| 7 7 4 23 169 104 177 181 170 125 170 117 110 107 4 1 108 3 2 1 105 2 1 1 2 2 2 2 2 106 1 1 1 1 1 1 1 1 106 1 1 1 109 11 98 6 2 47 3 104 102 189 161 159 1 159 2 156 2 156 36 2 155 155 184 2 181 190 105 29 5 1 4 1 3 3 6 5 4 1 1 3 1 2 1 1 3 2 1 1 1 3 1 2 2 2 29 29 29 1 16 28 2 26 1 1 1 3 1 1 1 1 1 1 1 1 6 1 5 3 6 6 1 3 3 2 18 18 4 14 30 8 4 3 2 1 1 5 1 2 2 154 153 104 154 104 154 153 154 154 115 115 2 114 114 116 181 1 2 1 182 2 2 179 4 177 4 4 1 3 3 174 178 102 3 3 3 179 29 2 153 2 2 1 1 1 153 1 1 1 1 152 1 1 1 1 153 1 1 1 1 153 1 1 1 1 1 1 1 153 152 153 182 116 11 11 7 1 3 6 1 5 1 1 1 1 1 1 1 1 2 2 1 1 7 4 1 3 1 1 1 2 1 11 154 123 1 6 1 1 1 1 123 9 115 2 2 1 1 1 1 1 1 1 113 113 1 1 112 114 3 1 111 1 1 1 1 1 1 111 1 1 1 109 111 1 1 1 109 1 1 1 109 112 1 1 1 111 154 1 102 102 1 102 102 1 102 159 161 154 154 110 105 102 102 105 104 104 104 110 111 136 6 3 136 136 80 81 79 80 174 28 109 110 110 14 14 14 5 5 110 110 25 14 5 23 110 109 25 25 25 25 20 20 14 20 20 19 7 6 4 3 2 4 2 1 1 11 11 10 8 8 2 6 9 2 7 6 2 5 5 5 5 5 2 15 15 14 14 14 14 14 3 161 57 161 136 1 1 8 4 3 19 18 16 19 6 9 14 7 11 2 1 1 1 1 1 1 1 1 1 1 1 4 4 3 3 3 2 1 2 5 5 3 10 10 110 110 76 76 65 65 73 4 1 2 1 1 1 2 2 1 1 1 1 1 1 1 1 1 11 8 7 5 2 1 9 9 8 1 15 6 27 1 5 2 10 47 110 110 109 110 110 95 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2007-2017 Nicira, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "flow.h" #include "datapath.h" #include <linux/uaccess.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <net/llc_pdu.h> #include <linux/kernel.h> #include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/llc.h> #include <linux/module.h> #include <linux/in.h> #include <linux/rcupdate.h> #include <linux/if_arp.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/sctp.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/icmp.h> #include <linux/icmpv6.h> #include <linux/rculist.h> #include <net/geneve.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/mpls.h> #include <net/vxlan.h> #include <net/tun_proto.h> #include <net/erspan.h> #include "drop.h" #include "flow_netlink.h" struct ovs_len_tbl { int len; const struct ovs_len_tbl *next; }; #define OVS_ATTR_NESTED -1 #define OVS_ATTR_VARIABLE -2 #define OVS_COPY_ACTIONS_MAX_DEPTH 16 static bool actions_may_change_flow(const struct nlattr *actions) { struct nlattr *nla; int rem; nla_for_each_nested(nla, actions, rem) { u16 action = nla_type(nla); switch (action) { case OVS_ACTION_ATTR_OUTPUT: case OVS_ACTION_ATTR_RECIRC: case OVS_ACTION_ATTR_TRUNC: case OVS_ACTION_ATTR_USERSPACE: case OVS_ACTION_ATTR_DROP: case OVS_ACTION_ATTR_PSAMPLE: break; case OVS_ACTION_ATTR_CT: case OVS_ACTION_ATTR_CT_CLEAR: case OVS_ACTION_ATTR_HASH: case OVS_ACTION_ATTR_POP_ETH: case OVS_ACTION_ATTR_POP_MPLS: case OVS_ACTION_ATTR_POP_NSH: case OVS_ACTION_ATTR_POP_VLAN: case OVS_ACTION_ATTR_PUSH_ETH: case OVS_ACTION_ATTR_PUSH_MPLS: case OVS_ACTION_ATTR_PUSH_NSH: case OVS_ACTION_ATTR_PUSH_VLAN: case OVS_ACTION_ATTR_SAMPLE: case OVS_ACTION_ATTR_SET: case OVS_ACTION_ATTR_SET_MASKED: case OVS_ACTION_ATTR_METER: case OVS_ACTION_ATTR_CHECK_PKT_LEN: case OVS_ACTION_ATTR_ADD_MPLS: case OVS_ACTION_ATTR_DEC_TTL: default: return true; } } return false; } static void update_range(struct sw_flow_match *match, size_t offset, size_t size, bool is_mask) { struct sw_flow_key_range *range; size_t start = rounddown(offset, sizeof(long)); size_t end = roundup(offset + size, sizeof(long)); if (!is_mask) range = &match->range; else range = &match->mask->range; if (range->start == range->end) { range->start = start; range->end = end; return; } if (range->start > start) range->start = start; if (range->end < end) range->end = end; } #define SW_FLOW_KEY_PUT(match, field, value, is_mask) \ do { \ update_range(match, offsetof(struct sw_flow_key, field), \ sizeof((match)->key->field), is_mask); \ if (is_mask) \ (match)->mask->key.field = value; \ else \ (match)->key->field = value; \ } while (0) #define SW_FLOW_KEY_MEMCPY_OFFSET(match, offset, value_p, len, is_mask) \ do { \ update_range(match, offset, len, is_mask); \ if (is_mask) \ memcpy((u8 *)&(match)->mask->key + offset, value_p, \ len); \ else \ memcpy((u8 *)(match)->key + offset, value_p, len); \ } while (0) #define SW_FLOW_KEY_MEMCPY(match, field, value_p, len, is_mask) \ SW_FLOW_KEY_MEMCPY_OFFSET(match, offsetof(struct sw_flow_key, field), \ value_p, len, is_mask) #define SW_FLOW_KEY_MEMSET_FIELD(match, field, value, is_mask) \ do { \ update_range(match, offsetof(struct sw_flow_key, field), \ sizeof((match)->key->field), is_mask); \ if (is_mask) \ memset((u8 *)&(match)->mask->key.field, value, \ sizeof((match)->mask->key.field)); \ else \ memset((u8 *)&(match)->key->field, value, \ sizeof((match)->key->field)); \ } while (0) #define SW_FLOW_KEY_BITMAP_COPY(match, field, value_p, nbits, is_mask) ({ \ update_range(match, offsetof(struct sw_flow_key, field), \ bitmap_size(nbits), is_mask); \ bitmap_copy(is_mask ? (match)->mask->key.field : (match)->key->field, \ value_p, nbits); \ }) static bool match_validate(const struct sw_flow_match *match, u64 key_attrs, u64 mask_attrs, bool log) { u64 key_expected = 0; u64 mask_allowed = key_attrs; /* At most allow all key attributes */ /* The following mask attributes allowed only if they * pass the validation tests. */ mask_allowed &= ~((1 << OVS_KEY_ATTR_IPV4) | (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4) | (1 << OVS_KEY_ATTR_IPV6) | (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6) | (1 << OVS_KEY_ATTR_TCP) | (1 << OVS_KEY_ATTR_TCP_FLAGS) | (1 << OVS_KEY_ATTR_UDP) | (1 << OVS_KEY_ATTR_SCTP) | (1 << OVS_KEY_ATTR_ICMP) | (1 << OVS_KEY_ATTR_ICMPV6) | (1 << OVS_KEY_ATTR_ARP) | (1 << OVS_KEY_ATTR_ND) | (1 << OVS_KEY_ATTR_MPLS) | (1 << OVS_KEY_ATTR_NSH)); /* Always allowed mask fields. */ mask_allowed |= ((1 << OVS_KEY_ATTR_TUNNEL) | (1 << OVS_KEY_ATTR_IN_PORT) | (1 << OVS_KEY_ATTR_ETHERTYPE)); /* Check key attributes. */ if (match->key->eth.type == htons(ETH_P_ARP) || match->key->eth.type == htons(ETH_P_RARP)) { key_expected |= 1 << OVS_KEY_ATTR_ARP; if (match->mask && (match->mask->key.eth.type == htons(0xffff))) mask_allowed |= 1 << OVS_KEY_ATTR_ARP; } if (eth_p_mpls(match->key->eth.type)) { key_expected |= 1 << OVS_KEY_ATTR_MPLS; if (match->mask && (match->mask->key.eth.type == htons(0xffff))) mask_allowed |= 1 << OVS_KEY_ATTR_MPLS; } if (match->key->eth.type == htons(ETH_P_IP)) { key_expected |= 1 << OVS_KEY_ATTR_IPV4; if (match->mask && match->mask->key.eth.type == htons(0xffff)) { mask_allowed |= 1 << OVS_KEY_ATTR_IPV4; mask_allowed |= 1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4; } if (match->key->ip.frag != OVS_FRAG_TYPE_LATER) { if (match->key->ip.proto == IPPROTO_UDP) { key_expected |= 1 << OVS_KEY_ATTR_UDP; if (match->mask && (match->mask->key.ip.proto == 0xff)) mask_allowed |= 1 << OVS_KEY_ATTR_UDP; } if (match->key->ip.proto == IPPROTO_SCTP) { key_expected |= 1 << OVS_KEY_ATTR_SCTP; if (match->mask && (match->mask->key.ip.proto == 0xff)) mask_allowed |= 1 << OVS_KEY_ATTR_SCTP; } if (match->key->ip.proto == IPPROTO_TCP) { key_expected |= 1 << OVS_KEY_ATTR_TCP; key_expected |= 1 << OVS_KEY_ATTR_TCP_FLAGS; if (match->mask && (match->mask->key.ip.proto == 0xff)) { mask_allowed |= 1 << OVS_KEY_ATTR_TCP; mask_allowed |= 1 << OVS_KEY_ATTR_TCP_FLAGS; } } if (match->key->ip.proto == IPPROTO_ICMP) { key_expected |= 1 << OVS_KEY_ATTR_ICMP; if (match->mask && (match->mask->key.ip.proto == 0xff)) mask_allowed |= 1 << OVS_KEY_ATTR_ICMP; } } } if (match->key->eth.type == htons(ETH_P_IPV6)) { key_expected |= 1 << OVS_KEY_ATTR_IPV6; if (match->mask && match->mask->key.eth.type == htons(0xffff)) { mask_allowed |= 1 << OVS_KEY_ATTR_IPV6; mask_allowed |= 1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6; } if (match->key->ip.frag != OVS_FRAG_TYPE_LATER) { if (match->key->ip.proto == IPPROTO_UDP) { key_expected |= 1 << OVS_KEY_ATTR_UDP; if (match->mask && (match->mask->key.ip.proto == 0xff)) mask_allowed |= 1 << OVS_KEY_ATTR_UDP; } if (match->key->ip.proto == IPPROTO_SCTP) { key_expected |= 1 << OVS_KEY_ATTR_SCTP; if (match->mask && (match->mask->key.ip.proto == 0xff)) mask_allowed |= 1 << OVS_KEY_ATTR_SCTP; } if (match->key->ip.proto == IPPROTO_TCP) { key_expected |= 1 << OVS_KEY_ATTR_TCP; key_expected |= 1 << OVS_KEY_ATTR_TCP_FLAGS; if (match->mask && (match->mask->key.ip.proto == 0xff)) { mask_allowed |= 1 << OVS_KEY_ATTR_TCP; mask_allowed |= 1 << OVS_KEY_ATTR_TCP_FLAGS; } } if (match->key->ip.proto == IPPROTO_ICMPV6) { key_expected |= 1 << OVS_KEY_ATTR_ICMPV6; if (match->mask && (match->mask->key.ip.proto == 0xff)) mask_allowed |= 1 << OVS_KEY_ATTR_ICMPV6; if (match->key->tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) || match->key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) { key_expected |= 1 << OVS_KEY_ATTR_ND; /* Original direction conntrack tuple * uses the same space as the ND fields * in the key, so both are not allowed * at the same time. */ mask_allowed &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6); if (match->mask && (match->mask->key.tp.src == htons(0xff))) mask_allowed |= 1 << OVS_KEY_ATTR_ND; } } } } if (match->key->eth.type == htons(ETH_P_NSH)) { key_expected |= 1 << OVS_KEY_ATTR_NSH; if (match->mask && match->mask->key.eth.type == htons(0xffff)) { mask_allowed |= 1 << OVS_KEY_ATTR_NSH; } } if ((key_attrs & key_expected) != key_expected) { /* Key attributes check failed. */ OVS_NLERR(log, "Missing key (keys=%llx, expected=%llx)", (unsigned long long)key_attrs, (unsigned long long)key_expected); return false; } if ((mask_attrs & mask_allowed) != mask_attrs) { /* Mask attributes check failed. */ OVS_NLERR(log, "Unexpected mask (mask=%llx, allowed=%llx)", (unsigned long long)mask_attrs, (unsigned long long)mask_allowed); return false; } return true; } size_t ovs_tun_key_attr_size(void) { /* Whenever adding new OVS_TUNNEL_KEY_ FIELDS, we should consider * updating this function. */ return nla_total_size_64bit(8) /* OVS_TUNNEL_KEY_ATTR_ID */ + nla_total_size(16) /* OVS_TUNNEL_KEY_ATTR_IPV[46]_SRC */ + nla_total_size(16) /* OVS_TUNNEL_KEY_ATTR_IPV[46]_DST */ + nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TOS */ + nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TTL */ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_CSUM */ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_OAM */ + nla_total_size(256) /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */ /* OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS and * OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS is mutually exclusive with * OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS and covered by it. */ + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_SRC */ + nla_total_size(2); /* OVS_TUNNEL_KEY_ATTR_TP_DST */ } static size_t ovs_nsh_key_attr_size(void) { /* Whenever adding new OVS_NSH_KEY_ FIELDS, we should consider * updating this function. */ return nla_total_size(NSH_BASE_HDR_LEN) /* OVS_NSH_KEY_ATTR_BASE */ /* OVS_NSH_KEY_ATTR_MD1 and OVS_NSH_KEY_ATTR_MD2 are * mutually exclusive, so the bigger one can cover * the small one. */ + nla_total_size(NSH_CTX_HDRS_MAX_LEN); } size_t ovs_key_attr_size(void) { /* Whenever adding new OVS_KEY_ FIELDS, we should consider * updating this function. */ BUILD_BUG_ON(OVS_KEY_ATTR_MAX != 32); return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */ + nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */ + ovs_tun_key_attr_size() + nla_total_size(4) /* OVS_KEY_ATTR_IN_PORT */ + nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */ + nla_total_size(4) /* OVS_KEY_ATTR_DP_HASH */ + nla_total_size(4) /* OVS_KEY_ATTR_RECIRC_ID */ + nla_total_size(4) /* OVS_KEY_ATTR_CT_STATE */ + nla_total_size(2) /* OVS_KEY_ATTR_CT_ZONE */ + nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */ + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABELS */ + nla_total_size(40) /* OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6 */ + nla_total_size(0) /* OVS_KEY_ATTR_NSH */ + ovs_nsh_key_attr_size() + nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */ + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */ + nla_total_size(4) /* OVS_KEY_ATTR_VLAN */ + nla_total_size(0) /* OVS_KEY_ATTR_ENCAP */ + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */ + nla_total_size(40) /* OVS_KEY_ATTR_IPV6 */ + nla_total_size(2) /* OVS_KEY_ATTR_ICMPV6 */ + nla_total_size(28) /* OVS_KEY_ATTR_ND */ + nla_total_size(2); /* OVS_KEY_ATTR_IPV6_EXTHDRS */ } static const struct ovs_len_tbl ovs_vxlan_ext_key_lens[OVS_VXLAN_EXT_MAX + 1] = { [OVS_VXLAN_EXT_GBP] = { .len = sizeof(u32) }, }; static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] = { [OVS_TUNNEL_KEY_ATTR_ID] = { .len = sizeof(u64) }, [OVS_TUNNEL_KEY_ATTR_IPV4_SRC] = { .len = sizeof(u32) }, [OVS_TUNNEL_KEY_ATTR_IPV4_DST] = { .len = sizeof(u32) }, [OVS_TUNNEL_KEY_ATTR_TOS] = { .len = 1 }, [OVS_TUNNEL_KEY_ATTR_TTL] = { .len = 1 }, [OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = { .len = 0 }, [OVS_TUNNEL_KEY_ATTR_CSUM] = { .len = 0 }, [OVS_TUNNEL_KEY_ATTR_TP_SRC] = { .len = sizeof(u16) }, [OVS_TUNNEL_KEY_ATTR_TP_DST] = { .len = sizeof(u16) }, [OVS_TUNNEL_KEY_ATTR_OAM] = { .len = 0 }, [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = { .len = OVS_ATTR_VARIABLE }, [OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS] = { .len = OVS_ATTR_NESTED, .next = ovs_vxlan_ext_key_lens }, [OVS_TUNNEL_KEY_ATTR_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, [OVS_TUNNEL_KEY_ATTR_IPV6_DST] = { .len = sizeof(struct in6_addr) }, [OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS] = { .len = OVS_ATTR_VARIABLE }, [OVS_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE] = { .len = 0 }, }; static const struct ovs_len_tbl ovs_nsh_key_attr_lens[OVS_NSH_KEY_ATTR_MAX + 1] = { [OVS_NSH_KEY_ATTR_BASE] = { .len = sizeof(struct ovs_nsh_key_base) }, [OVS_NSH_KEY_ATTR_MD1] = { .len = sizeof(struct ovs_nsh_key_md1) }, [OVS_NSH_KEY_ATTR_MD2] = { .len = OVS_ATTR_VARIABLE }, }; /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { [OVS_KEY_ATTR_ENCAP] = { .len = OVS_ATTR_NESTED }, [OVS_KEY_ATTR_PRIORITY] = { .len = sizeof(u32) }, [OVS_KEY_ATTR_IN_PORT] = { .len = sizeof(u32) }, [OVS_KEY_ATTR_SKB_MARK] = { .len = sizeof(u32) }, [OVS_KEY_ATTR_ETHERNET] = { .len = sizeof(struct ovs_key_ethernet) }, [OVS_KEY_ATTR_VLAN] = { .len = sizeof(__be16) }, [OVS_KEY_ATTR_ETHERTYPE] = { .len = sizeof(__be16) }, [OVS_KEY_ATTR_IPV4] = { .len = sizeof(struct ovs_key_ipv4) }, [OVS_KEY_ATTR_IPV6] = { .len = sizeof(struct ovs_key_ipv6) }, [OVS_KEY_ATTR_TCP] = { .len = sizeof(struct ovs_key_tcp) }, [OVS_KEY_ATTR_TCP_FLAGS] = { .len = sizeof(__be16) }, [OVS_KEY_ATTR_UDP] = { .len = sizeof(struct ovs_key_udp) }, [OVS_KEY_ATTR_SCTP] = { .len = sizeof(struct ovs_key_sctp) }, [OVS_KEY_ATTR_ICMP] = { .len = sizeof(struct ovs_key_icmp) }, [OVS_KEY_ATTR_ICMPV6] = { .len = sizeof(struct ovs_key_icmpv6) }, [OVS_KEY_ATTR_ARP] = { .len = sizeof(struct ovs_key_arp) }, [OVS_KEY_ATTR_ND] = { .len = sizeof(struct ovs_key_nd) }, [OVS_KEY_ATTR_RECIRC_ID] = { .len = sizeof(u32) }, [OVS_KEY_ATTR_DP_HASH] = { .len = sizeof(u32) }, [OVS_KEY_ATTR_TUNNEL] = { .len = OVS_ATTR_NESTED, .next = ovs_tunnel_key_lens, }, [OVS_KEY_ATTR_MPLS] = { .len = OVS_ATTR_VARIABLE }, [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u32) }, [OVS_KEY_ATTR_CT_ZONE] = { .len = sizeof(u16) }, [OVS_KEY_ATTR_CT_MARK] = { .len = sizeof(u32) }, [OVS_KEY_ATTR_CT_LABELS] = { .len = sizeof(struct ovs_key_ct_labels) }, [OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4] = { .len = sizeof(struct ovs_key_ct_tuple_ipv4) }, [OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6] = { .len = sizeof(struct ovs_key_ct_tuple_ipv6) }, [OVS_KEY_ATTR_NSH] = { .len = OVS_ATTR_NESTED, .next = ovs_nsh_key_attr_lens, }, [OVS_KEY_ATTR_IPV6_EXTHDRS] = { .len = sizeof(struct ovs_key_ipv6_exthdrs) }, }; static bool check_attr_len(unsigned int attr_len, unsigned int expected_len) { return expected_len == attr_len || expected_len == OVS_ATTR_NESTED || expected_len == OVS_ATTR_VARIABLE; } static bool is_all_zero(const u8 *fp, size_t size) { int i; if (!fp) return false; for (i = 0; i < size; i++) if (fp[i]) return false; return true; } static int __parse_flow_nlattrs(const struct nlattr *attr, const struct nlattr *a[], u64 *attrsp, bool log, bool nz) { const struct nlattr *nla; u64 attrs; int rem; attrs = *attrsp; nla_for_each_nested(nla, attr, rem) { u16 type = nla_type(nla); int expected_len; if (type > OVS_KEY_ATTR_MAX) { OVS_NLERR(log, "Key type %d is out of range max %d", type, OVS_KEY_ATTR_MAX); return -EINVAL; } if (type == OVS_KEY_ATTR_PACKET_TYPE || type == OVS_KEY_ATTR_ND_EXTENSIONS || type == OVS_KEY_ATTR_TUNNEL_INFO) { OVS_NLERR(log, "Key type %d is not supported", type); return -EINVAL; } if (attrs & (1ULL << type)) { OVS_NLERR(log, "Duplicate key (type %d).", type); return -EINVAL; } expected_len = ovs_key_lens[type].len; if (!check_attr_len(nla_len(nla), expected_len)) { OVS_NLERR(log, "Key %d has unexpected len %d expected %d", type, nla_len(nla), expected_len); return -EINVAL; } if (!nz || !is_all_zero(nla_data(nla), nla_len(nla))) { attrs |= 1ULL << type; a[type] = nla; } } if (rem) { OVS_NLERR(log, "Message has %d unknown bytes.", rem); return -EINVAL; } *attrsp = attrs; return 0; } static int parse_flow_mask_nlattrs(const struct nlattr *attr, const struct nlattr *a[], u64 *attrsp, bool log) { return __parse_flow_nlattrs(attr, a, attrsp, log, true); } int parse_flow_nlattrs(const struct nlattr *attr, const struct nlattr *a[], u64 *attrsp, bool log) { return __parse_flow_nlattrs(attr, a, attrsp, log, false); } static int genev_tun_opt_from_nlattr(const struct nlattr *a, struct sw_flow_match *match, bool is_mask, bool log) { unsigned long opt_key_offset; if (nla_len(a) > sizeof(match->key->tun_opts)) { OVS_NLERR(log, "Geneve option length err (len %d, max %zu).", nla_len(a), sizeof(match->key->tun_opts)); return -EINVAL; } if (nla_len(a) % 4 != 0) { OVS_NLERR(log, "Geneve opt len %d is not a multiple of 4.", nla_len(a)); return -EINVAL; } /* We need to record the length of the options passed * down, otherwise packets with the same format but * additional options will be silently matched. */ if (!is_mask) { SW_FLOW_KEY_PUT(match, tun_opts_len, nla_len(a), false); } else { /* This is somewhat unusual because it looks at * both the key and mask while parsing the * attributes (and by extension assumes the key * is parsed first). Normally, we would verify * that each is the correct length and that the * attributes line up in the validate function. * However, that is difficult because this is * variable length and we won't have the * information later. */ if (match->key->tun_opts_len != nla_len(a)) { OVS_NLERR(log, "Geneve option len %d != mask len %d", match->key->tun_opts_len, nla_len(a)); return -EINVAL; } SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, true); } opt_key_offset = TUN_METADATA_OFFSET(nla_len(a)); SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, nla_data(a), nla_len(a), is_mask); return 0; } static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool log) { struct nlattr *a; int rem; unsigned long opt_key_offset; struct vxlan_metadata opts; BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts)); memset(&opts, 0, sizeof(opts)); nla_for_each_nested(a, attr, rem) { int type = nla_type(a); if (type > OVS_VXLAN_EXT_MAX) { OVS_NLERR(log, "VXLAN extension %d out of range max %d", type, OVS_VXLAN_EXT_MAX); return -EINVAL; } if (!check_attr_len(nla_len(a), ovs_vxlan_ext_key_lens[type].len)) { OVS_NLERR(log, "VXLAN extension %d has unexpected len %d expected %d", type, nla_len(a), ovs_vxlan_ext_key_lens[type].len); return -EINVAL; } switch (type) { case OVS_VXLAN_EXT_GBP: opts.gbp = nla_get_u32(a); break; default: OVS_NLERR(log, "Unknown VXLAN extension attribute %d", type); return -EINVAL; } } if (rem) { OVS_NLERR(log, "VXLAN extension message has %d unknown bytes.", rem); return -EINVAL; } if (!is_mask) SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), false); else SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, true); opt_key_offset = TUN_METADATA_OFFSET(sizeof(opts)); SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, &opts, sizeof(opts), is_mask); return 0; } static int erspan_tun_opt_from_nlattr(const struct nlattr *a, struct sw_flow_match *match, bool is_mask, bool log) { unsigned long opt_key_offset; BUILD_BUG_ON(sizeof(struct erspan_metadata) > sizeof(match->key->tun_opts)); if (nla_len(a) > sizeof(match->key->tun_opts)) { OVS_NLERR(log, "ERSPAN option length err (len %d, max %zu).", nla_len(a), sizeof(match->key->tun_opts)); return -EINVAL; } if (!is_mask) SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(struct erspan_metadata), false); else SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, true); opt_key_offset = TUN_METADATA_OFFSET(nla_len(a)); SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, nla_data(a), nla_len(a), is_mask); return 0; } static int ip_tun_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool log) { bool ttl = false, ipv4 = false, ipv6 = false; IP_TUNNEL_DECLARE_FLAGS(tun_flags) = { }; bool info_bridge_mode = false; int opts_type = 0; struct nlattr *a; int rem; nla_for_each_nested(a, attr, rem) { int type = nla_type(a); int err; if (type > OVS_TUNNEL_KEY_ATTR_MAX) { OVS_NLERR(log, "Tunnel attr %d out of range max %d", type, OVS_TUNNEL_KEY_ATTR_MAX); return -EINVAL; } if (!check_attr_len(nla_len(a), ovs_tunnel_key_lens[type].len)) { OVS_NLERR(log, "Tunnel attr %d has unexpected len %d expected %d", type, nla_len(a), ovs_tunnel_key_lens[type].len); return -EINVAL; } switch (type) { case OVS_TUNNEL_KEY_ATTR_ID: SW_FLOW_KEY_PUT(match, tun_key.tun_id, nla_get_be64(a), is_mask); __set_bit(IP_TUNNEL_KEY_BIT, tun_flags); break; case OVS_TUNNEL_KEY_ATTR_IPV4_SRC: SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.src, nla_get_in_addr(a), is_mask); ipv4 = true; break; case OVS_TUNNEL_KEY_ATTR_IPV4_DST: SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.dst, nla_get_in_addr(a), is_mask); ipv4 = true; break; case OVS_TUNNEL_KEY_ATTR_IPV6_SRC: SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.src, nla_get_in6_addr(a), is_mask); ipv6 = true; break; case OVS_TUNNEL_KEY_ATTR_IPV6_DST: SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst, nla_get_in6_addr(a), is_mask); ipv6 = true; break; case OVS_TUNNEL_KEY_ATTR_TOS: SW_FLOW_KEY_PUT(match, tun_key.tos, nla_get_u8(a), is_mask); break; case OVS_TUNNEL_KEY_ATTR_TTL: SW_FLOW_KEY_PUT(match, tun_key.ttl, nla_get_u8(a), is_mask); ttl = true; break; case OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT: __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, tun_flags); break; case OVS_TUNNEL_KEY_ATTR_CSUM: __set_bit(IP_TUNNEL_CSUM_BIT, tun_flags); break; case OVS_TUNNEL_KEY_ATTR_TP_SRC: SW_FLOW_KEY_PUT(match, tun_key.tp_src, nla_get_be16(a), is_mask); break; case OVS_TUNNEL_KEY_ATTR_TP_DST: SW_FLOW_KEY_PUT(match, tun_key.tp_dst, nla_get_be16(a), is_mask); break; case OVS_TUNNEL_KEY_ATTR_OAM: __set_bit(IP_TUNNEL_OAM_BIT, tun_flags); break; case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS: if (opts_type) { OVS_NLERR(log, "Multiple metadata blocks provided"); return -EINVAL; } err = genev_tun_opt_from_nlattr(a, match, is_mask, log); if (err) return err; __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, tun_flags); opts_type = type; break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: if (opts_type) { OVS_NLERR(log, "Multiple metadata blocks provided"); return -EINVAL; } err = vxlan_tun_opt_from_nlattr(a, match, is_mask, log); if (err) return err; __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, tun_flags); opts_type = type; break; case OVS_TUNNEL_KEY_ATTR_PAD: break; case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: if (opts_type) { OVS_NLERR(log, "Multiple metadata blocks provided"); return -EINVAL; } err = erspan_tun_opt_from_nlattr(a, match, is_mask, log); if (err) return err; __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, tun_flags); opts_type = type; break; case OVS_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE: info_bridge_mode = true; ipv4 = true; break; default: OVS_NLERR(log, "Unknown IP tunnel attribute %d", type); return -EINVAL; } } SW_FLOW_KEY_BITMAP_COPY(match, tun_key.tun_flags, tun_flags, __IP_TUNNEL_FLAG_NUM, is_mask); if (is_mask) SW_FLOW_KEY_MEMSET_FIELD(match, tun_proto, 0xff, true); else SW_FLOW_KEY_PUT(match, tun_proto, ipv6 ? AF_INET6 : AF_INET, false); if (rem > 0) { OVS_NLERR(log, "IP tunnel attribute has %d unknown bytes.", rem); return -EINVAL; } if (ipv4 && ipv6) { OVS_NLERR(log, "Mixed IPv4 and IPv6 tunnel attributes"); return -EINVAL; } if (!is_mask) { if (!ipv4 && !ipv6) { OVS_NLERR(log, "IP tunnel dst address not specified"); return -EINVAL; } if (ipv4) { if (info_bridge_mode) { __clear_bit(IP_TUNNEL_KEY_BIT, tun_flags); if (match->key->tun_key.u.ipv4.src || match->key->tun_key.u.ipv4.dst || match->key->tun_key.tp_src || match->key->tun_key.tp_dst || match->key->tun_key.ttl || match->key->tun_key.tos || !ip_tunnel_flags_empty(tun_flags)) { OVS_NLERR(log, "IPv4 tun info is not correct"); return -EINVAL; } } else if (!match->key->tun_key.u.ipv4.dst) { OVS_NLERR(log, "IPv4 tunnel dst address is zero"); return -EINVAL; } } if (ipv6 && ipv6_addr_any(&match->key->tun_key.u.ipv6.dst)) { OVS_NLERR(log, "IPv6 tunnel dst address is zero"); return -EINVAL; } if (!ttl && !info_bridge_mode) { OVS_NLERR(log, "IP tunnel TTL not specified."); return -EINVAL; } } return opts_type; } static int vxlan_opt_to_nlattr(struct sk_buff *skb, const void *tun_opts, int swkey_tun_opts_len) { const struct vxlan_metadata *opts = tun_opts; struct nlattr *nla; nla = nla_nest_start_noflag(skb, OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS); if (!nla) return -EMSGSIZE; if (nla_put_u32(skb, OVS_VXLAN_EXT_GBP, opts->gbp) < 0) return -EMSGSIZE; nla_nest_end(skb, nla); return 0; } static int __ip_tun_to_nlattr(struct sk_buff *skb, const struct ip_tunnel_key *output, const void *tun_opts, int swkey_tun_opts_len, unsigned short tun_proto, u8 mode) { if (test_bit(IP_TUNNEL_KEY_BIT, output->tun_flags) && nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id, OVS_TUNNEL_KEY_ATTR_PAD)) return -EMSGSIZE; if (mode & IP_TUNNEL_INFO_BRIDGE) return nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_IPV4_INFO_BRIDGE) ? -EMSGSIZE : 0; switch (tun_proto) { case AF_INET: if (output->u.ipv4.src && nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, output->u.ipv4.src)) return -EMSGSIZE; if (output->u.ipv4.dst && nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, output->u.ipv4.dst)) return -EMSGSIZE; break; case AF_INET6: if (!ipv6_addr_any(&output->u.ipv6.src) && nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_SRC, &output->u.ipv6.src)) return -EMSGSIZE; if (!ipv6_addr_any(&output->u.ipv6.dst) && nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_DST, &output->u.ipv6.dst)) return -EMSGSIZE; break; } if (output->tos && nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->tos)) return -EMSGSIZE; if (nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TTL, output->ttl)) return -EMSGSIZE; if (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, output->tun_flags) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT)) return -EMSGSIZE; if (test_bit(IP_TUNNEL_CSUM_BIT, output->tun_flags) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM)) return -EMSGSIZE; if (output->tp_src && nla_put_be16(skb, OVS_TUNNEL_KEY_ATTR_TP_SRC, output->tp_src)) return -EMSGSIZE; if (output->tp_dst && nla_put_be16(skb, OVS_TUNNEL_KEY_ATTR_TP_DST, output->tp_dst)) return -EMSGSIZE; if (test_bit(IP_TUNNEL_OAM_BIT, output->tun_flags) && nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM)) return -EMSGSIZE; if (swkey_tun_opts_len) { if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, output->tun_flags) && nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS, swkey_tun_opts_len, tun_opts)) return -EMSGSIZE; else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, output->tun_flags) && vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len)) return -EMSGSIZE; else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, output->tun_flags) && nla_put(skb, OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, swkey_tun_opts_len, tun_opts)) return -EMSGSIZE; } return 0; } static int ip_tun_to_nlattr(struct sk_buff *skb, const struct ip_tunnel_key *output, const void *tun_opts, int swkey_tun_opts_len, unsigned short tun_proto, u8 mode) { struct nlattr *nla; int err; nla = nla_nest_start_noflag(skb, OVS_KEY_ATTR_TUNNEL); if (!nla) return -EMSGSIZE; err = __ip_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len, tun_proto, mode); if (err) return err; nla_nest_end(skb, nla); return 0; } int ovs_nla_put_tunnel_info(struct sk_buff *skb, struct ip_tunnel_info *tun_info) { return __ip_tun_to_nlattr(skb, &tun_info->key, ip_tunnel_info_opts(tun_info), tun_info->options_len, ip_tunnel_info_af(tun_info), tun_info->mode); } static int encode_vlan_from_nlattrs(struct sw_flow_match *match, const struct nlattr *a[], bool is_mask, bool inner) { __be16 tci = 0; __be16 tpid = 0; if (a[OVS_KEY_ATTR_VLAN]) tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]); if (a[OVS_KEY_ATTR_ETHERTYPE]) tpid = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]); if (likely(!inner)) { SW_FLOW_KEY_PUT(match, eth.vlan.tpid, tpid, is_mask); SW_FLOW_KEY_PUT(match, eth.vlan.tci, tci, is_mask); } else { SW_FLOW_KEY_PUT(match, eth.cvlan.tpid, tpid, is_mask); SW_FLOW_KEY_PUT(match, eth.cvlan.tci, tci, is_mask); } return 0; } static int validate_vlan_from_nlattrs(const struct sw_flow_match *match, u64 key_attrs, bool inner, const struct nlattr **a, bool log) { __be16 tci = 0; if (!((key_attrs & (1 << OVS_KEY_ATTR_ETHERNET)) && (key_attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) && eth_type_vlan(nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE])))) { /* Not a VLAN. */ return 0; } if (!((key_attrs & (1 << OVS_KEY_ATTR_VLAN)) && (key_attrs & (1 << OVS_KEY_ATTR_ENCAP)))) { OVS_NLERR(log, "Invalid %s frame", (inner) ? "C-VLAN" : "VLAN"); return -EINVAL; } if (a[OVS_KEY_ATTR_VLAN]) tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]); if (!(tci & htons(VLAN_CFI_MASK))) { if (tci) { OVS_NLERR(log, "%s TCI does not have VLAN_CFI_MASK bit set.", (inner) ? "C-VLAN" : "VLAN"); return -EINVAL; } else if (nla_len(a[OVS_KEY_ATTR_ENCAP])) { /* Corner case for truncated VLAN header. */ OVS_NLERR(log, "Truncated %s header has non-zero encap attribute.", (inner) ? "C-VLAN" : "VLAN"); return -EINVAL; } } return 1; } static int validate_vlan_mask_from_nlattrs(const struct sw_flow_match *match, u64 key_attrs, bool inner, const struct nlattr **a, bool log) { __be16 tci = 0; __be16 tpid = 0; bool encap_valid = !!(match->key->eth.vlan.tci & htons(VLAN_CFI_MASK)); bool i_encap_valid = !!(match->key->eth.cvlan.tci & htons(VLAN_CFI_MASK)); if (!(key_attrs & (1 << OVS_KEY_ATTR_ENCAP))) { /* Not a VLAN. */ return 0; } if ((!inner && !encap_valid) || (inner && !i_encap_valid)) { OVS_NLERR(log, "Encap mask attribute is set for non-%s frame.", (inner) ? "C-VLAN" : "VLAN"); return -EINVAL; } if (a[OVS_KEY_ATTR_VLAN]) tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]); if (a[OVS_KEY_ATTR_ETHERTYPE]) tpid = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]); if (tpid != htons(0xffff)) { OVS_NLERR(log, "Must have an exact match on %s TPID (mask=%x).", (inner) ? "C-VLAN" : "VLAN", ntohs(tpid)); return -EINVAL; } if (!(tci & htons(VLAN_CFI_MASK))) { OVS_NLERR(log, "%s TCI mask does not have exact match for VLAN_CFI_MASK bit.", (inner) ? "C-VLAN" : "VLAN"); return -EINVAL; } return 1; } static int __parse_vlan_from_nlattrs(struct sw_flow_match *match, u64 *key_attrs, bool inner, const struct nlattr **a, bool is_mask, bool log) { int err; const struct nlattr *encap; if (!is_mask) err = validate_vlan_from_nlattrs(match, *key_attrs, inner, a, log); else err = validate_vlan_mask_from_nlattrs(match, *key_attrs, inner, a, log); if (err <= 0) return err; err = encode_vlan_from_nlattrs(match, a, is_mask, inner); if (err) return err; *key_attrs &= ~(1 << OVS_KEY_ATTR_ENCAP); *key_attrs &= ~(1 << OVS_KEY_ATTR_VLAN); *key_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE); encap = a[OVS_KEY_ATTR_ENCAP]; if (!is_mask) err = parse_flow_nlattrs(encap, a, key_attrs, log); else err = parse_flow_mask_nlattrs(encap, a, key_attrs, log); return err; } static int parse_vlan_from_nlattrs(struct sw_flow_match *match, u64 *key_attrs, const struct nlattr **a, bool is_mask, bool log) { int err; bool encap_valid = false; err = __parse_vlan_from_nlattrs(match, key_attrs, false, a, is_mask, log); if (err) return err; encap_valid = !!(match->key->eth.vlan.tci & htons(VLAN_CFI_MASK)); if (encap_valid) { err = __parse_vlan_from_nlattrs(match, key_attrs, true, a, is_mask, log); if (err) return err; } return 0; } static int parse_eth_type_from_nlattrs(struct sw_flow_match *match, u64 *attrs, const struct nlattr **a, bool is_mask, bool log) { __be16 eth_type; eth_type = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]); if (is_mask) { /* Always exact match EtherType. */ eth_type = htons(0xffff); } else if (!eth_proto_is_802_3(eth_type)) { OVS_NLERR(log, "EtherType %x is less than min %x", ntohs(eth_type), ETH_P_802_3_MIN); return -EINVAL; } SW_FLOW_KEY_PUT(match, eth.type, eth_type, is_mask); *attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE); return 0; } static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, u64 *attrs, const struct nlattr **a, bool is_mask, bool log) { u8 mac_proto = MAC_PROTO_ETHERNET; if (*attrs & (1 << OVS_KEY_ATTR_DP_HASH)) { u32 hash_val = nla_get_u32(a[OVS_KEY_ATTR_DP_HASH]); SW_FLOW_KEY_PUT(match, ovs_flow_hash, hash_val, is_mask); *attrs &= ~(1 << OVS_KEY_ATTR_DP_HASH); } if (*attrs & (1 << OVS_KEY_ATTR_RECIRC_ID)) { u32 recirc_id = nla_get_u32(a[OVS_KEY_ATTR_RECIRC_ID]); SW_FLOW_KEY_PUT(match, recirc_id, recirc_id, is_mask); *attrs &= ~(1 << OVS_KEY_ATTR_RECIRC_ID); } if (*attrs & (1 << OVS_KEY_ATTR_PRIORITY)) { SW_FLOW_KEY_PUT(match, phy.priority, nla_get_u32(a[OVS_KEY_ATTR_PRIORITY]), is_mask); *attrs &= ~(1 << OVS_KEY_ATTR_PRIORITY); } if (*attrs & (1 << OVS_KEY_ATTR_IN_PORT)) { u32 in_port = nla_get_u32(a[OVS_KEY_ATTR_IN_PORT]); if (is_mask) { in_port = 0xffffffff; /* Always exact match in_port. */ } else if (in_port >= DP_MAX_PORTS) { OVS_NLERR(log, "Port %d exceeds max allowable %d", in_port, DP_MAX_PORTS); return -EINVAL; } SW_FLOW_KEY_PUT(match, phy.in_port, in_port, is_mask); *attrs &= ~(1 << OVS_KEY_ATTR_IN_PORT); } else if (!is_mask) { SW_FLOW_KEY_PUT(match, phy.in_port, DP_MAX_PORTS, is_mask); } if (*attrs & (1 << OVS_KEY_ATTR_SKB_MARK)) { uint32_t mark = nla_get_u32(a[OVS_KEY_ATTR_SKB_MARK]); SW_FLOW_KEY_PUT(match, phy.skb_mark, mark, is_mask); *attrs &= ~(1 << OVS_KEY_ATTR_SKB_MARK); } if (*attrs & (1 << OVS_KEY_ATTR_TUNNEL)) { if (ip_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match, is_mask, log) < 0) return -EINVAL; *attrs &= ~(1 << OVS_KEY_ATTR_TUNNEL); } if (*attrs & (1 << OVS_KEY_ATTR_CT_STATE) && ovs_ct_verify(net, OVS_KEY_ATTR_CT_STATE)) { u32 ct_state = nla_get_u32(a[OVS_KEY_ATTR_CT_STATE]); if (ct_state & ~CT_SUPPORTED_MASK) { OVS_NLERR(log, "ct_state flags %08x unsupported", ct_state); return -EINVAL; } SW_FLOW_KEY_PUT(match, ct_state, ct_state, is_mask); *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_STATE); } if (*attrs & (1 << OVS_KEY_ATTR_CT_ZONE) && ovs_ct_verify(net, OVS_KEY_ATTR_CT_ZONE)) { u16 ct_zone = nla_get_u16(a[OVS_KEY_ATTR_CT_ZONE]); SW_FLOW_KEY_PUT(match, ct_zone, ct_zone, is_mask); *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ZONE); } if (*attrs & (1 << OVS_KEY_ATTR_CT_MARK) && ovs_ct_verify(net, OVS_KEY_ATTR_CT_MARK)) { u32 mark = nla_get_u32(a[OVS_KEY_ATTR_CT_MARK]); SW_FLOW_KEY_PUT(match, ct.mark, mark, is_mask); *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_MARK); } if (*attrs & (1 << OVS_KEY_ATTR_CT_LABELS) && ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABELS)) { const struct ovs_key_ct_labels *cl; cl = nla_data(a[OVS_KEY_ATTR_CT_LABELS]); SW_FLOW_KEY_MEMCPY(match, ct.labels, cl->ct_labels, sizeof(*cl), is_mask); *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABELS); } if (*attrs & (1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4)) { const struct ovs_key_ct_tuple_ipv4 *ct; ct = nla_data(a[OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4]); SW_FLOW_KEY_PUT(match, ipv4.ct_orig.src, ct->ipv4_src, is_mask); SW_FLOW_KEY_PUT(match, ipv4.ct_orig.dst, ct->ipv4_dst, is_mask); SW_FLOW_KEY_PUT(match, ct.orig_tp.src, ct->src_port, is_mask); SW_FLOW_KEY_PUT(match, ct.orig_tp.dst, ct->dst_port, is_mask); SW_FLOW_KEY_PUT(match, ct_orig_proto, ct->ipv4_proto, is_mask); *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4); } if (*attrs & (1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6)) { const struct ovs_key_ct_tuple_ipv6 *ct; ct = nla_data(a[OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6]); SW_FLOW_KEY_MEMCPY(match, ipv6.ct_orig.src, &ct->ipv6_src, sizeof(match->key->ipv6.ct_orig.src), is_mask); SW_FLOW_KEY_MEMCPY(match, ipv6.ct_orig.dst, &ct->ipv6_dst, sizeof(match->key->ipv6.ct_orig.dst), is_mask); SW_FLOW_KEY_PUT(match, ct.orig_tp.src, ct->src_port, is_mask); SW_FLOW_KEY_PUT(match, ct.orig_tp.dst, ct->dst_port, is_mask); SW_FLOW_KEY_PUT(match, ct_orig_proto, ct->ipv6_proto, is_mask); *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6); } /* For layer 3 packets the Ethernet type is provided * and treated as metadata but no MAC addresses are provided. */ if (!(*attrs & (1ULL << OVS_KEY_ATTR_ETHERNET)) && (*attrs & (1ULL << OVS_KEY_ATTR_ETHERTYPE))) mac_proto = MAC_PROTO_NONE; /* Always exact match mac_proto */ SW_FLOW_KEY_PUT(match, mac_proto, is_mask ? 0xff : mac_proto, is_mask); if (mac_proto == MAC_PROTO_NONE) return parse_eth_type_from_nlattrs(match, attrs, a, is_mask, log); return 0; } int nsh_hdr_from_nlattr(const struct nlattr *attr, struct nshhdr *nh, size_t size) { struct nlattr *a; int rem; u8 flags = 0; u8 ttl = 0; int mdlen = 0; /* validate_nsh has check this, so we needn't do duplicate check here */ if (size < NSH_BASE_HDR_LEN) return -ENOBUFS; nla_for_each_nested(a, attr, rem) { int type = nla_type(a); switch (type) { case OVS_NSH_KEY_ATTR_BASE: { const struct ovs_nsh_key_base *base = nla_data(a); flags = base->flags; ttl = base->ttl; nh->np = base->np; nh->mdtype = base->mdtype; nh->path_hdr = base->path_hdr; break; } case OVS_NSH_KEY_ATTR_MD1: mdlen = nla_len(a); if (mdlen > size - NSH_BASE_HDR_LEN) return -ENOBUFS; memcpy(&nh->md1, nla_data(a), mdlen); break; case OVS_NSH_KEY_ATTR_MD2: mdlen = nla_len(a); if (mdlen > size - NSH_BASE_HDR_LEN) return -ENOBUFS; memcpy(&nh->md2, nla_data(a), mdlen); break; default: return -EINVAL; } } /* nsh header length = NSH_BASE_HDR_LEN + mdlen */ nh->ver_flags_ttl_len = 0; nsh_set_flags_ttl_len(nh, flags, ttl, NSH_BASE_HDR_LEN + mdlen); return 0; } int nsh_key_from_nlattr(const struct nlattr *attr, struct ovs_key_nsh *nsh, struct ovs_key_nsh *nsh_mask) { struct nlattr *a; int rem; /* validate_nsh has check this, so we needn't do duplicate check here */ nla_for_each_nested(a, attr, rem) { int type = nla_type(a); switch (type) { case OVS_NSH_KEY_ATTR_BASE: { const struct ovs_nsh_key_base *base = nla_data(a); const struct ovs_nsh_key_base *base_mask = base + 1; nsh->base = *base; nsh_mask->base = *base_mask; break; } case OVS_NSH_KEY_ATTR_MD1: { const struct ovs_nsh_key_md1 *md1 = nla_data(a); const struct ovs_nsh_key_md1 *md1_mask = md1 + 1; memcpy(nsh->context, md1->context, sizeof(*md1)); memcpy(nsh_mask->context, md1_mask->context, sizeof(*md1_mask)); break; } case OVS_NSH_KEY_ATTR_MD2: /* Not supported yet */ return -ENOTSUPP; default: return -EINVAL; } } return 0; } static int nsh_key_put_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool is_push_nsh, bool log) { struct nlattr *a; int rem; bool has_base = false; bool has_md1 = false; bool has_md2 = false; u8 mdtype = 0; int mdlen = 0; if (WARN_ON(is_push_nsh && is_mask)) return -EINVAL; nla_for_each_nested(a, attr, rem) { int type = nla_type(a); int i; if (type > OVS_NSH_KEY_ATTR_MAX) { OVS_NLERR(log, "nsh attr %d is out of range max %d", type, OVS_NSH_KEY_ATTR_MAX); return -EINVAL; } if (!check_attr_len(nla_len(a), ovs_nsh_key_attr_lens[type].len)) { OVS_NLERR( log, "nsh attr %d has unexpected len %d expected %d", type, nla_len(a), ovs_nsh_key_attr_lens[type].len ); return -EINVAL; } switch (type) { case OVS_NSH_KEY_ATTR_BASE: { const struct ovs_nsh_key_base *base = nla_data(a); has_base = true; mdtype = base->mdtype; SW_FLOW_KEY_PUT(match, nsh.base.flags, base->flags, is_mask); SW_FLOW_KEY_PUT(match, nsh.base.ttl, base->ttl, is_mask); SW_FLOW_KEY_PUT(match, nsh.base.mdtype, base->mdtype, is_mask); SW_FLOW_KEY_PUT(match, nsh.base.np, base->np, is_mask); SW_FLOW_KEY_PUT(match, nsh.base.path_hdr, base->path_hdr, is_mask); break; } case OVS_NSH_KEY_ATTR_MD1: { const struct ovs_nsh_key_md1 *md1 = nla_data(a); has_md1 = true; for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) SW_FLOW_KEY_PUT(match, nsh.context[i], md1->context[i], is_mask); break; } case OVS_NSH_KEY_ATTR_MD2: if (!is_push_nsh) /* Not supported MD type 2 yet */ return -ENOTSUPP; has_md2 = true; mdlen = nla_len(a); if (mdlen > NSH_CTX_HDRS_MAX_LEN || mdlen <= 0) { OVS_NLERR( log, "Invalid MD length %d for MD type %d", mdlen, mdtype ); return -EINVAL; } break; default: OVS_NLERR(log, "Unknown nsh attribute %d", type); return -EINVAL; } } if (rem > 0) { OVS_NLERR(log, "nsh attribute has %d unknown bytes.", rem); return -EINVAL; } if (has_md1 && has_md2) { OVS_NLERR( 1, "invalid nsh attribute: md1 and md2 are exclusive." ); return -EINVAL; } if (!is_mask) { if ((has_md1 && mdtype != NSH_M_TYPE1) || (has_md2 && mdtype != NSH_M_TYPE2)) { OVS_NLERR(1, "nsh attribute has unmatched MD type %d.", mdtype); return -EINVAL; } if (is_push_nsh && (!has_base || (!has_md1 && !has_md2))) { OVS_NLERR( 1, "push_nsh: missing base or metadata attributes" ); return -EINVAL; } } return 0; } static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match, u64 attrs, const struct nlattr **a, bool is_mask, bool log) { int err; err = metadata_from_nlattrs(net, match, &attrs, a, is_mask, log); if (err) return err; if (attrs & (1 << OVS_KEY_ATTR_ETHERNET)) { const struct ovs_key_ethernet *eth_key; eth_key = nla_data(a[OVS_KEY_ATTR_ETHERNET]); SW_FLOW_KEY_MEMCPY(match, eth.src, eth_key->eth_src, ETH_ALEN, is_mask); SW_FLOW_KEY_MEMCPY(match, eth.dst, eth_key->eth_dst, ETH_ALEN, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_ETHERNET); if (attrs & (1 << OVS_KEY_ATTR_VLAN)) { /* VLAN attribute is always parsed before getting here since it * may occur multiple times. */ OVS_NLERR(log, "VLAN attribute unexpected."); return -EINVAL; } if (attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) { err = parse_eth_type_from_nlattrs(match, &attrs, a, is_mask, log); if (err) return err; } else if (!is_mask) { SW_FLOW_KEY_PUT(match, eth.type, htons(ETH_P_802_2), is_mask); } } else if (!match->key->eth.type) { OVS_NLERR(log, "Either Ethernet header or EtherType is required."); return -EINVAL; } if (attrs & (1 << OVS_KEY_ATTR_IPV4)) { const struct ovs_key_ipv4 *ipv4_key; ipv4_key = nla_data(a[OVS_KEY_ATTR_IPV4]); if (!is_mask && ipv4_key->ipv4_frag > OVS_FRAG_TYPE_MAX) { OVS_NLERR(log, "IPv4 frag type %d is out of range max %d", ipv4_key->ipv4_frag, OVS_FRAG_TYPE_MAX); return -EINVAL; } SW_FLOW_KEY_PUT(match, ip.proto, ipv4_key->ipv4_proto, is_mask); SW_FLOW_KEY_PUT(match, ip.tos, ipv4_key->ipv4_tos, is_mask); SW_FLOW_KEY_PUT(match, ip.ttl, ipv4_key->ipv4_ttl, is_mask); SW_FLOW_KEY_PUT(match, ip.frag, ipv4_key->ipv4_frag, is_mask); SW_FLOW_KEY_PUT(match, ipv4.addr.src, ipv4_key->ipv4_src, is_mask); SW_FLOW_KEY_PUT(match, ipv4.addr.dst, ipv4_key->ipv4_dst, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_IPV4); } if (attrs & (1 << OVS_KEY_ATTR_IPV6)) { const struct ovs_key_ipv6 *ipv6_key; ipv6_key = nla_data(a[OVS_KEY_ATTR_IPV6]); if (!is_mask && ipv6_key->ipv6_frag > OVS_FRAG_TYPE_MAX) { OVS_NLERR(log, "IPv6 frag type %d is out of range max %d", ipv6_key->ipv6_frag, OVS_FRAG_TYPE_MAX); return -EINVAL; } if (!is_mask && ipv6_key->ipv6_label & htonl(0xFFF00000)) { OVS_NLERR(log, "IPv6 flow label %x is out of range (max=%x)", ntohl(ipv6_key->ipv6_label), (1 << 20) - 1); return -EINVAL; } SW_FLOW_KEY_PUT(match, ipv6.label, ipv6_key->ipv6_label, is_mask); SW_FLOW_KEY_PUT(match, ip.proto, ipv6_key->ipv6_proto, is_mask); SW_FLOW_KEY_PUT(match, ip.tos, ipv6_key->ipv6_tclass, is_mask); SW_FLOW_KEY_PUT(match, ip.ttl, ipv6_key->ipv6_hlimit, is_mask); SW_FLOW_KEY_PUT(match, ip.frag, ipv6_key->ipv6_frag, is_mask); SW_FLOW_KEY_MEMCPY(match, ipv6.addr.src, ipv6_key->ipv6_src, sizeof(match->key->ipv6.addr.src), is_mask); SW_FLOW_KEY_MEMCPY(match, ipv6.addr.dst, ipv6_key->ipv6_dst, sizeof(match->key->ipv6.addr.dst), is_mask); attrs &= ~(1 << OVS_KEY_ATTR_IPV6); } if (attrs & (1ULL << OVS_KEY_ATTR_IPV6_EXTHDRS)) { const struct ovs_key_ipv6_exthdrs *ipv6_exthdrs_key; ipv6_exthdrs_key = nla_data(a[OVS_KEY_ATTR_IPV6_EXTHDRS]); SW_FLOW_KEY_PUT(match, ipv6.exthdrs, ipv6_exthdrs_key->hdrs, is_mask); attrs &= ~(1ULL << OVS_KEY_ATTR_IPV6_EXTHDRS); } if (attrs & (1 << OVS_KEY_ATTR_ARP)) { const struct ovs_key_arp *arp_key; arp_key = nla_data(a[OVS_KEY_ATTR_ARP]); if (!is_mask && (arp_key->arp_op & htons(0xff00))) { OVS_NLERR(log, "Unknown ARP opcode (opcode=%d).", arp_key->arp_op); return -EINVAL; } SW_FLOW_KEY_PUT(match, ipv4.addr.src, arp_key->arp_sip, is_mask); SW_FLOW_KEY_PUT(match, ipv4.addr.dst, arp_key->arp_tip, is_mask); SW_FLOW_KEY_PUT(match, ip.proto, ntohs(arp_key->arp_op), is_mask); SW_FLOW_KEY_MEMCPY(match, ipv4.arp.sha, arp_key->arp_sha, ETH_ALEN, is_mask); SW_FLOW_KEY_MEMCPY(match, ipv4.arp.tha, arp_key->arp_tha, ETH_ALEN, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_ARP); } if (attrs & (1 << OVS_KEY_ATTR_NSH)) { if (nsh_key_put_from_nlattr(a[OVS_KEY_ATTR_NSH], match, is_mask, false, log) < 0) return -EINVAL; attrs &= ~(1 << OVS_KEY_ATTR_NSH); } if (attrs & (1 << OVS_KEY_ATTR_MPLS)) { const struct ovs_key_mpls *mpls_key; u32 hdr_len; u32 label_count, label_count_mask, i; mpls_key = nla_data(a[OVS_KEY_ATTR_MPLS]); hdr_len = nla_len(a[OVS_KEY_ATTR_MPLS]); label_count = hdr_len / sizeof(struct ovs_key_mpls); if (label_count == 0 || label_count > MPLS_LABEL_DEPTH || hdr_len % sizeof(struct ovs_key_mpls)) return -EINVAL; label_count_mask = GENMASK(label_count - 1, 0); for (i = 0 ; i < label_count; i++) SW_FLOW_KEY_PUT(match, mpls.lse[i], mpls_key[i].mpls_lse, is_mask); SW_FLOW_KEY_PUT(match, mpls.num_labels_mask, label_count_mask, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_MPLS); } if (attrs & (1 << OVS_KEY_ATTR_TCP)) { const struct ovs_key_tcp *tcp_key; tcp_key = nla_data(a[OVS_KEY_ATTR_TCP]); SW_FLOW_KEY_PUT(match, tp.src, tcp_key->tcp_src, is_mask); SW_FLOW_KEY_PUT(match, tp.dst, tcp_key->tcp_dst, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_TCP); } if (attrs & (1 << OVS_KEY_ATTR_TCP_FLAGS)) { SW_FLOW_KEY_PUT(match, tp.flags, nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]), is_mask); attrs &= ~(1 << OVS_KEY_ATTR_TCP_FLAGS); } if (attrs & (1 << OVS_KEY_ATTR_UDP)) { const struct ovs_key_udp *udp_key; udp_key = nla_data(a[OVS_KEY_ATTR_UDP]); SW_FLOW_KEY_PUT(match, tp.src, udp_key->udp_src, is_mask); SW_FLOW_KEY_PUT(match, tp.dst, udp_key->udp_dst, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_UDP); } if (attrs & (1 << OVS_KEY_ATTR_SCTP)) { const struct ovs_key_sctp *sctp_key; sctp_key = nla_data(a[OVS_KEY_ATTR_SCTP]); SW_FLOW_KEY_PUT(match, tp.src, sctp_key->sctp_src, is_mask); SW_FLOW_KEY_PUT(match, tp.dst, sctp_key->sctp_dst, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_SCTP); } if (attrs & (1 << OVS_KEY_ATTR_ICMP)) { const struct ovs_key_icmp *icmp_key; icmp_key = nla_data(a[OVS_KEY_ATTR_ICMP]); SW_FLOW_KEY_PUT(match, tp.src, htons(icmp_key->icmp_type), is_mask); SW_FLOW_KEY_PUT(match, tp.dst, htons(icmp_key->icmp_code), is_mask); attrs &= ~(1 << OVS_KEY_ATTR_ICMP); } if (attrs & (1 << OVS_KEY_ATTR_ICMPV6)) { const struct ovs_key_icmpv6 *icmpv6_key; icmpv6_key = nla_data(a[OVS_KEY_ATTR_ICMPV6]); SW_FLOW_KEY_PUT(match, tp.src, htons(icmpv6_key->icmpv6_type), is_mask); SW_FLOW_KEY_PUT(match, tp.dst, htons(icmpv6_key->icmpv6_code), is_mask); attrs &= ~(1 << OVS_KEY_ATTR_ICMPV6); } if (attrs & (1 << OVS_KEY_ATTR_ND)) { const struct ovs_key_nd *nd_key; nd_key = nla_data(a[OVS_KEY_ATTR_ND]); SW_FLOW_KEY_MEMCPY(match, ipv6.nd.target, nd_key->nd_target, sizeof(match->key->ipv6.nd.target), is_mask); SW_FLOW_KEY_MEMCPY(match, ipv6.nd.sll, nd_key->nd_sll, ETH_ALEN, is_mask); SW_FLOW_KEY_MEMCPY(match, ipv6.nd.tll, nd_key->nd_tll, ETH_ALEN, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_ND); } if (attrs != 0) { OVS_NLERR(log, "Unknown key attributes %llx", (unsigned long long)attrs); return -EINVAL; } return 0; } static void nlattr_set(struct nlattr *attr, u8 val, const struct ovs_len_tbl *tbl) { struct nlattr *nla; int rem; /* The nlattr stream should already have been validated */ nla_for_each_nested(nla, attr, rem) { if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) nlattr_set(nla, val, tbl[nla_type(nla)].next ? : tbl); else memset(nla_data(nla), val, nla_len(nla)); if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE) *(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK; } } static void mask_set_nlattr(struct nlattr *attr, u8 val) { nlattr_set(attr, val, ovs_key_lens); } /** * ovs_nla_get_match - parses Netlink attributes into a flow key and * mask. In case the 'mask' is NULL, the flow is treated as exact match * flow. Otherwise, it is treated as a wildcarded flow, except the mask * does not include any don't care bit. * @net: Used to determine per-namespace field support. * @match: receives the extracted flow match information. * @nla_key: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute * sequence. The fields should of the packet that triggered the creation * of this flow. * @nla_mask: Optional. Netlink attribute holding nested %OVS_KEY_ATTR_* * Netlink attribute specifies the mask field of the wildcarded flow. * @log: Boolean to allow kernel error logging. Normally true, but when * probing for feature compatibility this should be passed in as false to * suppress unnecessary error logging. */ int ovs_nla_get_match(struct net *net, struct sw_flow_match *match, const struct nlattr *nla_key, const struct nlattr *nla_mask, bool log) { const struct nlattr *a[OVS_KEY_ATTR_MAX + 1]; struct nlattr *newmask = NULL; u64 key_attrs = 0; u64 mask_attrs = 0; int err; err = parse_flow_nlattrs(nla_key, a, &key_attrs, log); if (err) return err; err = parse_vlan_from_nlattrs(match, &key_attrs, a, false, log); if (err) return err; err = ovs_key_from_nlattrs(net, match, key_attrs, a, false, log); if (err) return err; if (match->mask) { if (!nla_mask) { /* Create an exact match mask. We need to set to 0xff * all the 'match->mask' fields that have been touched * in 'match->key'. We cannot simply memset * 'match->mask', because padding bytes and fields not * specified in 'match->key' should be left to 0. * Instead, we use a stream of netlink attributes, * copied from 'key' and set to 0xff. * ovs_key_from_nlattrs() will take care of filling * 'match->mask' appropriately. */ newmask = kmemdup(nla_key, nla_total_size(nla_len(nla_key)), GFP_KERNEL); if (!newmask) return -ENOMEM; mask_set_nlattr(newmask, 0xff); /* The userspace does not send tunnel attributes that * are 0, but we should not wildcard them nonetheless. */ if (match->key->tun_proto) SW_FLOW_KEY_MEMSET_FIELD(match, tun_key, 0xff, true); nla_mask = newmask; } err = parse_flow_mask_nlattrs(nla_mask, a, &mask_attrs, log); if (err) goto free_newmask; /* Always match on tci. */ SW_FLOW_KEY_PUT(match, eth.vlan.tci, htons(0xffff), true); SW_FLOW_KEY_PUT(match, eth.cvlan.tci, htons(0xffff), true); err = parse_vlan_from_nlattrs(match, &mask_attrs, a, true, log); if (err) goto free_newmask; err = ovs_key_from_nlattrs(net, match, mask_attrs, a, true, log); if (err) goto free_newmask; } if (!match_validate(match, key_attrs, mask_attrs, log)) err = -EINVAL; free_newmask: kfree(newmask); return err; } static size_t get_ufid_len(const struct nlattr *attr, bool log) { size_t len; if (!attr) return 0; len = nla_len(attr); if (len < 1 || len > MAX_UFID_LENGTH) { OVS_NLERR(log, "ufid size %u bytes exceeds the range (1, %d)", nla_len(attr), MAX_UFID_LENGTH); return 0; } return len; } /* Initializes 'flow->ufid', returning true if 'attr' contains a valid UFID, * or false otherwise. */ bool ovs_nla_get_ufid(struct sw_flow_id *sfid, const struct nlattr *attr, bool log) { sfid->ufid_len = get_ufid_len(attr, log); if (sfid->ufid_len) memcpy(sfid->ufid, nla_data(attr), sfid->ufid_len); return sfid->ufid_len; } int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid, const struct sw_flow_key *key, bool log) { struct sw_flow_key *new_key; if (ovs_nla_get_ufid(sfid, ufid, log)) return 0; /* If UFID was not provided, use unmasked key. */ new_key = kmalloc(sizeof(*new_key), GFP_KERNEL); if (!new_key) return -ENOMEM; memcpy(new_key, key, sizeof(*key)); sfid->unmasked_key = new_key; return 0; } u32 ovs_nla_get_ufid_flags(const struct nlattr *attr) { return nla_get_u32_default(attr, 0); } /** * ovs_nla_get_flow_metadata - parses Netlink attributes into a flow key. * @net: Network namespace. * @key: Receives extracted in_port, priority, tun_key, skb_mark and conntrack * metadata. * @a: Array of netlink attributes holding parsed %OVS_KEY_ATTR_* Netlink * attributes. * @attrs: Bit mask for the netlink attributes included in @a. * @log: Boolean to allow kernel error logging. Normally true, but when * probing for feature compatibility this should be passed in as false to * suppress unnecessary error logging. * * This parses a series of Netlink attributes that form a flow key, which must * take the same form accepted by flow_from_nlattrs(), but only enough of it to * get the metadata, that is, the parts of the flow key that cannot be * extracted from the packet itself. * * This must be called before the packet key fields are filled in 'key'. */ int ovs_nla_get_flow_metadata(struct net *net, const struct nlattr *a[OVS_KEY_ATTR_MAX + 1], u64 attrs, struct sw_flow_key *key, bool log) { struct sw_flow_match match; memset(&match, 0, sizeof(match)); match.key = key; key->ct_state = 0; key->ct_zone = 0; key->ct_orig_proto = 0; memset(&key->ct, 0, sizeof(key->ct)); memset(&key->ipv4.ct_orig, 0, sizeof(key->ipv4.ct_orig)); memset(&key->ipv6.ct_orig, 0, sizeof(key->ipv6.ct_orig)); key->phy.in_port = DP_MAX_PORTS; return metadata_from_nlattrs(net, &match, &attrs, a, false, log); } static int ovs_nla_put_vlan(struct sk_buff *skb, const struct vlan_head *vh, bool is_mask) { __be16 eth_type = !is_mask ? vh->tpid : htons(0xffff); if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, eth_type) || nla_put_be16(skb, OVS_KEY_ATTR_VLAN, vh->tci)) return -EMSGSIZE; return 0; } static int nsh_key_to_nlattr(const struct ovs_key_nsh *nsh, bool is_mask, struct sk_buff *skb) { struct nlattr *start; start = nla_nest_start_noflag(skb, OVS_KEY_ATTR_NSH); if (!start) return -EMSGSIZE; if (nla_put(skb, OVS_NSH_KEY_ATTR_BASE, sizeof(nsh->base), &nsh->base)) goto nla_put_failure; if (is_mask || nsh->base.mdtype == NSH_M_TYPE1) { if (nla_put(skb, OVS_NSH_KEY_ATTR_MD1, sizeof(nsh->context), nsh->context)) goto nla_put_failure; } /* Don't support MD type 2 yet */ nla_nest_end(skb, start); return 0; nla_put_failure: return -EMSGSIZE; } static int __ovs_nla_put_key(const struct sw_flow_key *swkey, const struct sw_flow_key *output, bool is_mask, struct sk_buff *skb) { struct ovs_key_ethernet *eth_key; struct nlattr *nla; struct nlattr *encap = NULL; struct nlattr *in_encap = NULL; if (nla_put_u32(skb, OVS_KEY_ATTR_RECIRC_ID, output->recirc_id)) goto nla_put_failure; if (nla_put_u32(skb, OVS_KEY_ATTR_DP_HASH, output->ovs_flow_hash)) goto nla_put_failure; if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority)) goto nla_put_failure; if ((swkey->tun_proto || is_mask)) { const void *opts = NULL; if (ip_tunnel_is_options_present(output->tun_key.tun_flags)) opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len); if (ip_tun_to_nlattr(skb, &output->tun_key, opts, swkey->tun_opts_len, swkey->tun_proto, 0)) goto nla_put_failure; } if (swkey->phy.in_port == DP_MAX_PORTS) { if (is_mask && (output->phy.in_port == 0xffff)) if (nla_put_u32(skb, OVS_KEY_ATTR_IN_PORT, 0xffffffff)) goto nla_put_failure; } else { u16 upper_u16; upper_u16 = !is_mask ? 0 : 0xffff; if (nla_put_u32(skb, OVS_KEY_ATTR_IN_PORT, (upper_u16 << 16) | output->phy.in_port)) goto nla_put_failure; } if (nla_put_u32(skb, OVS_KEY_ATTR_SKB_MARK, output->phy.skb_mark)) goto nla_put_failure; if (ovs_ct_put_key(swkey, output, skb)) goto nla_put_failure; if (ovs_key_mac_proto(swkey) == MAC_PROTO_ETHERNET) { nla = nla_reserve(skb, OVS_KEY_ATTR_ETHERNET, sizeof(*eth_key)); if (!nla) goto nla_put_failure; eth_key = nla_data(nla); ether_addr_copy(eth_key->eth_src, output->eth.src); ether_addr_copy(eth_key->eth_dst, output->eth.dst); if (swkey->eth.vlan.tci || eth_type_vlan(swkey->eth.type)) { if (ovs_nla_put_vlan(skb, &output->eth.vlan, is_mask)) goto nla_put_failure; encap = nla_nest_start_noflag(skb, OVS_KEY_ATTR_ENCAP); if (!swkey->eth.vlan.tci) goto unencap; if (swkey->eth.cvlan.tci || eth_type_vlan(swkey->eth.type)) { if (ovs_nla_put_vlan(skb, &output->eth.cvlan, is_mask)) goto nla_put_failure; in_encap = nla_nest_start_noflag(skb, OVS_KEY_ATTR_ENCAP); if (!swkey->eth.cvlan.tci) goto unencap; } } if (swkey->eth.type == htons(ETH_P_802_2)) { /* * Ethertype 802.2 is represented in the netlink with omitted * OVS_KEY_ATTR_ETHERTYPE in the flow key attribute, and * 0xffff in the mask attribute. Ethertype can also * be wildcarded. */ if (is_mask && output->eth.type) if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, output->eth.type)) goto nla_put_failure; goto unencap; } } if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, output->eth.type)) goto nla_put_failure; if (eth_type_vlan(swkey->eth.type)) { /* There are 3 VLAN tags, we don't know anything about the rest * of the packet, so truncate here. */ WARN_ON_ONCE(!(encap && in_encap)); goto unencap; } if (swkey->eth.type == htons(ETH_P_IP)) { struct ovs_key_ipv4 *ipv4_key; nla = nla_reserve(skb, OVS_KEY_ATTR_IPV4, sizeof(*ipv4_key)); if (!nla) goto nla_put_failure; ipv4_key = nla_data(nla); ipv4_key->ipv4_src = output->ipv4.addr.src; ipv4_key->ipv4_dst = output->ipv4.addr.dst; ipv4_key->ipv4_proto = output->ip.proto; ipv4_key->ipv4_tos = output->ip.tos; ipv4_key->ipv4_ttl = output->ip.ttl; ipv4_key->ipv4_frag = output->ip.frag; } else if (swkey->eth.type == htons(ETH_P_IPV6)) { struct ovs_key_ipv6 *ipv6_key; struct ovs_key_ipv6_exthdrs *ipv6_exthdrs_key; nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6, sizeof(*ipv6_key)); if (!nla) goto nla_put_failure; ipv6_key = nla_data(nla); memcpy(ipv6_key->ipv6_src, &output->ipv6.addr.src, sizeof(ipv6_key->ipv6_src)); memcpy(ipv6_key->ipv6_dst, &output->ipv6.addr.dst, sizeof(ipv6_key->ipv6_dst)); ipv6_key->ipv6_label = output->ipv6.label; ipv6_key->ipv6_proto = output->ip.proto; ipv6_key->ipv6_tclass = output->ip.tos; ipv6_key->ipv6_hlimit = output->ip.ttl; ipv6_key->ipv6_frag = output->ip.frag; nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6_EXTHDRS, sizeof(*ipv6_exthdrs_key)); if (!nla) goto nla_put_failure; ipv6_exthdrs_key = nla_data(nla); ipv6_exthdrs_key->hdrs = output->ipv6.exthdrs; } else if (swkey->eth.type == htons(ETH_P_NSH)) { if (nsh_key_to_nlattr(&output->nsh, is_mask, skb)) goto nla_put_failure; } else if (swkey->eth.type == htons(ETH_P_ARP) || swkey->eth.type == htons(ETH_P_RARP)) { struct ovs_key_arp *arp_key; nla = nla_reserve(skb, OVS_KEY_ATTR_ARP, sizeof(*arp_key)); if (!nla) goto nla_put_failure; arp_key = nla_data(nla); memset(arp_key, 0, sizeof(struct ovs_key_arp)); arp_key->arp_sip = output->ipv4.addr.src; arp_key->arp_tip = output->ipv4.addr.dst; arp_key->arp_op = htons(output->ip.proto); ether_addr_copy(arp_key->arp_sha, output->ipv4.arp.sha); ether_addr_copy(arp_key->arp_tha, output->ipv4.arp.tha); } else if (eth_p_mpls(swkey->eth.type)) { u8 i, num_labels; struct ovs_key_mpls *mpls_key; num_labels = hweight_long(output->mpls.num_labels_mask); nla = nla_reserve(skb, OVS_KEY_ATTR_MPLS, num_labels * sizeof(*mpls_key)); if (!nla) goto nla_put_failure; mpls_key = nla_data(nla); for (i = 0; i < num_labels; i++) mpls_key[i].mpls_lse = output->mpls.lse[i]; } if ((swkey->eth.type == htons(ETH_P_IP) || swkey->eth.type == htons(ETH_P_IPV6)) && swkey->ip.frag != OVS_FRAG_TYPE_LATER) { if (swkey->ip.proto == IPPROTO_TCP) { struct ovs_key_tcp *tcp_key; nla = nla_reserve(skb, OVS_KEY_ATTR_TCP, sizeof(*tcp_key)); if (!nla) goto nla_put_failure; tcp_key = nla_data(nla); tcp_key->tcp_src = output->tp.src; tcp_key->tcp_dst = output->tp.dst; if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS, output->tp.flags)) goto nla_put_failure; } else if (swkey->ip.proto == IPPROTO_UDP) { struct ovs_key_udp *udp_key; nla = nla_reserve(skb, OVS_KEY_ATTR_UDP, sizeof(*udp_key)); if (!nla) goto nla_put_failure; udp_key = nla_data(nla); udp_key->udp_src = output->tp.src; udp_key->udp_dst = output->tp.dst; } else if (swkey->ip.proto == IPPROTO_SCTP) { struct ovs_key_sctp *sctp_key; nla = nla_reserve(skb, OVS_KEY_ATTR_SCTP, sizeof(*sctp_key)); if (!nla) goto nla_put_failure; sctp_key = nla_data(nla); sctp_key->sctp_src = output->tp.src; sctp_key->sctp_dst = output->tp.dst; } else if (swkey->eth.type == htons(ETH_P_IP) && swkey->ip.proto == IPPROTO_ICMP) { struct ovs_key_icmp *icmp_key; nla = nla_reserve(skb, OVS_KEY_ATTR_ICMP, sizeof(*icmp_key)); if (!nla) goto nla_put_failure; icmp_key = nla_data(nla); icmp_key->icmp_type = ntohs(output->tp.src); icmp_key->icmp_code = ntohs(output->tp.dst); } else if (swkey->eth.type == htons(ETH_P_IPV6) && swkey->ip.proto == IPPROTO_ICMPV6) { struct ovs_key_icmpv6 *icmpv6_key; nla = nla_reserve(skb, OVS_KEY_ATTR_ICMPV6, sizeof(*icmpv6_key)); if (!nla) goto nla_put_failure; icmpv6_key = nla_data(nla); icmpv6_key->icmpv6_type = ntohs(output->tp.src); icmpv6_key->icmpv6_code = ntohs(output->tp.dst); if (swkey->tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) || swkey->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) { struct ovs_key_nd *nd_key; nla = nla_reserve(skb, OVS_KEY_ATTR_ND, sizeof(*nd_key)); if (!nla) goto nla_put_failure; nd_key = nla_data(nla); memcpy(nd_key->nd_target, &output->ipv6.nd.target, sizeof(nd_key->nd_target)); ether_addr_copy(nd_key->nd_sll, output->ipv6.nd.sll); ether_addr_copy(nd_key->nd_tll, output->ipv6.nd.tll); } } } unencap: if (in_encap) nla_nest_end(skb, in_encap); if (encap) nla_nest_end(skb, encap); return 0; nla_put_failure: return -EMSGSIZE; } int ovs_nla_put_key(const struct sw_flow_key *swkey, const struct sw_flow_key *output, int attr, bool is_mask, struct sk_buff *skb) { int err; struct nlattr *nla; nla = nla_nest_start_noflag(skb, attr); if (!nla) return -EMSGSIZE; err = __ovs_nla_put_key(swkey, output, is_mask, skb); if (err) return err; nla_nest_end(skb, nla); return 0; } /* Called with ovs_mutex or RCU read lock. */ int ovs_nla_put_identifier(const struct sw_flow *flow, struct sk_buff *skb) { if (ovs_identifier_is_ufid(&flow->id)) return nla_put(skb, OVS_FLOW_ATTR_UFID, flow->id.ufid_len, flow->id.ufid); return ovs_nla_put_key(flow->id.unmasked_key, flow->id.unmasked_key, OVS_FLOW_ATTR_KEY, false, skb); } /* Called with ovs_mutex or RCU read lock. */ int ovs_nla_put_masked_key(const struct sw_flow *flow, struct sk_buff *skb) { return ovs_nla_put_key(&flow->key, &flow->key, OVS_FLOW_ATTR_KEY, false, skb); } /* Called with ovs_mutex or RCU read lock. */ int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb) { return ovs_nla_put_key(&flow->key, &flow->mask->key, OVS_FLOW_ATTR_MASK, true, skb); } static struct sw_flow_actions *nla_alloc_flow_actions(int size) { struct sw_flow_actions *sfa; sfa = kmalloc(kmalloc_size_roundup(sizeof(*sfa) + size), GFP_KERNEL); if (!sfa) return ERR_PTR(-ENOMEM); sfa->actions_len = 0; return sfa; } static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len); static void ovs_nla_free_check_pkt_len_action(const struct nlattr *action) { const struct nlattr *a; int rem; nla_for_each_nested(a, action, rem) { switch (nla_type(a)) { case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL: case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER: ovs_nla_free_nested_actions(nla_data(a), nla_len(a)); break; } } } static void ovs_nla_free_clone_action(const struct nlattr *action) { const struct nlattr *a = nla_data(action); int rem = nla_len(action); switch (nla_type(a)) { case OVS_CLONE_ATTR_EXEC: /* The real list of actions follows this attribute. */ a = nla_next(a, &rem); ovs_nla_free_nested_actions(a, rem); break; } } static void ovs_nla_free_dec_ttl_action(const struct nlattr *action) { const struct nlattr *a = nla_data(action); switch (nla_type(a)) { case OVS_DEC_TTL_ATTR_ACTION: ovs_nla_free_nested_actions(nla_data(a), nla_len(a)); break; } } static void ovs_nla_free_sample_action(const struct nlattr *action) { const struct nlattr *a = nla_data(action); int rem = nla_len(action); switch (nla_type(a)) { case OVS_SAMPLE_ATTR_ARG: /* The real list of actions follows this attribute. */ a = nla_next(a, &rem); ovs_nla_free_nested_actions(a, rem); break; } } static void ovs_nla_free_set_action(const struct nlattr *a) { const struct nlattr *ovs_key = nla_data(a); struct ovs_tunnel_info *ovs_tun; switch (nla_type(ovs_key)) { case OVS_KEY_ATTR_TUNNEL_INFO: ovs_tun = nla_data(ovs_key); dst_release((struct dst_entry *)ovs_tun->tun_dst); break; } } static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len) { const struct nlattr *a; int rem; /* Whenever new actions are added, the need to update this * function should be considered. */ BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 25); if (!actions) return; nla_for_each_attr(a, actions, len, rem) { switch (nla_type(a)) { case OVS_ACTION_ATTR_CHECK_PKT_LEN: ovs_nla_free_check_pkt_len_action(a); break; case OVS_ACTION_ATTR_CLONE: ovs_nla_free_clone_action(a); break; case OVS_ACTION_ATTR_CT: ovs_ct_free_action(a); break; case OVS_ACTION_ATTR_DEC_TTL: ovs_nla_free_dec_ttl_action(a); break; case OVS_ACTION_ATTR_SAMPLE: ovs_nla_free_sample_action(a); break; case OVS_ACTION_ATTR_SET: ovs_nla_free_set_action(a); break; } } } void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts) { if (!sf_acts) return; ovs_nla_free_nested_actions(sf_acts->actions, sf_acts->actions_len); kfree(sf_acts); } static void __ovs_nla_free_flow_actions(struct rcu_head *head) { ovs_nla_free_flow_actions(container_of(head, struct sw_flow_actions, rcu)); } /* Schedules 'sf_acts' to be freed after the next RCU grace period. * The caller must hold rcu_read_lock for this to be sensible. */ void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *sf_acts) { call_rcu(&sf_acts->rcu, __ovs_nla_free_flow_actions); } static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa, int attr_len, bool log) { struct sw_flow_actions *acts; int new_acts_size; size_t req_size = NLA_ALIGN(attr_len); int next_offset = offsetof(struct sw_flow_actions, actions) + (*sfa)->actions_len; if (req_size <= (ksize(*sfa) - next_offset)) goto out; new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2); acts = nla_alloc_flow_actions(new_acts_size); if (IS_ERR(acts)) return ERR_CAST(acts); memcpy(acts->actions, (*sfa)->actions, (*sfa)->actions_len); acts->actions_len = (*sfa)->actions_len; acts->orig_len = (*sfa)->orig_len; kfree(*sfa); *sfa = acts; out: (*sfa)->actions_len += req_size; return (struct nlattr *) ((unsigned char *)(*sfa) + next_offset); } static struct nlattr *__add_action(struct sw_flow_actions **sfa, int attrtype, void *data, int len, bool log) { struct nlattr *a; a = reserve_sfa_size(sfa, nla_attr_size(len), log); if (IS_ERR(a)) return a; a->nla_type = attrtype; a->nla_len = nla_attr_size(len); if (data) memcpy(nla_data(a), data, len); memset((unsigned char *) a + a->nla_len, 0, nla_padlen(len)); return a; } int ovs_nla_add_action(struct sw_flow_actions **sfa, int attrtype, void *data, int len, bool log) { struct nlattr *a; a = __add_action(sfa, attrtype, data, len, log); return PTR_ERR_OR_ZERO(a); } static inline int add_nested_action_start(struct sw_flow_actions **sfa, int attrtype, bool log) { int used = (*sfa)->actions_len; int err; err = ovs_nla_add_action(sfa, attrtype, NULL, 0, log); if (err) return err; return used; } static inline void add_nested_action_end(struct sw_flow_actions *sfa, int st_offset) { struct nlattr *a = (struct nlattr *) ((unsigned char *)sfa->actions + st_offset); a->nla_len = sfa->actions_len - st_offset; } static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, u32 mpls_label_count, bool log, u32 depth); static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, u32 mpls_label_count, bool log, bool last, u32 depth) { const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1]; const struct nlattr *probability, *actions; const struct nlattr *a; int rem, start, err; struct sample_arg arg; memset(attrs, 0, sizeof(attrs)); nla_for_each_nested(a, attr, rem) { int type = nla_type(a); if (!type || type > OVS_SAMPLE_ATTR_MAX || attrs[type]) return -EINVAL; attrs[type] = a; } if (rem) return -EINVAL; probability = attrs[OVS_SAMPLE_ATTR_PROBABILITY]; if (!probability || nla_len(probability) != sizeof(u32)) return -EINVAL; actions = attrs[OVS_SAMPLE_ATTR_ACTIONS]; if (!actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN)) return -EINVAL; /* validation done, copy sample action. */ start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE, log); if (start < 0) return start; /* When both skb and flow may be changed, put the sample * into a deferred fifo. On the other hand, if only skb * may be modified, the actions can be executed in place. * * Do this analysis at the flow installation time. * Set 'clone_action->exec' to true if the actions can be * executed without being deferred. * * If the sample is the last action, it can always be excuted * rather than deferred. */ arg.exec = last || !actions_may_change_flow(actions); arg.probability = nla_get_u32(probability); err = ovs_nla_add_action(sfa, OVS_SAMPLE_ATTR_ARG, &arg, sizeof(arg), log); if (err) return err; err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, vlan_tci, mpls_label_count, log, depth + 1); if (err) return err; add_nested_action_end(*sfa, start); return 0; } static int validate_and_copy_dec_ttl(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, u32 mpls_label_count, bool log, u32 depth) { const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1]; int start, action_start, err, rem; const struct nlattr *a, *actions; memset(attrs, 0, sizeof(attrs)); nla_for_each_nested(a, attr, rem) { int type = nla_type(a); /* Ignore unknown attributes to be future proof. */ if (type > OVS_DEC_TTL_ATTR_MAX) continue; if (!type || attrs[type]) { OVS_NLERR(log, "Duplicate or invalid key (type %d).", type); return -EINVAL; } attrs[type] = a; } if (rem) { OVS_NLERR(log, "Message has %d unknown bytes.", rem); return -EINVAL; } actions = attrs[OVS_DEC_TTL_ATTR_ACTION]; if (!actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN)) { OVS_NLERR(log, "Missing valid actions attribute."); return -EINVAL; } start = add_nested_action_start(sfa, OVS_ACTION_ATTR_DEC_TTL, log); if (start < 0) return start; action_start = add_nested_action_start(sfa, OVS_DEC_TTL_ATTR_ACTION, log); if (action_start < 0) return action_start; err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, vlan_tci, mpls_label_count, log, depth + 1); if (err) return err; add_nested_action_end(*sfa, action_start); add_nested_action_end(*sfa, start); return 0; } static int validate_and_copy_clone(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, u32 mpls_label_count, bool log, bool last, u32 depth) { int start, err; u32 exec; if (nla_len(attr) && nla_len(attr) < NLA_HDRLEN) return -EINVAL; start = add_nested_action_start(sfa, OVS_ACTION_ATTR_CLONE, log); if (start < 0) return start; exec = last || !actions_may_change_flow(attr); err = ovs_nla_add_action(sfa, OVS_CLONE_ATTR_EXEC, &exec, sizeof(exec), log); if (err) return err; err = __ovs_nla_copy_actions(net, attr, key, sfa, eth_type, vlan_tci, mpls_label_count, log, depth + 1); if (err) return err; add_nested_action_end(*sfa, start); return 0; } void ovs_match_init(struct sw_flow_match *match, struct sw_flow_key *key, bool reset_key, struct sw_flow_mask *mask) { memset(match, 0, sizeof(*match)); match->key = key; match->mask = mask; if (reset_key) memset(key, 0, sizeof(*key)); if (mask) { memset(&mask->key, 0, sizeof(mask->key)); mask->range.start = mask->range.end = 0; } } static int validate_geneve_opts(struct sw_flow_key *key) { struct geneve_opt *option; int opts_len = key->tun_opts_len; bool crit_opt = false; option = (struct geneve_opt *)TUN_METADATA_OPTS(key, key->tun_opts_len); while (opts_len > 0) { int len; if (opts_len < sizeof(*option)) return -EINVAL; len = sizeof(*option) + option->length * 4; if (len > opts_len) return -EINVAL; crit_opt |= !!(option->type & GENEVE_CRIT_OPT_TYPE); option = (struct geneve_opt *)((u8 *)option + len); opts_len -= len; } if (crit_opt) __set_bit(IP_TUNNEL_CRIT_OPT_BIT, key->tun_key.tun_flags); return 0; } static int validate_and_copy_set_tun(const struct nlattr *attr, struct sw_flow_actions **sfa, bool log) { IP_TUNNEL_DECLARE_FLAGS(dst_opt_type) = { }; struct sw_flow_match match; struct sw_flow_key key; struct metadata_dst *tun_dst; struct ip_tunnel_info *tun_info; struct ovs_tunnel_info *ovs_tun; struct nlattr *a; int err = 0, start, opts_type; ovs_match_init(&match, &key, true, NULL); opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log); if (opts_type < 0) return opts_type; if (key.tun_opts_len) { switch (opts_type) { case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS: err = validate_geneve_opts(&key); if (err < 0) return err; __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, dst_opt_type); break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, dst_opt_type); break; case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, dst_opt_type); break; } } start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET, log); if (start < 0) return start; tun_dst = metadata_dst_alloc(key.tun_opts_len, METADATA_IP_TUNNEL, GFP_KERNEL); if (!tun_dst) return -ENOMEM; err = dst_cache_init(&tun_dst->u.tun_info.dst_cache, GFP_KERNEL); if (err) { dst_release((struct dst_entry *)tun_dst); return err; } a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL, sizeof(*ovs_tun), log); if (IS_ERR(a)) { dst_release((struct dst_entry *)tun_dst); return PTR_ERR(a); } ovs_tun = nla_data(a); ovs_tun->tun_dst = tun_dst; tun_info = &tun_dst->u.tun_info; tun_info->mode = IP_TUNNEL_INFO_TX; if (key.tun_proto == AF_INET6) tun_info->mode |= IP_TUNNEL_INFO_IPV6; else if (key.tun_proto == AF_INET && key.tun_key.u.ipv4.dst == 0) tun_info->mode |= IP_TUNNEL_INFO_BRIDGE; tun_info->key = key.tun_key; /* We need to store the options in the action itself since * everything else will go away after flow setup. We can append * it to tun_info and then point there. */ ip_tunnel_info_opts_set(tun_info, TUN_METADATA_OPTS(&key, key.tun_opts_len), key.tun_opts_len, dst_opt_type); add_nested_action_end(*sfa, start); return err; } static bool validate_nsh(const struct nlattr *attr, bool is_mask, bool is_push_nsh, bool log) { struct sw_flow_match match; struct sw_flow_key key; int ret = 0; ovs_match_init(&match, &key, true, NULL); ret = nsh_key_put_from_nlattr(attr, &match, is_mask, is_push_nsh, log); return !ret; } /* Return false if there are any non-masked bits set. * Mask follows data immediately, before any netlink padding. */ static bool validate_masked(u8 *data, int len) { u8 *mask = data + len; while (len--) if (*data++ & ~*mask++) return false; return true; } static int validate_set(const struct nlattr *a, const struct sw_flow_key *flow_key, struct sw_flow_actions **sfa, bool *skip_copy, u8 mac_proto, __be16 eth_type, bool masked, bool log) { const struct nlattr *ovs_key = nla_data(a); int key_type = nla_type(ovs_key); size_t key_len; /* There can be only one key in a action */ if (!nla_ok(ovs_key, nla_len(a)) || nla_total_size(nla_len(ovs_key)) != nla_len(a)) return -EINVAL; key_len = nla_len(ovs_key); if (masked) key_len /= 2; if (key_type > OVS_KEY_ATTR_MAX || !check_attr_len(key_len, ovs_key_lens[key_type].len)) return -EINVAL; if (masked && !validate_masked(nla_data(ovs_key), key_len)) return -EINVAL; switch (key_type) { case OVS_KEY_ATTR_PRIORITY: case OVS_KEY_ATTR_SKB_MARK: case OVS_KEY_ATTR_CT_MARK: case OVS_KEY_ATTR_CT_LABELS: break; case OVS_KEY_ATTR_ETHERNET: if (mac_proto != MAC_PROTO_ETHERNET) return -EINVAL; break; case OVS_KEY_ATTR_TUNNEL: { int err; if (masked) return -EINVAL; /* Masked tunnel set not supported. */ *skip_copy = true; err = validate_and_copy_set_tun(a, sfa, log); if (err) return err; break; } case OVS_KEY_ATTR_IPV4: { const struct ovs_key_ipv4 *ipv4_key; if (eth_type != htons(ETH_P_IP)) return -EINVAL; ipv4_key = nla_data(ovs_key); if (masked) { const struct ovs_key_ipv4 *mask = ipv4_key + 1; /* Non-writeable fields. */ if (mask->ipv4_proto || mask->ipv4_frag) return -EINVAL; } else { if (ipv4_key->ipv4_proto != flow_key->ip.proto) return -EINVAL; if (ipv4_key->ipv4_frag != flow_key->ip.frag) return -EINVAL; } break; } case OVS_KEY_ATTR_IPV6: { const struct ovs_key_ipv6 *ipv6_key; if (eth_type != htons(ETH_P_IPV6)) return -EINVAL; ipv6_key = nla_data(ovs_key); if (masked) { const struct ovs_key_ipv6 *mask = ipv6_key + 1; /* Non-writeable fields. */ if (mask->ipv6_proto || mask->ipv6_frag) return -EINVAL; /* Invalid bits in the flow label mask? */ if (ntohl(mask->ipv6_label) & 0xFFF00000) return -EINVAL; } else { if (ipv6_key->ipv6_proto != flow_key->ip.proto) return -EINVAL; if (ipv6_key->ipv6_frag != flow_key->ip.frag) return -EINVAL; } if (ntohl(ipv6_key->ipv6_label) & 0xFFF00000) return -EINVAL; break; } case OVS_KEY_ATTR_TCP: if ((eth_type != htons(ETH_P_IP) && eth_type != htons(ETH_P_IPV6)) || flow_key->ip.proto != IPPROTO_TCP) return -EINVAL; break; case OVS_KEY_ATTR_UDP: if ((eth_type != htons(ETH_P_IP) && eth_type != htons(ETH_P_IPV6)) || flow_key->ip.proto != IPPROTO_UDP) return -EINVAL; break; case OVS_KEY_ATTR_MPLS: if (!eth_p_mpls(eth_type)) return -EINVAL; break; case OVS_KEY_ATTR_SCTP: if ((eth_type != htons(ETH_P_IP) && eth_type != htons(ETH_P_IPV6)) || flow_key->ip.proto != IPPROTO_SCTP) return -EINVAL; break; case OVS_KEY_ATTR_NSH: if (eth_type != htons(ETH_P_NSH)) return -EINVAL; if (!validate_nsh(nla_data(a), masked, false, log)) return -EINVAL; break; default: return -EINVAL; } /* Convert non-masked non-tunnel set actions to masked set actions. */ if (!masked && key_type != OVS_KEY_ATTR_TUNNEL) { int start, len = key_len * 2; struct nlattr *at; *skip_copy = true; start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET_TO_MASKED, log); if (start < 0) return start; at = __add_action(sfa, key_type, NULL, len, log); if (IS_ERR(at)) return PTR_ERR(at); memcpy(nla_data(at), nla_data(ovs_key), key_len); /* Key. */ memset(nla_data(at) + key_len, 0xff, key_len); /* Mask. */ /* Clear non-writeable bits from otherwise writeable fields. */ if (key_type == OVS_KEY_ATTR_IPV6) { struct ovs_key_ipv6 *mask = nla_data(at) + key_len; mask->ipv6_label &= htonl(0x000FFFFF); } add_nested_action_end(*sfa, start); } return 0; } static int validate_userspace(const struct nlattr *attr) { static const struct nla_policy userspace_policy[OVS_USERSPACE_ATTR_MAX + 1] = { [OVS_USERSPACE_ATTR_PID] = {.type = NLA_U32 }, [OVS_USERSPACE_ATTR_USERDATA] = {.type = NLA_UNSPEC }, [OVS_USERSPACE_ATTR_EGRESS_TUN_PORT] = {.type = NLA_U32 }, }; struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1]; int error; error = nla_parse_deprecated_strict(a, OVS_USERSPACE_ATTR_MAX, nla_data(attr), nla_len(attr), userspace_policy, NULL); if (error) return error; if (!a[OVS_USERSPACE_ATTR_PID] || !nla_get_u32(a[OVS_USERSPACE_ATTR_PID])) return -EINVAL; return 0; } static const struct nla_policy cpl_policy[OVS_CHECK_PKT_LEN_ATTR_MAX + 1] = { [OVS_CHECK_PKT_LEN_ATTR_PKT_LEN] = {.type = NLA_U16 }, [OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER] = {.type = NLA_NESTED }, [OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL] = {.type = NLA_NESTED }, }; static int validate_and_copy_check_pkt_len(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, u32 mpls_label_count, bool log, bool last, u32 depth) { const struct nlattr *acts_if_greater, *acts_if_lesser_eq; struct nlattr *a[OVS_CHECK_PKT_LEN_ATTR_MAX + 1]; struct check_pkt_len_arg arg; int nested_acts_start; int start, err; err = nla_parse_deprecated_strict(a, OVS_CHECK_PKT_LEN_ATTR_MAX, nla_data(attr), nla_len(attr), cpl_policy, NULL); if (err) return err; if (!a[OVS_CHECK_PKT_LEN_ATTR_PKT_LEN] || !nla_get_u16(a[OVS_CHECK_PKT_LEN_ATTR_PKT_LEN])) return -EINVAL; acts_if_lesser_eq = a[OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL]; acts_if_greater = a[OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER]; /* Both the nested action should be present. */ if (!acts_if_greater || !acts_if_lesser_eq) return -EINVAL; /* validation done, copy the nested actions. */ start = add_nested_action_start(sfa, OVS_ACTION_ATTR_CHECK_PKT_LEN, log); if (start < 0) return start; arg.pkt_len = nla_get_u16(a[OVS_CHECK_PKT_LEN_ATTR_PKT_LEN]); arg.exec_for_lesser_equal = last || !actions_may_change_flow(acts_if_lesser_eq); arg.exec_for_greater = last || !actions_may_change_flow(acts_if_greater); err = ovs_nla_add_action(sfa, OVS_CHECK_PKT_LEN_ATTR_ARG, &arg, sizeof(arg), log); if (err) return err; nested_acts_start = add_nested_action_start(sfa, OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL, log); if (nested_acts_start < 0) return nested_acts_start; err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa, eth_type, vlan_tci, mpls_label_count, log, depth + 1); if (err) return err; add_nested_action_end(*sfa, nested_acts_start); nested_acts_start = add_nested_action_start(sfa, OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER, log); if (nested_acts_start < 0) return nested_acts_start; err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa, eth_type, vlan_tci, mpls_label_count, log, depth + 1); if (err) return err; add_nested_action_end(*sfa, nested_acts_start); add_nested_action_end(*sfa, start); return 0; } static int validate_psample(const struct nlattr *attr) { static const struct nla_policy policy[OVS_PSAMPLE_ATTR_MAX + 1] = { [OVS_PSAMPLE_ATTR_GROUP] = { .type = NLA_U32 }, [OVS_PSAMPLE_ATTR_COOKIE] = { .type = NLA_BINARY, .len = OVS_PSAMPLE_COOKIE_MAX_SIZE, }, }; struct nlattr *a[OVS_PSAMPLE_ATTR_MAX + 1]; int err; if (!IS_ENABLED(CONFIG_PSAMPLE)) return -EOPNOTSUPP; err = nla_parse_nested(a, OVS_PSAMPLE_ATTR_MAX, attr, policy, NULL); if (err) return err; return a[OVS_PSAMPLE_ATTR_GROUP] ? 