arp(bat_priv, skb, hdr_size, "Parsing outgoing ARP REPLY"); hw_src = batadv_arp_hw_src(skb, hdr_size); ip_src = batadv_arp_ip_src(skb, hdr_size); hw_dst = batadv_arp_hw_dst(skb, hdr_size); ip_dst = batadv_arp_ip_dst(skb, hdr_size); batadv_dat_entry_add(bat_priv, ip_src, hw_src, vid); batadv_dat_entry_add(bat_priv, ip_dst, hw_dst, vid); /* Send the ARP reply to the candidates for both the IP addresses that * the node obtained from the ARP reply */ batadv_dat_forward_data(bat_priv, skb, ip_src, vid, BATADV_P_DAT_DHT_PUT); batadv_dat_forward_data(bat_priv, skb, ip_dst, vid, BATADV_P_DAT_DHT_PUT); } /** * batadv_dat_snoop_incoming_arp_reply() - snoop the ARP reply and fill the * local DAT storage only * @bat_priv: the bat priv with all the soft interface information * @skb: packet to check * @hdr_size: size of the encapsulation header * * Return: true if the packet was snooped and consumed by DAT. False if the * packet has to be delivered to the interface */ bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, struct sk_buff *skb, int hdr_size) { struct batadv_dat_entry *dat_entry = NULL; u16 type; __be32 ip_src, ip_dst; u8 *hw_src, *hw_dst; bool dropped = false; unsigned short vid; if (!atomic_read(&bat_priv->distributed_arp_table)) goto out; vid = batadv_dat_get_vid(skb, &hdr_size); type = batadv_arp_get_type(bat_priv, skb, hdr_size); if (type != ARPOP_REPLY) goto out; batadv_dbg_arp(bat_priv, skb, hdr_size, "Parsing incoming ARP REPLY"); hw_src = batadv_arp_hw_src(skb, hdr_size); ip_src = batadv_arp_ip_src(skb, hdr_size); hw_dst = batadv_arp_hw_dst(skb, hdr_size); ip_dst = batadv_arp_ip_dst(skb, hdr_size); /* If ip_dst is already in cache and has the right mac address, * drop this frame if this ARP reply is destined for us because it's * most probably an ARP reply generated by another node of the DHT. * We have most probably received already a reply earlier. Delivering * this frame would lead to doubled receive of an ARP reply. */ dat_entry = batadv_dat_entry_hash_find(bat_priv, ip_src, vid); if (dat_entry && batadv_compare_eth(hw_src, dat_entry->mac_addr)) { batadv_dbg(BATADV_DBG_DAT, bat_priv, "Doubled ARP reply removed: ARP MSG = [src: %pM-%pI4 dst: %pM-%pI4]; dat_entry: %pM-%pI4\n", hw_src, &ip_src, hw_dst, &ip_dst, dat_entry->mac_addr, &dat_entry->ip); dropped = true; } /* Update our internal cache with both the IP addresses the node got * within the ARP reply */ batadv_dat_entry_add(bat_priv, ip_src, hw_src, vid); batadv_dat_entry_add(bat_priv, ip_dst, hw_dst, vid); if (dropped) goto out; /* If BLA is enabled, only forward ARP replies if we have claimed the * source of the ARP reply or if no one else of the same backbone has * already claimed that client. This prevents that different gateways * to the same backbone all forward the ARP reply leading to multiple * replies in the backbone. */ if (!batadv_bla_check_claim(bat_priv, hw_src, vid)) { batadv_dbg(BATADV_DBG_DAT, bat_priv, "Device %pM claimed by another backbone gw. Drop ARP reply.\n", hw_src); dropped = true; goto out; } /* if this REPLY is directed to a client of mine, let's deliver the * packet to the interface */ dropped = !batadv_is_my_client(bat_priv, hw_dst, vid); /* if this REPLY is sent on behalf of a client of mine, let's drop the * packet because the client will reply by itself */ dropped |= batadv_is_my_client(bat_priv, hw_src, vid); out: if (dropped) kfree_skb(skb); batadv_dat_entry_put(dat_entry); /* if dropped == false -> deliver to the interface */ return dropped; } /** * batadv_dat_check_dhcp_ipudp() - check skb for IP+UDP headers valid for DHCP * @skb: the packet to check * @ip_src: a buffer to store the IPv4 source address in * * Checks whether the given skb has an IP and UDP header valid for a DHCP * message from a DHCP server. And if so, stores the IPv4 source address in * the provided buffer. * * Return: True if valid, false otherwise. */ static bool batadv_dat_check_dhcp_ipudp(struct sk_buff *skb, __be32 *ip_src) { unsigned int offset = skb_network_offset(skb); struct udphdr *udphdr, _udphdr; struct iphdr *iphdr, _iphdr; iphdr = skb_header_pointer(skb, offset, sizeof(_iphdr), &_iphdr); if (!iphdr || iphdr->version != 4 || iphdr->ihl * 4 < sizeof(_iphdr)) return false; if (iphdr->protocol != IPPROTO_UDP) return false; offset += iphdr->ihl * 4; skb_set_transport_header(skb, offset); udphdr = skb_header_pointer(skb, offset, sizeof(_udphdr), &_udphdr); if (!udphdr || udphdr->source != htons(67)) return false; *ip_src = get_unaligned(&iphdr->saddr); return true; } /** * batadv_dat_check_dhcp() - examine packet for valid DHCP message * @skb: the packet to check * @proto: ethernet protocol hint (behind a potential vlan) * @ip_src: a buffer to store the IPv4 source address in * * Checks whether the given skb is a valid DHCP packet. And if so, stores the * IPv4 source address in the provided buffer. * * Caller needs to ensure that the skb network header is set correctly. * * Return: If skb is a valid DHCP packet, then returns its op code * (e.g. BOOTREPLY vs. BOOTREQUEST). Otherwise returns -EINVAL. */ static int batadv_dat_check_dhcp(struct sk_buff *skb, __be16 proto, __be32 *ip_src) { __be32 *magic, _magic; unsigned int offset; struct { __u8 op; __u8 htype; __u8 hlen; __u8 hops; } *dhcp_h, _dhcp_h; if (proto != htons(ETH_P_IP)) return -EINVAL; if (!batadv_dat_check_dhcp_ipudp(skb, ip_src)) return -EINVAL; offset = skb_transport_offset(skb) + sizeof(struct udphdr); if (skb->len < offset + sizeof(struct batadv_dhcp_packet)) return -EINVAL; dhcp_h = skb_header_pointer(skb, offset, sizeof(_dhcp_h), &_dhcp_h); if (!dhcp_h || dhcp_h->htype != BATADV_HTYPE_ETHERNET || dhcp_h->hlen != ETH_ALEN) return -EINVAL; offset += offsetof(struct batadv_dhcp_packet, magic); magic = skb_header_pointer(skb, offset, sizeof(_magic), &_magic); if (!magic || get_unaligned(magic) != htonl(BATADV_DHCP_MAGIC)) return -EINVAL; return dhcp_h->op; } /** * batadv_dat_get_dhcp_message_type() - get message type of a DHCP packet * @skb: the DHCP packet to parse * * Iterates over the DHCP options of the given DHCP packet to find a * DHCP Message Type option and parse it. * * Caller needs to ensure that the given skb is a valid DHCP packet and * that the skb transport header is set correctly. * * Return: The found DHCP message type value, if found. -EINVAL otherwise. */ static int batadv_dat_get_dhcp_message_type(struct sk_buff *skb) { unsigned int offset = skb_transport_offset(skb) + sizeof(struct udphdr); u8 *type, _type; struct { u8 type; u8 len; } *tl, _tl; offset += sizeof(struct batadv_dhcp_packet); while ((tl = skb_header_pointer(skb, offset, sizeof(_tl), &_tl))) { if (tl->type == BATADV_DHCP_OPT_MSG_TYPE) break; if (tl->type == BATADV_DHCP_OPT_END) break; if (tl->type == BATADV_DHCP_OPT_PAD) offset++; else offset += tl->len + sizeof(_tl); } /* Option Overload Code not supported */ if (!tl || tl->type != BATADV_DHCP_OPT_MSG_TYPE || tl->len != sizeof(_type)) return -EINVAL; offset += sizeof(_tl); type = skb_header_pointer(skb, offset, sizeof(_type), &_type); if (!type) return -EINVAL; return *type; } /** * batadv_dat_dhcp_get_yiaddr() - get yiaddr from a DHCP packet * @skb: the DHCP packet to parse * @buf: a buffer to store the yiaddr in * * Caller needs to ensure that the given skb is a valid DHCP packet and * that the skb transport header is set correctly. * * Return: True on success, false otherwise. */ static bool batadv_dat_dhcp_get_yiaddr(struct sk_buff *skb, __be32 *buf) { unsigned int offset = skb_transport_offset(skb) + sizeof(struct udphdr); __be32 *yiaddr; offset += offsetof(struct batadv_dhcp_packet, yiaddr); yiaddr = skb_header_pointer(skb, offset, BATADV_DHCP_YIADDR_LEN, buf); if (!yiaddr) return false; if (yiaddr != buf) *buf = get_unaligned(yiaddr); return true; } /** * batadv_dat_get_dhcp_chaddr() - get chaddr from a DHCP packet * @skb: the DHCP packet to parse * @buf: a buffer to store the chaddr in * * Caller needs to ensure that the given skb is a valid DHCP packet and * that the skb transport header is set correctly. * * Return: True on success, false otherwise */ static bool batadv_dat_get_dhcp_chaddr(struct sk_buff *skb, u8 *buf) { unsigned int offset = skb_transport_offset(skb) + sizeof(struct udphdr); u8 *chaddr; offset += offsetof(struct batadv_dhcp_packet, chaddr); chaddr = skb_header_pointer(skb, offset, BATADV_DHCP_CHADDR_LEN, buf); if (!chaddr) return false; if (chaddr != buf) memcpy(buf, chaddr, BATADV_DHCP_CHADDR_LEN); return true; } /** * batadv_dat_put_dhcp() - puts addresses from a DHCP packet into the DHT and * DAT cache * @bat_priv: the bat priv with all the soft interface information * @chaddr: the DHCP client MAC address * @yiaddr: the DHCP client IP address * @hw_dst: the DHCP server MAC address * @ip_dst: the DHCP server IP address * @vid: VLAN identifier * * Adds given MAC/IP pairs to the local DAT cache and propagates them further * into the DHT. * * For the DHT propagation, client MAC + IP will appear