0 : -EINVAL; } static int copy_action(const struct nlattr *from, struct sw_flow_actions **sfa, bool log) { int totlen = NLA_ALIGN(from->nla_len); struct nlattr *to; to = reserve_sfa_size(sfa, from->nla_len, log); if (IS_ERR(to)) return PTR_ERR(to); memcpy(to, from, totlen); return 0; } static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, u32 mpls_label_count, bool log, u32 depth) { u8 mac_proto = ovs_key_mac_proto(key); const struct nlattr *a; int rem, err; if (depth > OVS_COPY_ACTIONS_MAX_DEPTH) return -EOVERFLOW; nla_for_each_nested(a, attr, rem) { /* Expected argument lengths, (u32)-1 for variable length. */ static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = { [OVS_ACTION_ATTR_OUTPUT] = sizeof(u32), [OVS_ACTION_ATTR_RECIRC] = sizeof(u32), [OVS_ACTION_ATTR_USERSPACE] = (u32)-1, [OVS_ACTION_ATTR_PUSH_MPLS] = sizeof(struct ovs_action_push_mpls), [OVS_ACTION_ATTR_POP_MPLS] = sizeof(__be16), [OVS_ACTION_ATTR_PUSH_VLAN] = sizeof(struct ovs_action_push_vlan), [OVS_ACTION_ATTR_POP_VLAN] = 0, [OVS_ACTION_ATTR_SET] = (u32)-1, [OVS_ACTION_ATTR_SET_MASKED] = (u32)-1, [OVS_ACTION_ATTR_SAMPLE] = (u32)-1, [OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash), [OVS_ACTION_ATTR_CT] = (u32)-1, [OVS_ACTION_ATTR_CT_CLEAR] = 0, [OVS_ACTION_ATTR_TRUNC] = sizeof(struct ovs_action_trunc), [OVS_ACTION_ATTR_PUSH_ETH] = sizeof(struct ovs_action_push_eth), [OVS_ACTION_ATTR_POP_ETH] = 0, [OVS_ACTION_ATTR_PUSH_NSH] = (u32)-1, [OVS_ACTION_ATTR_POP_NSH] = 0, [OVS_ACTION_ATTR_METER] = sizeof(u32), [OVS_ACTION_ATTR_CLONE] = (u32)-1, [OVS_ACTION_ATTR_CHECK_PKT_LEN] = (u32)-1, [OVS_ACTION_ATTR_ADD_MPLS] = sizeof(struct ovs_action_add_mpls), [OVS_ACTION_ATTR_DEC_TTL] = (u32)-1, [OVS_ACTION_ATTR_DROP] = sizeof(u32), [OVS_ACTION_ATTR_PSAMPLE] = (u32)-1, }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); bool skip_copy; if (type > OVS_ACTION_ATTR_MAX || (action_lens[type] != nla_len(a) && action_lens[type] != (u32)-1)) return -EINVAL; skip_copy = false; switch (type) { case OVS_ACTION_ATTR_UNSPEC: return -EINVAL; case OVS_ACTION_ATTR_USERSPACE: err = validate_userspace(a); if (err) return err; break; case OVS_ACTION_ATTR_OUTPUT: if (nla_get_u32(a) >= DP_MAX_PORTS) return -EINVAL; break; case OVS_ACTION_ATTR_TRUNC: { const struct ovs_action_trunc *trunc = nla_data(a); if (trunc->max_len < ETH_HLEN) return -EINVAL; break; } case OVS_ACTION_ATTR_HASH: { const struct ovs_action_hash *act_hash = nla_data(a); switch (act_hash->hash_alg) { case OVS_HASH_ALG_L4: fallthrough; case OVS_HASH_ALG_SYM_L4: break; default: return -EINVAL; } break; } case OVS_ACTION_ATTR_POP_VLAN: if (mac_proto != MAC_PROTO_ETHERNET) return -EINVAL; vlan_tci = htons(0); break; case OVS_ACTION_ATTR_PUSH_VLAN: if (mac_proto != MAC_PROTO_ETHERNET) return -EINVAL; vlan = nla_data(a); if (!eth_type_vlan(vlan->vlan_tpid)) return -EINVAL; if (!(vlan->vlan_tci & htons(VLAN_CFI_MASK))) return -EINVAL; vlan_tci = vlan->vlan_tci; break; case OVS_ACTION_ATTR_RECIRC: break; case OVS_ACTION_ATTR_ADD_MPLS: { const struct ovs_action_add_mpls *mpls = nla_data(a); if (!eth_p_mpls(mpls->mpls_ethertype)) return -EINVAL; if (mpls->tun_flags & OVS_MPLS_L3_TUNNEL_FLAG_MASK) { if (vlan_tci & htons(VLAN_CFI_MASK) || (eth_type != htons(ETH_P_IP) && eth_type != htons(ETH_P_IPV6) && eth_type != htons(ETH_P_ARP) && eth_type != htons(ETH_P_RARP) && !eth_p_mpls(eth_type))) return -EINVAL; mpls_label_count++; } else { if (mac_proto == MAC_PROTO_ETHERNET) { mpls_label_count = 1; mac_proto = MAC_PROTO_NONE; } else { mpls_label_count++; } } eth_type = mpls->mpls_ethertype; break; } case OVS_ACTION_ATTR_PUSH_MPLS: { const struct ovs_action_push_mpls *mpls = nla_data(a); if (!eth_p_mpls(mpls->mpls_ethertype)) return -EINVAL; /* Prohibit push MPLS other than to a white list * for packets that have a known tag order. */ if (vlan_tci & htons(VLAN_CFI_MASK) || (eth_type != htons(ETH_P_IP) && eth_type != htons(ETH_P_IPV6) && eth_type != htons(ETH_P_ARP) && eth_type != htons(ETH_P_RARP) && !eth_p_mpls(eth_type))) return -EINVAL; eth_type = mpls->mpls_ethertype; mpls_label_count++; break; } case OVS_ACTION_ATTR_POP_MPLS: { __be16 proto; if (vlan_tci & htons(VLAN_CFI_MASK) || !eth_p_mpls(eth_type)) return -EINVAL; /* Disallow subsequent L2.5+ set actions and mpls_pop * actions once the last MPLS label in the packet is * popped as there is no check here to ensure that * the new eth type is valid and thus set actions could * write off the end of the packet or otherwise corrupt * it. * * Support for these actions is planned using packet * recirculation. */ proto = nla_get_be16(a); if (proto == htons(ETH_P_TEB) && mac_proto != MAC_PROTO_NONE) return -EINVAL; mpls_label_count--; if (!eth_p_mpls(proto) || !mpls_label_count) eth_type = htons(0); else eth_type = proto; break; } case OVS_ACTION_ATTR_SET: err = validate_set(a, key, sfa, &skip_copy, mac_proto, eth_type, false, log); if (err) return err; break; case OVS_ACTION_ATTR_SET_MASKED: err = validate_set(a, key, sfa, &skip_copy, mac_proto, eth_type, true, log); if (err) return err; break; case OVS_ACTION_ATTR_SAMPLE: { bool last = nla_is_last(a, rem); err = validate_and_copy_sample(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, log, last, depth); if (err) return err; skip_copy = true; break; } case OVS_ACTION_ATTR_CT: err = ovs_ct_copy_action(net, a, key, sfa, log); if (err) return err; skip_copy = true; break; case OVS_ACTION_ATTR_CT_CLEAR: break; case OVS_ACTION_ATTR_PUSH_ETH: /* Disallow pushing an Ethernet header if one * is already present */ if (mac_proto != MAC_PROTO_NONE) return -EINVAL; mac_proto = MAC_PROTO_ETHERNET; break; case OVS_ACTION_ATTR_POP_ETH: if (mac_proto != MAC_PROTO_ETHERNET) return -EINVAL; if (vlan_tci & htons(VLAN_CFI_MASK)) return -EINVAL; mac_proto = MAC_PROTO_NONE; break; case OVS_ACTION_ATTR_PUSH_NSH: if (mac_proto != MAC_PROTO_ETHERNET) { u8 next_proto; next_proto = tun_p_from_eth_p(eth_type); if (!next_proto) return -EINVAL; } mac_proto = MAC_PROTO_NONE; if (!validate_nsh(nla_data(a), false, true, true)) return -EINVAL; break; case OVS_ACTION_ATTR_POP_NSH: { __be16 inner_proto; if (eth_type != htons(ETH_P_NSH)) return -EINVAL; inner_proto = tun_p_to_eth_p(key->nsh.base.np); if (!inner_proto) return -EINVAL; if (key->nsh.base.np == TUN_P_ETHERNET) mac_proto = MAC_PROTO_ETHERNET; else mac_proto = MAC_PROTO_NONE; break; } case OVS_ACTION_ATTR_METER: /* Non-existent meters are simply ignored. */ break; case OVS_ACTION_ATTR_CLONE: { bool last = nla_is_last(a, rem); err = validate_and_copy_clone(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, log, last, depth); if (err) return err; skip_copy = true; break; } case OVS_ACTION_ATTR_CHECK_PKT_LEN: { bool last = nla_is_last(a, rem); err = validate_and_copy_check_pkt_len(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, log, last, depth); if (err) return err; skip_copy = true; break; } case OVS_ACTION_ATTR_DEC_TTL: err = validate_and_copy_dec_ttl(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, log, depth); if (err) return err; skip_copy = true; break; case OVS_ACTION_ATTR_DROP: if (!nla_is_last(a, rem)) return -EINVAL; break; case OVS_ACTION_ATTR_PSAMPLE: err = validate_psample(a); if (err) return err; break; default: OVS_NLERR(log, "Unknown Action type %d", type); return -EINVAL; } if (!skip_copy) { err = copy_action(a, sfa, log); if (err) return err; } } if (rem > 0) return -EINVAL; return 0; } /* 'key' must be the masked key. */ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, bool log) { int err; u32 mpls_label_count = 0; *sfa = nla_alloc_flow_actions(nla_len(attr)); if (IS_ERR(*sfa)) return PTR_ERR(*sfa); if (eth_p_mpls(key->eth.type)) mpls_label_count = hweight_long(key->mpls.num_labels_mask); (*sfa)->orig_len = nla_len(attr); err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type, key->eth.vlan.tci, mpls_label_count, log, 0); if (err) ovs_nla_free_flow_actions(*sfa); return err; } static int sample_action_to_attr(const struct nlattr *attr, struct sk_buff *skb) { struct nlattr *start, *ac_start = NULL, *sample_arg; int err = 0, rem = nla_len(attr); const struct sample_arg *arg; struct nlattr *actions; start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_SAMPLE); if (!start) return -EMSGSIZE; sample_arg = nla_data(attr); arg = nla_data(sample_arg); actions = nla_next(sample_arg, &rem); if (nla_put_u32(skb, OVS_SAMPLE_ATTR_PROBABILITY, arg->probability)) { err = -EMSGSIZE; goto out; } ac_start = nla_nest_start_noflag(skb, OVS_SAMPLE_ATTR_ACTIONS); if (!ac_start) { err = -EMSGSIZE; goto out; } err = ovs_nla_put_actions(actions, rem, skb); out: if (err) { nla_nest_cancel(skb, ac_start); nla_nest_cancel(skb, start); } else { nla_nest_end(skb, ac_start); nla_nest_end(skb, start); } return err; } static int clone_action_to_attr(const struct nlattr *attr, struct sk_buff *skb) { struct nlattr *start; int err = 0, rem = nla_len(attr); start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_CLONE); if (!start) return -EMSGSIZE; /* Skipping the OVS_CLONE_ATTR_EXEC that is always the first attribute. */ attr = nla_next(nla_data(attr), &rem); err = ovs_nla_put_actions(attr, rem, skb); if (err) nla_nest_cancel(skb, start); else nla_nest_end(skb, start); return err; } static int check_pkt_len_action_to_attr(const struct nlattr *attr, struct sk_buff *skb) { struct nlattr *start, *ac_start = NULL; const struct check_pkt_len_arg *arg; const struct nlattr *a, *cpl_arg; int err = 0, rem = nla_len(attr); start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_CHECK_PKT_LEN); if (!start) return -EMSGSIZE; /* The first nested attribute in 'attr' is always * 'OVS_CHECK_PKT_LEN_ATTR_ARG'. */ cpl_arg = nla_data(attr); arg = nla_data(cpl_arg); if (nla_put_u16(skb, OVS_CHECK_PKT_LEN_ATTR_PKT_LEN, arg->pkt_len)) { err = -EMSGSIZE; goto out; } /* Second nested attribute in 'attr' is always * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'. */ a = nla_next(cpl_arg, &rem); ac_start = nla_nest_start_noflag(skb, OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL); if (!ac_start) { err = -EMSGSIZE; goto out; } err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb); if (err) { nla_nest_cancel(skb, ac_start); goto out; } else { nla_nest_end(skb, ac_start); } /* Third nested attribute in 'attr' is always * OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER. */ a = nla_next(a, &rem); ac_start = nla_nest_start_noflag(skb, OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER); if (!ac_start) { err = -EMSGSIZE; goto out; } err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb); if (err) { nla_nest_cancel(skb, ac_start); goto out; } else { nla_nest_end(skb, ac_start); } nla_nest_end(skb, start); return 0; out: nla_nest_cancel(skb, start); return err; } static int dec_ttl_action_to_attr(const struct nlattr *attr, struct sk_buff *skb) { struct nlattr *start, *action_start; const struct nlattr *a; int err = 0, rem; start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_DEC_TTL); if (!start) return -EMSGSIZE; nla_for_each_attr(a, nla_data(attr), nla_len(attr), rem) { switch (nla_type(a)) { case OVS_DEC_TTL_ATTR_ACTION: action_start = nla_nest_start_noflag(skb, OVS_DEC_TTL_ATTR_ACTION); if (!action_start) { err = -EMSGSIZE; goto out; } err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb); if (err) goto out; nla_nest_end(skb, action_start); break; default: /* Ignore all other option to be future compatible */ break; } } nla_nest_end(skb, start); return 0; out: nla_nest_cancel(skb, start); return err; } static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) { const struct nlattr *ovs_key = nla_data(a); int key_type = nla_type(ovs_key); struct nlattr *start; int err; switch (key_type) { case OVS_KEY_ATTR_TUNNEL_INFO: { struct ovs_tunnel_info *ovs_tun = nla_data(ovs_key); struct ip_tunnel_info *tun_info = &ovs_tun->tun_dst->u.tun_info; start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_SET); if (!start) return -EMSGSIZE; err = ip_tun_to_nlattr(skb, &tun_info->key, ip_tunnel_info_opts(tun_info), tun_info->options_len, ip_tunnel_info_af(tun_info), tun_info->mode); if (err) return err; nla_nest_end(skb, start); break; } default: if (nla_put(skb, OVS_ACTION_ATTR_SET, nla_len(a), ovs_key)) return -EMSGSIZE; break; } return 0; } static int masked_set_action_to_set_action_attr(const struct nlattr *a, struct sk_buff *skb) { const struct nlattr *ovs_key = nla_data(a); struct nlattr *nla; size_t key_len = nla_len(ovs_key) / 2; /* Revert the conversion we did from a non-masked set action to * masked set action. */ nla = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_SET); if (!nla) return -EMSGSIZE; if (nla_put(skb, nla_type(ovs_key), key_len, nla_data(ovs_key))) return -EMSGSIZE; nla_nest_end(skb, nla); return 0; } int ovs_nla_put_actions(const struct nlattr *attr, int len, struct sk_buff *skb) { const struct nlattr *a; int rem, err; nla_for_each_attr(a, attr, len, rem) { int type = nla_type(a); switch (type) { case OVS_ACTION_ATTR_SET: err = set_action_to_attr(a, skb); if (err) return err; break; case OVS_ACTION_ATTR_SET_TO_MASKED: err = masked_set_action_to_set_action_attr(a, skb); if (err) return err; break; case OVS_ACTION_ATTR_SAMPLE: err = sample_action_to_attr(a, skb); if (err) return err; break; case OVS_ACTION_ATTR_CT: err = ovs_ct_action_to_attr(nla_data(a), skb); if (err) return err; break; case OVS_ACTION_ATTR_CLONE: err = clone_action_to_attr(a, skb); if (err) return err; break; case OVS_ACTION_ATTR_CHECK_PKT_LEN: err = check_pkt_len_action_to_attr(a, skb); if (err) return err; break; case OVS_ACTION_ATTR_DEC_TTL: err = dec_ttl_action_to_attr(a, skb); if (err) return err; break; default: if (nla_put(skb, type, nla_len(a), nla_data(a))) return -EMSGSIZE; break; } } return 0; } |
| 107 107 107 171 171 125 171 25 25 21 24 25 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 | /* * linux/fs/hfs/string.c * * Copyright (C) 1995-1997 Paul H. Hargrove * (C) 2003 Ardis Technologies <roman@ardistech.com> * This file may be distributed under the terms of the GNU General Public License. * * This file contains the string comparison function for the * Macintosh character set. * * The code in this file is derived from code which is copyright * 1986, 1989, 1990 by Abacus Research and Development, Inc. (ARDI) * It is used here by the permission of ARDI's president Cliff Matthews. */ #include "hfs_fs.h" #include <linux/dcache.h> /*================ File-local variables ================*/ /* * unsigned char caseorder[] * * Defines the lexical ordering of characters on the Macintosh * * Composition of the 'casefold' and 'order' tables from ARDI's code * with the entry for 0x20 changed to match that for 0xCA to remove * special case for those two characters. */ static unsigned char caseorder[256] = { 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,0x08,0x09,0x0A,0x0B,0x0C,0x0D,0x0E,0x0F, 0x10,0x11,0x12,0x13,0x14,0x15,0x16,0x17,0x18,0x19,0x1A,0x1B,0x1C,0x1D,0x1E,0x1F, 0x20,0x22,0x23,0x28,0x29,0x2A,0x2B,0x2C,0x2F,0x30,0x31,0x32,0x33,0x34,0x35,0x36, 0x37,0x38,0x39,0x3A,0x3B,0x3C,0x3D,0x3E,0x3F,0x40,0x41,0x42,0x43,0x44,0x45,0x46, 0x47,0x48,0x57,0x59,0x5D,0x5F,0x66,0x68,0x6A,0x6C,0x72,0x74,0x76,0x78,0x7A,0x7E, 0x8C,0x8E,0x90,0x92,0x95,0x97,0x9E,0xA0,0xA2,0xA4,0xA7,0xA9,0xAA,0xAB,0xAC,0xAD, 0x4E,0x48,0x57,0x59,0x5D,0x5F,0x66,0x68,0x6A,0x6C,0x72,0x74,0x76,0x78,0x7A,0x7E, 0x8C,0x8E,0x90,0x92,0x95,0x97,0x9E,0xA0,0xA2,0xA4,0xA7,0xAF,0xB0,0xB1,0xB2,0xB3, 0x4A,0x4C,0x5A,0x60,0x7B,0x7F,0x98,0x4F,0x49,0x51,0x4A,0x4B,0x4C,0x5A,0x60,0x63, 0x64,0x65,0x6E,0x6F,0x70,0x71,0x7B,0x84,0x85,0x86,0x7F,0x80,0x9A,0x9B,0x9C,0x98, 0xB4,0xB5,0xB6,0xB7,0xB8,0xB9,0xBA,0x94,0xBB,0xBC,0xBD,0xBE,0xBF,0xC0,0x4D,0x81, 0xC1,0xC2,0xC3,0xC4,0xC5,0xC6,0xC7,0xC8,0xC9,0xCA,0xCB,0x55,0x8A,0xCC,0x4D,0x81, 0xCD,0xCE,0xCF,0xD0,0xD1,0xD2,0xD3,0x26,0x27,0xD4,0x20,0x49,0x4B,0x80,0x82,0x82, 0xD5,0xD6,0x24,0x25,0x2D,0x2E,0xD7,0xD8,0xA6,0xD9,0xDA,0xDB,0xDC,0xDD,0xDE,0xDF, 0xE0,0xE1,0xE2,0xE3,0xE4,0xE5,0xE6,0xE7,0xE8,0xE9,0xEA,0xEB,0xEC,0xED,0xEE,0xEF, 0xF0,0xF1,0xF2,0xF3,0xF4,0xF5,0xF6,0xF7,0xF8,0xF9,0xFA,0xFB,0xFC,0xFD,0xFE,0xFF }; /*================ Global functions ================*/ /* * Hash a string to an integer in a case-independent way */ int hfs_hash_dentry(const struct dentry *dentry, struct qstr *this) { const unsigned char *name = this->name; unsigned int hash, len = this->len; if (len > HFS_NAMELEN) len = HFS_NAMELEN; hash = init_name_hash(dentry); for (; len; len--) hash = partial_name_hash(caseorder[*name++], hash); this->hash = end_name_hash(hash); return 0; } /* * Compare two strings in the HFS filename character ordering * Returns positive, negative, or zero, not just 0 or (+/-)1 * * Equivalent to ARDI's call: * ROMlib_RelString(s1+1, s2+1, true, false, (s1[0]<<16) | s2[0]) */ int hfs_strcmp(const unsigned char *s1, unsigned int len1, const unsigned char *s2, unsigned int len2) { int len, tmp; len = (len1 > len2) ? len2 : len1; while (len--) { tmp = (int)caseorder[*(s1++)] - (int)caseorder[*(s2++)]; if (tmp) return tmp; } return len1 - len2; } /* * Test for equality of two strings in the HFS filename character ordering. * return 1 on failure and 0 on success */ int hfs_compare_dentry(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { const unsigned char *n1, *n2; if (len >= HFS_NAMELEN) { if (name->len < HFS_NAMELEN) return 1; len = HFS_NAMELEN; } else if (len != name->len) return 1; n1 = str; n2 = name->name; while (len--) { if (caseorder[*n1++] != caseorder[*n2++]) return 1; } return 0; } |
| 15 35 35 15 15 15 15 1 1 1 1 1 1 35 35 35 | 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 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "buckets_waiting_for_journal.h" #include <linux/hash.h> #include <linux/random.h> static inline struct bucket_hashed * bucket_hash(struct buckets_waiting_for_journal_table *t, unsigned hash_seed_idx, u64 dev_bucket) { return t->d + hash_64(dev_bucket ^ t->hash_seeds[hash_seed_idx], t->bits); } static void bucket_table_init(struct buckets_waiting_for_journal_table *t, size_t bits) { unsigned i; t->bits = bits; for (i = 0; i < ARRAY_SIZE(t->hash_seeds); i++) get_random_bytes(&t->hash_seeds[i], sizeof(t->hash_seeds[i])); memset(t->d, 0, sizeof(t->d[0]) << t->bits); } u64 bch2_bucket_journal_seq_ready(struct buckets_waiting_for_journal *b, unsigned dev, u64 bucket) { struct buckets_waiting_for_journal_table *t; u64 dev_bucket = (u64) dev << 56 | bucket; u64 ret = 0; mutex_lock(&b->lock); t = b->t; for (unsigned i = 0; i < ARRAY_SIZE(t->hash_seeds); i++) { struct bucket_hashed *h = bucket_hash(t, i, dev_bucket); if (h->dev_bucket == dev_bucket) { ret = h->journal_seq; break; } } mutex_unlock(&b->lock); return ret; } static bool bucket_table_insert(struct buckets_waiting_for_journal_table *t, struct bucket_hashed *new, u64 flushed_seq) { struct bucket_hashed *last_evicted = NULL; unsigned tries, i; for (tries = 0; tries < 10; tries++) { struct bucket_hashed *old, *victim = NULL; for (i = 0; i < ARRAY_SIZE(t->hash_seeds); i++) { old = bucket_hash(t, i, new->dev_bucket); if (old->dev_bucket == new->dev_bucket || old->journal_seq <= flushed_seq) { *old = *new; return true; } if (last_evicted != old) victim = old; } /* hashed to same slot 3 times: */ if (!victim) break; /* Failed to find an empty slot: */ swap(*new, *victim); last_evicted = victim; } return false; } int bch2_set_bucket_needs_journal_commit(struct buckets_waiting_for_journal *b, u64 flushed_seq, unsigned dev, u64 bucket, u64 journal_seq) { struct buckets_waiting_for_journal_table *t, *n; struct bucket_hashed tmp, new = { .dev_bucket = (u64) dev << 56 | bucket, .journal_seq = journal_seq, }; size_t i, size, new_bits, nr_elements = 1, nr_rehashes = 0, nr_rehashes_this_size = 0; int ret = 0; mutex_lock(&b->lock); if (likely(bucket_table_insert(b->t, &new, flushed_seq))) goto out; t = b->t; size = 1UL << t->bits; for (i = 0; i < size; i++) nr_elements += t->d[i].journal_seq > flushed_seq; new_bits = ilog2(roundup_pow_of_two(nr_elements * 3)); realloc: n = kvmalloc(sizeof(*n) + (sizeof(n->d[0]) << new_bits), GFP_KERNEL); if (!n) { struct bch_fs *c = container_of(b, struct bch_fs, buckets_waiting_for_journal); ret = bch_err_throw(c, ENOMEM_buckets_waiting_for_journal_set); goto out; } retry_rehash: if (nr_rehashes_this_size == 3) { new_bits++; nr_rehashes_this_size = 0; kvfree(n); goto realloc; } nr_rehashes++; nr_rehashes_this_size++; bucket_table_init(n, new_bits); tmp = new; BUG_ON(!bucket_table_insert(n, &tmp, flushed_seq)); for (i = 0; i < 1UL << t->bits; i++) { if (t->d[i].journal_seq <= flushed_seq) continue; tmp = t->d[i]; if (!bucket_table_insert(n, &tmp, flushed_seq)) goto retry_rehash; } b->t = n; kvfree(t); pr_debug("took %zu rehashes, table at %zu/%lu elements", nr_rehashes, nr_elements, 1UL << b->t->bits); out: mutex_unlock(&b->lock); return ret; } void bch2_fs_buckets_waiting_for_journal_exit(struct bch_fs *c) { struct buckets_waiting_for_journal *b = &c->buckets_waiting_for_journal; kvfree(b->t); } #define INITIAL_TABLE_BITS 3 int bch2_fs_buckets_waiting_for_journal_init(struct bch_fs *c) { struct buckets_waiting_for_journal *b = &c->buckets_waiting_for_journal; mutex_init(&b->lock); b->t = kvmalloc(sizeof(*b->t) + (sizeof(b->t->d[0]) << INITIAL_TABLE_BITS), GFP_KERNEL); if (!b->t) return -BCH_ERR_ENOMEM_buckets_waiting_for_journal_init; bucket_table_init(b->t, INITIAL_TABLE_BITS); return 0; } |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * (C) 2001 Clemson University and The University of Chicago * * See COPYING in top-level directory. */ #include "protocol.h" #include "orangefs-kernel.h" /* tags assigned to kernel upcall operations */ static __u64 next_tag_value; static DEFINE_SPINLOCK(next_tag_value_lock); /* the orangefs memory caches */ /* a cache for orangefs upcall/downcall operations */ static struct kmem_cache *op_cache; int op_cache_initialize(void) { op_cache = kmem_cache_create("orangefs_op_cache", sizeof(struct orangefs_kernel_op_s), 0, 0, NULL); if (!op_cache) { gossip_err("Cannot create orangefs_op_cache\n"); return -ENOMEM; } /* initialize our atomic tag counter */ spin_lock(&next_tag_value_lock); next_tag_value = 100; spin_unlock(&next_tag_value_lock); return 0; } int op_cache_finalize(void) { kmem_cache_destroy(op_cache); return 0; } char *get_opname_string(struct orangefs_kernel_op_s *new_op) { if (new_op) { __s32 type = new_op->upcall.type; if (type == ORANGEFS_VFS_OP_FILE_IO) return "OP_FILE_IO"; else if (type == ORANGEFS_VFS_OP_LOOKUP) return "OP_LOOKUP"; else if (type == ORANGEFS_VFS_OP_CREATE) return "OP_CREATE"; else if (type == ORANGEFS_VFS_OP_GETATTR) return "OP_GETATTR"; else if (type == ORANGEFS_VFS_OP_REMOVE) return "OP_REMOVE"; else if (type == ORANGEFS_VFS_OP_MKDIR) return "OP_MKDIR"; else if (type == ORANGEFS_VFS_OP_READDIR) return "OP_READDIR"; else if (type == ORANGEFS_VFS_OP_READDIRPLUS) return "OP_READDIRPLUS"; else if (type == ORANGEFS_VFS_OP_SETATTR) return "OP_SETATTR"; else if (type == ORANGEFS_VFS_OP_SYMLINK) return "OP_SYMLINK"; else if (type == ORANGEFS_VFS_OP_RENAME) return "OP_RENAME"; else if (type == ORANGEFS_VFS_OP_STATFS) return "OP_STATFS"; else if (type == ORANGEFS_VFS_OP_TRUNCATE) return "OP_TRUNCATE"; else if (type == ORANGEFS_VFS_OP_RA_FLUSH) return "OP_RA_FLUSH"; else if (type == ORANGEFS_VFS_OP_FS_MOUNT) return "OP_FS_MOUNT"; else if (type == ORANGEFS_VFS_OP_FS_UMOUNT) return "OP_FS_UMOUNT"; else if (type == ORANGEFS_VFS_OP_GETXATTR) return "OP_GETXATTR"; else if (type == ORANGEFS_VFS_OP_SETXATTR) return "OP_SETXATTR"; else if (type == ORANGEFS_VFS_OP_LISTXATTR) return "OP_LISTXATTR"; else if (type == ORANGEFS_VFS_OP_REMOVEXATTR) return "OP_REMOVEXATTR"; else if (type == ORANGEFS_VFS_OP_PARAM) return "OP_PARAM"; else if (type == ORANGEFS_VFS_OP_PERF_COUNT) return "OP_PERF_COUNT"; else if (type == ORANGEFS_VFS_OP_CANCEL) return "OP_CANCEL"; else if (type == ORANGEFS_VFS_OP_FSYNC) return "OP_FSYNC"; else if (type == ORANGEFS_VFS_OP_FSKEY) return "OP_FSKEY"; else if (type == ORANGEFS_VFS_OP_FEATURES) return "OP_FEATURES"; } return "OP_UNKNOWN?"; } void orangefs_new_tag(struct orangefs_kernel_op_s *op) { spin_lock(&next_tag_value_lock); op->tag = next_tag_value++; if (next_tag_value == 0) next_tag_value = 100; spin_unlock(&next_tag_value_lock); } struct orangefs_kernel_op_s *op_alloc(__s32 type) { struct orangefs_kernel_op_s *new_op = NULL; new_op = kmem_cache_zalloc(op_cache, GFP_KERNEL); if (new_op) { INIT_LIST_HEAD(&new_op->list); spin_lock_init(&new_op->lock); init_completion(&new_op->waitq); new_op->upcall.type = ORANGEFS_VFS_OP_INVALID; new_op->downcall.type = ORANGEFS_VFS_OP_INVALID; new_op->downcall.status = -1; new_op->op_state = OP_VFS_STATE_UNKNOWN; /* initialize the op specific tag and upcall credentials */ orangefs_new_tag(new_op); new_op->upcall.type = type; new_op->attempts = 0; gossip_debug(GOSSIP_CACHE_DEBUG, "Alloced OP (%p: %llu %s)\n", new_op, llu(new_op->tag), get_opname_string(new_op)); new_op->upcall.uid = from_kuid(&init_user_ns, current_fsuid()); new_op->upcall.gid = from_kgid(&init_user_ns, current_fsgid()); } else { gossip_err("op_alloc: kmem_cache_zalloc failed!\n"); } return new_op; } void op_release(struct orangefs_kernel_op_s *orangefs_op) { if (orangefs_op) { gossip_debug(GOSSIP_CACHE_DEBUG, "Releasing OP (%p: %llu)\n", orangefs_op, llu(orangefs_op->tag)); kmem_cache_free(op_cache, orangefs_op); } else { gossip_err("NULL pointer in op_release\n"); } } |
| 70 94 106 95 110 11 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * vivid-core.h - core datastructures * * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved. */ #ifndef _VIVID_CORE_H_ #define _VIVID_CORE_H_ #include <linux/fb.h> #include <linux/workqueue.h> #include <media/cec.h> #include <media/videobuf2-v4l2.h> #include <media/v4l2-device.h> #include <media/v4l2-dev.h> #include <media/v4l2-ctrls.h> #include <media/tpg/v4l2-tpg.h> #include "vivid-rds-gen.h" #include "vivid-vbi-gen.h" #define dprintk(dev, level, fmt, arg...) \ v4l2_dbg(level, vivid_debug, &dev->v4l2_dev, fmt, ## arg) /* The maximum number of inputs */ #define MAX_INPUTS 16 /* The maximum number of outputs */ #define MAX_OUTPUTS 16 /* The maximum number of video capture buffers */ #define MAX_VID_CAP_BUFFERS 64 /* The maximum up or down scaling factor is 4 */ #define MAX_ZOOM 4 /* The maximum image width/height are set to 4K DMT */ #define MAX_WIDTH 4096 #define MAX_HEIGHT 2160 /* The minimum image width/height */ #define MIN_WIDTH 16 #define MIN_HEIGHT MIN_WIDTH /* Pixel Array control divider */ #define PIXEL_ARRAY_DIV MIN_WIDTH /* The data_offset of plane 0 for the multiplanar formats */ #define PLANE0_DATA_OFFSET 128 /* The supported TV frequency range in MHz */ #define MIN_TV_FREQ (44U * 16U) #define MAX_TV_FREQ (958U * 16U) /* The number of samples returned in every SDR buffer */ #define SDR_CAP_SAMPLES_PER_BUF 0x4000 /* used by the threads to know when to resync internal counters */ #define JIFFIES_PER_DAY (3600U * 24U * HZ) #define JIFFIES_RESYNC (JIFFIES_PER_DAY * (0xf0000000U / JIFFIES_PER_DAY)) /* * Maximum number of HDMI inputs allowed by vivid, due to limitations * of the Physical Address in the EDID and used by CEC we stop at 15 * inputs and outputs. */ #define MAX_HDMI_INPUTS 15 #define MAX_HDMI_OUTPUTS 15 /* Maximum number of S-Video inputs allowed by vivid */ #define MAX_SVID_INPUTS 16 /* The maximum number of items in a menu control */ #define MAX_MENU_ITEMS BITS_PER_LONG_LONG /* Number of fixed menu items in the 'Connected To' menu controls */ #define FIXED_MENU_ITEMS 2 /* The maximum number of vivid devices */ #define VIVID_MAX_DEVS CONFIG_VIDEO_VIVID_MAX_DEVS extern const struct v4l2_rect vivid_min_rect; extern const struct v4l2_rect vivid_max_rect; extern unsigned vivid_debug; /* * NULL-terminated string array for the HDMI 'Connected To' menu controls * with the list of possible HDMI outputs. * * The first two items are fixed ("TPG" and "None"). */ extern char *vivid_ctrl_hdmi_to_output_strings[1 + MAX_MENU_ITEMS]; /* Menu control skip mask of all HDMI outputs that are in use */ extern u64 hdmi_to_output_menu_skip_mask; /* * Bitmask of which vivid instances need to update any connected * HDMI outputs. */ extern u64 hdmi_input_update_outputs_mask; /* * Spinlock for access to hdmi_to_output_menu_skip_mask and * hdmi_input_update_outputs_mask. */ extern spinlock_t hdmi_output_skip_mask_lock; /* * Workqueue that updates the menu controls whenever the HDMI menu skip mask * changes. */ extern struct workqueue_struct *update_hdmi_ctrls_workqueue; /* * The HDMI menu control value (index in the menu list) maps to an HDMI * output that is part of the given vivid_dev instance and has the given * output index (as returned by VIDIOC_G_OUTPUT). * * NULL/0 if not available. */ extern struct vivid_dev *vivid_ctrl_hdmi_to_output_instance[MAX_MENU_ITEMS]; extern unsigned int vivid_ctrl_hdmi_to_output_index[MAX_MENU_ITEMS]; /* * NULL-terminated string array for the S-Video 'Connected To' menu controls * with the list of possible S-Video outputs. * * The first two items are fixed ("TPG" and "None"). */ extern char *vivid_ctrl_svid_to_output_strings[1 + MAX_MENU_ITEMS]; /* Menu control skip mask of all S-Video outputs that are in use */ extern u64 svid_to_output_menu_skip_mask; /* Spinlock for access to svid_to_output_menu_skip_mask */ extern spinlock_t svid_output_skip_mask_lock; /* * Workqueue that updates the menu controls whenever the S-Video menu skip mask * changes. */ extern struct workqueue_struct *update_svid_ctrls_workqueue; /* * The S-Video menu control value (index in the menu list) maps to an S-Video * output that is part of the given vivid_dev instance and has the given * output index (as returned by VIDIOC_G_OUTPUT). * * NULL/0 if not available. */ extern struct vivid_dev *vivid_ctrl_svid_to_output_instance[MAX_MENU_ITEMS]; extern unsigned int vivid_ctrl_svid_to_output_index[MAX_MENU_ITEMS]; extern struct vivid_dev *vivid_devs[VIVID_MAX_DEVS]; extern unsigned int n_devs; struct vivid_fmt { u32 fourcc; /* v4l2 format id */ enum tgp_color_enc color_enc; bool can_do_overlay; u8 vdownsampling[TPG_MAX_PLANES]; u32 alpha_mask; u8 planes; u8 buffers; u32 data_offset[TPG_MAX_PLANES]; u32 bit_depth[TPG_MAX_PLANES]; }; extern struct vivid_fmt vivid_formats[]; /* buffer for one video frame */ struct vivid_buffer { /* common v4l buffer stuff -- must be first */ struct vb2_v4l2_buffer vb; struct list_head list; }; enum vivid_input { WEBCAM, TV, SVID, HDMI, }; enum vivid_signal_mode { CURRENT_DV_TIMINGS, CURRENT_STD = CURRENT_DV_TIMINGS, NO_SIGNAL, NO_LOCK, OUT_OF_RANGE, SELECTED_DV_TIMINGS, SELECTED_STD = SELECTED_DV_TIMINGS, CYCLE_DV_TIMINGS, CYCLE_STD = CYCLE_DV_TIMINGS, CUSTOM_DV_TIMINGS, }; enum vivid_colorspace { VIVID_CS_170M, VIVID_CS_709, VIVID_CS_SRGB, VIVID_CS_OPRGB, VIVID_CS_2020, VIVID_CS_DCI_P3, VIVID_CS_240M, VIVID_CS_SYS_M, VIVID_CS_SYS_BG, }; #define VIVID_INVALID_SIGNAL(mode) \ ((mode) == NO_SIGNAL || (mode) == NO_LOCK || (mode) == OUT_OF_RANGE) struct vivid_cec_xfer { struct cec_adapter *adap; u8 msg[CEC_MAX_MSG_SIZE]; u32 len; u32 sft; }; struct vivid_dev { u8 inst; struct v4l2_device v4l2_dev; #ifdef CONFIG_MEDIA_CONTROLLER struct media_device mdev; struct media_pad vid_cap_pad; struct media_pad vid_out_pad; struct media_pad vbi_cap_pad; struct media_pad vbi_out_pad; struct media_pad sdr_cap_pad; struct media_pad meta_cap_pad; struct media_pad meta_out_pad; struct media_pad touch_cap_pad; #endif struct v4l2_ctrl_handler ctrl_hdl_user_gen; struct v4l2_ctrl_handler ctrl_hdl_user_vid; struct v4l2_ctrl_handler ctrl_hdl_user_aud; struct v4l2_ctrl_handler ctrl_hdl_streaming; struct v4l2_ctrl_handler ctrl_hdl_sdtv_cap; struct v4l2_ctrl_handler ctrl_hdl_loop_cap; struct v4l2_ctrl_handler ctrl_hdl_fb; struct video_device vid_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_vid_cap; struct video_device vid_out_dev; struct v4l2_ctrl_handler ctrl_hdl_vid_out; struct video_device vbi_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_vbi_cap; struct video_device vbi_out_dev; struct v4l2_ctrl_handler ctrl_hdl_vbi_out; struct video_device radio_rx_dev; struct v4l2_ctrl_handler ctrl_hdl_radio_rx; struct video_device radio_tx_dev; struct v4l2_ctrl_handler ctrl_hdl_radio_tx; struct video_device sdr_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_sdr_cap; struct video_device meta_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_meta_cap; struct video_device meta_out_dev; struct v4l2_ctrl_handler ctrl_hdl_meta_out; struct video_device touch_cap_dev; struct v4l2_ctrl_handler ctrl_hdl_touch_cap; spinlock_t slock; struct mutex mutex; struct work_struct update_hdmi_ctrl_work; struct work_struct update_svid_ctrl_work; /* capabilities */ u32 vid_cap_caps; u32 vid_out_caps; u32 vbi_cap_caps; u32 vbi_out_caps; u32 sdr_cap_caps; u32 radio_rx_caps; u32 radio_tx_caps; u32 meta_cap_caps; u32 meta_out_caps; u32 touch_cap_caps; /* supported features */ bool multiplanar; u8 num_inputs; u8 num_hdmi_inputs; u8 num_svid_inputs; u8 input_type[MAX_INPUTS]; u8 input_name_counter[MAX_INPUTS]; u8 num_outputs; u8 num_hdmi_outputs; u8 output_type[MAX_OUTPUTS]; u8 output_name_counter[MAX_OUTPUTS]; bool has_audio_inputs; bool has_audio_outputs; bool has_vid_cap; bool has_vid_out; bool has_vbi_cap; bool has_raw_vbi_cap; bool has_sliced_vbi_cap; bool has_vbi_out; bool has_raw_vbi_out; bool has_sliced_vbi_out; bool has_radio_rx; bool has_radio_tx; bool has_sdr_cap; bool has_fb; bool has_meta_cap; bool has_meta_out; bool has_tv_tuner; bool has_touch_cap; /* Output index (0-MAX_OUTPUTS) to vivid instance of connected input */ struct vivid_dev *output_to_input_instance[MAX_OUTPUTS]; /* Output index (0-MAX_OUTPUTS) to input index (0-MAX_INPUTS) of connected input */ u8 output_to_input_index[MAX_OUTPUTS]; /* Output index (0-MAX_OUTPUTS) to HDMI or S-Video output index (0-MAX_HDMI/SVID_OUTPUTS) */ u8 output_to_iface_index[MAX_OUTPUTS]; /* ctrl_hdmi_to_output or ctrl_svid_to_output control value for each input */ s32 input_is_connected_to_output[MAX_INPUTS]; /* HDMI index (0-MAX_HDMI_OUTPUTS) to output index (0-MAX_OUTPUTS) */ u8 hdmi_index_to_output_index[MAX_HDMI_OUTPUTS]; /* HDMI index (0-MAX_HDMI_INPUTS) to input index (0-MAX_INPUTS) */ u8 hdmi_index_to_input_index[MAX_HDMI_INPUTS]; /* S-Video index (0-MAX_SVID_INPUTS) to input index (0-MAX_INPUTS) */ u8 svid_index_to_input_index[MAX_SVID_INPUTS]; /* controls */ struct v4l2_ctrl *brightness; struct v4l2_ctrl *contrast; struct v4l2_ctrl *saturation; struct v4l2_ctrl *hue; struct { /* autogain/gain cluster */ struct v4l2_ctrl *autogain; struct v4l2_ctrl *gain; }; struct v4l2_ctrl *volume; struct v4l2_ctrl *mute; struct v4l2_ctrl *alpha; struct v4l2_ctrl *button; struct v4l2_ctrl *boolean; struct v4l2_ctrl *int32; struct v4l2_ctrl *int64; struct v4l2_ctrl *menu; struct v4l2_ctrl *string; struct v4l2_ctrl *bitmask; struct v4l2_ctrl *int_menu; struct v4l2_ctrl *ro_int32; struct v4l2_ctrl *pixel_array; struct v4l2_ctrl *test_pattern; struct v4l2_ctrl *colorspace; struct v4l2_ctrl *rgb_range_cap; struct v4l2_ctrl *real_rgb_range_cap; struct { /* std_signal_mode/standard cluster */ struct v4l2_ctrl *ctrl_std_signal_mode; struct v4l2_ctrl *ctrl_standard; }; struct { /* dv_timings_signal_mode/timings cluster */ struct v4l2_ctrl *ctrl_dv_timings_signal_mode; struct v4l2_ctrl *ctrl_dv_timings; }; struct v4l2_ctrl *ctrl_has_crop_cap; struct v4l2_ctrl *ctrl_has_compose_cap; struct v4l2_ctrl *ctrl_has_scaler_cap; struct v4l2_ctrl *ctrl_has_crop_out; struct v4l2_ctrl *ctrl_has_compose_out; struct v4l2_ctrl *ctrl_has_scaler_out; struct v4l2_ctrl *ctrl_tx_mode; struct v4l2_ctrl *ctrl_tx_rgb_range; struct v4l2_ctrl *ctrl_tx_edid_present; struct v4l2_ctrl *ctrl_tx_hotplug; struct v4l2_ctrl *ctrl_tx_rxsense; struct v4l2_ctrl *ctrl_rx_power_present; struct v4l2_ctrl *radio_tx_rds_pi; struct v4l2_ctrl *radio_tx_rds_pty; struct v4l2_ctrl *radio_tx_rds_mono_stereo; struct v4l2_ctrl *radio_tx_rds_art_head; struct v4l2_ctrl *radio_tx_rds_compressed; struct v4l2_ctrl *radio_tx_rds_dyn_pty; struct v4l2_ctrl *radio_tx_rds_ta; struct v4l2_ctrl *radio_tx_rds_tp; struct v4l2_ctrl *radio_tx_rds_ms; struct v4l2_ctrl *radio_tx_rds_psname; struct v4l2_ctrl *radio_tx_rds_radiotext; struct v4l2_ctrl *radio_rx_rds_pty; struct v4l2_ctrl *radio_rx_rds_ta; struct v4l2_ctrl *radio_rx_rds_tp; struct v4l2_ctrl *radio_rx_rds_ms; struct v4l2_ctrl *radio_rx_rds_psname; struct v4l2_ctrl *radio_rx_rds_radiotext; struct v4l2_ctrl *ctrl_hdmi_to_output[MAX_HDMI_INPUTS]; char ctrl_hdmi_to_output_names[MAX_HDMI_INPUTS][32]; struct v4l2_ctrl *ctrl_svid_to_output[MAX_SVID_INPUTS]; char ctrl_svid_to_output_names[MAX_SVID_INPUTS][32]; unsigned input_brightness[MAX_INPUTS]; unsigned osd_mode; unsigned button_pressed; bool sensor_hflip; bool sensor_vflip; bool hflip; bool vflip; bool vbi_cap_interlaced; bool loop_video; bool reduced_fps; /* Framebuffer */ unsigned long video_pbase; void *video_vbase; u32 video_buffer_size; int display_width; int display_height; int display_byte_stride; int bits_per_pixel; int bytes_per_pixel; #ifdef CONFIG_VIDEO_VIVID_OSD struct fb_info fb_info; struct fb_var_screeninfo fb_defined; struct fb_fix_screeninfo fb_fix; #endif /* Error injection */ bool disconnect_error; bool queue_setup_error; bool buf_prepare_error; bool start_streaming_error; bool dqbuf_error; bool req_validate_error; bool seq_wrap; u64 time_wrap; u64 time_wrap_offset; unsigned perc_dropped_buffers; enum vivid_signal_mode std_signal_mode[MAX_INPUTS]; unsigned int query_std_last[MAX_INPUTS]; v4l2_std_id query_std[MAX_INPUTS]; enum tpg_video_aspect std_aspect_ratio[MAX_INPUTS]; enum vivid_signal_mode dv_timings_signal_mode[MAX_INPUTS]; char **query_dv_timings_qmenu; char *query_dv_timings_qmenu_strings; unsigned query_dv_timings_size; unsigned int query_dv_timings_last[MAX_INPUTS]; unsigned int query_dv_timings[MAX_INPUTS]; enum tpg_video_aspect dv_timings_aspect_ratio[MAX_INPUTS]; /* Input */ unsigned input; v4l2_std_id std_cap[MAX_INPUTS]; struct v4l2_dv_timings dv_timings_cap[MAX_INPUTS]; int dv_timings_cap_sel[MAX_INPUTS]; u32 service_set_cap; struct vivid_vbi_gen_data vbi_gen; u8 *edid; unsigned edid_blocks; unsigned edid_max_blocks; unsigned webcam_size_idx; unsigned webcam_ival_idx; unsigned tv_freq; unsigned tv_audmode; unsigned tv_field_cap; unsigned tv_audio_input; u32 power_present; /* Output */ unsigned output; v4l2_std_id std_out; struct v4l2_dv_timings dv_timings_out; u32 colorspace_out; u32 ycbcr_enc_out; u32 hsv_enc_out; u32 quantization_out; u32 xfer_func_out; u32 service_set_out; unsigned bytesperline_out[TPG_MAX_PLANES]; unsigned tv_field_out; unsigned tv_audio_output; bool vbi_out_have_wss; u8 vbi_out_wss[2]; bool vbi_out_have_cc[2]; u8 vbi_out_cc[2][2]; bool dvi_d_out; u8 *scaled_line; u8 *blended_line; unsigned cur_scaled_line; /* Output Overlay */ void *fb_vbase_out; bool overlay_out_enabled; int overlay_out_top, overlay_out_left; unsigned fbuf_out_flags; u32 chromakey_out; u8 global_alpha_out; /* video capture */ struct tpg_data tpg; unsigned ms_vid_cap; bool must_blank[MAX_VID_CAP_BUFFERS]; const struct vivid_fmt *fmt_cap; struct v4l2_fract timeperframe_vid_cap; enum v4l2_field field_cap; struct v4l2_rect src_rect; struct v4l2_rect fmt_cap_rect; struct v4l2_rect crop_cap; struct v4l2_rect compose_cap; struct v4l2_rect crop_bounds_cap; struct vb2_queue vb_vid_cap_q; struct list_head vid_cap_active; struct vb2_queue vb_vbi_cap_q; struct list_head vbi_cap_active; struct vb2_queue vb_meta_cap_q; struct list_head meta_cap_active; struct vb2_queue vb_touch_cap_q; struct list_head touch_cap_active; /* thread for generating video capture stream */ struct task_struct *kthread_vid_cap; unsigned long jiffies_vid_cap; u64 cap_stream_start; u64 cap_frame_period; u64 cap_frame_eof_offset; u32 cap_seq_offset; u32 cap_seq_count; bool cap_seq_resync; u32 vid_cap_seq_start; u32 vid_cap_seq_count; bool vid_cap_streaming; u32 vbi_cap_seq_start; u32 vbi_cap_seq_count; bool vbi_cap_streaming; u32 meta_cap_seq_start; u32 meta_cap_seq_count; bool meta_cap_streaming; /* Touch capture */ struct task_struct *kthread_touch_cap; unsigned long jiffies_touch_cap; u64 touch_cap_stream_start; u32 touch_cap_seq_offset; bool touch_cap_seq_resync; u32 touch_cap_seq_start; u32 touch_cap_seq_count; u32 touch_cap_with_seq_wrap_count; bool touch_cap_streaming; struct v4l2_fract timeperframe_tch_cap; struct v4l2_pix_format tch_format; int tch_pat_random; /* video output */ const struct vivid_fmt *fmt_out; struct v4l2_fract timeperframe_vid_out; enum v4l2_field field_out; struct v4l2_rect sink_rect; struct v4l2_rect fmt_out_rect; struct v4l2_rect crop_out; struct v4l2_rect compose_out; struct v4l2_rect compose_bounds_out; struct vb2_queue vb_vid_out_q; struct list_head vid_out_active; struct vb2_queue vb_vbi_out_q; struct list_head vbi_out_active; struct vb2_queue vb_meta_out_q; struct list_head meta_out_active; /* video loop precalculated rectangles */ /* * Intersection between what the output side composes and the capture side * crops. I.e., what actually needs to be copied from the output buffer to * the capture buffer. */ struct v4l2_rect loop_vid_copy; /* The part of the output buffer that (after scaling) corresponds to loop_vid_copy. */ struct v4l2_rect loop_vid_out; /* The part of the capture buffer that (after scaling) corresponds to loop_vid_copy. */ struct v4l2_rect loop_vid_cap; /* * The intersection of the framebuffer, the overlay output window and * loop_vid_copy. I.e., the part of the framebuffer that actually should be * blended with the compose_out rectangle. This uses the framebuffer origin. */ struct v4l2_rect loop_fb_copy; /* The same as loop_fb_copy but with compose_out origin. */ struct v4l2_rect loop_vid_overlay; /* * The part of the capture buffer that (after scaling) corresponds * to loop_vid_overlay. */ struct v4l2_rect loop_vid_overlay_cap; /* thread for generating video output stream */ struct task_struct *kthread_vid_out; unsigned long jiffies_vid_out; u32 out_seq_offset; u32 out_seq_count; bool out_seq_resync; u32 vid_out_seq_start; u32 vid_out_seq_count; bool vid_out_streaming; u32 vbi_out_seq_start; u32 vbi_out_seq_count; bool vbi_out_streaming; bool stream_sliced_vbi_out; u32 meta_out_seq_start; u32 meta_out_seq_count; bool meta_out_streaming; /* SDR capture */ struct vb2_queue vb_sdr_cap_q; struct list_head sdr_cap_active; u32 sdr_pixelformat; /* v4l2 format id */ unsigned sdr_buffersize; unsigned sdr_adc_freq; unsigned sdr_fm_freq; unsigned sdr_fm_deviation; int sdr_fixp_src_phase; int sdr_fixp_mod_phase; bool tstamp_src_is_soe; bool has_crop_cap; bool has_compose_cap; bool has_scaler_cap; bool has_crop_out; bool has_compose_out; bool has_scaler_out; /* thread for generating SDR stream */ struct task_struct *kthread_sdr_cap; unsigned long jiffies_sdr_cap; u32 sdr_cap_seq_offset; u32 sdr_cap_seq_start; u32 sdr_cap_seq_count; u32 sdr_cap_with_seq_wrap_count; bool sdr_cap_seq_resync; /* RDS generator */ struct vivid_rds_gen rds_gen; /* Radio receiver */ unsigned radio_rx_freq; unsigned radio_rx_audmode; int radio_rx_sig_qual; unsigned radio_rx_hw_seek_mode; bool radio_rx_hw_seek_prog_lim; bool radio_rx_rds_controls; bool radio_rx_rds_enabled; unsigned radio_rx_rds_use_alternates; unsigned radio_rx_rds_last_block; struct v4l2_fh *radio_rx_rds_owner; /* Radio transmitter */ unsigned radio_tx_freq; unsigned radio_tx_subchans; bool radio_tx_rds_controls; unsigned radio_tx_rds_last_block; struct v4l2_fh *radio_tx_rds_owner; /* Shared between radio receiver and transmitter */ bool radio_rds_loop; ktime_t radio_rds_init_time; /* CEC */ struct cec_adapter *cec_rx_adap; struct cec_adapter *cec_tx_adap[MAX_HDMI_OUTPUTS]; struct task_struct *kthread_cec; wait_queue_head_t kthread_waitq_cec; struct vivid_cec_xfer xfers[MAX_OUTPUTS]; spinlock_t cec_xfers_slock; /* read and write cec messages */ u32 cec_sft; /* bus signal free time, in bit periods */ u8 last_initiator; /* CEC OSD String */ char osd[14]; unsigned long osd_jiffies; bool meta_pts; bool meta_scr; }; static inline bool vivid_is_webcam(const struct vivid_dev *dev) { return dev->input_type[dev->input] == WEBCAM; } static inline bool vivid_is_tv_cap(const struct vivid_dev *dev) { return dev->input_type[dev->input] == TV; } static inline bool vivid_is_svid_cap(const struct vivid_dev *dev) { return dev->input_type[dev->input] == SVID; } static inline bool vivid_is_hdmi_cap(const struct vivid_dev *dev) { return dev->input_type[dev->input] == HDMI; } static inline bool vivid_is_sdtv_cap(const struct vivid_dev *dev) { return vivid_is_tv_cap(dev) || vivid_is_svid_cap(dev); } static inline bool vivid_is_svid_out(const struct vivid_dev *dev) { return dev->output_type[dev->output] == SVID; } static inline bool vivid_is_hdmi_out(const struct vivid_dev *dev) { return dev->output_type[dev->output] == HDMI; } #endif |
| 9 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 | // SPDX-License-Identifier: GPL-2.0-only /* * VMware VMCI Driver * * Copyright (C) 2012 VMware, Inc. All rights reserved. */ #include <linux/vmw_vmci_defs.h> #include <linux/vmw_vmci_api.h> #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include "vmci_driver.h" #include "vmci_event.h" static bool vmci_disable_host; module_param_named(disable_host, vmci_disable_host, bool, 0); MODULE_PARM_DESC(disable_host, "Disable driver host personality (default=enabled)"); static bool vmci_disable_guest; module_param_named(disable_guest, vmci_disable_guest, bool, 0); MODULE_PARM_DESC(disable_guest, "Disable driver guest personality (default=enabled)"); static bool vmci_guest_personality_initialized; static bool vmci_host_personality_initialized; static DEFINE_MUTEX(vmci_vsock_mutex); /* protects vmci_vsock_transport_cb */ static vmci_vsock_cb vmci_vsock_transport_cb; static bool vmci_vsock_cb_host_called; /* * vmci_get_context_id() - Gets the current context ID. * * Returns the current context ID. Note that since this is accessed only * from code running in the host, this always returns the host context ID. */ u32 vmci_get_context_id(void) { if (vmci_guest_code_active()) return vmci_get_vm_context_id(); else if (vmci_host_code_active()) return VMCI_HOST_CONTEXT_ID; return VMCI_INVALID_ID; } EXPORT_SYMBOL_GPL(vmci_get_context_id); /* * vmci_register_vsock_callback() - Register the VSOCK vmci_transport callback. * * The callback will be called when the first host or guest becomes active, * or if they are already active when this function is called. * To unregister the callback, call this function with NULL parameter. * * Returns 0 on success. -EBUSY if a callback is already registered. */ int vmci_register_vsock_callback(vmci_vsock_cb callback) { int err = 0; mutex_lock(&vmci_vsock_mutex); if (vmci_vsock_transport_cb && callback) { err = -EBUSY; goto out; } vmci_vsock_transport_cb = callback; if (!vmci_vsock_transport_cb) { vmci_vsock_cb_host_called = false; goto out; } if (vmci_guest_code_active()) vmci_vsock_transport_cb(false); if (vmci_host_users() > 0) { vmci_vsock_cb_host_called = true; vmci_vsock_transport_cb(true); } out: mutex_unlock(&vmci_vsock_mutex); return err; } EXPORT_SYMBOL_GPL(vmci_register_vsock_callback); void vmci_call_vsock_callback(bool is_host) { mutex_lock(&vmci_vsock_mutex); if (!vmci_vsock_transport_cb) goto out; /* In the host, this function could be called multiple times, * but we want to register it only once. */ if (is_host) { if (vmci_vsock_cb_host_called) goto out; vmci_vsock_cb_host_called = true; } vmci_vsock_transport_cb(is_host); out: mutex_unlock(&vmci_vsock_mutex); } static int __init vmci_drv_init(void) { int vmci_err; int error; vmci_err = vmci_event_init(); if (vmci_err < VMCI_SUCCESS) { pr_err("Failed to initialize VMCIEvent (result=%d)\n", vmci_err); return -EINVAL; } if (!vmci_disable_guest) { error = vmci_guest_init(); if (error) { pr_warn("Failed to initialize guest personality (err=%d)\n", error); } else { vmci_guest_personality_initialized = true; pr_info("Guest personality initialized and is %s\n", vmci_guest_code_active() ? "active" : "inactive"); } } if (!vmci_disable_host) { error = vmci_host_init(); if (error) { pr_warn("Unable to initialize host personality (err=%d)\n", error); } else { vmci_host_personality_initialized = true; pr_info("Initialized host personality\n"); } } if (!vmci_guest_personality_initialized && !vmci_host_personality_initialized) { vmci_event_exit(); return -ENODEV; } return 0; } module_init(vmci_drv_init); static void __exit vmci_drv_exit(void) { if (vmci_guest_personality_initialized) vmci_guest_exit(); if (vmci_host_personality_initialized) vmci_host_exit(); vmci_event_exit(); } module_exit(vmci_drv_exit); MODULE_AUTHOR("VMware, Inc."); MODULE_DESCRIPTION("VMware Virtual Machine Communication Interface."); MODULE_VERSION("1.1.6.0-k"); MODULE_LICENSE("GPL v2"); |
| 6 4 4 5 3 1 1 1 4 3 3 3 3 1 6 1 1 1 1 1 1 1 1 2 1 3 3 3 3 3 3 3 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Checksum updating actions * * Copyright (c) 2010 Gregoire Baron <baronchon@n7mm.org> */ #include <linux/types.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/netlink.h> #include <net/netlink.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/icmp.h> #include <linux/icmpv6.h> #include <linux/igmp.h> #include <net/tcp.h> #include <net/udp.h> #include <net/ip6_checksum.h> #include <net/sctp/checksum.h> #include <net/act_api.h> #include <net/pkt_cls.h> #include <linux/tc_act/tc_csum.h> #include <net/tc_act/tc_csum.h> #include <net/tc_wrapper.h> static const struct nla_policy csum_policy[TCA_CSUM_MAX + 1] = { [TCA_CSUM_PARMS] = { .len = sizeof(struct tc_csum), }, }; static struct tc_action_ops act_csum_ops; static int tcf_csum_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_csum_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct tcf_csum_params *params_new; struct nlattr *tb[TCA_CSUM_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_csum *parm; struct tcf_csum *p; int ret = 0, err; u32 index; if (nla == NULL) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_CSUM_MAX, nla, csum_policy, NULL); if (err < 0) return err; if (tb[TCA_CSUM_PARMS] == NULL) return -EINVAL; parm = nla_data(tb[TCA_CSUM_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { ret = tcf_idr_create_from_flags(tn, index, est, a, &act_csum_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else if (err > 0) { if (bind) /* dont override defaults */ return ACT_P_BOUND; if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } } else { return err; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; p = to_tcf_csum(*a); params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { err = -ENOMEM; goto put_chain; } params_new->update_flags = parm->update_flags; params_new->action = parm->action; spin_lock_bh(&p->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); params_new = rcu_replace_pointer(p->params, params_new, lockdep_is_held(&p->tcf_lock)); spin_unlock_bh(&p->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (params_new) kfree_rcu(params_new, rcu); return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } /** * tcf_csum_skb_nextlayer - Get next layer pointer * @skb: sk_buff to use * @ihl: previous summed headers length * @ipl: complete packet length * @jhl: next header length * * Check the expected next layer availability in the specified sk_buff. * Return the next layer pointer if pass, NULL otherwise. */ static void *tcf_csum_skb_nextlayer(struct sk_buff *skb, unsigned int ihl, unsigned int ipl, unsigned int jhl) { int ntkoff = skb_network_offset(skb); int hl = ihl + jhl; if (!pskb_may_pull(skb, ipl + ntkoff) || (ipl < hl) || skb_try_make_writable(skb, hl + ntkoff)) return NULL; else return (void *)(skb_network_header(skb) + ihl); } static int tcf_csum_ipv4_icmp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct icmphdr *icmph; icmph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*icmph)); if (icmph == NULL) return 0; icmph->checksum = 0; skb->csum = csum_partial(icmph, ipl - ihl, 0); icmph->checksum = csum_fold(skb->csum); skb->ip_summed = CHECKSUM_NONE; return 1; } static int tcf_csum_ipv4_igmp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct igmphdr *igmph; igmph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*igmph)); if (igmph == NULL) return 0; igmph->csum = 0; skb->csum = csum_partial(igmph, ipl - ihl, 0); igmph->csum = csum_fold(skb->csum); skb->ip_summed = CHECKSUM_NONE; return 1; } static int tcf_csum_ipv6_icmp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct icmp6hdr *icmp6h; const struct ipv6hdr *ip6h; icmp6h = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*icmp6h)); if (icmp6h == NULL) return 0; ip6h = ipv6_hdr(skb); icmp6h->icmp6_cksum = 0; skb->csum = csum_partial(icmp6h, ipl - ihl, 0); icmp6h->icmp6_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, ipl - ihl, IPPROTO_ICMPV6, skb->csum); skb->ip_summed = CHECKSUM_NONE; return 1; } static int tcf_csum_ipv4_tcp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct tcphdr *tcph; const struct iphdr *iph; if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) return 1; tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph)); if (tcph == NULL) return 0; iph = ip_hdr(skb); tcph->check = 0; skb->csum = csum_partial(tcph, ipl - ihl, 0); tcph->check = tcp_v4_check(ipl - ihl, iph->saddr, iph->daddr, skb->csum); skb->ip_summed = CHECKSUM_NONE; return 1; } static int tcf_csum_ipv6_tcp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct tcphdr *tcph; const struct ipv6hdr *ip6h; if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) return 1; tcph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*tcph)); if (tcph == NULL) return 0; ip6h = ipv6_hdr(skb); tcph->check = 0; skb->csum = csum_partial(tcph, ipl - ihl, 0); tcph->check = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, ipl - ihl, IPPROTO_TCP, skb->csum); skb->ip_summed = CHECKSUM_NONE; return 1; } static int tcf_csum_ipv4_udp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl, int udplite) { struct udphdr *udph; const struct iphdr *iph; u16 ul; if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP) return 1; /* * Support both UDP and UDPLITE checksum algorithms, Don't use * udph->len to get the real length without any protocol check, * UDPLITE uses udph->len for another thing, * Use iph->tot_len, or just ipl. */ udph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*udph)); if (udph == NULL) return 0; iph = ip_hdr(skb); ul = ntohs(udph->len); if (udplite || udph->check) { udph->check = 0; if (udplite) { if (ul == 0) skb->csum = csum_partial(udph, ipl - ihl, 0); else if ((ul >= sizeof(*udph)) && (ul <= ipl - ihl)) skb->csum = csum_partial(udph, ul, 0); else goto ignore_obscure_skb; } else { if (ul != ipl - ihl) goto ignore_obscure_skb; skb->csum = csum_partial(udph, ul, 0); } udph->check = csum_tcpudp_magic(iph->saddr, iph->daddr, ul, iph->protocol, skb->csum); if (!udph->check) udph->check = CSUM_MANGLED_0; } skb->ip_summed = CHECKSUM_NONE; ignore_obscure_skb: return 1; } static int tcf_csum_ipv6_udp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl, int udplite) { struct udphdr *udph; const struct ipv6hdr *ip6h; u16 ul; if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP) return 1; /* * Support both UDP and UDPLITE checksum algorithms, Don't use * udph->len to get the real length without any protocol check, * UDPLITE uses udph->len for another thing, * Use ip6h->payload_len + sizeof(*ip6h) ... , or just ipl. */ udph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*udph)); if (udph == NULL) return 0; ip6h = ipv6_hdr(skb); ul = ntohs(udph->len); udph->check = 0; if (udplite) { if (ul == 0) skb->csum = csum_partial(udph, ipl - ihl, 0); else if ((ul >= sizeof(*udph)) && (ul <= ipl - ihl)) skb->csum = csum_partial(udph, ul, 0); else goto ignore_obscure_skb; } else { if (ul != ipl - ihl) goto ignore_obscure_skb; skb->csum = csum_partial(udph, ul, 0); } udph->check = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, ul, udplite ? IPPROTO_UDPLITE : IPPROTO_UDP, skb->csum); if (!udph->check) udph->check = CSUM_MANGLED_0; skb->ip_summed = CHECKSUM_NONE; ignore_obscure_skb: return 1; } static int tcf_csum_sctp(struct sk_buff *skb, unsigned int ihl, unsigned int ipl) { struct sctphdr *sctph; if (skb_is_gso(skb) && skb_is_gso_sctp(skb)) return 1; sctph = tcf_csum_skb_nextlayer(skb, ihl, ipl, sizeof(*sctph)); if (!sctph) return 0; sctph->checksum = sctp_compute_cksum(skb, skb_network_offset(skb) + ihl); skb_reset_csum_not_inet(skb); return 1; } static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags) { const struct iphdr *iph; int ntkoff; ntkoff = skb_network_offset(skb); if (!pskb_may_pull(skb, sizeof(*iph) + ntkoff)) goto fail; iph = ip_hdr(skb); switch (iph->frag_off & htons(IP_OFFSET) ? 0 : iph->protocol) { case IPPROTO_ICMP: if (update_flags & TCA_CSUM_UPDATE_FLAG_ICMP) if (!tcf_csum_ipv4_icmp(skb, iph->ihl * 4, ntohs(iph->tot_len))) goto fail; break; case IPPROTO_IGMP: if (update_flags & TCA_CSUM_UPDATE_FLAG_IGMP) if (!tcf_csum_ipv4_igmp(skb, iph->ihl * 4, ntohs(iph->tot_len))) goto fail; break; case IPPROTO_TCP: if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP) if (!tcf_csum_ipv4_tcp(skb, iph->ihl * 4, ntohs(iph->tot_len))) goto fail; break; case IPPROTO_UDP: if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP) if (!tcf_csum_ipv4_udp(skb, iph->ihl * 4, ntohs(iph->tot_len), 0)) goto fail; break; case IPPROTO_UDPLITE: if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE) if (!tcf_csum_ipv4_udp(skb, iph->ihl * 4, ntohs(iph->tot_len), 1)) goto fail; break; case IPPROTO_SCTP: if ((update_flags & TCA_CSUM_UPDATE_FLAG_SCTP) && !tcf_csum_sctp(skb, iph->ihl * 4, ntohs(iph->tot_len))) goto fail; break; } if (update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) { if (skb_try_make_writable(skb, sizeof(*iph) + ntkoff)) goto fail; ip_send_check(ip_hdr(skb)); } return 1; fail: return 0; } static int tcf_csum_ipv6_hopopts(struct ipv6_opt_hdr *ip6xh, unsigned int ixhl, unsigned int *pl) { int off, len, optlen; unsigned char *xh = (void *)ip6xh; off = sizeof(*ip6xh); len = ixhl - off; while (len > 1) { switch (xh[off]) { case IPV6_TLV_PAD1: optlen = 1; break; case IPV6_TLV_JUMBO: optlen = xh[off + 1] + 2; if (optlen != 6 || len < 6 || (off & 3) != 2) /* wrong jumbo option length/alignment */ return 0; *pl = ntohl(*(__be32 *)(xh + off + 2)); goto done; default: optlen = xh[off + 1] + 2; if (optlen > len) /* ignore obscure options */ goto done; break; } off += optlen; len -= optlen; } done: return 1; } static int tcf_csum_ipv6(struct sk_buff *skb, u32 update_flags) { struct ipv6hdr *ip6h; struct ipv6_opt_hdr *ip6xh; unsigned int hl, ixhl; unsigned int pl; int ntkoff; u8 nexthdr; ntkoff = skb_network_offset(skb); hl = sizeof(*ip6h); if (!pskb_may_pull(skb, hl + ntkoff)) goto fail; ip6h = ipv6_hdr(skb); pl = ntohs(ip6h->payload_len); nexthdr = ip6h->nexthdr; do { switch (nexthdr) { case NEXTHDR_FRAGMENT: goto ignore_skb; case NEXTHDR_ROUTING: case NEXTHDR_HOP: case NEXTHDR_DEST: if (!pskb_may_pull(skb, hl + sizeof(*ip6xh) + ntkoff)) goto fail; ip6xh = (void *)(skb_network_header(skb) + hl); ixhl = ipv6_optlen(ip6xh); if (!pskb_may_pull(skb, hl + ixhl + ntkoff)) goto fail; ip6xh = (void *)(skb_network_header(skb) + hl); if ((nexthdr == NEXTHDR_HOP) && !(tcf_csum_ipv6_hopopts(ip6xh, ixhl, &pl))) goto fail; nexthdr = ip6xh->nexthdr; hl += ixhl; break; case IPPROTO_ICMPV6: if (update_flags & TCA_CSUM_UPDATE_FLAG_ICMP) if (!tcf_csum_ipv6_icmp(skb, hl, pl + sizeof(*ip6h))) goto fail; goto done; case IPPROTO_TCP: if (update_flags & TCA_CSUM_UPDATE_FLAG_TCP) if (!tcf_csum_ipv6_tcp(skb, hl, pl + sizeof(*ip6h))) goto fail; goto done; case IPPROTO_UDP: if (update_flags & TCA_CSUM_UPDATE_FLAG_UDP) if (!tcf_csum_ipv6_udp(skb, hl, pl + sizeof(*ip6h), 0)) goto fail; goto done; case IPPROTO_UDPLITE: if (update_flags & TCA_CSUM_UPDATE_FLAG_UDPLITE) if (!tcf_csum_ipv6_udp(skb, hl, pl + sizeof(*ip6h), 1)) goto fail; goto done; case IPPROTO_SCTP: if ((update_flags & TCA_CSUM_UPDATE_FLAG_SCTP) && !tcf_csum_sctp(skb, hl, pl + sizeof(*ip6h))) goto fail; goto done; default: goto ignore_skb; } } while (pskb_may_pull(skb, hl + 1 + ntkoff)); done: ignore_skb: return 1; fail: return 0; } TC_INDIRECT_SCOPE int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_csum *p = to_tcf_csum(a); bool orig_vlan_tag_present = false; unsigned int vlan_hdr_count = 0; struct tcf_csum_params *params; u32 update_flags; __be16 protocol; int action; params = rcu_dereference_bh(p->params); tcf_lastuse_update(&p->tcf_tm); tcf_action_update_bstats(&p->common, skb); action = params->action; if (unlikely(action == TC_ACT_SHOT)) goto drop; update_flags = params->update_flags; protocol = skb_protocol(skb, false); again: switch (protocol) { case cpu_to_be16(ETH_P_IP): if (!tcf_csum_ipv4(skb, update_flags)) goto drop; break; case cpu_to_be16(ETH_P_IPV6): if (!tcf_csum_ipv6(skb, update_flags)) goto drop; break; case cpu_to_be16(ETH_P_8021AD): fallthrough; case cpu_to_be16(ETH_P_8021Q): if (skb_vlan_tag_present(skb) && !orig_vlan_tag_present) { protocol = skb->protocol; orig_vlan_tag_present = true; } else { struct vlan_hdr *vlan = (struct vlan_hdr *)skb->data; protocol = vlan->h_vlan_encapsulated_proto; skb_pull(skb, VLAN_HLEN); skb_reset_network_header(skb); vlan_hdr_count++; } goto again; } out: /* Restore the skb for the pulled VLAN tags */ while (vlan_hdr_count--) { skb_push(skb, VLAN_HLEN); skb_reset_network_header(skb); } return action; drop: tcf_action_inc_drop_qstats(&p->common); action = TC_ACT_SHOT; goto out; } static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { const struct tcf_csum *p = to_tcf_csum(a); unsigned char *b = skb_tail_pointer(skb); const struct tcf_csum_params *params; struct tc_csum opt = { .index = p->tcf_index, .refcnt = refcount_read(&p->tcf_refcnt) - ref, .bindcnt = atomic_read(&p->tcf_bindcnt) - bind, }; struct tcf_t t; rcu_read_lock(); params = rcu_dereference(p->params); opt.action = params->action; opt.update_flags = params->update_flags; if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &p->tcf_tm); if (nla_put_64bit(skb, TCA_CSUM_TM, sizeof(t), &t, TCA_CSUM_PAD)) goto nla_put_failure; rcu_read_unlock(); return skb->len; nla_put_failure: rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } static void tcf_csum_cleanup(struct tc_action *a) { struct tcf_csum *p = to_tcf_csum(a); struct tcf_csum_params *params; params = rcu_dereference_protected(p->params, 1); if (params) kfree_rcu(params, rcu); } static size_t tcf_csum_get_fill_size(const struct tc_action *act) { return nla_total_size(sizeof(struct tc_csum)); } static int tcf_csum_offload_act_setup(struct tc_action *act, void *entry_data, u32 *index_inc, bool bind, struct netlink_ext_ack *extack) { if (bind) { struct flow_action_entry *entry = entry_data; entry->id = FLOW_ACTION_CSUM; entry->csum_flags = tcf_csum_update_flags(act); *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; fl_action->id = FLOW_ACTION_CSUM; } return 0; } static struct tc_action_ops act_csum_ops = { .kind = "csum", .id = TCA_ID_CSUM, .owner = THIS_MODULE, .act = tcf_csum_act, .dump = tcf_csum_dump, .init = tcf_csum_init, .cleanup = tcf_csum_cleanup, .get_fill_size = tcf_csum_get_fill_size, .offload_act_setup = tcf_csum_offload_act_setup, .size = sizeof(struct tcf_csum), }; MODULE_ALIAS_NET_ACT("csum"); static __net_init int csum_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_csum_ops.net_id); return tc_action_net_init(net, tn, &act_csum_ops); } static void __net_exit csum_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_csum_ops.net_id); } static struct pernet_operations csum_net_ops = { .init = csum_init_net, .exit_batch = csum_exit_net, .id = &act_csum_ops.net_id, .size = sizeof(struct tc_action_net), }; MODULE_DESCRIPTION("Checksum updating actions"); MODULE_LICENSE("GPL"); static int __init csum_init_module(void) { return tcf_register_action(&act_csum_ops, &csum_net_ops); } static void __exit csum_cleanup_module(void) { tcf_unregister_action(&act_csum_ops, &csum_net_ops); } module_init(csum_init_module); module_exit(csum_cleanup_module); |
| 11 2 2 2 4 7 2 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netfilter.h> #include <linux/rhashtable.h> #include <net/netfilter/nf_flow_table.h> #include <net/netfilter/nf_tables.h> #include <linux/if_vlan.h> static unsigned int nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct vlan_ethhdr *veth; __be16 proto; switch (skb->protocol) { case htons(ETH_P_8021Q): if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth))) return NF_ACCEPT; veth = (struct vlan_ethhdr *)skb_mac_header(skb); proto = veth->h_vlan_encapsulated_proto; break; case htons(ETH_P_PPP_SES): if (!nf_flow_pppoe_proto(skb, &proto)) return NF_ACCEPT; break; default: proto = skb->protocol; break; } switch (proto) { case htons(ETH_P_IP): return nf_flow_offload_ip_hook(priv, skb, state); case htons(ETH_P_IPV6): return nf_flow_offload_ipv6_hook(priv, skb, state); } return NF_ACCEPT; } static int nf_flow_rule_route_inet(struct net *net, struct flow_offload *flow, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { const struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple; int err; switch (flow_tuple->l3proto) { case NFPROTO_IPV4: err = nf_flow_rule_route_ipv4(net, flow, dir, flow_rule); break; case NFPROTO_IPV6: err = nf_flow_rule_route_ipv6(net, flow, dir, flow_rule); break; default: err = -1; break; } return err; } static struct nf_flowtable_type flowtable_inet = { .family = NFPROTO_INET, .init = nf_flow_table_init, .setup = nf_flow_table_offload_setup, .action = nf_flow_rule_route_inet, .free = nf_flow_table_free, .hook = nf_flow_offload_inet_hook, .owner = THIS_MODULE, }; static struct nf_flowtable_type flowtable_ipv4 = { .family = NFPROTO_IPV4, .init = nf_flow_table_init, .setup = nf_flow_table_offload_setup, .action = nf_flow_rule_route_ipv4, .free = nf_flow_table_free, .hook = nf_flow_offload_ip_hook, .owner = THIS_MODULE, }; static struct nf_flowtable_type flowtable_ipv6 = { .family = NFPROTO_IPV6, .init = nf_flow_table_init, .setup = nf_flow_table_offload_setup, .action = nf_flow_rule_route_ipv6, .free = nf_flow_table_free, .hook = nf_flow_offload_ipv6_hook, .owner = THIS_MODULE, }; static int __init nf_flow_inet_module_init(void) { nft_register_flowtable_type(&flowtable_ipv4); nft_register_flowtable_type(&flowtable_ipv6); nft_register_flowtable_type(&flowtable_inet); return 0; } static void __exit nf_flow_inet_module_exit(void) { nft_unregister_flowtable_type(&flowtable_inet); nft_unregister_flowtable_type(&flowtable_ipv6); nft_unregister_flowtable_type(&flowtable_ipv4); } module_init(nf_flow_inet_module_init); module_exit(nf_flow_inet_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NF_FLOWTABLE(AF_INET); MODULE_ALIAS_NF_FLOWTABLE(AF_INET6); MODULE_ALIAS_NF_FLOWTABLE(1); /* NFPROTO_INET */ MODULE_DESCRIPTION("Netfilter flow table mixed IPv4/IPv6 module"); |
| 403 37 31 14275 2227 2173 552 459 1090 1644 8 16311 15621 11874 11894 9612 11714 2955 2266 4 9670 66 66 29 394 33 93 88 89 6 6 13 101 1356 120 119 153 548 341 234 40 138 8844 88 16124 13020 13 274 15836 39 31 1865 14 37 33 34 25 13 34 11 9 34 12 5 2 28 78 11 28 28 1850 9217 1075 421 97 97 353 56 302 52 3340 623 763 7 9 25 12 29 111 21 2 122 75 44 9 45 5904 198 25 25 14 14 14 1239 707 11 4 311 565 56 349 99 60 35 10 88 12 31 117 170 3 1133 3 1133 1677 877 1214 1045 85 24 24 10130 7735 4 23 59 65 178 209 68 468 470 468 61 405 404 404 15495 83 67 11762 5010 5541 2 76 16 217 2 1 4 988 1570 82 8873 11023 11042 10773 299 6803 279 99 6788 809 807 1610 8735 3177 156 162 161 1 31 35 201 507 35 131 35 1329 8 3 6 6 8 53 5 1898 1816 2107 154 820 1271 36 36 863 1766 2526 103 953 10199 89 626 2636 2660 23 23 1692 88 10299 52 243 271 1367 1003 900 38 1165 810 1106 1338 49 344 26 1360 1485 46 1482 166 41 129 138 251 4 2 46 7 46 3962 1870 593 3997 16 12005 16 1324 9 244 177 11 11 899 1069 358 115 18 18 466 30 9 9 32 72 15 1 120 42 69 11 187 3 3 3 249 265 174 110 271 26 166 41 11 2 1 1 39 3 70 616 51 2 29 29 28 29 28 497 141 2 1 2 2 1 2 929 91 8725 54 475 633 1794 281 6 378 1116 455 8778 18 272 1 195 850 20 9 487 749 857 918 553 31 31 19 97 1165 18 679 671 117 15 13 3 1 5 13 3 3 13 10 3 656 50 4 162 47 15 355 217 29 1 15703 273 10 15540 12062 42 43 43 107 84 9609 265 25 9593 50 216 23 999 1018 12029 42 108 107 108 61 604 8898 171 122 388 153 1266 8815 9016 26 3 2 2 49 1 1 1178 754 422 56 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Definitions for the 'struct sk_buff' memory handlers. * * Authors: * Alan Cox, <gw4pts@gw4pts.ampr.org> * Florian La Roche, <rzsfl@rz.uni-sb.de> */ #ifndef _LINUX_SKBUFF_H #define _LINUX_SKBUFF_H #include <linux/kernel.h> #include <linux/compiler.h> #include <linux/time.h> #include <linux/bug.h> #include <linux/bvec.h> #include <linux/cache.h> #include <linux/rbtree.h> #include <linux/socket.h> #include <linux/refcount.h> #include <linux/atomic.h> #include <asm/types.h> #include <linux/spinlock.h> #include <net/checksum.h> #include <linux/rcupdate.h> #include <linux/dma-mapping.h> #include <linux/netdev_features.h> #include <net/flow_dissector.h> #include <linux/in6.h> #include <linux/if_packet.h> #include <linux/llist.h> #include <linux/page_frag_cache.h> #include <net/flow.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> #endif #include <net/net_debug.h> #include <net/dropreason-core.h> #include <net/netmem.h> /** * DOC: skb checksums * * The interface for checksum offload between the stack and networking drivers * is as follows... * * IP checksum related features * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Drivers advertise checksum offload capabilities in the features of a device. * From the stack's point of view these are capabilities offered by the driver. * A driver typically only advertises features that it is capable of offloading * to its device. * * .. flat-table:: Checksum related device features * :widths: 1 10 * * * - %NETIF_F_HW_CSUM * - The driver (or its device) is able to compute one * IP (one's complement) checksum for any combination * of protocols or protocol layering. The checksum is * computed and set in a packet per the CHECKSUM_PARTIAL * interface (see below). * * * - %NETIF_F_IP_CSUM * - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv4. These are specifically * unencapsulated packets of the form IPv4|TCP or * IPv4|UDP where the Protocol field in the IPv4 header * is TCP or UDP. The IPv4 header may contain IP options. * This feature cannot be set in features for a device * with NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). * * * - %NETIF_F_IPV6_CSUM * - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv6. These are specifically * unencapsulated packets of the form IPv6|TCP or * IPv6|UDP where the Next Header field in the IPv6 * header is either TCP or UDP. IPv6 extension headers * are not supported with this feature. This feature * cannot be set in features for a device with * NETIF_F_HW_CSUM also set. This feature is being * DEPRECATED (see below). * * * - %NETIF_F_RXCSUM * - Driver (device) performs receive checksum offload. * This flag is only used to disable the RX checksum * feature for a device. The stack will accept receive * checksum indication in packets received on a device * regardless of whether NETIF_F_RXCSUM is set. * * Checksumming of received packets by device * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * Indication of checksum verification is set in &sk_buff.ip_summed. * Possible values are: * * - %CHECKSUM_NONE * * Device did not checksum this packet e.g. due to lack of capabilities. * The packet contains full (though not verified) checksum in packet but * not in skb->csum. Thus, skb->csum is undefined in this case. * * - %CHECKSUM_UNNECESSARY * * The hardware you're dealing with doesn't calculate the full checksum * (as in %CHECKSUM_COMPLETE), but it does parse headers and verify checksums * for specific protocols. For such packets it will set %CHECKSUM_UNNECESSARY * if their checksums are okay. &sk_buff.csum is still undefined in this case * though. A driver or device must never modify the checksum field in the * packet even if checksum is verified. * * %CHECKSUM_UNNECESSARY is applicable to following protocols: * * - TCP: IPv6 and IPv4. * - UDP: IPv4 and IPv6. A device may apply CHECKSUM_UNNECESSARY to a * zero UDP checksum for either IPv4 or IPv6, the networking stack * may perform further validation in this case. * - GRE: only if the checksum is present in the header. * - SCTP: indicates the CRC in SCTP header has been validated. * - FCOE: indicates the CRC in FC frame has been validated. * * &sk_buff.csum_level indicates the number of consecutive checksums found in * the packet minus one that have been verified as %CHECKSUM_UNNECESSARY. * For instance if a device receives an IPv6->UDP->GRE->IPv4->TCP packet * and a device is able to verify the checksums for UDP (possibly zero), * GRE (checksum flag is set) and TCP, &sk_buff.csum_level would be set to * two. If the device were only able to verify the UDP checksum and not * GRE, either because it doesn't support GRE checksum or because GRE * checksum is bad, skb->csum_level would be set to zero (TCP checksum is * not considered in this case). * * - %CHECKSUM_COMPLETE * * This is the most generic way. The device supplied checksum of the _whole_ * packet as seen by netif_rx() and fills in &sk_buff.csum. This means the * hardware doesn't need to parse L3/L4 headers to implement this. * * Notes: * * - Even if device supports only some protocols, but is able to produce * skb->csum, it MUST use CHECKSUM_COMPLETE, not CHECKSUM_UNNECESSARY. * - CHECKSUM_COMPLETE is not applicable to SCTP and FCoE protocols. * * - %CHECKSUM_PARTIAL * * A checksum is set up to be offloaded to a device as described in the * output description for CHECKSUM_PARTIAL. This may occur on a packet * received directly from another Linux OS, e.g., a virtualized Linux kernel * on the same host, or it may be set in the input path in GRO or remote * checksum offload. For the purposes of checksum verification, the checksum * referred to by skb->csum_start + skb->csum_offset and any preceding * checksums in the packet are considered verified. Any checksums in the * packet that are after the checksum being offloaded are not considered to * be verified. * * Checksumming on transmit for non-GSO * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * The stack requests checksum offload in the &sk_buff.ip_summed for a packet. * Values are: * * - %CHECKSUM_PARTIAL * * The driver is required to checksum the packet as seen by hard_start_xmit() * from &sk_buff.csum_start up to the end, and to record/write the checksum at * offset &sk_buff.csum_start + &sk_buff.csum_offset. * A driver may verify that the * csum_start and csum_offset values are valid values given the length and * offset of the packet, but it should not attempt to validate that the * checksum refers to a legitimate transport layer checksum -- it is the * purview of the stack to validate that csum_start and csum_offset are set * correctly. * * When the stack requests checksum offload for a packet, the driver MUST * ensure that the checksum is set correctly. A driver can either offload the * checksum calculation to the device, or call skb_checksum_help (in the case * that the device does not support offload for a particular checksum). * * %NETIF_F_IP_CSUM and %NETIF_F_IPV6_CSUM are being deprecated in favor of * %NETIF_F_HW_CSUM. New devices should use %NETIF_F_HW_CSUM to indicate * checksum offload capability. * skb_csum_hwoffload_help() can be called to resolve %CHECKSUM_PARTIAL based * on network device checksumming capabilities: if a packet does not match * them, skb_checksum_help() or skb_crc32c_help() (depending on the value of * &sk_buff.csum_not_inet, see :ref:`crc`) * is called to resolve the checksum. * * - %CHECKSUM_NONE * * The skb was already checksummed by the protocol, or a checksum is not * required. * * - %CHECKSUM_UNNECESSARY * * This has the same meaning as CHECKSUM_NONE for checksum offload on * output. * * - %CHECKSUM_COMPLETE * * Not used in checksum output. If a driver observes a packet with this value * set in skbuff, it should treat the packet as if %CHECKSUM_NONE were set. * * .. _crc: * * Non-IP checksum (CRC) offloads * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * .. flat-table:: * :widths: 1 10 * * * - %NETIF_F_SCTP_CRC * - This feature indicates that a device is capable of * offloading the SCTP CRC in a packet. To perform this offload the stack * will set csum_start and csum_offset accordingly, set ip_summed to * %CHECKSUM_PARTIAL and set csum_not_inet to 1, to provide an indication * in the skbuff that the %CHECKSUM_PARTIAL refers to CRC32c. * A driver that supports both IP checksum offload and SCTP CRC32c offload * must verify which offload is configured for a packet by testing the * value of &sk_buff.csum_not_inet; skb_crc32c_csum_help() is provided to * resolve %CHECKSUM_PARTIAL on skbs where csum_not_inet is set to 1. * * * - %NETIF_F_FCOE_CRC * - This feature indicates that a device is capable of offloading the FCOE * CRC in a packet. To perform this offload the stack will set ip_summed * to %CHECKSUM_PARTIAL and set csum_start and csum_offset * accordingly. Note that there is no indication in the skbuff that the * %CHECKSUM_PARTIAL refers to an FCOE checksum, so a driver that supports * both IP checksum offload and FCOE CRC offload must verify which offload * is configured for a packet, presumably by inspecting packet headers. * * Checksumming on output with GSO * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * In the case of a GSO packet (skb_is_gso() is true), checksum offload * is implied by the SKB_GSO_* flags in gso_type. Most obviously, if the * gso_type is %SKB_GSO_TCPV4 or %SKB_GSO_TCPV6, TCP checksum offload as * part of the GSO operation is implied. If a checksum is being offloaded * with GSO then ip_summed is %CHECKSUM_PARTIAL, and both csum_start and * csum_offset are set to refer to the outermost checksum being offloaded * (two offloaded checksums are possible with UDP encapsulation). */ /* Don't change this without changing skb_csum_unnecessary! */ #define CHECKSUM_NONE 0 #define CHECKSUM_UNNECESSARY 1 #define CHECKSUM_COMPLETE 2 #define CHECKSUM_PARTIAL 3 /* Maximum value in skb->csum_level */ #define SKB_MAX_CSUM_LEVEL 3 #define SKB_DATA_ALIGN(X) ALIGN(X, SMP_CACHE_BYTES) #define SKB_WITH_OVERHEAD(X) \ ((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) /* For X bytes available in skb->head, what is the minimal * allocation needed, knowing struct skb_shared_info needs * to be aligned. */ #define SKB_HEAD_ALIGN(X) (SKB_DATA_ALIGN(X) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) #define SKB_MAX_ORDER(X, ORDER) \ SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X)) #define SKB_MAX_HEAD(X) (SKB_MAX_ORDER((X), 0)) #define SKB_MAX_ALLOC (SKB_MAX_ORDER(0, 2)) /* return minimum truesize of one skb containing X bytes of data */ #define SKB_TRUESIZE(X) ((X) + \ SKB_DATA_ALIGN(sizeof(struct sk_buff)) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) struct net_device; struct scatterlist; struct pipe_inode_info; struct iov_iter; struct napi_struct; struct bpf_prog; union bpf_attr; struct skb_ext; struct ts_config; #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info { enum { BRNF_PROTO_UNCHANGED, BRNF_PROTO_8021Q, BRNF_PROTO_PPPOE } orig_proto:8; u8 pkt_otherhost:1; u8 in_prerouting:1; u8 bridged_dnat:1; u8 sabotage_in_done:1; __u16 frag_max_size; int physinif; /* always valid & non-NULL from FORWARD on, for physdev match */ struct net_device *physoutdev; union { /* prerouting: detect dnat in orig/reply direction */ __be32 ipv4_daddr; struct in6_addr ipv6_daddr; /* after prerouting + nat detected: store original source * mac since neigh resolution overwrites it, only used while * skb is out in neigh layer. */ char neigh_header[8]; }; }; #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) /* Chain in tc_skb_ext will be used to share the tc chain with * ovs recirc_id. It will be set to the current chain by tc * and read by ovs to recirc_id. */ struct tc_skb_ext { union { u64 act_miss_cookie; __u32 chain; }; __u16 mru; __u16 zone; u8 post_ct:1; u8 post_ct_snat:1; u8 post_ct_dnat:1; u8 act_miss:1; /* Set if act_miss_cookie is used */ u8 l2_miss:1; /* Set by bridge upon FDB or MDB miss */ }; #endif struct sk_buff_head { /* These two members must be first to match sk_buff. */ struct_group_tagged(sk_buff_list, list, struct sk_buff *next; struct sk_buff *prev; ); __u32 qlen; spinlock_t lock; }; struct sk_buff; #ifndef CONFIG_MAX_SKB_FRAGS # define CONFIG_MAX_SKB_FRAGS 17 #endif #define MAX_SKB_FRAGS CONFIG_MAX_SKB_FRAGS /* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to * segment using its current segmentation instead. */ #define GSO_BY_FRAGS 0xFFFF typedef struct skb_frag { netmem_ref netmem; unsigned int len; unsigned int offset; } skb_frag_t; /** * skb_frag_size() - Returns the size of a skb fragment * @frag: skb fragment */ static inline unsigned int skb_frag_size(const skb_frag_t *frag) { return frag->len; } /** * skb_frag_size_set() - Sets the size of a skb fragment * @frag: skb fragment * @size: size of fragment */ static inline void skb_frag_size_set(skb_frag_t *frag, unsigned int size) { frag->len = size; } /** * skb_frag_size_add() - Increments the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_size_add(skb_frag_t *frag, int delta) { frag->len += delta; } /** * skb_frag_size_sub() - Decrements the size of a skb fragment by @delta * @frag: skb fragment * @delta: value to subtract */ static inline void skb_frag_size_sub(skb_frag_t *frag, int delta) { frag->len -= delta; } /** * skb_frag_must_loop - Test if %p is a high memory page * @p: fragment's page */ static inline bool skb_frag_must_loop(struct page *p) { #if defined(CONFIG_HIGHMEM) if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP) || PageHighMem(p)) return true; #endif return false; } /** * skb_frag_foreach_page - loop over pages in a fragment * * @f: skb frag to operate on * @f_off: offset from start of f->netmem * @f_len: length from f_off to loop over * @p: (temp var) current page * @p_off: (temp var) offset from start of current page, * non-zero only on first page. * @p_len: (temp var) length in current page, * < PAGE_SIZE only on first and last page. * @copied: (temp var) length so far, excluding current p_len. * * A fragment can hold a compound page, in which case per-page * operations, notably kmap_atomic, must be called for each * regular page. */ #define skb_frag_foreach_page(f, f_off, f_len, p, p_off, p_len, copied) \ for (p = skb_frag_page(f) + ((f_off) >> PAGE_SHIFT), \ p_off = (f_off) & (PAGE_SIZE - 1), \ p_len = skb_frag_must_loop(p) ? \ min_t(u32, f_len, PAGE_SIZE - p_off) : f_len, \ copied = 0; \ copied < f_len; \ copied += p_len, p++, p_off = 0, \ p_len = min_t(u32, f_len - copied, PAGE_SIZE)) \ /** * struct skb_shared_hwtstamps - hardware time stamps * @hwtstamp: hardware time stamp transformed into duration * since arbitrary point in time * @netdev_data: address/cookie of network device driver used as * reference to actual hardware time stamp * * Software time stamps generated by ktime_get_real() are stored in * skb->tstamp. * * hwtstamps can only be compared against other hwtstamps from * the same device. * * This structure is attached to packets as part of the * &skb_shared_info. Use skb_hwtstamps() to get a pointer. */ struct skb_shared_hwtstamps { union { ktime_t hwtstamp; void *netdev_data; }; }; /* Definitions for tx_flags in struct skb_shared_info */ enum { /* generate hardware time stamp */ SKBTX_HW_TSTAMP_NOBPF = 1 << 0, /* generate software time stamp when queueing packet to NIC */ SKBTX_SW_TSTAMP = 1 << 1, /* device driver is going to provide hardware time stamp */ SKBTX_IN_PROGRESS = 1 << 2, /* generate software time stamp on packet tx completion */ SKBTX_COMPLETION_TSTAMP = 1 << 3, /* determine hardware time stamp based on time or cycles */ SKBTX_HW_TSTAMP_NETDEV = 1 << 5, /* generate software time stamp when entering packet scheduling */ SKBTX_SCHED_TSTAMP = 1 << 6, /* used for bpf extension when a bpf program is loaded */ SKBTX_BPF = 1 << 7, }; #define SKBTX_HW_TSTAMP (SKBTX_HW_TSTAMP_NOBPF | SKBTX_BPF) #define SKBTX_ANY_SW_TSTAMP (SKBTX_SW_TSTAMP | \ SKBTX_SCHED_TSTAMP | \ SKBTX_BPF | \ SKBTX_COMPLETION_TSTAMP) #define SKBTX_ANY_TSTAMP (SKBTX_HW_TSTAMP | \ SKBTX_ANY_SW_TSTAMP) /* Definitions for flags in struct skb_shared_info */ enum { /* use zcopy routines */ SKBFL_ZEROCOPY_ENABLE = BIT(0), /* This indicates at least one fragment might be overwritten * (as in vmsplice(), sendfile() ...) * If we need to compute a TX checksum, we'll need to copy * all frags to avoid possible bad checksum */ SKBFL_SHARED_FRAG = BIT(1), /* segment contains only zerocopy data and should not be * charged to the kernel memory. */ SKBFL_PURE_ZEROCOPY = BIT(2), SKBFL_DONT_ORPHAN = BIT(3), /* page references are managed by the ubuf_info, so it's safe to * use frags only up until ubuf_info is released */ SKBFL_MANAGED_FRAG_REFS = BIT(4), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) #define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) struct ubuf_info_ops { void (*complete)(struct sk_buff *, struct ubuf_info *, bool zerocopy_success); /* has to be compatible with skb_zcopy_set() */ int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg); }; /* * The callback notifies userspace to release buffers when skb DMA is done in * lower device, the skb last reference should be 0 when calling this. * The zerocopy_success argument is true if zero copy transmit occurred, * false on data copy or out of memory error caused by data copy attempt. * The ctx field is used to track device context. * The desc field is used to track userspace buffer index. */ struct ubuf_info { const struct ubuf_info_ops *ops; refcount_t refcnt; u8 flags; }; struct ubuf_info_msgzc { struct ubuf_info ubuf; union { struct { unsigned long desc; void *ctx; }; struct { u32 id; u16 len; u16 zerocopy:1; u32 bytelen; }; }; struct mmpin { struct user_struct *user; unsigned int num_pg; } mmp; }; #define skb_uarg(SKB) ((struct ubuf_info *)(skb_shinfo(SKB)->destructor_arg)) #define uarg_to_msgzc(ubuf_ptr) container_of((ubuf_ptr), struct ubuf_info_msgzc, \ ubuf) int mm_account_pinned_pages(struct mmpin *mmp, size_t size); void mm_unaccount_pinned_pages(struct mmpin *mmp); /* Preserve some data across TX submission and completion. * * Note, this state is stored in the driver. Extending the layout * might need some special care. */ struct xsk_tx_metadata_compl { __u64 *tx_timestamp; }; /* This data is invariant across clones and lives at * the end of the header data, ie. at skb->end. */ struct skb_shared_info { __u8 flags; __u8 meta_len; __u8 nr_frags; __u8 tx_flags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; struct sk_buff *frag_list; union { struct skb_shared_hwtstamps hwtstamps; struct xsk_tx_metadata_compl xsk_meta; }; unsigned int gso_type; u32 tskey; /* * Warning : all fields before dataref are cleared in __alloc_skb() */ atomic_t dataref; union { struct { u32 xdp_frags_size; u32 xdp_frags_truesize; }; /* * Intermediate layers must ensure that destructor_arg * remains valid until skb destructor. */ void *destructor_arg; }; /* must be last field, see pskb_expand_head() */ skb_frag_t frags[MAX_SKB_FRAGS]; }; /** * DOC: dataref and headerless skbs * * Transport layers send out clones of payload skbs they hold for * retransmissions. To allow lower layers of the stack to prepend their headers * we split &skb_shared_info.dataref into two halves. * The lower 16 bits count the overall number of references. * The higher 16 bits indicate how many of the references are payload-only. * skb_header_cloned() checks if skb is allowed to add / write the headers. * * The creator of the skb (e.g. TCP) marks its skb as &sk_buff.nohdr * (via __skb_header_release()). Any clone created from marked skb will get * &sk_buff.hdr_len populated with the available headroom. * If there's the only clone in existence it's able to modify the headroom * at will. The sequence of calls inside the transport layer is:: * * <alloc skb> * skb_reserve() * __skb_header_release() * skb_clone() * // send the clone down the stack * * This is not a very generic construct and it depends on the transport layers * doing the right thing. In practice there's usually only one payload-only skb. * Having multiple payload-only skbs with different lengths of hdr_len is not * possible. The payload-only skbs should never leave their owner. */ #define SKB_DATAREF_SHIFT 16 #define SKB_DATAREF_MASK ((1 << SKB_DATAREF_SHIFT) - 1) enum { SKB_FCLONE_UNAVAILABLE, /* skb has no fclone (from head_cache) */ SKB_FCLONE_ORIG, /* orig skb (from fclone_cache) */ SKB_FCLONE_CLONE, /* companion fclone skb (from fclone_cache) */ }; enum { SKB_GSO_TCPV4 = 1 << 0, /* This indicates the skb is from an untrusted source. */ SKB_GSO_DODGY = 1 << 1, /* This indicates the tcp segment has CWR set. */ SKB_GSO_TCP_ECN = 1 << 2, SKB_GSO_TCP_FIXEDID = 1 << 3, SKB_GSO_TCPV6 = 1 << 4, SKB_GSO_FCOE = 1 << 5, SKB_GSO_GRE = 1 << 6, SKB_GSO_GRE_CSUM = 1 << 7, SKB_GSO_IPXIP4 = 1 << 8, SKB_GSO_IPXIP6 = 1 << 9, SKB_GSO_UDP_TUNNEL = 1 << 10, SKB_GSO_UDP_TUNNEL_CSUM = 1 << 11, SKB_GSO_PARTIAL = 1 << 12, SKB_GSO_TUNNEL_REMCSUM = 1 << 13, SKB_GSO_SCTP = 1 << 14, SKB_GSO_ESP = 1 << 15, SKB_GSO_UDP = 1 << 16, SKB_GSO_UDP_L4 = 1 << 17, SKB_GSO_FRAGLIST = 1 << 18, SKB_GSO_TCP_ACCECN = 1 << 19, }; #if BITS_PER_LONG > 32 #define NET_SKBUFF_DATA_USES_OFFSET 1 #endif #ifdef NET_SKBUFF_DATA_USES_OFFSET typedef unsigned int sk_buff_data_t; #else typedef unsigned char *sk_buff_data_t; #endif enum skb_tstamp_type { SKB_CLOCK_REALTIME, SKB_CLOCK_MONOTONIC, SKB_CLOCK_TAI, __SKB_CLOCK_MAX = SKB_CLOCK_TAI, }; /** * DOC: Basic sk_buff geometry * * struct sk_buff itself is a metadata structure and does not hold any packet * data. All the data is held in associated buffers. * * &sk_buff.head points to the main "head" buffer. The head buffer is divided * into two parts: * * - data buffer, containing headers and sometimes payload; * this is the part of the skb operated on by the common helpers * such as skb_put() or skb_pull(); * - shared info (struct skb_shared_info) which holds an array of pointers * to read-only data in the (page, offset, length) format. * * Optionally &skb_shared_info.frag_list may point to another skb. * * Basic diagram may look like this:: * * --------------- * | sk_buff | * --------------- * ,--------------------------- + head * / ,----------------- + data * / / ,----------- + tail * | | | , + end * | | | | * v v v v * ----------------------------------------------- * | headroom | data | tailroom | skb_shared_info | * ----------------------------------------------- * + [page frag] * + [page frag] * + [page frag] * + [page frag] --------- * + frag_list --> | sk_buff | * --------- * */ /** * struct sk_buff - socket buffer * @next: Next buffer in list * @prev: Previous buffer in list * @tstamp: Time we arrived/left * @skb_mstamp_ns: (aka @tstamp) earliest departure time; start point * for retransmit timer * @rbnode: RB tree node, alternative to next/prev for netem/tcp * @list: queue head * @ll_node: anchor in an llist (eg socket defer_list) * @sk: Socket we are owned by * @dev: Device we arrived on/are leaving by * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here * @_skb_refdst: destination entry (with norefcount bit) * @len: Length of actual data * @data_len: Data length * @mac_len: Length of link layer header * @hdr_len: writable header length of cloned skb * @csum: Checksum (must include start/offset pair) * @csum_start: Offset from skb->head where checksumming should start * @csum_offset: Offset from csum_start where checksum should be stored * @priority: Packet queueing priority * @ignore_df: allow local fragmentation * @cloned: Head may be cloned (check refcnt to be sure) * @ip_summed: Driver fed us an IP checksum * @nohdr: Payload reference only, must not modify header * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs * @inner_protocol_type: whether the inner protocol is * ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO * @remcsum_offload: remote checksum offload is enabled * @offload_fwd_mark: Packet was L2-forwarded in hardware * @offload_l3_fwd_mark: Packet was L3-forwarded in hardware * @tc_skip_classify: do not classify packet. set by IFB device * @tc_at_ingress: used within tc_classify to distinguish in/egress * @redirected: packet was redirected by packet classifier * @from_ingress: packet was redirected from the ingress path * @nf_skip_egress: packet shall skip nf egress - see netfilter_netdev.h * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag * @protocol: Packet protocol from driver * @destructor: Destruct function * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue) * @_sk_redir: socket redirection information for skmsg * @_nfct: Associated connection, if any (with nfctinfo bits) * @skb_iif: ifindex of device we arrived on * @tc_index: Traffic control index * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices * @head_frag: skb was allocated from page fragments, * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @pp_recycle: mark the packet for recycling instead of freeing (implies * page_pool support on driver) * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed * @l4_hash: indicate hash is a canonical 4-tuple hash over transport * ports. * @sw_hash: indicates hash was computed in software stack * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS * @encapsulation: indicates the inner headers in the skbuff are valid * @encap_hdr_csum: software checksum is needed * @csum_valid: checksum is already valid * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL * @csum_complete_sw: checksum was completed by software * @csum_level: indicates the number of consecutive checksums found in * the packet minus one that have been verified as * CHECKSUM_UNNECESSARY (max 3) * @unreadable: indicates that at least 1 of the fragments in this skb is * unreadable. * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required * @tstamp_type: When set, skb->tstamp has the * delivery_time clock base of skb->tstamp. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @alloc_cpu: CPU which did the skb allocation. * @secmark: security marking * @mark: Generic packet mark * @reserved_tailroom: (aka @mark) number of bytes of free space available * at the tail of an sk_buff * @vlan_all: vlan fields (proto & tci) * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_protocol: Protocol (encapsulation) * @inner_ipproto: (aka @inner_protocol) stores ipproto when * skb->inner_protocol_type == ENCAP_TYPE_IPPROTO; * @inner_transport_header: Inner transport layer header (encapsulation) * @inner_network_header: Network layer header (encapsulation) * @inner_mac_header: Link layer header (encapsulation) * @transport_header: Transport layer header * @network_header: Network layer header * @mac_header: Link layer header * @kcov_handle: KCOV remote handle for remote coverage collection * @tail: Tail pointer * @end: End pointer * @head: Head of buffer * @data: Data head pointer * @truesize: Buffer size * @users: User count - see {datagram,tcp}.c * @extensions: allocated extensions, valid if active_extensions is nonzero */ struct sk_buff { union { struct { /* These two members must be first to match sk_buff_head. */ struct sk_buff *next; struct sk_buff *prev; union { struct net_device *dev; /* Some protocols might use this space to store information, * while device pointer would be NULL. * UDP receive path is one user. */ unsigned long dev_scratch; }; }; struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */ struct list_head list; struct llist_node ll_node; }; struct sock *sk; union { ktime_t tstamp; u64 skb_mstamp_ns; /* earliest departure time */ }; /* * This is the control buffer. It is free to use for every * layer. Please put your private variables there. If you * want to keep them across layers you have to do a skb_clone() * first. This is owned by whoever has the skb queued ATM. */ char cb[48] __aligned(8); union { struct { unsigned long _skb_refdst; void (*destructor)(struct sk_buff *skb); }; struct list_head tcp_tsorted_anchor; #ifdef CONFIG_NET_SOCK_MSG unsigned long _sk_redir; #endif }; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) unsigned long _nfct; #endif unsigned int len, data_len; __u16 mac_len, hdr_len; /* Following fields are _not_ copied in __copy_skb_header() * Note that queue_mapping is here mostly to fill a hole. */ __u16 queue_mapping; /* if you move cloned around you also must adapt those constants */ #ifdef __BIG_ENDIAN_BITFIELD #define CLONED_MASK (1 << 7) #else #define CLONED_MASK 1 #endif #define CLONED_OFFSET offsetof(struct sk_buff, __cloned_offset) /* private: */ __u8 __cloned_offset[0]; /* public: */ __u8 cloned:1, nohdr:1, fclone:2, peeked:1, head_frag:1, pfmemalloc:1, pp_recycle:1; /* page_pool recycle indicator */ #ifdef CONFIG_SKB_EXTENSIONS __u8 active_extensions; #endif /* Fields enclosed in headers group are copied * using a single memcpy() in __copy_skb_header() */ struct_group(headers, /* private: */ __u8 __pkt_type_offset[0]; /* public: */ __u8 pkt_type:3; /* see PKT_TYPE_MAX */ __u8 ignore_df:1; __u8 dst_pending_confirm:1; __u8 ip_summed:2; __u8 ooo_okay:1; /* private: */ __u8 __mono_tc_offset[0]; /* public: */ __u8 tstamp_type:2; /* See skb_tstamp_type */ #ifdef CONFIG_NET_XGRESS __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ __u8 tc_skip_classify:1; #endif __u8 remcsum_offload:1; __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 inner_protocol_type:1; __u8 l4_hash:1; __u8 sw_hash:1; #ifdef CONFIG_WIRELESS __u8 wifi_acked_valid:1; __u8 wifi_acked:1; #endif __u8 no_fcs:1; /* Indicates the inner headers are valid in the skbuff. */ __u8 encapsulation:1; __u8 encap_hdr_csum:1; __u8 csum_valid:1; #ifdef CONFIG_IPV6_NDISC_NODETYPE __u8 ndisc_nodetype:2; #endif #if IS_ENABLED(CONFIG_IP_VS) __u8 ipvs_property:1; #endif #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) __u8 nf_trace:1; #endif #ifdef CONFIG_NET_SWITCHDEV __u8 offload_fwd_mark:1; __u8 offload_l3_fwd_mark:1; #endif __u8 redirected:1; #ifdef CONFIG_NET_REDIRECT __u8 from_ingress:1; #endif #ifdef CONFIG_NETFILTER_SKIP_EGRESS __u8 nf_skip_egress:1; #endif #ifdef CONFIG_SKB_DECRYPTED __u8 decrypted:1; #endif __u8 slow_gro:1; #if IS_ENABLED(CONFIG_IP_SCTP) __u8 csum_not_inet:1; #endif __u8 unreadable:1; #if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS) __u16 tc_index; /* traffic control index */ #endif u16 alloc_cpu; union { __wsum csum; struct { __u16 csum_start; __u16 csum_offset; }; }; __u32 priority; int skb_iif; __u32 hash; union { u32 vlan_all; struct { __be16 vlan_proto; __u16 vlan_tci; }; }; #if defined(CONFIG_NET_RX_BUSY_POLL) || defined(CONFIG_XPS) union { unsigned int napi_id; unsigned int sender_cpu; }; #endif #ifdef CONFIG_NETWORK_SECMARK __u32 secmark; #endif union { __u32 mark; __u32 reserved_tailroom; }; union { __be16 inner_protocol; __u8 inner_ipproto; }; __u16 inner_transport_header; __u16 inner_network_header; __u16 inner_mac_header; __be16 protocol; __u16 transport_header; __u16 network_header; __u16 mac_header; #ifdef CONFIG_KCOV u64 kcov_handle; #endif ); /* end headers group */ /* These elements must be at the end, see alloc_skb() for details. */ sk_buff_data_t tail; sk_buff_data_t end; unsigned char *head, *data; unsigned int truesize; refcount_t users; #ifdef CONFIG_SKB_EXTENSIONS /* only usable after checking ->active_extensions != 0 */ struct skb_ext *extensions; #endif }; /* if you move pkt_type around you also must adapt those constants */ #ifdef __BIG_ENDIAN_BITFIELD #define PKT_TYPE_MAX (7 << 5) #else #define PKT_TYPE_MAX 7 #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) /* if you move tc_at_ingress or tstamp_type * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD #define SKB_TSTAMP_TYPE_MASK (3 << 6) #define SKB_TSTAMP_TYPE_RSHIFT (6) #define TC_AT_INGRESS_MASK (1 << 5) #else #define SKB_TSTAMP_TYPE_MASK (3) #define TC_AT_INGRESS_MASK (1 << 2) #endif #define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset) #ifdef __KERNEL__ /* * Handling routines are only of interest to the kernel */ #define SKB_ALLOC_FCLONE 0x01 #define SKB_ALLOC_RX 0x02 #define SKB_ALLOC_NAPI 0x04 /** * skb_pfmemalloc - Test if the skb was allocated from PFMEMALLOC reserves * @skb: buffer */ static inline bool skb_pfmemalloc(const struct sk_buff *skb) { return unlikely(skb->pfmemalloc); } /* * skb might have a dst pointer attached, refcounted or not. * _skb_refdst low order bit is set if refcount was _not_ taken */ #define SKB_DST_NOREF 1UL #define SKB_DST_PTRMASK ~(SKB_DST_NOREF) /** * skb_dst - returns skb dst_entry * @skb: buffer * * Returns: skb dst_entry, regardless of reference taken or not. */ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) { /* If refdst was not refcounted, check we still are in a * rcu_read_lock section */ WARN_ON((skb->_skb_refdst & SKB_DST_NOREF) && !rcu_read_lock_held() && !rcu_read_lock_bh_held()); return (struct dst_entry *)(skb->_skb_refdst & SKB_DST_PTRMASK); } /** * skb_dst_set - sets skb dst * @skb: buffer * @dst: dst entry * * Sets skb dst, assuming a reference was taken on dst and should * be released by skb_dst_drop() */ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) { skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst; } /** * skb_dst_set_noref - sets skb dst, hopefully, without taking reference * @skb: buffer * @dst: dst entry * * Sets skb dst, assuming a reference was not taken on dst. * If dst entry is cached, we do not take reference and dst_release * will be avoided by refdst_drop. If dst entry is not cached, we take * reference, so that last dst_release can destroy the dst immediately. */ static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) { WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); skb->slow_gro |= !!dst; skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; } /** * skb_dst_is_noref - Test if skb dst isn't refcounted * @skb: buffer */ static inline bool skb_dst_is_noref(const struct sk_buff *skb) { return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } /* For mangling skb->pkt_type from user space side from applications * such as nft, tc, etc, we only allow a conservative subset of * possible pkt_types to be set. */ static inline bool skb_pkt_type_ok(u32 ptype) { return ptype <= PACKET_OTHERHOST; } /** * skb_napi_id - Returns the skb's NAPI id * @skb: buffer */ static inline unsigned int skb_napi_id(const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL return skb->napi_id; #else return 0; #endif } static inline bool skb_wifi_acked_valid(const struct sk_buff *skb) { #ifdef CONFIG_WIRELESS return skb->wifi_acked_valid; #else return 0; #endif } /** * skb_unref - decrement the skb's reference count * @skb: buffer * * Returns: true if we can free the skb. */ static inline bool skb_unref(struct sk_buff *skb) { if (unlikely(!skb)) return false; if (!IS_ENABLED(CONFIG_DEBUG_NET) && likely(refcount_read(&skb->users) == 1)) smp_rmb(); else if (likely(!refcount_dec_and_test(&skb->users))) return false; return true; } static inline bool skb_data_unref(const struct sk_buff *skb, struct skb_shared_info *shinfo) { int bias; if (!skb->cloned) return true; bias = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1; if (atomic_read(&shinfo->dataref) == bias) smp_rmb(); else if (atomic_sub_return(bias, &shinfo->dataref)) return false; return true; } void __fix_address sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason reason); static inline void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) { sk_skb_reason_drop(NULL, skb, reason); } /** * kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason * @skb: buffer to free */ static inline void kfree_skb(struct sk_buff *skb) { kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } void skb_release_head_state(struct sk_buff *skb); void kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); static inline void kfree_skb_list(struct sk_buff *segs) { kfree_skb_list_reason(segs, SKB_DROP_REASON_NOT_SPECIFIED); } #ifdef CONFIG_TRACEPOINTS void consume_skb(struct sk_buff *skb); #else static inline void consume_skb(struct sk_buff *skb) { return kfree_skb(skb); } #endif void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); void kfree_skb_partial(struct sk_buff *skb, bool head_stolen); bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize); struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb_around(struct sk_buff *skb, void *data, unsigned int frag_size); void skb_attempt_defer_free(struct sk_buff *skb); u32 napi_skb_cache_get_bulk(void **skbs, u32 n); struct sk_buff *napi_build_skb(void *data, unsigned int frag_size); struct sk_buff *slab_build_skb(void *data); /** * alloc_skb - allocate a network buffer * @size: size to allocate * @priority: allocation mask * * This function is a convenient wrapper around __alloc_skb(). */ static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, 0, NUMA_NO_NODE); } struct sk_buff *alloc_skb_with_frags(unsigned long header_len, unsigned long data_len, int max_page_order, int *errcode, gfp_t gfp_mask); struct sk_buff *alloc_skb_for_msg(struct sk_buff *first); /* Layout of fast clones : [skb1][skb2][fclone_ref] */ struct sk_buff_fclones { struct sk_buff skb1; struct sk_buff skb2; refcount_t fclone_ref; }; /** * skb_fclone_busy - check if fclone is busy * @sk: socket * @skb: buffer * * Returns: true if skb is a fast clone, and its clone is not freed. * Some drivers call skb_orphan() in their ndo_start_xmit(), * so we also check that didn't happen. */ static inline bool skb_fclone_busy(const struct sock *sk, const struct sk_buff *skb) { const struct sk_buff_fclones *fclones; fclones = container_of(skb, struct sk_buff_fclones, skb1); return skb->fclone == SKB_FCLONE_ORIG && refcount_read(&fclones->fclone_ref) > 1 && READ_ONCE(fclones->skb2.sk) == sk; } /** * alloc_skb_fclone - allocate a network buffer from fclone cache * @size: size to allocate * @priority: allocation mask * * This function is a convenient wrapper around __alloc_skb(). */ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, gfp_t priority) { return __alloc_skb(size, priority, SKB_ALLOC_FCLONE, NUMA_NO_NODE); } struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); void skb_headers_offset_update(struct sk_buff *skb, int off); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); void skb_copy_header(struct sk_buff *new, const struct sk_buff *old); struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t priority); struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone); static inline struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask) { return __pskb_copy_fclone(skb, headroom, gfp_mask, false); } int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, gfp_t gfp_mask); struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom); struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); int __must_check skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int __must_check skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error); /** * skb_pad - zero pad the tail of an skb * @skb: buffer to pad * @pad: space to pad * * Ensure that a buffer is followed by a padding area that is zero * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * * May return error in out of memory cases. The skb is freed on error. */ static inline int skb_pad(struct sk_buff *skb, int pad) { return __skb_pad(skb, pad, true); } #define dev_kfree_skb(a) consume_skb(a) int skb_append_pagefrags(struct sk_buff *skb, struct page *page, int offset, size_t size, size_t max_frags); struct skb_seq_state { __u32 lower_offset; __u32 upper_offset; __u32 frag_idx; __u32 stepped_offset; struct sk_buff *root_skb; struct sk_buff *cur_skb; __u8 *frag_data; __u32 frag_off; }; void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, unsigned int to, struct skb_seq_state *st); unsigned int skb_seq_read(unsigned int consumed, const u8 **data, struct skb_seq_state *st); void skb_abort_seq_read(struct skb_seq_state *st); int skb_copy_seq_read(struct skb_seq_state *st, int offset, void *to, int len); unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config); /* * Packet hash types specify the type of hash in skb_set_hash. * * Hash types refer to the protocol layer addresses which are used to * construct a packet's hash. The hashes are used to differentiate or identify * flows of the protocol layer for the hash type. Hash types are either * layer-2 (L2), layer-3 (L3), or layer-4 (L4). * * Properties of hashes: * * 1) Two packets in different flows have different hash values * 2) Two packets in the same flow should have the same hash value * * A hash at a higher layer is considered to be more specific. A driver should * set the most specific hash possible. * * A driver cannot indicate a more specific hash than the layer at which a hash * was computed. For instance an L3 hash cannot be set as an L4 hash. * * A driver may indicate a hash level which is less specific than the * actual layer the hash was computed on. For instance, a hash computed * at L4 may be considered an L3 hash. This should only be done if the * driver can't unambiguously determine that the HW computed the hash at * the higher layer. Note that the "should" in the second property above * permits this. */ enum pkt_hash_types { PKT_HASH_TYPE_NONE, /* Undefined type */ PKT_HASH_TYPE_L2, /* Input: src_MAC, dest_MAC */ PKT_HASH_TYPE_L3, /* Input: src_IP, dst_IP */ PKT_HASH_TYPE_L4, /* Input: src_IP, dst_IP, src_port, dst_port */ }; static inline void skb_clear_hash(struct sk_buff *skb) { skb->hash = 0; skb->sw_hash = 0; skb->l4_hash = 0; } static inline void skb_clear_hash_if_not_l4(struct sk_buff *skb) { if (!skb->l4_hash) skb_clear_hash(skb); } static inline void __skb_set_hash(struct sk_buff *skb, __u32 hash, bool is_sw, bool is_l4) { skb->l4_hash = is_l4; skb->sw_hash = is_sw; skb->hash = hash; } static inline void skb_set_hash(struct sk_buff *skb, __u32 hash, enum pkt_hash_types type) { /* Used by drivers to set hash from HW */ __skb_set_hash(skb, hash, false, type == PKT_HASH_TYPE_L4); } static inline void __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) { __skb_set_hash(skb, hash, true, is_l4); } u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb); static inline u32 __skb_get_hash_symmetric(const struct sk_buff *skb) { return __skb_get_hash_symmetric_net(NULL, skb); } void __skb_get_hash_net(const struct net *net, struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen); __be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, const void *data, int hlen_proto); void skb_flow_dissector_init(struct flow_dissector *flow_dissector, const struct flow_dissector_key *key, unsigned int key_count); struct bpf_flow_dissector; u32 bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen, unsigned int flags); bool __skb_flow_dissect(const struct net *net, const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags); static inline bool skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, unsigned int flags) { return __skb_flow_dissect(NULL, skb, flow_dissector, target_container, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, struct flow_keys *flow, unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(NULL, skb, &flow_keys_dissector, flow, NULL, 0, 0, 0, flags); } static inline bool skb_flow_dissect_flow_keys_basic(const struct net *net, const struct sk_buff *skb, struct flow_keys_basic *flow, const void *data, __be16 proto, int nhoff, int hlen, unsigned int flags) { memset(flow, 0, sizeof(*flow)); return __skb_flow_dissect(net, skb, &flow_keys_basic_dissector, flow, data, proto, nhoff, hlen, flags); } void skb_flow_dissect_meta(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); /* Gets a skb connection tracking info, ctinfo map should be a * map of mapsize to translate enum ip_conntrack_info states * to user states. */ void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize, bool post_ct, u16 zone); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); static inline __u32 skb_get_hash_net(const struct net *net, struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) __skb_get_hash_net(net, skb); return skb->hash; } static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) __skb_get_hash_net(NULL, skb); return skb->hash; } static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 *fl6) { if (!skb->l4_hash && !skb->sw_hash) { struct flow_keys keys; __u32 hash = __get_hash_from_flowi6(fl6, &keys); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } return skb->hash; } __u32 skb_get_hash_perturb(const struct sk_buff *skb, const siphash_key_t *perturb); static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) { return skb->hash; } static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) { to->hash = from->hash; to->sw_hash = from->sw_hash; to->l4_hash = from->l4_hash; }; static inline int skb_cmp_decrypted(const struct sk_buff *skb1, const struct sk_buff *skb2) { #ifdef CONFIG_SKB_DECRYPTED return skb2->decrypted - skb1->decrypted; #else return 0; #endif } static inline bool skb_is_decrypted(const struct sk_buff *skb) { #ifdef CONFIG_SKB_DECRYPTED return skb->decrypted; #else return false; #endif } static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { #ifdef CONFIG_SKB_DECRYPTED to->decrypted = from->decrypted; #endif } #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->head + skb->end; } static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end; } static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) { skb->end = offset; } #else static inline unsigned char *skb_end_pointer(const struct sk_buff *skb) { return skb->end; } static inline unsigned int skb_end_offset(const struct sk_buff *skb) { return skb->end - skb->head; } static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) { skb->end = skb->head + offset; } #endif extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops; struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg, bool devmem); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); struct net_devmem_dmabuf_binding; int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, struct iov_iter *from, size_t length, struct net_devmem_dmabuf_binding *binding); int zerocopy_fill_skb_from_iter(struct sk_buff *skb, struct iov_iter *from, size_t length); static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len, NULL); } int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, struct msghdr *msg, int len, struct ubuf_info *uarg, struct net_devmem_dmabuf_binding *binding); /* Internal */ #define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB))) static inline struct skb_shared_hwtstamps *skb_hwtstamps(struct sk_buff *skb) { return &skb_shinfo(skb)->hwtstamps; } static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) { bool is_zcopy = skb && skb_shinfo(skb)->flags & SKBFL_ZEROCOPY_ENABLE; return is_zcopy ? skb_uarg(skb) : NULL; } static inline bool skb_zcopy_pure(const struct sk_buff *skb) { return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY; } static inline bool skb_zcopy_managed(const struct sk_buff *skb) { return skb_shinfo(skb)->flags & SKBFL_MANAGED_FRAG_REFS; } static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1, const struct sk_buff *skb2) { return skb_zcopy_pure(skb1) == skb_zcopy_pure(skb2); } static inline void net_zcopy_get(struct ubuf_info *uarg) { refcount_inc(&uarg->refcnt); } static inline void skb_zcopy_init(struct sk_buff *skb, struct ubuf_info *uarg) { skb_shinfo(skb)->destructor_arg = uarg; skb_shinfo(skb)->flags |= uarg->flags; } static inline void skb_zcopy_set(struct sk_buff *skb, struct ubuf_info *uarg, bool *have_ref) { if (skb && uarg && !skb_zcopy(skb)) { if (unlikely(have_ref && *have_ref)) *have_ref = false; else net_zcopy_get(uarg); skb_zcopy_init(skb, uarg); } } static inline void skb_zcopy_set_nouarg(struct sk_buff *skb, void *val) { skb_shinfo(skb)->destructor_arg = (void *)((uintptr_t) val | 0x1UL); skb_shinfo(skb)->flags |= SKBFL_ZEROCOPY_FRAG; } static inline bool skb_zcopy_is_nouarg(struct sk_buff *skb) { return (uintptr_t) skb_shinfo(skb)->destructor_arg & 0x1UL; } static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) { return (void *)((uintptr_t) skb_shinfo(skb)->destructor_arg & ~0x1UL); } static inline void net_zcopy_put(struct ubuf_info *uarg) { if (uarg) uarg->ops->complete(NULL, uarg, true); } static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { if (uarg->ops == &msg_zerocopy_ubuf_ops) msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) net_zcopy_put(uarg); } } /* Release a reference on a zerocopy structure */ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) { struct ubuf_info *uarg = skb_zcopy(skb); if (uarg) { if (!skb_zcopy_is_nouarg(skb)) uarg->ops->complete(skb, uarg, zerocopy_success); skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } } void __skb_zcopy_downgrade_managed(struct sk_buff *skb); static inline void skb_zcopy_downgrade_managed(struct sk_buff *skb) { if (unlikely(skb_zcopy_managed(skb))) __skb_zcopy_downgrade_managed(skb); } /* Return true if frags in this skb are readable by the host. */ static inline bool skb_frags_readable(const struct sk_buff *skb) { return !skb->unreadable; } static inline void skb_mark_not_on_list(struct sk_buff *skb) { skb->next = NULL; } static inline void skb_poison_list(struct sk_buff *skb) { #ifdef CONFIG_DEBUG_NET skb->next = SKB_LIST_POISON_NEXT; #endif } /* Iterate through singly-linked GSO fragments of an skb. */ #define skb_list_walk_safe(first, skb, next_skb) \ for ((skb) = (first), (next_skb) = (skb) ? (skb)->next : NULL; (skb); \ (skb) = (next_skb), (next_skb) = (skb) ? (skb)->next : NULL) static inline void skb_list_del_init(struct sk_buff *skb) { __list_del_entry(&skb->list); skb_mark_not_on_list(skb); } /** * skb_queue_empty - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. */ static inline int skb_queue_empty(const struct sk_buff_head *list) { return list->next == (const struct sk_buff *) list; } /** * skb_queue_empty_lockless - check if a queue is empty * @list: queue head * * Returns true if the queue is empty, false otherwise. * This variant can be used in lockless contexts. */ static inline bool skb_queue_empty_lockless(const struct sk_buff_head *list) { return READ_ONCE(list->next) == (const struct sk_buff *) list; } /** * skb_queue_is_last - check if skb is the last entry in the queue * @list: queue head * @skb: buffer * * Returns true if @skb is the last buffer on the list. */ static inline bool skb_queue_is_last(const struct sk_buff_head *list, const struct sk_buff *skb) { return skb->next == (const struct sk_buff *) list; } /** * skb_queue_is_first - check if skb is the first entry in the queue * @list: queue head * @skb: buffer * * Returns true if @skb is the first buffer on the list. */ static inline bool skb_queue_is_first(const struct sk_buff_head *list, const struct sk_buff *skb) { return skb->prev == (const struct sk_buff *) list; } /** * skb_queue_next - return the next packet in the queue * @list: queue head * @skb: current buffer * * Return the next packet in @list after @skb. It is only valid to * call this if skb_queue_is_last() evaluates to false. */ static inline struct sk_buff *skb_queue_next(const struct sk_buff_head *list, const struct sk_buff *skb) { /* This BUG_ON may seem severe, but if we just return then we * are going to dereference garbage. */ BUG_ON(skb_queue_is_last(list, skb)); return skb->next; } /** * skb_queue_prev - return the prev packet in the queue * @list: queue head * @skb: current buffer * * Return the prev packet in @list before @skb. It is only valid to * call this if skb_queue_is_first() evaluates to false. */ static inline struct sk_buff *skb_queue_prev(const struct sk_buff_head *list, const struct sk_buff *skb) { /* This BUG_ON may seem severe, but if we just return then we * are going to dereference garbage. */ BUG_ON(skb_queue_is_first(list, skb)); return skb->prev; } /** * skb_get - reference buffer * @skb: buffer to reference * * Makes another reference to a socket buffer and returns a pointer * to the buffer. */ static inline struct sk_buff *skb_get(struct sk_buff *skb) { refcount_inc(&skb->users); return skb; } /* * If users == 1, we are the only owner and can avoid redundant atomic changes. */ /** * skb_cloned - is the buffer a clone * @skb: buffer to check * * Returns true if the buffer was generated with skb_clone() and is * one of multiple shared copies of the buffer. Cloned buffers are * shared data so must not be written to under normal circumstances. */ static inline int skb_cloned(const struct sk_buff *skb) { return skb->cloned && (atomic_read(&skb_shinfo(skb)->dataref) & SKB_DATAREF_MASK) != 1; } static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); return 0; } /* This variant of skb_unclone() makes sure skb->truesize * and skb_end_offset() are not changed, whenever a new skb->head is needed. * * Indeed there is no guarantee that ksize(kmalloc(X)) == ksize(kmalloc(X)) * when various debugging features are in place. */ int __skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri); static inline int skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) return __skb_unclone_keeptruesize(skb, pri); return 0; } /** * skb_header_cloned - is the header a clone * @skb: buffer to check * * Returns true if modifying the header part of the buffer requires * the data to be copied. */ static inline int skb_header_cloned(const struct sk_buff *skb) { int dataref; if (!skb->cloned) return 0; dataref = atomic_read(&skb_shinfo(skb)->dataref); dataref = (dataref & SKB_DATAREF_MASK) - (dataref >> SKB_DATAREF_SHIFT); return dataref != 1; } static inline int skb_header_unclone(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_header_cloned(skb)) return pskb_expand_head(skb, 0, 0, pri); return 0; } /** * __skb_header_release() - allow clones to use the headroom * @skb: buffer to operate on * * See "DOC: dataref and headerless skbs". */ static inline void __skb_header_release(struct sk_buff *skb) { skb->nohdr = 1; atomic_set(&skb_shinfo(skb)->dataref, 1 + (1 << SKB_DATAREF_SHIFT)); } /** * skb_shared - is the buffer shared * @skb: buffer to check * * Returns true if more than one person has a reference to this * buffer. */ static inline int skb_shared(const struct sk_buff *skb) { return refcount_read(&skb->users) != 1; } /** * skb_share_check - check if buffer is shared and if so clone it * @skb: buffer to check * @pri: priority for memory allocation * * If the buffer is shared the buffer is cloned and the old copy * drops a reference. A new clone with a single reference is returned. * If the buffer is not shared the original buffer is returned. When * being called from interrupt status or with spinlocks held pri must * be GFP_ATOMIC. * * NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, pri); if (likely(nskb)) consume_skb(skb); else kfree_skb(skb); skb = nskb; } return skb; } /* * Copy shared buffers into a new sk_buff. We effectively do COW on * packets to handle cases where we have a local reader and forward * and a couple of other messy ones. The normal one is tcpdumping * a packet that's being forwarded. */ /** * skb_unshare - make a copy of a shared buffer * @skb: buffer to check * @pri: priority for memory allocation * * If the socket buffer is a clone then this function creates a new * copy of the data, drops a reference count on the old copy and returns * the new copy with the reference count at 1. If the buffer is not a clone * the original buffer is returned. When called with a spinlock held or * from interrupt state @pri must be %GFP_ATOMIC * * %NULL is returned on a memory allocation failure. */ static inline struct sk_buff *skb_unshare(struct sk_buff *skb, gfp_t pri) { might_sleep_if(gfpflags_allow_blocking(pri)); if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, pri); /* Free our shared copy */ if (likely(nskb)) consume_skb(skb); else kfree_skb(skb); skb = nskb; } return skb; } /** * skb_peek - peek at the head of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the head element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek(const struct sk_buff_head *list_) { struct sk_buff *skb = list_->next; if (skb == (struct sk_buff *)list_) skb = NULL; return skb; } /** * __skb_peek - peek at the head of a non-empty &sk_buff_head * @list_: list to peek at * * Like skb_peek(), but the caller knows that the list is not empty. */ static inline struct sk_buff *__skb_peek(const struct sk_buff_head *list_) { return list_->next; } /** * skb_peek_next - peek skb following the given one from a queue * @skb: skb to start from * @list_: list to peek at * * Returns %NULL when the end of the list is met or a pointer to the * next element. The reference count is not incremented and the * reference is therefore volatile. Use with caution. */ static inline struct sk_buff *skb_peek_next(struct sk_buff *skb, const struct sk_buff_head *list_) { struct sk_buff *next = skb->next; if (next == (struct sk_buff *)list_) next = NULL; return next; } /** * skb_peek_tail - peek at the tail of an &sk_buff_head * @list_: list to peek at * * Peek an &sk_buff. Unlike most other operations you _MUST_ * be careful with this one. A peek leaves the buffer on the * list and someone else may run off with it. You must hold * the appropriate locks or have a private queue to do this. * * Returns %NULL for an empty list or a pointer to the tail element. * The reference count is not incremented and the reference is therefore * volatile. Use with caution. */ static inline struct sk_buff *skb_peek_tail(const struct sk_buff_head *list_) { struct sk_buff *skb = READ_ONCE(list_->prev); if (skb == (struct sk_buff *)list_) skb = NULL; return skb; } /** * skb_queue_len - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. */ static inline __u32 skb_queue_len(const struct sk_buff_head *list_) { return list_->qlen; } /** * skb_queue_len_lockless - get queue length * @list_: list to measure * * Return the length of an &sk_buff queue. * This variant can be used in lockless contexts. */ static inline __u32 skb_queue_len_lockless(const struct sk_buff_head *list_) { return READ_ONCE(list_->qlen); } /** * __skb_queue_head_init - initialize non-spinlock portions of sk_buff_head * @list: queue to initialize * * This initializes only the list and queue length aspects of * an sk_buff_head object. This allows to initialize the list * aspects of an sk_buff_head without reinitializing things like * the spinlock. It can also be used for on-stack sk_buff_head * objects where the spinlock is known to not be used. */ static inline void __skb_queue_head_init(struct sk_buff_head *list) { list->prev = list->next = (struct sk_buff *)list; list->qlen = 0; } /* * This function creates a split out lock class for each invocation; * this is needed for now since a whole lot of users of the skb-queue * infrastructure in drivers have different locking usage (in hardirq) * than the networking core (in softirq only). In the long run either the * network layer or drivers should need annotation to consolidate the * main types of usage into 3 classes. */ static inline void skb_queue_head_init(struct sk_buff_head *list) { spin_lock_init(&list->lock); __skb_queue_head_init(list); } static inline void skb_queue_head_init_class(struct sk_buff_head *list, struct lock_class_key *class) { skb_queue_head_init(list); lockdep_set_class(&list->lock, class); } /* * Insert an sk_buff on a list. * * The "__skb_xxxx()" functions are the non-atomic ones that * can only be called with interrupts disabled. */ static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) { /* See skb_queue_empty_lockless() and skb_peek_tail() * for the opposite READ_ONCE() */ WRITE_ONCE(newsk->next, next); WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(((struct sk_buff_list *)next)->prev, newsk); WRITE_ONCE(((struct sk_buff_list *)prev)->next, newsk); WRITE_ONCE(list->qlen, list->qlen + 1); } static inline void __skb_queue_splice(const struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *next) { struct sk_buff *first = list->next; struct sk_buff *last = list->prev; WRITE_ONCE(first->prev, prev); WRITE_ONCE(prev->next, first); WRITE_ONCE(last->next, next); WRITE_ONCE(next->prev, last); } /** * skb_queue_splice - join two skb lists, this is designed for stacks * @list: the new list to add * @head: the place to add it in the first list */ static inline void skb_queue_splice(const struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, (struct sk_buff *) head, head->next); head->qlen += list->qlen; } } /** * skb_queue_splice_init - join two skb lists and reinitialise the emptied list * @list: the new list to add * @head: the place to add it in the first list * * The list at @list is reinitialised */ static inline void skb_queue_splice_init(struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, (struct sk_buff *) head, head->next); head->qlen += list->qlen; __skb_queue_head_init(list); } } /** * skb_queue_splice_tail - join two skb lists, each list being a queue * @list: the new list to add * @head: the place to add it in the first list */ static inline void skb_queue_splice_tail(const struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head); head->qlen += list->qlen; } } /** * skb_queue_splice_tail_init - join two skb lists and reinitialise the emptied list * @list: the new list to add * @head: the place to add it in the first list * * Each of the lists is a queue. * The list at @list is reinitialised */ static inline void skb_queue_splice_tail_init(struct sk_buff_head *list, struct sk_buff_head *head) { if (!skb_queue_empty(list)) { __skb_queue_splice(list, head->prev, (struct sk_buff *) head); head->qlen += list->qlen; __skb_queue_head_init(list); } } /** * __skb_queue_after - queue a buffer at the list head * @list: list to use * @prev: place after this buffer * @newsk: buffer to queue * * Queue a buffer int the middle of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_after(struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *newsk) { __skb_insert(newsk, prev, ((struct sk_buff_list *)prev)->next, list); } void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head *list); static inline void __skb_queue_before(struct sk_buff_head *list, struct sk_buff *next, struct sk_buff *newsk) { __skb_insert(newsk, ((struct sk_buff_list *)next)->prev, next, list); } /** * __skb_queue_head - queue a buffer at the list head * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the start of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_after(list, (struct sk_buff *)list, newsk); } void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk); /** * __skb_queue_tail - queue a buffer at the list tail * @list: list to use * @newsk: buffer to queue * * Queue a buffer at the end of a list. This function takes no locks * and you must therefore hold required locks before calling it. * * A buffer cannot be placed on two lists at the same time. */ static inline void __skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_before(list, (struct sk_buff *)list, newsk); } void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk); /* * remove sk_buff from list. _Must_ be called atomically, and with * the list known.. */ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list); static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { struct sk_buff *next, *prev; WRITE_ONCE(list->qlen, list->qlen - 1); next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; WRITE_ONCE(next->prev, prev); WRITE_ONCE(prev->next, next); } /** * __skb_dequeue - remove from the head of the queue * @list: list to dequeue from * * Remove the head of the list. This function does not take any locks * so must be used with appropriate locks held only. The head item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek(list); if (skb) __skb_unlink(skb, list); return skb; } struct sk_buff *skb_dequeue(struct sk_buff_head *list); /** * __skb_dequeue_tail - remove from the tail of the queue * @list: list to dequeue from * * Remove the tail of the list. This function does not take any locks * so must be used with appropriate locks held only. The tail item is * returned or %NULL if the list is empty. */ static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek_tail(list); if (skb) __skb_unlink(skb, list); return skb; } struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list); static inline bool skb_is_nonlinear(const struct sk_buff *skb) { return skb->data_len; } static inline unsigned int skb_headlen(const struct sk_buff *skb) { return skb->len - skb->data_len; } static inline unsigned int __skb_pagelen(const struct sk_buff *skb) { unsigned int i, len = 0; for (i = skb_shinfo(skb)->nr_frags - 1; (int)i >= 0; i--) len += skb_frag_size(&skb_shinfo(skb)->frags[i]); return len; } static inline unsigned int skb_pagelen(const struct sk_buff *skb) { return skb_headlen(skb) + __skb_pagelen(skb); } static inline void skb_frag_fill_netmem_desc(skb_frag_t *frag, netmem_ref netmem, int off, int size) { frag->netmem = netmem; frag->offset = off; skb_frag_size_set(frag, size); } static inline void skb_frag_fill_page_desc(skb_frag_t *frag, struct page *page, int off, int size) { skb_frag_fill_netmem_desc(frag, page_to_netmem(page), off, size); } static inline void __skb_fill_netmem_desc_noacc(struct skb_shared_info *shinfo, int i, netmem_ref netmem, int off, int size) { skb_frag_t *frag = &shinfo->frags[i]; skb_frag_fill_netmem_desc(frag, netmem, off, size); } static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo, int i, struct page *page, int off, int size) { __skb_fill_netmem_desc_noacc(shinfo, i, page_to_netmem(page), off, size); } /** * skb_len_add - adds a number to len fields of skb * @skb: buffer to add len to * @delta: number of bytes to add */ static inline void skb_len_add(struct sk_buff *skb, int delta) { skb->len += delta; skb->data_len += delta; skb->truesize += delta; } /** * __skb_fill_netmem_desc - initialise a fragment in an skb * @skb: buffer containing fragment to be initialised * @i: fragment index to initialise * @netmem: the netmem to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * Initialises the @i'th fragment of @skb to point to &size bytes at * offset @off within @page. * * Does not take any additional reference on the fragment. */ static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { struct page *page; __skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size); if (netmem_is_net_iov(netmem)) { skb->unreadable = true; return; } page = netmem_to_page(netmem); /* Propagate page pfmemalloc to the skb if we can. The problem is * that not all callers have unique ownership of the page but rely * on page_is_pfmemalloc doing the right thing(tm). */ page = compound_head(page); if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } static inline void __skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { __skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } static inline void skb_fill_netmem_desc(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size) { __skb_fill_netmem_desc(skb, i, netmem, off, size); skb_shinfo(skb)->nr_frags = i + 1; } /** * skb_fill_page_desc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise * @page: the page to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * As per __skb_fill_page_desc() -- initialises the @i'th fragment of * @skb to point to @size bytes at offset @off within @page. In * addition updates @skb such that @i is the last fragment. * * Does not take any additional reference on the fragment. */ static inline void skb_fill_page_desc(struct sk_buff *skb, int i, struct page *page, int off, int size) { skb_fill_netmem_desc(skb, i, page_to_netmem(page), off, size); } /** * skb_fill_page_desc_noacc - initialise a paged fragment in an skb * @skb: buffer containing fragment to be initialised * @i: paged fragment index to initialise * @page: the page to use for this fragment * @off: the offset to the data with @page * @size: the length of the data * * Variant of skb_fill_page_desc() which does not deal with * pfmemalloc, if page is not owned by us. */ static inline void skb_fill_page_desc_noacc(struct sk_buff *skb, int i, struct page *page, int off, int size) { struct skb_shared_info *shinfo = skb_shinfo(skb); __skb_fill_page_desc_noacc(shinfo, i, page, off, size); shinfo->nr_frags = i + 1; } void skb_add_rx_frag_netmem(struct sk_buff *skb, int i, netmem_ref netmem, int off, int size, unsigned int truesize); static inline void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size, unsigned int truesize) { skb_add_rx_frag_netmem(skb, i, page_to_netmem(page), off, size, truesize); } void skb_coalesce_rx_frag(struct sk_buff *skb, int i, int size, unsigned int truesize); #define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb)) #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->head + skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data - skb->head; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb_reset_tail_pointer(skb); skb->tail += offset; } #else /* NET_SKBUFF_DATA_USES_OFFSET */ static inline unsigned char *skb_tail_pointer(const struct sk_buff *skb) { return skb->tail; } static inline void skb_reset_tail_pointer(struct sk_buff *skb) { skb->tail = skb->data; } static inline void skb_set_tail_pointer(struct sk_buff *skb, const int offset) { skb->tail = skb->data + offset; } #endif /* NET_SKBUFF_DATA_USES_OFFSET */ static inline void skb_assert_len(struct sk_buff *skb) { #ifdef CONFIG_DEBUG_NET if (WARN_ONCE(!skb->len, "%s\n", __func__)) DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); #endif /* CONFIG_DEBUG_NET */ } #if defined(CONFIG_FAIL_SKB_REALLOC) void skb_might_realloc(struct sk_buff *skb); #else static inline void skb_might_realloc(struct sk_buff *skb) {} #endif /* * Add data to an sk_buff */ void *pskb_put(struct sk_buff *skb, struct sk_buff *tail, int len); void *skb_put(struct sk_buff *skb, unsigned int len); static inline void *__skb_put(struct sk_buff *skb, unsigned int len) { void *tmp = skb_tail_pointer(skb); SKB_LINEAR_ASSERT(skb); skb->tail += len; skb->len += len; return tmp; } static inline void *__skb_put_zero(struct sk_buff *skb, unsigned int len) { void *tmp = __skb_put(skb, len); memset(tmp, 0, len); return tmp; } static inline void *__skb_put_data(struct sk_buff *skb, const void *data, unsigned int len) { void *tmp = __skb_put(skb, len); memcpy(tmp, data, len); return tmp; } static inline void __skb_put_u8(struct sk_buff *skb, u8 val) { *(u8 *)__skb_put(skb, 1) = val; } static inline void *skb_put_zero(struct sk_buff *skb, unsigned int len) { void *tmp = skb_put(skb, len); memset(tmp, 0, len); return tmp; } static inline void *skb_put_data(struct sk_buff *skb, const void *data, unsigned int len) { void *tmp = skb_put(skb, len); memcpy(tmp, data, len); return tmp; } static inline void skb_put_u8(struct sk_buff *skb, u8 val) { *(u8 *)skb_put(skb, 1) = val; } void *skb_push(struct sk_buff *skb, unsigned int len); static inline void *__skb_push(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb->data -= len; skb->len += len; return skb->data; } void *skb_pull(struct sk_buff *skb, unsigned int len); static inline void *__skb_pull(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb->len -= len; if (unlikely(skb->len < skb->data_len)) { #if defined(CONFIG_DEBUG_NET) skb->len += len; pr_err("__skb_pull(len=%u)\n", len); skb_dump(KERN_ERR, skb, false); #endif BUG(); } return skb->data += len; } static inline void *skb_pull_inline(struct sk_buff *skb, unsigned int len) { return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len); } void *skb_pull_data(struct sk_buff *skb, size_t len); void *__pskb_pull_tail(struct sk_buff *skb, int delta); static inline enum skb_drop_reason pskb_may_pull_reason(struct sk_buff *skb, unsigned int len) { DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); skb_might_realloc(skb); if (likely(len <= skb_headlen(skb))) return SKB_NOT_DROPPED_YET; if (unlikely(len > skb->len)) return SKB_DROP_REASON_PKT_TOO_SMALL; if (unlikely(!__pskb_pull_tail(skb, len - skb_headlen(skb)))) return SKB_DROP_REASON_NOMEM; return SKB_NOT_DROPPED_YET; } static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET; } static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) { if (!pskb_may_pull(skb, len)) return NULL; skb->len -= len; return skb->data += len; } void skb_condense(struct sk_buff *skb); /** * skb_headroom - bytes at buffer head * @skb: buffer to check * * Return the number of bytes of free space at the head of an &sk_buff. */ static inline unsigned int skb_headroom(const struct sk_buff *skb) { return skb->data - skb->head; } /** * skb_tailroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff */ static inline int skb_tailroom(const struct sk_buff *skb) { return skb_is_nonlinear(skb) ? 0 : skb->end - skb->tail; } /** * skb_availroom - bytes at buffer end * @skb: buffer to check * * Return the number of bytes of free space at the tail of an sk_buff * allocated by sk_stream_alloc() */ static inline int skb_availroom(const struct sk_buff *skb) { if (skb_is_nonlinear(skb)) return 0; return skb->end - skb->tail - skb->reserved_tailroom; } /** * skb_reserve - adjust headroom * @skb: buffer to alter * @len: bytes to move * * Increase the headroom of an empty &sk_buff by reducing the tail * room. This is only allowed for an empty buffer. */ static inline void skb_reserve(struct sk_buff *skb, int len) { skb->data += len; skb->tail += len; } /** * skb_tailroom_reserve - adjust reserved_tailroom * @skb: buffer to alter * @mtu: maximum amount of headlen permitted * @needed_tailroom: minimum amount of reserved_tailroom * * Set reserved_tailroom so that headlen can be as large as possible but * not larger than mtu and tailroom cannot be smaller than * needed_tailroom. * The required headroom should already have been reserved before using * this function. */ static inline void skb_tailroom_reserve(struct sk_buff *skb, unsigned int mtu, unsigned int needed_tailroom) { SKB_LINEAR_ASSERT(skb); if (mtu < skb_tailroom(skb) - needed_tailroom) /* use at most mtu */ skb->reserved_tailroom = skb_tailroom(skb) - mtu; else /* use up to all available space */ skb->reserved_tailroom = needed_tailroom; } #define ENCAP_TYPE_ETHER 0 #define ENCAP_TYPE_IPPROTO 1 static inline void skb_set_inner_protocol(struct sk_buff *skb, __be16 protocol) { skb->inner_protocol = protocol; skb->inner_protocol_type = ENCAP_TYPE_ETHER; } static inline void skb_set_inner_ipproto(struct sk_buff *skb, __u8 ipproto) { skb->inner_ipproto = ipproto; skb->inner_protocol_type = ENCAP_TYPE_IPPROTO; } static inline void skb_reset_inner_headers(struct sk_buff *skb) { skb->inner_mac_header = skb->mac_header; skb->inner_network_header = skb->network_header; skb->inner_transport_header = skb->transport_header; } static inline int skb_mac_header_was_set(const struct sk_buff *skb) { return skb->mac_header != (typeof(skb->mac_header))~0U; } static inline void skb_reset_mac_len(struct sk_buff *skb) { if (!skb_mac_header_was_set(skb)) { DEBUG_NET_WARN_ON_ONCE(1); skb->mac_len = 0; } else { skb->mac_len = skb->network_header - skb->mac_header; } } static inline unsigned char *skb_inner_transport_header(const struct sk_buff *skb) { return skb->head + skb->inner_transport_header; } static inline int skb_inner_transport_offset(const struct sk_buff *skb) { return skb_inner_transport_header(skb) - skb->data; } static inline void skb_reset_inner_transport_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_transport_header))offset); skb->inner_transport_header = offset; } static inline void skb_set_inner_transport_header(struct sk_buff *skb, const int offset) { skb_reset_inner_transport_header(skb); skb->inner_transport_header += offset; } static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb) { return skb->head + skb->inner_network_header; } static inline void skb_reset_inner_network_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_network_header))offset); skb->inner_network_header = offset; } static inline void skb_set_inner_network_header(struct sk_buff *skb, const int offset) { skb_reset_inner_network_header(skb); skb->inner_network_header += offset; } static inline bool skb_inner_network_header_was_set(const struct sk_buff *skb) { return skb->inner_network_header > 0; } static inline unsigned char *skb_inner_mac_header(const struct sk_buff *skb) { return skb->head + skb->inner_mac_header; } static inline void skb_reset_inner_mac_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->inner_mac_header))offset); skb->inner_mac_header = offset; } static inline void skb_set_inner_mac_header(struct sk_buff *skb, const int offset) { skb_reset_inner_mac_header(skb); skb->inner_mac_header += offset; } static inline bool skb_transport_header_was_set(const struct sk_buff *skb) { return skb->transport_header != (typeof(skb->transport_header))~0U; } static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->head + skb->transport_header; } static inline void skb_reset_transport_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->transport_header))offset); skb->transport_header = offset; } /** * skb_reset_transport_header_careful - conditionally reset transport header * @skb: buffer to alter * * Hardened version of skb_reset_transport_header(). * * Returns: true if the operation was a success. */ static inline bool __must_check skb_reset_transport_header_careful(struct sk_buff *skb) { long offset = skb->data - skb->head; if (unlikely(offset != (typeof(skb->transport_header))offset)) return false; if (unlikely(offset == (typeof(skb->transport_header))~0U)) return false; skb->transport_header = offset; return true; } static inline void skb_set_transport_header(struct sk_buff *skb, const int offset) { skb_reset_transport_header(skb); skb->transport_header += offset; } static inline unsigned char *skb_network_header(const struct sk_buff *skb) { return skb->head + skb->network_header; } static inline void skb_reset_network_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->network_header))offset); skb->network_header = offset; } static inline void skb_set_network_header(struct sk_buff *skb, const int offset) { skb_reset_network_header(skb); skb->network_header += offset; } static inline unsigned char *skb_mac_header(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->head + skb->mac_header; } static inline int skb_mac_offset(const struct sk_buff *skb) { return skb_mac_header(skb) - skb->data; } static inline u32 skb_mac_header_len(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_mac_header_was_set(skb)); return skb->network_header - skb->mac_header; } static inline void skb_unset_mac_header(struct sk_buff *skb) { skb->mac_header = (typeof(skb->mac_header))~0U; } static inline void skb_reset_mac_header(struct sk_buff *skb) { long offset = skb->data - skb->head; DEBUG_NET_WARN_ON_ONCE(offset != (typeof(skb->mac_header))offset); skb->mac_header = offset; } static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) { skb_reset_mac_header(skb); skb->mac_header += offset; } static inline void skb_pop_mac_header(struct sk_buff *skb) { skb->mac_header = skb->network_header; } static inline void skb_probe_transport_header(struct sk_buff *skb) { struct flow_keys_basic keys; if (skb_transport_header_was_set(skb)) return; if (skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); } static inline void skb_mac_header_rebuild(struct sk_buff *skb) { if (skb_mac_header_was_set(skb)) { const unsigned char *old_mac = skb_mac_header(skb); skb_set_mac_header(skb, -skb->mac_len); memmove(skb_mac_header(skb), old_mac, skb->mac_len); } } /* Move the full mac header up to current network_header. * Leaves skb->data pointing at offset skb->mac_len into the mac_header. * Must be provided the complete mac header length. */ static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len) { if (skb_mac_header_was_set(skb)) { const unsigned char *old_mac = skb_mac_header(skb); skb_set_mac_header(skb, -full_mac_len); memmove(skb_mac_header(skb), old_mac, full_mac_len); __skb_push(skb, full_mac_len - skb->mac_len); } } static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); } static inline unsigned char *skb_checksum_start(const struct sk_buff *skb) { return skb->head + skb->csum_start; } static inline int skb_transport_offset(const struct sk_buff *skb) { return skb_transport_header(skb) - skb->data; } static inline u32 skb_network_header_len(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb)); return skb->transport_header - skb->network_header; } static inline u32 skb_inner_network_header_len(const struct sk_buff *skb) { return skb->inner_transport_header - skb->inner_network_header; } static inline int skb_network_offset(const struct sk_buff *skb) { return skb_network_header(skb) - skb->data; } static inline int skb_inner_network_offset(const struct sk_buff *skb) { return skb_inner_network_header(skb) - skb->data; } static inline enum skb_drop_reason pskb_network_may_pull_reason(struct sk_buff *skb, unsigned int len) { return pskb_may_pull_reason(skb, skb_network_offset(skb) + len); } static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) { return pskb_network_may_pull_reason(skb, len) == SKB_NOT_DROPPED_YET; } /* * CPUs often take a performance hit when accessing unaligned memory * locations. The actual performance hit varies, it can be small if the * hardware handles it or large if we have to take an exception and fix it * in software. * * Since an ethernet header is 14 bytes network drivers often end up with * the IP header at an unaligned offset. The IP header can be aligned by * shifting the start of the packet by 2 bytes. Drivers should do this * with: * * skb_reserve(skb, NET_IP_ALIGN); * * The downside to this alignment of the IP header is that the DMA is now * unaligned. On some architectures the cost of an unaligned DMA is high * and this cost outweighs the gains made by aligning the IP header. * * Since this trade off varies between architectures, we allow NET_IP_ALIGN * to be overridden. */ #ifndef NET_IP_ALIGN #define NET_IP_ALIGN 2 #endif /* * The networking layer reserves some headroom in skb data (via * dev_alloc_skb). This is used to avoid having to reallocate skb data when * the header has to grow. In the default case, if the header has to grow * 32 bytes or less we avoid the reallocation. * * Unfortunately this headroom changes the DMA alignment of the resulting * network packet. As for NET_IP_ALIGN, this unaligned DMA is expensive * on some architectures. An architecture can override this value, * perhaps setting it to a cacheline in size (since that will maintain * cacheline alignment of the DMA). It must be a power of 2. * * Various parts of the networking layer expect at least 32 bytes of * headroom, you should not reduce this. * * Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS) * to reduce average number of cache lines per packet. * get_rps_cpu() for example only access one 64 bytes aligned block : * NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8) */ #ifndef NET_SKB_PAD #define NET_SKB_PAD max(32, L1_CACHE_BYTES) #endif int ___pskb_trim(struct sk_buff *skb, unsigned int len); static inline void __skb_set_length(struct sk_buff *skb, unsigned int len) { if (WARN_ON(skb_is_nonlinear(skb))) return; skb->len = len; skb_set_tail_pointer(skb, len); } static inline void __skb_trim(struct sk_buff *skb, unsigned int len) { __skb_set_length(skb, len); } void skb_trim(struct sk_buff *skb, unsigned int len); static inline int __pskb_trim(struct sk_buff *skb, unsigned int len) { if (skb->data_len) return ___pskb_trim(skb, len); __skb_trim(skb, len); return 0; } static inline int pskb_trim(struct sk_buff *skb, unsigned int len) { skb_might_realloc(skb); return (len < skb->len) ? __pskb_trim(skb, len) : 0; } /** * pskb_trim_unique - remove end from a paged unique (not cloned) buffer * @skb: buffer to alter * @len: new length * * This is identical to pskb_trim except that the caller knows that * the skb is not cloned so we should never get an error due to out- * of-memory. */ static inline void pskb_trim_unique(struct sk_buff *skb, unsigned int len) { int err = pskb_trim(skb, len); BUG_ON(err); } static inline int __skb_grow(struct sk_buff *skb, unsigned int len) { unsigned int diff = len - skb->len; if (skb_tailroom(skb) < diff) { int ret = pskb_expand_head(skb, 0, diff - skb_tailroom(skb), GFP_ATOMIC); if (ret) return ret; } __skb_set_length(skb, len); return 0; } /** * skb_orphan - orphan a buffer * @skb: buffer to orphan * * If a buffer currently has an owner then we call the owner's * destructor function and make the @skb unowned. The buffer continues * to exist but is no longer charged to its former owner. */ static inline void skb_orphan(struct sk_buff *skb) { if (skb->destructor) { skb->destructor(skb); skb->destructor = NULL; skb->sk = NULL; } else { BUG_ON(skb->sk); } } /** * skb_orphan_frags - orphan the frags contained in a buffer * @skb: buffer to orphan frags from * @gfp_mask: allocation mask for replacement pages * * For each frag in the SKB which needs a destructor (i.e. has an * owner) create a copy of that frag and release the original * page by calling the destructor. */ static inline int skb_orphan_frags(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; if (skb_shinfo(skb)->flags & SKBFL_DONT_ORPHAN) return 0; return skb_copy_ubufs(skb, gfp_mask); } /* Frags must be orphaned, even if refcounted, if skb might loop to rx path */ static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) { if (likely(!skb_zcopy(skb))) return 0; return skb_copy_ubufs(skb, gfp_mask); } /** * __skb_queue_purge_reason - empty a list * @list: list to empty * @reason: drop reason * * Delete all buffers on an &sk_buff list. Each buffer is removed from * the list and one reference dropped. This function does not take the * list lock and the caller must hold the relevant locks to use it. */ static inline void __skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason) { struct sk_buff *skb; while ((skb = __skb_dequeue(list)) != NULL) kfree_skb_reason(skb, reason); } static inline void __skb_queue_purge(struct sk_buff_head *list) { __skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); } void skb_queue_purge_reason(struct sk_buff_head *list, enum skb_drop_reason reason); static inline void skb_queue_purge(struct sk_buff_head *list) { skb_queue_purge_reason(list, SKB_DROP_REASON_QUEUE_PURGE); } unsigned int skb_rbtree_purge(struct rb_root *root); void skb_errqueue_purge(struct sk_buff_head *list); void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); /** * netdev_alloc_frag - allocate a page fragment * @fragsz: fragment size * * Allocates a frag from a page for receive buffer. * Uses GFP_ATOMIC allocations. */ static inline void *netdev_alloc_frag(unsigned int fragsz) { return __netdev_alloc_frag_align(fragsz, ~0u); } static inline void *netdev_alloc_frag_align(unsigned int fragsz, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); return __netdev_alloc_frag_align(fragsz, -align); } struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, gfp_t gfp_mask); /** * netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @length: length to allocate * * Allocate a new &sk_buff and assign it a usage count of one. The * buffer has unspecified headroom built in. Users should allocate * the headroom they think they need without accounting for the * built in space. The built in space is used for optimisations. * * %NULL is returned if there is no free memory. Although this function * allocates memory it can be called from an interrupt. */ static inline struct sk_buff *netdev_alloc_skb(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb(dev, length, GFP_ATOMIC); } /* legacy helper around __netdev_alloc_skb() */ static inline struct sk_buff *__dev_alloc_skb(unsigned int length, gfp_t gfp_mask) { return __netdev_alloc_skb(NULL, length, gfp_mask); } /* legacy helper around netdev_alloc_skb() */ static inline struct sk_buff *dev_alloc_skb(unsigned int length) { return netdev_alloc_skb(NULL, length); } static inline struct sk_buff *__netdev_alloc_skb_ip_align(struct net_device *dev, unsigned int length, gfp_t gfp) { struct sk_buff *skb = __netdev_alloc_skb(dev, length + NET_IP_ALIGN, gfp); if (NET_IP_ALIGN && skb) skb_reserve(skb, NET_IP_ALIGN); return skb; } static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev, unsigned int length) { return __netdev_alloc_skb_ip_align(dev, length, GFP_ATOMIC); } static inline void skb_free_frag(void *addr) { page_frag_free(addr); } void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask); static inline void *napi_alloc_frag(unsigned int fragsz) { return __napi_alloc_frag_align(fragsz, ~0u); } static inline void *napi_alloc_frag_align(unsigned int fragsz, unsigned int align) { WARN_ON_ONCE(!is_power_of_2(align)); return __napi_alloc_frag_align(fragsz, -align); } struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int length); void napi_consume_skb(struct sk_buff *skb, int budget); void napi_skb_free_stolen_head(struct sk_buff *skb); void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason); /** * __dev_alloc_pages - allocate page for network Rx * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx * @order: size of the allocation * * Allocate a new page. * * %NULL is returned if there is no free memory. */ static inline struct page *__dev_alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { /* This piece of code contains several assumptions. * 1. This is for device Rx, therefore a cold page is preferred. * 2. The expectation is the user wants a compound page. * 3. If requesting a order 0 page it will not be compound * due to the check to see if order has a value in prep_new_page * 4. __GFP_MEMALLOC is ignored if __GFP_NOMEMALLOC is set due to * code in gfp_to_alloc_flags that should be enforcing this. */ gfp_mask |= __GFP_COMP | __GFP_MEMALLOC; return alloc_pages_node_noprof(NUMA_NO_NODE, gfp_mask, order); } #define __dev_alloc_pages(...) alloc_hooks(__dev_alloc_pages_noprof(__VA_ARGS__)) /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). */ #define dev_alloc_pages(_order) __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, _order) /** * __dev_alloc_page - allocate a page for network Rx * @gfp_mask: allocation priority. Set __GFP_NOMEMALLOC if not for network Rx * * Allocate a new page. * * %NULL is returned if there is no free memory. */ static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask) { return __dev_alloc_pages_noprof(gfp_mask, 0); } #define __dev_alloc_page(...) alloc_hooks(__dev_alloc_page_noprof(__VA_ARGS__)) /* * This specialized allocator has to be a macro for its allocations to be * accounted separately (to have a separate alloc_tag). */ #define dev_alloc_page() dev_alloc_pages(0) /** * dev_page_is_reusable - check whether a page can be reused for network Rx * @page: the page to test * * A page shouldn't be considered for reusing/recycling if it was allocated * under memory pressure or at a distant memory node. * * Returns: false if this page should be returned to page allocator, true * otherwise. */ static inline bool dev_page_is_reusable(const struct page *page) { return likely(page_to_nid(page) == numa_mem_id() && !page_is_pfmemalloc(page)); } /** * skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page * @page: The page that was allocated from skb_alloc_page * @skb: The skb that may need pfmemalloc set */ static inline void skb_propagate_pfmemalloc(const struct page *page, struct sk_buff *skb) { if (page_is_pfmemalloc(page)) skb->pfmemalloc = true; } /** * skb_frag_off() - Returns the offset of a skb fragment * @frag: the paged fragment */ static inline unsigned int skb_frag_off(const skb_frag_t *frag) { return frag->offset; } /** * skb_frag_off_add() - Increments the offset of a skb fragment by @delta * @frag: skb fragment * @delta: value to add */ static inline void skb_frag_off_add(skb_frag_t *frag, int delta) { frag->offset += delta; } /** * skb_frag_off_set() - Sets the offset of a skb fragment * @frag: skb fragment * @offset: offset of fragment */ static inline void skb_frag_off_set(skb_frag_t *frag, unsigned int offset) { frag->offset = offset; } /** * skb_frag_off_copy() - Sets the offset of a skb fragment from another fragment * @fragto: skb fragment where offset is set * @fragfrom: skb fragment offset is copied from */ static inline void skb_frag_off_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { fragto->offset = fragfrom->offset; } /* Return: true if the skb_frag contains a net_iov. */ static inline bool skb_frag_is_net_iov(const skb_frag_t *frag) { return netmem_is_net_iov(frag->netmem); } /** * skb_frag_net_iov - retrieve the net_iov referred to by fragment * @frag: the fragment * * Return: the &struct net_iov associated with @frag. Returns NULL if this * frag has no associated net_iov. */ static inline struct net_iov *skb_frag_net_iov(const skb_frag_t *frag) { if (!skb_frag_is_net_iov(frag)) return NULL; return netmem_to_net_iov(frag->netmem); } /** * skb_frag_page - retrieve the page referred to by a paged fragment * @frag: the paged fragment * * Return: the &struct page associated with @frag. Returns NULL if this frag * has no associated page. */ static inline struct page *skb_frag_page(const skb_frag_t *frag) { if (skb_frag_is_net_iov(frag)) return NULL; return netmem_to_page(frag->netmem); } /** * skb_frag_netmem - retrieve the netmem referred to by a fragment * @frag: the fragment * * Return: the &netmem_ref associated with @frag. */ static inline netmem_ref skb_frag_netmem(const skb_frag_t *frag) { return frag->netmem; } int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, const struct bpf_prog *prog); /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * * Returns: the address of the data within @frag. The page must already * be mapped. */ static inline void *skb_frag_address(const skb_frag_t *frag) { if (!skb_frag_page(frag)) return NULL; return page_address(skb_frag_page(frag)) + skb_frag_off(frag); } /** * skb_frag_address_safe - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer * * Returns: the address of the data within @frag. Checks that the page * is mapped and returns %NULL otherwise. */ static inline void *skb_frag_address_safe(const skb_frag_t *frag) { struct page *page = skb_frag_page(frag); void *ptr; if (!page) return NULL; ptr = page_address(page); if (unlikely(!ptr)) return NULL; return ptr + skb_frag_off(frag); } /** * skb_frag_page_copy() - sets the page in a fragment from another fragment * @fragto: skb fragment where page is set * @fragfrom: skb fragment page is copied from */ static inline void skb_frag_page_copy(skb_frag_t *fragto, const skb_frag_t *fragfrom) { fragto->netmem = fragfrom->netmem; } bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t prio); /** * __skb_frag_dma_map - maps a paged fragment via the DMA API * @dev: the device to map the fragment to * @frag: the paged fragment to map * @offset: the offset within the fragment (starting at the * fragment's own offset) * @size: the number of bytes to map * @dir: the direction of the mapping (``PCI_DMA_*``) * * Maps the page associated with @frag to @device. */ static inline dma_addr_t __skb_frag_dma_map(struct device *dev, const skb_frag_t *frag, size_t offset, size_t size, enum dma_data_direction dir) { if (skb_frag_is_net_iov(frag)) { return netmem_to_net_iov(frag->netmem)->dma_addr + offset + frag->offset; } return dma_map_page(dev, skb_frag_page(frag), skb_frag_off(frag) + offset, size, dir); } #define skb_frag_dma_map(dev, frag, ...) \ CONCATENATE(_skb_frag_dma_map, \ COUNT_ARGS(__VA_ARGS__))(dev, frag, ##__VA_ARGS__) #define __skb_frag_dma_map1(dev, frag, offset, uf, uo) ({ \ const skb_frag_t *uf = (frag); \ size_t uo = (offset); \ \ __skb_frag_dma_map(dev, uf, uo, skb_frag_size(uf) - uo, \ DMA_TO_DEVICE); \ }) #define _skb_frag_dma_map1(dev, frag, offset) \ __skb_frag_dma_map1(dev, frag, offset, __UNIQUE_ID(frag_), \ __UNIQUE_ID(offset_)) #define _skb_frag_dma_map0(dev, frag) \ _skb_frag_dma_map1(dev, frag, 0) #define _skb_frag_dma_map2(dev, frag, offset, size) \ __skb_frag_dma_map(dev, frag, offset, size, DMA_TO_DEVICE) #define _skb_frag_dma_map3(dev, frag, offset, size, dir) \ __skb_frag_dma_map(dev, frag, offset, size, dir) static inline struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) { return __pskb_copy(skb, skb_headroom(skb), gfp_mask); } static inline struct sk_buff *pskb_copy_for_clone(struct sk_buff *skb, gfp_t gfp_mask) { return __pskb_copy_fclone(skb, skb_headroom(skb), gfp_mask, true); } /** * skb_clone_writable - is the header of a clone writable * @skb: buffer to check * @len: length up to which to write * * Returns true if modifying the header part of the cloned buffer * does not requires the data to be copied. */ static inline int skb_clone_writable(const struct sk_buff *skb, unsigned int len) { return !skb_header_cloned(skb) && skb_headroom(skb) + len <= skb->hdr_len; } static inline int skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { return skb_cloned(skb) && !skb_clone_writable(skb, write_len) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC); } static inline int __skb_cow(struct sk_buff *skb, unsigned int headroom, int cloned) { int delta = 0; if (headroom > skb_headroom(skb)) delta = headroom - skb_headroom(skb); if (delta || cloned) return pskb_expand_head(skb, ALIGN(delta, NET_SKB_PAD), 0, GFP_ATOMIC); return 0; } /** * skb_cow - copy header of skb when it is required * @skb: buffer to cow * @headroom: needed headroom * * If the skb passed lacks sufficient headroom or its data part * is shared, data is reallocated. If reallocation fails, an error * is returned and original skb is not changed. * * The result is skb with writable area skb->head...skb->tail * and at least @headroom of space at head. */ static inline int skb_cow(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_cloned(skb)); } /** * skb_cow_head - skb_cow but only making the head writable * @skb: buffer to cow * @headroom: needed headroom * * This function is identical to skb_cow except that we replace the * skb_cloned check by skb_header_cloned. It should be used when * you only need to push on some header and do not need to modify * the data. */ static inline int skb_cow_head(struct sk_buff *skb, unsigned int headroom) { return __skb_cow(skb, headroom, skb_header_cloned(skb)); } /** * skb_padto - pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int skb_padto(struct sk_buff *skb, unsigned int len) { unsigned int size = skb->len; if (likely(size >= len)) return 0; return skb_pad(skb, len - size); } /** * __skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * @free_on_error: free buffer on error * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error if @free_on_error is true. */ static inline int __must_check __skb_put_padto(struct sk_buff *skb, unsigned int len, bool free_on_error) { unsigned int size = skb->len; if (unlikely(size < len)) { len -= size; if (__skb_pad(skb, len, free_on_error)) return -ENOMEM; __skb_put(skb, len); } return 0; } /** * skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len) { return __skb_put_padto(skb, len, true); } bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i) __must_check; static inline bool skb_can_coalesce_netmem(struct sk_buff *skb, int i, netmem_ref netmem, int off) { if (skb_zcopy(skb)) return false; if (i) { const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; return netmem == skb_frag_netmem(frag) && off == skb_frag_off(frag) + skb_frag_size(frag); } return false; } static inline bool skb_can_coalesce(struct sk_buff *skb, int i, const struct page *page, int off) { return skb_can_coalesce_netmem(skb, i, page_to_netmem(page), off); } static inline int __skb_linearize(struct sk_buff *skb) { return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM; } /** * skb_linearize - convert paged skb to linear one * @skb: buffer to linarize * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize(struct sk_buff *skb) { return skb_is_nonlinear(skb) ? __skb_linearize(skb) : 0; } /** * skb_has_shared_frag - can any frag be overwritten * @skb: buffer to test * * Return: true if the skb has at least one frag that might be modified * by an external entity (as in vmsplice()/sendfile()) */ static inline bool skb_has_shared_frag(const struct sk_buff *skb) { return skb_is_nonlinear(skb) && skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; } /** * skb_linearize_cow - make sure skb is linear and writable * @skb: buffer to process * * If there is no free memory -ENOMEM is returned, otherwise zero * is returned and the old skb data released. */ static inline int skb_linearize_cow(struct sk_buff *skb) { return skb_is_nonlinear(skb) || skb_cloned(skb) ? __skb_linearize(skb) : 0; } static __always_inline void __skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len, unsigned int off) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_block_sub(skb->csum, csum_partial(start, len, 0), off); else if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } /** * skb_postpull_rcsum - update checksum for received skb after pull * @skb: buffer to update * @start: start of data before pull * @len: length of data pulled * * After doing a pull on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum, or set ip_summed to * CHECKSUM_NONE so that it can be recomputed from scratch. */ static inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = wsum_negate(csum_partial(start, len, wsum_negate(skb->csum))); else if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } static __always_inline void __skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len, unsigned int off) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_block_add(skb->csum, csum_partial(start, len, 0), off); } /** * skb_postpush_rcsum - update checksum for received skb after push * @skb: buffer to update * @start: start of data after push * @len: length of data pushed * * After doing a push on a received packet, you need to call this to * update the CHECKSUM_COMPLETE checksum. */ static inline void skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { __skb_postpush_rcsum(skb, start, len, 0); } void *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); /** * skb_push_rcsum - push skb and update receive checksum * @skb: buffer to update * @len: length of data pulled * * This function performs an skb_push on the packet and updates * the CHECKSUM_COMPLETE checksum. It should be used on * receive path processing instead of skb_push unless you know * that the checksum difference is zero (e.g., a valid IP header) * or you are setting ip_summed to CHECKSUM_NONE. */ static inline void *skb_push_rcsum(struct sk_buff *skb, unsigned int len) { skb_push(skb, len); skb_postpush_rcsum(skb, skb->data, len); return skb->data; } int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim * @len: new length * * This is exactly the same as pskb_trim except that it ensures the * checksum of received packets are still valid after the operation. * It can change skb pointers. */ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { skb_might_realloc(skb); if (likely(len >= skb->len)) return 0; return pskb_trim_rcsum_slow(skb, len); } static inline int __skb_trim_rcsum(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; __skb_trim(skb, len); return 0; } static inline int __skb_grow_rcsum(struct sk_buff *skb, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; return __skb_grow(skb, len); } #define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode) #define skb_rb_first(root) rb_to_skb(rb_first(root)) #define skb_rb_last(root) rb_to_skb(rb_last(root)) #define skb_rb_next(skb) rb_to_skb(rb_next(&(skb)->rbnode)) #define skb_rb_prev(skb) rb_to_skb(rb_prev(&(skb)->rbnode)) #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ skb = skb->next) #define skb_queue_walk_safe(queue, skb, tmp) \ for (skb = (queue)->next, tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->next) #define skb_queue_walk_from(queue, skb) \ for (; skb != (struct sk_buff *)(queue); \ skb = skb->next) #define skb_rbtree_walk(skb, root) \ for (skb = skb_rb_first(root); skb != NULL; \ skb = skb_rb_next(skb)) #define skb_rbtree_walk_from(skb) \ for (; skb != NULL; \ skb = skb_rb_next(skb)) #define skb_rbtree_walk_from_safe(skb, tmp) \ for (; tmp = skb ? skb_rb_next(skb) : NULL, (skb != NULL); \ skb = tmp) #define skb_queue_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->next; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->next) #define skb_queue_reverse_walk(queue, skb) \ for (skb = (queue)->prev; \ skb != (struct sk_buff *)(queue); \ skb = skb->prev) #define skb_queue_reverse_walk_safe(queue, skb, tmp) \ for (skb = (queue)->prev, tmp = skb->prev; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->prev) #define skb_queue_reverse_walk_from_safe(queue, skb, tmp) \ for (tmp = skb->prev; \ skb != (struct sk_buff *)(queue); \ skb = tmp, tmp = skb->prev) static inline bool skb_has_frag_list(const struct sk_buff *skb) { return skb_shinfo(skb)->frag_list != NULL; } static inline void skb_frag_list_init(struct sk_buff *skb) { skb_shinfo(skb)->frag_list = NULL; } #define skb_walk_frags(skb, iter) \ for (iter = skb_shinfo(skb)->frag_list; iter; iter = iter->next) int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue, int *err, long *timeo_p, const struct sk_buff *skb); struct sk_buff *__skb_try_recv_from_queue(struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_try_recv_datagram(struct sock *sk, struct sk_buff_head *queue, unsigned int flags, int *off, int *err, struct sk_buff **last); struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, unsigned int flags, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err); __poll_t datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, struct iov_iter *to, int size); static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset, struct msghdr *msg, int size) { return skb_copy_datagram_iter(from, offset, &msg->msg_iter, size); } int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen, struct msghdr *msg); int skb_copy_and_crc32c_datagram_iter(const struct sk_buff *skb, int offset, struct iov_iter *to, int len, u32 *crcp); int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, u8 *to, int len); int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset, struct pipe_inode_info *pipe, unsigned int len, unsigned int flags); int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset, int len); int skb_send_sock_locked_with_flags(struct sock *sk, struct sk_buff *skb, int offset, int len, int flags); int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); unsigned int skb_zerocopy_headlen(const struct sk_buff *from); int skb_zerocopy(struct sk_buff *to, struct sk_buff *from, int len, int hlen); void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct sk_buff *skb_segment_list(struct sk_buff *skb, netdev_features_t features, unsigned int offset); struct sk_buff *skb_vlan_untag(struct sk_buff *skb); int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len); int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); int skb_eth_pop(struct sk_buff *skb); int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, const unsigned char *src); int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, int mac_len, bool ethernet); int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, bool ethernet); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); int skb_mpls_dec_ttl(struct sk_buff *skb); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, gfp_t gfp); static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len) { return copy_from_iter_full(data, len, &msg->msg_iter) ? 0 : -EFAULT; } static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len) { return copy_to_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT; } __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum); u32 skb_crc32c(const struct sk_buff *skb, int offset, int len, u32 crc); static inline void * __must_check __skb_header_pointer(const struct sk_buff *skb, int offset, int len, const void *data, int hlen, void *buffer) { if (likely(hlen - offset >= len)) return (void *)data + offset; if (!skb || unlikely(skb_copy_bits(skb, offset, buffer, len) < 0)) return NULL; return buffer; } static inline void * __must_check skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { return __skb_header_pointer(skb, offset, len, skb->data, skb_headlen(skb), buffer); } static inline void * __must_check skb_pointer_if_linear(const struct sk_buff *skb, int offset, int len) { if (likely(skb_headlen(skb) - offset >= len)) return skb->data + offset; return NULL; } /** * skb_needs_linearize - check if we need to linearize a given skb * depending on the given device features. * @skb: socket buffer to check * @features: net device features * * Returns true if either: * 1. skb has frag_list and the device doesn't support FRAGLIST, or * 2. skb is fragmented and the device does not support SG. */ static inline bool skb_needs_linearize(struct sk_buff *skb, netdev_features_t features) { return skb_is_nonlinear(skb) && ((skb_has_frag_list(skb) && !(features & NETIF_F_FRAGLIST)) || (skb_shinfo(skb)->nr_frags && !(features & NETIF_F_SG))); } static inline void skb_copy_from_linear_data(const struct sk_buff *skb, void *to, const unsigned int len) { memcpy(to, skb->data, len); } static inline void skb_copy_from_linear_data_offset(const struct sk_buff *skb, const int offset, void *to, const unsigned int len) { memcpy(to, skb->data + offset, len); } static inline void skb_copy_to_linear_data(struct sk_buff *skb, const void *from, const unsigned int len) { memcpy(skb->data, from, len); } static inline void skb_copy_to_linear_data_offset(struct sk_buff *skb, const int offset, const void *from, const unsigned int len) { memcpy(skb->data + offset, from, len); } void skb_init(void); static inline ktime_t skb_get_ktime(const struct sk_buff *skb) { return skb->tstamp; } /** * skb_get_timestamp - get timestamp from a skb * @skb: skb to get stamp from * @stamp: pointer to struct __kernel_old_timeval to store stamp in * * Timestamps are stored in the skb as offsets to a base timestamp. * This function converts the offset back to a struct timeval and stores * it in stamp. */ static inline void skb_get_timestamp(const struct sk_buff *skb, struct __kernel_old_timeval *stamp) { *stamp = ns_to_kernel_old_timeval(skb->tstamp); } static inline void skb_get_new_timestamp(const struct sk_buff *skb, struct __kernel_sock_timeval *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_usec = ts.tv_nsec / 1000; } static inline void skb_get_timestampns(const struct sk_buff *skb, struct __kernel_old_timespec *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_nsec = ts.tv_nsec; } static inline void skb_get_new_timestampns(const struct sk_buff *skb, struct __kernel_timespec *stamp) { struct timespec64 ts = ktime_to_timespec64(skb->tstamp); stamp->tv_sec = ts.tv_sec; stamp->tv_nsec = ts.tv_nsec; } static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline ktime_t net_timedelta(ktime_t t) { return ktime_sub(ktime_get_real(), t); } static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, u8 tstamp_type) { skb->tstamp = kt; if (kt) skb->tstamp_type = tstamp_type; else skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb, ktime_t kt, clockid_t clockid) { u8 tstamp_type = SKB_CLOCK_REALTIME; switch (clockid) { case CLOCK_REALTIME: break; case CLOCK_MONOTONIC: tstamp_type = SKB_CLOCK_MONOTONIC; break; case CLOCK_TAI: tstamp_type = SKB_CLOCK_TAI; break; default: WARN_ON_ONCE(1); kt = 0; } skb_set_delivery_time(skb, kt, tstamp_type); } DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); /* It is used in the ingress path to clear the delivery_time. * If needed, set the skb->tstamp to the (rcv) timestamp. */ static inline void skb_clear_delivery_time(struct sk_buff *skb) { if (skb->tstamp_type) { skb->tstamp_type = SKB_CLOCK_REALTIME; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); else skb->tstamp = 0; } } static inline void skb_clear_tstamp(struct sk_buff *skb) { if (skb->tstamp_type) return; skb->tstamp = 0; } static inline ktime_t skb_tstamp(const struct sk_buff *skb) { if (skb->tstamp_type) return 0; return skb->tstamp; } static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond) { if (skb->tstamp_type != SKB_CLOCK_MONOTONIC && skb->tstamp) return skb->tstamp; if (static_branch_unlikely(&netstamp_needed_key) || cond) return ktime_get_real(); return 0; } static inline u8 skb_metadata_len(const struct sk_buff *skb) { return skb_shinfo(skb)->meta_len; } static inline void *skb_metadata_end(const struct sk_buff *skb) { return skb_mac_header(skb); } static inline bool __skb_metadata_differs(const struct sk_buff *skb_a, const struct sk_buff *skb_b, u8 meta_len) { const void *a = skb_metadata_end(skb_a); const void *b = skb_metadata_end(skb_b); u64 diffs = 0; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || BITS_PER_LONG != 64) goto slow; /* Using more efficient variant than plain call to memcmp(). */ switch (meta_len) { #define __it(x, op) (x -= sizeof(u##op)) #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op)) case 32: diffs |= __it_diff(a, b, 64); fallthrough; case 24: diffs |= __it_diff(a, b, 64); fallthrough; case 16: diffs |= __it_diff(a, b, 64); fallthrough; case 8: diffs |= __it_diff(a, b, 64); break; case 28: diffs |= __it_diff(a, b, 64); fallthrough; case 20: diffs |= __it_diff(a, b, 64); fallthrough; case 12: diffs |= __it_diff(a, b, 64); fallthrough; case 4: diffs |= __it_diff(a, b, 32); break; default: slow: return memcmp(a - meta_len, b - meta_len, meta_len); } return diffs; } static inline bool skb_metadata_differs(const struct sk_buff *skb_a, const struct sk_buff *skb_b) { u8 len_a = skb_metadata_len(skb_a); u8 len_b = skb_metadata_len(skb_b); if (!(len_a | len_b)) return false; return len_a != len_b ? true : __skb_metadata_differs(skb_a, skb_b, len_a); } static inline void skb_metadata_set(struct sk_buff *skb, u8 meta_len) { skb_shinfo(skb)->meta_len = meta_len; } static inline void skb_metadata_clear(struct sk_buff *skb) { skb_metadata_set(skb, 0); } struct sk_buff *skb_clone_sk(struct sk_buff *skb); #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING void skb_clone_tx_timestamp(struct sk_buff *skb); bool skb_defer_rx_timestamp(struct sk_buff *skb); #else /* CONFIG_NETWORK_PHY_TIMESTAMPING */ static inline void skb_clone_tx_timestamp(struct sk_buff *skb) { } static inline bool skb_defer_rx_timestamp(struct sk_buff *skb) { return false; } #endif /* !CONFIG_NETWORK_PHY_TIMESTAMPING */ /** * skb_complete_tx_timestamp() - deliver cloned skb with tx timestamps * * PHY drivers may accept clones of transmitted packets for * timestamping via their phy_driver.txtstamp method. These drivers * must call this function to return the skb back to the stack with a * timestamp. * * @skb: clone of the original outgoing packet * @hwtstamps: hardware time stamps * */ void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps); void __skb_tstamp_tx(struct sk_buff *orig_skb, const struct sk_buff *ack_skb, struct skb_shared_hwtstamps *hwtstamps, struct sock *sk, int tstype); /** * skb_tstamp_tx - queue clone of skb with send time stamps * @orig_skb: the original outgoing packet * @hwtstamps: hardware time stamps, may be NULL if not available * * If the skb has a socket associated, then this function clones the * skb (thus sharing the actual data and optional structures), stores * the optional hardware time stamping information (if non NULL) or * generates a software time stamp (otherwise), then queues the clone * to the error queue of the socket. Errors are silently ignored. */ void skb_tstamp_tx(struct sk_buff *orig_skb, struct skb_shared_hwtstamps *hwtstamps); /** * skb_tx_timestamp() - Driver hook for transmit timestamping * * Ethernet MAC Drivers should call this function in their hard_xmit() * function immediately before giving the sk_buff to the MAC hardware. * * Specifically, one should make absolutely sure that this function is * called before TX completion of this packet can trigger. Otherwise * the packet could potentially already be freed. * * @skb: A socket buffer. */ static inline void skb_tx_timestamp(struct sk_buff *skb) { skb_clone_tx_timestamp(skb); if (skb_shinfo(skb)->tx_flags & (SKBTX_SW_TSTAMP | SKBTX_BPF)) skb_tstamp_tx(skb, NULL); } /** * skb_complete_wifi_ack - deliver skb with wifi status * * @skb: the original outgoing packet * @acked: ack status * */ void skb_complete_wifi_ack(struct sk_buff *skb, bool acked); __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len); __sum16 __skb_checksum_complete(struct sk_buff *skb); static inline int skb_csum_unnecessary(const struct sk_buff *skb) { return ((skb->ip_summed == CHECKSUM_UNNECESSARY) || skb->csum_valid || (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) >= 0)); } /** * skb_checksum_complete - Calculate checksum of an entire packet * @skb: packet to process * * This function calculates the checksum over the entire packet plus * the value of skb->csum. The latter can be used to supply the * checksum of a pseudo header as used by TCP/UDP. It returns the * checksum. * * For protocols that contain complete checksums such as ICMP/TCP/UDP, * this function can be used to verify that checksum on received * packets. In that case the function should return zero if the * checksum is correct. In particular, this function will return zero * if skb->ip_summed is CHECKSUM_UNNECESSARY which indicates that the * hardware has already verified the correctness of the checksum. */ static inline __sum16 skb_checksum_complete(struct sk_buff *skb) { return skb_csum_unnecessary(skb) ? 0 : __skb_checksum_complete(skb); } static inline void __skb_decr_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { if (skb->csum_level == 0) skb->ip_summed = CHECKSUM_NONE; else skb->csum_level--; } } static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { if (skb->csum_level < SKB_MAX_CSUM_LEVEL) skb->csum_level++; } else if (skb->ip_summed == CHECKSUM_NONE) { skb->ip_summed = CHECKSUM_UNNECESSARY; skb->csum_level = 0; } } static inline void __skb_reset_checksum_unnecessary(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_UNNECESSARY) { skb->ip_summed = CHECKSUM_NONE; skb->csum_level = 0; } } /* Check if we need to perform checksum complete validation. * * Returns: true if checksum complete is needed, false otherwise * (either checksum is unnecessary or zero checksum is allowed). */ static inline bool __skb_checksum_validate_needed(struct sk_buff *skb, bool zero_okay, __sum16 check) { if (skb_csum_unnecessary(skb) || (zero_okay && !check)) { skb->csum_valid = 1; __skb_decr_checksum_unnecessary(skb); return false; } return true; } /* For small packets <= CHECKSUM_BREAK perform checksum complete directly * in checksum_init. */ #define CHECKSUM_BREAK 76 /* Unset checksum-complete * * Unset checksum complete can be done when packet is being modified * (uncompressed for instance) and checksum-complete value is * invalidated. */ static inline void skb_checksum_complete_unset(struct sk_buff *skb) { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; } /* Validate (init) checksum based on checksum complete. * * Return values: * 0: checksum is validated or try to in skb_checksum_complete. In the latter * case the ip_summed will not be CHECKSUM_UNNECESSARY and the pseudo * checksum is stored in skb->csum for use in __skb_checksum_complete * non-zero: value of invalid checksum * */ static inline __sum16 __skb_checksum_validate_complete(struct sk_buff *skb, bool complete, __wsum psum) { if (skb->ip_summed == CHECKSUM_COMPLETE) { if (!csum_fold(csum_add(psum, skb->csum))) { skb->csum_valid = 1; return 0; } } skb->csum = psum; if (complete || skb->len <= CHECKSUM_BREAK) { __sum16 csum; csum = __skb_checksum_complete(skb); skb->csum_valid = !csum; return csum; } return 0; } static inline __wsum null_compute_pseudo(struct sk_buff *skb, int proto) { return 0; } /* Perform checksum validate (init). Note that this is a macro since we only * want to calculate the pseudo header which is an input function if necessary. * First we try to validate without any computation (checksum unnecessary) and * then calculate based on checksum complete calling the function to compute * pseudo header. * * Return values: * 0: checksum is validated or try to in skb_checksum_complete * non-zero: value of invalid checksum */ #define __skb_checksum_validate(skb, proto, complete, \ zero_okay, check, compute_pseudo) \ ({ \ __sum16 __ret = 0; \ skb->csum_valid = 0; \ if (__skb_checksum_validate_needed(skb, zero_okay, check)) \ __ret = __skb_checksum_validate_complete(skb, \ complete, compute_pseudo(skb, proto)); \ __ret; \ }) #define skb_checksum_init(skb, proto, compute_pseudo) \ __skb_checksum_validate(skb, proto, false, false, 0, compute_pseudo) #define skb_checksum_init_zero_check(skb, proto, check, compute_pseudo) \ __skb_checksum_validate(skb, proto, false, true, check, compute_pseudo) #define skb_checksum_validate(skb, proto, compute_pseudo) \ __skb_checksum_validate(skb, proto, true, false, 0, compute_pseudo) #define skb_checksum_validate_zero_check(skb, proto, check, \ compute_pseudo) \ __skb_checksum_validate(skb, proto, true, true, check, compute_pseudo) #define skb_checksum_simple_validate(skb) \ __skb_checksum_validate(skb, 0, true, false, 0, null_compute_pseudo) static inline bool __skb_checksum_convert_check(struct sk_buff *skb) { return (skb->ip_summed == CHECKSUM_NONE && skb->csum_valid); } static inline void __skb_checksum_convert(struct sk_buff *skb, __wsum pseudo) { skb->csum = ~pseudo; skb->ip_summed = CHECKSUM_COMPLETE; } #define skb_checksum_try_convert(skb, proto, compute_pseudo) \ do { \ if (__skb_checksum_convert_check(skb)) \ __skb_checksum_convert(skb, compute_pseudo(skb, proto)); \ } while (0) static inline void skb_remcsum_adjust_partial(struct sk_buff *skb, void *ptr, u16 start, u16 offset) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = ((unsigned char *)ptr + start) - skb->head; skb->csum_offset = offset - start; } /* Update skbuf and packet to reflect the remote checksum offload operation. * When called, ptr indicates the starting point for skb->csum when * ip_summed is CHECKSUM_COMPLETE. If we need create checksum complete * here, skb_postpull_rcsum is done so skb->csum start is ptr. */ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, int start, int offset, bool nopartial) { __wsum delta; if (!nopartial) { skb_remcsum_adjust_partial(skb, ptr, start, offset); return; } if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { __skb_checksum_complete(skb); skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data); } delta = remcsum_adjust(ptr, skb->csum, start, offset); /* Adjust skb->csum since we changed the packet */ skb->csum = csum_add(skb->csum, delta); } static inline struct nf_conntrack *skb_nfct(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) return (void *)(skb->_nfct & NFCT_PTRMASK); #else return NULL; #endif } static inline unsigned long skb_get_nfct(const struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) return skb->_nfct; #else return 0UL; #endif } static inline void skb_set_nfct(struct sk_buff *skb, unsigned long nfct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) skb->slow_gro |= !!nfct; skb->_nfct = nfct; #endif } #ifdef CONFIG_SKB_EXTENSIONS enum skb_ext_id { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) SKB_EXT_BRIDGE_NF, #endif #ifdef CONFIG_XFRM SKB_EXT_SEC_PATH, #endif #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) TC_SKB_EXT, #endif #if IS_ENABLED(CONFIG_MPTCP) SKB_EXT_MPTCP, #endif #if IS_ENABLED(CONFIG_MCTP_FLOWS) SKB_EXT_MCTP, #endif SKB_EXT_NUM, /* must be last */ }; /** * struct skb_ext - sk_buff extensions * @refcnt: 1 on allocation, deallocated on 0 * @offset: offset to add to @data to obtain extension address * @chunks: size currently allocated, stored in SKB_EXT_ALIGN_SHIFT units * @data: start of extension data, variable sized * * Note: offsets/lengths are stored in chunks of 8 bytes, this allows * to use 'u8' types while allowing up to 2kb worth of extension data. */ struct skb_ext { refcount_t refcnt; u8 offset[SKB_EXT_NUM]; /* in chunks of 8 bytes */ u8 chunks; /* same */ char data[] __aligned(8); }; struct skb_ext *__skb_ext_alloc(gfp_t flags); void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, struct skb_ext *ext); void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id); void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id); void __skb_ext_put(struct skb_ext *ext); static inline void skb_ext_put(struct sk_buff *skb) { if (skb->active_extensions) __skb_ext_put(skb->extensions); } static inline void __skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src) { dst->active_extensions = src->active_extensions; if (src->active_extensions) { struct skb_ext *ext = src->extensions; refcount_inc(&ext->refcnt); dst->extensions = ext; } } static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *src) { skb_ext_put(dst); __skb_ext_copy(dst, src); } static inline bool __skb_ext_exist(const struct skb_ext *ext, enum skb_ext_id i) { return !!ext->offset[i]; } static inline bool skb_ext_exist(const struct sk_buff *skb, enum skb_ext_id id) { return skb->active_extensions & (1 << id); } static inline void skb_ext_del(struct sk_buff *skb, enum skb_ext_id id) { if (skb_ext_exist(skb, id)) __skb_ext_del(skb, id); } static inline void *skb_ext_find(const struct sk_buff *skb, enum skb_ext_id id) { if (skb_ext_exist(skb, id)) { struct skb_ext *ext = skb->extensions; return (void *)ext + (ext->offset[id] << 3); } return NULL; } static inline void skb_ext_reset(struct sk_buff *skb) { if (unlikely(skb->active_extensions)) { __skb_ext_put(skb->extensions); skb->active_extensions = 0; } } static inline bool skb_has_extensions(struct sk_buff *skb) { return unlikely(skb->active_extensions); } #else static inline void skb_ext_put(struct sk_buff *skb) {} static inline void skb_ext_reset(struct sk_buff *skb) {} static inline void skb_ext_del(struct sk_buff *skb, int unused) {} static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {} static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {} static inline bool skb_has_extensions(struct sk_buff *skb) { return false; } #endif /* CONFIG_SKB_EXTENSIONS */ static inline void nf_reset_ct(struct sk_buff *skb) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(skb)); skb->_nfct = 0; #endif } static inline void nf_reset_trace(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } static inline void ipvs_reset(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IP_VS) skb->ipvs_property = 0; #endif } /* Note: This doesn't put any conntrack info in dst. */ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src, bool copy) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) dst->_nfct = src->_nfct; nf_conntrack_get(skb_nfct(src)); #endif #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || IS_ENABLED(CONFIG_NF_TABLES) if (copy) dst->nf_trace = src->nf_trace; #endif } static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(dst)); #endif dst->slow_gro = src->slow_gro; __nf_copy(dst, src, true); } #ifdef CONFIG_NETWORK_SECMARK static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from) { to->secmark = from->secmark; } static inline void skb_init_secmark(struct sk_buff *skb) { skb->secmark = 0; } #else static inline void skb_copy_secmark(struct sk_buff *to, const struct sk_buff *from) { } static inline void skb_init_secmark(struct sk_buff *skb) { } #endif static inline int secpath_exists(const struct sk_buff *skb) { #ifdef CONFIG_XFRM return skb_ext_exist(skb, SKB_EXT_SEC_PATH); #else return 0; #endif } static inline bool skb_irq_freeable(const struct sk_buff *skb) { return !skb->destructor && !secpath_exists(skb) && !skb_nfct(skb) && !skb->_skb_refdst && !skb_has_frag_list(skb); } static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping) { skb->queue_mapping = queue_mapping; } static inline u16 skb_get_queue_mapping(const struct sk_buff *skb) { return skb->queue_mapping; } static inline void skb_copy_queue_mapping(struct sk_buff *to, const struct sk_buff *from) { to->queue_mapping = from->queue_mapping; } static inline void skb_record_rx_queue(struct sk_buff *skb, u16 rx_queue) { skb->queue_mapping = rx_queue + 1; } static inline u16 skb_get_rx_queue(const struct sk_buff *skb) { return skb->queue_mapping - 1; } static inline bool skb_rx_queue_recorded(const struct sk_buff *skb) { return skb->queue_mapping != 0; } static inline void skb_set_dst_pending_confirm(struct sk_buff *skb, u32 val) { skb->dst_pending_confirm = val; } static inline bool skb_get_dst_pending_confirm(const struct sk_buff *skb) { return skb->dst_pending_confirm != 0; } static inline struct sec_path *skb_sec_path(const struct sk_buff *skb) { #ifdef CONFIG_XFRM return skb_ext_find(skb, SKB_EXT_SEC_PATH); #else return NULL; #endif } static inline bool skb_is_gso(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_size; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_v6(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_sctp(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP; } /* Note: Should be called only if skb_is_gso(skb) is true */ static inline bool skb_is_gso_tcp(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6); } static inline void skb_gso_reset(struct sk_buff *skb) { skb_shinfo(skb)->gso_size = 0; skb_shinfo(skb)->gso_segs = 0; skb_shinfo(skb)->gso_type = 0; } static inline void skb_increase_gso_size(struct skb_shared_info *shinfo, u16 increment) { if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) return; shinfo->gso_size += increment; } static inline void skb_decrease_gso_size(struct skb_shared_info *shinfo, u16 decrement) { if (WARN_ON_ONCE(shinfo->gso_size == GSO_BY_FRAGS)) return; shinfo->gso_size -= decrement; } void __skb_warn_lro_forwarding(const struct sk_buff *skb); static inline bool skb_warn_if_lro(const struct sk_buff *skb) { /* LRO sets gso_size but not gso_type, whereas if GSO is really * wanted then gso_type will be set. */ const struct skb_shared_info *shinfo = skb_shinfo(skb); if (skb_is_nonlinear(skb) && shinfo->gso_size != 0 && unlikely(shinfo->gso_type == 0)) { __skb_warn_lro_forwarding(skb); return true; } return false; } static inline void skb_forward_csum(struct sk_buff *skb) { /* Unfortunately we don't support this one. Any brave souls? */ if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; } /** * skb_checksum_none_assert - make sure skb ip_summed is CHECKSUM_NONE * @skb: skb to check * * fresh skbs have their ip_summed set to CHECKSUM_NONE. * Instead of forcing ip_summed to CHECKSUM_NONE, we can * use this helper, to document places where we make this assertion. */ static inline void skb_checksum_none_assert(const struct sk_buff *skb) { DEBUG_NET_WARN_ON_ONCE(skb->ip_summed != CHECKSUM_NONE); } bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off); int skb_checksum_setup(struct sk_buff *skb, bool recalculate); struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb, unsigned int transport_len, __sum16(*skb_chkf)(struct sk_buff *skb)); /** * skb_head_is_locked - Determine if the skb->head is locked down * @skb: skb to check * * The head on skbs build around a head frag can be removed if they are * not cloned. This function returns true if the skb head is locked down * due to either being allocated via kmalloc, or by being a clone with * multiple references to the head. */ static inline bool skb_head_is_locked(const struct sk_buff *skb) { return !skb->head_frag || skb_cloned(skb); } /* Local Checksum Offload. * Compute outer checksum based on the assumption that the * inner checksum will be offloaded later. * See Documentation/networking/checksum-offloads.rst for * explanation of how this works. * Fill in outer checksum adjustment (e.g. with sum of outer * pseudo-header) before calling. * Also ensure that inner checksum is in linear data area. */ static inline __wsum lco_csum(struct sk_buff *skb) { unsigned char *csum_start = skb_checksum_start(skb); unsigned char *l4_hdr = skb_transport_header(skb); __wsum partial; /* Start with complement of inner checksum adjustment */ partial = ~csum_unfold(*(__force __sum16 *)(csum_start + skb->csum_offset)); /* Add in checksum of our headers (incl. outer checksum * adjustment filled in by caller) and return result. */ return csum_partial(l4_hdr, csum_start - l4_hdr, partial); } static inline bool skb_is_redirected(const struct sk_buff *skb) { return skb->redirected; } static inline void skb_set_redirected(struct sk_buff *skb, bool from_ingress) { skb->redirected = 1; #ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; if (skb->from_ingress) skb_clear_tstamp(skb); #endif } static inline void skb_reset_redirect(struct sk_buff *skb) { skb->redirected = 0; } static inline void skb_set_redirected_noclear(struct sk_buff *skb, bool from_ingress) { skb->redirected = 1; #ifdef CONFIG_NET_REDIRECT skb->from_ingress = from_ingress; #endif } static inline bool skb_csum_is_sctp(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IP_SCTP) return skb->csum_not_inet; #else return 0; #endif } static inline void skb_reset_csum_not_inet(struct sk_buff *skb) { skb->ip_summed = CHECKSUM_NONE; #if IS_ENABLED(CONFIG_IP_SCTP) skb->csum_not_inet = 0; #endif } static inline void skb_set_kcov_handle(struct sk_buff *skb, const u64 kcov_handle) { #ifdef CONFIG_KCOV skb->kcov_handle = kcov_handle; #endif } static inline u64 skb_get_kcov_handle(struct sk_buff *skb) { #ifdef CONFIG_KCOV return skb->kcov_handle; #else return 0; #endif } static inline void skb_mark_for_recycle(struct sk_buff *skb) { #ifdef CONFIG_PAGE_POOL skb->pp_recycle = 1; #endif } ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter, ssize_t maxsize); #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* AFS volume management * * Copyright (C) 2002, 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/kernel.h> #include <linux/slab.h> #include "internal.h" static unsigned __read_mostly afs_volume_record_life = 60 * 60; static atomic_t afs_volume_debug_id; static void afs_destroy_volume(struct work_struct *work); /* * Insert a volume into a cell. If there's an existing volume record, that is * returned instead with a ref held. */ static struct afs_volume *afs_insert_volume_into_cell(struct afs_cell *cell, struct afs_volume *volume) { struct afs_volume *p; struct rb_node *parent = NULL, **pp; write_seqlock(&cell->volume_lock); pp = &cell->volumes.rb_node; while (*pp) { parent = *pp; p = rb_entry(parent, struct afs_volume, cell_node); if (p->vid < volume->vid) { pp = &(*pp)->rb_left; } else if (p->vid > volume->vid) { pp = &(*pp)->rb_right; } else { if (afs_try_get_volume(p, afs_volume_trace_get_cell_insert)) { volume = p; goto found; } set_bit(AFS_VOLUME_RM_TREE, &volume->flags); rb_replace_node_rcu(&p->cell_node, &volume->cell_node, &cell->volumes); } } rb_link_node_rcu(&volume->cell_node, parent, pp); rb_insert_color(&volume->cell_node, &cell->volumes); hlist_add_head_rcu(&volume->proc_link, &cell->proc_volumes); found: write_sequnlock(&cell->volume_lock); return volume; } static void afs_remove_volume_from_cell(struct afs_volume *volume) { struct afs_cell *cell = volume->cell; if (!hlist_unhashed(&volume->proc_link)) { trace_afs_volume(volume->debug_id, volume->vid, refcount_read(&volume->ref), afs_volume_trace_remove); write_seqlock(&cell->volume_lock); hlist_del_rcu(&volume->proc_link); if (!test_and_set_bit(AFS_VOLUME_RM_TREE, &volume->flags)) rb_erase(&volume->cell_node, &cell->volumes); write_sequnlock(&cell->volume_lock); } } /* * Allocate a volume record and load it up from a vldb record. */ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params, struct afs_vldb_entry *vldb, struct afs_server_list **_slist) { struct afs_server_list *slist; struct afs_volume *volume; int ret = -ENOMEM, i; volume = kzalloc(sizeof(struct afs_volume), GFP_KERNEL); if (!volume) goto error_0; volume->debug_id = atomic_inc_return(&afs_volume_debug_id); volume->vid = vldb->vid[params->type]; volume->update_at = ktime_get_real_seconds() + afs_volume_record_life; volume->cell = afs_get_cell(params->cell, afs_cell_trace_get_vol); volume->type = params->type; volume->type_force = params->force; volume->name_len = vldb->name_len; volume->creation_time = TIME64_MIN; volume->update_time = TIME64_MIN; refcount_set(&volume->ref, 1); INIT_HLIST_NODE(&volume->proc_link); INIT_WORK(&volume->destructor, afs_destroy_volume); rwlock_init(&volume->servers_lock); mutex_init(&volume->volsync_lock); mutex_init(&volume->cb_check_lock); rwlock_init(&volume->cb_v_break_lock); INIT_LIST_HEAD(&volume->open_mmaps); init_rwsem(&volume->open_mmaps_lock); memcpy(volume->name, vldb->name, vldb->name_len + 1); for (i = 0; i < AFS_MAXTYPES; i++) volume->vids[i] = vldb->vid[i]; slist = afs_alloc_server_list(volume, params->key, vldb); if (IS_ERR(slist)) { ret = PTR_ERR(slist); goto error_1; } *_slist = slist; rcu_assign_pointer(volume->servers, slist); trace_afs_volume(volume->debug_id, volume->vid, 1, afs_volume_trace_alloc); return volume; error_1: afs_put_cell(volume->cell, afs_cell_trace_put_vol); kfree(volume); error_0: return ERR_PTR(ret); } /* * Look up or allocate a volume record. */ static struct afs_volume *afs_lookup_volume(struct afs_fs_context *params, struct afs_vldb_entry *vldb) { struct afs_server_list *slist; struct afs_volume *candidate, *volume; candidate = afs_alloc_volume(params, vldb, &slist); if (IS_ERR(candidate)) return candidate; volume = afs_insert_volume_into_cell(params->cell, candidate); if (volume == candidate) afs_attach_volume_to_servers(volume, slist); else afs_put_volume(candidate, afs_volume_trace_put_cell_dup); return volume; } /* * Look up a VLDB record for a volume. */ static struct afs_vldb_entry *afs_vl_lookup_vldb(struct afs_cell *cell, struct key *key, const char *volname, size_t volnamesz) { struct afs_vldb_entry *vldb = ERR_PTR(-EDESTADDRREQ); struct afs_vl_cursor vc; int ret; if (!afs_begin_vlserver_operation(&vc, cell, key)) return ERR_PTR(-ERESTARTSYS); while (afs_select_vlserver(&vc)) { vldb = afs_vl_get_entry_by_name_u(&vc, volname, volnamesz); } ret = afs_end_vlserver_operation(&vc); return ret < 0 ? ERR_PTR(ret) : vldb; } /* * Look up a volume in the VL server and create a candidate volume record for * it. * * The volume name can be one of the following: * "%[cell:]volume[.]" R/W volume * "#[cell:]volume[.]" R/O or R/W volume (rwparent=0), * or R/W (rwparent=1) volume * "%[cell:]volume.readonly" R/O volume * "#[cell:]volume.readonly" R/O volume * "%[cell:]volume.backup" Backup volume * "#[cell:]volume.backup" Backup volume * * The cell name is optional, and defaults to the current cell. * * See "The Rules of Mount Point Traversal" in Chapter 5 of the AFS SysAdmin * Guide * - Rule 1: Explicit type suffix forces access of that type or nothing * (no suffix, then use Rule 2 & 3) * - Rule 2: If parent volume is R/O, then mount R/O volume by preference, R/W * if not available * - Rule 3: If parent volume is R/W, then only mount R/W volume unless * explicitly told otherwise */ struct afs_volume *afs_create_volume(struct afs_fs_context *params) { struct afs_vldb_entry *vldb; struct afs_volume *volume; unsigned long type_mask = 1UL << params->type; vldb = afs_vl_lookup_vldb(params->cell, params->key, params->volname, params->volnamesz); if (IS_ERR(vldb)) return ERR_CAST(vldb); if (test_bit(AFS_VLDB_QUERY_ERROR, &vldb->flags)) { volume = ERR_PTR(vldb->error); goto error; } /* Make the final decision on the type we want */ volume = ERR_PTR(-ENOMEDIUM); if (params->force) { if (!(vldb->flags & type_mask)) goto error; } else if (test_bit(AFS_VLDB_HAS_RO, &vldb->flags)) { params->type = AFSVL_ROVOL; } else if (test_bit(AFS_VLDB_HAS_RW, &vldb->flags)) { params->type = AFSVL_RWVOL; } else { goto error; } volume = afs_lookup_volume(params, vldb); error: kfree(vldb); return volume; } /* * Destroy a volume record */ static void afs_destroy_volume(struct work_struct *work) { struct afs_volume *volume = container_of(work, struct afs_volume, destructor); struct afs_server_list *slist = rcu_access_pointer(volume->servers); _enter("%p", volume); #ifdef CONFIG_AFS_FSCACHE ASSERTCMP(volume->cache, ==, NULL); #endif afs_detach_volume_from_servers(volume, slist); afs_remove_volume_from_cell(volume); afs_put_serverlist(volume->cell->net, slist); afs_put_cell(volume->cell, afs_cell_trace_put_vol); trace_afs_volume(volume->debug_id, volume->vid, refcount_read(&volume->ref), afs_volume_trace_free); kfree_rcu(volume, rcu); _leave(" [destroyed]"); } /* * Try to get a reference on a volume record. */ bool afs_try_get_volume(struct afs_volume *volume, enum afs_volume_trace reason) { int r; if (__refcount_inc_not_zero(&volume->ref, &r)) { trace_afs_volume(volume->debug_id, volume->vid, r + 1, reason); return true; } return false; } /* * Get a reference on a volume record. */ struct afs_volume *afs_get_volume(struct afs_volume *volume, enum afs_volume_trace reason) { if (volume) { int r; __refcount_inc(&volume->ref, &r); trace_afs_volume(volume->debug_id, volume->vid, r + 1, reason); } return volume; } /* * Drop a reference on a volume record. */ void afs_put_volume(struct afs_volume *volume, enum afs_volume_trace reason) { if (volume) { unsigned int debug_id = volume->debug_id; afs_volid_t vid = volume->vid; bool zero; int r; zero = __refcount_dec_and_test(&volume->ref, &r); trace_afs_volume(debug_id, vid, r - 1, reason); if (zero) schedule_work(&volume->destructor); } } /* * Activate a volume. */ int afs_activate_volume(struct afs_volume *volume) { #ifdef CONFIG_AFS_FSCACHE struct fscache_volume *vcookie; char *name; name = kasprintf(GFP_KERNEL, "afs,%s,%llx", volume->cell->name, volume->vid); if (!name) return -ENOMEM; vcookie = fscache_acquire_volume(name, NULL, NULL, 0); if (IS_ERR(vcookie)) { if (vcookie != ERR_PTR(-EBUSY)) { kfree(name); return PTR_ERR(vcookie); } pr_err("AFS: Cache volume key already in use (%s)\n", name); vcookie = NULL; } volume->cache = vcookie; kfree(name); #endif return 0; } /* * Deactivate a volume. */ void afs_deactivate_volume(struct afs_volume *volume) { _enter("%s", volume->name); #ifdef CONFIG_AFS_FSCACHE fscache_relinquish_volume(volume->cache, NULL, test_bit(AFS_VOLUME_DELETED, &volume->flags)); volume->cache = NULL; #endif _leave(""); } /* * Query the VL service to update the volume status. */ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) { struct afs_server_list *new, *old, *discard; struct afs_vldb_entry *vldb; char idbuf[24]; int ret, idsz; _enter(""); /* We look up an ID by passing it as a decimal string in the * operation's name parameter. */ idsz = snprintf(idbuf, sizeof(idbuf), "%llu", volume->vid); vldb = afs_vl_lookup_vldb(volume->cell, key, idbuf, idsz); if (IS_ERR(vldb)) { ret = PTR_ERR(vldb); goto error; } /* See if the volume got renamed. */ if (vldb->name_len != volume->name_len || memcmp(vldb->name, volume->name, vldb->name_len) != 0) { /* TODO: Use RCU'd string. */ memcpy(volume->name, vldb->name, AFS_MAXVOLNAME); volume->name_len = vldb->name_len; } /* See if the volume's server list got updated. */ new = afs_alloc_server_list(volume, key, vldb); if (IS_ERR(new)) { ret = PTR_ERR(new); goto error_vldb; } write_lock(&volume->servers_lock); discard = new; old = rcu_dereference_protected(volume->servers, lockdep_is_held(&volume->servers_lock)); if (afs_annotate_server_list(new, old)) { new->seq = volume->servers_seq + 1; rcu_assign_pointer(volume->servers, new); smp_wmb(); volume->servers_seq++; discard = old; } /* Check more often if replication is ongoing. */ if (new->ro_replicating) volume->update_at = ktime_get_real_seconds() + 10 * 60; else volume->update_at = ktime_get_real_seconds() + afs_volume_record_life; write_unlock(&volume->servers_lock); if (discard == old) afs_reattach_volume_to_servers(volume, new, old); afs_put_serverlist(volume->cell->net, discard); ret = 0; error_vldb: kfree(vldb); error: _leave(" = %d", ret); return ret; } /* * Make sure the volume record is up to date. */ int afs_check_volume_status(struct afs_volume *volume, struct afs_operation *op) { int ret, retries = 0; _enter(""); retry: if (test_bit(AFS_VOLUME_WAIT, &volume->flags)) goto wait; if (volume->update_at <= ktime_get_real_seconds() || test_bit(AFS_VOLUME_NEEDS_UPDATE, &volume->flags)) goto update; _leave(" = 0"); return 0; update: if (!test_and_set_bit_lock(AFS_VOLUME_UPDATING, &volume->flags)) { clear_bit(AFS_VOLUME_NEEDS_UPDATE, &volume->flags); ret = afs_update_volume_status(volume, op->key); if (ret < 0) set_bit(AFS_VOLUME_NEEDS_UPDATE, &volume->flags); clear_bit_unlock(AFS_VOLUME_WAIT, &volume->flags); clear_bit_unlock(AFS_VOLUME_UPDATING, &volume->flags); wake_up_bit(&volume->flags, AFS_VOLUME_WAIT); _leave(" = %d", ret); return ret; } wait: if (!test_bit(AFS_VOLUME_WAIT, &volume->flags)) { _leave(" = 0 [no wait]"); return 0; } ret = wait_on_bit(&volume->flags, AFS_VOLUME_WAIT, (op->flags & AFS_OPERATION_UNINTR) ? TASK_UNINTERRUPTIBLE : TASK_INTERRUPTIBLE); if (ret == -ERESTARTSYS) { _leave(" = %d", ret); return ret; } retries++; if (retries == 4) { _leave(" = -ESTALE"); return -ESTALE; } goto retry; } |
| 4 4 4 13 13 13 12 5 5 1 5 5 5 1 1 1 1 1 4 4 4 4 4 4 4 4 4 4 4 5 5 5 5 5 5 1 4 4 4 4 4 4 4 5 4 4 4 4 2 1 2 2 2 4 4 7 7 7 7 4 7 7 7 7 7 5 5 7 7 7 7 7 7 4 7 7 7 7 7 7 7 7 7 7 7 7 7 1 7 7 7 7 7 7 7 3 7 7 7 7 7 7 3 3 3 3 7 13 2 1 12 11 5 4 2 13 13 12 12 11 9 9 9 9 8 7 1 7 7 7 3 9 13 | 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2017 Oracle. All Rights Reserved. * * Author: Darrick J. Wong <darrick.wong@oracle.com> */ #include "ext4.h" #include <linux/fsmap.h> #include "fsmap.h" #include "mballoc.h" #include <linux/sort.h> #include <linux/list_sort.h> #include <trace/events/ext4.h> /* Convert an ext4_fsmap to an fsmap. */ void ext4_fsmap_from_internal(struct super_block *sb, struct fsmap *dest, struct ext4_fsmap *src) { dest->fmr_device = src->fmr_device; dest->fmr_flags = src->fmr_flags; dest->fmr_physical = src->fmr_physical << sb->s_blocksize_bits; dest->fmr_owner = src->fmr_owner; dest->fmr_offset = 0; dest->fmr_length = src->fmr_length << sb->s_blocksize_bits; dest->fmr_reserved[0] = 0; dest->fmr_reserved[1] = 0; dest->fmr_reserved[2] = 0; } /* Convert an fsmap to an ext4_fsmap. */ void ext4_fsmap_to_internal(struct super_block *sb, struct ext4_fsmap *dest, struct fsmap *src) { dest->fmr_device = src->fmr_device; dest->fmr_flags = src->fmr_flags; dest->fmr_physical = src->fmr_physical >> sb->s_blocksize_bits; dest->fmr_owner = src->fmr_owner; dest->fmr_length = src->fmr_length >> sb->s_blocksize_bits; } /* getfsmap query state */ struct ext4_getfsmap_info { struct ext4_fsmap_head *gfi_head; ext4_fsmap_format_t gfi_formatter; /* formatting fn */ void *gfi_format_arg;/* format buffer */ ext4_fsblk_t gfi_next_fsblk; /* next fsblock we expect */ u32 gfi_dev; /* device id */ ext4_group_t gfi_agno; /* bg number, if applicable */ struct ext4_fsmap gfi_low; /* low rmap key */ struct ext4_fsmap gfi_high; /* high rmap key */ struct ext4_fsmap gfi_lastfree; /* free ext at end of last bg */ struct list_head gfi_meta_list; /* fixed metadata list */ bool gfi_last; /* last extent? */ }; /* Associate a device with a getfsmap handler. */ struct ext4_getfsmap_dev { int (*gfd_fn)(struct super_block *sb, struct ext4_fsmap *keys, struct ext4_getfsmap_info *info); u32 gfd_dev; }; /* Compare two getfsmap device handlers. */ static int ext4_getfsmap_dev_compare(const void *p1, const void *p2) { const struct ext4_getfsmap_dev *d1 = p1; const struct ext4_getfsmap_dev *d2 = p2; return d1->gfd_dev - d2->gfd_dev; } /* Compare a record against our starting point */ static bool ext4_getfsmap_rec_before_low_key(struct ext4_getfsmap_info *info, struct ext4_fsmap *rec) { return rec->fmr_physical < info->gfi_low.fmr_physical; } /* * Format a reverse mapping for getfsmap, having translated rm_startblock * into the appropriate daddr units. */ static int ext4_getfsmap_helper(struct super_block *sb, struct ext4_getfsmap_info *info, struct ext4_fsmap *rec) { struct ext4_fsmap fmr; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t rec_fsblk = rec->fmr_physical; ext4_group_t agno; ext4_grpblk_t cno; int error; if (fatal_signal_pending(current)) return -EINTR; /* * Filter out records that start before our startpoint, if the * caller requested that. */ if (ext4_getfsmap_rec_before_low_key(info, rec)) { rec_fsblk += rec->fmr_length; if (info->gfi_next_fsblk < rec_fsblk) info->gfi_next_fsblk = rec_fsblk; return EXT4_QUERY_RANGE_CONTINUE; } /* Are we just counting mappings? */ if (info->gfi_head->fmh_count == 0) { if (info->gfi_head->fmh_entries == UINT_MAX) return EXT4_QUERY_RANGE_ABORT; if (rec_fsblk > info->gfi_next_fsblk) info->gfi_head->fmh_entries++; if (info->gfi_last) return EXT4_QUERY_RANGE_CONTINUE; info->gfi_head->fmh_entries++; rec_fsblk += rec->fmr_length; if (info->gfi_next_fsblk < rec_fsblk) info->gfi_next_fsblk = rec_fsblk; return EXT4_QUERY_RANGE_CONTINUE; } /* * If the record starts past the last physical block we saw, * then we've found a gap. Report the gap as being owned by * whatever the caller specified is the missing owner. */ if (rec_fsblk > info->gfi_next_fsblk) { if (info->gfi_head->fmh_entries >= info->gfi_head->fmh_count) return EXT4_QUERY_RANGE_ABORT; ext4_get_group_no_and_offset(sb, info->gfi_next_fsblk, &agno, &cno); trace_ext4_fsmap_mapping(sb, info->gfi_dev, agno, EXT4_C2B(sbi, cno), rec_fsblk - info->gfi_next_fsblk, EXT4_FMR_OWN_UNKNOWN); fmr.fmr_device = info->gfi_dev; fmr.fmr_physical = info->gfi_next_fsblk; fmr.fmr_owner = EXT4_FMR_OWN_UNKNOWN; fmr.fmr_length = rec_fsblk - info->gfi_next_fsblk; fmr.fmr_flags = FMR_OF_SPECIAL_OWNER; error = info->gfi_formatter(&fmr, info->gfi_format_arg); if (error) return error; info->gfi_head->fmh_entries++; } if (info->gfi_last) goto out; /* Fill out the extent we found */ if (info->gfi_head->fmh_entries >= info->gfi_head->fmh_count) return EXT4_QUERY_RANGE_ABORT; ext4_get_group_no_and_offset(sb, rec_fsblk, &agno, &cno); trace_ext4_fsmap_mapping(sb, info->gfi_dev, agno, EXT4_C2B(sbi, cno), rec->fmr_length, rec->fmr_owner); fmr.fmr_device = info->gfi_dev; fmr.fmr_physical = rec_fsblk; fmr.fmr_owner = rec->fmr_owner; fmr.fmr_flags = FMR_OF_SPECIAL_OWNER; fmr.fmr_length = rec->fmr_length; error = info->gfi_formatter(&fmr, info->gfi_format_arg); if (error) return error; info->gfi_head->fmh_entries++; out: rec_fsblk += rec->fmr_length; if (info->gfi_next_fsblk < rec_fsblk) info->gfi_next_fsblk = rec_fsblk; return EXT4_QUERY_RANGE_CONTINUE; } static inline ext4_fsblk_t ext4_fsmap_next_pblk(struct ext4_fsmap *fmr) { return fmr->fmr_physical + fmr->fmr_length; } static int ext4_getfsmap_meta_helper(struct super_block *sb, ext4_group_t agno, ext4_grpblk_t start, ext4_grpblk_t len, void *priv) { struct ext4_getfsmap_info *info = priv; struct ext4_fsmap *p; struct ext4_fsmap *tmp; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t fsb, fs_start, fs_end; int error; fs_start = fsb = (EXT4_C2B(sbi, start) + ext4_group_first_block_no(sb, agno)); fs_end = fs_start + EXT4_C2B(sbi, len); /* Return relevant extents from the meta_list */ list_for_each_entry_safe(p, tmp, &info->gfi_meta_list, fmr_list) { if (p->fmr_physical < info->gfi_next_fsblk) { list_del(&p->fmr_list); kfree(p); continue; } if (p->fmr_physical <= fs_start || p->fmr_physical + p->fmr_length <= fs_end) { /* Emit the retained free extent record if present */ if (info->gfi_lastfree.fmr_owner) { error = ext4_getfsmap_helper(sb, info, &info->gfi_lastfree); if (error) return error; info->gfi_lastfree.fmr_owner = 0; } error = ext4_getfsmap_helper(sb, info, p); if (error) return error; fsb = p->fmr_physical + p->fmr_length; if (info->gfi_next_fsblk < fsb) info->gfi_next_fsblk = fsb; list_del(&p->fmr_list); kfree(p); continue; } } if (info->gfi_next_fsblk < fsb) info->gfi_next_fsblk = fsb; return 0; } /* Transform a blockgroup's free record into a fsmap */ static int ext4_getfsmap_datadev_helper(struct super_block *sb, ext4_group_t agno, ext4_grpblk_t start, ext4_grpblk_t len, void *priv) { struct ext4_fsmap irec; struct ext4_getfsmap_info *info = priv; struct ext4_fsmap *p; struct ext4_fsmap *tmp; struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t fsb; ext4_fsblk_t fslen; int error; fsb = (EXT4_C2B(sbi, start) + ext4_group_first_block_no(sb, agno)); fslen = EXT4_C2B(sbi, len); /* If the retained free extent record is set... */ if (info->gfi_lastfree.fmr_owner) { /* ...and abuts this one, lengthen it and return. */ if (ext4_fsmap_next_pblk(&info->gfi_lastfree) == fsb) { info->gfi_lastfree.fmr_length += fslen; return 0; } /* * There's a gap between the two free extents; emit the * retained extent prior to merging the meta_list. */ error = ext4_getfsmap_helper(sb, info, &info->gfi_lastfree); if (error) return error; info->gfi_lastfree.fmr_owner = 0; } /* Merge in any relevant extents from the meta_list */ list_for_each_entry_safe(p, tmp, &info->gfi_meta_list, fmr_list) { if (p->fmr_physical + p->fmr_length <= info->gfi_next_fsblk) { list_del(&p->fmr_list); kfree(p); } else if (p->fmr_physical < fsb) { error = ext4_getfsmap_helper(sb, info, p); if (error) return error; list_del(&p->fmr_list); kfree(p); } } irec.fmr_device = 0; irec.fmr_physical = fsb; irec.fmr_length = fslen; irec.fmr_owner = EXT4_FMR_OWN_FREE; irec.fmr_flags = 0; /* If this is a free extent at the end of a bg, buffer it. */ if (ext4_fsmap_next_pblk(&irec) == ext4_group_first_block_no(sb, agno + 1)) { info->gfi_lastfree = irec; return 0; } /* Otherwise, emit it */ return ext4_getfsmap_helper(sb, info, &irec); } /* Execute a getfsmap query against the log device. */ static int ext4_getfsmap_logdev(struct super_block *sb, struct ext4_fsmap *keys, struct ext4_getfsmap_info *info) { journal_t *journal = EXT4_SB(sb)->s_journal; struct ext4_fsmap irec; /* Set up search keys */ info->gfi_low = keys[0]; info->gfi_low.fmr_length = 0; memset(&info->gfi_high, 0xFF, sizeof(info->gfi_high)); trace_ext4_fsmap_low_key(sb, info->gfi_dev, 0, info->gfi_low.fmr_physical, info->gfi_low.fmr_length, info->gfi_low.fmr_owner); trace_ext4_fsmap_high_key(sb, info->gfi_dev, 0, info->gfi_high.fmr_physical, info->gfi_high.fmr_length, info->gfi_high.fmr_owner); if (keys[0].fmr_physical > 0) return 0; /* Fabricate an rmap entry for the external log device. */ irec.fmr_physical = journal->j_blk_offset; irec.fmr_length = journal->j_total_len; irec.fmr_owner = EXT4_FMR_OWN_LOG; irec.fmr_flags = 0; return ext4_getfsmap_helper(sb, info, &irec); } /* Helper to fill out an ext4_fsmap. */ static inline int ext4_getfsmap_fill(struct list_head *meta_list, ext4_fsblk_t fsb, ext4_fsblk_t len, uint64_t owner) { struct ext4_fsmap *fsm; fsm = kmalloc(sizeof(*fsm), GFP_NOFS); if (!fsm) return -ENOMEM; fsm->fmr_device = 0; fsm->fmr_flags = 0; fsm->fmr_physical = fsb; fsm->fmr_owner = owner; fsm->fmr_length = len; list_add_tail(&fsm->fmr_list, meta_list); return 0; } /* * This function returns the number of file system metadata blocks at * the beginning of a block group, including the reserved gdt blocks. */ static unsigned int ext4_getfsmap_find_sb(struct super_block *sb, ext4_group_t agno, struct list_head *meta_list) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t fsb = ext4_group_first_block_no(sb, agno); ext4_fsblk_t len; unsigned long first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg); unsigned long metagroup = agno / EXT4_DESC_PER_BLOCK(sb); int error; /* Record the superblock. */ if (ext4_bg_has_super(sb, agno)) { error = ext4_getfsmap_fill(meta_list, fsb, 1, EXT4_FMR_OWN_FS); if (error) return error; fsb++; } /* Record the group descriptors. */ len = ext4_bg_num_gdb(sb, agno); if (!len) return 0; error = ext4_getfsmap_fill(meta_list, fsb, len, EXT4_FMR_OWN_GDT); if (error) return error; fsb += len; /* Reserved GDT blocks */ if (!ext4_has_feature_meta_bg(sb) || metagroup < first_meta_bg) { len = le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks); error = ext4_getfsmap_fill(meta_list, fsb, len, EXT4_FMR_OWN_RESV_GDT); if (error) return error; } return 0; } /* Compare two fsmap items. */ static int ext4_getfsmap_compare(void *priv, const struct list_head *a, const struct list_head *b) { struct ext4_fsmap *fa; struct ext4_fsmap *fb; fa = container_of(a, struct ext4_fsmap, fmr_list); fb = container_of(b, struct ext4_fsmap, fmr_list); if (fa->fmr_physical < fb->fmr_physical) return -1; else if (fa->fmr_physical > fb->fmr_physical) return 1; return 0; } /* Merge adjacent extents of fixed metadata. */ static void ext4_getfsmap_merge_fixed_metadata(struct list_head *meta_list) { struct ext4_fsmap *p; struct ext4_fsmap *prev = NULL; struct ext4_fsmap *tmp; list_for_each_entry_safe(p, tmp, meta_list, fmr_list) { if (!prev) { prev = p; continue; } if (prev->fmr_owner == p->fmr_owner && prev->fmr_physical + prev->fmr_length == p->fmr_physical) { prev->fmr_length += p->fmr_length; list_del(&p->fmr_list); kfree(p); } else prev = p; } } /* Free a list of fixed metadata. */ static void ext4_getfsmap_free_fixed_metadata(struct list_head *meta_list) { struct ext4_fsmap *p; struct ext4_fsmap *tmp; list_for_each_entry_safe(p, tmp, meta_list, fmr_list) { list_del(&p->fmr_list); kfree(p); } } /* Find all the fixed metadata in the filesystem. */ static int ext4_getfsmap_find_fixed_metadata(struct super_block *sb, struct list_head *meta_list) { struct ext4_group_desc *gdp; ext4_group_t agno; int error; INIT_LIST_HEAD(meta_list); /* Collect everything. */ for (agno = 0; agno < EXT4_SB(sb)->s_groups_count; agno++) { gdp = ext4_get_group_desc(sb, agno, NULL); if (!gdp) { error = -EFSCORRUPTED; goto err; } /* Superblock & GDT */ error = ext4_getfsmap_find_sb(sb, agno, meta_list); if (error) goto err; /* Block bitmap */ error = ext4_getfsmap_fill(meta_list, ext4_block_bitmap(sb, gdp), 1, EXT4_FMR_OWN_BLKBM); if (error) goto err; /* Inode bitmap */ error = ext4_getfsmap_fill(meta_list, ext4_inode_bitmap(sb, gdp), 1, EXT4_FMR_OWN_INOBM); if (error) goto err; /* Inodes */ error = ext4_getfsmap_fill(meta_list, ext4_inode_table(sb, gdp), EXT4_SB(sb)->s_itb_per_group, EXT4_FMR_OWN_INODES); if (error) goto err; } /* Sort the list */ list_sort(NULL, meta_list, ext4_getfsmap_compare); /* Merge adjacent extents */ ext4_getfsmap_merge_fixed_metadata(meta_list); return 0; err: ext4_getfsmap_free_fixed_metadata(meta_list); return error; } /* Execute a getfsmap query against the buddy bitmaps */ static int ext4_getfsmap_datadev(struct super_block *sb, struct ext4_fsmap *keys, struct ext4_getfsmap_info *info) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t start_fsb; ext4_fsblk_t end_fsb; ext4_fsblk_t bofs; ext4_fsblk_t eofs; ext4_group_t start_ag; ext4_group_t end_ag; ext4_grpblk_t first_cluster; ext4_grpblk_t last_cluster; int error = 0; bofs = le32_to_cpu(sbi->s_es->s_first_data_block); eofs = ext4_blocks_count(sbi->s_es); if (keys[0].fmr_physical >= eofs) return 0; else if (keys[0].fmr_physical < bofs) keys[0].fmr_physical = bofs; if (keys[1].fmr_physical >= eofs) keys[1].fmr_physical = eofs - 1; if (keys[1].fmr_physical < keys[0].fmr_physical) return 0; start_fsb = keys[0].fmr_physical; end_fsb = keys[1].fmr_physical; /* Determine first and last group to examine based on start and end */ ext4_get_group_no_and_offset(sb, start_fsb, &start_ag, &first_cluster); ext4_get_group_no_and_offset(sb, end_fsb, &end_ag, &last_cluster); /* * Convert the fsmap low/high keys to bg based keys. Initialize * low to the fsmap low key and max out the high key to the end * of the bg. */ info->gfi_low = keys[0]; info->gfi_low.fmr_physical = EXT4_C2B(sbi, first_cluster); info->gfi_low.fmr_length = 0; memset(&info->gfi_high, 0xFF, sizeof(info->gfi_high)); /* Assemble a list of all the fixed-location metadata. */ error = ext4_getfsmap_find_fixed_metadata(sb, &info->gfi_meta_list); if (error) goto err; /* Query each bg */ for (info->gfi_agno = start_ag; info->gfi_agno <= end_ag; info->gfi_agno++) { /* * Set the bg high key from the fsmap high key if this * is the last bg that we're querying. */ if (info->gfi_agno == end_ag) { info->gfi_high = keys[1]; info->gfi_high.fmr_physical = EXT4_C2B(sbi, last_cluster); info->gfi_high.fmr_length = 0; } trace_ext4_fsmap_low_key(sb, info->gfi_dev, info->gfi_agno, info->gfi_low.fmr_physical, info->gfi_low.fmr_length, info->gfi_low.fmr_owner); trace_ext4_fsmap_high_key(sb, info->gfi_dev, info->gfi_agno, info->gfi_high.fmr_physical, info->gfi_high.fmr_length, info->gfi_high.fmr_owner); error = ext4_mballoc_query_range(sb, info->gfi_agno, EXT4_B2C(sbi, info->gfi_low.fmr_physical), EXT4_B2C(sbi, info->gfi_high.fmr_physical), ext4_getfsmap_meta_helper, ext4_getfsmap_datadev_helper, info); if (error) goto err; /* * Set the bg low key to the start of the bg prior to * moving on to the next bg. */ if (info->gfi_agno == start_ag) memset(&info->gfi_low, 0, sizeof(info->gfi_low)); } /* Do we have a retained free extent? */ if (info->gfi_lastfree.fmr_owner) { error = ext4_getfsmap_helper(sb, info, &info->gfi_lastfree); if (error) goto err; } /* Report any gaps at the end of the bg */ info->gfi_last = true; error = ext4_getfsmap_datadev_helper(sb, end_ag, last_cluster + 1, 0, info); if (error) goto err; err: ext4_getfsmap_free_fixed_metadata(&info->gfi_meta_list); return error; } /* Do we recognize the device? */ static bool ext4_getfsmap_is_valid_device(struct super_block *sb, struct ext4_fsmap *fm) { if (fm->fmr_device == 0 || fm->fmr_device == UINT_MAX || fm->fmr_device == new_encode_dev(sb->s_bdev->bd_dev)) return true; if (EXT4_SB(sb)->s_journal_bdev_file && fm->fmr_device == new_encode_dev(file_bdev(EXT4_SB(sb)->s_journal_bdev_file)->bd_dev)) return true; return false; } /* Ensure that the low key is less than the high key. */ static bool ext4_getfsmap_check_keys(struct ext4_fsmap *low_key, struct ext4_fsmap *high_key) { if (low_key->fmr_device > high_key->fmr_device) return false; if (low_key->fmr_device < high_key->fmr_device) return true; if (low_key->fmr_physical > high_key->fmr_physical) return false; if (low_key->fmr_physical < high_key->fmr_physical) return true; if (low_key->fmr_owner > high_key->fmr_owner) return false; if (low_key->fmr_owner < high_key->fmr_owner) return true; return false; } #define EXT4_GETFSMAP_DEVS 2 /* * Get filesystem's extents as described in head, and format for * output. Calls formatter to fill the user's buffer until all * extents are mapped, until the passed-in head->fmh_count slots have * been filled, or until the formatter short-circuits the loop, if it * is tracking filled-in extents on its own. * * Key to Confusion * ---------------- * There are multiple levels of keys and counters at work here: * _fsmap_head.fmh_keys -- low and high fsmap keys passed in; * these reflect fs-wide block addrs. * dkeys -- fmh_keys used to query each device; * these are fmh_keys but w/ the low key * bumped up by fmr_length. * _getfsmap_info.gfi_next_fsblk-- next fs block we expect to see; this * is how we detect gaps in the fsmap * records and report them. * _getfsmap_info.gfi_low/high -- per-bg low/high keys computed from * dkeys; used to query the free space. */ int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head, ext4_fsmap_format_t formatter, void *arg) { struct ext4_fsmap dkeys[2]; /* per-dev keys */ struct ext4_getfsmap_dev handlers[EXT4_GETFSMAP_DEVS]; struct ext4_getfsmap_info info = { NULL }; int i; int error = 0; if (head->fmh_iflags & ~FMH_IF_VALID) return -EINVAL; if (!ext4_getfsmap_is_valid_device(sb, &head->fmh_keys[0]) || !ext4_getfsmap_is_valid_device(sb, &head->fmh_keys[1])) return -EINVAL; head->fmh_entries = 0; /* Set up our device handlers. */ memset(handlers, 0, sizeof(handlers)); handlers[0].gfd_dev = new_encode_dev(sb->s_bdev->bd_dev); handlers[0].gfd_fn = ext4_getfsmap_datadev; if (EXT4_SB(sb)->s_journal_bdev_file) { handlers[1].gfd_dev = new_encode_dev( file_bdev(EXT4_SB(sb)->s_journal_bdev_file)->bd_dev); handlers[1].gfd_fn = ext4_getfsmap_logdev; } sort(handlers, EXT4_GETFSMAP_DEVS, sizeof(struct ext4_getfsmap_dev), ext4_getfsmap_dev_compare, NULL); /* * To continue where we left off, we allow userspace to use the * last mapping from a previous call as the low key of the next. * This is identified by a non-zero length in the low key. We * have to increment the low key in this scenario to ensure we * don't return the same mapping again, and instead return the * very next mapping. * * Bump the physical offset as there can be no other mapping for * the same physical block range. */ dkeys[0] = head->fmh_keys[0]; dkeys[0].fmr_physical += dkeys[0].fmr_length; dkeys[0].fmr_owner = 0; dkeys[0].fmr_length = 0; memset(&dkeys[1], 0xFF, sizeof(struct ext4_fsmap)); if (!ext4_getfsmap_check_keys(dkeys, &head->fmh_keys[1])) return -EINVAL; info.gfi_next_fsblk = head->fmh_keys[0].fmr_physical + head->fmh_keys[0].fmr_length; info.gfi_formatter = formatter; info.gfi_format_arg = arg; info.gfi_head = head; /* For each device we support... */ for (i = 0; i < EXT4_GETFSMAP_DEVS; i++) { /* Is this device within the range the user asked for? */ if (!handlers[i].gfd_fn) continue; if (head->fmh_keys[0].fmr_device > handlers[i].gfd_dev) continue; if (head->fmh_keys[1].fmr_device < handlers[i].gfd_dev) break; /* * If this device number matches the high key, we have * to pass the high key to the handler to limit the * query results. If the device number exceeds the * low key, zero out the low key so that we get * everything from the beginning. */ if (handlers[i].gfd_dev == head->fmh_keys[1].fmr_device) dkeys[1] = head->fmh_keys[1]; if (handlers[i].gfd_dev > head->fmh_keys[0].fmr_device) memset(&dkeys[0], 0, sizeof(struct ext4_fsmap)); info.gfi_dev = handlers[i].gfd_dev; info.gfi_last = false; info.gfi_agno = -1; error = handlers[i].gfd_fn(sb, dkeys, &info); if (error) break; info.gfi_next_fsblk = 0; } head->fmh_oflags = FMH_OF_DEV_T; return error; } |