as the ARP Reply * transmitter (and hw_dst/ip_dst as the target). */ static void batadv_dat_put_dhcp(struct batadv_priv *bat_priv, u8 *chaddr, __be32 yiaddr, u8 *hw_dst, __be32 ip_dst, unsigned short vid) { struct sk_buff *skb; skb = batadv_dat_arp_create_reply(bat_priv, yiaddr, ip_dst, chaddr, hw_dst, vid); if (!skb) return; skb_set_network_header(skb, ETH_HLEN); batadv_dat_entry_add(bat_priv, yiaddr, chaddr, vid); batadv_dat_entry_add(bat_priv, ip_dst, hw_dst, vid); batadv_dat_forward_data(bat_priv, skb, yiaddr, vid, BATADV_P_DAT_DHT_PUT); batadv_dat_forward_data(bat_priv, skb, ip_dst, vid, BATADV_P_DAT_DHT_PUT); consume_skb(skb); batadv_dbg(BATADV_DBG_DAT, bat_priv, "Snooped from outgoing DHCPACK (server address): %pI4, %pM (vid: %i)\n", &ip_dst, hw_dst, batadv_print_vid(vid)); batadv_dbg(BATADV_DBG_DAT, bat_priv, "Snooped from outgoing DHCPACK (client address): %pI4, %pM (vid: %i)\n", &yiaddr, chaddr, batadv_print_vid(vid)); } /** * batadv_dat_check_dhcp_ack() - examine packet for valid DHCP message * @skb: the packet to check * @proto: ethernet protocol hint (behind a potential vlan) * @ip_src: a buffer to store the IPv4 source address in * @chaddr: a buffer to store the DHCP Client Hardware Address in * @yiaddr: a buffer to store the DHCP Your IP Address in * * Checks whether the given skb is a valid DHCPACK. And if so, stores the * IPv4 server source address (ip_src), client MAC address (chaddr) and client * IPv4 address (yiaddr) in the provided buffers. * * Caller needs to ensure that the skb network header is set correctly. * * Return: True if the skb is a valid DHCPACK. False otherwise. */ static bool batadv_dat_check_dhcp_ack(struct sk_buff *skb, __be16 proto, __be32 *ip_src, u8 *chaddr, __be32 *yiaddr) { int type; type = batadv_dat_check_dhcp(skb, proto, ip_src); if (type != BATADV_BOOTREPLY) return false; type = batadv_dat_get_dhcp_message_type(skb); if (type != BATADV_DHCPACK) return false; if (!batadv_dat_dhcp_get_yiaddr(skb, yiaddr)) return false; if (!batadv_dat_get_dhcp_chaddr(skb, chaddr)) return false; return true; } /** * batadv_dat_snoop_outgoing_dhcp_ack() - snoop DHCPACK and fill DAT with it * @bat_priv: the bat priv with all the soft interface information * @skb: the packet to snoop * @proto: ethernet protocol hint (behind a potential vlan) * @vid: VLAN identifier * * This function first checks whether the given skb is a valid DHCPACK. If * so then its source MAC and IP as well as its DHCP Client Hardware Address * field and DHCP Your IP Address field are added to the local DAT cache and * propagated into the DHT. * * Caller needs to ensure that the skb mac and network headers are set * correctly. */ void batadv_dat_snoop_outgoing_dhcp_ack(struct batadv_priv *bat_priv, struct sk_buff *skb, __be16 proto, unsigned short vid) { u8 chaddr[BATADV_DHCP_CHADDR_LEN]; __be32 ip_src, yiaddr; if (!atomic_read(&bat_priv->distributed_arp_table)) return; if (!batadv_dat_check_dhcp_ack(skb, proto, &ip_src, chaddr, &yiaddr)) return; batadv_dat_put_dhcp(bat_priv, chaddr, yiaddr, eth_hdr(skb)->h_source, ip_src, vid); } /** * batadv_dat_snoop_incoming_dhcp_ack() - snoop DHCPACK and fill DAT cache * @bat_priv: the bat priv with all the soft interface information * @skb: the packet to snoop * @hdr_size: header size, up to the tail of the batman-adv header * * This function first checks whether the given skb is a valid DHCPACK. If * so then its source MAC and IP as well as its DHCP Client Hardware Address * field and DHCP Your IP Address field are added to the local DAT cache. */ void batadv_dat_snoop_incoming_dhcp_ack(struct batadv_priv *bat_priv, struct sk_buff *skb, int hdr_size) { u8 chaddr[BATADV_DHCP_CHADDR_LEN]; struct ethhdr *ethhdr; __be32 ip_src, yiaddr; unsigned short vid; __be16 proto; u8 *hw_src; if (!atomic_read(&bat_priv->distributed_arp_table)) return; if (unlikely(!pskb_may_pull(skb, hdr_size + ETH_HLEN))) return; ethhdr = (struct ethhdr *)(skb->data + hdr_size); skb_set_network_header(skb, hdr_size + ETH_HLEN); proto = ethhdr->h_proto; if (!batadv_dat_check_dhcp_ack(skb, proto, &ip_src, chaddr, &yiaddr)) return; hw_src = ethhdr->h_source; vid = batadv_dat_get_vid(skb, &hdr_size); batadv_dat_entry_add(bat_priv, yiaddr, chaddr, vid); batadv_dat_entry_add(bat_priv, ip_src, hw_src, vid); batadv_dbg(BATADV_DBG_DAT, bat_priv, "Snooped from incoming DHCPACK (server address): %pI4, %pM (vid: %i)\n", &ip_src, hw_src, batadv_print_vid(vid)); batadv_dbg(BATADV_DBG_DAT, bat_priv, "Snooped from