| 28 28 3 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef IOU_NAPI_H #define IOU_NAPI_H #include <linux/kernel.h> #include <linux/io_uring.h> #include <net/busy_poll.h> #ifdef CONFIG_NET_RX_BUSY_POLL void io_napi_init(struct io_ring_ctx *ctx); void io_napi_free(struct io_ring_ctx *ctx); int io_register_napi(struct io_ring_ctx *ctx, void __user *arg); int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg); int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id); void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq); int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx); static inline bool io_napi(struct io_ring_ctx *ctx) { return !list_empty(&ctx->napi_list); } static inline void io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) { if (!io_napi(ctx)) return; __io_napi_busy_loop(ctx, iowq); } /* * io_napi_add() - Add napi id to the busy poll list * @req: pointer to io_kiocb request * * Add the napi id of the socket to the napi busy poll list and hash table. */ static inline void io_napi_add(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; struct socket *sock; if (READ_ONCE(ctx->napi_track_mode) != IO_URING_NAPI_TRACKING_DYNAMIC) return; sock = sock_from_file(req->file); if (sock && sock->sk) __io_napi_add_id(ctx, READ_ONCE(sock->sk->sk_napi_id)); } #else static inline void io_napi_init(struct io_ring_ctx *ctx) { } static inline void io_napi_free(struct io_ring_ctx *ctx) { } static inline int io_register_napi(struct io_ring_ctx *ctx, void __user *arg) { return -EOPNOTSUPP; } static inline int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg) { return -EOPNOTSUPP; } static inline bool io_napi(struct io_ring_ctx *ctx) { return false; } static inline void io_napi_add(struct io_kiocb *req) { } static inline void io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) { } static inline int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx) { return 0; } #endif /* CONFIG_NET_RX_BUSY_POLL */ #endif |
| 16 34 90 22 90 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM mptcp #if !defined(_TRACE_MPTCP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MPTCP_H #include <linux/tracepoint.h> #define show_mapping_status(status) \ __print_symbolic(status, \ { 0, "MAPPING_OK" }, \ { 1, "MAPPING_INVALID" }, \ { 2, "MAPPING_EMPTY" }, \ { 3, "MAPPING_DATA_FIN" }, \ { 4, "MAPPING_DUMMY" }) TRACE_EVENT(mptcp_subflow_get_send, TP_PROTO(struct mptcp_subflow_context *subflow), TP_ARGS(subflow), TP_STRUCT__entry( __field(bool, active) __field(bool, free) __field(u32, snd_wnd) __field(u32, pace) __field(u8, backup) __field(u64, ratio) ), TP_fast_assign( struct sock *ssk; __entry->active = mptcp_subflow_active(subflow); __entry->backup = subflow->backup || subflow->request_bkup; if (subflow->tcp_sock && sk_fullsock(subflow->tcp_sock)) __entry->free = sk_stream_memory_free(subflow->tcp_sock); else __entry->free = 0; ssk = mptcp_subflow_tcp_sock(subflow); if (ssk && sk_fullsock(ssk)) { __entry->snd_wnd = tcp_sk(ssk)->snd_wnd; __entry->pace = READ_ONCE(ssk->sk_pacing_rate); } else { __entry->snd_wnd = 0; __entry->pace = 0; } if (ssk && sk_fullsock(ssk) && __entry->pace) __entry->ratio = div_u64((u64)ssk->sk_wmem_queued << 32, __entry->pace); else __entry->ratio = 0; ), TP_printk("active=%d free=%d snd_wnd=%u pace=%u backup=%u ratio=%llu", __entry->active, __entry->free, __entry->snd_wnd, __entry->pace, __entry->backup, __entry->ratio) ); DECLARE_EVENT_CLASS(mptcp_dump_mpext, TP_PROTO(struct mptcp_ext *mpext), TP_ARGS(mpext), TP_STRUCT__entry( __field(u64, data_ack) __field(u64, data_seq) __field(u32, subflow_seq) __field(u16, data_len) __field(u16, csum) __field(u8, use_map) __field(u8, dsn64) __field(u8, data_fin) __field(u8, use_ack) __field(u8, ack64) __field(u8, mpc_map) __field(u8, frozen) __field(u8, reset_transient) __field(u8, reset_reason) __field(u8, csum_reqd) __field(u8, infinite_map) ), TP_fast_assign( __entry->data_ack = mpext->ack64 ? mpext->data_ack : mpext->data_ack32; __entry->data_seq = mpext->data_seq; __entry->subflow_seq = mpext->subflow_seq; __entry->data_len = mpext->data_len; __entry->csum = (__force u16)mpext->csum; __entry->use_map = mpext->use_map; __entry->dsn64 = mpext->dsn64; __entry->data_fin = mpext->data_fin; __entry->use_ack = mpext->use_ack; __entry->ack64 = mpext->ack64; __entry->mpc_map = mpext->mpc_map; __entry->frozen = mpext->frozen; __entry->reset_transient = mpext->reset_transient; __entry->reset_reason = mpext->reset_reason; __entry->csum_reqd = mpext->csum_reqd; __entry->infinite_map = mpext->infinite_map; ), TP_printk("data_ack=%llu data_seq=%llu subflow_seq=%u data_len=%u csum=%x use_map=%u dsn64=%u data_fin=%u use_ack=%u ack64=%u mpc_map=%u frozen=%u reset_transient=%u reset_reason=%u csum_reqd=%u infinite_map=%u", __entry->data_ack, __entry->data_seq, __entry->subflow_seq, __entry->data_len, __entry->csum, __entry->use_map, __entry->dsn64, __entry->data_fin, __entry->use_ack, __entry->ack64, __entry->mpc_map, __entry->frozen, __entry->reset_transient, __entry->reset_reason, __entry->csum_reqd, __entry->infinite_map) ); DEFINE_EVENT(mptcp_dump_mpext, mptcp_sendmsg_frag, TP_PROTO(struct mptcp_ext *mpext), TP_ARGS(mpext)); DEFINE_EVENT(mptcp_dump_mpext, get_mapping_status, TP_PROTO(struct mptcp_ext *mpext), TP_ARGS(mpext)); TRACE_EVENT(ack_update_msk, TP_PROTO(u64 data_ack, u64 old_snd_una, u64 new_snd_una, u64 new_wnd_end, u64 msk_wnd_end), TP_ARGS(data_ack, old_snd_una, new_snd_una, new_wnd_end, msk_wnd_end), TP_STRUCT__entry( __field(u64, data_ack) __field(u64, old_snd_una) __field(u64, new_snd_una) __field(u64, new_wnd_end) __field(u64, msk_wnd_end) ), TP_fast_assign( __entry->data_ack = data_ack; __entry->old_snd_una = old_snd_una; __entry->new_snd_una = new_snd_una; __entry->new_wnd_end = new_wnd_end; __entry->msk_wnd_end = msk_wnd_end; ), TP_printk("data_ack=%llu old_snd_una=%llu new_snd_una=%llu new_wnd_end=%llu msk_wnd_end=%llu", __entry->data_ack, __entry->old_snd_una, __entry->new_snd_una, __entry->new_wnd_end, __entry->msk_wnd_end) ); TRACE_EVENT(subflow_check_data_avail, TP_PROTO(__u8 status, struct sk_buff *skb), TP_ARGS(status, skb), TP_STRUCT__entry( __field(u8, status) __field(const void *, skb) ), TP_fast_assign( __entry->status = status; __entry->skb = skb; ), TP_printk("mapping_status=%s, skb=%p", show_mapping_status(__entry->status), __entry->skb) ); #endif /* _TRACE_MPTCP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 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 | /* 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. */ #ifndef RXE_H #define RXE_H #ifdef pr_fmt #undef pr_fmt #endif #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/skbuff.h> #include <rdma/ib_verbs.h> #include <rdma/ib_user_verbs.h> #include <rdma/ib_pack.h> #include <rdma/ib_smi.h> #include <rdma/ib_umem.h> #include <rdma/ib_cache.h> #include <rdma/ib_addr.h> #include "rxe_net.h" #include "rxe_opcode.h" #include "rxe_hdr.h" #include "rxe_param.h" #include "rxe_verbs.h" #include "rxe_loc.h" /* * Version 1 and Version 2 are identical on 64 bit machines, but on 32 bit * machines Version 2 has a different struct layout. */ #define RXE_UVERBS_ABI_VERSION 2 #define RXE_ROCE_V2_SPORT (0xc000) #define rxe_dbg(fmt, ...) pr_debug("%s: " fmt, __func__, ##__VA_ARGS__) #define rxe_dbg_dev(rxe, fmt, ...) ibdev_dbg(&(rxe)->ib_dev, \ "%s: " fmt, __func__, ##__VA_ARGS__) #define rxe_dbg_uc(uc, fmt, ...) ibdev_dbg((uc)->ibuc.device, \ "uc#%d %s: " fmt, (uc)->elem.index, __func__, ##__VA_ARGS__) #define rxe_dbg_pd(pd, fmt, ...) ibdev_dbg((pd)->ibpd.device, \ "pd#%d %s: " fmt, (pd)->elem.index, __func__, ##__VA_ARGS__) #define rxe_dbg_ah(ah, fmt, ...) ibdev_dbg((ah)->ibah.device, \ "ah#%d %s: " fmt, (ah)->elem.index, __func__, ##__VA_ARGS__) #define rxe_dbg_srq(srq, fmt, ...) ibdev_dbg((srq)->ibsrq.device, \ "srq#%d %s: " fmt, (srq)->elem.index, __func__, ##__VA_ARGS__) #define rxe_dbg_qp(qp, fmt, ...) ibdev_dbg((qp)->ibqp.device, \ "qp#%d %s: " fmt, (qp)->elem.index, __func__, ##__VA_ARGS__) #define rxe_dbg_cq(cq, fmt, ...) ibdev_dbg((cq)->ibcq.device, \ "cq#%d %s: " fmt, (cq)->elem.index, __func__, ##__VA_ARGS__) #define rxe_dbg_mr(mr, fmt, ...) ibdev_dbg((mr)->ibmr.device, \ "mr#%d %s: " fmt, (mr)->elem.index, __func__, ##__VA_ARGS__) #define rxe_dbg_mw(mw, fmt, ...) ibdev_dbg((mw)->ibmw.device, \ "mw#%d %s: " fmt, (mw)->elem.index, __func__, ##__VA_ARGS__) #define rxe_err(fmt, ...) pr_err_ratelimited("%s: " fmt, __func__, \ ##__VA_ARGS__) #define rxe_err_dev(rxe, fmt, ...) ibdev_err_ratelimited(&(rxe)->ib_dev, \ "%s: " fmt, __func__, ##__VA_ARGS__) #define rxe_err_uc(uc, fmt, ...) ibdev_err_ratelimited((uc)->ibuc.device, \ "uc#%d %s: " fmt, (uc)->elem.index, __func__, ##__VA_ARGS__) #define rxe_err_pd(pd, fmt, ...) ibdev_err_ratelimited((pd)->ibpd.device, \ "pd#%d %s: " fmt, (pd)->elem.index, __func__, ##__VA_ARGS__) #define rxe_err_ah(ah, fmt, ...) ibdev_err_ratelimited((ah)->ibah.device, \ "ah#%d %s: " fmt, (ah)->elem.index, __func__, ##__VA_ARGS__) #define rxe_err_srq(srq, fmt, ...) ibdev_err_ratelimited((srq)->ibsrq.device, \ "srq#%d %s: " fmt, (srq)->elem.index, __func__, ##__VA_ARGS__) #define rxe_err_qp(qp, fmt, ...) ibdev_err_ratelimited((qp)->ibqp.device, \ "qp#%d %s: " fmt, (qp)->elem.index, __func__, ##__VA_ARGS__) #define rxe_err_cq(cq, fmt, ...) ibdev_err_ratelimited((cq)->ibcq.device, \ "cq#%d %s: " fmt, (cq)->elem.index, __func__, ##__VA_ARGS__) #define rxe_err_mr(mr, fmt, ...) ibdev_err_ratelimited((mr)->ibmr.device, \ "mr#%d %s: " fmt, (mr)->elem.index, __func__, ##__VA_ARGS__) #define rxe_err_mw(mw, fmt, ...) ibdev_err_ratelimited((mw)->ibmw.device, \ "mw#%d %s: " fmt, (mw)->elem.index, __func__, ##__VA_ARGS__) #define rxe_info(fmt, ...) pr_info_ratelimited("%s: " fmt, __func__, \ ##__VA_ARGS__) #define rxe_info_dev(rxe, fmt, ...) ibdev_info_ratelimited(&(rxe)->ib_dev, \ "%s: " fmt, __func__, ##__VA_ARGS__) #define rxe_info_uc(uc, fmt, ...) ibdev_info_ratelimited((uc)->ibuc.device, \ "uc#%d %s: " fmt, (uc)->elem.index, __func__, ##__VA_ARGS__) #define rxe_info_pd(pd, fmt, ...) ibdev_info_ratelimited((pd)->ibpd.device, \ "pd#%d %s: " fmt, (pd)->elem.index, __func__, ##__VA_ARGS__) #define rxe_info_ah(ah, fmt, ...) ibdev_info_ratelimited((ah)->ibah.device, \ "ah#%d %s: " fmt, (ah)->elem.index, __func__, ##__VA_ARGS__) #define rxe_info_srq(srq, fmt, ...) ibdev_info_ratelimited((srq)->ibsrq.device, \ "srq#%d %s: " fmt, (srq)->elem.index, __func__, ##__VA_ARGS__) #define rxe_info_qp(qp, fmt, ...) ibdev_info_ratelimited((qp)->ibqp.device, \ "qp#%d %s: " fmt, (qp)->elem.index, __func__, ##__VA_ARGS__) #define rxe_info_cq(cq, fmt, ...) ibdev_info_ratelimited((cq)->ibcq.device, \ "cq#%d %s: " fmt, (cq)->elem.index, __func__, ##__VA_ARGS__) #define rxe_info_mr(mr, fmt, ...) ibdev_info_ratelimited((mr)->ibmr.device, \ "mr#%d %s: " fmt, (mr)->elem.index, __func__, ##__VA_ARGS__) #define rxe_info_mw(mw, fmt, ...) ibdev_info_ratelimited((mw)->ibmw.device, \ "mw#%d %s: " fmt, (mw)->elem.index, __func__, ##__VA_ARGS__) void rxe_set_mtu(struct rxe_dev *rxe, unsigned int dev_mtu); int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name, struct net_device *ndev); void rxe_rcv(struct sk_buff *skb); /* The caller must do a matching ib_device_put(&dev->ib_dev) */ static inline struct rxe_dev *rxe_get_dev_from_net(struct net_device *ndev) { struct ib_device *ibdev = ib_device_get_by_netdev(ndev, RDMA_DRIVER_RXE); if (!ibdev) return NULL; return container_of(ibdev, struct rxe_dev, ib_dev); } void rxe_port_up(struct rxe_dev *rxe); void rxe_port_down(struct rxe_dev *rxe); void rxe_set_port_state(struct rxe_dev *rxe); #endif /* RXE_H */ |
| 2 2 2 2 2 2 2 2 2 2 2 25 4 1 4 4 4 3 3 3 4 1 3 3 4 3 3 3 26 26 26 25 41 41 41 41 41 41 22 19 21 21 25 25 25 25 25 25 25 25 25 25 25 25 10 10 3 25 22 25 21 25 18 18 25 21 25 22 24 25 25 25 25 25 25 26 26 26 26 26 26 26 26 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic MIDI synth driver for ALSA sequencer * Copyright (c) 1998 by Frank van de Pol <fvdpol@coil.demon.nl> * Jaroslav Kysela <perex@perex.cz> */ /* Possible options for midisynth module: - automatic opening of midi ports on first received event or subscription (close will be performed when client leaves) */ #include <linux/init.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/string.h> #include <linux/module.h> #include <linux/mutex.h> #include <sound/core.h> #include <sound/rawmidi.h> #include <sound/seq_kernel.h> #include <sound/seq_device.h> #include <sound/seq_midi_event.h> #include <sound/initval.h> MODULE_AUTHOR("Frank van de Pol <fvdpol@coil.demon.nl>, Jaroslav Kysela <perex@perex.cz>"); MODULE_DESCRIPTION("Advanced Linux Sound Architecture sequencer MIDI synth."); MODULE_LICENSE("GPL"); static int output_buffer_size = PAGE_SIZE; module_param(output_buffer_size, int, 0644); MODULE_PARM_DESC(output_buffer_size, "Output buffer size in bytes."); static int input_buffer_size = PAGE_SIZE; module_param(input_buffer_size, int, 0644); MODULE_PARM_DESC(input_buffer_size, "Input buffer size in bytes."); /* data for this midi synth driver */ struct seq_midisynth { struct snd_card *card; struct snd_rawmidi *rmidi; int device; int subdevice; struct snd_rawmidi_file input_rfile; struct snd_rawmidi_file output_rfile; int seq_client; int seq_port; struct snd_midi_event *parser; }; struct seq_midisynth_client { int seq_client; int num_ports; int ports_per_device[SNDRV_RAWMIDI_DEVICES]; struct seq_midisynth *ports[SNDRV_RAWMIDI_DEVICES]; }; static struct seq_midisynth_client *synths[SNDRV_CARDS]; static DEFINE_MUTEX(register_mutex); /* handle rawmidi input event (MIDI v1.0 stream) */ static void snd_midi_input_event(struct snd_rawmidi_substream *substream) { struct snd_rawmidi_runtime *runtime; struct seq_midisynth *msynth; struct snd_seq_event ev; char buf[16], *pbuf; long res; if (substream == NULL) return; runtime = substream->runtime; msynth = runtime->private_data; if (msynth == NULL) return; memset(&ev, 0, sizeof(ev)); while (runtime->avail > 0) { res = snd_rawmidi_kernel_read(substream, buf, sizeof(buf)); if (res <= 0) continue; if (msynth->parser == NULL) continue; pbuf = buf; while (res-- > 0) { if (!snd_midi_event_encode_byte(msynth->parser, *pbuf++, &ev)) continue; ev.source.port = msynth->seq_port; ev.dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS; snd_seq_kernel_client_dispatch(msynth->seq_client, &ev, 1, 0); /* clear event and reset header */ memset(&ev, 0, sizeof(ev)); } } } static int dump_midi(struct snd_rawmidi_substream *substream, const char *buf, int count) { struct snd_rawmidi_runtime *runtime; int tmp; if (snd_BUG_ON(!substream || !buf)) return -EINVAL; runtime = substream->runtime; tmp = runtime->avail; if (tmp < count) { if (printk_ratelimit()) pr_err("ALSA: seq_midi: MIDI output buffer overrun\n"); return -ENOMEM; } if (snd_rawmidi_kernel_write(substream, buf, count) < count) return -EINVAL; return 0; } /* callback for snd_seq_dump_var_event(), bridging to dump_midi() */ static int __dump_midi(void *ptr, void *buf, int count) { return dump_midi(ptr, buf, count); } static int event_process_midi(struct snd_seq_event *ev, int direct, void *private_data, int atomic, int hop) { struct seq_midisynth *msynth = private_data; unsigned char msg[10]; /* buffer for constructing midi messages */ struct snd_rawmidi_substream *substream; int len; if (snd_BUG_ON(!msynth)) return -EINVAL; substream = msynth->output_rfile.output; if (substream == NULL) return -ENODEV; if (ev->type == SNDRV_SEQ_EVENT_SYSEX) { /* special case, to save space */ if ((ev->flags & SNDRV_SEQ_EVENT_LENGTH_MASK) != SNDRV_SEQ_EVENT_LENGTH_VARIABLE) { /* invalid event */ pr_debug("ALSA: seq_midi: invalid sysex event flags = 0x%x\n", ev->flags); return 0; } snd_seq_dump_var_event(ev, __dump_midi, substream); snd_midi_event_reset_decode(msynth->parser); } else { if (msynth->parser == NULL) return -EIO; len = snd_midi_event_decode(msynth->parser, msg, sizeof(msg), ev); if (len < 0) return 0; if (dump_midi(substream, msg, len) < 0) snd_midi_event_reset_decode(msynth->parser); } return 0; } static int snd_seq_midisynth_new(struct seq_midisynth *msynth, struct snd_card *card, int device, int subdevice) { if (snd_midi_event_new(MAX_MIDI_EVENT_BUF, &msynth->parser) < 0) return -ENOMEM; msynth->card = card; msynth->device = device; msynth->subdevice = subdevice; return 0; } /* open associated midi device for input */ static int midisynth_subscribe(void *private_data, struct snd_seq_port_subscribe *info) { int err; struct seq_midisynth *msynth = private_data; struct snd_rawmidi_runtime *runtime; struct snd_rawmidi_params params; /* open midi port */ err = snd_rawmidi_kernel_open(msynth->rmidi, msynth->subdevice, SNDRV_RAWMIDI_LFLG_INPUT, &msynth->input_rfile); if (err < 0) { pr_debug("ALSA: seq_midi: midi input open failed!!!\n"); return err; } runtime = msynth->input_rfile.input->runtime; memset(¶ms, 0, sizeof(params)); params.avail_min = 1; params.buffer_size = input_buffer_size; err = snd_rawmidi_input_params(msynth->input_rfile.input, ¶ms); if (err < 0) { snd_rawmidi_kernel_release(&msynth->input_rfile); return err; } snd_midi_event_reset_encode(msynth->parser); runtime->event = snd_midi_input_event; runtime->private_data = msynth; snd_rawmidi_kernel_read(msynth->input_rfile.input, NULL, 0); return 0; } /* close associated midi device for input */ static int midisynth_unsubscribe(void *private_data, struct snd_seq_port_subscribe *info) { int err; struct seq_midisynth *msynth = private_data; if (snd_BUG_ON(!msynth->input_rfile.input)) return -EINVAL; err = snd_rawmidi_kernel_release(&msynth->input_rfile); return err; } /* open associated midi device for output */ static int midisynth_use(void *private_data, struct snd_seq_port_subscribe *info) { int err; struct seq_midisynth *msynth = private_data; struct snd_rawmidi_params params; /* open midi port */ err = snd_rawmidi_kernel_open(msynth->rmidi, msynth->subdevice, SNDRV_RAWMIDI_LFLG_OUTPUT, &msynth->output_rfile); if (err < 0) { pr_debug("ALSA: seq_midi: midi output open failed!!!\n"); return err; } memset(¶ms, 0, sizeof(params)); params.avail_min = 1; params.buffer_size = output_buffer_size; params.no_active_sensing = 1; err = snd_rawmidi_output_params(msynth->output_rfile.output, ¶ms); if (err < 0) { snd_rawmidi_kernel_release(&msynth->output_rfile); return err; } snd_midi_event_reset_decode(msynth->parser); return 0; } /* close associated midi device for output */ static int midisynth_unuse(void *private_data, struct snd_seq_port_subscribe *info) { struct seq_midisynth *msynth = private_data; if (snd_BUG_ON(!msynth->output_rfile.output)) return -EINVAL; snd_rawmidi_drain_output(msynth->output_rfile.output); return snd_rawmidi_kernel_release(&msynth->output_rfile); } /* delete given midi synth port */ static void snd_seq_midisynth_delete(struct seq_midisynth *msynth) { if (msynth == NULL) return; if (msynth->seq_client > 0) { /* delete port */ snd_seq_event_port_detach(msynth->seq_client, msynth->seq_port); } snd_midi_event_free(msynth->parser); } /* register new midi synth port */ static int snd_seq_midisynth_probe(struct device *_dev) { struct snd_seq_device *dev = to_seq_dev(_dev); struct seq_midisynth_client *client; struct seq_midisynth *msynth, *ms; struct snd_seq_port_info *port __free(kfree) = NULL; struct snd_rawmidi_info *info __free(kfree) = NULL; struct snd_rawmidi *rmidi = dev->private_data; int newclient = 0; unsigned int p, ports; struct snd_seq_port_callback pcallbacks; struct snd_card *card = dev->card; int device = dev->device; unsigned int input_count = 0, output_count = 0; if (snd_BUG_ON(!card || device < 0 || device >= SNDRV_RAWMIDI_DEVICES)) return -EINVAL; info = kmalloc(sizeof(*info), GFP_KERNEL); if (! info) return -ENOMEM; info->device = device; info->stream = SNDRV_RAWMIDI_STREAM_OUTPUT; info->subdevice = 0; if (snd_rawmidi_info_select(card, info) >= 0) output_count = info->subdevices_count; info->stream = SNDRV_RAWMIDI_STREAM_INPUT; if (snd_rawmidi_info_select(card, info) >= 0) { input_count = info->subdevices_count; } ports = output_count; if (ports < input_count) ports = input_count; if (ports == 0) return -ENODEV; if (ports > (256 / SNDRV_RAWMIDI_DEVICES)) ports = 256 / SNDRV_RAWMIDI_DEVICES; guard(mutex)(®ister_mutex); client = synths[card->number]; if (client == NULL) { newclient = 1; client = kzalloc(sizeof(*client), GFP_KERNEL); if (client == NULL) return -ENOMEM; client->seq_client = snd_seq_create_kernel_client( card, 0, "%s", card->shortname[0] ? (const char *)card->shortname : "External MIDI"); if (client->seq_client < 0) { kfree(client); return -ENOMEM; } } msynth = kcalloc(ports, sizeof(struct seq_midisynth), GFP_KERNEL); port = kmalloc(sizeof(*port), GFP_KERNEL); if (msynth == NULL || port == NULL) goto __nomem; for (p = 0; p < ports; p++) { ms = &msynth[p]; ms->rmidi = rmidi; if (snd_seq_midisynth_new(ms, card, device, p) < 0) goto __nomem; /* declare port */ memset(port, 0, sizeof(*port)); port->addr.client = client->seq_client; port->addr.port = device * (256 / SNDRV_RAWMIDI_DEVICES) + p; port->flags = SNDRV_SEQ_PORT_FLG_GIVEN_PORT; memset(info, 0, sizeof(*info)); info->device = device; if (p < output_count) info->stream = SNDRV_RAWMIDI_STREAM_OUTPUT; else info->stream = SNDRV_RAWMIDI_STREAM_INPUT; info->subdevice = p; if (snd_rawmidi_info_select(card, info) >= 0) strscpy(port->name, info->subname); if (! port->name[0]) { if (info->name[0]) { if (ports > 1) scnprintf(port->name, sizeof(port->name), "%s-%u", info->name, p); else scnprintf(port->name, sizeof(port->name), "%s", info->name); } else { /* last resort */ if (ports > 1) sprintf(port->name, "MIDI %d-%d-%u", card->number, device, p); else sprintf(port->name, "MIDI %d-%d", card->number, device); } } if ((info->flags & SNDRV_RAWMIDI_INFO_OUTPUT) && p < output_count) port->capability |= SNDRV_SEQ_PORT_CAP_WRITE | SNDRV_SEQ_PORT_CAP_SYNC_WRITE | SNDRV_SEQ_PORT_CAP_SUBS_WRITE; if ((info->flags & SNDRV_RAWMIDI_INFO_INPUT) && p < input_count) port->capability |= SNDRV_SEQ_PORT_CAP_READ | SNDRV_SEQ_PORT_CAP_SYNC_READ | SNDRV_SEQ_PORT_CAP_SUBS_READ; if ((port->capability & (SNDRV_SEQ_PORT_CAP_WRITE|SNDRV_SEQ_PORT_CAP_READ)) == (SNDRV_SEQ_PORT_CAP_WRITE|SNDRV_SEQ_PORT_CAP_READ) && info->flags & SNDRV_RAWMIDI_INFO_DUPLEX) port->capability |= SNDRV_SEQ_PORT_CAP_DUPLEX; if (port->capability & SNDRV_SEQ_PORT_CAP_READ) port->direction |= SNDRV_SEQ_PORT_DIR_INPUT; if (port->capability & SNDRV_SEQ_PORT_CAP_WRITE) port->direction |= SNDRV_SEQ_PORT_DIR_OUTPUT; port->type = SNDRV_SEQ_PORT_TYPE_MIDI_GENERIC | SNDRV_SEQ_PORT_TYPE_HARDWARE | SNDRV_SEQ_PORT_TYPE_PORT; port->midi_channels = 16; memset(&pcallbacks, 0, sizeof(pcallbacks)); pcallbacks.owner = THIS_MODULE; pcallbacks.private_data = ms; pcallbacks.subscribe = midisynth_subscribe; pcallbacks.unsubscribe = midisynth_unsubscribe; pcallbacks.use = midisynth_use; pcallbacks.unuse = midisynth_unuse; pcallbacks.event_input = event_process_midi; port->kernel = &pcallbacks; if (rmidi->ops && rmidi->ops->get_port_info) rmidi->ops->get_port_info(rmidi, p, port); if (snd_seq_kernel_client_ctl(client->seq_client, SNDRV_SEQ_IOCTL_CREATE_PORT, port)<0) goto __nomem; ms->seq_client = client->seq_client; ms->seq_port = port->addr.port; } client->ports_per_device[device] = ports; client->ports[device] = msynth; client->num_ports++; if (newclient) synths[card->number] = client; return 0; /* success */ __nomem: if (msynth != NULL) { for (p = 0; p < ports; p++) snd_seq_midisynth_delete(&msynth[p]); kfree(msynth); } if (newclient) { snd_seq_delete_kernel_client(client->seq_client); kfree(client); } return -ENOMEM; } /* release midi synth port */ static int snd_seq_midisynth_remove(struct device *_dev) { struct snd_seq_device *dev = to_seq_dev(_dev); struct seq_midisynth_client *client; struct seq_midisynth *msynth; struct snd_card *card = dev->card; int device = dev->device, p, ports; guard(mutex)(®ister_mutex); client = synths[card->number]; if (client == NULL || client->ports[device] == NULL) return -ENODEV; ports = client->ports_per_device[device]; client->ports_per_device[device] = 0; msynth = client->ports[device]; client->ports[device] = NULL; for (p = 0; p < ports; p++) snd_seq_midisynth_delete(&msynth[p]); kfree(msynth); client->num_ports--; if (client->num_ports <= 0) { snd_seq_delete_kernel_client(client->seq_client); synths[card->number] = NULL; kfree(client); } return 0; } static struct snd_seq_driver seq_midisynth_driver = { .driver = { .name = KBUILD_MODNAME, .probe = snd_seq_midisynth_probe, .remove = snd_seq_midisynth_remove, }, .id = SNDRV_SEQ_DEV_ID_MIDISYNTH, .argsize = 0, }; module_snd_seq_driver(seq_midisynth_driver); |
| 8 8 8 8 8 8 8 8 8 8 8 8 10 10 10 10 8 10 10 10 10 8 8 9 9 8 8 8 5 1 1 1 4 1 1 2 8 4 8 10 10 10 10 9 10 10 10 10 10 10 10 10 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 | // SPDX-License-Identifier: ISC /* * Copyright (c) 2007-2011 Atheros Communications Inc. * Copyright (c) 2011-2012,2017 Qualcomm Atheros, Inc. * Copyright (c) 2016-2017 Erik Stromdahl <erik.stromdahl@gmail.com> */ #include <linux/module.h> #include <linux/usb.h> #include "debug.h" #include "core.h" #include "bmi.h" #include "hif.h" #include "htc.h" #include "usb.h" static void ath10k_usb_post_recv_transfers(struct ath10k *ar, struct ath10k_usb_pipe *recv_pipe); /* inlined helper functions */ static inline enum ath10k_htc_ep_id eid_from_htc_hdr(struct ath10k_htc_hdr *htc_hdr) { return (enum ath10k_htc_ep_id)htc_hdr->eid; } static inline bool is_trailer_only_msg(struct ath10k_htc_hdr *htc_hdr) { return __le16_to_cpu(htc_hdr->len) == htc_hdr->trailer_len; } /* pipe/urb operations */ static struct ath10k_urb_context * ath10k_usb_alloc_urb_from_pipe(struct ath10k_usb_pipe *pipe) { struct ath10k_urb_context *urb_context = NULL; unsigned long flags; /* bail if this pipe is not initialized */ if (!pipe->ar_usb) return NULL; spin_lock_irqsave(&pipe->ar_usb->cs_lock, flags); if (!list_empty(&pipe->urb_list_head)) { urb_context = list_first_entry(&pipe->urb_list_head, struct ath10k_urb_context, link); list_del(&urb_context->link); pipe->urb_cnt--; } spin_unlock_irqrestore(&pipe->ar_usb->cs_lock, flags); return urb_context; } static void ath10k_usb_free_urb_to_pipe(struct ath10k_usb_pipe *pipe, struct ath10k_urb_context *urb_context) { unsigned long flags; /* bail if this pipe is not initialized */ if (!pipe->ar_usb) return; spin_lock_irqsave(&pipe->ar_usb->cs_lock, flags); pipe->urb_cnt++; list_add(&urb_context->link, &pipe->urb_list_head); spin_unlock_irqrestore(&pipe->ar_usb->cs_lock, flags); } static void ath10k_usb_cleanup_recv_urb(struct ath10k_urb_context *urb_context) { dev_kfree_skb(urb_context->skb); urb_context->skb = NULL; ath10k_usb_free_urb_to_pipe(urb_context->pipe, urb_context); } static void ath10k_usb_free_pipe_resources(struct ath10k *ar, struct ath10k_usb_pipe *pipe) { struct ath10k_urb_context *urb_context; if (!pipe->ar_usb) { /* nothing allocated for this pipe */ return; } ath10k_dbg(ar, ATH10K_DBG_USB, "usb free resources lpipe %d hpipe 0x%x urbs %d avail %d\n", pipe->logical_pipe_num, pipe->usb_pipe_handle, pipe->urb_alloc, pipe->urb_cnt); if (pipe->urb_alloc != pipe->urb_cnt) { ath10k_dbg(ar, ATH10K_DBG_USB, "usb urb leak lpipe %d hpipe 0x%x urbs %d avail %d\n", pipe->logical_pipe_num, pipe->usb_pipe_handle, pipe->urb_alloc, pipe->urb_cnt); } for (;;) { urb_context = ath10k_usb_alloc_urb_from_pipe(pipe); if (!urb_context) break; kfree(urb_context); } } static void ath10k_usb_cleanup_pipe_resources(struct ath10k *ar) { struct ath10k_usb *ar_usb = ath10k_usb_priv(ar); int i; for (i = 0; i < ATH10K_USB_PIPE_MAX; i++) ath10k_usb_free_pipe_resources(ar, &ar_usb->pipes[i]); } /* hif usb rx/tx completion functions */ static void ath10k_usb_recv_complete(struct urb *urb) { struct ath10k_urb_context *urb_context = urb->context; struct ath10k_usb_pipe *pipe = urb_context->pipe; struct ath10k *ar = pipe->ar_usb->ar; struct sk_buff *skb; int status = 0; ath10k_dbg(ar, ATH10K_DBG_USB_BULK, "usb recv pipe %d stat %d len %d urb 0x%p\n", pipe->logical_pipe_num, urb->status, urb->actual_length, urb); if (urb->status != 0) { status = -EIO; switch (urb->status) { case -ECONNRESET: case -ENOENT: case -ESHUTDOWN: /* no need to spew these errors when device * removed or urb killed due to driver shutdown */ status = -ECANCELED; break; default: ath10k_dbg(ar, ATH10K_DBG_USB_BULK, "usb recv pipe %d ep 0x%2.2x failed: %d\n", pipe->logical_pipe_num, pipe->ep_address, urb->status); break; } goto cleanup_recv_urb; } if (urb->actual_length == 0) goto cleanup_recv_urb; skb = urb_context->skb; /* we are going to pass it up */ urb_context->skb = NULL; skb_put(skb, urb->actual_length); /* note: queue implements a lock */ skb_queue_tail(&pipe->io_comp_queue, skb); schedule_work(&pipe->io_complete_work); cleanup_recv_urb: ath10k_usb_cleanup_recv_urb(urb_context); if (status == 0 && pipe->urb_cnt >= pipe->urb_cnt_thresh) { /* our free urbs are piling up, post more transfers */ ath10k_usb_post_recv_transfers(ar, pipe); } } static void ath10k_usb_transmit_complete(struct urb *urb) { struct ath10k_urb_context *urb_context = urb->context; struct ath10k_usb_pipe *pipe = urb_context->pipe; struct ath10k *ar = pipe->ar_usb->ar; struct sk_buff *skb; if (urb->status != 0) { ath10k_dbg(ar, ATH10K_DBG_USB_BULK, "pipe: %d, failed:%d\n", pipe->logical_pipe_num, urb->status); } skb = urb_context->skb; urb_context->skb = NULL; ath10k_usb_free_urb_to_pipe(urb_context->pipe, urb_context); /* note: queue implements a lock */ skb_queue_tail(&pipe->io_comp_queue, skb); schedule_work(&pipe->io_complete_work); } /* pipe operations */ static void ath10k_usb_post_recv_transfers(struct ath10k *ar, struct ath10k_usb_pipe *recv_pipe) { struct ath10k_urb_context *urb_context; struct urb *urb; int usb_status; for (;;) { urb_context = ath10k_usb_alloc_urb_from_pipe(recv_pipe); if (!urb_context) break; urb_context->skb = dev_alloc_skb(ATH10K_USB_RX_BUFFER_SIZE); if (!urb_context->skb) goto err; urb = usb_alloc_urb(0, GFP_ATOMIC); if (!urb) goto err; usb_fill_bulk_urb(urb, recv_pipe->ar_usb->udev, recv_pipe->usb_pipe_handle, urb_context->skb->data, ATH10K_USB_RX_BUFFER_SIZE, ath10k_usb_recv_complete, urb_context); ath10k_dbg(ar, ATH10K_DBG_USB_BULK, "usb bulk recv submit %d 0x%x ep 0x%2.2x len %d buf 0x%p\n", recv_pipe->logical_pipe_num, recv_pipe->usb_pipe_handle, recv_pipe->ep_address, ATH10K_USB_RX_BUFFER_SIZE, urb_context->skb); usb_anchor_urb(urb, &recv_pipe->urb_submitted); usb_status = usb_submit_urb(urb, GFP_ATOMIC); if (usb_status) { ath10k_dbg(ar, ATH10K_DBG_USB_BULK, "usb bulk recv failed: %d\n", usb_status); usb_unanchor_urb(urb); usb_free_urb(urb); goto err; } usb_free_urb(urb); } return; err: ath10k_usb_cleanup_recv_urb(urb_context); } static void ath10k_usb_flush_all(struct ath10k *ar) { struct ath10k_usb *ar_usb = ath10k_usb_priv(ar); int i; for (i = 0; i < ATH10K_USB_PIPE_MAX; i++) { if (ar_usb->pipes[i].ar_usb) { usb_kill_anchored_urbs(&ar_usb->pipes[i].urb_submitted); cancel_work_sync(&ar_usb->pipes[i].io_complete_work); } } } static void ath10k_usb_start_recv_pipes(struct ath10k *ar) { struct ath10k_usb *ar_usb = ath10k_usb_priv(ar); ar_usb->pipes[ATH10K_USB_PIPE_RX_DATA].urb_cnt_thresh = 1; ath10k_usb_post_recv_transfers(ar, &ar_usb->pipes[ATH10K_USB_PIPE_RX_DATA]); } static void ath10k_usb_tx_complete(struct ath10k *ar, struct sk_buff *skb) { struct ath10k_htc_hdr *htc_hdr; struct ath10k_htc_ep *ep; htc_hdr = (struct ath10k_htc_hdr *)skb->data; ep = &ar->htc.endpoint[htc_hdr->eid]; ath10k_htc_notify_tx_completion(ep, skb); /* The TX complete handler now owns the skb... */ } static void ath10k_usb_rx_complete(struct ath10k *ar, struct sk_buff *skb) { struct ath10k_htc *htc = &ar->htc; struct ath10k_htc_hdr *htc_hdr; enum ath10k_htc_ep_id eid; struct ath10k_htc_ep *ep; u16 payload_len; u8 *trailer; int ret; htc_hdr = (struct ath10k_htc_hdr *)skb->data; eid = eid_from_htc_hdr(htc_hdr); ep = &ar->htc.endpoint[eid]; if (ep->service_id == 0) { ath10k_warn(ar, "ep %d is not connected\n", eid); goto out_free_skb; } payload_len = le16_to_cpu(htc_hdr->len); if (!payload_len) { ath10k_warn(ar, "zero length frame received, firmware crashed?\n"); goto out_free_skb; } if (payload_len < htc_hdr->trailer_len) { ath10k_warn(ar, "malformed frame received, firmware crashed?\n"); goto out_free_skb; } if (htc_hdr->flags & ATH10K_HTC_FLAG_TRAILER_PRESENT) { trailer = skb->data + sizeof(*htc_hdr) + payload_len - htc_hdr->trailer_len; ret = ath10k_htc_process_trailer(htc, trailer, htc_hdr->trailer_len, eid, NULL, NULL); if (ret) goto out_free_skb; if (is_trailer_only_msg(htc_hdr)) goto out_free_skb; /* strip off the trailer from the skb since it should not * be passed on to upper layers */ skb_trim(skb, skb->len - htc_hdr->trailer_len); } skb_pull(skb, sizeof(*htc_hdr)); ep->ep_ops.ep_rx_complete(ar, skb); /* The RX complete handler now owns the skb... */ if (test_bit(ATH10K_FLAG_CORE_REGISTERED, &ar->dev_flags)) { local_bh_disable(); napi_schedule(&ar->napi); local_bh_enable(); } return; out_free_skb: dev_kfree_skb(skb); } static void ath10k_usb_io_comp_work(struct work_struct *work) { struct ath10k_usb_pipe *pipe = container_of(work, struct ath10k_usb_pipe, io_complete_work); struct ath10k *ar = pipe->ar_usb->ar; struct sk_buff *skb; while ((skb = skb_dequeue(&pipe->io_comp_queue))) { if (pipe->flags & ATH10K_USB_PIPE_FLAG_TX) ath10k_usb_tx_complete(ar, skb); else ath10k_usb_rx_complete(ar, skb); } } #define ATH10K_USB_MAX_DIAG_CMD (sizeof(struct ath10k_usb_ctrl_diag_cmd_write)) #define ATH10K_USB_MAX_DIAG_RESP (sizeof(struct ath10k_usb_ctrl_diag_resp_read)) static void ath10k_usb_destroy(struct ath10k *ar) { struct ath10k_usb *ar_usb = ath10k_usb_priv(ar); ath10k_usb_flush_all(ar); ath10k_usb_cleanup_pipe_resources(ar); usb_set_intfdata(ar_usb->interface, NULL); kfree(ar_usb->diag_cmd_buffer); kfree(ar_usb->diag_resp_buffer); } static int ath10k_usb_hif_start(struct ath10k *ar) { int i; struct ath10k_usb *ar_usb = ath10k_usb_priv(ar); ath10k_core_napi_enable(ar); ath10k_usb_start_recv_pipes(ar); /* set the TX resource avail threshold for each TX pipe */ for (i = ATH10K_USB_PIPE_TX_CTRL; i <= ATH10K_USB_PIPE_TX_DATA_HP; i++) { ar_usb->pipes[i].urb_cnt_thresh = ar_usb->pipes[i].urb_alloc / 2; } return 0; } static int ath10k_usb_hif_tx_sg(struct ath10k *ar, u8 pipe_id, struct ath10k_hif_sg_item *items, int n_items) { struct ath10k_usb *ar_usb = ath10k_usb_priv(ar); struct ath10k_usb_pipe *pipe = &ar_usb->pipes[pipe_id]; struct ath10k_urb_context *urb_context; struct sk_buff *skb; struct urb *urb; int ret, i; for (i = 0; i < n_items; i++) { urb_context = ath10k_usb_alloc_urb_from_pipe(pipe); if (!urb_context) { ret = -ENOMEM; goto err; } skb = items[i].transfer_context; urb_context->skb = skb; urb = usb_alloc_urb(0, GFP_ATOMIC); if (!urb) { ret = -ENOMEM; goto err_free_urb_to_pipe; } usb_fill_bulk_urb(urb, ar_usb->udev, pipe->usb_pipe_handle, skb->data, skb->len, ath10k_usb_transmit_complete, urb_context); if (!(skb->len % pipe->max_packet_size)) { /* hit a max packet boundary on this pipe */ urb->transfer_flags |= URB_ZERO_PACKET; } usb_anchor_urb(urb, &pipe->urb_submitted); ret = usb_submit_urb(urb, GFP_ATOMIC); if (ret) { ath10k_dbg(ar, ATH10K_DBG_USB_BULK, "usb bulk transmit failed: %d\n", ret); usb_unanchor_urb(urb); usb_free_urb(urb); ret = -EINVAL; goto err_free_urb_to_pipe; } usb_free_urb(urb); } return 0; err_free_urb_to_pipe: ath10k_usb_free_urb_to_pipe(urb_context->pipe, urb_context); err: return ret; } static void ath10k_usb_hif_stop(struct ath10k *ar) { ath10k_usb_flush_all(ar); ath10k_core_napi_sync_disable(ar); } static u16 ath10k_usb_hif_get_free_queue_number(struct ath10k *ar, u8 pipe_id) { struct ath10k_usb *ar_usb = ath10k_usb_priv(ar); return ar_usb->pipes[pipe_id].urb_cnt; } static int ath10k_usb_submit_ctrl_out(struct ath10k *ar, u8 req, u16 value, u16 index, void *data, u32 size) { struct ath10k_usb *ar_usb = ath10k_usb_priv(ar); u8 *buf = NULL; int ret; if (size > 0) { buf = kmemdup(data, size, GFP_KERNEL); if (!buf) return -ENOMEM; } /* note: if successful returns number of bytes transferred */ ret = usb_control_msg(ar_usb->udev, usb_sndctrlpipe(ar_usb->udev, 0), req, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, buf, size, 1000); if (ret < 0) { ath10k_warn(ar, "Failed to submit usb control message: %d\n", ret); kfree(buf); return ret; } kfree(buf); return 0; } static int ath10k_usb_submit_ctrl_in(struct ath10k *ar, u8 req, u16 value, u16 index, void *data, u32 size) { struct ath10k_usb *ar_usb = ath10k_usb_priv(ar); u8 *buf = NULL; int ret; if (size > 0) { buf = kmalloc(size, GFP_KERNEL); if (!buf) return -ENOMEM; } /* note: if successful returns number of bytes transferred */ ret = usb_control_msg(ar_usb->udev, usb_rcvctrlpipe(ar_usb->udev, 0), req, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, buf, size, 2000); if (ret < 0) { ath10k_warn(ar, "Failed to read usb control message: %d\n", ret); kfree(buf); return ret; } memcpy((u8 *)data, buf, size); kfree(buf); return 0; } static int ath10k_usb_ctrl_msg_exchange(struct ath10k *ar, u8 req_val, u8 *req_buf, u32 req_len, u8 resp_val, u8 *resp_buf, u32 *resp_len) { int ret; /* send command */ ret = ath10k_usb_submit_ctrl_out(ar, req_val, 0, 0, req_buf, req_len); if (ret) goto err; /* get response */ if (resp_buf) { ret = ath10k_usb_submit_ctrl_in(ar, resp_val, 0, 0, resp_buf, *resp_len); if (ret) goto err; } return 0; err: return ret; } static int ath10k_usb_hif_diag_read(struct ath10k *ar, u32 address, void *buf, size_t buf_len) { struct ath10k_usb *ar_usb = ath10k_usb_priv(ar); struct ath10k_usb_ctrl_diag_cmd_read *cmd; u32 resp_len; int ret; if (buf_len < sizeof(struct ath10k_usb_ctrl_diag_resp_read)) return -EINVAL; cmd = (struct ath10k_usb_ctrl_diag_cmd_read *)ar_usb->diag_cmd_buffer; memset(cmd, 0, sizeof(*cmd)); cmd->cmd = ATH10K_USB_CTRL_DIAG_CC_READ; cmd->address = cpu_to_le32(address); resp_len = sizeof(struct ath10k_usb_ctrl_diag_resp_read); ret = ath10k_usb_ctrl_msg_exchange(ar, ATH10K_USB_CONTROL_REQ_DIAG_CMD, (u8 *)cmd, sizeof(*cmd), ATH10K_USB_CONTROL_REQ_DIAG_RESP, ar_usb->diag_resp_buffer, &resp_len); if (ret) return ret; if (resp_len != sizeof(struct ath10k_usb_ctrl_diag_resp_read)) return -EMSGSIZE; memcpy(buf, ar_usb->diag_resp_buffer, sizeof(struct ath10k_usb_ctrl_diag_resp_read)); return 0; } static int ath10k_usb_hif_diag_write(struct ath10k *ar, u32 address, const void *data, int nbytes) { struct ath10k_usb *ar_usb = ath10k_usb_priv(ar); struct ath10k_usb_ctrl_diag_cmd_write *cmd; int ret; if (nbytes != sizeof(cmd->value)) return -EINVAL; cmd = (struct ath10k_usb_ctrl_diag_cmd_write *)ar_usb->diag_cmd_buffer; memset(cmd, 0, sizeof(*cmd)); cmd->cmd = cpu_to_le32(ATH10K_USB_CTRL_DIAG_CC_WRITE); cmd->address = cpu_to_le32(address); memcpy(&cmd->value, data, nbytes); ret = ath10k_usb_ctrl_msg_exchange(ar, ATH10K_USB_CONTROL_REQ_DIAG_CMD, (u8 *)cmd, sizeof(*cmd), 0, NULL, NULL); if (ret) return ret; return 0; } static int ath10k_usb_bmi_exchange_msg(struct ath10k *ar, void *req, u32 req_len, void *resp, u32 *resp_len) { int ret; if (req) { ret = ath10k_usb_submit_ctrl_out(ar, ATH10K_USB_CONTROL_REQ_SEND_BMI_CMD, 0, 0, req, req_len); if (ret) { ath10k_warn(ar, "unable to send the bmi data to the device: %d\n", ret); return ret; } } if (resp) { ret = ath10k_usb_submit_ctrl_in(ar, ATH10K_USB_CONTROL_REQ_RECV_BMI_RESP, 0, 0, resp, *resp_len); if (ret) { ath10k_warn(ar, "Unable to read the bmi data from the device: %d\n", ret); return ret; } } return 0; } static void ath10k_usb_hif_get_default_pipe(struct ath10k *ar, u8 *ul_pipe, u8 *dl_pipe) { *ul_pipe = ATH10K_USB_PIPE_TX_CTRL; *dl_pipe = ATH10K_USB_PIPE_RX_CTRL; } static int ath10k_usb_hif_map_service_to_pipe(struct ath10k *ar, u16 svc_id, u8 *ul_pipe, u8 *dl_pipe) { switch (svc_id) { case ATH10K_HTC_SVC_ID_RSVD_CTRL: case ATH10K_HTC_SVC_ID_WMI_CONTROL: *ul_pipe = ATH10K_USB_PIPE_TX_CTRL; /* due to large control packets, shift to data pipe */ *dl_pipe = ATH10K_USB_PIPE_RX_DATA; break; case ATH10K_HTC_SVC_ID_HTT_DATA_MSG: *ul_pipe = ATH10K_USB_PIPE_TX_DATA_LP; /* Disable rxdata2 directly, it will be enabled * if FW enable rxdata2 */ *dl_pipe = ATH10K_USB_PIPE_RX_DATA; break; default: return -EPERM; } return 0; } static int ath10k_usb_hif_power_up(struct ath10k *ar, enum ath10k_firmware_mode fw_mode) { return 0; } static void ath10k_usb_hif_power_down(struct ath10k *ar) { ath10k_usb_flush_all(ar); } #ifdef CONFIG_PM static int ath10k_usb_hif_suspend(struct ath10k *ar) { return -EOPNOTSUPP; } static int ath10k_usb_hif_resume(struct ath10k *ar) { return -EOPNOTSUPP; } #endif static const struct ath10k_hif_ops ath10k_usb_hif_ops = { .tx_sg = ath10k_usb_hif_tx_sg, .diag_read = ath10k_usb_hif_diag_read, .diag_write = ath10k_usb_hif_diag_write, .exchange_bmi_msg = ath10k_usb_bmi_exchange_msg, .start = ath10k_usb_hif_start, .stop = ath10k_usb_hif_stop, .map_service_to_pipe = ath10k_usb_hif_map_service_to_pipe, .get_default_pipe = ath10k_usb_hif_get_default_pipe, .get_free_queue_number = ath10k_usb_hif_get_free_queue_number, .power_up = ath10k_usb_hif_power_up, .power_down = ath10k_usb_hif_power_down, #ifdef CONFIG_PM .suspend = ath10k_usb_hif_suspend, .resume = ath10k_usb_hif_resume, #endif }; static u8 ath10k_usb_get_logical_pipe_num(u8 ep_address, int *urb_count) { u8 pipe_num = ATH10K_USB_PIPE_INVALID; switch (ep_address) { case ATH10K_USB_EP_ADDR_APP_CTRL_IN: pipe_num = ATH10K_USB_PIPE_RX_CTRL; *urb_count = RX_URB_COUNT; break; case ATH10K_USB_EP_ADDR_APP_DATA_IN: pipe_num = ATH10K_USB_PIPE_RX_DATA; *urb_count = RX_URB_COUNT; break; case ATH10K_USB_EP_ADDR_APP_INT_IN: pipe_num = ATH10K_USB_PIPE_RX_INT; *urb_count = RX_URB_COUNT; break; case ATH10K_USB_EP_ADDR_APP_DATA2_IN: pipe_num = ATH10K_USB_PIPE_RX_DATA2; *urb_count = RX_URB_COUNT; break; case ATH10K_USB_EP_ADDR_APP_CTRL_OUT: pipe_num = ATH10K_USB_PIPE_TX_CTRL; *urb_count = TX_URB_COUNT; break; case ATH10K_USB_EP_ADDR_APP_DATA_LP_OUT: pipe_num = ATH10K_USB_PIPE_TX_DATA_LP; *urb_count = TX_URB_COUNT; break; case ATH10K_USB_EP_ADDR_APP_DATA_MP_OUT: pipe_num = ATH10K_USB_PIPE_TX_DATA_MP; *urb_count = TX_URB_COUNT; break; case ATH10K_USB_EP_ADDR_APP_DATA_HP_OUT: pipe_num = ATH10K_USB_PIPE_TX_DATA_HP; *urb_count = TX_URB_COUNT; break; default: /* note: there may be endpoints not currently used */ break; } return pipe_num; } static int ath10k_usb_alloc_pipe_resources(struct ath10k *ar, struct ath10k_usb_pipe *pipe, int urb_cnt) { struct ath10k_urb_context *urb_context; int i; INIT_LIST_HEAD(&pipe->urb_list_head); init_usb_anchor(&pipe->urb_submitted); for (i = 0; i < urb_cnt; i++) { urb_context = kzalloc(sizeof(*urb_context), GFP_KERNEL); if (!urb_context) return -ENOMEM; urb_context->pipe = pipe; /* we are only allocate the urb contexts here, the actual URB * is allocated from the kernel as needed to do a transaction */ pipe->urb_alloc++; ath10k_usb_free_urb_to_pipe(pipe, urb_context); } ath10k_dbg(ar, ATH10K_DBG_USB, "usb alloc resources lpipe %d hpipe 0x%x urbs %d\n", pipe->logical_pipe_num, pipe->usb_pipe_handle, pipe->urb_alloc); return 0; } static int ath10k_usb_setup_pipe_resources(struct ath10k *ar, struct usb_interface *interface) { struct ath10k_usb *ar_usb = ath10k_usb_priv(ar); struct usb_host_interface *iface_desc = interface->cur_altsetting; struct usb_endpoint_descriptor *endpoint; struct ath10k_usb_pipe *pipe; int ret, i, urbcount; u8 pipe_num; ath10k_dbg(ar, ATH10K_DBG_USB, "usb setting up pipes using interface\n"); /* walk descriptors and setup pipes */ for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { endpoint = &iface_desc->endpoint[i].desc; if (ATH10K_USB_IS_BULK_EP(endpoint->bmAttributes)) { ath10k_dbg(ar, ATH10K_DBG_USB, "usb %s bulk ep 0x%2.2x maxpktsz %d\n", ATH10K_USB_IS_DIR_IN (endpoint->bEndpointAddress) ? "rx" : "tx", endpoint->bEndpointAddress, le16_to_cpu(endpoint->wMaxPacketSize)); } else if (ATH10K_USB_IS_INT_EP(endpoint->bmAttributes)) { ath10k_dbg(ar, ATH10K_DBG_USB, "usb %s int ep 0x%2.2x maxpktsz %d interval %d\n", ATH10K_USB_IS_DIR_IN (endpoint->bEndpointAddress) ? "rx" : "tx", endpoint->bEndpointAddress, le16_to_cpu(endpoint->wMaxPacketSize), endpoint->bInterval); } else if (ATH10K_USB_IS_ISOC_EP(endpoint->bmAttributes)) { /* TODO for ISO */ ath10k_dbg(ar, ATH10K_DBG_USB, "usb %s isoc ep 0x%2.2x maxpktsz %d interval %d\n", ATH10K_USB_IS_DIR_IN (endpoint->bEndpointAddress) ? "rx" : "tx", endpoint->bEndpointAddress, le16_to_cpu(endpoint->wMaxPacketSize), endpoint->bInterval); } /* Ignore broken descriptors. */ if (usb_endpoint_maxp(endpoint) == 0) continue; urbcount = 0; pipe_num = ath10k_usb_get_logical_pipe_num(endpoint->bEndpointAddress, &urbcount); if (pipe_num == ATH10K_USB_PIPE_INVALID) continue; pipe = &ar_usb->pipes[pipe_num]; if (pipe->ar_usb) /* hmmm..pipe was already setup */ continue; pipe->ar_usb = ar_usb; pipe->logical_pipe_num = pipe_num; pipe->ep_address = endpoint->bEndpointAddress; pipe->max_packet_size = le16_to_cpu(endpoint->wMaxPacketSize); if (ATH10K_USB_IS_BULK_EP(endpoint->bmAttributes)) { if (ATH10K_USB_IS_DIR_IN(pipe->ep_address)) { pipe->usb_pipe_handle = usb_rcvbulkpipe(ar_usb->udev, pipe->ep_address); } else { pipe->usb_pipe_handle = usb_sndbulkpipe(ar_usb->udev, pipe->ep_address); } } else if (ATH10K_USB_IS_INT_EP(endpoint->bmAttributes)) { if (ATH10K_USB_IS_DIR_IN(pipe->ep_address)) { pipe->usb_pipe_handle = usb_rcvintpipe(ar_usb->udev, pipe->ep_address); } else { pipe->usb_pipe_handle = usb_sndintpipe(ar_usb->udev, pipe->ep_address); } } else if (ATH10K_USB_IS_ISOC_EP(endpoint->bmAttributes)) { /* TODO for ISO */ if (ATH10K_USB_IS_DIR_IN(pipe->ep_address)) { pipe->usb_pipe_handle = usb_rcvisocpipe(ar_usb->udev, pipe->ep_address); } else { pipe->usb_pipe_handle = usb_sndisocpipe(ar_usb->udev, pipe->ep_address); } } pipe->ep_desc = endpoint; if (!ATH10K_USB_IS_DIR_IN(pipe->ep_address)) pipe->flags |= ATH10K_USB_PIPE_FLAG_TX; ret = ath10k_usb_alloc_pipe_resources(ar, pipe, urbcount); if (ret) return ret; } return 0; } static int ath10k_usb_create(struct ath10k *ar, struct usb_interface *interface) { struct ath10k_usb *ar_usb = ath10k_usb_priv(ar); struct usb_device *dev = interface_to_usbdev(interface); struct ath10k_usb_pipe *pipe; int ret, i; usb_set_intfdata(interface, ar_usb); spin_lock_init(&ar_usb->cs_lock); ar_usb->udev = dev; ar_usb->interface = interface; for (i = 0; i < ATH10K_USB_PIPE_MAX; i++) { pipe = &ar_usb->pipes[i]; INIT_WORK(&pipe->io_complete_work, ath10k_usb_io_comp_work); skb_queue_head_init(&pipe->io_comp_queue); } ar_usb->diag_cmd_buffer = kzalloc(ATH10K_USB_MAX_DIAG_CMD, GFP_KERNEL); if (!ar_usb->diag_cmd_buffer) { ret = -ENOMEM; goto err; } ar_usb->diag_resp_buffer = kzalloc(ATH10K_USB_MAX_DIAG_RESP, GFP_KERNEL); if (!ar_usb->diag_resp_buffer) { ret = -ENOMEM; goto err; } ret = ath10k_usb_setup_pipe_resources(ar, interface); if (ret) goto err; return 0; err: ath10k_usb_destroy(ar); return ret; } static int ath10k_usb_napi_poll(struct napi_struct *ctx, int budget) { struct ath10k *ar = container_of(ctx, struct ath10k, napi); int done; done = ath10k_htt_rx_hl_indication(ar, budget); ath10k_dbg(ar, ATH10K_DBG_USB, "napi poll: done: %d, budget:%d\n", done, budget); if (done < budget) napi_complete_done(ctx, done); return done; } /* ath10k usb driver registered functions */ static int ath10k_usb_probe(struct usb_interface *interface, const struct usb_device_id *id) { struct ath10k *ar; struct ath10k_usb *ar_usb; struct usb_device *dev = interface_to_usbdev(interface); int ret, vendor_id, product_id; enum ath10k_hw_rev hw_rev; struct ath10k_bus_params bus_params = {}; /* Assumption: All USB based chipsets (so far) are QCA9377 based. * If there will be newer chipsets that does not use the hw reg * setup as defined in qca6174_regs and qca6174_values, this * assumption is no longer valid and hw_rev must be setup differently * depending on chipset. */ hw_rev = ATH10K_HW_QCA9377; ar = ath10k_core_create(sizeof(*ar_usb), &dev->dev, ATH10K_BUS_USB, hw_rev, &ath10k_usb_hif_ops); if (!ar) { dev_err(&dev->dev, "failed to allocate core\n"); return -ENOMEM; } netif_napi_add(ar->napi_dev, &ar->napi, ath10k_usb_napi_poll); usb_get_dev(dev); vendor_id = le16_to_cpu(dev->descriptor.idVendor); product_id = le16_to_cpu(dev->descriptor.idProduct); ath10k_dbg(ar, ATH10K_DBG_BOOT, "usb new func vendor 0x%04x product 0x%04x\n", vendor_id, product_id); ar_usb = ath10k_usb_priv(ar); ret = ath10k_usb_create(ar, interface); if (ret) goto err; ar_usb->ar = ar; ar->dev_id = product_id; ar->id.vendor = vendor_id; ar->id.device = product_id; bus_params.dev_type = ATH10K_DEV_TYPE_HL; /* TODO: don't know yet how to get chip_id with USB */ bus_params.chip_id = 0; bus_params.hl_msdu_ids = true; ret = ath10k_core_register(ar, &bus_params); if (ret) { ath10k_warn(ar, "failed to register driver core: %d\n", ret); goto err_usb_destroy; } /* TODO: remove this once USB support is fully implemented */ ath10k_warn(ar, "Warning: ath10k USB support is incomplete, don't expect anything to work!\n"); return 0; err_usb_destroy: ath10k_usb_destroy(ar); err: ath10k_core_destroy(ar); usb_put_dev(dev); return ret; } static void ath10k_usb_remove(struct usb_interface *interface) { struct ath10k_usb *ar_usb; ar_usb = usb_get_intfdata(interface); if (!ar_usb) return; ath10k_core_unregister(ar_usb->ar); netif_napi_del(&ar_usb->ar->napi); ath10k_usb_destroy(ar_usb->ar); usb_put_dev(interface_to_usbdev(interface)); ath10k_core_destroy(ar_usb->ar); } #ifdef CONFIG_PM static int ath10k_usb_pm_suspend(struct usb_interface *interface, pm_message_t message) { struct ath10k_usb *ar_usb = usb_get_intfdata(interface); ath10k_usb_flush_all(ar_usb->ar); return 0; } static int ath10k_usb_pm_resume(struct usb_interface *interface) { struct ath10k_usb *ar_usb = usb_get_intfdata(interface); struct ath10k *ar = ar_usb->ar; ath10k_usb_post_recv_transfers(ar, &ar_usb->pipes[ATH10K_USB_PIPE_RX_DATA]); return 0; } #else #define ath10k_usb_pm_suspend NULL #define ath10k_usb_pm_resume NULL #endif /* table of devices that work with this driver */ static struct usb_device_id ath10k_usb_ids[] = { {USB_DEVICE(0x13b1, 0x0042)}, /* Linksys WUSB6100M */ { /* Terminating entry */ }, }; MODULE_DEVICE_TABLE(usb, ath10k_usb_ids); static struct usb_driver ath10k_usb_driver = { .name = "ath10k_usb", .probe = ath10k_usb_probe, .suspend = ath10k_usb_pm_suspend, .resume = ath10k_usb_pm_resume, .disconnect = ath10k_usb_remove, .id_table = ath10k_usb_ids, .supports_autosuspend = true, .disable_hub_initiated_lpm = 1, }; module_usb_driver(ath10k_usb_driver); MODULE_AUTHOR("Atheros Communications, Inc."); MODULE_DESCRIPTION("Driver support for Qualcomm Atheros USB 802.11ac WLAN devices"); MODULE_LICENSE("Dual BSD/GPL"); |
| 2 2 2 2 2 2 2 1 5 5 4 4 4 4 4 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/usb/input.h> #include <linux/unaligned.h> /* * Pressure-threshold modules param code from Alex Perry <alex.perry@ieee.org> */ MODULE_AUTHOR("Josh Myer <josh@joshisanerd.com>"); MODULE_DESCRIPTION("USB KB Gear JamStudio Tablet driver"); MODULE_LICENSE("GPL"); #define USB_VENDOR_ID_KBGEAR 0x084e static int kb_pressure_click = 0x10; module_param(kb_pressure_click, int, 0); MODULE_PARM_DESC(kb_pressure_click, "pressure threshold for clicks"); struct kbtab { unsigned char *data; dma_addr_t data_dma; struct input_dev *dev; struct usb_interface *intf; struct urb *irq; char phys[32]; }; static void kbtab_irq(struct urb *urb) { struct kbtab *kbtab = urb->context; unsigned char *data = kbtab->data; struct input_dev *dev = kbtab->dev; int pressure; int retval; switch (urb->status) { case 0: /* success */ break; case -ECONNRESET: case -ENOENT: case -ESHUTDOWN: /* this urb is terminated, clean up */ dev_dbg(&kbtab->intf->dev, "%s - urb shutting down with status: %d\n", __func__, urb->status); return; default: dev_dbg(&kbtab->intf->dev, "%s - nonzero urb status received: %d\n", __func__, urb->status); goto exit; } input_report_key(dev, BTN_TOOL_PEN, 1); input_report_abs(dev, ABS_X, get_unaligned_le16(&data[1])); input_report_abs(dev, ABS_Y, get_unaligned_le16(&data[3])); /*input_report_key(dev, BTN_TOUCH , data[0] & 0x01);*/ input_report_key(dev, BTN_RIGHT, data[0] & 0x02); pressure = data[5]; if (kb_pressure_click == -1) input_report_abs(dev, ABS_PRESSURE, pressure); else input_report_key(dev, BTN_LEFT, pressure > kb_pressure_click ? 1 : 0); input_sync(dev); exit: retval = usb_submit_urb(urb, GFP_ATOMIC); if (retval) dev_err(&kbtab->intf->dev, "%s - usb_submit_urb failed with result %d\n", __func__, retval); } static const struct usb_device_id kbtab_ids[] = { { USB_DEVICE(USB_VENDOR_ID_KBGEAR, 0x1001), .driver_info = 0 }, { } }; MODULE_DEVICE_TABLE(usb, kbtab_ids); static int kbtab_open(struct input_dev *dev) { struct kbtab *kbtab = input_get_drvdata(dev); struct usb_device *udev = interface_to_usbdev(kbtab->intf); kbtab->irq->dev = udev; if (usb_submit_urb(kbtab->irq, GFP_KERNEL)) return -EIO; return 0; } static void kbtab_close(struct input_dev *dev) { struct kbtab *kbtab = input_get_drvdata(dev); usb_kill_urb(kbtab->irq); } static int kbtab_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct usb_device *dev = interface_to_usbdev(intf); struct usb_endpoint_descriptor *endpoint; struct kbtab *kbtab; struct input_dev *input_dev; int error = -ENOMEM; if (intf->cur_altsetting->desc.bNumEndpoints < 1) return -ENODEV; endpoint = &intf->cur_altsetting->endpoint[0].desc; if (!usb_endpoint_is_int_in(endpoint)) return -ENODEV; kbtab = kzalloc(sizeof(*kbtab), GFP_KERNEL); input_dev = input_allocate_device(); if (!kbtab || !input_dev) goto fail1; kbtab->data = usb_alloc_coherent(dev, 8, GFP_KERNEL, &kbtab->data_dma); if (!kbtab->data) goto fail1; kbtab->irq = usb_alloc_urb(0, GFP_KERNEL); if (!kbtab->irq) goto fail2; kbtab->intf = intf; kbtab->dev = input_dev; usb_make_path(dev, kbtab->phys, sizeof(kbtab->phys)); strlcat(kbtab->phys, "/input0", sizeof(kbtab->phys)); input_dev->name = "KB Gear Tablet"; input_dev->phys = kbtab->phys; usb_to_input_id(dev, &input_dev->id); input_dev->dev.parent = &intf->dev; input_set_drvdata(input_dev, kbtab); input_dev->open = kbtab_open; input_dev->close = kbtab_close; input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS); input_dev->keybit[BIT_WORD(BTN_LEFT)] |= BIT_MASK(BTN_LEFT) | BIT_MASK(BTN_RIGHT); input_dev->keybit[BIT_WORD(BTN_DIGI)] |= BIT_MASK(BTN_TOOL_PEN) | BIT_MASK(BTN_TOUCH); input_set_abs_params(input_dev, ABS_X, 0, 0x2000, 4, 0); input_set_abs_params(input_dev, ABS_Y, 0, 0x1750, 4, 0); input_set_abs_params(input_dev, ABS_PRESSURE, 0, 0xff, 0, 0); usb_fill_int_urb(kbtab->irq, dev, usb_rcvintpipe(dev, endpoint->bEndpointAddress), kbtab->data, 8, kbtab_irq, kbtab, endpoint->bInterval); kbtab->irq->transfer_dma = kbtab->data_dma; kbtab->irq->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; error = input_register_device(kbtab->dev); if (error) goto fail3; usb_set_intfdata(intf, kbtab); return 0; fail3: usb_free_urb(kbtab->irq); fail2: usb_free_coherent(dev, 8, kbtab->data, kbtab->data_dma); fail1: input_free_device(input_dev); kfree(kbtab); return error; } static void kbtab_disconnect(struct usb_interface *intf) { struct kbtab *kbtab = usb_get_intfdata(intf); struct usb_device *udev = interface_to_usbdev(intf); usb_set_intfdata(intf, NULL); input_unregister_device(kbtab->dev); usb_free_urb(kbtab->irq); usb_free_coherent(udev, 8, kbtab->data, kbtab->data_dma); kfree(kbtab); } static struct usb_driver kbtab_driver = { .name = "kbtab", .probe = kbtab_probe, .disconnect = kbtab_disconnect, .id_table = kbtab_ids, }; module_usb_driver(kbtab_driver); |
| 2 2 2 4 4 4 4 4 4 4 2 4 4 4 4 2 2 2 2 2 1 2 4 4 1 6 5 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 | // SPDX-License-Identifier: GPL-2.0-only /* * vsock sock_diag(7) module * * Copyright (C) 2017 Red Hat, Inc. * Author: Stefan Hajnoczi <stefanha@redhat.com> */ #include <linux/module.h> #include <linux/sock_diag.h> #include <linux/vm_sockets_diag.h> #include <net/af_vsock.h> static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, u32 portid, u32 seq, u32 flags) { struct vsock_sock *vsk = vsock_sk(sk); struct vsock_diag_msg *rep; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep), flags); if (!nlh) return -EMSGSIZE; rep = nlmsg_data(nlh); rep->vdiag_family = AF_VSOCK; /* Lock order dictates that sk_lock is acquired before * vsock_table_lock, so we cannot lock here. Simply don't take * sk_lock; sk is guaranteed to stay alive since vsock_table_lock is * held. */ rep->vdiag_type = sk->sk_type; rep->vdiag_state = sk->sk_state; rep->vdiag_shutdown = sk->sk_shutdown; rep->vdiag_src_cid = vsk->local_addr.svm_cid; rep->vdiag_src_port = vsk->local_addr.svm_port; rep->vdiag_dst_cid = vsk->remote_addr.svm_cid; rep->vdiag_dst_port = vsk->remote_addr.svm_port; rep->vdiag_ino = sock_i_ino(sk); sock_diag_save_cookie(sk, rep->vdiag_cookie); return 0; } static int vsock_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct vsock_diag_req *req; struct vsock_sock *vsk; unsigned int bucket; unsigned int last_i; unsigned int table; struct net *net; unsigned int i; req = nlmsg_data(cb->nlh); net = sock_net(skb->sk); /* State saved between calls: */ table = cb->args[0]; bucket = cb->args[1]; i = last_i = cb->args[2]; /* TODO VMCI pending sockets? */ spin_lock_bh(&vsock_table_lock); /* Bind table (locally created sockets) */ if (table == 0) { while (bucket < ARRAY_SIZE(vsock_bind_table)) { struct list_head *head = &vsock_bind_table[bucket]; i = 0; list_for_each_entry(vsk, head, bound_table) { struct sock *sk = sk_vsock(vsk); if (!net_eq(sock_net(sk), net)) continue; if (i < last_i) goto next_bind; if (!(req->vdiag_states & (1 << sk->sk_state))) goto next_bind; if (sk_diag_fill(sk, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) goto done; next_bind: i++; } last_i = 0; bucket++; } table++; bucket = 0; } /* Connected table (accepted connections) */ while (bucket < ARRAY_SIZE(vsock_connected_table)) { struct list_head *head = &vsock_connected_table[bucket]; i = 0; list_for_each_entry(vsk, head, connected_table) { struct sock *sk = sk_vsock(vsk); /* Skip sockets we've already seen above */ if (__vsock_in_bound_table(vsk)) continue; if (!net_eq(sock_net(sk), net)) continue; if (i < last_i) goto next_connected; if (!(req->vdiag_states & (1 << sk->sk_state))) goto next_connected; if (sk_diag_fill(sk, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) goto done; next_connected: i++; } last_i = 0; bucket++; } done: spin_unlock_bh(&vsock_table_lock); cb->args[0] = table; cb->args[1] = bucket; cb->args[2] = i; return skb->len; } static int vsock_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) { int hdrlen = sizeof(struct vsock_diag_req); struct net *net = sock_net(skb->sk); if (nlmsg_len(h) < hdrlen) return -EINVAL; if (h->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .dump = vsock_diag_dump, }; return netlink_dump_start(net->diag_nlsk, skb, h, &c); } return -EOPNOTSUPP; } static const struct sock_diag_handler vsock_diag_handler = { .owner = THIS_MODULE, .family = AF_VSOCK, .dump = vsock_diag_handler_dump, }; static int __init vsock_diag_init(void) { return sock_diag_register(&vsock_diag_handler); } static void __exit vsock_diag_exit(void) { sock_diag_unregister(&vsock_diag_handler); } module_init(vsock_diag_init); module_exit(vsock_diag_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("VMware Virtual Sockets monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 40 /* AF_VSOCK */); |
| 30 30 30 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* mpihelp-mul_2.c - MPI helper functions * Copyright (C) 1994, 1996, 1997, 1998, 2001 Free Software Foundation, Inc. * * This file is part of GnuPG. * * Note: This code is heavily based on the GNU MP Library. * Actually it's the same code with only minor changes in the * way the data is stored; this is to support the abstraction * of an optional secure memory allocation which may be used * to avoid revealing of sensitive data due to paging etc. * The GNU MP Library itself is published under the LGPL; * however I decided to publish this code under the plain GPL. */ #include "mpi-internal.h" #include "longlong.h" mpi_limb_t mpihelp_addmul_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, mpi_size_t s1_size, mpi_limb_t s2_limb) { mpi_limb_t cy_limb; mpi_size_t j; mpi_limb_t prod_high, prod_low; mpi_limb_t x; /* The loop counter and index J goes from -SIZE to -1. This way * the loop becomes faster. */ j = -s1_size; res_ptr -= j; s1_ptr -= j; cy_limb = 0; do { umul_ppmm(prod_high, prod_low, s1_ptr[j], s2_limb); prod_low += cy_limb; cy_limb = (prod_low < cy_limb ? 1 : 0) + prod_high; x = res_ptr[j]; prod_low = x + prod_low; cy_limb += prod_low < x ? 1 : 0; res_ptr[j] = prod_low; } while (++j); return cy_limb; } |
| 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 | // SPDX-License-Identifier: GPL-2.0 #ifndef _MEDIA_FRAME_VECTOR_H #define _MEDIA_FRAME_VECTOR_H /* Container for pinned pfns / pages in frame_vector.c */ struct frame_vector { unsigned int nr_allocated; /* Number of frames we have space for */ unsigned int nr_frames; /* Number of frames stored in ptrs array */ bool got_ref; /* Did we pin pages by getting page ref? */ bool is_pfns; /* Does array contain pages or pfns? */ void *ptrs[]; /* Array of pinned pfns / pages. Use * pfns_vector_pages() or pfns_vector_pfns() * for access */ }; struct frame_vector *frame_vector_create(unsigned int nr_frames); void frame_vector_destroy(struct frame_vector *vec); int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, bool write, struct frame_vector *vec); void put_vaddr_frames(struct frame_vector *vec); int frame_vector_to_pages(struct frame_vector *vec); void frame_vector_to_pfns(struct frame_vector *vec); static inline unsigned int frame_vector_count(struct frame_vector *vec) { return vec->nr_frames; } static inline struct page **frame_vector_pages(struct frame_vector *vec) { if (vec->is_pfns) { int err = frame_vector_to_pages(vec); if (err) return ERR_PTR(err); } return (struct page **)(vec->ptrs); } static inline unsigned long *frame_vector_pfns(struct frame_vector *vec) { if (!vec->is_pfns) frame_vector_to_pfns(vec); return (unsigned long *)(vec->ptrs); } #endif /* _MEDIA_FRAME_VECTOR_H */ |
| 3 3 3 3 2 1 1 1 2 1 1 2 1 1 1 3 29 30 29 29 28 5 2 26 23 16 24 24 21 26 25 30 26 23 25 22 21 9 19 58 56 58 19 19 58 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * read/write/select interface to device file * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include "seq_oss_device.h" #include "seq_oss_readq.h" #include "seq_oss_writeq.h" #include "seq_oss_synth.h" #include <sound/seq_oss_legacy.h> #include "seq_oss_event.h" #include "seq_oss_timer.h" #include "../seq_clientmgr.h" /* * protoypes */ static int insert_queue(struct seq_oss_devinfo *dp, union evrec *rec, struct file *opt); /* * read interface */ int snd_seq_oss_read(struct seq_oss_devinfo *dp, char __user *buf, int count) { struct seq_oss_readq *readq = dp->readq; int result = 0, err = 0; int ev_len; union evrec rec; unsigned long flags; if (readq == NULL || ! is_read_mode(dp->file_mode)) return -ENXIO; while (count >= SHORT_EVENT_SIZE) { snd_seq_oss_readq_lock(readq, flags); err = snd_seq_oss_readq_pick(readq, &rec); if (err == -EAGAIN && !is_nonblock_mode(dp->file_mode) && result == 0) { snd_seq_oss_readq_unlock(readq, flags); snd_seq_oss_readq_wait(readq); snd_seq_oss_readq_lock(readq, flags); if (signal_pending(current)) err = -ERESTARTSYS; else err = snd_seq_oss_readq_pick(readq, &rec); } if (err < 0) { snd_seq_oss_readq_unlock(readq, flags); break; } ev_len = ev_length(&rec); if (ev_len < count) { snd_seq_oss_readq_unlock(readq, flags); break; } snd_seq_oss_readq_free(readq); snd_seq_oss_readq_unlock(readq, flags); if (copy_to_user(buf, &rec, ev_len)) { err = -EFAULT; break; } result += ev_len; buf += ev_len; count -= ev_len; } return result > 0 ? result : err; } /* * write interface */ int snd_seq_oss_write(struct seq_oss_devinfo *dp, const char __user *buf, int count, struct file *opt) { int result = 0, err = 0; int ev_size, fmt; union evrec rec; if (! is_write_mode(dp->file_mode) || dp->writeq == NULL) return -ENXIO; while (count >= SHORT_EVENT_SIZE) { if (copy_from_user(&rec, buf, SHORT_EVENT_SIZE)) { err = -EFAULT; break; } if (rec.s.code == SEQ_FULLSIZE) { /* load patch */ if (result > 0) { err = -EINVAL; break; } fmt = (*(unsigned short *)rec.c) & 0xffff; /* FIXME the return value isn't correct */ return snd_seq_oss_synth_load_patch(dp, rec.s.dev, fmt, buf, 0, count); } if (ev_is_long(&rec)) { /* extended code */ if (rec.s.code == SEQ_EXTENDED && dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) { err = -EINVAL; break; } ev_size = LONG_EVENT_SIZE; if (count < ev_size) break; /* copy the reset 4 bytes */ if (copy_from_user(rec.c + SHORT_EVENT_SIZE, buf + SHORT_EVENT_SIZE, LONG_EVENT_SIZE - SHORT_EVENT_SIZE)) { err = -EFAULT; break; } } else { /* old-type code */ if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) { err = -EINVAL; break; } ev_size = SHORT_EVENT_SIZE; } /* insert queue */ err = insert_queue(dp, &rec, opt); if (err < 0) break; result += ev_size; buf += ev_size; count -= ev_size; } return result > 0 ? result : err; } /* * insert event record to write queue * return: 0 = OK, non-zero = NG */ static int insert_queue(struct seq_oss_devinfo *dp, union evrec *rec, struct file *opt) { int rc = 0; struct snd_seq_event event; /* if this is a timing event, process the current time */ if (snd_seq_oss_process_timer_event(dp->timer, rec)) return 0; /* no need to insert queue */ /* parse this event */ memset(&event, 0, sizeof(event)); /* set dummy -- to be sure */ event.type = SNDRV_SEQ_EVENT_NOTEOFF; snd_seq_oss_fill_addr(dp, &event, dp->addr.client, dp->addr.port); if (snd_seq_oss_process_event(dp, rec, &event)) return 0; /* invalid event - no need to insert queue */ event.time.tick = snd_seq_oss_timer_cur_tick(dp->timer); if (dp->timer->realtime || !dp->timer->running) snd_seq_oss_dispatch(dp, &event, 0, 0); else rc = snd_seq_kernel_client_enqueue(dp->cseq, &event, opt, !is_nonblock_mode(dp->file_mode)); return rc; } /* * select / poll */ __poll_t snd_seq_oss_poll(struct seq_oss_devinfo *dp, struct file *file, poll_table * wait) { __poll_t mask = 0; /* input */ if (dp->readq && is_read_mode(dp->file_mode)) { if (snd_seq_oss_readq_poll(dp->readq, file, wait)) mask |= EPOLLIN | EPOLLRDNORM; } /* output */ if (dp->writeq && is_write_mode(dp->file_mode)) { if (snd_seq_kernel_client_write_poll(dp->cseq, file, wait)) mask |= EPOLLOUT | EPOLLWRNORM; } return mask; } |
| 24 22 24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 | // SPDX-License-Identifier: GPL-2.0-or-later /* mpihelp-add_2.c - MPI helper functions * Copyright (C) 1994, 1996, 1997, 1998, 2001 Free Software Foundation, Inc. * * This file is part of GnuPG. * * Note: This code is heavily based on the GNU MP Library. * Actually it's the same code with only minor changes in the * way the data is stored; this is to support the abstraction * of an optional secure memory allocation which may be used * to avoid revealing of sensitive data due to paging etc. * The GNU MP Library itself is published under the LGPL; * however I decided to publish this code under the plain GPL. */ #include "mpi-internal.h" #include "longlong.h" mpi_limb_t mpihelp_sub_n(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, mpi_ptr_t s2_ptr, mpi_size_t size) { mpi_limb_t x, y, cy; mpi_size_t j; /* The loop counter and index J goes from -SIZE to -1. This way the loop becomes faster. */ j = -size; /* Offset the base pointers to compensate for the negative indices. */ s1_ptr -= j; s2_ptr -= j; res_ptr -= j; cy = 0; do { y = s2_ptr[j]; x = s1_ptr[j]; y += cy; /* add previous carry to subtrahend */ cy = y < cy; /* get out carry from that addition */ y = x - y; /* main subtract */ cy += y > x; /* get out carry from the subtract, combine */ res_ptr[j] = y; } while (++j); return cy; } |
| 1 14 2 84 84 83 46 6 49 1 75 12 13 13 1 11 11 10 2 12 5 6 6 1 4 4 3 2 5 4 3 4 2 1 1 1 1 1 2 2 1 1 9 9 8 8 8 8 8 9 10 2 10 10 10 10 10 10 10 8 8 8 8 8 1 5 5 5 2 2 4 13 12 11 11 6 8 4 2 2 2 2 2 2 1 2 4 2 1 2 3 2 3 5 5 6 3 11 13 6 1 1 3 3 3 2 3 3 5 4 3 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 | // SPDX-License-Identifier: GPL-2.0+ /* * NILFS pathname lookup operations. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * * Modified for NILFS by Amagai Yoshiji and Ryusuke Konishi. */ /* * linux/fs/ext2/namei.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/namei.c * * Copyright (C) 1991, 1992 Linus Torvalds * * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 */ #include <linux/pagemap.h> #include "nilfs.h" #include "export.h" #define NILFS_FID_SIZE_NON_CONNECTABLE \ (offsetof(struct nilfs_fid, parent_gen) / 4) #define NILFS_FID_SIZE_CONNECTABLE (sizeof(struct nilfs_fid) / 4) static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode) { int err = nilfs_add_link(dentry, inode); if (!err) { d_instantiate_new(dentry, inode); return 0; } inode_dec_link_count(inode); unlock_new_inode(inode); iput(inode); return err; } /* * Methods themselves. */ static struct dentry * nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode; ino_t ino; int res; if (dentry->d_name.len > NILFS_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); res = nilfs_inode_by_name(dir, &dentry->d_name, &ino); if (res) { if (res != -ENOENT) return ERR_PTR(res); inode = NULL; } else { inode = nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino); if (inode == ERR_PTR(-ESTALE)) { nilfs_error(dir->i_sb, "deleted inode referenced: %lu", ino); return ERR_PTR(-EIO); } } return d_splice_alias(inode, dentry); } /* * By the time this is called, we already have created * the directory cache entry for the new file, but it * is so far negative - it has no inode. * * If the create succeeds, we fill in the inode information * with d_instantiate(). */ static int nilfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode; struct nilfs_transaction_info ti; int err; err = nilfs_transaction_begin(dir->i_sb, &ti, 1); if (err) return err; inode = nilfs_new_inode(dir, mode); err = PTR_ERR(inode); if (!IS_ERR(inode)) { inode->i_op = &nilfs_file_inode_operations; inode->i_fop = &nilfs_file_operations; inode->i_mapping->a_ops = &nilfs_aops; nilfs_mark_inode_dirty(inode); err = nilfs_add_nondir(dentry, inode); } if (!err) err = nilfs_transaction_commit(dir->i_sb); else nilfs_transaction_abort(dir->i_sb); return err; } static int nilfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode *inode; struct nilfs_transaction_info ti; int err; err = nilfs_transaction_begin(dir->i_sb, &ti, 1); if (err) return err; inode = nilfs_new_inode(dir, mode); err = PTR_ERR(inode); if (!IS_ERR(inode)) { init_special_inode(inode, inode->i_mode, rdev); nilfs_mark_inode_dirty(inode); err = nilfs_add_nondir(dentry, inode); } if (!err) err = nilfs_transaction_commit(dir->i_sb); else nilfs_transaction_abort(dir->i_sb); return err; } static int nilfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct nilfs_transaction_info ti; struct super_block *sb = dir->i_sb; unsigned int l = strlen(symname) + 1; struct inode *inode; int err; if (l > sb->s_blocksize) return -ENAMETOOLONG; err = nilfs_transaction_begin(dir->i_sb, &ti, 1); if (err) return err; inode = nilfs_new_inode(dir, S_IFLNK | 0777); err = PTR_ERR(inode); if (IS_ERR(inode)) goto out; /* slow symlink */ inode->i_op = &nilfs_symlink_inode_operations; inode_nohighmem(inode); mapping_set_gfp_mask(inode->i_mapping, mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS)); inode->i_mapping->a_ops = &nilfs_aops; err = page_symlink(inode, symname, l); if (err) goto out_fail; /* mark_inode_dirty(inode); */ /* page_symlink() do this */ err = nilfs_add_nondir(dentry, inode); out: if (!err) err = nilfs_transaction_commit(dir->i_sb); else nilfs_transaction_abort(dir->i_sb); return err; out_fail: drop_nlink(inode); nilfs_mark_inode_dirty(inode); unlock_new_inode(inode); iput(inode); goto out; } static int nilfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); struct nilfs_transaction_info ti; int err; err = nilfs_transaction_begin(dir->i_sb, &ti, 1); if (err) return err; inode_set_ctime_current(inode); inode_inc_link_count(inode); ihold(inode); err = nilfs_add_link(dentry, inode); if (!err) { d_instantiate(dentry, inode); err = nilfs_transaction_commit(dir->i_sb); } else { inode_dec_link_count(inode); iput(inode); nilfs_transaction_abort(dir->i_sb); } return err; } static struct dentry *nilfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; struct nilfs_transaction_info ti; int err; err = nilfs_transaction_begin(dir->i_sb, &ti, 1); if (err) return ERR_PTR(err); inc_nlink(dir); inode = nilfs_new_inode(dir, S_IFDIR | mode); err = PTR_ERR(inode); if (IS_ERR(inode)) goto out_dir; inode->i_op = &nilfs_dir_inode_operations; inode->i_fop = &nilfs_dir_operations; inode->i_mapping->a_ops = &nilfs_aops; inc_nlink(inode); err = nilfs_make_empty(inode, dir); if (err) goto out_fail; err = nilfs_add_link(dentry, inode); if (err) goto out_fail; nilfs_mark_inode_dirty(inode); d_instantiate_new(dentry, inode); out: if (!err) err = nilfs_transaction_commit(dir->i_sb); else nilfs_transaction_abort(dir->i_sb); return ERR_PTR(err); out_fail: drop_nlink(inode); drop_nlink(inode); nilfs_mark_inode_dirty(inode); unlock_new_inode(inode); iput(inode); out_dir: drop_nlink(dir); nilfs_mark_inode_dirty(dir); goto out; } static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode; struct nilfs_dir_entry *de; struct folio *folio; int err; de = nilfs_find_entry(dir, &dentry->d_name, &folio); if (IS_ERR(de)) { err = PTR_ERR(de); goto out; } inode = d_inode(dentry); err = -EIO; if (le64_to_cpu(de->inode) != inode->i_ino) goto out; if (!inode->i_nlink) { nilfs_warn(inode->i_sb, "deleting nonexistent file (ino=%lu), %d", inode->i_ino, inode->i_nlink); set_nlink(inode, 1); } err = nilfs_delete_entry(de, folio); folio_release_kmap(folio, de); if (err) goto out; inode_set_ctime_to_ts(inode, inode_get_ctime(dir)); drop_nlink(inode); err = 0; out: return err; } static int nilfs_unlink(struct inode *dir, struct dentry *dentry) { struct nilfs_transaction_info ti; int err; err = nilfs_transaction_begin(dir->i_sb, &ti, 0); if (err) return err; err = nilfs_do_unlink(dir, dentry); if (!err) { nilfs_mark_inode_dirty(dir); nilfs_mark_inode_dirty(d_inode(dentry)); err = nilfs_transaction_commit(dir->i_sb); } else nilfs_transaction_abort(dir->i_sb); return err; } static int nilfs_rmdir(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); struct nilfs_transaction_info ti; int err; err = nilfs_transaction_begin(dir->i_sb, &ti, 0); if (err) return err; err = -ENOTEMPTY; if (nilfs_empty_dir(inode)) { err = nilfs_do_unlink(dir, dentry); if (!err) { inode->i_size = 0; drop_nlink(inode); nilfs_mark_inode_dirty(inode); drop_nlink(dir); nilfs_mark_inode_dirty(dir); } } if (!err) err = nilfs_transaction_commit(dir->i_sb); else nilfs_transaction_abort(dir->i_sb); return err; } static int nilfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); struct folio *dir_folio = NULL; struct nilfs_dir_entry *dir_de = NULL; struct folio *old_folio; struct nilfs_dir_entry *old_de; struct nilfs_transaction_info ti; bool old_is_dir = S_ISDIR(old_inode->i_mode); int err; if (flags & ~RENAME_NOREPLACE) return -EINVAL; err = nilfs_transaction_begin(old_dir->i_sb, &ti, 1); if (unlikely(err)) return err; old_de = nilfs_find_entry(old_dir, &old_dentry->d_name, &old_folio); if (IS_ERR(old_de)) { err = PTR_ERR(old_de); goto out; } if (old_is_dir && old_dir != new_dir) { err = -EIO; dir_de = nilfs_dotdot(old_inode, &dir_folio); if (!dir_de) goto out_old; } if (new_inode) { struct folio *new_folio; struct nilfs_dir_entry *new_de; err = -ENOTEMPTY; if (old_is_dir && !nilfs_empty_dir(new_inode)) goto out_dir; new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, &new_folio); if (IS_ERR(new_de)) { err = PTR_ERR(new_de); goto out_dir; } err = nilfs_set_link(new_dir, new_de, new_folio, old_inode); folio_release_kmap(new_folio, new_de); if (unlikely(err)) goto out_dir; nilfs_mark_inode_dirty(new_dir); inode_set_ctime_current(new_inode); if (old_is_dir) drop_nlink(new_inode); drop_nlink(new_inode); nilfs_mark_inode_dirty(new_inode); } else { err = nilfs_add_link(new_dentry, old_inode); if (err) goto out_dir; if (old_is_dir) { inc_nlink(new_dir); nilfs_mark_inode_dirty(new_dir); } } /* * Like most other Unix systems, set the ctime for inodes on a * rename. */ inode_set_ctime_current(old_inode); err = nilfs_delete_entry(old_de, old_folio); if (likely(!err)) { if (old_is_dir) { if (old_dir != new_dir) err = nilfs_set_link(old_inode, dir_de, dir_folio, new_dir); drop_nlink(old_dir); } nilfs_mark_inode_dirty(old_dir); } nilfs_mark_inode_dirty(old_inode); out_dir: if (dir_de) folio_release_kmap(dir_folio, dir_de); out_old: folio_release_kmap(old_folio, old_de); out: if (likely(!err)) err = nilfs_transaction_commit(old_dir->i_sb); else nilfs_transaction_abort(old_dir->i_sb); return err; } /* * Export operations */ static struct dentry *nilfs_get_parent(struct dentry *child) { ino_t ino; int res; struct nilfs_root *root; res = nilfs_inode_by_name(d_inode(child), &dotdot_name, &ino); if (res) return ERR_PTR(res); root = NILFS_I(d_inode(child))->i_root; return d_obtain_alias(nilfs_iget(child->d_sb, root, ino)); } static struct dentry *nilfs_get_dentry(struct super_block *sb, u64 cno, u64 ino, u32 gen) { struct nilfs_root *root; struct inode *inode; if (ino < NILFS_FIRST_INO(sb) && ino != NILFS_ROOT_INO) return ERR_PTR(-ESTALE); root = nilfs_lookup_root(sb->s_fs_info, cno); if (!root) return ERR_PTR(-ESTALE); inode = nilfs_iget(sb, root, ino); nilfs_put_root(root); if (IS_ERR(inode)) return ERR_CAST(inode); if (gen && inode->i_generation != gen) { iput(inode); return ERR_PTR(-ESTALE); } return d_obtain_alias(inode); } static struct dentry *nilfs_fh_to_dentry(struct super_block *sb, struct fid *fh, int fh_len, int fh_type) { struct nilfs_fid *fid = (struct nilfs_fid *)fh; if (fh_len < NILFS_FID_SIZE_NON_CONNECTABLE || (fh_type != FILEID_NILFS_WITH_PARENT && fh_type != FILEID_NILFS_WITHOUT_PARENT)) return NULL; return nilfs_get_dentry(sb, fid->cno, fid->ino, fid->gen); } static struct dentry *nilfs_fh_to_parent(struct super_block *sb, struct fid *fh, int fh_len, int fh_type) { struct nilfs_fid *fid = (struct nilfs_fid *)fh; if (fh_len < NILFS_FID_SIZE_CONNECTABLE || fh_type != FILEID_NILFS_WITH_PARENT) return NULL; return nilfs_get_dentry(sb, fid->cno, fid->parent_ino, fid->parent_gen); } static int nilfs_encode_fh(struct inode *inode, __u32 *fh, int *lenp, struct inode *parent) { struct nilfs_fid *fid = (struct nilfs_fid *)fh; struct nilfs_root *root = NILFS_I(inode)->i_root; int type; if (parent && *lenp < NILFS_FID_SIZE_CONNECTABLE) { *lenp = NILFS_FID_SIZE_CONNECTABLE; return FILEID_INVALID; } if (*lenp < NILFS_FID_SIZE_NON_CONNECTABLE) { *lenp = NILFS_FID_SIZE_NON_CONNECTABLE; return FILEID_INVALID; } fid->cno = root->cno; fid->ino = inode->i_ino; fid->gen = inode->i_generation; if (parent) { fid->parent_ino = parent->i_ino; fid->parent_gen = parent->i_generation; type = FILEID_NILFS_WITH_PARENT; *lenp = NILFS_FID_SIZE_CONNECTABLE; } else { type = FILEID_NILFS_WITHOUT_PARENT; *lenp = NILFS_FID_SIZE_NON_CONNECTABLE; } return type; } const struct inode_operations nilfs_dir_inode_operations = { .create = nilfs_create, .lookup = nilfs_lookup, .link = nilfs_link, .unlink = nilfs_unlink, .symlink = nilfs_symlink, .mkdir = nilfs_mkdir, .rmdir = nilfs_rmdir, .mknod = nilfs_mknod, .rename = nilfs_rename, .setattr = nilfs_setattr, .permission = nilfs_permission, .fiemap = nilfs_fiemap, .fileattr_get = nilfs_fileattr_get, .fileattr_set = nilfs_fileattr_set, }; const struct inode_operations nilfs_special_inode_operations = { .setattr = nilfs_setattr, .permission = nilfs_permission, }; const struct inode_operations nilfs_symlink_inode_operations = { .get_link = page_get_link, .permission = nilfs_permission, }; const struct export_operations nilfs_export_ops = { .encode_fh = nilfs_encode_fh, .fh_to_dentry = nilfs_fh_to_dentry, .fh_to_parent = nilfs_fh_to_parent, .get_parent = nilfs_get_parent, }; |