incoming DHCPACK (client address): %pI4, %pM (vid: %i)\n", &yiaddr, chaddr, batadv_print_vid(vid)); } /** * batadv_dat_drop_broadcast_packet() - check if an ARP request has to be * dropped (because the node has already obtained the reply via DAT) or not * @bat_priv: the bat priv with all the soft interface information * @forw_packet: the broadcast packet * * Return: true if the node can drop the packet, false otherwise. */ bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet) { u16 type; __be32 ip_dst; struct batadv_dat_entry *dat_entry = NULL; bool ret = false; int hdr_size = sizeof(struct batadv_bcast_packet); unsigned short vid; if (!atomic_read(&bat_priv->distributed_arp_table)) goto out; /* If this packet is an ARP_REQUEST and the node already has the * information that it is going to ask, then the packet can be dropped */ if (batadv_forw_packet_is_rebroadcast(forw_packet)) goto out; vid = batadv_dat_get_vid(forw_packet->skb, &hdr_size); type = batadv_arp_get_type(bat_priv, forw_packet->skb, hdr_size); if (type != ARPOP_REQUEST) goto out; ip_dst = batadv_arp_ip_dst(forw_packet->skb, hdr_size); dat_entry = batadv_dat_entry_hash_find(bat_priv, ip_dst, vid); /* check if the node already got this entry */ if (!dat_entry) { batadv_dbg(BATADV_DBG_DAT, bat_priv, "ARP Request for %pI4: fallback\n", &ip_dst); goto out; } batadv_dbg(BATADV_DBG_DAT, bat_priv, "ARP Request for %pI4: fallback prevented\n", &ip_dst); ret = true; out: batadv_dat_entry_put(dat_entry); return ret; } |
| 492 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Filesystem parameter description and parser * * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_FS_PARSER_H #define _LINUX_FS_PARSER_H #include <linux/fs_context.h> struct path; struct constant_table { const char *name; int value; }; struct fs_parameter_spec; struct fs_parse_result; typedef int fs_param_type(struct p_log *, const struct fs_parameter_spec *, struct fs_parameter *, struct fs_parse_result *); /* * The type of parameter expected. */ fs_param_type fs_param_is_bool, fs_param_is_u32, fs_param_is_s32, fs_param_is_u64, fs_param_is_enum, fs_param_is_string, fs_param_is_blob, fs_param_is_blockdev, fs_param_is_path, fs_param_is_fd, fs_param_is_uid, fs_param_is_gid, fs_param_is_file_or_string; /* * Specification of the type of value a parameter wants. * * Note that the fsparam_flag(), fsparam_string(), fsparam_u32(), ... macros * should be used to generate elements of this type. */ struct fs_parameter_spec { const char *name; fs_param_type *type; /* The desired parameter type */ u8 opt; /* Option number (returned by fs_parse()) */ unsigned short flags; #define fs_param_neg_with_no 0x0002 /* "noxxx" is negative param */ #define fs_param_can_be_empty 0x0004 /* "xxx=" is allowed */ #define fs_param_deprecated 0x0008 /* The param is deprecated */ const void *data; }; /* * Result of parse. */ struct fs_parse_result { bool negated; /* T if param was "noxxx" */ union { bool boolean; /* For spec_bool */ int int_32; /* For spec_s32/spec_enum */ unsigned int uint_32; /* For spec_u32{,_octal,_hex}/spec_enum */ u64 uint_64; /* For spec_u64 */ kuid_t uid; kgid_t gid; }; }; extern int __fs_parse(struct p_log *log, const struct fs_parameter_spec *desc, struct fs_parameter *value, struct fs_parse_result *result); static inline int fs_parse(struct fs_context *fc, const struct fs_parameter_spec *desc, struct fs_parameter *param, struct fs_parse_result *result) { return __fs_parse(&fc->log, desc, param, result); } extern int fs_lookup_param(struct fs_context *fc, struct fs_parameter *param, bool want_bdev, unsigned int flags, struct path *_path); extern int lookup_constant(const struct constant_table tbl[], const char *name, int not_found); #ifdef CONFIG_VALIDATE_FS_PARSER extern bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, int low, int high, int special); extern bool fs_validate_description(const char *name, const struct fs_parameter_spec *desc); #else static inline bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size, int low, int high, int special) { return true; } static inline bool fs_validate_description(const char *name, const struct fs_parameter_spec *desc) { return true; } #endif /* * Parameter type, name, index and flags element constructors. Use as: * * fsparam_xxxx("foo", Opt_foo) * * If existing helpers are not enough, direct use of __fsparam() would * work, but any such case is probably a sign that new helper is needed. * Helpers will remain