| 5 63 63 34 34 1 33 63 64 64 64 4 3 1 63 63 63 63 63 17 54 52 50 52 48 22 54 63 396 402 396 395 393 31 396 2 97 96 3 2 94 93 92 4 91 11 2 9 91 27 96 26 28 22 5 18 22 5 18 49 66 32 31 27 25 30 2 62 18 52 48 41 41 41 5 5 5 5 5 5 10 1 1 1 1 1 4 4 2 2 2 2 2 14 11 13 12 25 25 17 13 17 1 16 16 4 3 4 3 1 16 13 14 4 14 11 3 11 11 3 1 16 25 2 2 2 2 2 2 1 2 2 2 29 4 29 3 1 4 4 29 27 27 1 27 1 26 3 3 2 27 1 27 5 2 2 1 1 1 1 1 2 27 1 27 1 27 1 27 27 1 4 1 27 5 5 4 4 4 27 1 27 8 83 86 83 82 7 75 68 13 12 5 3 5 2 9 9 9 4 1 84 5 7 4 6 4 5 8 13 12 2 11 15 14 14 13 11 10 8 9 9 10 9 9 8 1 7 6 5 4 3 2 2 1 7 6 3 2 1 5 4 3 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * common UDP/RAW code * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/interrupt.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in6.h> #include <linux/ipv6.h> #include <linux/route.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/icmp.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/transp_v6.h> #include <net/ip6_route.h> #include <net/tcp_states.h> #include <net/dsfield.h> #include <net/sock_reuseport.h> #include <linux/errqueue.h> #include <linux/uaccess.h> static bool ipv6_mapped_addr_any(const struct in6_addr *a) { return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0); } static void ip6_datagram_flow_key_init(struct flowi6 *fl6, const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); const struct ipv6_pinfo *np = inet6_sk(sk); int oif = sk->sk_bound_dev_if; memset(fl6, 0, sizeof(*fl6)); fl6->flowi6_proto = sk->sk_protocol; fl6->daddr = sk->sk_v6_daddr; fl6->saddr = np->saddr; fl6->flowi6_mark = sk->sk_mark; fl6->fl6_dport = inet->inet_dport; fl6->fl6_sport = inet->inet_sport; fl6->flowlabel = ip6_make_flowinfo(np->tclass, np->flow_label); fl6->flowi6_uid = sk_uid(sk); if (!oif) oif = np->sticky_pktinfo.ipi6_ifindex; if (!oif) { if (ipv6_addr_is_multicast(&fl6->daddr)) oif = READ_ONCE(np->mcast_oif); else oif = READ_ONCE(np->ucast_oif); } fl6->flowi6_oif = oif; security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6)); } int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr) { struct ip6_flowlabel *flowlabel = NULL; struct in6_addr *final_p, final; struct ipv6_txoptions *opt; struct dst_entry *dst; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct flowi6 fl6; int err = 0; if (inet6_test_bit(SNDFLOW, sk) && (np->flow_label & IPV6_FLOWLABEL_MASK)) { flowlabel = fl6_sock_lookup(sk, np->flow_label); if (IS_ERR(flowlabel)) return -EINVAL; } ip6_datagram_flow_key_init(&fl6, sk); rcu_read_lock(); opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt); final_p = fl6_update_dst(&fl6, opt, &final); rcu_read_unlock(); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; } if (fix_sk_saddr) { if (ipv6_addr_any(&np->saddr)) np->saddr = fl6.saddr; if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { sk->sk_v6_rcv_saddr = fl6.saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); } } ip6_sk_dst_store_flow(sk, dst, &fl6); out: fl6_sock_release(flowlabel); return err; } void ip6_datagram_release_cb(struct sock *sk) { struct dst_entry *dst; if (ipv6_addr_v4mapped(&sk->sk_v6_daddr)) return; rcu_read_lock(); dst = __sk_dst_get(sk); if (!dst || !READ_ONCE(dst->obsolete) || dst->ops->check(dst, inet6_sk(sk)->dst_cookie)) { rcu_read_unlock(); return; } rcu_read_unlock(); ip6_datagram_dst_update(sk, false); } EXPORT_SYMBOL_GPL(ip6_datagram_release_cb); int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *daddr, old_daddr; __be32 fl6_flowlabel = 0; __be32 old_fl6_flowlabel; __be16 old_dport; int addr_type; int err; if (usin->sin6_family == AF_INET) { if (ipv6_only_sock(sk)) return -EAFNOSUPPORT; err = __ip4_datagram_connect(sk, uaddr, addr_len); goto ipv4_connected; } if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; if (inet6_test_bit(SNDFLOW, sk)) fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK; if (ipv6_addr_any(&usin->sin6_addr)) { /* * connect to self */ if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK), &usin->sin6_addr); else usin->sin6_addr = in6addr_loopback; } addr_type = ipv6_addr_type(&usin->sin6_addr); daddr = &usin->sin6_addr; if (addr_type & IPV6_ADDR_MAPPED) { struct sockaddr_in sin; if (ipv6_only_sock(sk)) { err = -ENETUNREACH; goto out; } sin.sin_family = AF_INET; sin.sin_addr.s_addr = daddr->s6_addr32[3]; sin.sin_port = usin->sin6_port; err = __ip4_datagram_connect(sk, (struct sockaddr *) &sin, sizeof(sin)); ipv4_connected: if (err) goto out; ipv6_addr_set_v4mapped(inet->inet_daddr, &sk->sk_v6_daddr); if (ipv6_addr_any(&np->saddr) || ipv6_mapped_addr_any(&np->saddr)) ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); if (ipv6_addr_any(&sk->sk_v6_rcv_saddr) || ipv6_mapped_addr_any(&sk->sk_v6_rcv_saddr)) { ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &sk->sk_v6_rcv_saddr); if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); } goto out; } if (__ipv6_addr_needs_scope_id(addr_type)) { if (addr_len >= sizeof(struct sockaddr_in6) && usin->sin6_scope_id) { if (!sk_dev_equal_l3scope(sk, usin->sin6_scope_id)) { err = -EINVAL; goto out; } WRITE_ONCE(sk->sk_bound_dev_if, usin->sin6_scope_id); } if (!sk->sk_bound_dev_if && (addr_type & IPV6_ADDR_MULTICAST)) WRITE_ONCE(sk->sk_bound_dev_if, READ_ONCE(np->mcast_oif)); /* Connect to link-local address requires an interface */ if (!sk->sk_bound_dev_if) { err = -EINVAL; goto out; } } /* save the current peer information before updating it */ old_daddr = sk->sk_v6_daddr; old_fl6_flowlabel = np->flow_label; old_dport = inet->inet_dport; sk->sk_v6_daddr = *daddr; np->flow_label = fl6_flowlabel; inet->inet_dport = usin->sin6_port; /* * Check for a route to destination an obtain the * destination cache for it. */ err = ip6_datagram_dst_update(sk, true); if (err) { /* Restore the socket peer info, to keep it consistent with * the old socket state */ sk->sk_v6_daddr = old_daddr; np->flow_label = old_fl6_flowlabel; inet->inet_dport = old_dport; goto out; } reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); out: return err; } EXPORT_SYMBOL_GPL(__ip6_datagram_connect); int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { int res; lock_sock(sk); res = __ip6_datagram_connect(sk, uaddr, addr_len); release_sock(sk); return res; } EXPORT_SYMBOL_GPL(ip6_datagram_connect); int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *uaddr, int addr_len) { DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, uaddr); if (sin6->sin6_family != AF_INET6) return -EAFNOSUPPORT; return ip6_datagram_connect(sk, uaddr, addr_len); } EXPORT_SYMBOL_GPL(ip6_datagram_connect_v6_only); static void ipv6_icmp_error_rfc4884(const struct sk_buff *skb, struct sock_ee_data_rfc4884 *out) { switch (icmp6_hdr(skb)->icmp6_type) { case ICMPV6_TIME_EXCEED: case ICMPV6_DEST_UNREACH: ip_icmp_error_rfc4884(skb, out, sizeof(struct icmp6hdr), icmp6_hdr(skb)->icmp6_datagram_len * 8); } } void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) { struct icmp6hdr *icmph = icmp6_hdr(skb); struct sock_exterr_skb *serr; if (!inet6_test_bit(RECVERR6, sk)) return; skb = skb_clone(skb, GFP_ATOMIC); if (!skb) return; skb->protocol = htons(ETH_P_IPV6); serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; serr->ee.ee_origin = SO_EE_ORIGIN_ICMP6; serr->ee.ee_type = icmph->icmp6_type; serr->ee.ee_code = icmph->icmp6_code; serr->ee.ee_pad = 0; serr->ee.ee_info = info; serr->ee.ee_data = 0; serr->addr_offset = (u8 *)&(((struct ipv6hdr *)(icmph + 1))->daddr) - skb_network_header(skb); serr->port = port; __skb_pull(skb, payload - skb->data); if (inet6_test_bit(RECVERR6_RFC4884, sk)) ipv6_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884); skb_reset_transport_header(skb); if (sock_queue_err_skb(sk, skb)) kfree_skb(skb); } EXPORT_SYMBOL_GPL(ipv6_icmp_error); void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info) { struct sock_exterr_skb *serr; struct ipv6hdr *iph; struct sk_buff *skb; if (!inet6_test_bit(RECVERR6, sk)) return; skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC); if (!skb) return; skb->protocol = htons(ETH_P_IPV6); skb_put(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); iph = ipv6_hdr(skb); iph->daddr = fl6->daddr; ip6_flow_hdr(iph, 0, 0); serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL; serr->ee.ee_type = 0; serr->ee.ee_code = 0; serr->ee.ee_pad = 0; serr->ee.ee_info = info; serr->ee.ee_data = 0; serr->addr_offset = (u8 *)&iph->daddr - skb_network_header(skb); serr->port = fl6->fl6_dport; __skb_pull(skb, skb_tail_pointer(skb) - skb->data); skb_reset_transport_header(skb); if (sock_queue_err_skb(sk, skb)) kfree_skb(skb); } void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6hdr *iph; struct sk_buff *skb; struct ip6_mtuinfo *mtu_info; if (!np->rxopt.bits.rxpmtu) return; skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC); if (!skb) return; skb_put(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); iph = ipv6_hdr(skb); iph->daddr = fl6->daddr; mtu_info = IP6CBMTU(skb); mtu_info->ip6m_mtu = mtu; mtu_info->ip6m_addr.sin6_family = AF_INET6; mtu_info->ip6m_addr.sin6_port = 0; mtu_info->ip6m_addr.sin6_flowinfo = 0; mtu_info->ip6m_addr.sin6_scope_id = fl6->flowi6_oif; mtu_info->ip6m_addr.sin6_addr = ipv6_hdr(skb)->daddr; __skb_pull(skb, skb_tail_pointer(skb) - skb->data); skb_reset_transport_header(skb); skb = xchg(&np->rxpmtu, skb); kfree_skb(skb); } /* For some errors we have valid addr_offset even with zero payload and * zero port. Also, addr_offset should be supported if port is set. */ static inline bool ipv6_datagram_support_addr(struct sock_exterr_skb *serr) { return serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6 || serr->ee.ee_origin == SO_EE_ORIGIN_ICMP || serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL || serr->port; } /* IPv6 supports cmsg on all origins aside from SO_EE_ORIGIN_LOCAL. * * At one point, excluding local errors was a quick test to identify icmp/icmp6 * errors. This is no longer true, but the test remained, so the v6 stack, * unlike v4, also honors cmsg requests on all wifi and timestamp errors. */ static bool ip6_datagram_support_cmsg(struct sk_buff *skb, struct sock_exterr_skb *serr) { if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP || serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6) return true; if (serr->ee.ee_origin == SO_EE_ORIGIN_LOCAL) return false; if (!IP6CB(skb)->iif) return false; return true; } /* * Handle MSG_ERRQUEUE */ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sock_exterr_skb *serr; struct sk_buff *skb; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name); struct { struct sock_extended_err ee; struct sockaddr_in6 offender; } errhdr; int err; int copied; err = -EAGAIN; skb = sock_dequeue_err_skb(sk); if (!skb) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (unlikely(err)) { kfree_skb(skb); return err; } sock_recv_timestamp(msg, sk, skb); serr = SKB_EXT_ERR(skb); if (sin && ipv6_datagram_support_addr(serr)) { const unsigned char *nh = skb_network_header(skb); sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; sin->sin6_port = serr->port; if (skb->protocol == htons(ETH_P_IPV6)) { const struct ipv6hdr *ip6h = container_of((struct in6_addr *)(nh + serr->addr_offset), struct ipv6hdr, daddr); sin->sin6_addr = ip6h->daddr; if (inet6_test_bit(SNDFLOW, sk)) sin->sin6_flowinfo = ip6_flowinfo(ip6h); sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, IP6CB(skb)->iif); } else { ipv6_addr_set_v4mapped(*(__be32 *)(nh + serr->addr_offset), &sin->sin6_addr); sin->sin6_scope_id = 0; } *addr_len = sizeof(*sin); } memcpy(&errhdr.ee, &serr->ee, sizeof(struct sock_extended_err)); sin = &errhdr.offender; memset(sin, 0, sizeof(*sin)); if (ip6_datagram_support_cmsg(skb, serr)) { sin->sin6_family = AF_INET6; if (np->rxopt.all) ip6_datagram_recv_common_ctl(sk, msg, skb); if (skb->protocol == htons(ETH_P_IPV6)) { sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) ip6_datagram_recv_specific_ctl(sk, msg, skb); sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, IP6CB(skb)->iif); } else { ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &sin->sin6_addr); if (inet_cmsg_flags(inet_sk(sk))) ip_cmsg_recv(msg, skb); } } put_cmsg(msg, SOL_IPV6, IPV6_RECVERR, sizeof(errhdr), &errhdr); /* Now we could try to dump offended packet options */ msg->msg_flags |= MSG_ERRQUEUE; err = copied; consume_skb(skb); out: return err; } EXPORT_SYMBOL_GPL(ipv6_recv_error); /* * Handle IPV6_RECVPATHMTU */ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; struct ip6_mtuinfo mtu_info; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin, msg->msg_name); int err; int copied; err = -EAGAIN; skb = xchg(&np->rxpmtu, NULL); if (!skb) goto out; copied = skb->len; if (copied > len) { msg->msg_flags |= MSG_TRUNC; copied = len; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free_skb; sock_recv_timestamp(msg, sk, skb); memcpy(&mtu_info, IP6CBMTU(skb), sizeof(mtu_info)); if (sin) { sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; sin->sin6_port = 0; sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id; sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr; *addr_len = sizeof(*sin); } put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info); err = copied; out_free_skb: kfree_skb(skb); out: return err; } void ip6_datagram_recv_common_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); bool is_ipv6 = skb->protocol == htons(ETH_P_IPV6); if (np->rxopt.bits.rxinfo) { struct in6_pktinfo src_info; if (is_ipv6) { src_info.ipi6_ifindex = IP6CB(skb)->iif; src_info.ipi6_addr = ipv6_hdr(skb)->daddr; } else { src_info.ipi6_ifindex = PKTINFO_SKB_CB(skb)->ipi_ifindex; ipv6_addr_set_v4mapped(ip_hdr(skb)->daddr, &src_info.ipi6_addr); } if (src_info.ipi6_ifindex >= 0) put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } } void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); struct inet6_skb_parm *opt = IP6CB(skb); unsigned char *nh = skb_network_header(skb); if (np->rxopt.bits.rxhlim) { int hlim = ipv6_hdr(skb)->hop_limit; put_cmsg(msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim); } if (np->rxopt.bits.rxtclass) { int tclass = ipv6_get_dsfield(ipv6_hdr(skb)); put_cmsg(msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass); } if (np->rxopt.bits.rxflow) { __be32 flowinfo = ip6_flowinfo((struct ipv6hdr *)nh); if (flowinfo) put_cmsg(msg, SOL_IPV6, IPV6_FLOWINFO, sizeof(flowinfo), &flowinfo); } /* HbH is allowed only once */ if (np->rxopt.bits.hopopts && (opt->flags & IP6SKB_HOPBYHOP)) { u8 *ptr = nh + sizeof(struct ipv6hdr); put_cmsg(msg, SOL_IPV6, IPV6_HOPOPTS, (ptr[1]+1)<<3, ptr); } if (opt->lastopt && (np->rxopt.bits.dstopts || np->rxopt.bits.srcrt)) { /* * Silly enough, but we need to reparse in order to * report extension headers (except for HbH) * in order. * * Also note that IPV6_RECVRTHDRDSTOPTS is NOT * (and WILL NOT be) defined because * IPV6_RECVDSTOPTS is more generic. --yoshfuji */ unsigned int off = sizeof(struct ipv6hdr); u8 nexthdr = ipv6_hdr(skb)->nexthdr; while (off <= opt->lastopt) { unsigned int len; u8 *ptr = nh + off; switch (nexthdr) { case IPPROTO_DSTOPTS: nexthdr = ptr[0]; len = (ptr[1] + 1) << 3; if (np->rxopt.bits.dstopts) put_cmsg(msg, SOL_IPV6, IPV6_DSTOPTS, len, ptr); break; case IPPROTO_ROUTING: nexthdr = ptr[0]; len = (ptr[1] + 1) << 3; if (np->rxopt.bits.srcrt) put_cmsg(msg, SOL_IPV6, IPV6_RTHDR, len, ptr); break; case IPPROTO_AH: nexthdr = ptr[0]; len = (ptr[1] + 2) << 2; break; default: nexthdr = ptr[0]; len = (ptr[1] + 1) << 3; break; } off += len; } } /* socket options in old style */ if (np->rxopt.bits.rxoinfo) { struct in6_pktinfo src_info; src_info.ipi6_ifindex = opt->iif; src_info.ipi6_addr = ipv6_hdr(skb)->daddr; put_cmsg(msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxohlim) { int hlim = ipv6_hdr(skb)->hop_limit; put_cmsg(msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim); } if (np->rxopt.bits.ohopopts && (opt->flags & IP6SKB_HOPBYHOP)) { u8 *ptr = nh + sizeof(struct ipv6hdr); put_cmsg(msg, SOL_IPV6, IPV6_2292HOPOPTS, (ptr[1]+1)<<3, ptr); } if (np->rxopt.bits.odstopts && opt->dst0) { u8 *ptr = nh + opt->dst0; put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, (ptr[1]+1)<<3, ptr); } if (np->rxopt.bits.osrcrt && opt->srcrt) { struct ipv6_rt_hdr *rthdr = (struct ipv6_rt_hdr *)(nh + opt->srcrt); put_cmsg(msg, SOL_IPV6, IPV6_2292RTHDR, (rthdr->hdrlen+1) << 3, rthdr); } if (np->rxopt.bits.odstopts && opt->dst1) { u8 *ptr = nh + opt->dst1; put_cmsg(msg, SOL_IPV6, IPV6_2292DSTOPTS, (ptr[1]+1)<<3, ptr); } if (np->rxopt.bits.rxorigdstaddr) { struct sockaddr_in6 sin6; __be16 _ports[2], *ports; ports = skb_header_pointer(skb, skb_transport_offset(skb), sizeof(_ports), &_ports); if (ports) { /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ sin6.sin6_family = AF_INET6; sin6.sin6_addr = ipv6_hdr(skb)->daddr; sin6.sin6_port = ports[1]; sin6.sin6_flowinfo = 0; sin6.sin6_scope_id = ipv6_iface_scope_id(&ipv6_hdr(skb)->daddr, opt->iif); put_cmsg(msg, SOL_IPV6, IPV6_ORIGDSTADDR, sizeof(sin6), &sin6); } } if (np->rxopt.bits.recvfragsize && opt->frag_max_size) { int val = opt->frag_max_size; put_cmsg(msg, SOL_IPV6, IPV6_RECVFRAGSIZE, sizeof(val), &val); } } void ip6_datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { ip6_datagram_recv_common_ctl(sk, msg, skb); ip6_datagram_recv_specific_ctl(sk, msg, skb); } EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl); int ip6_datagram_send_ctl(struct net *net, struct sock *sk, struct msghdr *msg, struct flowi6 *fl6, struct ipcm6_cookie *ipc6) { struct in6_pktinfo *src_info; struct cmsghdr *cmsg; struct ipv6_rt_hdr *rthdr; struct ipv6_opt_hdr *hdr; struct ipv6_txoptions *opt = ipc6->opt; int len; int err = 0; for_each_cmsghdr(cmsg, msg) { int addr_type; if (!CMSG_OK(msg, cmsg)) { err = -EINVAL; goto exit_f; } if (cmsg->cmsg_level == SOL_SOCKET) { err = __sock_cmsg_send(sk, cmsg, &ipc6->sockc); if (err) return err; continue; } if (cmsg->cmsg_level != SOL_IPV6) continue; switch (cmsg->cmsg_type) { case IPV6_PKTINFO: case IPV6_2292PKTINFO: { struct net_device *dev = NULL; int src_idx; if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct in6_pktinfo))) { err = -EINVAL; goto exit_f; } src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg); src_idx = src_info->ipi6_ifindex; if (src_idx) { if (fl6->flowi6_oif && src_idx != fl6->flowi6_oif && (READ_ONCE(sk->sk_bound_dev_if) != fl6->flowi6_oif || !sk_dev_equal_l3scope(sk, src_idx))) return -EINVAL; fl6->flowi6_oif = src_idx; } addr_type = __ipv6_addr_type(&src_info->ipi6_addr); rcu_read_lock(); if (fl6->flowi6_oif) { dev = dev_get_by_index_rcu(net, fl6->flowi6_oif); if (!dev) { rcu_read_unlock(); return -ENODEV; } } else if (addr_type & IPV6_ADDR_LINKLOCAL) { rcu_read_unlock(); return -EINVAL; } if (addr_type != IPV6_ADDR_ANY) { int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; if (!ipv6_can_nonlocal_bind(net, inet_sk(sk)) && !ipv6_chk_addr_and_flags(net, &src_info->ipi6_addr, dev, !strict, 0, IFA_F_TENTATIVE) && !ipv6_chk_acast_addr_src(net, dev, &src_info->ipi6_addr)) err = -EINVAL; else fl6->saddr = src_info->ipi6_addr; } rcu_read_unlock(); if (err) goto exit_f; break; } case IPV6_FLOWINFO: if (cmsg->cmsg_len < CMSG_LEN(4)) { err = -EINVAL; goto exit_f; } if (fl6->flowlabel&IPV6_FLOWINFO_MASK) { if ((fl6->flowlabel^*(__be32 *)CMSG_DATA(cmsg))&~IPV6_FLOWINFO_MASK) { err = -EINVAL; goto exit_f; } } fl6->flowlabel = IPV6_FLOWINFO_MASK & *(__be32 *)CMSG_DATA(cmsg); break; case IPV6_2292HOPOPTS: case IPV6_HOPOPTS: if (opt->hopopt || cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) { err = -EINVAL; goto exit_f; } hdr = (struct ipv6_opt_hdr *)CMSG_DATA(cmsg); len = ((hdr->hdrlen + 1) << 3); if (cmsg->cmsg_len < CMSG_LEN(len)) { err = -EINVAL; goto exit_f; } if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } opt->opt_nflen += len; opt->hopopt = hdr; break; case IPV6_2292DSTOPTS: if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) { err = -EINVAL; goto exit_f; } hdr = (struct ipv6_opt_hdr *)CMSG_DATA(cmsg); len = ((hdr->hdrlen + 1) << 3); if (cmsg->cmsg_len < CMSG_LEN(len)) { err = -EINVAL; goto exit_f; } if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } if (opt->dst1opt) { err = -EINVAL; goto exit_f; } opt->opt_flen += len; opt->dst1opt = hdr; break; case IPV6_DSTOPTS: case IPV6_RTHDRDSTOPTS: if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_opt_hdr))) { err = -EINVAL; goto exit_f; } hdr = (struct ipv6_opt_hdr *)CMSG_DATA(cmsg); len = ((hdr->hdrlen + 1) << 3); if (cmsg->cmsg_len < CMSG_LEN(len)) { err = -EINVAL; goto exit_f; } if (!ns_capable(net->user_ns, CAP_NET_RAW)) { err = -EPERM; goto exit_f; } if (cmsg->cmsg_type == IPV6_DSTOPTS) { opt->opt_flen += len; opt->dst1opt = hdr; } else { opt->opt_nflen += len; opt->dst0opt = hdr; } break; case IPV6_2292RTHDR: case IPV6_RTHDR: if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct ipv6_rt_hdr))) { err = -EINVAL; goto exit_f; } rthdr = (struct ipv6_rt_hdr *)CMSG_DATA(cmsg); switch (rthdr->type) { #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPV6_SRCRT_TYPE_2: if (rthdr->hdrlen != 2 || rthdr->segments_left != 1) { err = -EINVAL; goto exit_f; } break; #endif default: err = -EINVAL; goto exit_f; } len = ((rthdr->hdrlen + 1) << 3); if (cmsg->cmsg_len < CMSG_LEN(len)) { err = -EINVAL; goto exit_f; } /* segments left must also match */ if ((rthdr->hdrlen >> 1) != rthdr->segments_left) { err = -EINVAL; goto exit_f; } opt->opt_nflen += len; opt->srcrt = rthdr; if (cmsg->cmsg_type == IPV6_2292RTHDR && opt->dst1opt) { int dsthdrlen = ((opt->dst1opt->hdrlen+1)<<3); opt->opt_nflen += dsthdrlen; opt->dst0opt = opt->dst1opt; opt->dst1opt = NULL; opt->opt_flen -= dsthdrlen; } break; case IPV6_2292HOPLIMIT: case IPV6_HOPLIMIT: if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) { err = -EINVAL; goto exit_f; } ipc6->hlimit = *(int *)CMSG_DATA(cmsg); if (ipc6->hlimit < -1 || ipc6->hlimit > 0xff) { err = -EINVAL; goto exit_f; } break; case IPV6_TCLASS: { int tc; err = -EINVAL; if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) goto exit_f; tc = *(int *)CMSG_DATA(cmsg); if (tc < -1 || tc > 0xff) goto exit_f; err = 0; ipc6->tclass = tc; break; } case IPV6_DONTFRAG: { int df; err = -EINVAL; if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) goto exit_f; df = *(int *)CMSG_DATA(cmsg); if (df < 0 || df > 1) goto exit_f; err = 0; ipc6->dontfrag = df; break; } default: net_dbg_ratelimited("invalid cmsg type: %d\n", cmsg->cmsg_type); err = -EINVAL; goto exit_f; } } exit_f: return err; } EXPORT_SYMBOL_GPL(ip6_datagram_send_ctl); void __ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp, __u16 srcp, __u16 destp, int rqueue, int bucket) { const struct in6_addr *dest, *src; dest = &sp->sk_v6_daddr; src = &sp->sk_v6_rcv_saddr; seq_printf(seq, "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u\n", bucket, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, sp->sk_state, sk_wmem_alloc_get(sp), rqueue, 0, 0L, 0, from_kuid_munged(seq_user_ns(seq), sk_uid(sp)), 0, sock_i_ino(sp), refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops)); } |
| 2601 34 4563 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 | /* SPDX-License-Identifier: GPL-2.0 OR MIT */ #ifndef __LINUX_OVERFLOW_H #define __LINUX_OVERFLOW_H #include <linux/compiler.h> #include <linux/limits.h> #include <linux/const.h> /* * We need to compute the minimum and maximum values representable in a given * type. These macros may also be useful elsewhere. It would seem more obvious * to do something like: * * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0) * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0) * * Unfortunately, the middle expressions, strictly speaking, have * undefined behaviour, and at least some versions of gcc warn about * the type_max expression (but not if -fsanitize=undefined is in * effect; in that case, the warning is deferred to runtime...). * * The slightly excessive casting in type_min is to make sure the * macros also produce sensible values for the exotic type _Bool. [The * overflow checkers only almost work for _Bool, but that's * a-feature-not-a-bug, since people shouldn't be doing arithmetic on * _Bools. Besides, the gcc builtins don't allow _Bool* as third * argument.] * * Idea stolen from * https://mail-index.netbsd.org/tech-misc/2007/02/05/0000.html - * credit to Christian Biere. */ #define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type))) #define __type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T))) #define type_max(t) __type_max(typeof(t)) #define __type_min(T) ((T)((T)-type_max(T)-(T)1)) #define type_min(t) __type_min(typeof(t)) /* * Avoids triggering -Wtype-limits compilation warning, * while using unsigned data types to check a < 0. */ #define is_non_negative(a) ((a) > 0 || (a) == 0) #define is_negative(a) (!(is_non_negative(a))) /* * Allows for effectively applying __must_check to a macro so we can have * both the type-agnostic benefits of the macros while also being able to * enforce that the return value is, in fact, checked. */ static inline bool __must_check __must_check_overflow(bool overflow) { return unlikely(overflow); } /** * check_add_overflow() - Calculate addition with overflow checking * @a: first addend * @b: second addend * @d: pointer to store sum * * Returns true on wrap-around, false otherwise. * * *@d holds the results of the attempted addition, regardless of whether * wrap-around occurred. */ #define check_add_overflow(a, b, d) \ __must_check_overflow(__builtin_add_overflow(a, b, d)) /** * wrapping_add() - Intentionally perform a wrapping addition * @type: type for result of calculation * @a: first addend * @b: second addend * * Return the potentially wrapped-around addition without * tripping any wrap-around sanitizers that may be enabled. */ #define wrapping_add(type, a, b) \ ({ \ type __val; \ __builtin_add_overflow(a, b, &__val); \ __val; \ }) /** * wrapping_assign_add() - Intentionally perform a wrapping increment assignment * @var: variable to be incremented * @offset: amount to add * * Increments @var by @offset with wrap-around. Returns the resulting * value of @var. Will not trip any wrap-around sanitizers. * * Returns the new value of @var. */ #define wrapping_assign_add(var, offset) \ ({ \ typeof(var) *__ptr = &(var); \ *__ptr = wrapping_add(typeof(var), *__ptr, offset); \ }) /** * check_sub_overflow() - Calculate subtraction with overflow checking * @a: minuend; value to subtract from * @b: subtrahend; value to subtract from @a * @d: pointer to store difference * * Returns true on wrap-around, false otherwise. * * *@d holds the results of the attempted subtraction, regardless of whether * wrap-around occurred. */ #define check_sub_overflow(a, b, d) \ __must_check_overflow(__builtin_sub_overflow(a, b, d)) /** * wrapping_sub() - Intentionally perform a wrapping subtraction * @type: type for result of calculation * @a: minuend; value to subtract from * @b: subtrahend; value to subtract from @a * * Return the potentially wrapped-around subtraction without * tripping any wrap-around sanitizers that may be enabled. */ #define wrapping_sub(type, a, b) \ ({ \ type __val; \ __builtin_sub_overflow(a, b, &__val); \ __val; \ }) /** * wrapping_assign_sub() - Intentionally perform a wrapping decrement assign * @var: variable to be decremented * @offset: amount to subtract * * Decrements @var by @offset with wrap-around. Returns the resulting * value of @var. Will not trip any wrap-around sanitizers. * * Returns the new value of @var. */ #define wrapping_assign_sub(var, offset) \ ({ \ typeof(var) *__ptr = &(var); \ *__ptr = wrapping_sub(typeof(var), *__ptr, offset); \ }) /** * check_mul_overflow() - Calculate multiplication with overflow checking * @a: first factor * @b: second factor * @d: pointer to store product * * Returns true on wrap-around, false otherwise. * * *@d holds the results of the attempted multiplication, regardless of whether * wrap-around occurred. */ #define check_mul_overflow(a, b, d) \ __must_check_overflow(__builtin_mul_overflow(a, b, d)) /** * wrapping_mul() - Intentionally perform a wrapping multiplication * @type: type for result of calculation * @a: first factor * @b: second factor * * Return the potentially wrapped-around multiplication without * tripping any wrap-around sanitizers that may be enabled. */ #define wrapping_mul(type, a, b) \ ({ \ type __val; \ __builtin_mul_overflow(a, b, &__val); \ __val; \ }) /** * check_shl_overflow() - Calculate a left-shifted value and check overflow * @a: Value to be shifted * @s: How many bits left to shift * @d: Pointer to where to store the result * * Computes *@d = (@a << @s) * * Returns true if '*@d' cannot hold the result or when '@a << @s' doesn't * make sense. Example conditions: * * - '@a << @s' causes bits to be lost when stored in *@d. * - '@s' is garbage (e.g. negative) or so large that the result of * '@a << @s' is guaranteed to be 0. * - '@a' is negative. * - '@a << @s' sets the sign bit, if any, in '*@d'. * * '*@d' will hold the results of the attempted shift, but is not * considered "safe for use" if true is returned. */ #define check_shl_overflow(a, s, d) __must_check_overflow(({ \ typeof(a) _a = a; \ typeof(s) _s = s; \ typeof(d) _d = d; \ unsigned long long _a_full = _a; \ unsigned int _to_shift = \ is_non_negative(_s) && _s < 8 * sizeof(*d) ? _s : 0; \ *_d = (_a_full << _to_shift); \ (_to_shift != _s || is_negative(*_d) || is_negative(_a) || \ (*_d >> _to_shift) != _a); \ })) #define __overflows_type_constexpr(x, T) ( \ is_unsigned_type(typeof(x)) ? \ (x) > type_max(T) : \ is_unsigned_type(typeof(T)) ? \ (x) < 0 || (x) > type_max(T) : \ (x) < type_min(T) || (x) > type_max(T)) #define __overflows_type(x, T) ({ \ typeof(T) v = 0; \ check_add_overflow((x), v, &v); \ }) /** * overflows_type - helper for checking the overflows between value, variables, * or data type * * @n: source constant value or variable to be checked * @T: destination variable or data type proposed to store @x * * Compares the @x expression for whether or not it can safely fit in * the storage of the type in @T. @x and @T can have different types. * If @x is a constant expression, this will also resolve to a constant * expression. * * Returns: true if overflow can occur, false otherwise. */ #define overflows_type(n, T) \ __builtin_choose_expr(__is_constexpr(n), \ __overflows_type_constexpr(n, T), \ __overflows_type(n, T)) /** * castable_to_type - like __same_type(), but also allows for casted literals * * @n: variable or constant value * @T: variable or data type * * Unlike the __same_type() macro, this allows a constant value as the * first argument. If this value would not overflow into an assignment * of the second argument's type, it returns true. Otherwise, this falls * back to __same_type(). */ #define castable_to_type(n, T) \ __builtin_choose_expr(__is_constexpr(n), \ !__overflows_type_constexpr(n, T), \ __same_type(n, T)) /** * size_mul() - Calculate size_t multiplication with saturation at SIZE_MAX * @factor1: first factor * @factor2: second factor * * Returns: calculate @factor1 * @factor2, both promoted to size_t, * with any overflow causing the return value to be SIZE_MAX. The * lvalue must be size_t to avoid implicit type conversion. */ static inline size_t __must_check size_mul(size_t factor1, size_t factor2) { size_t bytes; if (check_mul_overflow(factor1, factor2, &bytes)) return SIZE_MAX; return bytes; } /** * size_add() - Calculate size_t addition with saturation at SIZE_MAX * @addend1: first addend * @addend2: second addend * * Returns: calculate @addend1 + @addend2, both promoted to size_t, * with any overflow causing the return value to be SIZE_MAX. The * lvalue must be size_t to avoid implicit type conversion. */ static inline size_t __must_check size_add(size_t addend1, size_t addend2) { size_t bytes; if (check_add_overflow(addend1, addend2, &bytes)) return SIZE_MAX; return bytes; } /** * size_sub() - Calculate size_t subtraction with saturation at SIZE_MAX * @minuend: value to subtract from * @subtrahend: value to subtract from @minuend * * Returns: calculate @minuend - @subtrahend, both promoted to size_t, * with any overflow causing the return value to be SIZE_MAX. For * composition with the size_add() and size_mul() helpers, neither * argument may be SIZE_MAX (or the result with be forced to SIZE_MAX). * The lvalue must be size_t to avoid implicit type conversion. */ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) { size_t bytes; if (minuend == SIZE_MAX || subtrahend == SIZE_MAX || check_sub_overflow(minuend, subtrahend, &bytes)) return SIZE_MAX; return bytes; } /** * array_size() - Calculate size of 2-dimensional array. * @a: dimension one * @b: dimension two * * Calculates size of 2-dimensional array: @a * @b. * * Returns: number of bytes needed to represent the array or SIZE_MAX on * overflow. */ #define array_size(a, b) size_mul(a, b) /** * array3_size() - Calculate size of 3-dimensional array. * @a: dimension one * @b: dimension two * @c: dimension three * * Calculates size of 3-dimensional array: @a * @b * @c. * * Returns: number of bytes needed to represent the array or SIZE_MAX on * overflow. */ #define array3_size(a, b, c) size_mul(size_mul(a, b), c) /** * flex_array_size() - Calculate size of a flexible array member * within an enclosing structure. * @p: Pointer to the structure. * @member: Name of the flexible array member. * @count: Number of elements in the array. * * Calculates size of a flexible array of @count number of @member * elements, at the end of structure @p. * * Return: number of bytes needed or SIZE_MAX on overflow. */ #define flex_array_size(p, member, count) \ __builtin_choose_expr(__is_constexpr(count), \ (count) * sizeof(*(p)->member) + __must_be_array((p)->member), \ size_mul(count, sizeof(*(p)->member) + __must_be_array((p)->member))) /** * struct_size() - Calculate size of structure with trailing flexible array. * @p: Pointer to the structure. * @member: Name of the array member. * @count: Number of elements in the array. * * Calculates size of memory needed for structure of @p followed by an * array of @count number of @member elements. * * Return: number of bytes needed or SIZE_MAX on overflow. */ #define struct_size(p, member, count) \ __builtin_choose_expr(__is_constexpr(count), \ sizeof(*(p)) + flex_array_size(p, member, count), \ size_add(sizeof(*(p)), flex_array_size(p, member, count))) /** * struct_size_t() - Calculate size of structure with trailing flexible array * @type: structure type name. * @member: Name of the array member. * @count: Number of elements in the array. * * Calculates size of memory needed for structure @type followed by an * array of @count number of @member elements. Prefer using struct_size() * when possible instead, to keep calculations associated with a specific * instance variable of type @type. * * Return: number of bytes needed or SIZE_MAX on overflow. */ #define struct_size_t(type, member, count) \ struct_size((type *)NULL, member, count) /** * __DEFINE_FLEX() - helper macro for DEFINE_FLEX() family. * Enables caller macro to pass arbitrary trailing expressions * * @type: structure type name, including "struct" keyword. * @name: Name for a variable to define. * @member: Name of the array member. * @count: Number of elements in the array; must be compile-time const. * @trailer: Trailing expressions for attributes and/or initializers. */ #define __DEFINE_FLEX(type, name, member, count, trailer...) \ _Static_assert(__builtin_constant_p(count), \ "onstack flex array members require compile-time const count"); \ union { \ u8 bytes[struct_size_t(type, member, count)]; \ type obj; \ } name##_u trailer; \ type *name = (type *)&name##_u /** * _DEFINE_FLEX() - helper macro for DEFINE_FLEX() family. * Enables caller macro to pass (different) initializer. * * @type: structure type name, including "struct" keyword. * @name: Name for a variable to define. * @member: Name of the array member. * @count: Number of elements in the array; must be compile-time const. * @initializer: Initializer expression (e.g., pass `= { }` at minimum). */ #define _DEFINE_FLEX(type, name, member, count, initializer...) \ __DEFINE_FLEX(type, name, member, count, = { .obj initializer }) /** * DEFINE_RAW_FLEX() - Define an on-stack instance of structure with a trailing * flexible array member, when it does not have a __counted_by annotation. * * @type: structure type name, including "struct" keyword. * @name: Name for a variable to define. * @member: Name of the array member. * @count: Number of elements in the array; must be compile-time const. * * Define a zeroed, on-stack, instance of @type structure with a trailing * flexible array member. * Use __struct_size(@name) to get compile-time size of it afterwards. * Use __member_size(@name->member) to get compile-time size of @name members. * Use STACK_FLEX_ARRAY_SIZE(@name, @member) to get compile-time number of * elements in array @member. */ #define DEFINE_RAW_FLEX(type, name, member, count) \ __DEFINE_FLEX(type, name, member, count, = { }) /** * DEFINE_FLEX() - Define an on-stack instance of structure with a trailing * flexible array member. * * @TYPE: structure type name, including "struct" keyword. * @NAME: Name for a variable to define. * @MEMBER: Name of the array member. * @COUNTER: Name of the __counted_by member. * @COUNT: Number of elements in the array; must be compile-time const. * * Define a zeroed, on-stack, instance of @TYPE structure with a trailing * flexible array member. * Use __struct_size(@NAME) to get compile-time size of it afterwards. * Use __member_size(@NAME->member) to get compile-time size of @NAME members. * Use STACK_FLEX_ARRAY_SIZE(@name, @member) to get compile-time number of * elements in array @member. */ #define DEFINE_FLEX(TYPE, NAME, MEMBER, COUNTER, COUNT) \ _DEFINE_FLEX(TYPE, NAME, MEMBER, COUNT, = { .COUNTER = COUNT, }) /** * STACK_FLEX_ARRAY_SIZE() - helper macro for DEFINE_FLEX() family. * Returns the number of elements in @array. * * @name: Name for a variable defined in DEFINE_RAW_FLEX()/DEFINE_FLEX(). * @array: Name of the array member. */ #define STACK_FLEX_ARRAY_SIZE(name, array) \ (__member_size((name)->array) / sizeof(*(name)->array) + \ __must_be_array((name)->array)) #endif /* __LINUX_OVERFLOW_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0+ /* * LEGO USB Tower driver * * Copyright (C) 2003 David Glance <davidgsf@sourceforge.net> * 2001-2004 Juergen Stuber <starblue@users.sourceforge.net> * * derived from USB Skeleton driver - 0.5 * Copyright (C) 2001 Greg Kroah-Hartman (greg@kroah.com) * * History: * * 2001-10-13 - 0.1 js * - first version * 2001-11-03 - 0.2 js * - simplified buffering, one-shot URBs for writing * 2001-11-10 - 0.3 js * - removed IOCTL (setting power/mode is more complicated, postponed) * 2001-11-28 - 0.4 js * - added vendor commands for mode of operation and power level in open * 2001-12-04 - 0.5 js * - set IR mode by default (by oversight 0.4 set VLL mode) * 2002-01-11 - 0.5? pcchan * - make read buffer reusable and work around bytes_to_write issue between * uhci and legusbtower * 2002-09-23 - 0.52 david (david@csse.uwa.edu.au) * - imported into lejos project * - changed wake_up to wake_up_interruptible * - changed to use lego0 rather than tower0 * - changed dbg() to use __func__ rather than deprecated __func__ * 2003-01-12 - 0.53 david (david@csse.uwa.edu.au) * - changed read and write to write everything or * timeout (from a patch by Chris Riesen and Brett Thaeler driver) * - added ioctl functionality to set timeouts * 2003-07-18 - 0.54 davidgsf (david@csse.uwa.edu.au) * - initial import into LegoUSB project * - merge of existing LegoUSB.c driver * 2003-07-18 - 0.56 davidgsf (david@csse.uwa.edu.au) * - port to 2.6 style driver * 2004-02-29 - 0.6 Juergen Stuber <starblue@users.sourceforge.net> * - fix locking * - unlink read URBs which are no longer needed * - allow increased buffer size, eliminates need for timeout on write * - have read URB running continuously * - added poll * - forbid seeking * - added nonblocking I/O * - changed back __func__ to __func__ * - read and log tower firmware version * - reset tower on probe, avoids failure of first write * 2004-03-09 - 0.7 Juergen Stuber <starblue@users.sourceforge.net> * - timeout read now only after inactivity, shorten default accordingly * 2004-03-11 - 0.8 Juergen Stuber <starblue@users.sourceforge.net> * - log major, minor instead of possibly confusing device filename * - whitespace cleanup * 2004-03-12 - 0.9 Juergen Stuber <starblue@users.sourceforge.net> * - normalize whitespace in debug messages * - take care about endianness in control message responses * 2004-03-13 - 0.91 Juergen Stuber <starblue@users.sourceforge.net> * - make default intervals longer to accommodate current EHCI driver * 2004-03-19 - 0.92 Juergen Stuber <starblue@users.sourceforge.net> * - replaced atomic_t by memory barriers * 2004-04-21 - 0.93 Juergen Stuber <starblue@users.sourceforge.net> * - wait for completion of write urb in release (needed for remotecontrol) * - corrected poll for write direction (missing negation) * 2004-04-22 - 0.94 Juergen Stuber <starblue@users.sourceforge.net> * - make device locking interruptible * 2004-04-30 - 0.95 Juergen Stuber <starblue@users.sourceforge.net> * - check for valid udev on resubmitting and unlinking urbs * 2004-08-03 - 0.96 Juergen Stuber <starblue@users.sourceforge.net> * - move reset into open to clean out spurious data */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/completion.h> #include <linux/mutex.h> #include <linux/uaccess.h> #include <linux/usb.h> #include <linux/poll.h> #define DRIVER_AUTHOR "Juergen Stuber <starblue@sourceforge.net>" #define DRIVER_DESC "LEGO USB Tower Driver" /* The defaults are chosen to work with the latest versions of leJOS and NQC. */ /* Some legacy software likes to receive packets in one piece. * In this case read_buffer_size should exceed the maximal packet length * (417 for datalog uploads), and packet_timeout should be set. */ static int read_buffer_size = 480; module_param(read_buffer_size, int, 0); MODULE_PARM_DESC(read_buffer_size, "Read buffer size"); /* Some legacy software likes to send packets in one piece. * In this case write_buffer_size should exceed the maximal packet length * (417 for firmware and program downloads). * A problem with long writes is that the following read may time out * if the software is not prepared to wait long enough. */ static int write_buffer_size = 480; module_param(write_buffer_size, int, 0); MODULE_PARM_DESC(write_buffer_size, "Write buffer size"); /* Some legacy software expects reads to contain whole LASM packets. * To achieve this, characters which arrive before a packet timeout * occurs will be returned in a single read operation. * A problem with long reads is that the software may time out * if it is not prepared to wait long enough. * The packet timeout should be greater than the time between the * reception of subsequent characters, which should arrive about * every 5ms for the standard 2400 baud. * Set it to 0 to disable. */ static int packet_timeout = 50; module_param(packet_timeout, int, 0); MODULE_PARM_DESC(packet_timeout, "Packet timeout in ms"); /* Some legacy software expects blocking reads to time out. * Timeout occurs after the specified time of read and write inactivity. * Set it to 0 to disable. */ static int read_timeout = 200; module_param(read_timeout, int, 0); MODULE_PARM_DESC(read_timeout, "Read timeout in ms"); /* As of kernel version 2.6.4 ehci-hcd uses an * "only one interrupt transfer per frame" shortcut * to simplify the scheduling of periodic transfers. * This conflicts with our standard 1ms intervals for in and out URBs. * We use default intervals of 2ms for in and 8ms for out transfers, * which is fast enough for 2400 baud and allows a small additional load. * Increase the interval to allow more devices that do interrupt transfers, * or set to 0 to use the standard interval from the endpoint descriptors. */ static int interrupt_in_interval = 2; module_param(interrupt_in_interval, int, 0); MODULE_PARM_DESC(interrupt_in_interval, "Interrupt in interval in ms"); static int interrupt_out_interval = 8; module_param(interrupt_out_interval, int, 0); MODULE_PARM_DESC(interrupt_out_interval, "Interrupt out interval in ms"); /* Define these values to match your device */ #define LEGO_USB_TOWER_VENDOR_ID 0x0694 #define LEGO_USB_TOWER_PRODUCT_ID 0x0001 /* Vendor requests */ #define LEGO_USB_TOWER_REQUEST_RESET 0x04 #define LEGO_USB_TOWER_REQUEST_GET_VERSION 0xFD struct tower_reset_reply { __le16 size; __u8 err_code; __u8 spare; }; struct tower_get_version_reply { __le16 size; __u8 err_code; __u8 spare; __u8 major; __u8 minor; __le16 build_no; }; /* table of devices that work with this driver */ static const struct usb_device_id tower_table[] = { { USB_DEVICE(LEGO_USB_TOWER_VENDOR_ID, LEGO_USB_TOWER_PRODUCT_ID) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, tower_table); #define LEGO_USB_TOWER_MINOR_BASE 160 /* Structure to hold all of our device specific stuff */ struct lego_usb_tower { struct mutex lock; /* locks this structure */ struct usb_device *udev; /* save off the usb device pointer */ unsigned char minor; /* the starting minor number for this device */ int open_count; /* number of times this port has been opened */ unsigned long disconnected:1; char *read_buffer; size_t read_buffer_length; /* this much came in */ size_t read_packet_length; /* this much will be returned on read */ spinlock_t read_buffer_lock; int packet_timeout_jiffies; unsigned long read_last_arrival; wait_queue_head_t read_wait; wait_queue_head_t write_wait; char *interrupt_in_buffer; struct usb_endpoint_descriptor *interrupt_in_endpoint; struct urb *interrupt_in_urb; int interrupt_in_interval; int interrupt_in_done; char *interrupt_out_buffer; struct usb_endpoint_descriptor *interrupt_out_endpoint; struct urb *interrupt_out_urb; int interrupt_out_interval; int interrupt_out_busy; }; /* local function prototypes */ static ssize_t tower_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos); static ssize_t tower_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos); static inline void tower_delete(struct lego_usb_tower *dev); static int tower_open(struct inode *inode, struct file *file); static int tower_release(struct inode *inode, struct file *file); static __poll_t tower_poll(struct file *file, poll_table *wait); static loff_t tower_llseek(struct file *file, loff_t off, int whence); static void tower_check_for_read_packet(struct lego_usb_tower *dev); static void tower_interrupt_in_callback(struct urb *urb); static void tower_interrupt_out_callback(struct urb *urb); static int tower_probe(struct usb_interface *interface, const struct usb_device_id *id); static void tower_disconnect(struct usb_interface *interface); /* file operations needed when we register this driver */ static const struct file_operations tower_fops = { .owner = THIS_MODULE, .read = tower_read, .write = tower_write, .open = tower_open, .release = tower_release, .poll = tower_poll, .llseek = tower_llseek, }; static char *legousbtower_devnode(const struct device *dev, umode_t *mode) { return kasprintf(GFP_KERNEL, "usb/%s", dev_name(dev)); } /* * usb class driver info in order to get a minor number from the usb core, * and to have the device registered with the driver core */ static struct usb_class_driver tower_class = { .name = "legousbtower%d", .devnode = legousbtower_devnode, .fops = &tower_fops, .minor_base = LEGO_USB_TOWER_MINOR_BASE, }; /* usb specific object needed to register this driver with the usb subsystem */ static struct usb_driver tower_driver = { .name = "legousbtower", .probe = tower_probe, .disconnect = tower_disconnect, .id_table = tower_table, }; /* * lego_usb_tower_debug_data */ static inline void lego_usb_tower_debug_data(struct device *dev, const char *function, int size, const unsigned char *data) { dev_dbg(dev, "%s - length = %d, data = %*ph\n", function, size, size, data); } /* * tower_delete */ static inline void tower_delete(struct lego_usb_tower *dev) { /* free data structures */ usb_free_urb(dev->interrupt_in_urb); usb_free_urb(dev->interrupt_out_urb); kfree(dev->read_buffer); kfree(dev->interrupt_in_buffer); kfree(dev->interrupt_out_buffer); usb_put_dev(dev->udev); kfree(dev); } /* * tower_open */ static int tower_open(struct inode *inode, struct file *file) { struct lego_usb_tower *dev = NULL; int subminor; int retval = 0; struct usb_interface *interface; struct tower_reset_reply reset_reply; int result; nonseekable_open(inode, file); subminor = iminor(inode); interface = usb_find_interface(&tower_driver, subminor); if (!interface) { pr_err("error, can't find device for minor %d\n", subminor); retval = -ENODEV; goto exit; } dev = usb_get_intfdata(interface); if (!dev) { retval = -ENODEV; goto exit; } /* lock this device */ if (mutex_lock_interruptible(&dev->lock)) { retval = -ERESTARTSYS; goto exit; } /* allow opening only once */ if (dev->open_count) { retval = -EBUSY; goto unlock_exit; } /* reset the tower */ result = usb_control_msg_recv(dev->udev, 0, LEGO_USB_TOWER_REQUEST_RESET, USB_TYPE_VENDOR | USB_DIR_IN | USB_RECIP_DEVICE, 0, 0, &reset_reply, sizeof(reset_reply), 1000, GFP_KERNEL); if (result < 0) { dev_err(&dev->udev->dev, "LEGO USB Tower reset control request failed\n"); retval = result; goto unlock_exit; } /* initialize in direction */ dev->read_buffer_length = 0; dev->read_packet_length = 0; usb_fill_int_urb(dev->interrupt_in_urb, dev->udev, usb_rcvintpipe(dev->udev, dev->interrupt_in_endpoint->bEndpointAddress), dev->interrupt_in_buffer, usb_endpoint_maxp(dev->interrupt_in_endpoint), tower_interrupt_in_callback, dev, dev->interrupt_in_interval); dev->interrupt_in_done = 0; mb(); retval = usb_submit_urb(dev->interrupt_in_urb, GFP_KERNEL); if (retval) { dev_err(&dev->udev->dev, "Couldn't submit interrupt_in_urb %d\n", retval); goto unlock_exit; } /* save device in the file's private structure */ file->private_data = dev; dev->open_count = 1; unlock_exit: mutex_unlock(&dev->lock); exit: return retval; } /* * tower_release */ static int tower_release(struct inode *inode, struct file *file) { struct lego_usb_tower *dev; int retval = 0; dev = file->private_data; if (dev == NULL) { retval = -ENODEV; goto exit; } mutex_lock(&dev->lock); if (dev->disconnected) { /* the device was unplugged before the file was released */ /* unlock here as tower_delete frees dev */ mutex_unlock(&dev->lock); tower_delete(dev); goto exit; } /* wait until write transfer is finished */ if (dev->interrupt_out_busy) { wait_event_interruptible_timeout(dev->write_wait, !dev->interrupt_out_busy, 2 * HZ); } /* shutdown transfers */ usb_kill_urb(dev->interrupt_in_urb); usb_kill_urb(dev->interrupt_out_urb); dev->open_count = 0; mutex_unlock(&dev->lock); exit: return retval; } /* * tower_check_for_read_packet * * To get correct semantics for signals and non-blocking I/O * with packetizing we pretend not to see any data in the read buffer * until it has been there unchanged for at least * dev->packet_timeout_jiffies, or until the buffer is full. */ static void tower_check_for_read_packet(struct lego_usb_tower *dev) { spin_lock_irq(&dev->read_buffer_lock); if (!packet_timeout || time_after(jiffies, dev->read_last_arrival + dev->packet_timeout_jiffies) || dev->read_buffer_length == read_buffer_size) { dev->read_packet_length = dev->read_buffer_length; } dev->interrupt_in_done = 0; spin_unlock_irq(&dev->read_buffer_lock); } /* * tower_poll */ static __poll_t tower_poll(struct file *file, poll_table *wait) { struct lego_usb_tower *dev; __poll_t mask = 0; dev = file->private_data; if (dev->disconnected) return EPOLLERR | EPOLLHUP; poll_wait(file, &dev->read_wait, wait); poll_wait(file, &dev->write_wait, wait); tower_check_for_read_packet(dev); if (dev->read_packet_length > 0) mask |= EPOLLIN | EPOLLRDNORM; if (!dev->interrupt_out_busy) mask |= EPOLLOUT | EPOLLWRNORM; return mask; } /* * tower_llseek */ static loff_t tower_llseek(struct file *file, loff_t off, int whence) { return -ESPIPE; /* unseekable */ } /* * tower_read */ static ssize_t tower_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { struct lego_usb_tower *dev; size_t bytes_to_read; int i; int retval = 0; unsigned long timeout = 0; dev = file->private_data; /* lock this object */ if (mutex_lock_interruptible(&dev->lock)) { retval = -ERESTARTSYS; goto exit; } /* verify that the device wasn't unplugged */ if (dev->disconnected) { retval = -ENODEV; goto unlock_exit; } /* verify that we actually have some data to read */ if (count == 0) { dev_dbg(&dev->udev->dev, "read request of 0 bytes\n"); goto unlock_exit; } if (read_timeout) timeout = jiffies + msecs_to_jiffies(read_timeout); /* wait for data */ tower_check_for_read_packet(dev); while (dev->read_packet_length == 0) { if (file->f_flags & O_NONBLOCK) { retval = -EAGAIN; goto unlock_exit; } retval = wait_event_interruptible_timeout(dev->read_wait, dev->interrupt_in_done, dev->packet_timeout_jiffies); if (retval < 0) goto unlock_exit; /* reset read timeout during read or write activity */ if (read_timeout && (dev->read_buffer_length || dev->interrupt_out_busy)) { timeout = jiffies + msecs_to_jiffies(read_timeout); } /* check for read timeout */ if (read_timeout && time_after(jiffies, timeout)) { retval = -ETIMEDOUT; goto unlock_exit; } tower_check_for_read_packet(dev); } /* copy the data from read_buffer into userspace */ bytes_to_read = min(count, dev->read_packet_length); if (copy_to_user(buffer, dev->read_buffer, bytes_to_read)) { retval = -EFAULT; goto unlock_exit; } spin_lock_irq(&dev->read_buffer_lock); dev->read_buffer_length -= bytes_to_read; dev->read_packet_length -= bytes_to_read; for (i = 0; i < dev->read_buffer_length; i++) dev->read_buffer[i] = dev->read_buffer[i+bytes_to_read]; spin_unlock_irq(&dev->read_buffer_lock); retval = bytes_to_read; unlock_exit: /* unlock the device */ mutex_unlock(&dev->lock); exit: return retval; } /* * tower_write */ static ssize_t tower_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { struct lego_usb_tower *dev; size_t bytes_to_write; int retval = 0; dev = file->private_data; /* lock this object */ if (mutex_lock_interruptible(&dev->lock)) { retval = -ERESTARTSYS; goto exit; } /* verify that the device wasn't unplugged */ if (dev->disconnected) { retval = -ENODEV; goto unlock_exit; } /* verify that we actually have some data to write */ if (count == 0) { dev_dbg(&dev->udev->dev, "write request of 0 bytes\n"); goto unlock_exit; } /* wait until previous transfer is finished */ while (dev->interrupt_out_busy) { if (file->f_flags & O_NONBLOCK) { retval = -EAGAIN; goto unlock_exit; } retval = wait_event_interruptible(dev->write_wait, !dev->interrupt_out_busy); if (retval) goto unlock_exit; } /* write the data into interrupt_out_buffer from userspace */ bytes_to_write = min_t(int, count, write_buffer_size); dev_dbg(&dev->udev->dev, "%s: count = %zd, bytes_to_write = %zd\n", __func__, count, bytes_to_write); if (copy_from_user(dev->interrupt_out_buffer, buffer, bytes_to_write)) { retval = -EFAULT; goto unlock_exit; } /* send off the urb */ usb_fill_int_urb(dev->interrupt_out_urb, dev->udev, usb_sndintpipe(dev->udev, dev->interrupt_out_endpoint->bEndpointAddress), dev->interrupt_out_buffer, bytes_to_write, tower_interrupt_out_callback, dev, dev->interrupt_out_interval); dev->interrupt_out_busy = 1; wmb(); retval = usb_submit_urb(dev->interrupt_out_urb, GFP_KERNEL); if (retval) { dev->interrupt_out_busy = 0; dev_err(&dev->udev->dev, "Couldn't submit interrupt_out_urb %d\n", retval); goto unlock_exit; } retval = bytes_to_write; unlock_exit: /* unlock the device */ mutex_unlock(&dev->lock); exit: return retval; } /* * tower_interrupt_in_callback */ static void tower_interrupt_in_callback(struct urb *urb) { struct lego_usb_tower *dev = urb->context; int status = urb->status; int retval; unsigned long flags; lego_usb_tower_debug_data(&dev->udev->dev, __func__, urb->actual_length, urb->transfer_buffer); if (status) { if (status == -ENOENT || status == -ECONNRESET || status == -ESHUTDOWN) { goto exit; } else { dev_dbg(&dev->udev->dev, "%s: nonzero status received: %d\n", __func__, status); goto resubmit; /* maybe we can recover */ } } if (urb->actual_length > 0) { spin_lock_irqsave(&dev->read_buffer_lock, flags); if (dev->read_buffer_length + urb->actual_length < read_buffer_size) { memcpy(dev->read_buffer + dev->read_buffer_length, dev->interrupt_in_buffer, urb->actual_length); dev->read_buffer_length += urb->actual_length; dev->read_last_arrival = jiffies; dev_dbg(&dev->udev->dev, "%s: received %d bytes\n", __func__, urb->actual_length); } else { pr_warn("read_buffer overflow, %d bytes dropped\n", urb->actual_length); } spin_unlock_irqrestore(&dev->read_buffer_lock, flags); } resubmit: retval = usb_submit_urb(dev->interrupt_in_urb, GFP_ATOMIC); if (retval) { dev_err(&dev->udev->dev, "%s: usb_submit_urb failed (%d)\n", __func__, retval); } exit: dev->interrupt_in_done = 1; wake_up_interruptible(&dev->read_wait); } /* * tower_interrupt_out_callback */ static void tower_interrupt_out_callback(struct urb *urb) { struct lego_usb_tower *dev = urb->context; int status = urb->status; lego_usb_tower_debug_data(&dev->udev->dev, __func__, urb->actual_length, urb->transfer_buffer); /* sync/async unlink faults aren't errors */ if (status && !(status == -ENOENT || status == -ECONNRESET || status == -ESHUTDOWN)) { dev_dbg(&dev->udev->dev, "%s: nonzero write bulk status received: %d\n", __func__, status); } dev->interrupt_out_busy = 0; wake_up_interruptible(&dev->write_wait); } /* * tower_probe * * Called by the usb core when a new device is connected that it thinks * this driver might be interested in. */ static int tower_probe(struct usb_interface *interface, const struct usb_device_id *id) { struct device *idev = &interface->dev; struct usb_device *udev = interface_to_usbdev(interface); struct lego_usb_tower *dev; struct tower_get_version_reply get_version_reply; int retval = -ENOMEM; int result; /* allocate memory for our device state and initialize it */ dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) goto exit; mutex_init(&dev->lock); dev->udev = usb_get_dev(udev); spin_lock_init(&dev->read_buffer_lock); dev->packet_timeout_jiffies = msecs_to_jiffies(packet_timeout); dev->read_last_arrival = jiffies; init_waitqueue_head(&dev->read_wait); init_waitqueue_head(&dev->write_wait); result = usb_find_common_endpoints_reverse(interface->cur_altsetting, NULL, NULL, &dev->interrupt_in_endpoint, &dev->interrupt_out_endpoint); if (result) { dev_err(idev, "interrupt endpoints not found\n"); retval = result; goto error; } dev->read_buffer = kmalloc(read_buffer_size, GFP_KERNEL); if (!dev->read_buffer) goto error; dev->interrupt_in_buffer = kmalloc(usb_endpoint_maxp(dev->interrupt_in_endpoint), GFP_KERNEL); if (!dev->interrupt_in_buffer) goto error; dev->interrupt_in_urb = usb_alloc_urb(0, GFP_KERNEL); if (!dev->interrupt_in_urb) goto error; dev->interrupt_out_buffer = kmalloc(write_buffer_size, GFP_KERNEL); if (!dev->interrupt_out_buffer) goto error; dev->interrupt_out_urb = usb_alloc_urb(0, GFP_KERNEL); if (!dev->interrupt_out_urb) goto error; dev->interrupt_in_interval = interrupt_in_interval ? interrupt_in_interval : dev->interrupt_in_endpoint->bInterval; dev->interrupt_out_interval = interrupt_out_interval ? interrupt_out_interval : dev->interrupt_out_endpoint->bInterval; /* get the firmware version and log it */ result = usb_control_msg_recv(udev, 0, LEGO_USB_TOWER_REQUEST_GET_VERSION, USB_TYPE_VENDOR | USB_DIR_IN | USB_RECIP_DEVICE, 0, 0, &get_version_reply, sizeof(get_version_reply), 1000, GFP_KERNEL); if (result) { dev_err(idev, "get version request failed: %d\n", result); retval = result; goto error; } dev_info(&interface->dev, "LEGO USB Tower firmware version is %d.%d build %d\n", get_version_reply.major, get_version_reply.minor, le16_to_cpu(get_version_reply.build_no)); /* we can register the device now, as it is ready */ usb_set_intfdata(interface, dev); retval = usb_register_dev(interface, &tower_class); if (retval) { /* something prevented us from registering this driver */ dev_err(idev, "Not able to get a minor for this device.\n"); goto error; } dev->minor = interface->minor; /* let the user know what node this device is now attached to */ dev_info(&interface->dev, "LEGO USB Tower #%d now attached to major " "%d minor %d\n", (dev->minor - LEGO_USB_TOWER_MINOR_BASE), USB_MAJOR, dev->minor); exit: return retval; error: tower_delete(dev); return retval; } /* * tower_disconnect * * Called by the usb core when the device is removed from the system. */ static void tower_disconnect(struct usb_interface *interface) { struct lego_usb_tower *dev; int minor; dev = usb_get_intfdata(interface); minor = dev->minor; /* give back our minor and prevent further open() */ usb_deregister_dev(interface, &tower_class); /* stop I/O */ usb_poison_urb(dev->interrupt_in_urb); usb_poison_urb(dev->interrupt_out_urb); mutex_lock(&dev->lock); /* if the device is not opened, then we clean up right now */ if (!dev->open_count) { mutex_unlock(&dev->lock); tower_delete(dev); } else { dev->disconnected = 1; /* wake up pollers */ wake_up_interruptible_all(&dev->read_wait); wake_up_interruptible_all(&dev->write_wait); mutex_unlock(&dev->lock); } dev_info(&interface->dev, "LEGO USB Tower #%d now disconnected\n", (minor - LEGO_USB_TOWER_MINOR_BASE)); } module_usb_driver(tower_driver); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); |
| 10809 10743 16596 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_WORD_AT_A_TIME_H #define _ASM_WORD_AT_A_TIME_H #include <linux/bitops.h> #include <linux/wordpart.h> struct word_at_a_time { const unsigned long one_bits, high_bits; }; #define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) } /* Return nonzero if it has a zero */ static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c) { unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits; *bits = mask; return mask; } static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c) { return bits; } #ifdef CONFIG_64BIT /* Keep the initial has_zero() value for both bitmask and size calc */ #define create_zero_mask(bits) (bits) static inline unsigned long zero_bytemask(unsigned long bits) { bits = (bits - 1) & ~bits; return bits >> 7; } #define find_zero(bits) (__ffs(bits) >> 3) #else /* Create the final mask for both bytemask and size */ static inline unsigned long create_zero_mask(unsigned long bits) { bits = (bits - 1) & ~bits; return bits >> 7; } /* The mask we created is directly usable as a bytemask */ #define zero_bytemask(mask) (mask) /* Carl Chatfield / Jan Achrenius G+ version for 32-bit */ static inline unsigned long find_zero(unsigned long mask) { /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */ long a = (0x0ff0001+mask) >> 23; /* Fix the 1 for 00 case */ return a & mask; } #endif /* * Load an unaligned word from kernel space. * * In the (very unlikely) case of the word being a page-crosser * and the next page not being mapped, take the exception and * return zeroes in the non-existing part. */ static inline unsigned long load_unaligned_zeropad(const void *addr) { unsigned long ret; asm volatile( "1: mov %[mem], %[ret]\n" "2:\n" _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_ZEROPAD) : [ret] "=r" (ret) : [mem] "m" (*(unsigned long *)addr)); return ret; } #endif /* _ASM_WORD_AT_A_TIME_H */ |