stable; low-level implementation may change. */ #define __fsparam(TYPE, NAME, OPT, FLAGS, DATA) \ { \ .name = NAME, \ .opt = OPT, \ .type = TYPE, \ .flags = FLAGS, \ .data = DATA \ } #define fsparam_flag(NAME, OPT) __fsparam(NULL, NAME, OPT, 0, NULL) #define fsparam_flag_no(NAME, OPT) \ __fsparam(NULL, NAME, OPT, fs_param_neg_with_no, NULL) #define fsparam_bool(NAME, OPT) __fsparam(fs_param_is_bool, NAME, OPT, 0, NULL) #define fsparam_u32(NAME, OPT) __fsparam(fs_param_is_u32, NAME, OPT, 0, NULL) #define fsparam_u32oct(NAME, OPT) \ __fsparam(fs_param_is_u32, NAME, OPT, 0, (void *)8) #define fsparam_u32hex(NAME, OPT) \ __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *)16) #define fsparam_s32(NAME, OPT) __fsparam(fs_param_is_s32, NAME, OPT, 0, NULL) #define fsparam_u64(NAME, OPT) __fsparam(fs_param_is_u64, NAME, OPT, 0, NULL) #define fsparam_enum(NAME, OPT, array) __fsparam(fs_param_is_enum, NAME, OPT, 0, array) #define fsparam_string(NAME, OPT) \ __fsparam(fs_param_is_string, NAME, OPT, 0, NULL) #define fsparam_blob(NAME, OPT) __fsparam(fs_param_is_blob, NAME, OPT, 0, NULL) #define fsparam_bdev(NAME, OPT) __fsparam(fs_param_is_blockdev, NAME, OPT, 0, NULL) #define fsparam_path(NAME, OPT) __fsparam(fs_param_is_path, NAME, OPT, 0, NULL) #define fsparam_fd(NAME, OPT) __fsparam(fs_param_is_fd, NAME, OPT, 0, NULL) #define fsparam_file_or_string(NAME, OPT) \ __fsparam(fs_param_is_file_or_string, NAME, OPT, 0, NULL) #define fsparam_uid(NAME, OPT) __fsparam(fs_param_is_uid, NAME, OPT, 0, NULL) #define fsparam_gid(NAME, OPT) __fsparam(fs_param_is_gid, NAME, OPT, 0, NULL) /* String parameter that allows empty argument */ #define fsparam_string_empty(NAME, OPT) \ __fsparam(fs_param_is_string, NAME, OPT, fs_param_can_be_empty, NULL) #endif /* _LINUX_FS_PARSER_H */ |
| 181 10 182 10 68 103 6 6 6 6 102 65 103 103 103 103 27 28 13 17 14 161 28 161 25 21 161 108 109 77 108 76 103 31 103 109 109 109 109 108 109 109 108 3 3 3 25 86 86 86 226 133 133 133 133 176 64 108 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Tty buffer allocation management */ #include <linux/types.h> #include <linux/errno.h> #include <linux/minmax.h> #include <linux/tty.h> #include <linux/tty_buffer.h> #include <linux/tty_driver.h> #include <linux/tty_flip.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/bitops.h> #include <linux/delay.h> #include <linux/module.h> #include <linux/ratelimit.h> #include "tty.h" #define MIN_TTYB_SIZE 256 #define TTYB_ALIGN_MASK 0xff /* * Byte threshold to limit memory consumption for flip buffers. * The actual memory limit is > 2x this amount. */ #define TTYB_DEFAULT_MEM_LIMIT (640 * 1024UL) /* * We default to dicing tty buffer allocations to this many characters * in order to avoid multiple page allocations. We know the size of * tty_buffer itself but it must also be taken into account that the * buffer is 256 byte aligned. See tty_buffer_find for the allocation * logic this must match. */ #define TTY_BUFFER_PAGE (((PAGE_SIZE - sizeof(struct tty_buffer)) / 2) & ~TTYB_ALIGN_MASK) /** * tty_buffer_lock_exclusive - gain exclusive access to buffer * @port: tty port owning the flip buffer * * Guarantees safe use of the &tty_ldisc_ops.receive_buf() method by excluding * the buffer work and any pending flush from using the flip buffer. Data can * continue to be added concurrently to the flip buffer from the driver side. * * See also tty_buffer_unlock_exclusive(). */ void tty_buffer_lock_exclusive(struct tty_port *port) { struct tty_bufhead *buf = &port->buf; atomic_inc(&buf->priority); mutex_lock(&buf->lock); } EXPORT_SYMBOL_GPL(tty_buffer_lock_exclusive); /** * tty_buffer_unlock_exclusive - release exclusive access * @port: tty port owning the flip buffer * * The buffer work is restarted if there is data in the flip buffer. * * See also tty_buffer_lock_exclusive(). */ void tty_buffer_unlock_exclusive(struct tty_port *port) { struct tty_bufhead *buf = &port->buf; bool restart = buf->head->commit != buf->head->read; atomic_dec(&buf->priority); mutex_unlock(&buf->lock); if (restart) queue_work(system_unbound_wq, &buf->work); } EXPORT_SYMBOL_GPL(tty_buffer_unlock_exclusive); /** * tty_buffer_space_avail - return unused buffer space * @port: tty port owning the flip buffer * * Returns: the # of bytes which can be written by the driver without reaching * the buffer limit. * * Note: this does not guarantee that memory is available to write the returned * # of bytes (use tty_prepare_flip_string() to pre-allocate if memory * guarantee is required). */ unsigned int tty_buffer_space_avail(struct tty_port *port) { int space = port->buf.mem_limit - atomic_read(&port->buf.mem_used); return max(space, 0); } EXPORT_SYMBOL_GPL(tty_buffer_space_avail); static void tty_buffer_reset(struct tty_buffer *p, size_t size) { p->used = 0; p->size = size; p->next = NULL; p->commit = 0; p->lookahead = 0; p->read = 0; p->flags = true; } /** * tty_buffer_free_all - free buffers used by a tty * @port: tty port to free from * * Remove all the buffers pending on a tty whether queued with data or in the * free ring. Must be called when the tty is no longer in use. */ void tty_buffer_free_all(struct tty_port *port) { struct tty_bufhead *buf = &port->buf; struct tty_buffer *p, *next; struct llist_node *llist; unsigned int freed = 0; int still_used; while ((p = buf->head) != NULL) { buf->head = p->next; freed += p->size; if (p->size > 0) kfree(p); } llist = llist_del_all(&buf->free); llist_for_each_entry_safe(p, next, llist, free) kfree(p); tty_buffer_reset(&buf->sentinel, 0); buf->head = &buf->sentinel; buf->tail = &buf->sentinel; still_used = atomic_xchg(&buf->mem_used, 0); WARN(still_used != freed, "we still have not freed %d bytes!", still_used - freed); } /** * tty_buffer_alloc - allocate a tty buffer * @port: tty port * @size: desired size (characters) * * Allocate a new tty buffer to hold the desired number of characters. We * round our buffers off in 256 character chunks to get better allocation * behaviour. * * Returns: %NULL if out of memory or the allocation would exceed the per * device queue. */ static struct tty_buffer *tty_buffer_alloc(struct tty_port *port, size_t size) { struct llist_node *free; struct tty_buffer *p; /* Round the buffer size out */ size = __ALIGN_MASK(size, TTYB_ALIGN_MASK); if (size <= MIN_TTYB_SIZE) { free = llist_del_first(&port->buf.free); if (free) { p = llist_entry(free, struct tty_buffer, free); goto found; } } /* Should possibly check if this fails for the largest buffer we * have queued and recycle that ? */ if (atomic_read(&port->buf.mem_used) > port->buf.mem_limit) return NULL; p = kmalloc(struct_size(p, data, 2 * size), GFP_ATOMIC | __GFP_NOWARN); if (p == NULL) return NULL; found: tty_buffer_reset(p, size); atomic_add(size, &port->buf.mem_used); return p; } /** * tty_buffer_free - free a tty buffer * @port: tty port owning the buffer * @b: the buffer to free * * Free a tty buffer, or add it to the free list according to our internal * strategy. */ static void tty_buffer_free(struct tty_port *port, struct tty_buffer *b) { struct tty_bufhead *buf = &port->buf; /* Dumb strategy for now - should keep some stats */ WARN_ON(atomic_sub_return(b->size, &buf->mem_used) < 0); if (b->size > MIN_TTYB_SIZE) kfree(b); else if (b->size > 0) llist_add(&b->free, &buf->free); } /** * tty_buffer_flush - flush full tty buffers * @tty: tty to flush * @ld: optional ldisc ptr (must be referenced) * * Flush all the buffers containing receive data. If @ld != %NULL, flush the * ldisc input buffer. * * Locking: takes buffer lock to ensure single-threaded flip buffer 'consumer'. */ void tty_buffer_flush(struct tty_struct *tty, struct tty_ldisc *ld) { struct tty_port *port = tty->port; struct tty_bufhead *buf = &port->buf; struct tty_buffer *next; atomic_inc(&buf->priority); mutex_lock(&buf->lock); /* paired w/ release in __tty_buffer_request_room; ensures there are * no pending memory accesses to the freed buffer */ while ((next = smp_load_acquire(&buf->head->next)) != NULL) { tty_buffer_free(port, buf->head); buf->head = next; } buf->head->read = buf->head->commit; buf->head->lookahead = buf->head->read; if (ld && ld->ops->flush_buffer) ld->ops->flush_buffer(tty); atomic_dec(&buf->priority); mutex_unlock(&buf->lock); } /** * __tty_buffer_request_room - grow tty buffer if needed * @port: tty port * @size: size desired * @flags: buffer has to store flags along character data * * Make at least @size bytes of linear space available for the tty buffer. * * Will change over to a new buffer if the current buffer is encoded as * %TTY_NORMAL (so has no flags buffer) and the new buffer requires a flags * buffer. * * Returns: the size we managed to find. */ static int __tty_buffer_request_room(struct tty_port *port, size_t size, bool flags) { struct tty_bufhead *buf = &port->buf; struct tty_buffer *n, *b = buf->tail; size_t left = (b->flags ? 