| 3 137 412 415 414 413 140 140 140 140 139 140 139 29 139 138 140 2 415 411 413 56 413 415 1 1 6 1 241 6 6 6 12 101 101 101 101 3 137 137 137 138 138 3 3 3 3 3 3 281 281 155 144 273 9 281 281 280 281 282 280 705 529 526 138 138 3 3 3 3 137 3 135 138 3 135 3 138 138 138 138 138 138 138 137 138 138 1159 1160 484 484 484 483 127 482 483 115 117 483 485 138 485 1122 546 523 519 547 381 377 379 5 3 380 382 400 400 399 399 400 397 400 380 380 382 7 382 400 395 395 79 357 380 376 331 2 73 400 389 394 3 397 398 36 36 12 35 730 708 707 704 689 1 723 282 1327 1393 1327 2175 2181 2177 2174 2180 2181 2171 2176 2181 133 133 133 2173 2172 2181 2181 2177 372 392 369 372 4 4 4 4 4 4 4 4 1932 1732 2 1736 225 70 70 1082 133 133 133 133 987 768 771 673 28 674 672 674 673 674 765 642 204 204 204 242 242 239 241 241 236 235 236 205 242 211 242 241 241 240 656 655 657 660 651 645 642 6 648 651 648 649 649 649 9 660 660 669 389 311 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/page-writeback.c * * Copyright (C) 2002, Linus Torvalds. * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Contains functions related to writing back dirty pages at the * address_space level. * * 10Apr2002 Andrew Morton * Initial version */ #include <linux/kernel.h> #include <linux/math64.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/writeback.h> #include <linux/init.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/blkdev.h> #include <linux/mpage.h> #include <linux/rmap.h> #include <linux/percpu.h> #include <linux/smp.h> #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/pagevec.h> #include <linux/timer.h> #include <linux/sched/rt.h> #include <linux/sched/signal.h> #include <linux/mm_inline.h> #include <trace/events/writeback.h> #include "internal.h" #include "swap.h" /* * Sleep at most 200ms at a time in balance_dirty_pages(). */ #define MAX_PAUSE max(HZ/5, 1) /* * Try to keep balance_dirty_pages() call intervals higher than this many pages * by raising pause time to max_pause when falls below it. */ #define DIRTY_POLL_THRESH (128 >> (PAGE_SHIFT - 10)) /* * Estimate write bandwidth or update dirty limit at 200ms intervals. */ #define BANDWIDTH_INTERVAL max(HZ/5, 1) #define RATELIMIT_CALC_SHIFT 10 /* * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited * will look to see if it needs to force writeback or throttling. */ static long ratelimit_pages = 32; /* The following parameters are exported via /proc/sys/vm */ /* * Start background writeback (via writeback threads) at this percentage */ static int dirty_background_ratio = 10; /* * dirty_background_bytes starts at 0 (disabled) so that it is a function of * dirty_background_ratio * the amount of dirtyable memory */ static unsigned long dirty_background_bytes; /* * free highmem will not be subtracted from the total free memory * for calculating free ratios if vm_highmem_is_dirtyable is true */ static int vm_highmem_is_dirtyable; /* * The generator of dirty data starts writeback at this percentage */ static int vm_dirty_ratio = 20; /* * vm_dirty_bytes starts at 0 (disabled) so that it is a function of * vm_dirty_ratio * the amount of dirtyable memory */ static unsigned long vm_dirty_bytes; /* * The interval between `kupdate'-style writebacks */ unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */ EXPORT_SYMBOL_GPL(dirty_writeback_interval); /* * The longest time for which data is allowed to remain dirty */ unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */ /* * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies: * a full sync is triggered after this time elapses without any disk activity. */ int laptop_mode; EXPORT_SYMBOL(laptop_mode); /* End of sysctl-exported parameters */ struct wb_domain global_wb_domain; /* * Length of period for aging writeout fractions of bdis. This is an * arbitrarily chosen number. The longer the period, the slower fractions will * reflect changes in current writeout rate. */ #define VM_COMPLETIONS_PERIOD_LEN (3*HZ) #ifdef CONFIG_CGROUP_WRITEBACK #define GDTC_INIT(__wb) .wb = (__wb), \ .dom = &global_wb_domain, \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB .dom = &global_wb_domain #define MDTC_INIT(__wb, __gdtc) .wb = (__wb), \ .dom = mem_cgroup_wb_domain(__wb), \ .wb_completions = &(__wb)->memcg_completions, \ .gdtc = __gdtc static bool mdtc_valid(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return dtc->dom; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return mdtc->gdtc; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return &wb->memcg_completions; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { unsigned long this_bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); unsigned long long min = wb->bdi->min_ratio; unsigned long long max = wb->bdi->max_ratio; /* * @wb may already be clean by the time control reaches here and * the total may not include its bw. */ if (this_bw < tot_bw) { if (min) { min *= this_bw; min = div64_ul(min, tot_bw); } if (max < 100 * BDI_RATIO_SCALE) { max *= this_bw; max = div64_ul(max, tot_bw); } } *minp = min; *maxp = max; } #else /* CONFIG_CGROUP_WRITEBACK */ #define GDTC_INIT(__wb) .wb = (__wb), \ .wb_completions = &(__wb)->completions #define GDTC_INIT_NO_WB #define MDTC_INIT(__wb, __gdtc) static bool mdtc_valid(struct dirty_throttle_control *dtc) { return false; } static struct wb_domain *dtc_dom(struct dirty_throttle_control *dtc) { return &global_wb_domain; } static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *mdtc) { return NULL; } static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb) { return NULL; } static void wb_min_max_ratio(struct bdi_writeback *wb, unsigned long *minp, unsigned long *maxp) { *minp = wb->bdi->min_ratio; *maxp = wb->bdi->max_ratio; } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * In a memory zone, there is a certain amount of pages we consider * available for the page cache, which is essentially the number of * free and reclaimable pages, minus some zone reserves to protect * lowmem and the ability to uphold the zone's watermarks without * requiring writeback. * * This number of dirtyable pages is the base value of which the * user-configurable dirty ratio is the effective number of pages that * are allowed to be actually dirtied. Per individual zone, or * globally by using the sum of dirtyable pages over all zones. * * Because the user is allowed to specify the dirty limit globally as * absolute number of bytes, calculating the per-zone dirty limit can * require translating the configured limit into a percentage of * global dirtyable memory first. */ /** * node_dirtyable_memory - number of dirtyable pages in a node * @pgdat: the node * * Return: the node's number of pages potentially available for dirty * page cache. This is the base value for the per-node dirty limits. */ static unsigned long node_dirtyable_memory(struct pglist_data *pgdat) { unsigned long nr_pages = 0; int z; for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = pgdat->node_zones + z; if (!populated_zone(zone)) continue; nr_pages += zone_page_state(zone, NR_FREE_PAGES); } /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ nr_pages -= min(nr_pages, pgdat->totalreserve_pages); nr_pages += node_page_state(pgdat, NR_INACTIVE_FILE); nr_pages += node_page_state(pgdat, NR_ACTIVE_FILE); return nr_pages; } static unsigned long highmem_dirtyable_memory(unsigned long total) { #ifdef CONFIG_HIGHMEM int node; unsigned long x = 0; int i; for_each_node_state(node, N_HIGH_MEMORY) { for (i = ZONE_NORMAL + 1; i < MAX_NR_ZONES; i++) { struct zone *z; unsigned long nr_pages; if (!is_highmem_idx(i)) continue; z = &NODE_DATA(node)->node_zones[i]; if (!populated_zone(z)) continue; nr_pages = zone_page_state(z, NR_FREE_PAGES); /* watch for underflows */ nr_pages -= min(nr_pages, high_wmark_pages(z)); nr_pages += zone_page_state(z, NR_ZONE_INACTIVE_FILE); nr_pages += zone_page_state(z, NR_ZONE_ACTIVE_FILE); x += nr_pages; } } /* * Make sure that the number of highmem pages is never larger * than the number of the total dirtyable memory. This can only * occur in very strange VM situations but we want to make sure * that this does not occur. */ return min(x, total); #else return 0; #endif } /** * global_dirtyable_memory - number of globally dirtyable pages * * Return: the global number of pages potentially available for dirty * page cache. This is the base value for the global dirty limits. */ static unsigned long global_dirtyable_memory(void) { unsigned long x; x = global_zone_page_state(NR_FREE_PAGES); /* * Pages reserved for the kernel should not be considered * dirtyable, to prevent a situation where reclaim has to * clean pages in order to balance the zones. */ x -= min(x, totalreserve_pages); x += global_node_page_state(NR_INACTIVE_FILE); x += global_node_page_state(NR_ACTIVE_FILE); if (!vm_highmem_is_dirtyable) x -= highmem_dirtyable_memory(x); return x + 1; /* Ensure that we never return 0 */ } /** * domain_dirty_limits - calculate thresh and bg_thresh for a wb_domain * @dtc: dirty_throttle_control of interest * * Calculate @dtc->thresh and ->bg_thresh considering * vm_dirty_{bytes|ratio} and dirty_background_{bytes|ratio}. The caller * must ensure that @dtc->avail is set before calling this function. The * dirty limits will be lifted by 1/4 for real-time tasks. */ static void domain_dirty_limits(struct dirty_throttle_control *dtc) { const unsigned long available_memory = dtc->avail; struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc); unsigned long bytes = vm_dirty_bytes; unsigned long bg_bytes = dirty_background_bytes; /* convert ratios to per-PAGE_SIZE for higher precision */ unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100; unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100; unsigned long thresh; unsigned long bg_thresh; struct task_struct *tsk; /* gdtc is !NULL iff @dtc is for memcg domain */ if (gdtc) { unsigned long global_avail = gdtc->avail; /* * The byte settings can't be applied directly to memcg * domains. Convert them to ratios by scaling against * globally available memory. As the ratios are in * per-PAGE_SIZE, they can be obtained by dividing bytes by * number of pages. */ if (bytes) ratio = min(DIV_ROUND_UP(bytes, global_avail), PAGE_SIZE); if (bg_bytes) bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail), PAGE_SIZE); bytes = bg_bytes = 0; } if (bytes) thresh = DIV_ROUND_UP(bytes, PAGE_SIZE); else thresh = (ratio * available_memory) / PAGE_SIZE; if (bg_bytes) bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE); else bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE; tsk = current; if (rt_or_dl_task(tsk)) { bg_thresh += bg_thresh / 4 + global_wb_domain.dirty_limit / 32; thresh += thresh / 4 + global_wb_domain.dirty_limit / 32; } /* * Dirty throttling logic assumes the limits in page units fit into * 32-bits. This gives 16TB dirty limits max which is hopefully enough. */ if (thresh > UINT_MAX) thresh = UINT_MAX; /* This makes sure bg_thresh is within 32-bits as well */ if (bg_thresh >= thresh) bg_thresh = thresh / 2; dtc->thresh = thresh; dtc->bg_thresh = bg_thresh; /* we should eventually report the domain in the TP */ if (!gdtc) trace_global_dirty_state(bg_thresh, thresh); } /** * global_dirty_limits - background-writeback and dirty-throttling thresholds * @pbackground: out parameter for bg_thresh * @pdirty: out parameter for thresh * * Calculate bg_thresh and thresh for global_wb_domain. See * domain_dirty_limits() for details. */ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty) { struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; gdtc.avail = global_dirtyable_memory(); domain_dirty_limits(&gdtc); *pbackground = gdtc.bg_thresh; *pdirty = gdtc.thresh; } /** * node_dirty_limit - maximum number of dirty pages allowed in a node * @pgdat: the node * * Return: the maximum number of dirty pages allowed in a node, based * on the node's dirtyable memory. */ static unsigned long node_dirty_limit(struct pglist_data *pgdat) { unsigned long node_memory = node_dirtyable_memory(pgdat); struct task_struct *tsk = current; unsigned long dirty; if (vm_dirty_bytes) dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) * node_memory / global_dirtyable_memory(); else dirty = vm_dirty_ratio * node_memory / 100; if (rt_or_dl_task(tsk)) dirty += dirty / 4; /* * Dirty throttling logic assumes the limits in page units fit into * 32-bits. This gives 16TB dirty limits max which is hopefully enough. */ return min_t(unsigned long, dirty, UINT_MAX); } /** * node_dirty_ok - tells whether a node is within its dirty limits * @pgdat: the node to check * * Return: %true when the dirty pages in @pgdat are within the node's * dirty limit, %false if the limit is exceeded. */ bool node_dirty_ok(struct pglist_data *pgdat) { unsigned long limit = node_dirty_limit(pgdat); unsigned long nr_pages = 0; nr_pages += node_page_state(pgdat, NR_FILE_DIRTY); nr_pages += node_page_state(pgdat, NR_WRITEBACK); return nr_pages <= limit; } #ifdef CONFIG_SYSCTL static int dirty_background_ratio_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) dirty_background_bytes = 0; return ret; } static int dirty_background_bytes_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; unsigned long old_bytes = dirty_background_bytes; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) { if (DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE) > UINT_MAX) { dirty_background_bytes = old_bytes; return -ERANGE; } dirty_background_ratio = 0; } return ret; } static int dirty_ratio_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int old_ratio = vm_dirty_ratio; int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_ratio != old_ratio) { vm_dirty_bytes = 0; writeback_set_ratelimit(); } return ret; } static int dirty_bytes_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { unsigned long old_bytes = vm_dirty_bytes; int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write && vm_dirty_bytes != old_bytes) { if (DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) > UINT_MAX) { vm_dirty_bytes = old_bytes; return -ERANGE; } writeback_set_ratelimit(); vm_dirty_ratio = 0; } return ret; } #endif static unsigned long wp_next_time(unsigned long cur_time) { cur_time += VM_COMPLETIONS_PERIOD_LEN; /* 0 has a special meaning... */ if (!cur_time) return 1; return cur_time; } static void wb_domain_writeout_add(struct wb_domain *dom, struct fprop_local_percpu *completions, unsigned int max_prop_frac, long nr) { __fprop_add_percpu_max(&dom->completions, completions, max_prop_frac, nr); /* First event after period switching was turned off? */ if (unlikely(!dom->period_time)) { /* * We can race with other wb_domain_writeout_add calls here but * it does not cause any harm since the resulting time when * timer will fire and what is in writeout_period_time will be * roughly the same. */ dom->period_time = wp_next_time(jiffies); mod_timer(&dom->period_timer, dom->period_time); } } /* * Increment @wb's writeout completion count and the global writeout * completion count. Called from __folio_end_writeback(). */ static inline void __wb_writeout_add(struct bdi_writeback *wb, long nr) { struct wb_domain *cgdom; wb_stat_mod(wb, WB_WRITTEN, nr); wb_domain_writeout_add(&global_wb_domain, &wb->completions, wb->bdi->max_prop_frac, nr); cgdom = mem_cgroup_wb_domain(wb); if (cgdom) wb_domain_writeout_add(cgdom, wb_memcg_completions(wb), wb->bdi->max_prop_frac, nr); } void wb_writeout_inc(struct bdi_writeback *wb) { unsigned long flags; local_irq_save(flags); __wb_writeout_add(wb, 1); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(wb_writeout_inc); /* * On idle system, we can be called long after we scheduled because we use * deferred timers so count with missed periods. */ static void writeout_period(struct timer_list *t) { struct wb_domain *dom = timer_container_of(dom, t, period_timer); int miss_periods = (jiffies - dom->period_time) / VM_COMPLETIONS_PERIOD_LEN; if (fprop_new_period(&dom->completions, miss_periods + 1)) { dom->period_time = wp_next_time(dom->period_time + miss_periods * VM_COMPLETIONS_PERIOD_LEN); mod_timer(&dom->period_timer, dom->period_time); } else { /* * Aging has zeroed all fractions. Stop wasting CPU on period * updates. */ dom->period_time = 0; } } int wb_domain_init(struct wb_domain *dom, gfp_t gfp) { memset(dom, 0, sizeof(*dom)); spin_lock_init(&dom->lock); timer_setup(&dom->period_timer, writeout_period, TIMER_DEFERRABLE); dom->dirty_limit_tstamp = jiffies; return fprop_global_init(&dom->completions, gfp); } #ifdef CONFIG_CGROUP_WRITEBACK void wb_domain_exit(struct wb_domain *dom) { timer_delete_sync(&dom->period_timer); fprop_global_destroy(&dom->completions); } #endif /* * bdi_min_ratio keeps the sum of the minimum dirty shares of all * registered backing devices, which, for obvious reasons, can not * exceed 100%. */ static unsigned int bdi_min_ratio; static int bdi_check_pages_limit(unsigned long pages) { unsigned long max_dirty_pages = global_dirtyable_memory(); if (pages > max_dirty_pages) return -EINVAL; return 0; } static unsigned long bdi_ratio_from_pages(unsigned long pages) { unsigned long background_thresh; unsigned long dirty_thresh; unsigned long ratio; global_dirty_limits(&background_thresh, &dirty_thresh); if (!dirty_thresh) return -EINVAL; ratio = div64_u64(pages * 100ULL * BDI_RATIO_SCALE, dirty_thresh); return ratio; } static u64 bdi_get_bytes(unsigned int ratio) { unsigned long background_thresh; unsigned long dirty_thresh; u64 bytes; global_dirty_limits(&background_thresh, &dirty_thresh); bytes = (dirty_thresh * PAGE_SIZE * ratio) / BDI_RATIO_SCALE / 100; return bytes; } static int __bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { unsigned int delta; int ret = 0; if (min_ratio > 100 * BDI_RATIO_SCALE) return -EINVAL; spin_lock_bh(&bdi_lock); if (min_ratio > bdi->max_ratio) { ret = -EINVAL; } else { if (min_ratio < bdi->min_ratio) { delta = bdi->min_ratio - min_ratio; bdi_min_ratio -= delta; bdi->min_ratio = min_ratio; } else { delta = min_ratio - bdi->min_ratio; if (bdi_min_ratio + delta < 100 * BDI_RATIO_SCALE) { bdi_min_ratio += delta; bdi->min_ratio = min_ratio; } else { ret = -EINVAL; } } } spin_unlock_bh(&bdi_lock); return ret; } static int __bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio) { int ret = 0; if (max_ratio > 100 * BDI_RATIO_SCALE) return -EINVAL; spin_lock_bh(&bdi_lock); if (bdi->min_ratio > max_ratio) { ret = -EINVAL; } else { bdi->max_ratio = max_ratio; bdi->max_prop_frac = (FPROP_FRAC_BASE * max_ratio) / (100 * BDI_RATIO_SCALE); } spin_unlock_bh(&bdi_lock); return ret; } int bdi_set_min_ratio_no_scale(struct backing_dev_info *bdi, unsigned int min_ratio) { return __bdi_set_min_ratio(bdi, min_ratio); } int bdi_set_max_ratio_no_scale(struct backing_dev_info *bdi, unsigned int max_ratio) { return __bdi_set_max_ratio(bdi, max_ratio); } int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio) { return __bdi_set_min_ratio(bdi, min_ratio * BDI_RATIO_SCALE); } int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio) { return __bdi_set_max_ratio(bdi, max_ratio * BDI_RATIO_SCALE); } EXPORT_SYMBOL(bdi_set_max_ratio); u64 bdi_get_min_bytes(struct backing_dev_info *bdi) { return bdi_get_bytes(bdi->min_ratio); } int bdi_set_min_bytes(struct backing_dev_info *bdi, u64 min_bytes) { int ret; unsigned long pages = min_bytes >> PAGE_SHIFT; long min_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; min_ratio = bdi_ratio_from_pages(pages); if (min_ratio < 0) return min_ratio; return __bdi_set_min_ratio(bdi, min_ratio); } u64 bdi_get_max_bytes(struct backing_dev_info *bdi) { return bdi_get_bytes(bdi->max_ratio); } int bdi_set_max_bytes(struct backing_dev_info *bdi, u64 max_bytes) { int ret; unsigned long pages = max_bytes >> PAGE_SHIFT; long max_ratio; ret = bdi_check_pages_limit(pages); if (ret) return ret; max_ratio = bdi_ratio_from_pages(pages); if (max_ratio < 0) return max_ratio; return __bdi_set_max_ratio(bdi, max_ratio); } int bdi_set_strict_limit(struct backing_dev_info *bdi, unsigned int strict_limit) { if (strict_limit > 1) return -EINVAL; spin_lock_bh(&bdi_lock); if (strict_limit) bdi->capabilities |= BDI_CAP_STRICTLIMIT; else bdi->capabilities &= ~BDI_CAP_STRICTLIMIT; spin_unlock_bh(&bdi_lock); return 0; } static unsigned long dirty_freerun_ceiling(unsigned long thresh, unsigned long bg_thresh) { return (thresh + bg_thresh) / 2; } static unsigned long hard_dirty_limit(struct wb_domain *dom, unsigned long thresh) { return max(thresh, dom->dirty_limit); } /* * Memory which can be further allocated to a memcg domain is capped by * system-wide clean memory excluding the amount being used in the domain. */ static void mdtc_calc_avail(struct dirty_throttle_control *mdtc, unsigned long filepages, unsigned long headroom) { struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc); unsigned long clean = filepages - min(filepages, mdtc->dirty); unsigned long global_clean = gdtc->avail - min(gdtc->avail, gdtc->dirty); unsigned long other_clean = global_clean - min(global_clean, clean); mdtc->avail = filepages + min(headroom, other_clean); } static inline bool dtc_is_global(struct dirty_throttle_control *dtc) { return mdtc_gdtc(dtc) == NULL; } /* * Dirty background will ignore pages being written as we're trying to * decide whether to put more under writeback. */ static void domain_dirty_avail(struct dirty_throttle_control *dtc, bool include_writeback) { if (dtc_is_global(dtc)) { dtc->avail = global_dirtyable_memory(); dtc->dirty = global_node_page_state(NR_FILE_DIRTY); if (include_writeback) dtc->dirty += global_node_page_state(NR_WRITEBACK); } else { unsigned long filepages = 0, headroom = 0, writeback = 0; mem_cgroup_wb_stats(dtc->wb, &filepages, &headroom, &dtc->dirty, &writeback); if (include_writeback) dtc->dirty += writeback; mdtc_calc_avail(dtc, filepages, headroom); } } /** * __wb_calc_thresh - @wb's share of dirty threshold * @dtc: dirty_throttle_context of interest * @thresh: dirty throttling or dirty background threshold of wb_domain in @dtc * * Note that balance_dirty_pages() will only seriously take dirty throttling * threshold as a hard limit when sleeping max_pause per page is not enough * to keep the dirty pages under control. For example, when the device is * completely stalled due to some error conditions, or when there are 1000 * dd tasks writing to a slow 10MB/s USB key. * In the other normal situations, it acts more gently by throttling the tasks * more (rather than completely block them) when the wb dirty pages go high. * * It allocates high/low dirty limits to fast/slow devices, in order to prevent * - starving fast devices * - piling up dirty pages (that will take long time to sync) on slow devices * * The wb's share of dirty limit will be adapting to its throughput and * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set. * * Return: @wb's dirty limit in pages. For dirty throttling limit, the term * "dirty" in the context of dirty balancing includes all PG_dirty and * PG_writeback pages. */ static unsigned long __wb_calc_thresh(struct dirty_throttle_control *dtc, unsigned long thresh) { struct wb_domain *dom = dtc_dom(dtc); struct bdi_writeback *wb = dtc->wb; u64 wb_thresh; u64 wb_max_thresh; unsigned long numerator, denominator; unsigned long wb_min_ratio, wb_max_ratio; /* * Calculate this wb's share of the thresh ratio. */ fprop_fraction_percpu(&dom->completions, dtc->wb_completions, &numerator, &denominator); wb_thresh = (thresh * (100 * BDI_RATIO_SCALE - bdi_min_ratio)) / (100 * BDI_RATIO_SCALE); wb_thresh *= numerator; wb_thresh = div64_ul(wb_thresh, denominator); wb_min_max_ratio(wb, &wb_min_ratio, &wb_max_ratio); wb_thresh += (thresh * wb_min_ratio) / (100 * BDI_RATIO_SCALE); /* * It's very possible that wb_thresh is close to 0 not because the * device is slow, but that it has remained inactive for long time. * Honour such devices a reasonable good (hopefully IO efficient) * threshold, so that the occasional writes won't be blocked and active * writes can rampup the threshold quickly. */ if (thresh > dtc->dirty) { if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) wb_thresh = max(wb_thresh, (thresh - dtc->dirty) / 100); else wb_thresh = max(wb_thresh, (thresh - dtc->dirty) / 8); } wb_max_thresh = thresh * wb_max_ratio / (100 * BDI_RATIO_SCALE); if (wb_thresh > wb_max_thresh) wb_thresh = wb_max_thresh; return wb_thresh; } unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; domain_dirty_avail(&gdtc, true); return __wb_calc_thresh(&gdtc, thresh); } unsigned long cgwb_calc_thresh(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc = { GDTC_INIT_NO_WB }; struct dirty_throttle_control mdtc = { MDTC_INIT(wb, &gdtc) }; domain_dirty_avail(&gdtc, true); domain_dirty_avail(&mdtc, true); domain_dirty_limits(&mdtc); return __wb_calc_thresh(&mdtc, mdtc.thresh); } /* * setpoint - dirty 3 * f(dirty) := 1.0 + (----------------) * limit - setpoint * * it's a 3rd order polynomial that subjects to * * (1) f(freerun) = 2.0 => rampup dirty_ratelimit reasonably fast * (2) f(setpoint) = 1.0 => the balance point * (3) f(limit) = 0 => the hard limit * (4) df/dx <= 0 => negative feedback control * (5) the closer to setpoint, the smaller |df/dx| (and the reverse) * => fast response on large errors; small oscillation near setpoint */ static long long pos_ratio_polynom(unsigned long setpoint, unsigned long dirty, unsigned long limit) { long long pos_ratio; long x; x = div64_s64(((s64)setpoint - (s64)dirty) << RATELIMIT_CALC_SHIFT, (limit - setpoint) | 1); pos_ratio = x; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT; pos_ratio += 1 << RATELIMIT_CALC_SHIFT; return clamp(pos_ratio, 0LL, 2LL << RATELIMIT_CALC_SHIFT); } /* * Dirty position control. * * (o) global/bdi setpoints * * We want the dirty pages be balanced around the global/wb setpoints. * When the number of dirty pages is higher/lower than the setpoint, the * dirty position control ratio (and hence task dirty ratelimit) will be * decreased/increased to bring the dirty pages back to the setpoint. * * pos_ratio = 1 << RATELIMIT_CALC_SHIFT * * if (dirty < setpoint) scale up pos_ratio * if (dirty > setpoint) scale down pos_ratio * * if (wb_dirty < wb_setpoint) scale up pos_ratio * if (wb_dirty > wb_setpoint) scale down pos_ratio * * task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT * * (o) global control line * * ^ pos_ratio * | * | |<===== global dirty control scope ======>| * 2.0 * * * * * * * * | .* * | . * * | . * * | . * * | . * * | . * * 1.0 ................................* * | . . * * | . . * * | . . * * | . . * * | . . * * 0 +------------.------------------.----------------------*-------------> * freerun^ setpoint^ limit^ dirty pages * * (o) wb control line * * ^ pos_ratio * | * | * * | * * | * * | * * | * |<=========== span ============>| * 1.0 .......................* * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * | . * * 1/4 ...............................................* * * * * * * * * * * * * | . . * | . . * | . . * 0 +----------------------.-------------------------------.-------------> * wb_setpoint^ x_intercept^ * * The wb control line won't drop below pos_ratio=1/4, so that wb_dirty can * be smoothly throttled down to normal if it starts high in situations like * - start writing to a slow SD card and a fast disk at the same time. The SD * card's wb_dirty may rush to many times higher than wb_setpoint. * - the wb dirty thresh drops quickly due to change of JBOD workload */ static void wb_position_ratio(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long write_bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = dtc->limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long wb_thresh = dtc->wb_thresh; unsigned long x_intercept; unsigned long setpoint; /* dirty pages' target balance point */ unsigned long wb_setpoint; unsigned long span; long long pos_ratio; /* for scaling up/down the rate limit */ long x; dtc->pos_ratio = 0; if (unlikely(dtc->dirty >= limit)) return; /* * global setpoint * * See comment for pos_ratio_polynom(). */ setpoint = (freerun + limit) / 2; pos_ratio = pos_ratio_polynom(setpoint, dtc->dirty, limit); /* * The strictlimit feature is a tool preventing mistrusted filesystems * from growing a large number of dirty pages before throttling. For * such filesystems balance_dirty_pages always checks wb counters * against wb limits. Even if global "nr_dirty" is under "freerun". * This is especially important for fuse which sets bdi->max_ratio to * 1% by default. * * Here, in wb_position_ratio(), we calculate pos_ratio based on * two values: wb_dirty and wb_thresh. Let's consider an example: * total amount of RAM is 16GB, bdi->max_ratio is equal to 1%, global * limits are set by default to 10% and 20% (background and throttle). * Then wb_thresh is 1% of 20% of 16GB. This amounts to ~8K pages. * wb_calc_thresh(wb, bg_thresh) is about ~4K pages. wb_setpoint is * about ~6K pages (as the average of background and throttle wb * limits). The 3rd order polynomial will provide positive feedback if * wb_dirty is under wb_setpoint and vice versa. * * Note, that we cannot use global counters in these calculations * because we want to throttle process writing to a strictlimit wb * much earlier than global "freerun" is reached (~23MB vs. ~2.3GB * in the example above). */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { long long wb_pos_ratio; if (dtc->wb_dirty >= wb_thresh) return; wb_setpoint = dirty_freerun_ceiling(wb_thresh, dtc->wb_bg_thresh); if (wb_setpoint == 0 || wb_setpoint == wb_thresh) return; wb_pos_ratio = pos_ratio_polynom(wb_setpoint, dtc->wb_dirty, wb_thresh); /* * Typically, for strictlimit case, wb_setpoint << setpoint * and pos_ratio >> wb_pos_ratio. In the other words global * state ("dirty") is not limiting factor and we have to * make decision based on wb counters. But there is an * important case when global pos_ratio should get precedence: * global limits are exceeded (e.g. due to activities on other * wb's) while given strictlimit wb is below limit. * * "pos_ratio * wb_pos_ratio" would work for the case above, * but it would look too non-natural for the case of all * activity in the system coming from a single strictlimit wb * with bdi->max_ratio == 100%. * * Note that min() below somewhat changes the dynamics of the * control system. Normally, pos_ratio value can be well over 3 * (when globally we are at freerun and wb is well below wb * setpoint). Now the maximum pos_ratio in the same situation * is 2. We might want to tweak this if we observe the control * system is too slow to adapt. */ dtc->pos_ratio = min(pos_ratio, wb_pos_ratio); return; } /* * We have computed basic pos_ratio above based on global situation. If * the wb is over/under its share of dirty pages, we want to scale * pos_ratio further down/up. That is done by the following mechanism. */ /* * wb setpoint * * f(wb_dirty) := 1.0 + k * (wb_dirty - wb_setpoint) * * x_intercept - wb_dirty * := -------------------------- * x_intercept - wb_setpoint * * The main wb control line is a linear function that subjects to * * (1) f(wb_setpoint) = 1.0 * (2) k = - 1 / (8 * write_bw) (in single wb case) * or equally: x_intercept = wb_setpoint + 8 * write_bw * * For single wb case, the dirty pages are observed to fluctuate * regularly within range * [wb_setpoint - write_bw/2, wb_setpoint + write_bw/2] * for various filesystems, where (2) can yield in a reasonable 12.5% * fluctuation range for pos_ratio. * * For JBOD case, wb_thresh (not wb_dirty!) could fluctuate up to its * own size, so move the slope over accordingly and choose a slope that * yields 100% pos_ratio fluctuation on suddenly doubled wb_thresh. */ if (unlikely(wb_thresh > dtc->thresh)) wb_thresh = dtc->thresh; /* * scale global setpoint to wb's: * wb_setpoint = setpoint * wb_thresh / thresh */ x = div_u64((u64)wb_thresh << 16, dtc->thresh | 1); wb_setpoint = setpoint * (u64)x >> 16; /* * Use span=(8*write_bw) in single wb case as indicated by * (thresh - wb_thresh ~= 0) and transit to wb_thresh in JBOD case. * * wb_thresh thresh - wb_thresh * span = --------- * (8 * write_bw) + ------------------ * wb_thresh * thresh thresh */ span = (dtc->thresh - wb_thresh + 8 * write_bw) * (u64)x >> 16; x_intercept = wb_setpoint + span; if (dtc->wb_dirty < x_intercept - span / 4) { pos_ratio = div64_u64(pos_ratio * (x_intercept - dtc->wb_dirty), (x_intercept - wb_setpoint) | 1); } else pos_ratio /= 4; /* * wb reserve area, safeguard against dirty pool underrun and disk idle * It may push the desired control point of global dirty pages higher * than setpoint. */ x_intercept = wb_thresh / 2; if (dtc->wb_dirty < x_intercept) { if (dtc->wb_dirty > x_intercept / 8) pos_ratio = div_u64(pos_ratio * x_intercept, dtc->wb_dirty); else pos_ratio *= 8; } dtc->pos_ratio = pos_ratio; } static void wb_update_write_bandwidth(struct bdi_writeback *wb, unsigned long elapsed, unsigned long written) { const unsigned long period = roundup_pow_of_two(3 * HZ); unsigned long avg = wb->avg_write_bandwidth; unsigned long old = wb->write_bandwidth; u64 bw; /* * bw = written * HZ / elapsed * * bw * elapsed + write_bandwidth * (period - elapsed) * write_bandwidth = --------------------------------------------------- * period * * @written may have decreased due to folio_redirty_for_writepage(). * Avoid underflowing @bw calculation. */ bw = written - min(written, wb->written_stamp); bw *= HZ; if (unlikely(elapsed > period)) { bw = div64_ul(bw, elapsed); avg = bw; goto out; } bw += (u64)wb->write_bandwidth * (period - elapsed); bw >>= ilog2(period); /* * one more level of smoothing, for filtering out sudden spikes */ if (avg > old && old >= (unsigned long)bw) avg -= (avg - old) >> 3; if (avg < old && old <= (unsigned long)bw) avg += (old - avg) >> 3; out: /* keep avg > 0 to guarantee that tot > 0 if there are dirty wbs */ avg = max(avg, 1LU); if (wb_has_dirty_io(wb)) { long delta = avg - wb->avg_write_bandwidth; WARN_ON_ONCE(atomic_long_add_return(delta, &wb->bdi->tot_write_bandwidth) <= 0); } wb->write_bandwidth = bw; WRITE_ONCE(wb->avg_write_bandwidth, avg); } static void update_dirty_limit(struct dirty_throttle_control *dtc) { struct wb_domain *dom = dtc_dom(dtc); unsigned long thresh = dtc->thresh; unsigned long limit = dom->dirty_limit; /* * Follow up in one step. */ if (limit < thresh) { limit = thresh; goto update; } /* * Follow down slowly. Use the higher one as the target, because thresh * may drop below dirty. This is exactly the reason to introduce * dom->dirty_limit which is guaranteed to lie above the dirty pages. */ thresh = max(thresh, dtc->dirty); if (limit > thresh) { limit -= (limit - thresh) >> 5; goto update; } return; update: dom->dirty_limit = limit; } static void domain_update_dirty_limit(struct dirty_throttle_control *dtc, unsigned long now) { struct wb_domain *dom = dtc_dom(dtc); /* * check locklessly first to optimize away locking for the most time */ if (time_before(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) return; spin_lock(&dom->lock); if (time_after_eq(now, dom->dirty_limit_tstamp + BANDWIDTH_INTERVAL)) { update_dirty_limit(dtc); dom->dirty_limit_tstamp = now; } spin_unlock(&dom->lock); } /* * Maintain wb->dirty_ratelimit, the base dirty throttle rate. * * Normal wb tasks will be curbed at or below it in long term. * Obviously it should be around (write_bw / N) when there are N dd tasks. */ static void wb_update_dirty_ratelimit(struct dirty_throttle_control *dtc, unsigned long dirtied, unsigned long elapsed) { struct bdi_writeback *wb = dtc->wb; unsigned long dirty = dtc->dirty; unsigned long freerun = dirty_freerun_ceiling(dtc->thresh, dtc->bg_thresh); unsigned long limit = hard_dirty_limit(dtc_dom(dtc), dtc->thresh); unsigned long setpoint = (freerun + limit) / 2; unsigned long write_bw = wb->avg_write_bandwidth; unsigned long dirty_ratelimit = wb->dirty_ratelimit; unsigned long dirty_rate; unsigned long task_ratelimit; unsigned long balanced_dirty_ratelimit; unsigned long step; unsigned long x; unsigned long shift; /* * The dirty rate will match the writeout rate in long term, except * when dirty pages are truncated by userspace or re-dirtied by FS. */ dirty_rate = (dirtied - wb->dirtied_stamp) * HZ / elapsed; /* * task_ratelimit reflects each dd's dirty rate for the past 200ms. */ task_ratelimit = (u64)dirty_ratelimit * dtc->pos_ratio >> RATELIMIT_CALC_SHIFT; task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */ /* * A linear estimation of the "balanced" throttle rate. The theory is, * if there are N dd tasks, each throttled at task_ratelimit, the wb's * dirty_rate will be measured to be (N * task_ratelimit). So the below * formula will yield the balanced rate limit (write_bw / N). * * Note that the expanded form is not a pure rate feedback: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) (1) * but also takes pos_ratio into account: * rate_(i+1) = rate_(i) * (write_bw / dirty_rate) * pos_ratio (2) * * (1) is not realistic because pos_ratio also takes part in balancing * the dirty rate. Consider the state * pos_ratio = 0.5 (3) * rate = 2 * (write_bw / N) (4) * If (1) is used, it will stuck in that state! Because each dd will * be throttled at * task_ratelimit = pos_ratio * rate = (write_bw / N) (5) * yielding * dirty_rate = N * task_ratelimit = write_bw (6) * put (6) into (1) we get * rate_(i+1) = rate_(i) (7) * * So we end up using (2) to always keep * rate_(i+1) ~= (write_bw / N) (8) * regardless of the value of pos_ratio. As long as (8) is satisfied, * pos_ratio is able to drive itself to 1.0, which is not only where * the dirty count meet the setpoint, but also where the slope of * pos_ratio is most flat and hence task_ratelimit is least fluctuated. */ balanced_dirty_ratelimit = div_u64((u64)task_ratelimit * write_bw, dirty_rate | 1); /* * balanced_dirty_ratelimit ~= (write_bw / N) <= write_bw */ if (unlikely(balanced_dirty_ratelimit > write_bw)) balanced_dirty_ratelimit = write_bw; /* * We could safely do this and return immediately: * * wb->dirty_ratelimit = balanced_dirty_ratelimit; * * However to get a more stable dirty_ratelimit, the below elaborated * code makes use of task_ratelimit to filter out singular points and * limit the step size. * * The below code essentially only uses the relative value of * * task_ratelimit - dirty_ratelimit * = (pos_ratio - 1) * dirty_ratelimit * * which reflects the direction and size of dirty position error. */ /* * dirty_ratelimit will follow balanced_dirty_ratelimit iff * task_ratelimit is on the same side of dirty_ratelimit, too. * For example, when * - dirty_ratelimit > balanced_dirty_ratelimit * - dirty_ratelimit > task_ratelimit (dirty pages are above setpoint) * lowering dirty_ratelimit will help meet both the position and rate * control targets. Otherwise, don't update dirty_ratelimit if it will * only help meet the rate target. After all, what the users ultimately * feel and care are stable dirty rate and small position error. * * |task_ratelimit - dirty_ratelimit| is used to limit the step size * and filter out the singular points of balanced_dirty_ratelimit. Which * keeps jumping around randomly and can even leap far away at times * due to the small 200ms estimation period of dirty_rate (we want to * keep that period small to reduce time lags). */ step = 0; /* * For strictlimit case, calculations above were based on wb counters * and limits (starting from pos_ratio = wb_position_ratio() and up to * balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate). * Hence, to calculate "step" properly, we have to use wb_dirty as * "dirty" and wb_setpoint as "setpoint". */ if (unlikely(wb->bdi->capabilities & BDI_CAP_STRICTLIMIT)) { dirty = dtc->wb_dirty; setpoint = (dtc->wb_thresh + dtc->wb_bg_thresh) / 2; } if (dirty < setpoint) { x = min3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit < x) step = x - dirty_ratelimit; } else { x = max3(wb->balanced_dirty_ratelimit, balanced_dirty_ratelimit, task_ratelimit); if (dirty_ratelimit > x) step = dirty_ratelimit - x; } /* * Don't pursue 100% rate matching. It's impossible since the balanced * rate itself is constantly fluctuating. So decrease the track speed * when it gets close to the target. Helps eliminate pointless tremors. */ shift = dirty_ratelimit / (2 * step + 1); if (shift < BITS_PER_LONG) step = DIV_ROUND_UP(step >> shift, 8); else step = 0; if (dirty_ratelimit < balanced_dirty_ratelimit) dirty_ratelimit += step; else dirty_ratelimit -= step; WRITE_ONCE(wb->dirty_ratelimit, max(dirty_ratelimit, 1UL)); wb->balanced_dirty_ratelimit = balanced_dirty_ratelimit; trace_bdi_dirty_ratelimit(wb, dirty_rate, task_ratelimit); } static void __wb_update_bandwidth(struct dirty_throttle_control *gdtc, struct dirty_throttle_control *mdtc, bool update_ratelimit) { struct bdi_writeback *wb = gdtc->wb; unsigned long now = jiffies; unsigned long elapsed; unsigned long dirtied; unsigned long written; spin_lock(&wb->list_lock); /* * Lockless checks for elapsed time are racy and delayed update after * IO completion doesn't do it at all (to make sure written pages are * accounted reasonably quickly). Make sure elapsed >= 1 to avoid * division errors. */ elapsed = max(now - wb->bw_time_stamp, 1UL); dirtied = percpu_counter_read(&wb->stat[WB_DIRTIED]); written = percpu_counter_read(&wb->stat[WB_WRITTEN]); if (update_ratelimit) { domain_update_dirty_limit(gdtc, now); wb_update_dirty_ratelimit(gdtc, dirtied, elapsed); /* * @mdtc is always NULL if !CGROUP_WRITEBACK but the * compiler has no way to figure that out. Help it. */ if (IS_ENABLED(CONFIG_CGROUP_WRITEBACK) && mdtc) { domain_update_dirty_limit(mdtc, now); wb_update_dirty_ratelimit(mdtc, dirtied, elapsed); } } wb_update_write_bandwidth(wb, elapsed, written); wb->dirtied_stamp = dirtied; wb->written_stamp = written; WRITE_ONCE(wb->bw_time_stamp, now); spin_unlock(&wb->list_lock); } void wb_update_bandwidth(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; __wb_update_bandwidth(&gdtc, NULL, false); } /* Interval after which we consider wb idle and don't estimate bandwidth */ #define WB_BANDWIDTH_IDLE_JIF (HZ) static void wb_bandwidth_estimate_start(struct bdi_writeback *wb) { unsigned long now = jiffies; unsigned long elapsed = now - READ_ONCE(wb->bw_time_stamp); if (elapsed > WB_BANDWIDTH_IDLE_JIF && !atomic_read(&wb->writeback_inodes)) { spin_lock(&wb->list_lock); wb->dirtied_stamp = wb_stat(wb, WB_DIRTIED); wb->written_stamp = wb_stat(wb, WB_WRITTEN); WRITE_ONCE(wb->bw_time_stamp, now); spin_unlock(&wb->list_lock); } } /* * After a task dirtied this many pages, balance_dirty_pages_ratelimited() * will look to see if it needs to start dirty throttling. * * If dirty_poll_interval is too low, big NUMA machines will call the expensive * global_zone_page_state() too often. So scale it near-sqrt to the safety margin * (the number of pages we may dirty without exceeding the dirty limits). */ static unsigned long dirty_poll_interval(unsigned long dirty, unsigned long thresh) { if (thresh > dirty) return 1UL << (ilog2(thresh - dirty) >> 1); return 1; } static unsigned long wb_max_pause(struct bdi_writeback *wb, unsigned long wb_dirty) { unsigned long bw = READ_ONCE(wb->avg_write_bandwidth); unsigned long t; /* * Limit pause time for small memory systems. If sleeping for too long * time, a small pool of dirty/writeback pages may go empty and disk go * idle. * * 8 serves as the safety ratio. */ t = wb_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8)); t++; return min_t(unsigned long, t, MAX_PAUSE); } static long wb_min_pause(struct bdi_writeback *wb, long max_pause, unsigned long task_ratelimit, unsigned long dirty_ratelimit, int *nr_dirtied_pause) { long hi = ilog2(READ_ONCE(wb->avg_write_bandwidth)); long lo = ilog2(READ_ONCE(wb->dirty_ratelimit)); long t; /* target pause */ long pause; /* estimated next pause */ int pages; /* target nr_dirtied_pause */ /* target for 10ms pause on 1-dd case */ t = max(1, HZ / 100); /* * Scale up pause time for concurrent dirtiers in order to reduce CPU * overheads. * * (N * 10ms) on 2^N concurrent tasks. */ if (hi > lo) t += (hi - lo) * (10 * HZ) / 1024; /* * This is a bit convoluted. We try to base the next nr_dirtied_pause * on the much more stable dirty_ratelimit. However the next pause time * will be computed based on task_ratelimit and the two rate limits may * depart considerably at some time. Especially if task_ratelimit goes * below dirty_ratelimit/2 and the target pause is max_pause, the next * pause time will be max_pause*2 _trimmed down_ to max_pause. As a * result task_ratelimit won't be executed faithfully, which could * eventually bring down dirty_ratelimit. * * We apply two rules to fix it up: * 1) try to estimate the next pause time and if necessary, use a lower * nr_dirtied_pause so as not to exceed max_pause. When this happens, * nr_dirtied_pause will be "dancing" with task_ratelimit. * 2) limit the target pause time to max_pause/2, so that the normal * small fluctuations of task_ratelimit won't trigger rule (1) and * nr_dirtied_pause will remain as stable as dirty_ratelimit. */ t = min(t, 1 + max_pause / 2); pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); /* * Tiny nr_dirtied_pause is found to hurt I/O performance in the test * case fio-mmap-randwrite-64k, which does 16*{sync read, async write}. * When the 16 consecutive reads are often interrupted by some dirty * throttling pause during the async writes, cfq will go into idles * (deadline is fine). So push nr_dirtied_pause as high as possible * until reaches DIRTY_POLL_THRESH=32 pages. */ if (pages < DIRTY_POLL_THRESH) { t = max_pause; pages = dirty_ratelimit * t / roundup_pow_of_two(HZ); if (pages > DIRTY_POLL_THRESH) { pages = DIRTY_POLL_THRESH; t = HZ * DIRTY_POLL_THRESH / dirty_ratelimit; } } pause = HZ * pages / (task_ratelimit + 1); if (pause > max_pause) { t = max_pause; pages = task_ratelimit * t / roundup_pow_of_two(HZ); } *nr_dirtied_pause = pages; /* * The minimal pause time will normally be half the target pause time. */ return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t; } static inline void wb_dirty_limits(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; unsigned long wb_reclaimable; /* * wb_thresh is not treated as some limiting factor as * dirty_thresh, due to reasons * - in JBOD setup, wb_thresh can fluctuate a lot * - in a system with HDD and USB key, the USB key may somehow * go into state (wb_dirty >> wb_thresh) either because * wb_dirty starts high, or because wb_thresh drops low. * In this case we don't want to hard throttle the USB key * dirtiers for 100 seconds until wb_dirty drops under * wb_thresh. Instead the auxiliary wb control line in * wb_position_ratio() will let the dirtier task progress * at some rate <= (write_bw / 2) for bringing down wb_dirty. */ dtc->wb_thresh = __wb_calc_thresh(dtc, dtc->thresh); dtc->wb_bg_thresh = dtc->thresh ? div_u64((u64)dtc->wb_thresh * dtc->bg_thresh, dtc->thresh) : 0; /* * In order to avoid the stacked BDI deadlock we need * to ensure we accurately count the 'dirty' pages when * the threshold is low. * * Otherwise it would be possible to get thresh+n pages * reported dirty, even though there are thresh-m pages * actually dirty; with m+n sitting in the percpu * deltas. */ if (dtc->wb_thresh < 2 * wb_stat_error()) { wb_reclaimable = wb_stat_sum(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat_sum(wb, WB_WRITEBACK); } else { wb_reclaimable = wb_stat(wb, WB_RECLAIMABLE); dtc->wb_dirty = wb_reclaimable + wb_stat(wb, WB_WRITEBACK); } } static unsigned long domain_poll_intv(struct dirty_throttle_control *dtc, bool strictlimit) { unsigned long dirty, thresh; if (strictlimit) { dirty = dtc->wb_dirty; thresh = dtc->wb_thresh; } else { dirty = dtc->dirty; thresh = dtc->thresh; } return dirty_poll_interval(dirty, thresh); } /* * Throttle it only when the background writeback cannot catch-up. This avoids * (excessively) small writeouts when the wb limits are ramping up in case of * !strictlimit. * * In strictlimit case make decision based on the wb counters and limits. Small * writeouts when the wb limits are ramping up are the price we consciously pay * for strictlimit-ing. */ static void domain_dirty_freerun(struct dirty_throttle_control *dtc, bool strictlimit) { unsigned long dirty, thresh, bg_thresh; if (unlikely(strictlimit)) { wb_dirty_limits(dtc); dirty = dtc->wb_dirty; thresh = dtc->wb_thresh; bg_thresh = dtc->wb_bg_thresh; } else { dirty = dtc->dirty; thresh = dtc->thresh; bg_thresh = dtc->bg_thresh; } dtc->freerun = dirty <= dirty_freerun_ceiling(thresh, bg_thresh); } static void balance_domain_limits(struct dirty_throttle_control *dtc, bool strictlimit) { domain_dirty_avail(dtc, true); domain_dirty_limits(dtc); domain_dirty_freerun(dtc, strictlimit); } static void wb_dirty_freerun(struct dirty_throttle_control *dtc, bool strictlimit) { dtc->freerun = false; /* was already handled in domain_dirty_freerun */ if (strictlimit) return; wb_dirty_limits(dtc); /* * LOCAL_THROTTLE tasks must not be throttled when below the per-wb * freerun ceiling. */ if (!(current->flags & PF_LOCAL_THROTTLE)) return; dtc->freerun = dtc->wb_dirty < dirty_freerun_ceiling(dtc->wb_thresh, dtc->wb_bg_thresh); } static inline void wb_dirty_exceeded(struct dirty_throttle_control *dtc, bool strictlimit) { dtc->dirty_exceeded = (dtc->wb_dirty > dtc->wb_thresh) && ((dtc->dirty > dtc->thresh) || strictlimit); } /* * The limits fields dirty_exceeded and pos_ratio won't be updated if wb is * in freerun state. Please don't use these invalid fields in freerun case. */ static void balance_wb_limits(struct dirty_throttle_control *dtc, bool strictlimit) { wb_dirty_freerun(dtc, strictlimit); if (dtc->freerun) return; wb_dirty_exceeded(dtc, strictlimit); wb_position_ratio(dtc); } /* * balance_dirty_pages() must be called by processes which are generating dirty * data. It looks at the number of dirty pages in the machine and will force * the caller to wait once crossing the (background_thresh + dirty_thresh) / 2. * If we're over `background_thresh' then the writeback threads are woken to * perform some writeout. */ static int balance_dirty_pages(struct bdi_writeback *wb, unsigned long pages_dirtied, unsigned int flags) { struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc_stor = { MDTC_INIT(wb, &gdtc_stor) }; struct dirty_throttle_control * const gdtc = &gdtc_stor; struct dirty_throttle_control * const mdtc = mdtc_valid(&mdtc_stor) ? &mdtc_stor : NULL; struct dirty_throttle_control *sdtc; unsigned long nr_dirty; long period; long pause; long max_pause; long min_pause; int nr_dirtied_pause; unsigned long task_ratelimit; unsigned long dirty_ratelimit; struct backing_dev_info *bdi = wb->bdi; bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; unsigned long start_time = jiffies; int ret = 0; for (;;) { unsigned long now = jiffies; nr_dirty = global_node_page_state(NR_FILE_DIRTY); balance_domain_limits(gdtc, strictlimit); if (mdtc) { /* * If @wb belongs to !root memcg, repeat the same * basic calculations for the memcg domain. */ balance_domain_limits(mdtc, strictlimit); } /* * In laptop mode, we wait until hitting the higher threshold * before starting background writeout, and then write out all * the way down to the lower threshold. So slow writers cause * minimal disk activity. * * In normal mode, we start background writeout at the lower * background_thresh, to keep the amount of dirty memory low. */ if (!laptop_mode && nr_dirty > gdtc->bg_thresh && !writeback_in_progress(wb)) wb_start_background_writeback(wb); /* * If memcg domain is in effect, @dirty should be under * both global and memcg freerun ceilings. */ if (gdtc->freerun && (!mdtc || mdtc->freerun)) { unsigned long intv; unsigned long m_intv; free_running: intv = domain_poll_intv(gdtc, strictlimit); m_intv = ULONG_MAX; current->dirty_paused_when = now; current->nr_dirtied = 0; if (mdtc) m_intv = domain_poll_intv(mdtc, strictlimit); current->nr_dirtied_pause = min(intv, m_intv); break; } /* Start writeback even when in laptop mode */ if (unlikely(!writeback_in_progress(wb))) wb_start_background_writeback(wb); mem_cgroup_flush_foreign(wb); /* * Calculate global domain's pos_ratio and select the * global dtc by default. */ balance_wb_limits(gdtc, strictlimit); if (gdtc->freerun) goto free_running; sdtc = gdtc; if (mdtc) { /* * If memcg domain is in effect, calculate its * pos_ratio. @wb should satisfy constraints from * both global and memcg domains. Choose the one * w/ lower pos_ratio. */ balance_wb_limits(mdtc, strictlimit); if (mdtc->freerun) goto free_running; if (mdtc->pos_ratio < gdtc->pos_ratio) sdtc = mdtc; } wb->dirty_exceeded = gdtc->dirty_exceeded || (mdtc && mdtc->dirty_exceeded); if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) + BANDWIDTH_INTERVAL)) __wb_update_bandwidth(gdtc, mdtc, true); /* throttle according to the chosen dtc */ dirty_ratelimit = READ_ONCE(wb->dirty_ratelimit); task_ratelimit = ((u64)dirty_ratelimit * sdtc->pos_ratio) >> RATELIMIT_CALC_SHIFT; max_pause = wb_max_pause(wb, sdtc->wb_dirty); min_pause = wb_min_pause(wb, max_pause, task_ratelimit, dirty_ratelimit, &nr_dirtied_pause); if (unlikely(task_ratelimit == 0)) { period = max_pause; pause = max_pause; goto pause; } period = HZ * pages_dirtied / task_ratelimit; pause = period; if (current->dirty_paused_when) pause -= now - current->dirty_paused_when; /* * For less than 1s think time (ext3/4 may block the dirtier * for up to 800ms from time to time on 1-HDD; so does xfs, * however at much less frequency), try to compensate it in * future periods by updating the virtual time; otherwise just * do a reset, as it may be a light dirtier. */ if (pause < min_pause) { trace_balance_dirty_pages(wb, sdtc, dirty_ratelimit, task_ratelimit, pages_dirtied, period, min(pause, 0L), start_time); if (pause < -HZ) { current->dirty_paused_when = now; current->nr_dirtied = 0; } else if (period) { current->dirty_paused_when += period; current->nr_dirtied = 0; } else if (current->nr_dirtied_pause <= pages_dirtied) current->nr_dirtied_pause += pages_dirtied; break; } if (unlikely(pause > max_pause)) { /* for occasional dropped task_ratelimit */ now += min(pause - max_pause, max_pause); pause = max_pause; } pause: trace_balance_dirty_pages(wb, sdtc, dirty_ratelimit, task_ratelimit, pages_dirtied, period, pause, start_time); if (flags & BDP_ASYNC) { ret = -EAGAIN; break; } __set_current_state(TASK_KILLABLE); bdi->last_bdp_sleep = jiffies; io_schedule_timeout(pause); current->dirty_paused_when = now + pause; current->nr_dirtied = 0; current->nr_dirtied_pause = nr_dirtied_pause; /* * This is typically equal to (dirty < thresh) and can also * keep "1000+ dd on a slow USB stick" under control. */ if (task_ratelimit) break; /* * In the case of an unresponsive NFS server and the NFS dirty * pages exceeds dirty_thresh, give the other good wb's a pipe * to go through, so that tasks on them still remain responsive. * * In theory 1 page is enough to keep the consumer-producer * pipe going: the flusher cleans 1 page => the task dirties 1 * more page. However wb_dirty has accounting errors. So use * the larger and more IO friendly wb_stat_error. */ if (sdtc->wb_dirty <= wb_stat_error()) break; if (fatal_signal_pending(current)) break; } return ret; } static DEFINE_PER_CPU(int, bdp_ratelimits); /* * Normal tasks are throttled by * loop { * dirty tsk->nr_dirtied_pause pages; * take a snap in balance_dirty_pages(); * } * However there is a worst case. If every task exit immediately when dirtied * (tsk->nr_dirtied_pause - 1) pages, balance_dirty_pages() will never be * called to throttle the page dirties. The solution is to save the not yet * throttled page dirties in dirty_throttle_leaks on task exit and charge them * randomly into the running tasks. This works well for the above worst case, * as the new task will pick up and accumulate the old task's leaked dirty * count and eventually get throttled. */ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; /** * balance_dirty_pages_ratelimited_flags - Balance dirty memory state. * @mapping: address_space which was dirtied. * @flags: BDP flags. * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * See balance_dirty_pages_ratelimited() for details. * * Return: If @flags contains BDP_ASYNC, it may return -EAGAIN to * indicate that memory is out of balance and the caller must wait * for I/O to complete. Otherwise, it will return 0 to indicate * that either memory was already in balance, or it was able to sleep * until the amount of dirty memory returned to balance. */ int balance_dirty_pages_ratelimited_flags(struct address_space *mapping, unsigned int flags) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; int ratelimit; int ret = 0; int *p; if (!(bdi->capabilities & BDI_CAP_WRITEBACK)) return ret; if (inode_cgwb_enabled(inode)) wb = wb_get_create_current(bdi, GFP_KERNEL); if (!wb) wb = &bdi->wb; ratelimit = current->nr_dirtied_pause; if (wb->dirty_exceeded) ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10)); preempt_disable(); /* * This prevents one CPU to accumulate too many dirtied pages without * calling into balance_dirty_pages(), which can happen when there are * 1000+ tasks, all of them start dirtying pages at exactly the same * time, hence all honoured too large initial task->nr_dirtied_pause. */ p = this_cpu_ptr(&bdp_ratelimits); if (unlikely(current->nr_dirtied >= ratelimit)) *p = 0; else if (unlikely(*p >= ratelimit_pages)) { *p = 0; ratelimit = 0; } /* * Pick up the dirtied pages by the exited tasks. This avoids lots of * short-lived tasks (eg. gcc invocations in a kernel build) escaping * the dirty throttling and livelock other long-run dirtiers. */ p = this_cpu_ptr(&dirty_throttle_leaks); if (*p > 0 && current->nr_dirtied < ratelimit) { unsigned long nr_pages_dirtied; nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied); *p -= nr_pages_dirtied; current->nr_dirtied += nr_pages_dirtied; } preempt_enable(); if (unlikely(current->nr_dirtied >= ratelimit)) ret = balance_dirty_pages(wb, current->nr_dirtied, flags); wb_put(wb); return ret; } EXPORT_SYMBOL_GPL(balance_dirty_pages_ratelimited_flags); /** * balance_dirty_pages_ratelimited - balance dirty memory state. * @mapping: address_space which was dirtied. * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * Once we're over the dirty memory limit we decrease the ratelimiting * by a lot, to prevent individual processes from overshooting the limit * by (ratelimit_pages) each. */ void balance_dirty_pages_ratelimited(struct address_space *mapping) { balance_dirty_pages_ratelimited_flags(mapping, 0); } EXPORT_SYMBOL(balance_dirty_pages_ratelimited); /* * Similar to wb_dirty_limits, wb_bg_dirty_limits also calculates dirty * and thresh, but it's for background writeback. */ static void wb_bg_dirty_limits(struct dirty_throttle_control *dtc) { struct bdi_writeback *wb = dtc->wb; dtc->wb_bg_thresh = __wb_calc_thresh(dtc, dtc->bg_thresh); if (dtc->wb_bg_thresh < 2 * wb_stat_error()) dtc->wb_dirty = wb_stat_sum(wb, WB_RECLAIMABLE); else dtc->wb_dirty = wb_stat(wb, WB_RECLAIMABLE); } static bool domain_over_bg_thresh(struct dirty_throttle_control *dtc) { domain_dirty_avail(dtc, false); domain_dirty_limits(dtc); if (dtc->dirty > dtc->bg_thresh) return true; wb_bg_dirty_limits(dtc); if (dtc->wb_dirty > dtc->wb_bg_thresh) return true; return false; } /** * wb_over_bg_thresh - does @wb need to be written back? * @wb: bdi_writeback of interest * * Determines whether background writeback should keep writing @wb or it's * clean enough. * * Return: %true if writeback should continue. */ bool wb_over_bg_thresh(struct bdi_writeback *wb) { struct dirty_throttle_control gdtc = { GDTC_INIT(wb) }; struct dirty_throttle_control mdtc = { MDTC_INIT(wb, &gdtc) }; if (domain_over_bg_thresh(&gdtc)) return true; if (mdtc_valid(&mdtc)) return domain_over_bg_thresh(&mdtc); return false; } #ifdef CONFIG_SYSCTL /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ static int dirty_writeback_centisecs_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos) { unsigned int old_interval = dirty_writeback_interval; int ret; ret = proc_dointvec(table, write, buffer, length, ppos); /* * Writing 0 to dirty_writeback_interval will disable periodic writeback * and a different non-zero value will wakeup the writeback threads. * wb_wakeup_delayed() would be more appropriate, but it's a pain to * iterate over all bdis and wbs. * The reason we do this is to make the change take effect immediately. */ if (!ret && write && dirty_writeback_interval && dirty_writeback_interval != old_interval) wakeup_flusher_threads(WB_REASON_PERIODIC); return ret; } #endif void laptop_mode_timer_fn(struct timer_list *t) { struct backing_dev_info *backing_dev_info = timer_container_of(backing_dev_info, t, laptop_mode_wb_timer); wakeup_flusher_threads_bdi(backing_dev_info, WB_REASON_LAPTOP_TIMER); } /* * We've spun up the disk and we're in laptop mode: schedule writeback * of all dirty data a few seconds from now. If the flush is already scheduled * then push it back - the user is still using the disk. */ void laptop_io_completion(struct backing_dev_info *info) { mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode); } /* * We're in laptop mode and we've just synced. The sync's writes will have * caused another writeback to be scheduled by laptop_io_completion. * Nothing needs to be written back anymore, so we unschedule the writeback. */ void laptop_sync_completion(void) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) timer_delete(&bdi->laptop_mode_wb_timer); rcu_read_unlock(); } /* * If ratelimit_pages is too high then we can get into dirty-data overload * if a large number of processes all perform writes at the same time. * * Here we set ratelimit_pages to a level which ensures that when all CPUs are * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory * thresholds. */ void writeback_set_ratelimit(void) { struct wb_domain *dom = &global_wb_domain; unsigned long background_thresh; unsigned long dirty_thresh; global_dirty_limits(&background_thresh, &dirty_thresh); dom->dirty_limit = dirty_thresh; ratelimit_pages = dirty_thresh / (num_online_cpus() * 32); if (ratelimit_pages < 16) ratelimit_pages = 16; } static int page_writeback_cpu_online(unsigned int cpu) { writeback_set_ratelimit(); return 0; } #ifdef CONFIG_SYSCTL /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE; static const struct ctl_table vm_page_writeback_sysctls[] = { { .procname = "dirty_background_ratio", .data = &dirty_background_ratio, .maxlen = sizeof(dirty_background_ratio), .mode = 0644, .proc_handler = dirty_background_ratio_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_background_bytes", .data = &dirty_background_bytes, .maxlen = sizeof(dirty_background_bytes), .mode = 0644, .proc_handler = dirty_background_bytes_handler, .extra1 = SYSCTL_LONG_ONE, }, { .procname = "dirty_ratio", .data = &vm_dirty_ratio, .maxlen = sizeof(vm_dirty_ratio), .mode = 0644, .proc_handler = dirty_ratio_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_bytes", .data = &vm_dirty_bytes, .maxlen = sizeof(vm_dirty_bytes), .mode = 0644, .proc_handler = dirty_bytes_handler, .extra1 = (void *)&dirty_bytes_min, }, { .procname = "dirty_writeback_centisecs", .data = &dirty_writeback_interval, .maxlen = sizeof(dirty_writeback_interval), .mode = 0644, .proc_handler = dirty_writeback_centisecs_handler, }, { .procname = "dirty_expire_centisecs", .data = &dirty_expire_interval, .maxlen = sizeof(dirty_expire_interval), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, }, #ifdef CONFIG_HIGHMEM { .procname = "highmem_is_dirtyable", .data = &vm_highmem_is_dirtyable, .maxlen = sizeof(vm_highmem_is_dirtyable), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif { .procname = "laptop_mode", .data = &laptop_mode, .maxlen = sizeof(laptop_mode), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, }; #endif /* * Called early on to tune the page writeback dirty limits. * * We used to scale dirty pages according to how total memory * related to pages that could be allocated for buffers. * * However, that was when we used "dirty_ratio" to scale with * all memory, and we don't do that any more. "dirty_ratio" * is now applied to total non-HIGHPAGE memory, and as such we can't * get into the old insane situation any more where we had * large amounts of dirty pages compared to a small amount of * non-HIGHMEM memory. * * But we might still want to scale the dirty_ratio by how * much memory the box has.. */ void __init page_writeback_init(void) { BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL)); cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/writeback:online", page_writeback_cpu_online, NULL); cpuhp_setup_state(CPUHP_MM_WRITEBACK_DEAD, "mm/writeback:dead", NULL, page_writeback_cpu_online); #ifdef CONFIG_SYSCTL register_sysctl_init("vm", vm_page_writeback_sysctls); #endif } /** * tag_pages_for_writeback - tag pages to be written by writeback * @mapping: address space structure to write * @start: starting page index * @end: ending page index (inclusive) * * This function scans the page range from @start to @end (inclusive) and tags * all pages that have DIRTY tag set with a special TOWRITE tag. The caller * can then use the TOWRITE tag to identify pages eligible for writeback. * This mechanism is used to avoid livelocking of writeback by a process * steadily creating new dirty pages in the file (thus it is important for this * function to be quick so that it can tag pages faster than a dirtying process * can create them). */ void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end) { XA_STATE(xas, &mapping->i_pages, start); unsigned int tagged = 0; void *page; xas_lock_irq(&xas); xas_for_each_marked(&xas, page, end, PAGECACHE_TAG_DIRTY) { xas_set_mark(&xas, PAGECACHE_TAG_TOWRITE); if (++tagged % XA_CHECK_SCHED) continue; xas_pause(&xas); xas_unlock_irq(&xas); cond_resched(); xas_lock_irq(&xas); } xas_unlock_irq(&xas); } EXPORT_SYMBOL(tag_pages_for_writeback); static bool folio_prepare_writeback(struct address_space *mapping, struct writeback_control *wbc, struct folio *folio) { /* * Folio truncated or invalidated. We can freely skip it then, * even for data integrity operations: the folio has disappeared * concurrently, so there could be no real expectation of this * data integrity operation even if there is now a new, dirty * folio at the same pagecache index. */ if (unlikely(folio->mapping != mapping)) return false; /* * Did somebody else write it for us? */ if (!folio_test_dirty(folio)) return false; if (folio_test_writeback(folio)) { if (wbc->sync_mode == WB_SYNC_NONE) return false; folio_wait_writeback(folio); } BUG_ON(folio_test_writeback(folio)); if (!folio_clear_dirty_for_io(folio)) return false; return true; } static xa_mark_t wbc_to_tag(struct writeback_control *wbc) { if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) return PAGECACHE_TAG_TOWRITE; return PAGECACHE_TAG_DIRTY; } static pgoff_t wbc_end(struct writeback_control *wbc) { if (wbc->range_cyclic) return -1; return wbc->range_end >> PAGE_SHIFT; } static struct folio *writeback_get_folio(struct address_space *mapping, struct writeback_control *wbc) { struct folio *folio; retry: folio = folio_batch_next(&wbc->fbatch); if (!folio) { folio_batch_release(&wbc->fbatch); cond_resched(); filemap_get_folios_tag(mapping, &wbc->index, wbc_end(wbc), wbc_to_tag(wbc), &wbc->fbatch); folio = folio_batch_next(&wbc->fbatch); if (!folio) return NULL; } folio_lock(folio); if (unlikely(!folio_prepare_writeback(mapping, wbc, folio))) { folio_unlock(folio); goto retry; } trace_wbc_writepage(wbc, inode_to_bdi(mapping->host)); return folio; } /** * writeback_iter - iterate folio of a mapping for writeback * @mapping: address space structure to write * @wbc: writeback context * @folio: previously iterated folio (%NULL to start) * @error: in-out pointer for writeback errors (see below) * * This function returns the next folio for the writeback operation described by * @wbc on @mapping and should be called in a while loop in the ->writepages * implementation. * * To start the writeback operation, %NULL is passed in the @folio argument, and * for every subsequent iteration the folio returned previously should be passed * back in. * * If there was an error in the per-folio writeback inside the writeback_iter() * loop, @error should be set to the error value. * * Once the writeback described in @wbc has finished, this function will return * %NULL and if there was an error in any iteration restore it to @error. * * Note: callers should not manually break out of the loop using break or goto * but must keep calling writeback_iter() until it returns %NULL. * * Return: the folio to write or %NULL if the loop is done. */ struct folio *writeback_iter(struct address_space *mapping, struct writeback_control *wbc, struct folio *folio, int *error) { if (!folio) { folio_batch_init(&wbc->fbatch); wbc->saved_err = *error = 0; /* * For range cyclic writeback we remember where we stopped so * that we can continue where we stopped. * * For non-cyclic writeback we always start at the beginning of * the passed in range. */ if (wbc->range_cyclic) wbc->index = mapping->writeback_index; else wbc->index = wbc->range_start >> PAGE_SHIFT; /* * To avoid livelocks when other processes dirty new pages, we * first tag pages which should be written back and only then * start writing them. * * For data-integrity writeback we have to be careful so that we * do not miss some pages (e.g., because some other process has * cleared the TOWRITE tag we set). The rule we follow is that * TOWRITE tag can be cleared only by the process clearing the * DIRTY tag (and submitting the page for I/O). */ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag_pages_for_writeback(mapping, wbc->index, wbc_end(wbc)); } else { wbc->nr_to_write -= folio_nr_pages(folio); WARN_ON_ONCE(*error > 0); /* * For integrity writeback we have to keep going until we have * written all the folios we tagged for writeback above, even if * we run past wbc->nr_to_write or encounter errors. * We stash away the first error we encounter in wbc->saved_err * so that it can be retrieved when we're done. This is because * the file system may still have state to clear for each folio. * * For background writeback we exit as soon as we run past * wbc->nr_to_write or encounter the first error. */ if (wbc->sync_mode == WB_SYNC_ALL) { if (*error && !wbc->saved_err) wbc->saved_err = *error; } else { if (*error || wbc->nr_to_write <= 0) goto done; } } folio = writeback_get_folio(mapping, wbc); if (!folio) { /* * To avoid deadlocks between range_cyclic writeback and callers * that hold folios in writeback to aggregate I/O until * the writeback iteration finishes, we do not loop back to the * start of the file. Doing so causes a folio lock/folio * writeback access order inversion - we should only ever lock * multiple folios in ascending folio->index order, and looping * back to the start of the file violates that rule and causes * deadlocks. */ if (wbc->range_cyclic) mapping->writeback_index = 0; /* * Return the first error we encountered (if there was any) to * the caller. */ *error = wbc->saved_err; } return folio; done: if (wbc->range_cyclic) mapping->writeback_index = folio_next_index(folio); folio_batch_release(&wbc->fbatch); return NULL; } EXPORT_SYMBOL_GPL(writeback_iter); /** * write_cache_pages - walk the list of dirty pages of the given address space and write all of them. * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * @writepage: function called for each page * @data: data passed to writepage function * * Return: %0 on success, negative error code otherwise * * Note: please use writeback_iter() instead. */ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data) { struct folio *folio = NULL; int error; while ((folio = writeback_iter(mapping, wbc, folio, &error))) { error = writepage(folio, wbc, data); if (error == AOP_WRITEPAGE_ACTIVATE) { folio_unlock(folio); error = 0; } } return error; } EXPORT_SYMBOL(write_cache_pages); int do_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret; struct bdi_writeback *wb; if (wbc->nr_to_write <= 0) return 0; wb = inode_to_wb_wbc(mapping->host, wbc); wb_bandwidth_estimate_start(wb); while (1) { if (mapping->a_ops->writepages) ret = mapping->a_ops->writepages(mapping, wbc); else /* deal with chardevs and other special files */ ret = 0; if (ret != -ENOMEM || wbc->sync_mode != WB_SYNC_ALL) break; /* * Lacking an allocation context or the locality or writeback * state of any of the inode's pages, throttle based on * writeback activity on the local node. It's as good a * guess as any. */ reclaim_throttle(NODE_DATA(numa_node_id()), VMSCAN_THROTTLE_WRITEBACK); } /* * Usually few pages are written by now from those we've just submitted * but if there's constant writeback being submitted, this makes sure * writeback bandwidth is updated once in a while. */ if (time_is_before_jiffies(READ_ONCE(wb->bw_time_stamp) + BANDWIDTH_INTERVAL)) wb_update_bandwidth(wb); return ret; } /* * For address_spaces which do not use buffers nor write back. */ bool noop_dirty_folio(struct address_space *mapping, struct folio *folio) { if (!folio_test_dirty(folio)) return !folio_test_set_dirty(folio); return false; } EXPORT_SYMBOL(noop_dirty_folio); /* * Helper function for set_page_dirty family. * * NOTE: This relies on being atomic wrt interrupts. */ static void folio_account_dirtied(struct folio *folio, struct address_space *mapping) { struct inode *inode = mapping->host; trace_writeback_dirty_folio(folio, mapping); if (mapping_can_writeback(mapping)) { struct bdi_writeback *wb; long nr = folio_nr_pages(folio); inode_attach_wb(inode, folio); wb = inode_to_wb(inode); __lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, nr); __zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); __node_stat_mod_folio(folio, NR_DIRTIED, nr); wb_stat_mod(wb, WB_RECLAIMABLE, nr); wb_stat_mod(wb, WB_DIRTIED, nr); task_io_account_write(nr * PAGE_SIZE); current->nr_dirtied += nr; __this_cpu_add(bdp_ratelimits, nr); mem_cgroup_track_foreign_dirty(folio, wb); } } /* * Helper function for deaccounting dirty page without writeback. * */ void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb) { long nr = folio_nr_pages(folio); lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); wb_stat_mod(wb, WB_RECLAIMABLE, -nr); task_io_account_cancelled_write(nr * PAGE_SIZE); } /* * Mark the folio dirty, and set it dirty in the page cache. * * If warn is true, then emit a warning if the folio is not uptodate and has * not been truncated. * * It is the caller's responsibility to prevent the folio from being truncated * while this function is in progress, although it may have been truncated * before this function is called. Most callers have the folio locked. * A few have the folio blocked from truncation through other means (e.g. * zap_vma_pages() has it mapped and is holding the page table lock). * When called from mark_buffer_dirty(), the filesystem should hold a * reference to the buffer_head that is being marked dirty, which causes * try_to_free_buffers() to fail. */ void __folio_mark_dirty(struct folio *folio, struct address_space *mapping, int warn) { unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); if (folio->mapping) { /* Race with truncate? */ WARN_ON_ONCE(warn && !folio_test_uptodate(folio)); folio_account_dirtied(folio, mapping); __xa_set_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_DIRTY); } xa_unlock_irqrestore(&mapping->i_pages, flags); } /** * filemap_dirty_folio - Mark a folio dirty for filesystems which do not use buffer_heads. * @mapping: Address space this folio belongs to. * @folio: Folio to be marked as dirty. * * Filesystems which do not use buffer heads should call this function * from their dirty_folio address space operation. It ignores the * contents of folio_get_private(), so if the filesystem marks individual * blocks as dirty, the filesystem should handle that itself. * * This is also sometimes used by filesystems which use buffer_heads when * a single buffer is being dirtied: we want to set the folio dirty in * that case, but not all the buffers. This is a "bottom-up" dirtying, * whereas block_dirty_folio() is a "top-down" dirtying. * * The caller must ensure this doesn't race with truncation. Most will * simply hold the folio lock, but e.g. zap_pte_range() calls with the * folio mapped and the pte lock held, which also locks out truncation. */ bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio) { if (folio_test_set_dirty(folio)) return false; __folio_mark_dirty(folio, mapping, !folio_test_private(folio)); if (mapping->host) { /* !PageAnon && !swapper_space */ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } return true; } EXPORT_SYMBOL(filemap_dirty_folio); /** * folio_redirty_for_writepage - Decline to write a dirty folio. * @wbc: The writeback control. * @folio: The folio. * * When a writepage implementation decides that it doesn't want to write * @folio for some reason, it should call this function, unlock @folio and * return 0. * * Return: True if we redirtied the folio. False if someone else dirtied * it first. */ bool folio_redirty_for_writepage(struct writeback_control *wbc, struct folio *folio) { struct address_space *mapping = folio->mapping; long nr = folio_nr_pages(folio); bool ret; wbc->pages_skipped += nr; ret = filemap_dirty_folio(mapping, folio); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; wb = unlocked_inode_to_wb_begin(inode, &cookie); current->nr_dirtied -= nr; node_stat_mod_folio(folio, NR_DIRTIED, -nr); wb_stat_mod(wb, WB_DIRTIED, -nr); unlocked_inode_to_wb_end(inode, &cookie); } return ret; } EXPORT_SYMBOL(folio_redirty_for_writepage); /** * folio_mark_dirty - Mark a folio as being modified. * @folio: The folio. * * The folio may not be truncated while this function is running. * Holding the folio lock is sufficient to prevent truncation, but some * callers cannot acquire a sleeping lock. These callers instead hold * the page table lock for a page table which contains at least one page * in this folio. Truncation will block on the page table lock as it * unmaps pages before removing the folio from its mapping. * * Return: True if the folio was newly dirtied, false if it was already dirty. */ bool folio_mark_dirty(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (likely(mapping)) { /* * readahead/folio_deactivate could remain * PG_readahead/PG_reclaim due to race with folio_end_writeback * About readahead, if the folio is written, the flags would be * reset. So no problem. * About folio_deactivate, if the folio is redirtied, * the flag will be reset. So no problem. but if the * folio is used by readahead it will confuse readahead * and make it restart the size rampup process. But it's * a trivial problem. */ if (folio_test_reclaim(folio)) folio_clear_reclaim(folio); return mapping->a_ops->dirty_folio(mapping, folio); } return noop_dirty_folio(mapping, folio); } EXPORT_SYMBOL(folio_mark_dirty); /* * folio_mark_dirty() is racy if the caller has no reference against * folio->mapping->host, and if the folio is unlocked. This is because another * CPU could truncate the folio off the mapping and then free the mapping. * * Usually, the folio _is_ locked, or the caller is a user-space process which * holds a reference on the inode by having an open file. * * In other cases, the folio should be locked before running folio_mark_dirty(). */ bool folio_mark_dirty_lock(struct folio *folio) { bool ret; folio_lock(folio); ret = folio_mark_dirty(folio); folio_unlock(folio); return ret; } EXPORT_SYMBOL(folio_mark_dirty_lock); /* * This cancels just the dirty bit on the kernel page itself, it does NOT * actually remove dirty bits on any mmap's that may be around. It also * leaves the page tagged dirty, so any sync activity will still find it on * the dirty lists, and in particular, clear_page_dirty_for_io() will still * look at the dirty bits in the VM. * * Doing this should *normally* only ever be done when a page is truncated, * and is not actually mapped anywhere at all. However, fs/buffer.c does * this when it notices that somebody has cleaned out all the buffers on a * page without actually doing it through the VM. Can you say "ext3 is * horribly ugly"? Thought you could. */ void __folio_cancel_dirty(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; wb = unlocked_inode_to_wb_begin(inode, &cookie); if (folio_test_clear_dirty(folio)) folio_account_cleaned(folio, wb); unlocked_inode_to_wb_end(inode, &cookie); } else { folio_clear_dirty(folio); } } EXPORT_SYMBOL(__folio_cancel_dirty); /* * Clear a folio's dirty flag, while caring for dirty memory accounting. * Returns true if the folio was previously dirty. * * This is for preparing to put the folio under writeout. We leave * the folio tagged as dirty in the xarray so that a concurrent * write-for-sync can discover it via a PAGECACHE_TAG_DIRTY walk. * The ->writepage implementation will run either folio_start_writeback() * or folio_mark_dirty(), at which stage we bring the folio's dirty flag * and xarray dirty tag back into sync. * * This incoherency between the folio's dirty flag and xarray tag is * unfortunate, but it only exists while the folio is locked. */ bool folio_clear_dirty_for_io(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); bool ret = false; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; /* * Yes, Virginia, this is indeed insane. * * We use this sequence to make sure that * (a) we account for dirty stats properly * (b) we tell the low-level filesystem to * mark the whole folio dirty if it was * dirty in a pagetable. Only to then * (c) clean the folio again and return 1 to * cause the writeback. * * This way we avoid all nasty races with the * dirty bit in multiple places and clearing * them concurrently from different threads. * * Note! Normally the "folio_mark_dirty(folio)" * has no effect on the actual dirty bit - since * that will already usually be set. But we * need the side effects, and it can help us * avoid races. * * We basically use the folio "master dirty bit" * as a serialization point for all the different * threads doing their things. */ if (folio_mkclean(folio)) folio_mark_dirty(folio); /* * We carefully synchronise fault handlers against * installing a dirty pte and marking the folio dirty * at this point. We do this by having them hold the * page lock while dirtying the folio, and folios are * always locked coming in here, so we get the desired * exclusion. */ wb = unlocked_inode_to_wb_begin(inode, &cookie); if (folio_test_clear_dirty(folio)) { long nr = folio_nr_pages(folio); lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); wb_stat_mod(wb, WB_RECLAIMABLE, -nr); ret = true; } unlocked_inode_to_wb_end(inode, &cookie); return ret; } return folio_test_clear_dirty(folio); } EXPORT_SYMBOL(folio_clear_dirty_for_io); static void wb_inode_writeback_start(struct bdi_writeback *wb) { atomic_inc(&wb->writeback_inodes); } static void wb_inode_writeback_end(struct bdi_writeback *wb) { unsigned long flags; atomic_dec(&wb->writeback_inodes); /* * Make sure estimate of writeback throughput gets updated after * writeback completed. We delay the update by BANDWIDTH_INTERVAL * (which is the interval other bandwidth updates use for batching) so * that if multiple inodes end writeback at a similar time, they get * batched into one bandwidth update. */ spin_lock_irqsave(&wb->work_lock, flags); if (test_bit(WB_registered, &wb->state)) queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL); spin_unlock_irqrestore(&wb->work_lock, flags); } bool __folio_end_writeback(struct folio *folio) { long nr = folio_nr_pages(folio); struct address_space *mapping = folio_mapping(folio); bool ret; if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback); __xa_clear_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); wb_stat_mod(wb, WB_WRITEBACK, -nr); __wb_writeout_add(wb, nr); if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) wb_inode_writeback_end(wb); } if (mapping->host && !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) sb_clear_inode_writeback(mapping->host); xa_unlock_irqrestore(&mapping->i_pages, flags); } else { ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback); } lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); node_stat_mod_folio(folio, NR_WRITTEN, nr); return ret; } void __folio_start_writeback(struct folio *folio, bool keep_write) { long nr = folio_nr_pages(folio); struct address_space *mapping = folio_mapping(folio); int access_ret; VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (mapping && mapping_use_writeback_tags(mapping)) { XA_STATE(xas, &mapping->i_pages, folio_index(folio)); struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; bool on_wblist; xas_lock_irqsave(&xas, flags); xas_load(&xas); folio_test_set_writeback(folio); on_wblist = mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); wb_stat_mod(wb, WB_WRITEBACK, nr); if (!on_wblist) wb_inode_writeback_start(wb); } /* * We can come through here when swapping anonymous * folios, so we don't necessarily have an inode to * track for sync. */ if (mapping->host && !on_wblist) sb_mark_inode_writeback(mapping->host); if (!folio_test_dirty(folio)) xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); if (!keep_write) xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irqrestore(&xas, flags); } else { folio_test_set_writeback(folio); } lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr); zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); access_ret = arch_make_folio_accessible(folio); /* * If writeback has been triggered on a page that cannot be made * accessible, it is too late to recover here. */ VM_BUG_ON_FOLIO(access_ret != 0, folio); } EXPORT_SYMBOL(__folio_start_writeback); /** * folio_wait_writeback - Wait for a folio to finish writeback. * @folio: The folio to wait for. * * If the folio is currently being written back to storage, wait for the * I/O to complete. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. */ void folio_wait_writeback(struct folio *folio) { while (folio_test_writeback(folio)) { trace_folio_wait_writeback(folio, folio_mapping(folio)); folio_wait_bit(folio, PG_writeback); } } EXPORT_SYMBOL_GPL(folio_wait_writeback); /** * folio_wait_writeback_killable - Wait for a folio to finish writeback. * @folio: The folio to wait for. * * If the folio is currently being written back to storage, wait for the * I/O to complete or a fatal signal to arrive. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. * Return: 0 on success, -EINTR if we get a fatal signal while waiting. */ int folio_wait_writeback_killable(struct folio *folio) { while (folio_test_writeback(folio)) { trace_folio_wait_writeback(folio, folio_mapping(folio)); if (folio_wait_bit_killable(folio, PG_writeback)) return -EINTR; } return 0; } EXPORT_SYMBOL_GPL(folio_wait_writeback_killable); /** * folio_wait_stable() - wait for writeback to finish, if necessary. * @folio: The folio to wait on. * * This function determines if the given folio is related to a backing * device that requires folio contents to be held stable during writeback. * If so, then it will wait for any pending writeback to complete. * * Context: Sleeps. Must be called in process context and with * no spinlocks held. Caller should hold a reference on the folio. * If the folio is not locked, writeback may start again after writeback * has finished. */ void folio_wait_stable(struct folio *folio) { if (mapping_stable_writes(folio_mapping(folio))) folio_wait_writeback(folio); } EXPORT_SYMBOL_GPL(folio_wait_stable); |