1 : 2) * b->size - b->used; bool change = !b->flags && flags; if (!change && left >= size) return size; /* This is the slow path - looking for new buffers to use */ n = tty_buffer_alloc(port, size); if (n == NULL) return change ? 0 : left; n->flags = flags; buf->tail = n; /* * Paired w/ acquire in flush_to_ldisc() and lookahead_bufs() * ensures they see all buffer data. */ smp_store_release(&b->commit, b->used); /* * Paired w/ acquire in flush_to_ldisc() and lookahead_bufs() * ensures the latest commit value can be read before the head * is advanced to the next buffer. */ smp_store_release(&b->next, n); return size; } int tty_buffer_request_room(struct tty_port *port, size_t size) { return __tty_buffer_request_room(port, size, true); } EXPORT_SYMBOL_GPL(tty_buffer_request_room); size_t __tty_insert_flip_string_flags(struct tty_port *port, const u8 *chars, const u8 *flags, bool mutable_flags, size_t size) { bool need_flags = mutable_flags || flags[0] != TTY_NORMAL; size_t copied = 0; do { size_t goal = min_t(size_t, size - copied, TTY_BUFFER_PAGE); size_t space = __tty_buffer_request_room(port, goal, need_flags); struct tty_buffer *tb = port->buf.tail; if (unlikely(space == 0)) break; memcpy(char_buf_ptr(tb, tb->used), chars, space); if (mutable_flags) { memcpy(flag_buf_ptr(tb, tb->used), flags, space); flags += space; } else if (tb->flags) { memset(flag_buf_ptr(tb, tb->used), flags[0], space); } else { /* tb->flags should be available once requested */ WARN_ON_ONCE(need_flags); } tb->used += space; copied += space; chars += space; /* There is a small chance that we need to split the data over * several buffers. If this is the case we must loop. */ } while (unlikely(size > copied)); return copied; } EXPORT_SYMBOL(__tty_insert_flip_string_flags); /** * tty_prepare_flip_string - make room for characters * @port: tty port * @chars: return pointer for character write area * @size: desired size * * Prepare a block of space in the buffer for data. * * This is used for drivers that need their own block copy routines into the * buffer. There is no guarantee the buffer is a DMA target! * * Returns: the length available and buffer pointer (@chars) to the space which * is now allocated and accounted for as ready for normal characters. */ size_t tty_prepare_flip_string(struct tty_port *port, u8 **chars, size_t size) { size_t space = __tty_buffer_request_room(port, size, false); if (likely(space)) { struct tty_buffer *tb = port->buf.tail; *chars = char_buf_ptr(tb, tb->used); if (tb->flags) memset(flag_buf_ptr(tb, tb->used), TTY_NORMAL, space); tb->used += space; } return space; } EXPORT_SYMBOL_GPL(tty_prepare_flip_string); /** * tty_ldisc_receive_buf - forward data to line discipline * @ld: line discipline to process input * @p: char buffer * @f: %TTY_NORMAL, %TTY_BREAK, etc. flags buffer * @count: number of bytes to process * * Callers other than flush_to_ldisc() need to exclude the kworker from * concurrent use of the line discipline, see paste_selection(). * * Returns: the number of bytes processed. */ size_t tty_ldisc_receive_buf(struct tty_ldisc *ld, const u8 *p, const u8 *f, size_t count) { if (ld->ops->receive_buf2) count = ld->ops->receive_buf2(ld->tty, p, f, count); else { count = min_t(size_t, count, ld->tty->receive_room); if (count && ld->ops->receive_buf) ld->ops->receive_buf(ld->tty, p, f, count); } return count; } EXPORT_SYMBOL_GPL(tty_ldisc_receive_buf); static void lookahead_bufs(struct tty_port *port, struct tty_buffer *head) { head->lookahead = max(head->lookahead, head->read); while (head) { struct tty_buffer *next; unsigned int count; /* * Paired w/ release in __tty_buffer_request_room(); * ensures commit value read is not stale if the head * is advancing to the next buffer. */ next = smp_load_acquire(&head->next); /* * Paired w/ release in __tty_buffer_request_room() or in * tty_buffer_flush(); ensures we see the committed buffer data. */ count = smp_load_acquire(&head->commit) - head->lookahead; if (!count) { head = next; continue; } if (port->client_ops->lookahead_buf) { u8 *p, *f = NULL; p = char_buf_ptr(head, head->lookahead); if (head->flags) f = flag_buf_ptr(head, head->lookahead); port->client_ops->lookahead_buf(port, p, f, count); } head->lookahead += count; } } static size_t receive_buf(struct tty_port *port, struct tty_buffer *head, size_t count) { u8 *p = char_buf_ptr(head, head->read); const u8 *f = NULL; size_t n; if (head->flags) f = flag_buf_ptr(head, head->read); n = port->client_ops->receive_buf(port, p, f, count); if (n > 0) memset(p, 0, n); return n; } /** * flush_to_ldisc - flush data from buffer to ldisc * @work: tty structure passed from work queue. * * This routine is called out of the software interrupt to flush data from the * buffer chain to the line discipline. * * The receive_buf() method is single threaded for each tty instance. * * Locking: takes buffer lock to ensure single-threaded flip buffer 'consumer'. */ static void flush_to_ldisc(struct work_struct *work) { struct tty_port *port = container_of(work, struct tty_port, buf.work); struct tty_bufhead *buf = &port->buf; mutex_lock(&buf->lock); while (1) { struct tty_buffer *head = buf->head; struct tty_buffer *next; size_t count, rcvd; /* Ldisc or user is trying to gain exclusive access */ if (atomic_read(&buf->priority)) break; /* paired w/ release in __tty_buffer_request_room(); * ensures commit value read is not stale if the head * is advancing to the next buffer */ next = smp_load_acquire(&head->next); /* paired w/ release in __tty_buffer_request_room() or in * tty_buffer_flush(); ensures we see the committed buffer data */ count = smp_load_acquire(&head->commit) - head->read; if (!count) { if (next == NULL) break; buf->head = next; tty_buffer_free(port, head); continue; } rcvd = receive_buf(port, head, count); head->read += rcvd; if (rcvd < count) lookahead_bufs(port, head); if (!rcvd) break; if (need_resched()) cond_resched(); } mutex_unlock(&buf->lock); } static inline void tty_flip_buffer_commit(struct tty_buffer *tail) { /* * Paired w/ acquire in flush_to_ldisc(); ensures flush_to_ldisc() sees * buffer data. */ smp_store_release(&tail->commit, tail->used); } /** * tty_flip_buffer_push - push terminal buffers * @port: tty port to push * * Queue a push of the terminal flip buffers to the line discipline. Can be * called from IRQ/atomic context. * * In the event of the queue being busy for flipping the work will be held off * and retried later. */ void tty_flip_buffer_push(struct tty_port *port) { struct tty_bufhead *buf = &port->buf; tty_flip_buffer_commit(buf->tail); queue_work(system_unbound_wq, &buf->work); } EXPORT_SYMBOL(tty_flip_buffer_push); /** * tty_insert_flip_string_and_push_buffer - add characters to the tty buffer and * push * @port: tty port * @chars: characters * @size: size * * The function combines tty_insert_flip_string() and tty_flip_buffer_push() * with the exception of properly holding the @port->lock. * * To be used only internally (by pty currently). * * Returns: the number added. */ int tty_insert_flip_string_and_push_buffer(struct tty_port *port, const u8 *chars, size_t size) { struct tty_bufhead *buf = &port->buf; unsigned long flags; spin_lock_irqsave(&port->lock, flags); size = tty_insert_flip_string(port, chars, size); if (size) tty_flip_buffer_commit(buf->tail); spin_unlock_irqrestore(&port->lock, flags); queue_work(system_unbound_wq, &buf->work); return size; } /** * tty_buffer_init - prepare a tty buffer structure * @port: tty port to initialise * * Set up the initial state of the buffer management for a tty device. Must be * called before the other tty buffer functions are used. */ void tty_buffer_init(struct tty_port *port) { struct tty_bufhead *buf = &port->buf; mutex_init(&buf->lock); tty_buffer_reset(&buf->sentinel, 0); buf->head = &buf->sentinel; buf->tail = &buf->sentinel; init_llist_head(&buf->free); atomic_set(&buf->mem_used, 0); atomic_set(&buf->priority, 0); INIT_WORK(&buf->work, flush_to_ldisc); buf->mem_limit = TTYB_DEFAULT_MEM_LIMIT; } /** * tty_buffer_set_limit - change the tty buffer memory limit * @port: tty port to change * @limit: memory limit to set * * Change the tty buffer memory limit. * * Must be called before the other tty buffer functions are used. */ int tty_buffer_set_limit(struct tty_port *port, int limit) { if (limit < MIN_TTYB_SIZE) return -EINVAL; port->buf.mem_limit = limit; return 0; } EXPORT_SYMBOL_GPL(tty_buffer_set_limit); /* slave ptys can claim nested buffer lock when handling BRK and INTR */ void tty_buffer_set_lock_subclass(struct tty_port *port) { lockdep_set_subclass(&port->buf.lock, TTY_LOCK_SLAVE); } bool tty_buffer_restart_work(struct tty_port *port) { return queue_work(system_unbound_wq, &port->buf.work); } bool tty_buffer_cancel_work(struct tty_port *port) { return cancel_work_sync(&port->buf.work); } void tty_buffer_flush_work(struct tty_port *port) { flush_work(&port->buf.work); } |
| 1723 1723 25 10 4 4 29 15 1 1 46 43 11 9 17 8 8 8 32 32 32 32 32 32 3 32 5 3 3 3 15 15 15 15 29 29 29 15 15 15 5 5 5 5 5 5 |