| 2 2 2 2 2 2 2 2 1 1 1 1 1 2 2 2 2 2 1 1 1 1 4 7 4 3 4 45 45 45 45 45 3 3 3 3 3 3 3 3 3 3 3 3 3 3 15 15 14 15 15 15 15 15 15 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 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 | /* * 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/ethtool_netlink.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <net/netdev_queues.h> #include <net/netdev_rx_queue.h> #include <net/page_pool/helpers.h> #include <net/netlink.h> #include <net/net_shaper.h> #include <net/netdev_lock.h> #include <net/pkt_cls.h> #include <net/rtnetlink.h> #include <net/udp_tunnel.h> #include <net/busy_poll.h> #include "netdevsim.h" MODULE_IMPORT_NS("NETDEV_INTERNAL"); #define NSIM_RING_SIZE 256 static void nsim_start_peer_tx_queue(struct net_device *dev, struct nsim_rq *rq) { struct netdevsim *ns = netdev_priv(dev); struct net_device *peer_dev; struct netdevsim *peer_ns; struct netdev_queue *txq; u16 idx; idx = rq->napi.index; rcu_read_lock(); peer_ns = rcu_dereference(ns->peer); if (!peer_ns) goto out; /* TX device */ peer_dev = peer_ns->netdev; if (dev->real_num_tx_queues != peer_dev->num_rx_queues) goto out; txq = netdev_get_tx_queue(peer_dev, idx); if (!netif_tx_queue_stopped(txq)) goto out; netif_tx_wake_queue(txq); out: rcu_read_unlock(); } static void nsim_stop_tx_queue(struct net_device *tx_dev, struct net_device *rx_dev, struct nsim_rq *rq, u16 idx) { /* If different queues size, do not stop, since it is not * easy to find which TX queue is mapped here */ if (rx_dev->real_num_tx_queues != tx_dev->num_rx_queues) return; /* rq is the queue on the receive side */ netif_subqueue_try_stop(tx_dev, idx, NSIM_RING_SIZE - skb_queue_len(&rq->skb_queue), NSIM_RING_SIZE / 2); } static int nsim_napi_rx(struct net_device *tx_dev, struct net_device *rx_dev, 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); /* Stop the peer TX queue avoiding dropping packets later */ if (skb_queue_len(&rq->skb_queue) >= NSIM_RING_SIZE) nsim_stop_tx_queue(tx_dev, rx_dev, rq, skb_get_queue_mapping(skb)); return NET_RX_SUCCESS; } static int nsim_forward_skb(struct net_device *tx_dev, struct net_device *rx_dev, struct sk_buff *skb, struct nsim_rq *rq) { return __dev_forward_skb(rx_dev, skb) ?: nsim_napi_rx(tx_dev, rx_dev, 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 netdev_config *cfg; 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]; cfg = peer_dev->cfg; if (skb_is_nonlinear(skb) && (cfg->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED || (cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED && cfg->hds_thresh > len))) skb_linearize(skb); skb_tx_timestamp(skb); if (unlikely(nsim_forward_skb(dev, peer_dev, skb, rq) == NET_RX_DROP)) goto out_drop_cnt; if (!hrtimer_active(&rq->napi_timer)) hrtimer_start(&rq->napi_timer, us_to_ktime(5), HRTIMER_MODE_REL); rcu_read_unlock(); dev_dstats_tx_add(dev, len); return NETDEV_TX_OK; out_drop_free: dev_kfree_skb(skb); out_drop_cnt: rcu_read_unlock(); dev_dstats_tx_dropped(dev); 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 && !ns->xdp.prog->aux->xdp_has_frags && new_mtu > NSIM_XDP_MAX_MTU) return -EBUSY; WRITE_ONCE(dev->mtu, new_mtu); return 0; } 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 net_device *dev = rq->napi.dev; struct bpf_prog *xdp_prog; struct netdevsim *ns; struct sk_buff *skb; unsigned int skblen; int i, ret; ns = netdev_priv(dev); xdp_prog = READ_ONCE(ns->xdp.prog); for (i = 0; i < budget; i++) { if (skb_queue_empty(&rq->skb_queue)) break; skb = skb_dequeue(&rq->skb_queue); if (xdp_prog) { /* skb might be freed directly by XDP, save the len */ skblen = skb->len; if (skb->ip_summed == CHECKSUM_PARTIAL) skb_checksum_help(skb); ret = do_xdp_generic(xdp_prog, &skb); if (ret != XDP_PASS) { dev_dstats_rx_add(dev, skblen); continue; } } /* skb might be discard at netif_receive_skb, save the len */ skblen = skb->len; skb_mark_napi_id(skb, &rq->napi); ret = netif_receive_skb(skb); if (ret == NET_RX_SUCCESS) dev_dstats_rx_add(dev, skblen); else dev_dstats_rx_dropped(dev); } nsim_start_peer_tx_queue(dev, rq); 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); if (done < budget) napi_complete_done(napi, done); return done; } static int nsim_create_page_pool(struct page_pool **p, struct napi_struct *napi) { struct page_pool_params params = { .order = 0, .pool_size = NSIM_RING_SIZE, .nid = NUMA_NO_NODE, .dev = &napi->dev->dev, .napi = napi, .dma_dir = DMA_BIDIRECTIONAL, .netdev = napi->dev, }; struct page_pool *pool; pool = page_pool_create(¶ms); if (IS_ERR(pool)) return PTR_ERR(pool); *p = pool; 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_config_locked(dev, &rq->napi, nsim_poll, i); } for (i = 0; i < dev->num_rx_queues; i++) { rq = ns->rq[i]; err = nsim_create_page_pool(&rq->page_pool, &rq->napi); 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_locked(&ns->rq[i]->napi); return err; } static enum hrtimer_restart nsim_napi_schedule(struct hrtimer *timer) { struct nsim_rq *rq; rq = container_of(timer, struct nsim_rq, napi_timer); napi_schedule(&rq->napi); return HRTIMER_NORESTART; } static void nsim_rq_timer_init(struct nsim_rq *rq) { hrtimer_setup(&rq->napi_timer, nsim_napi_schedule, CLOCK_MONOTONIC, HRTIMER_MODE_REL); } 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_locked(&rq->napi); } } static int nsim_open(struct net_device *dev) { struct netdevsim *ns = netdev_priv(dev); int err; netdev_assert_locked(dev); 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_locked(&rq->napi); __netif_napi_del_locked(&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; netdev_assert_locked(dev); 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_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_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) dev_get_stats(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) dev_get_stats(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 = {}; dev_get_stats(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 struct nsim_rq *nsim_queue_alloc(void) { struct nsim_rq *rq; rq = kzalloc(sizeof(*rq), GFP_KERNEL_ACCOUNT); if (!rq) return NULL; skb_queue_head_init(&rq->skb_queue); nsim_rq_timer_init(rq); return rq; } static void nsim_queue_free(struct net_device *dev, struct nsim_rq *rq) { hrtimer_cancel(&rq->napi_timer); local_bh_disable(); dev_dstats_rx_dropped_add(dev, rq->skb_queue.qlen); local_bh_enable(); skb_queue_purge_reason(&rq->skb_queue, SKB_DROP_REASON_QUEUE_PURGE); kfree(rq); } /* Queue reset mode is controlled by ns->rq_reset_mode. * - normal - new NAPI new pool (old NAPI enabled when new added) * - mode 1 - allocate new pool (NAPI is only disabled / enabled) * - mode 2 - new NAPI new pool (old NAPI removed before new added) * - mode 3 - new NAPI new pool (old NAPI disabled when new added) */ struct nsim_queue_mem { struct nsim_rq *rq; struct page_pool *pp; }; static int nsim_queue_mem_alloc(struct net_device *dev, void *per_queue_mem, int idx) { struct nsim_queue_mem *qmem = per_queue_mem; struct netdevsim *ns = netdev_priv(dev); int err; if (ns->rq_reset_mode > 3) return -EINVAL; if (ns->rq_reset_mode == 1) { if (!netif_running(ns->netdev)) return -ENETDOWN; return nsim_create_page_pool(&qmem->pp, &ns->rq[idx]->napi); } qmem->rq = nsim_queue_alloc(); if (!qmem->rq) return -ENOMEM; err = nsim_create_page_pool(&qmem->rq->page_pool, &qmem->rq->napi); if (err) goto err_free; if (!ns->rq_reset_mode) netif_napi_add_config_locked(dev, &qmem->rq->napi, nsim_poll, idx); return 0; err_free: nsim_queue_free(dev, qmem->rq); return err; } static void nsim_queue_mem_free(struct net_device *dev, void *per_queue_mem) { struct nsim_queue_mem *qmem = per_queue_mem; struct netdevsim *ns = netdev_priv(dev); page_pool_destroy(qmem->pp); if (qmem->rq) { if (!ns->rq_reset_mode) netif_napi_del_locked(&qmem->rq->napi); page_pool_destroy(qmem->rq->page_pool); nsim_queue_free(dev, qmem->rq); } } static int nsim_queue_start(struct net_device *dev, void *per_queue_mem, int idx) { struct nsim_queue_mem *qmem = per_queue_mem; struct netdevsim *ns = netdev_priv(dev); netdev_assert_locked(dev); if (ns->rq_reset_mode == 1) { ns->rq[idx]->page_pool = qmem->pp; napi_enable_locked(&ns->rq[idx]->napi); return 0; } /* netif_napi_add()/_del() should normally be called from alloc/free, * here we want to test various call orders. */ if (ns->rq_reset_mode == 2) { netif_napi_del_locked(&ns->rq[idx]->napi); netif_napi_add_config_locked(dev, &qmem->rq->napi, nsim_poll, idx); } else if (ns->rq_reset_mode == 3) { netif_napi_add_config_locked(dev, &qmem->rq->napi, nsim_poll, idx); netif_napi_del_locked(&ns->rq[idx]->napi); } ns->rq[idx] = qmem->rq; napi_enable_locked(&ns->rq[idx]->napi); return 0; } static int nsim_queue_stop(struct net_device *dev, void *per_queue_mem, int idx) { struct nsim_queue_mem *qmem = per_queue_mem; struct netdevsim *ns = netdev_priv(dev); netdev_assert_locked(dev); napi_disable_locked(&ns->rq[idx]->napi); if (ns->rq_reset_mode == 1) { qmem->pp = ns->rq[idx]->page_pool; page_pool_disable_direct_recycling(qmem->pp); } else { qmem->rq = ns->rq[idx]; } return 0; } static const struct netdev_queue_mgmt_ops nsim_queue_mgmt_ops = { .ndo_queue_mem_size = sizeof(struct nsim_queue_mem), .ndo_queue_mem_alloc = nsim_queue_mem_alloc, .ndo_queue_mem_free = nsim_queue_mem_free, .ndo_queue_start = nsim_queue_start, .ndo_queue_stop = nsim_queue_stop, }; static ssize_t nsim_qreset_write(struct file *file, const char __user *data, size_t count, loff_t *ppos) { struct netdevsim *ns = file->private_data; unsigned int queue, mode; char buf[32]; ssize_t ret; if (count >= sizeof(buf)) return -EINVAL; if (copy_from_user(buf, data, count)) return -EFAULT; buf[count] = '\0'; ret = sscanf(buf, "%u %u", &queue, &mode); if (ret != 2) return -EINVAL; netdev_lock(ns->netdev); if (queue >= ns->netdev->real_num_rx_queues) { ret = -EINVAL; goto exit_unlock; } ns->rq_reset_mode = mode; ret = netdev_rx_queue_restart(ns->netdev, queue); ns->rq_reset_mode = 0; if (ret) goto exit_unlock; ret = count; exit_unlock: netdev_unlock(ns->netdev); return ret; } static const struct file_operations nsim_qreset_fops = { .open = simple_open, .write = nsim_qreset_write, .owner = THIS_MODULE, }; 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(pp_page_to_nmdesc(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->flags &= ~IFF_MULTICAST; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; dev->features |= NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | NETIF_F_LRO | NETIF_F_TSO; dev->hw_features |= NETIF_F_HW_TC | NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | NETIF_F_LRO | NETIF_F_TSO; dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; dev->max_mtu = ETH_MAX_MTU; dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_HW_OFFLOAD; } static int nsim_queue_init(struct netdevsim *ns) { struct net_device *dev = ns->netdev; int i; ns->rq = kcalloc(dev->num_rx_queues, sizeof(*ns->rq), GFP_KERNEL_ACCOUNT); if (!ns->rq) return -ENOMEM; for (i = 0; i < dev->num_rx_queues; i++) { ns->rq[i] = nsim_queue_alloc(); if (!ns->rq[i]) goto err_free_prev; } return 0; err_free_prev: while (i--) kfree(ns->rq[i]); kfree(ns->rq); return -ENOMEM; } static void nsim_queue_uninit(struct netdevsim *ns) { struct net_device *dev = ns->netdev; int i; for (i = 0; i < dev->num_rx_queues; i++) nsim_queue_free(dev, ns->rq[i]); kfree(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; ns->netdev->queue_mgmt_ops = &nsim_queue_mgmt_ops; netdev_lockdep_set_classes(ns->netdev); 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(); if (IS_ENABLED(CONFIG_DEBUG_NET)) { ns->nb.notifier_call = netdev_debug_event; if (register_netdevice_notifier_dev_net(ns->netdev, &ns->nb, &ns->nn)) ns->nb.notifier_call = NULL; } return 0; err_ipsec_teardown: nsim_ipsec_teardown(ns); nsim_macsec_teardown(ns); nsim_bpf_uninit(ns); err_rq_destroy: nsim_queue_uninit(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, u8 perm_addr[ETH_ALEN]) { 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); if (perm_addr) memcpy(dev->perm_addr, perm_addr, ETH_ALEN); dev_net_set(dev, nsim_dev_net(nsim_dev)); ns = netdev_priv(dev); ns->netdev = dev; 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); ns->qr_dfs = debugfs_create_file("queue_reset", 0200, nsim_dev_port->ddir, ns, &nsim_qreset_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->qr_dfs); debugfs_remove(ns->pp_dfs); if (ns->nb.notifier_call) unregister_netdevice_notifier_dev_net(ns->netdev, &ns->nb, &ns->nn); 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_uninit(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(pp_page_to_nmdesc(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); |
| 87 95 1 2 27 27 27 26 27 27 7 27 27 27 27 1 1 1 1 1 1 87 1 1 2 2 2 2 2 2 2 2 2 18 18 18 17 17 17 17 16 7 6 6 2 7 7 7 7 7 7 7 14 13 14 13 13 13 13 13 4 4 4 1 1 25 10 4 10 10 9 10 2 9 9 9 9 9 1 9 9 9 1 1 1 1 9 9 2 10 9 10 9 10 1 10 10 10 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 2 2 2 6 6 6 6 6 2 4 2 1 1 1 1 2 2 2 2 4 2 2 2 2 2 2 17 17 17 17 6 2 2 1 16 14 11 14 14 6 1 13 13 3 3 3 3 3 1 2 3 1 2 10 10 10 10 4 4 10 10 10 10 7 10 3 10 10 10 3 3 3 9 8 3 1 1 3 1 3 3 3 5 8 8 8 9 2 9 3 7 8 3 10 8 10 27 27 2 27 27 117 119 119 119 119 4 4 4 4 4 4 1 4 1 4 4 4 4 5 5 5 5 5 1 1 1 1 1 5 5 2 2 2 2 1 1 1 2 1 1 1 2 2 4 4 1 3 5 5 5 4 5 5 4 4 5 5 5 5 1 5 5 4 4 2 4 1 1 1 5 5 4 6 6 6 6 6 6 6 6 6 6 6 6 6 3 6 2 6 6 6 4 2 6 5 3 3 3 1 5 5 5 5 6 6 6 5 6 2 2 2 1 2 6 6 5 6 4 6 6 6 19 2 17 19 2 2 2 2 1 1 18 18 18 18 17 2 18 18 18 18 18 17 18 18 2 2 2 1 18 18 18 19 4 19 19 19 16 18 4 4 4 4 18 18 18 1 17 17 17 14 14 10 9 3 3 3 3 3 14 14 13 15 5 5 5 5 5 1 3 4 4 5 5 5 5 5 4 4 4 1 1 3 3 2 4 7 7 7 7 7 7 7 6 6 4 2 5 5 6 1 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * file.c * * File open, close, extend, truncate * * Copyright (C) 2002, 2004 Oracle. All rights reserved. */ #include <linux/capability.h> #include <linux/fs.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/uio.h> #include <linux/sched.h> #include <linux/splice.h> #include <linux/mount.h> #include <linux/writeback.h> #include <linux/falloc.h> #include <linux/quotaops.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <cluster/masklog.h> #include "ocfs2.h" #include "alloc.h" #include "aops.h" #include "dir.h" #include "dlmglue.h" #include "extent_map.h" #include "file.h" #include "sysfile.h" #include "inode.h" #include "ioctl.h" #include "journal.h" #include "locks.h" #include "mmap.h" #include "suballoc.h" #include "super.h" #include "xattr.h" #include "acl.h" #include "quota.h" #include "refcounttree.h" #include "ocfs2_trace.h" #include "buffer_head_io.h" static int ocfs2_init_file_private(struct inode *inode, struct file *file) { struct ocfs2_file_private *fp; fp = kzalloc(sizeof(struct ocfs2_file_private), GFP_KERNEL); if (!fp) return -ENOMEM; fp->fp_file = file; mutex_init(&fp->fp_mutex); ocfs2_file_lock_res_init(&fp->fp_flock, fp); file->private_data = fp; return 0; } static void ocfs2_free_file_private(struct inode *inode, struct file *file) { struct ocfs2_file_private *fp = file->private_data; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); if (fp) { ocfs2_simple_drop_lockres(osb, &fp->fp_flock); ocfs2_lock_res_free(&fp->fp_flock); kfree(fp); file->private_data = NULL; } } static int ocfs2_file_open(struct inode *inode, struct file *file) { int status; int mode = file->f_flags; struct ocfs2_inode_info *oi = OCFS2_I(inode); trace_ocfs2_file_open(inode, file, file->f_path.dentry, (unsigned long long)oi->ip_blkno, file->f_path.dentry->d_name.len, file->f_path.dentry->d_name.name, mode); if (file->f_mode & FMODE_WRITE) { status = dquot_initialize(inode); if (status) goto leave; } spin_lock(&oi->ip_lock); /* Check that the inode hasn't been wiped from disk by another * node. If it hasn't then we're safe as long as we hold the * spin lock until our increment of open count. */ if (oi->ip_flags & OCFS2_INODE_DELETED) { spin_unlock(&oi->ip_lock); status = -ENOENT; goto leave; } if (mode & O_DIRECT) oi->ip_flags |= OCFS2_INODE_OPEN_DIRECT; oi->ip_open_count++; spin_unlock(&oi->ip_lock); status = ocfs2_init_file_private(inode, file); if (status) { /* * We want to set open count back if we're failing the * open. */ spin_lock(&oi->ip_lock); oi->ip_open_count--; spin_unlock(&oi->ip_lock); } file->f_mode |= FMODE_NOWAIT; leave: return status; } static int ocfs2_file_release(struct inode *inode, struct file *file) { struct ocfs2_inode_info *oi = OCFS2_I(inode); spin_lock(&oi->ip_lock); if (!--oi->ip_open_count) oi->ip_flags &= ~OCFS2_INODE_OPEN_DIRECT; trace_ocfs2_file_release(inode, file, file->f_path.dentry, oi->ip_blkno, file->f_path.dentry->d_name.len, file->f_path.dentry->d_name.name, oi->ip_open_count); spin_unlock(&oi->ip_lock); ocfs2_free_file_private(inode, file); return 0; } static int ocfs2_dir_open(struct inode *inode, struct file *file) { return ocfs2_init_file_private(inode, file); } static int ocfs2_dir_release(struct inode *inode, struct file *file) { ocfs2_free_file_private(inode, file); return 0; } static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { int err = 0; struct inode *inode = file->f_mapping->host; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_inode_info *oi = OCFS2_I(inode); journal_t *journal = osb->journal->j_journal; int ret; tid_t commit_tid; bool needs_barrier = false; trace_ocfs2_sync_file(inode, file, file->f_path.dentry, oi->ip_blkno, file->f_path.dentry->d_name.len, file->f_path.dentry->d_name.name, (unsigned long long)datasync); if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) return -EROFS; err = file_write_and_wait_range(file, start, end); if (err) return err; commit_tid = datasync ? oi->i_datasync_tid : oi->i_sync_tid; if (journal->j_flags & JBD2_BARRIER && !jbd2_trans_will_send_data_barrier(journal, commit_tid)) needs_barrier = true; err = jbd2_complete_transaction(journal, commit_tid); if (needs_barrier) { ret = blkdev_issue_flush(inode->i_sb->s_bdev); if (!err) err = ret; } if (err) mlog_errno(err); return (err < 0) ? -EIO : 0; } int ocfs2_should_update_atime(struct inode *inode, struct vfsmount *vfsmnt) { struct timespec64 now; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) return 0; if ((inode->i_flags & S_NOATIME) || ((inode->i_sb->s_flags & SB_NODIRATIME) && S_ISDIR(inode->i_mode))) return 0; /* * We can be called with no vfsmnt structure - NFSD will * sometimes do this. * * Note that our action here is different than touch_atime() - * if we can't tell whether this is a noatime mount, then we * don't know whether to trust the value of s_atime_quantum. */ if (vfsmnt == NULL) return 0; if ((vfsmnt->mnt_flags & MNT_NOATIME) || ((vfsmnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))) return 0; if (vfsmnt->mnt_flags & MNT_RELATIME) { struct timespec64 ctime = inode_get_ctime(inode); struct timespec64 atime = inode_get_atime(inode); struct timespec64 mtime = inode_get_mtime(inode); if ((timespec64_compare(&atime, &mtime) <= 0) || (timespec64_compare(&atime, &ctime) <= 0)) return 1; return 0; } now = current_time(inode); if ((now.tv_sec - inode_get_atime_sec(inode) <= osb->s_atime_quantum)) return 0; else return 1; } int ocfs2_update_inode_atime(struct inode *inode, struct buffer_head *bh) { int ret; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); handle_t *handle; struct ocfs2_dinode *di = (struct ocfs2_dinode *) bh->b_data; handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto out; } ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_commit; } /* * Don't use ocfs2_mark_inode_dirty() here as we don't always * have i_rwsem to guard against concurrent changes to other * inode fields. */ inode_set_atime_to_ts(inode, current_time(inode)); di->i_atime = cpu_to_le64(inode_get_atime_sec(inode)); di->i_atime_nsec = cpu_to_le32(inode_get_atime_nsec(inode)); ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, bh); out_commit: ocfs2_commit_trans(osb, handle); out: return ret; } int ocfs2_set_inode_size(handle_t *handle, struct inode *inode, struct buffer_head *fe_bh, u64 new_i_size) { int status; i_size_write(inode, new_i_size); inode->i_blocks = ocfs2_inode_sector_count(inode); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); status = ocfs2_mark_inode_dirty(handle, inode, fe_bh); if (status < 0) { mlog_errno(status); goto bail; } bail: return status; } int ocfs2_simple_size_update(struct inode *inode, struct buffer_head *di_bh, u64 new_i_size) { int ret; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); handle_t *handle = NULL; handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto out; } ret = ocfs2_set_inode_size(handle, inode, di_bh, new_i_size); if (ret < 0) mlog_errno(ret); ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_commit_trans(osb, handle); out: return ret; } static int ocfs2_cow_file_pos(struct inode *inode, struct buffer_head *fe_bh, u64 offset) { int status; u32 phys, cpos = offset >> OCFS2_SB(inode->i_sb)->s_clustersize_bits; unsigned int num_clusters = 0; unsigned int ext_flags = 0; /* * If the new offset is aligned to the range of the cluster, there is * no space for ocfs2_zero_range_for_truncate to fill, so no need to * CoW either. */ if ((offset & (OCFS2_SB(inode->i_sb)->s_clustersize - 1)) == 0) return 0; status = ocfs2_get_clusters(inode, cpos, &phys, &num_clusters, &ext_flags); if (status) { mlog_errno(status); goto out; } if (!(ext_flags & OCFS2_EXT_REFCOUNTED)) goto out; return ocfs2_refcount_cow(inode, fe_bh, cpos, 1, cpos+1); out: return status; } static int ocfs2_orphan_for_truncate(struct ocfs2_super *osb, struct inode *inode, struct buffer_head *fe_bh, u64 new_i_size) { int status; handle_t *handle; struct ocfs2_dinode *di; u64 cluster_bytes; /* * We need to CoW the cluster contains the offset if it is reflinked * since we will call ocfs2_zero_range_for_truncate later which will * write "0" from offset to the end of the cluster. */ status = ocfs2_cow_file_pos(inode, fe_bh, new_i_size); if (status) { mlog_errno(status); return status; } /* TODO: This needs to actually orphan the inode in this * transaction. */ handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { status = PTR_ERR(handle); mlog_errno(status); goto out; } status = ocfs2_journal_access_di(handle, INODE_CACHE(inode), fe_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto out_commit; } /* * Do this before setting i_size. */ cluster_bytes = ocfs2_align_bytes_to_clusters(inode->i_sb, new_i_size); status = ocfs2_zero_range_for_truncate(inode, handle, new_i_size, cluster_bytes); if (status) { mlog_errno(status); goto out_commit; } i_size_write(inode, new_i_size); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); di = (struct ocfs2_dinode *) fe_bh->b_data; di->i_size = cpu_to_le64(new_i_size); di->i_ctime = di->i_mtime = cpu_to_le64(inode_get_ctime_sec(inode)); di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, fe_bh); out_commit: ocfs2_commit_trans(osb, handle); out: return status; } int ocfs2_truncate_file(struct inode *inode, struct buffer_head *di_bh, u64 new_i_size) { int status = 0; struct ocfs2_dinode *fe = NULL; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); /* We trust di_bh because it comes from ocfs2_inode_lock(), which * already validated it */ fe = (struct ocfs2_dinode *) di_bh->b_data; trace_ocfs2_truncate_file((unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)le64_to_cpu(fe->i_size), (unsigned long long)new_i_size); mlog_bug_on_msg(le64_to_cpu(fe->i_size) != i_size_read(inode), "Inode %llu, inode i_size = %lld != di " "i_size = %llu, i_flags = 0x%x\n", (unsigned long long)OCFS2_I(inode)->ip_blkno, i_size_read(inode), (unsigned long long)le64_to_cpu(fe->i_size), le32_to_cpu(fe->i_flags)); if (new_i_size > le64_to_cpu(fe->i_size)) { trace_ocfs2_truncate_file_error( (unsigned long long)le64_to_cpu(fe->i_size), (unsigned long long)new_i_size); status = -EINVAL; mlog_errno(status); goto bail; } down_write(&OCFS2_I(inode)->ip_alloc_sem); ocfs2_resv_discard(&osb->osb_la_resmap, &OCFS2_I(inode)->ip_la_data_resv); /* * The inode lock forced other nodes to sync and drop their * pages, which (correctly) happens even if we have a truncate * without allocation change - ocfs2 cluster sizes can be much * greater than page size, so we have to truncate them * anyway. */ if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { unmap_mapping_range(inode->i_mapping, new_i_size + PAGE_SIZE - 1, 0, 1); truncate_inode_pages(inode->i_mapping, new_i_size); status = ocfs2_truncate_inline(inode, di_bh, new_i_size, i_size_read(inode), 1); if (status) mlog_errno(status); goto bail_unlock_sem; } /* alright, we're going to need to do a full blown alloc size * change. Orphan the inode so that recovery can complete the * truncate if necessary. This does the task of marking * i_size. */ status = ocfs2_orphan_for_truncate(osb, inode, di_bh, new_i_size); if (status < 0) { mlog_errno(status); goto bail_unlock_sem; } unmap_mapping_range(inode->i_mapping, new_i_size + PAGE_SIZE - 1, 0, 1); truncate_inode_pages(inode->i_mapping, new_i_size); status = ocfs2_commit_truncate(osb, inode, di_bh); if (status < 0) { mlog_errno(status); goto bail_unlock_sem; } /* TODO: orphan dir cleanup here. */ bail_unlock_sem: up_write(&OCFS2_I(inode)->ip_alloc_sem); bail: if (!status && OCFS2_I(inode)->ip_clusters == 0) status = ocfs2_try_remove_refcount_tree(inode, di_bh); return status; } /* * extend file allocation only here. * we'll update all the disk stuff, and oip->alloc_size * * expect stuff to be locked, a transaction started and enough data / * metadata reservations in the contexts. * * Will return -EAGAIN, and a reason if a restart is needed. * If passed in, *reason will always be set, even in error. */ int ocfs2_add_inode_data(struct ocfs2_super *osb, struct inode *inode, u32 *logical_offset, u32 clusters_to_add, int mark_unwritten, struct buffer_head *fe_bh, handle_t *handle, struct ocfs2_alloc_context *data_ac, struct ocfs2_alloc_context *meta_ac, enum ocfs2_alloc_restarted *reason_ret) { struct ocfs2_extent_tree et; ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), fe_bh); return ocfs2_add_clusters_in_btree(handle, &et, logical_offset, clusters_to_add, mark_unwritten, data_ac, meta_ac, reason_ret); } static int ocfs2_extend_allocation(struct inode *inode, u32 logical_start, u32 clusters_to_add, int mark_unwritten) { int status = 0; int restart_func = 0; int credits; u32 prev_clusters; struct buffer_head *bh = NULL; struct ocfs2_dinode *fe = NULL; handle_t *handle = NULL; struct ocfs2_alloc_context *data_ac = NULL; struct ocfs2_alloc_context *meta_ac = NULL; enum ocfs2_alloc_restarted why = RESTART_NONE; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_extent_tree et; int did_quota = 0; /* * Unwritten extent only exists for file systems which * support holes. */ BUG_ON(mark_unwritten && !ocfs2_sparse_alloc(osb)); status = ocfs2_read_inode_block(inode, &bh); if (status < 0) { mlog_errno(status); goto leave; } fe = (struct ocfs2_dinode *) bh->b_data; restart_all: BUG_ON(le32_to_cpu(fe->i_clusters) != OCFS2_I(inode)->ip_clusters); ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), bh); status = ocfs2_lock_allocators(inode, &et, clusters_to_add, 0, &data_ac, &meta_ac); if (status) { mlog_errno(status); goto leave; } credits = ocfs2_calc_extend_credits(osb->sb, &fe->id2.i_list); handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { status = PTR_ERR(handle); handle = NULL; mlog_errno(status); goto leave; } restarted_transaction: trace_ocfs2_extend_allocation( (unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)i_size_read(inode), le32_to_cpu(fe->i_clusters), clusters_to_add, why, restart_func); status = dquot_alloc_space_nodirty(inode, ocfs2_clusters_to_bytes(osb->sb, clusters_to_add)); if (status) goto leave; did_quota = 1; /* reserve a write to the file entry early on - that we if we * run out of credits in the allocation path, we can still * update i_size. */ status = ocfs2_journal_access_di(handle, INODE_CACHE(inode), bh, OCFS2_JOURNAL_ACCESS_WRITE); if (status < 0) { mlog_errno(status); goto leave; } prev_clusters = OCFS2_I(inode)->ip_clusters; status = ocfs2_add_inode_data(osb, inode, &logical_start, clusters_to_add, mark_unwritten, bh, handle, data_ac, meta_ac, &why); if ((status < 0) && (status != -EAGAIN)) { if (status != -ENOSPC) mlog_errno(status); goto leave; } ocfs2_update_inode_fsync_trans(handle, inode, 1); ocfs2_journal_dirty(handle, bh); spin_lock(&OCFS2_I(inode)->ip_lock); clusters_to_add -= (OCFS2_I(inode)->ip_clusters - prev_clusters); spin_unlock(&OCFS2_I(inode)->ip_lock); /* Release unused quota reservation */ dquot_free_space(inode, ocfs2_clusters_to_bytes(osb->sb, clusters_to_add)); did_quota = 0; if (why != RESTART_NONE && clusters_to_add) { if (why == RESTART_META) { restart_func = 1; status = 0; } else { BUG_ON(why != RESTART_TRANS); status = ocfs2_allocate_extend_trans(handle, 1); if (status < 0) { /* handle still has to be committed at * this point. */ status = -ENOMEM; mlog_errno(status); goto leave; } goto restarted_transaction; } } trace_ocfs2_extend_allocation_end(OCFS2_I(inode)->ip_blkno, le32_to_cpu(fe->i_clusters), (unsigned long long)le64_to_cpu(fe->i_size), OCFS2_I(inode)->ip_clusters, (unsigned long long)i_size_read(inode)); leave: if (status < 0 && did_quota) dquot_free_space(inode, ocfs2_clusters_to_bytes(osb->sb, clusters_to_add)); if (handle) { ocfs2_commit_trans(osb, handle); handle = NULL; } if (data_ac) { ocfs2_free_alloc_context(data_ac); data_ac = NULL; } if (meta_ac) { ocfs2_free_alloc_context(meta_ac); meta_ac = NULL; } if ((!status) && restart_func) { restart_func = 0; goto restart_all; } brelse(bh); bh = NULL; return status; } /* * While a write will already be ordering the data, a truncate will not. * Thus, we need to explicitly order the zeroed pages. */ static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode, struct buffer_head *di_bh, loff_t start_byte, loff_t length) { struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); handle_t *handle = NULL; int ret = 0; if (!ocfs2_should_order_data(inode)) goto out; handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { ret = -ENOMEM; mlog_errno(ret); goto out; } ret = ocfs2_jbd2_inode_add_write(handle, inode, start_byte, length); if (ret < 0) { mlog_errno(ret); goto out; } ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) mlog_errno(ret); ocfs2_update_inode_fsync_trans(handle, inode, 1); out: if (ret) { if (!IS_ERR(handle)) ocfs2_commit_trans(osb, handle); handle = ERR_PTR(ret); } return handle; } /* Some parts of this taken from generic_cont_expand, which turned out * to be too fragile to do exactly what we need without us having to * worry about recursive locking in ->write_begin() and ->write_end(). */ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from, u64 abs_to, struct buffer_head *di_bh) { struct address_space *mapping = inode->i_mapping; struct folio *folio; unsigned long index = abs_from >> PAGE_SHIFT; handle_t *handle; int ret = 0; unsigned zero_from, zero_to, block_start, block_end; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; BUG_ON(abs_from >= abs_to); BUG_ON(abs_to > (((u64)index + 1) << PAGE_SHIFT)); BUG_ON(abs_from & (inode->i_blkbits - 1)); handle = ocfs2_zero_start_ordered_transaction(inode, di_bh, abs_from, abs_to - abs_from); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out; } folio = __filemap_get_folio(mapping, index, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_NOFS); if (IS_ERR(folio)) { ret = PTR_ERR(folio); mlog_errno(ret); goto out_commit_trans; } /* Get the offsets within the folio that we want to zero */ zero_from = offset_in_folio(folio, abs_from); zero_to = offset_in_folio(folio, abs_to); if (!zero_to) zero_to = folio_size(folio); trace_ocfs2_write_zero_page( (unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)abs_from, (unsigned long long)abs_to, index, zero_from, zero_to); /* We know that zero_from is block aligned */ for (block_start = zero_from; block_start < zero_to; block_start = block_end) { block_end = block_start + i_blocksize(inode); /* * block_start is block-aligned. Bump it by one to force * __block_write_begin and block_commit_write to zero the * whole block. */ ret = __block_write_begin(folio, block_start + 1, 0, ocfs2_get_block); if (ret < 0) { mlog_errno(ret); goto out_unlock; } /* must not update i_size! */ block_commit_write(folio, block_start + 1, block_start + 1); } /* * fs-writeback will release the dirty pages without page lock * whose offset are over inode size, the release happens at * block_write_full_folio(). */ i_size_write(inode, abs_to); inode->i_blocks = ocfs2_inode_sector_count(inode); di->i_size = cpu_to_le64((u64)i_size_read(inode)); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); di->i_mtime = di->i_ctime = cpu_to_le64(inode_get_mtime_sec(inode)); di->i_ctime_nsec = cpu_to_le32(inode_get_mtime_nsec(inode)); di->i_mtime_nsec = di->i_ctime_nsec; if (handle) { ocfs2_journal_dirty(handle, di_bh); ocfs2_update_inode_fsync_trans(handle, inode, 1); } out_unlock: folio_unlock(folio); folio_put(folio); out_commit_trans: if (handle) ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle); out: return ret; } /* * Find the next range to zero. We do this in terms of bytes because * that's what ocfs2_zero_extend() wants, and it is dealing with the * pagecache. We may return multiple extents. * * zero_start and zero_end are ocfs2_zero_extend()s current idea of what * needs to be zeroed. range_start and range_end return the next zeroing * range. A subsequent call should pass the previous range_end as its * zero_start. If range_end is 0, there's nothing to do. * * Unwritten extents are skipped over. Refcounted extents are CoWd. */ static int ocfs2_zero_extend_get_range(struct inode *inode, struct buffer_head *di_bh, u64 zero_start, u64 zero_end, u64 *range_start, u64 *range_end) { int rc = 0, needs_cow = 0; u32 p_cpos, zero_clusters = 0; u32 zero_cpos = zero_start >> OCFS2_SB(inode->i_sb)->s_clustersize_bits; u32 last_cpos = ocfs2_clusters_for_bytes(inode->i_sb, zero_end); unsigned int num_clusters = 0; unsigned int ext_flags = 0; while (zero_cpos < last_cpos) { rc = ocfs2_get_clusters(inode, zero_cpos, &p_cpos, &num_clusters, &ext_flags); if (rc) { mlog_errno(rc); goto out; } if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) { zero_clusters = num_clusters; if (ext_flags & OCFS2_EXT_REFCOUNTED) needs_cow = 1; break; } zero_cpos += num_clusters; } if (!zero_clusters) { *range_end = 0; goto out; } while ((zero_cpos + zero_clusters) < last_cpos) { rc = ocfs2_get_clusters(inode, zero_cpos + zero_clusters, &p_cpos, &num_clusters, &ext_flags); if (rc) { mlog_errno(rc); goto out; } if (!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN)) break; if (ext_flags & OCFS2_EXT_REFCOUNTED) needs_cow = 1; zero_clusters += num_clusters; } if ((zero_cpos + zero_clusters) > last_cpos) zero_clusters = last_cpos - zero_cpos; if (needs_cow) { rc = ocfs2_refcount_cow(inode, di_bh, zero_cpos, zero_clusters, UINT_MAX); if (rc) { mlog_errno(rc); goto out; } } *range_start = ocfs2_clusters_to_bytes(inode->i_sb, zero_cpos); *range_end = ocfs2_clusters_to_bytes(inode->i_sb, zero_cpos + zero_clusters); out: return rc; } /* * Zero one range returned from ocfs2_zero_extend_get_range(). The caller * has made sure that the entire range needs zeroing. */ static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start, u64 range_end, struct buffer_head *di_bh) { int rc = 0; u64 next_pos; u64 zero_pos = range_start; trace_ocfs2_zero_extend_range( (unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)range_start, (unsigned long long)range_end); BUG_ON(range_start >= range_end); while (zero_pos < range_end) { next_pos = (zero_pos & PAGE_MASK) + PAGE_SIZE; if (next_pos > range_end) next_pos = range_end; rc = ocfs2_write_zero_page(inode, zero_pos, next_pos, di_bh); if (rc < 0) { mlog_errno(rc); break; } zero_pos = next_pos; /* * Very large extends have the potential to lock up * the cpu for extended periods of time. */ cond_resched(); } return rc; } int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh, loff_t zero_to_size) { int ret = 0; u64 zero_start, range_start = 0, range_end = 0; struct super_block *sb = inode->i_sb; zero_start = ocfs2_align_bytes_to_blocks(sb, i_size_read(inode)); trace_ocfs2_zero_extend((unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)zero_start, (unsigned long long)i_size_read(inode)); while (zero_start < zero_to_size) { ret = ocfs2_zero_extend_get_range(inode, di_bh, zero_start, zero_to_size, &range_start, &range_end); if (ret) { mlog_errno(ret); break; } if (!range_end) break; /* Trim the ends */ if (range_start < zero_start) range_start = zero_start; if (range_end > zero_to_size) range_end = zero_to_size; ret = ocfs2_zero_extend_range(inode, range_start, range_end, di_bh); if (ret) { mlog_errno(ret); break; } zero_start = range_end; } return ret; } int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh, u64 new_i_size, u64 zero_to) { int ret; u32 clusters_to_add; struct ocfs2_inode_info *oi = OCFS2_I(inode); /* * Only quota files call this without a bh, and they can't be * refcounted. */ BUG_ON(!di_bh && ocfs2_is_refcount_inode(inode)); BUG_ON(!di_bh && !(oi->ip_flags & OCFS2_INODE_SYSTEM_FILE)); clusters_to_add = ocfs2_clusters_for_bytes(inode->i_sb, new_i_size); if (clusters_to_add < oi->ip_clusters) clusters_to_add = 0; else clusters_to_add -= oi->ip_clusters; if (clusters_to_add) { ret = ocfs2_extend_allocation(inode, oi->ip_clusters, clusters_to_add, 0); if (ret) { mlog_errno(ret); goto out; } } /* * Call this even if we don't add any clusters to the tree. We * still need to zero the area between the old i_size and the * new i_size. */ ret = ocfs2_zero_extend(inode, di_bh, zero_to); if (ret < 0) mlog_errno(ret); out: return ret; } static int ocfs2_extend_file(struct inode *inode, struct buffer_head *di_bh, u64 new_i_size) { int ret = 0; struct ocfs2_inode_info *oi = OCFS2_I(inode); BUG_ON(!di_bh); /* setattr sometimes calls us like this. */ if (new_i_size == 0) goto out; if (i_size_read(inode) == new_i_size) goto out; BUG_ON(new_i_size < i_size_read(inode)); /* * The alloc sem blocks people in read/write from reading our * allocation until we're done changing it. We depend on * i_rwsem to block other extend/truncate calls while we're * here. We even have to hold it for sparse files because there * might be some tail zeroing. */ down_write(&oi->ip_alloc_sem); if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) { /* * We can optimize small extends by keeping the inodes * inline data. */ if (ocfs2_size_fits_inline_data(di_bh, new_i_size)) { up_write(&oi->ip_alloc_sem); goto out_update_size; } ret = ocfs2_convert_inline_data_to_extents(inode, di_bh); if (ret) { up_write(&oi->ip_alloc_sem); mlog_errno(ret); goto out; } } if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb))) ret = ocfs2_zero_extend(inode, di_bh, new_i_size); else ret = ocfs2_extend_no_holes(inode, di_bh, new_i_size, new_i_size); up_write(&oi->ip_alloc_sem); if (ret < 0) { mlog_errno(ret); goto out; } out_update_size: ret = ocfs2_simple_size_update(inode, di_bh, new_i_size); if (ret < 0) mlog_errno(ret); out: return ret; } int ocfs2_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { int status = 0, size_change; int inode_locked = 0; struct inode *inode = d_inode(dentry); struct super_block *sb = inode->i_sb; struct ocfs2_super *osb = OCFS2_SB(sb); struct buffer_head *bh = NULL; handle_t *handle = NULL; struct dquot *transfer_to[MAXQUOTAS] = { }; int qtype; int had_lock; struct ocfs2_lock_holder oh; trace_ocfs2_setattr(inode, dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, dentry->d_name.len, dentry->d_name.name, attr->ia_valid, attr->ia_valid & ATTR_MODE ? attr->ia_mode : 0, attr->ia_valid & ATTR_UID ? from_kuid(&init_user_ns, attr->ia_uid) : 0, attr->ia_valid & ATTR_GID ? from_kgid(&init_user_ns, attr->ia_gid) : 0); /* ensuring we don't even attempt to truncate a symlink */ if (S_ISLNK(inode->i_mode)) attr->ia_valid &= ~ATTR_SIZE; #define OCFS2_VALID_ATTRS (ATTR_ATIME | ATTR_MTIME | ATTR_CTIME | ATTR_SIZE \ | ATTR_GID | ATTR_UID | ATTR_MODE) if (!(attr->ia_valid & OCFS2_VALID_ATTRS)) return 0; status = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (status) return status; if (is_quota_modification(&nop_mnt_idmap, inode, attr)) { status = dquot_initialize(inode); if (status) return status; } size_change = S_ISREG(inode->i_mode) && attr->ia_valid & ATTR_SIZE; if (size_change) { /* * Here we should wait dio to finish before inode lock * to avoid a deadlock between ocfs2_setattr() and * ocfs2_dio_end_io_write() */ inode_dio_wait(inode); status = ocfs2_rw_lock(inode, 1); if (status < 0) { mlog_errno(status); goto bail; } } had_lock = ocfs2_inode_lock_tracker(inode, &bh, 1, &oh); if (had_lock < 0) { status = had_lock; goto bail_unlock_rw; } else if (had_lock) { /* * As far as we know, ocfs2_setattr() could only be the first * VFS entry point in the call chain of recursive cluster * locking issue. * * For instance: * chmod_common() * notify_change() * ocfs2_setattr() * posix_acl_chmod() * ocfs2_iop_get_acl() * * But, we're not 100% sure if it's always true, because the * ordering of the VFS entry points in the call chain is out * of our control. So, we'd better dump the stack here to * catch the other cases of recursive locking. */ mlog(ML_ERROR, "Another case of recursive locking:\n"); dump_stack(); } inode_locked = 1; if (size_change) { status = inode_newsize_ok(inode, attr->ia_size); if (status) goto bail_unlock; if (i_size_read(inode) >= attr->ia_size) { if (ocfs2_should_order_data(inode)) { status = ocfs2_begin_ordered_truncate(inode, attr->ia_size); if (status) goto bail_unlock; } status = ocfs2_truncate_file(inode, bh, attr->ia_size); } else status = ocfs2_extend_file(inode, bh, attr->ia_size); if (status < 0) { if (status != -ENOSPC) mlog_errno(status); status = -ENOSPC; goto bail_unlock; } } if ((attr->ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) || (attr->ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) { /* * Gather pointers to quota structures so that allocation / * freeing of quota structures happens here and not inside * dquot_transfer() where we have problems with lock ordering */ if (attr->ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid) && OCFS2_HAS_RO_COMPAT_FEATURE(sb, OCFS2_FEATURE_RO_COMPAT_USRQUOTA)) { transfer_to[USRQUOTA] = dqget(sb, make_kqid_uid(attr->ia_uid)); if (IS_ERR(transfer_to[USRQUOTA])) { status = PTR_ERR(transfer_to[USRQUOTA]); transfer_to[USRQUOTA] = NULL; goto bail_unlock; } } if (attr->ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid) && OCFS2_HAS_RO_COMPAT_FEATURE(sb, OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)) { transfer_to[GRPQUOTA] = dqget(sb, make_kqid_gid(attr->ia_gid)); if (IS_ERR(transfer_to[GRPQUOTA])) { status = PTR_ERR(transfer_to[GRPQUOTA]); transfer_to[GRPQUOTA] = NULL; goto bail_unlock; } } down_write(&OCFS2_I(inode)->ip_alloc_sem); handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS + 2 * ocfs2_quota_trans_credits(sb)); if (IS_ERR(handle)) { status = PTR_ERR(handle); mlog_errno(status); goto bail_unlock_alloc; } status = __dquot_transfer(inode, transfer_to); if (status < 0) goto bail_commit; } else { down_write(&OCFS2_I(inode)->ip_alloc_sem); handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { status = PTR_ERR(handle); mlog_errno(status); goto bail_unlock_alloc; } } setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); status = ocfs2_mark_inode_dirty(handle, inode, bh); if (status < 0) mlog_errno(status); bail_commit: ocfs2_commit_trans(osb, handle); bail_unlock_alloc: up_write(&OCFS2_I(inode)->ip_alloc_sem); bail_unlock: if (status && inode_locked) { ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock); inode_locked = 0; } bail_unlock_rw: if (size_change) ocfs2_rw_unlock(inode, 1); bail: /* Release quota pointers in case we acquired them */ for (qtype = 0; qtype < OCFS2_MAXQUOTAS; qtype++) dqput(transfer_to[qtype]); if (!status && attr->ia_valid & ATTR_MODE) { status = ocfs2_acl_chmod(inode, bh); if (status < 0) mlog_errno(status); } if (inode_locked) ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock); brelse(bh); return status; } int ocfs2_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { struct inode *inode = d_inode(path->dentry); struct super_block *sb = path->dentry->d_sb; struct ocfs2_super *osb = sb->s_fs_info; int err; err = ocfs2_inode_revalidate(path->dentry); if (err) { if (err != -ENOENT) mlog_errno(err); goto bail; } generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); /* * If there is inline data in the inode, the inode will normally not * have data blocks allocated (it may have an external xattr block). * Report at least one sector for such files, so tools like tar, rsync, * others don't incorrectly think the file is completely sparse. */ if (unlikely(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)) stat->blocks += (stat->size + 511)>>9; /* We set the blksize from the cluster size for performance */ stat->blksize = osb->s_clustersize; bail: return err; } int ocfs2_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { int ret, had_lock; struct ocfs2_lock_holder oh; if (mask & MAY_NOT_BLOCK) return -ECHILD; had_lock = ocfs2_inode_lock_tracker(inode, NULL, 0, &oh); if (had_lock < 0) { ret = had_lock; goto out; } else if (had_lock) { /* See comments in ocfs2_setattr() for details. * The call chain of this case could be: * do_sys_open() * may_open() * inode_permission() * ocfs2_permission() * ocfs2_iop_get_acl() */ mlog(ML_ERROR, "Another case of recursive locking:\n"); dump_stack(); } ret = generic_permission(&nop_mnt_idmap, inode, mask); ocfs2_inode_unlock_tracker(inode, 0, &oh, had_lock); out: return ret; } static int __ocfs2_write_remove_suid(struct inode *inode, struct buffer_head *bh) { int ret; handle_t *handle; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_dinode *di; trace_ocfs2_write_remove_suid( (unsigned long long)OCFS2_I(inode)->ip_blkno, inode->i_mode); handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto out; } ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret < 0) { mlog_errno(ret); goto out_trans; } inode->i_mode &= ~S_ISUID; if ((inode->i_mode & S_ISGID) && (inode->i_mode & S_IXGRP)) inode->i_mode &= ~S_ISGID; di = (struct ocfs2_dinode *) bh->b_data; di->i_mode = cpu_to_le16(inode->i_mode); ocfs2_update_inode_fsync_trans(handle, inode, 0); ocfs2_journal_dirty(handle, bh); out_trans: ocfs2_commit_trans(osb, handle); out: return ret; } static int ocfs2_write_remove_suid(struct inode *inode) { int ret; struct buffer_head *bh = NULL; ret = ocfs2_read_inode_block(inode, &bh); if (ret < 0) { mlog_errno(ret); goto out; } ret = __ocfs2_write_remove_suid(inode, bh); out: brelse(bh); return ret; } /* * Allocate enough extents to cover the region starting at byte offset * start for len bytes. Existing extents are skipped, any extents * added are marked as "unwritten". */ static int ocfs2_allocate_unwritten_extents(struct inode *inode, u64 start, u64 len) { int ret; u32 cpos, phys_cpos, clusters, alloc_size; u64 end = start + len; struct buffer_head *di_bh = NULL; if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { ret = ocfs2_read_inode_block(inode, &di_bh); if (ret) { mlog_errno(ret); goto out; } /* * Nothing to do if the requested reservation range * fits within the inode. */ if (ocfs2_size_fits_inline_data(di_bh, end)) goto out; ret = ocfs2_convert_inline_data_to_extents(inode, di_bh); if (ret) { mlog_errno(ret); goto out; } } /* * We consider both start and len to be inclusive. */ cpos = start >> OCFS2_SB(inode->i_sb)->s_clustersize_bits; clusters = ocfs2_clusters_for_bytes(inode->i_sb, start + len); clusters -= cpos; while (clusters) { ret = ocfs2_get_clusters(inode, cpos, &phys_cpos, &alloc_size, NULL); if (ret) { mlog_errno(ret); goto out; } /* * Hole or existing extent len can be arbitrary, so * cap it to our own allocation request. */ if (alloc_size > clusters) alloc_size = clusters; if (phys_cpos) { /* * We already have an allocation at this * region so we can safely skip it. */ goto next; } ret = ocfs2_extend_allocation(inode, cpos, alloc_size, 1); if (ret) { if (ret != -ENOSPC) mlog_errno(ret); goto out; } next: cpos += alloc_size; clusters -= alloc_size; } ret = 0; out: brelse(di_bh); return ret; } /* * Truncate a byte range, avoiding pages within partial clusters. This * preserves those pages for the zeroing code to write to. */ static void ocfs2_truncate_cluster_pages(struct inode *inode, u64 byte_start, u64 byte_len) { struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); loff_t start, end; struct address_space *mapping = inode->i_mapping; start = (loff_t)ocfs2_align_bytes_to_clusters(inode->i_sb, byte_start); end = byte_start + byte_len; end = end & ~(osb->s_clustersize - 1); if (start < end) { unmap_mapping_range(mapping, start, end - start, 0); truncate_inode_pages_range(mapping, start, end - 1); } } /* * zero out partial blocks of one cluster. * * start: file offset where zero starts, will be made upper block aligned. * len: it will be trimmed to the end of current cluster if "start + len" * is bigger than it. */ static int ocfs2_zeroout_partial_cluster(struct inode *inode, u64 start, u64 len) { int ret; u64 start_block, end_block, nr_blocks; u64 p_block, offset; u32 cluster, p_cluster, nr_clusters; struct super_block *sb = inode->i_sb; u64 end = ocfs2_align_bytes_to_clusters(sb, start); if (start + len < end) end = start + len; start_block = ocfs2_blocks_for_bytes(sb, start); end_block = ocfs2_blocks_for_bytes(sb, end); nr_blocks = end_block - start_block; if (!nr_blocks) return 0; cluster = ocfs2_bytes_to_clusters(sb, start); ret = ocfs2_get_clusters(inode, cluster, &p_cluster, &nr_clusters, NULL); if (ret) return ret; if (!p_cluster) return 0; offset = start_block - ocfs2_clusters_to_blocks(sb, cluster); p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset; return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS); } static int ocfs2_zero_partial_clusters(struct inode *inode, u64 start, u64 len) { int ret = 0; u64 tmpend = 0; u64 end = start + len; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); unsigned int csize = osb->s_clustersize; handle_t *handle; loff_t isize = i_size_read(inode); /* * The "start" and "end" values are NOT necessarily part of * the range whose allocation is being deleted. Rather, this * is what the user passed in with the request. We must zero * partial clusters here. There's no need to worry about * physical allocation - the zeroing code knows to skip holes. */ trace_ocfs2_zero_partial_clusters( (unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)start, (unsigned long long)end); /* * If both edges are on a cluster boundary then there's no * zeroing required as the region is part of the allocation to * be truncated. */ if ((start & (csize - 1)) == 0 && (end & (csize - 1)) == 0) goto out; /* No page cache for EOF blocks, issue zero out to disk. */ if (end > isize) { /* * zeroout eof blocks in last cluster starting from * "isize" even "start" > "isize" because it is * complicated to zeroout just at "start" as "start" * may be not aligned with block size, buffer write * would be required to do that, but out of eof buffer * write is not supported. */ ret = ocfs2_zeroout_partial_cluster(inode, isize, end - isize); if (ret) { mlog_errno(ret); goto out; } if (start >= isize) goto out; end = isize; } handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto out; } /* * If start is on a cluster boundary and end is somewhere in another * cluster, we have not COWed the cluster starting at start, unless * end is also within the same cluster. So, in this case, we skip this * first call to ocfs2_zero_range_for_truncate() truncate and move on * to the next one. */ if ((start & (csize - 1)) != 0) { /* * We want to get the byte offset of the end of the 1st * cluster. */ tmpend = (u64)osb->s_clustersize + (start & ~(osb->s_clustersize - 1)); if (tmpend > end) tmpend = end; trace_ocfs2_zero_partial_clusters_range1( (unsigned long long)start, (unsigned long long)tmpend); ret = ocfs2_zero_range_for_truncate(inode, handle, start, tmpend); if (ret) mlog_errno(ret); } if (tmpend < end) { /* * This may make start and end equal, but the zeroing * code will skip any work in that case so there's no * need to catch it up here. */ start = end & ~(osb->s_clustersize - 1); trace_ocfs2_zero_partial_clusters_range2( (unsigned long long)start, (unsigned long long)end); ret = ocfs2_zero_range_for_truncate(inode, handle, start, end); if (ret) mlog_errno(ret); } ocfs2_update_inode_fsync_trans(handle, inode, 1); ocfs2_commit_trans(osb, handle); out: return ret; } static int ocfs2_find_rec(struct ocfs2_extent_list *el, u32 pos) { int i; struct ocfs2_extent_rec *rec = NULL; for (i = le16_to_cpu(el->l_next_free_rec) - 1; i >= 0; i--) { rec = &el->l_recs[i]; if (le32_to_cpu(rec->e_cpos) < pos) break; } return i; } /* * Helper to calculate the punching pos and length in one run, we handle the * following three cases in order: * * - remove the entire record * - remove a partial record * - no record needs to be removed (hole-punching completed) */ static void ocfs2_calc_trunc_pos(struct inode *inode, struct ocfs2_extent_list *el, struct ocfs2_extent_rec *rec, u32 trunc_start, u32 *trunc_cpos, u32 *trunc_len, u32 *trunc_end, u64 *blkno, int *done) { int ret = 0; u32 coff, range; range = le32_to_cpu(rec->e_cpos) + ocfs2_rec_clusters(el, rec); if (le32_to_cpu(rec->e_cpos) >= trunc_start) { /* * remove an entire extent record. */ *trunc_cpos = le32_to_cpu(rec->e_cpos); /* * Skip holes if any. */ if (range < *trunc_end) *trunc_end = range; *trunc_len = *trunc_end - le32_to_cpu(rec->e_cpos); *blkno = le64_to_cpu(rec->e_blkno); *trunc_end = le32_to_cpu(rec->e_cpos); } else if (range > trunc_start) { /* * remove a partial extent record, which means we're * removing the last extent record. */ *trunc_cpos = trunc_start; /* * skip hole if any. */ if (range < *trunc_end) *trunc_end = range; *trunc_len = *trunc_end - trunc_start; coff = trunc_start - le32_to_cpu(rec->e_cpos); *blkno = le64_to_cpu(rec->e_blkno) + ocfs2_clusters_to_blocks(inode->i_sb, coff); *trunc_end = trunc_start; } else { /* * It may have two following possibilities: * * - last record has been removed * - trunc_start was within a hole * * both two cases mean the completion of hole punching. */ ret = 1; } *done = ret; } int ocfs2_remove_inode_range(struct inode *inode, struct buffer_head *di_bh, u64 byte_start, u64 byte_len) { int ret = 0, flags = 0, done = 0, i; u32 trunc_start, trunc_len, trunc_end, trunc_cpos, phys_cpos; u32 cluster_in_el; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_cached_dealloc_ctxt dealloc; struct address_space *mapping = inode->i_mapping; struct ocfs2_extent_tree et; struct ocfs2_path *path = NULL; struct ocfs2_extent_list *el = NULL; struct ocfs2_extent_rec *rec = NULL; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; u64 blkno, refcount_loc = le64_to_cpu(di->i_refcount_loc); ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh); ocfs2_init_dealloc_ctxt(&dealloc); trace_ocfs2_remove_inode_range( (unsigned long long)OCFS2_I(inode)->ip_blkno, (unsigned long long)byte_start, (unsigned long long)byte_len); if (byte_len == 0) return 0; if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { int id_count = ocfs2_max_inline_data_with_xattr(inode->i_sb, di); if (byte_start > id_count || byte_start + byte_len > id_count) { ret = -EINVAL; mlog_errno(ret); goto out; } ret = ocfs2_truncate_inline(inode, di_bh, byte_start, byte_start + byte_len, 0); if (ret) { mlog_errno(ret); goto out; } /* * There's no need to get fancy with the page cache * truncate of an inline-data inode. We're talking * about less than a page here, which will be cached * in the dinode buffer anyway. */ unmap_mapping_range(mapping, 0, 0, 0); truncate_inode_pages(mapping, 0); goto out; } /* * For reflinks, we may need to CoW 2 clusters which might be * partially zero'd later, if hole's start and end offset were * within one cluster(means is not exactly aligned to clustersize). */ if (ocfs2_is_refcount_inode(inode)) { ret = ocfs2_cow_file_pos(inode, di_bh, byte_start); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_cow_file_pos(inode, di_bh, byte_start + byte_len); if (ret) { mlog_errno(ret); goto out; } } trunc_start = ocfs2_clusters_for_bytes(osb->sb, byte_start); trunc_end = (byte_start + byte_len) >> osb->s_clustersize_bits; cluster_in_el = trunc_end; ret = ocfs2_zero_partial_clusters(inode, byte_start, byte_len); if (ret) { mlog_errno(ret); goto out; } path = ocfs2_new_path_from_et(&et); if (!path) { ret = -ENOMEM; mlog_errno(ret); goto out; } while (trunc_end > trunc_start) { ret = ocfs2_find_path(INODE_CACHE(inode), path, cluster_in_el); if (ret) { mlog_errno(ret); goto out; } el = path_leaf_el(path); i = ocfs2_find_rec(el, trunc_end); /* * Need to go to previous extent block. */ if (i < 0) { if (path->p_tree_depth == 0) break; ret = ocfs2_find_cpos_for_left_leaf(inode->i_sb, path, &cluster_in_el); if (ret) { mlog_errno(ret); goto out; } /* * We've reached the leftmost extent block, * it's safe to leave. */ if (cluster_in_el == 0) break; /* * The 'pos' searched for previous extent block is * always one cluster less than actual trunc_end. */ trunc_end = cluster_in_el + 1; ocfs2_reinit_path(path, 1); continue; } else rec = &el->l_recs[i]; ocfs2_calc_trunc_pos(inode, el, rec, trunc_start, &trunc_cpos, &trunc_len, &trunc_end, &blkno, &done); if (done) break; flags = rec->e_flags; phys_cpos = ocfs2_blocks_to_clusters(inode->i_sb, blkno); ret = ocfs2_remove_btree_range(inode, &et, trunc_cpos, phys_cpos, trunc_len, flags, &dealloc, refcount_loc, false); if (ret < 0) { mlog_errno(ret); goto out; } cluster_in_el = trunc_end; ocfs2_reinit_path(path, 1); } ocfs2_truncate_cluster_pages(inode, byte_start, byte_len); out: ocfs2_free_path(path); ocfs2_schedule_truncate_log_flush(osb, 1); ocfs2_run_deallocs(osb, &dealloc); return ret; } /* * Parts of this function taken from xfs_change_file_space() */ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, loff_t f_pos, unsigned int cmd, struct ocfs2_space_resv *sr, int change_size) { int ret; s64 llen; loff_t size, orig_isize; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct buffer_head *di_bh = NULL; handle_t *handle; unsigned long long max_off = inode->i_sb->s_maxbytes; if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) return -EROFS; inode_lock(inode); /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); /* * This prevents concurrent writes on other nodes */ ret = ocfs2_rw_lock(inode, 1); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_inode_lock(inode, &di_bh, 1); if (ret) { mlog_errno(ret); goto out_rw_unlock; } if (inode->i_flags & (S_IMMUTABLE|S_APPEND)) { ret = -EPERM; goto out_inode_unlock; } switch (sr->l_whence) { case 0: /*SEEK_SET*/ break; case 1: /*SEEK_CUR*/ sr->l_start += f_pos; break; case 2: /*SEEK_END*/ sr->l_start += i_size_read(inode); break; default: ret = -EINVAL; goto out_inode_unlock; } sr->l_whence = 0; llen = sr->l_len > 0 ? sr->l_len - 1 : sr->l_len; if (sr->l_start < 0 || sr->l_start > max_off || (sr->l_start + llen) < 0 || (sr->l_start + llen) > max_off) { ret = -EINVAL; goto out_inode_unlock; } size = sr->l_start + sr->l_len; if (cmd == OCFS2_IOC_RESVSP || cmd == OCFS2_IOC_RESVSP64 || cmd == OCFS2_IOC_UNRESVSP || cmd == OCFS2_IOC_UNRESVSP64) { if (sr->l_len <= 0) { ret = -EINVAL; goto out_inode_unlock; } } if (file && setattr_should_drop_suidgid(&nop_mnt_idmap, file_inode(file))) { ret = __ocfs2_write_remove_suid(inode, di_bh); if (ret) { mlog_errno(ret); goto out_inode_unlock; } } down_write(&OCFS2_I(inode)->ip_alloc_sem); switch (cmd) { case OCFS2_IOC_RESVSP: case OCFS2_IOC_RESVSP64: /* * This takes unsigned offsets, but the signed ones we * pass have been checked against overflow above. */ ret = ocfs2_allocate_unwritten_extents(inode, sr->l_start, sr->l_len); break; case OCFS2_IOC_UNRESVSP: case OCFS2_IOC_UNRESVSP64: ret = ocfs2_remove_inode_range(inode, di_bh, sr->l_start, sr->l_len); break; default: ret = -EINVAL; } orig_isize = i_size_read(inode); /* zeroout eof blocks in the cluster. */ if (!ret && change_size && orig_isize < size) { ret = ocfs2_zeroout_partial_cluster(inode, orig_isize, size - orig_isize); if (!ret) i_size_write(inode, size); } up_write(&OCFS2_I(inode)->ip_alloc_sem); if (ret) { mlog_errno(ret); goto out_inode_unlock; } /* * We update c/mtime for these changes */ handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto out_inode_unlock; } inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); ret = ocfs2_mark_inode_dirty(handle, inode, di_bh); if (ret < 0) mlog_errno(ret); if (file && (file->f_flags & O_SYNC)) handle->h_sync = 1; ocfs2_commit_trans(osb, handle); out_inode_unlock: brelse(di_bh); ocfs2_inode_unlock(inode, 1); out_rw_unlock: ocfs2_rw_unlock(inode, 1); out: inode_unlock(inode); return ret; } int ocfs2_change_file_space(struct file *file, unsigned int cmd, struct ocfs2_space_resv *sr) { struct inode *inode = file_inode(file); struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); int ret; if ((cmd == OCFS2_IOC_RESVSP || cmd == OCFS2_IOC_RESVSP64) && !ocfs2_writes_unwritten_extents(osb)) return -ENOTTY; else if ((cmd == OCFS2_IOC_UNRESVSP || cmd == OCFS2_IOC_UNRESVSP64) && !ocfs2_sparse_alloc(osb)) return -ENOTTY; if (!S_ISREG(inode->i_mode)) return -EINVAL; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; ret = mnt_want_write_file(file); if (ret) return ret; ret = __ocfs2_change_file_space(file, inode, file->f_pos, cmd, sr, 0); mnt_drop_write_file(file); return ret; } static long ocfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_space_resv sr; int change_size = 1; int cmd = OCFS2_IOC_RESVSP64; int ret = 0; if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) return -EOPNOTSUPP; if (!ocfs2_writes_unwritten_extents(osb)) return -EOPNOTSUPP; if (mode & FALLOC_FL_KEEP_SIZE) { change_size = 0; } else { ret = inode_newsize_ok(inode, offset + len); if (ret) return ret; } if (mode & FALLOC_FL_PUNCH_HOLE) cmd = OCFS2_IOC_UNRESVSP64; sr.l_whence = 0; sr.l_start = (s64)offset; sr.l_len = (s64)len; return __ocfs2_change_file_space(NULL, inode, offset, cmd, &sr, change_size); } int ocfs2_check_range_for_refcount(struct inode *inode, loff_t pos, size_t count) { int ret = 0; unsigned int extent_flags; u32 cpos, clusters, extent_len, phys_cpos; struct super_block *sb = inode->i_sb; if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb)) || !ocfs2_is_refcount_inode(inode) || OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) return 0; cpos = pos >> OCFS2_SB(sb)->s_clustersize_bits; clusters = ocfs2_clusters_for_bytes(sb, pos + count) - cpos; while (clusters) { ret = ocfs2_get_clusters(inode, cpos, &phys_cpos, &extent_len, &extent_flags); if (ret < 0) { mlog_errno(ret); goto out; } if (phys_cpos && (extent_flags & OCFS2_EXT_REFCOUNTED)) { ret = 1; break; } if (extent_len > clusters) extent_len = clusters; clusters -= extent_len; cpos += extent_len; } out: return ret; } static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos) { int blockmask = inode->i_sb->s_blocksize - 1; loff_t final_size = pos + count; if ((pos & blockmask) || (final_size & blockmask)) return 1; return 0; } static int ocfs2_inode_lock_for_extent_tree(struct inode *inode, struct buffer_head **di_bh, int meta_level, int write_sem, int wait) { int ret = 0; if (wait) ret = ocfs2_inode_lock(inode, di_bh, meta_level); else ret = ocfs2_try_inode_lock(inode, di_bh, meta_level); if (ret < 0) goto out; if (wait) { if (write_sem) down_write(&OCFS2_I(inode)->ip_alloc_sem); else down_read(&OCFS2_I(inode)->ip_alloc_sem); } else { if (write_sem) ret = down_write_trylock(&OCFS2_I(inode)->ip_alloc_sem); else ret = down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem); if (!ret) { ret = -EAGAIN; goto out_unlock; } } return ret; out_unlock: brelse(*di_bh); *di_bh = NULL; ocfs2_inode_unlock(inode, meta_level); out: return ret; } static void ocfs2_inode_unlock_for_extent_tree(struct inode *inode, struct buffer_head **di_bh, int meta_level, int write_sem) { if (write_sem) up_write(&OCFS2_I(inode)->ip_alloc_sem); else up_read(&OCFS2_I(inode)->ip_alloc_sem); brelse(*di_bh); *di_bh = NULL; if (meta_level >= 0) ocfs2_inode_unlock(inode, meta_level); } static int ocfs2_prepare_inode_for_write(struct file *file, loff_t pos, size_t count, int wait) { int ret = 0, meta_level = 0, overwrite_io = 0; int write_sem = 0; struct dentry *dentry = file->f_path.dentry; struct inode *inode = d_inode(dentry); struct buffer_head *di_bh = NULL; u32 cpos; u32 clusters; /* * We start with a read level meta lock and only jump to an ex * if we need to make modifications here. */ for(;;) { ret = ocfs2_inode_lock_for_extent_tree(inode, &di_bh, meta_level, write_sem, wait); if (ret < 0) { if (ret != -EAGAIN) mlog_errno(ret); goto out; } /* * Check if IO will overwrite allocated blocks in case * IOCB_NOWAIT flag is set. */ if (!wait && !overwrite_io) { overwrite_io = 1; ret = ocfs2_overwrite_io(inode, di_bh, pos, count); if (ret < 0) { if (ret != -EAGAIN) mlog_errno(ret); goto out_unlock; } } /* Clear suid / sgid if necessary. We do this here * instead of later in the write path because * remove_suid() calls ->setattr without any hint that * we may have already done our cluster locking. Since * ocfs2_setattr() *must* take cluster locks to * proceed, this will lead us to recursively lock the * inode. There's also the dinode i_size state which * can be lost via setattr during extending writes (we * set inode->i_size at the end of a write. */ if (setattr_should_drop_suidgid(&nop_mnt_idmap, inode)) { if (meta_level == 0) { ocfs2_inode_unlock_for_extent_tree(inode, &di_bh, meta_level, write_sem); meta_level = 1; continue; } ret = ocfs2_write_remove_suid(inode); if (ret < 0) { mlog_errno(ret); goto out_unlock; } } ret = ocfs2_check_range_for_refcount(inode, pos, count); if (ret == 1) { ocfs2_inode_unlock_for_extent_tree(inode, &di_bh, meta_level, write_sem); meta_level = 1; write_sem = 1; ret = ocfs2_inode_lock_for_extent_tree(inode, &di_bh, meta_level, write_sem, wait); if (ret < 0) { if (ret != -EAGAIN) mlog_errno(ret); goto out; } cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits; clusters = ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos; ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX); } if (ret < 0) { if (ret != -EAGAIN) mlog_errno(ret); goto out_unlock; } break; } out_unlock: trace_ocfs2_prepare_inode_for_write(OCFS2_I(inode)->ip_blkno, pos, count, wait); ocfs2_inode_unlock_for_extent_tree(inode, &di_bh, meta_level, write_sem); out: return ret; } static ssize_t ocfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { int rw_level; ssize_t written = 0; ssize_t ret; size_t count = iov_iter_count(from); struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); int full_coherency = !(osb->s_mount_opt & OCFS2_MOUNT_COHERENCY_BUFFERED); void *saved_ki_complete = NULL; int append_write = ((iocb->ki_pos + count) >= i_size_read(inode) ? 1 : 0); int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0; int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0; trace_ocfs2_file_write_iter(inode, file, file->f_path.dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, file->f_path.dentry->d_name.len, file->f_path.dentry->d_name.name, (unsigned int)from->nr_segs); /* GRRRRR */ if (!direct_io && nowait) return -EOPNOTSUPP; if (count == 0) return 0; if (nowait) { if (!inode_trylock(inode)) return -EAGAIN; } else inode_lock(inode); ocfs2_iocb_init_rw_locked(iocb); /* * Concurrent O_DIRECT writes are allowed with * mount_option "coherency=buffered". * For append write, we must take rw EX. */ rw_level = (!direct_io || full_coherency || append_write); if (nowait) ret = ocfs2_try_rw_lock(inode, rw_level); else ret = ocfs2_rw_lock(inode, rw_level); if (ret < 0) { if (ret != -EAGAIN) mlog_errno(ret); goto out_mutex; } /* * O_DIRECT writes with "coherency=full" need to take EX cluster * inode_lock to guarantee coherency. */ if (direct_io && full_coherency) { /* * We need to take and drop the inode lock to force * other nodes to drop their caches. Buffered I/O * already does this in write_begin(). */ if (nowait) ret = ocfs2_try_inode_lock(inode, NULL, 1); else ret = ocfs2_inode_lock(inode, NULL, 1); if (ret < 0) { if (ret != -EAGAIN) mlog_errno(ret); goto out; } ocfs2_inode_unlock(inode, 1); } ret = generic_write_checks(iocb, from); if (ret <= 0) { if (ret) mlog_errno(ret); goto out; } count = ret; ret = ocfs2_prepare_inode_for_write(file, iocb->ki_pos, count, !nowait); if (ret < 0) { if (ret != -EAGAIN) mlog_errno(ret); goto out; } if (direct_io && !is_sync_kiocb(iocb) && ocfs2_is_io_unaligned(inode, count, iocb->ki_pos)) { /* * Make it a sync io if it's an unaligned aio. */ saved_ki_complete = xchg(&iocb->ki_complete, NULL); } /* communicate with ocfs2_dio_end_io */ ocfs2_iocb_set_rw_locked(iocb, rw_level); written = __generic_file_write_iter(iocb, from); /* buffered aio wouldn't have proper lock coverage today */ BUG_ON(written == -EIOCBQUEUED && !direct_io); /* * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io * function pointer which is called when o_direct io completes so that * it can unlock our rw lock. * Unfortunately there are error cases which call end_io and others * that don't. so we don't have to unlock the rw_lock if either an * async dio is going to do it in the future or an end_io after an * error has already done it. */ if ((written == -EIOCBQUEUED) || (!ocfs2_iocb_is_rw_locked(iocb))) { rw_level = -1; } if (unlikely(written <= 0)) goto out; if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode)) { ret = filemap_fdatawrite_range(file->f_mapping, iocb->ki_pos - written, iocb->ki_pos - 1); if (ret < 0) written = ret; if (!ret) { ret = jbd2_journal_force_commit(osb->journal->j_journal); if (ret < 0) written = ret; } if (!ret) ret = filemap_fdatawait_range(file->f_mapping, iocb->ki_pos - written, iocb->ki_pos - 1); } out: if (saved_ki_complete) xchg(&iocb->ki_complete, saved_ki_complete); if (rw_level != -1) ocfs2_rw_unlock(inode, rw_level); out_mutex: inode_unlock(inode); if (written) ret = written; return ret; } static ssize_t ocfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { int ret = 0, rw_level = -1, lock_level = 0; struct file *filp = iocb->ki_filp; struct inode *inode = file_inode(filp); int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0; int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0; trace_ocfs2_file_read_iter(inode, filp, filp->f_path.dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, filp->f_path.dentry->d_name.len, filp->f_path.dentry->d_name.name, to->nr_segs); /* GRRRRR */ if (!inode) { ret = -EINVAL; mlog_errno(ret); goto bail; } if (!direct_io && nowait) return -EOPNOTSUPP; ocfs2_iocb_init_rw_locked(iocb); /* * buffered reads protect themselves in ->read_folio(). O_DIRECT reads * need locks to protect pending reads from racing with truncate. */ if (direct_io) { if (nowait) ret = ocfs2_try_rw_lock(inode, 0); else ret = ocfs2_rw_lock(inode, 0); if (ret < 0) { if (ret != -EAGAIN) mlog_errno(ret); goto bail; } rw_level = 0; /* communicate with ocfs2_dio_end_io */ ocfs2_iocb_set_rw_locked(iocb, rw_level); } /* * We're fine letting folks race truncates and extending * writes with read across the cluster, just like they can * locally. Hence no rw_lock during read. * * Take and drop the meta data lock to update inode fields * like i_size. This allows the checks down below * copy_splice_read() a chance of actually working. */ ret = ocfs2_inode_lock_atime(inode, filp->f_path.mnt, &lock_level, !nowait); if (ret < 0) { if (ret != -EAGAIN) mlog_errno(ret); goto bail; } ocfs2_inode_unlock(inode, lock_level); ret = generic_file_read_iter(iocb, to); trace_generic_file_read_iter_ret(ret); /* buffered aio wouldn't have proper lock coverage today */ BUG_ON(ret == -EIOCBQUEUED && !direct_io); /* see ocfs2_file_write_iter */ if (ret == -EIOCBQUEUED || !ocfs2_iocb_is_rw_locked(iocb)) { rw_level = -1; } bail: if (rw_level != -1) ocfs2_rw_unlock(inode, rw_level); return ret; } static ssize_t ocfs2_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct inode *inode = file_inode(in); ssize_t ret = 0; int lock_level = 0; trace_ocfs2_file_splice_read(inode, in, in->f_path.dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, in->f_path.dentry->d_name.len, in->f_path.dentry->d_name.name, flags); /* * We're fine letting folks race truncates and extending writes with * read across the cluster, just like they can locally. Hence no * rw_lock during read. * * Take and drop the meta data lock to update inode fields like i_size. * This allows the checks down below filemap_splice_read() a chance of * actually working. */ ret = ocfs2_inode_lock_atime(inode, in->f_path.mnt, &lock_level, 1); if (ret < 0) { if (ret != -EAGAIN) mlog_errno(ret); goto bail; } ocfs2_inode_unlock(inode, lock_level); ret = filemap_splice_read(in, ppos, pipe, len, flags); trace_filemap_splice_read_ret(ret); bail: return ret; } /* Refer generic_file_llseek_unlocked() */ static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; int ret = 0; inode_lock(inode); switch (whence) { case SEEK_SET: break; case SEEK_END: /* SEEK_END requires the OCFS2 inode lock for the file * because it references the file's size. */ ret = ocfs2_inode_lock(inode, NULL, 0); if (ret < 0) { mlog_errno(ret); goto out; } offset += i_size_read(inode); ocfs2_inode_unlock(inode, 0); break; case SEEK_CUR: if (offset == 0) { offset = file->f_pos; goto out; } offset += file->f_pos; break; case SEEK_DATA: case SEEK_HOLE: ret = ocfs2_seek_data_hole_offset(file, &offset, whence); if (ret) goto out; break; default: ret = -EINVAL; goto out; } offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes); out: inode_unlock(inode); if (ret) return ret; return offset; } static loff_t ocfs2_remap_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); struct ocfs2_super *osb = OCFS2_SB(inode_in->i_sb); struct buffer_head *in_bh = NULL, *out_bh = NULL; bool same_inode = (inode_in == inode_out); loff_t remapped = 0; ssize_t ret; if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) return -EINVAL; if (!ocfs2_refcount_tree(osb)) return -EOPNOTSUPP; if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) return -EROFS; /* Lock both files against IO */ ret = ocfs2_reflink_inodes_lock(inode_in, &in_bh, inode_out, &out_bh); if (ret) return ret; /* Check file eligibility and prepare for block sharing. */ ret = -EINVAL; if ((OCFS2_I(inode_in)->ip_flags & OCFS2_INODE_SYSTEM_FILE) || (OCFS2_I(inode_out)->ip_flags & OCFS2_INODE_SYSTEM_FILE)) goto out_unlock; ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, &len, remap_flags); if (ret < 0 || len == 0) goto out_unlock; /* Lock out changes to the allocation maps and remap. */ down_write(&OCFS2_I(inode_in)->ip_alloc_sem); if (!same_inode) down_write_nested(&OCFS2_I(inode_out)->ip_alloc_sem, SINGLE_DEPTH_NESTING); /* Zap any page cache for the destination file's range. */ truncate_inode_pages_range(&inode_out->i_data, round_down(pos_out, PAGE_SIZE), round_up(pos_out + len, PAGE_SIZE) - 1); remapped = ocfs2_reflink_remap_blocks(inode_in, in_bh, pos_in, inode_out, out_bh, pos_out, len); up_write(&OCFS2_I(inode_in)->ip_alloc_sem); if (!same_inode) up_write(&OCFS2_I(inode_out)->ip_alloc_sem); if (remapped < 0) { ret = remapped; mlog_errno(ret); goto out_unlock; } /* * Empty the extent map so that we may get the right extent * record from the disk. */ ocfs2_extent_map_trunc(inode_in, 0); ocfs2_extent_map_trunc(inode_out, 0); ret = ocfs2_reflink_update_dest(inode_out, out_bh, pos_out + len); if (ret) { mlog_errno(ret); goto out_unlock; } out_unlock: ocfs2_reflink_inodes_unlock(inode_in, in_bh, inode_out, out_bh); return remapped > 0 ? remapped : ret; } static loff_t ocfs2_dir_llseek(struct file *file, loff_t offset, int whence) { struct ocfs2_file_private *fp = file->private_data; return generic_llseek_cookie(file, offset, whence, &fp->cookie); } const struct inode_operations ocfs2_file_iops = { .setattr = ocfs2_setattr, .getattr = ocfs2_getattr, .permission = ocfs2_permission, .listxattr = ocfs2_listxattr, .fiemap = ocfs2_fiemap, .get_inode_acl = ocfs2_iop_get_acl, .set_acl = ocfs2_iop_set_acl, .fileattr_get = ocfs2_fileattr_get, .fileattr_set = ocfs2_fileattr_set, }; const struct inode_operations ocfs2_special_file_iops = { .setattr = ocfs2_setattr, .getattr = ocfs2_getattr, .listxattr = ocfs2_listxattr, .permission = ocfs2_permission, .get_inode_acl = ocfs2_iop_get_acl, .set_acl = ocfs2_iop_set_acl, }; /* * Other than ->lock, keep ocfs2_fops and ocfs2_dops in sync with * ocfs2_fops_no_plocks and ocfs2_dops_no_plocks! */ const struct file_operations ocfs2_fops = { .llseek = ocfs2_file_llseek, .mmap_prepare = ocfs2_mmap_prepare, .fsync = ocfs2_sync_file, .release = ocfs2_file_release, .open = ocfs2_file_open, .read_iter = ocfs2_file_read_iter, .write_iter = ocfs2_file_write_iter, .unlocked_ioctl = ocfs2_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ocfs2_compat_ioctl, #endif .lock = ocfs2_lock, .flock = ocfs2_flock, .splice_read = ocfs2_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = ocfs2_fallocate, .remap_file_range = ocfs2_remap_file_range, .fop_flags = FOP_ASYNC_LOCK, }; WRAP_DIR_ITER(ocfs2_readdir) // FIXME! const struct file_operations ocfs2_dops = { .llseek = ocfs2_dir_llseek, .read = generic_read_dir, .iterate_shared = shared_ocfs2_readdir, .fsync = ocfs2_sync_file, .release = ocfs2_dir_release, .open = ocfs2_dir_open, .unlocked_ioctl = ocfs2_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ocfs2_compat_ioctl, #endif .lock = ocfs2_lock, .flock = ocfs2_flock, .fop_flags = FOP_ASYNC_LOCK, }; /* * POSIX-lockless variants of our file_operations. * * These will be used if the underlying cluster stack does not support * posix file locking, if the user passes the "localflocks" mount * option, or if we have a local-only fs. * * ocfs2_flock is in here because all stacks handle UNIX file locks, * so we still want it in the case of no stack support for * plocks. Internally, it will do the right thing when asked to ignore * the cluster. */ const struct file_operations ocfs2_fops_no_plocks = { .llseek = ocfs2_file_llseek, .mmap_prepare = ocfs2_mmap_prepare, .fsync = ocfs2_sync_file, .release = ocfs2_file_release, .open = ocfs2_file_open, .read_iter = ocfs2_file_read_iter, .write_iter = ocfs2_file_write_iter, .unlocked_ioctl = ocfs2_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ocfs2_compat_ioctl, #endif .flock = ocfs2_flock, .splice_read = filemap_splice_read, .splice_write = iter_file_splice_write, .fallocate = ocfs2_fallocate, .remap_file_range = ocfs2_remap_file_range, }; const struct file_operations ocfs2_dops_no_plocks = { .llseek = ocfs2_dir_llseek, .read = generic_read_dir, .iterate_shared = shared_ocfs2_readdir, .fsync = ocfs2_sync_file, .release = ocfs2_dir_release, .open = ocfs2_dir_open, .unlocked_ioctl = ocfs2_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ocfs2_compat_ioctl, #endif .flock = ocfs2_flock, }; |
| 17 18 17 18 18 17 18 18 17 17 17 16 17 15 15 16 14 16 15 14 14 2 2 2 2 1 2 16 16 12 12 11 3 12 12 12 6 3 8 8 5 3 2 2 4 2 2 4 4 4 1 2 1 4 4 4 2 2 4 4 4 2 4 8 8 3 2 2 2 2 2 2 2 1 1 2 2 2 2 1 2 6 6 6 6 6 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 | // SPDX-License-Identifier: GPL-2.0-only /* * v4l2-dv-timings - dv-timings helper functions * * Copyright 2013 Cisco Systems, Inc. and/or its affiliates. All rights reserved. */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/rational.h> #include <linux/videodev2.h> #include <linux/v4l2-dv-timings.h> #include <media/v4l2-dv-timings.h> #include <linux/math64.h> #include <linux/hdmi.h> #include <media/cec.h> MODULE_AUTHOR("Hans Verkuil"); MODULE_DESCRIPTION("V4L2 DV Timings Helper Functions"); MODULE_LICENSE("GPL"); const struct v4l2_dv_timings v4l2_dv_timings_presets[] = { V4L2_DV_BT_CEA_640X480P59_94, V4L2_DV_BT_CEA_720X480I59_94, V4L2_DV_BT_CEA_720X480P59_94, V4L2_DV_BT_CEA_720X576I50, V4L2_DV_BT_CEA_720X576P50, V4L2_DV_BT_CEA_1280X720P24, V4L2_DV_BT_CEA_1280X720P25, V4L2_DV_BT_CEA_1280X720P30, V4L2_DV_BT_CEA_1280X720P50, V4L2_DV_BT_CEA_1280X720P60, V4L2_DV_BT_CEA_1920X1080P24, V4L2_DV_BT_CEA_1920X1080P25, V4L2_DV_BT_CEA_1920X1080P30, V4L2_DV_BT_CEA_1920X1080I50, V4L2_DV_BT_CEA_1920X1080P50, V4L2_DV_BT_CEA_1920X1080I60, V4L2_DV_BT_CEA_1920X1080P60, V4L2_DV_BT_DMT_640X350P85, V4L2_DV_BT_DMT_640X400P85, V4L2_DV_BT_DMT_720X400P85, V4L2_DV_BT_DMT_640X480P72, V4L2_DV_BT_DMT_640X480P75, V4L2_DV_BT_DMT_640X480P85, V4L2_DV_BT_DMT_800X600P56, V4L2_DV_BT_DMT_800X600P60, V4L2_DV_BT_DMT_800X600P72, V4L2_DV_BT_DMT_800X600P75, V4L2_DV_BT_DMT_800X600P85, V4L2_DV_BT_DMT_800X600P120_RB, V4L2_DV_BT_DMT_848X480P60, V4L2_DV_BT_DMT_1024X768I43, V4L2_DV_BT_DMT_1024X768P60, V4L2_DV_BT_DMT_1024X768P70, V4L2_DV_BT_DMT_1024X768P75, V4L2_DV_BT_DMT_1024X768P85, V4L2_DV_BT_DMT_1024X768P120_RB, V4L2_DV_BT_DMT_1152X864P75, V4L2_DV_BT_DMT_1280X768P60_RB, V4L2_DV_BT_DMT_1280X768P60, V4L2_DV_BT_DMT_1280X768P75, V4L2_DV_BT_DMT_1280X768P85, V4L2_DV_BT_DMT_1280X768P120_RB, V4L2_DV_BT_DMT_1280X800P60_RB, V4L2_DV_BT_DMT_1280X800P60, V4L2_DV_BT_DMT_1280X800P75, V4L2_DV_BT_DMT_1280X800P85, V4L2_DV_BT_DMT_1280X800P120_RB, V4L2_DV_BT_DMT_1280X960P60, V4L2_DV_BT_DMT_1280X960P85, V4L2_DV_BT_DMT_1280X960P120_RB, V4L2_DV_BT_DMT_1280X1024P60, V4L2_DV_BT_DMT_1280X1024P75, V4L2_DV_BT_DMT_1280X1024P85, V4L2_DV_BT_DMT_1280X1024P120_RB, V4L2_DV_BT_DMT_1360X768P60, V4L2_DV_BT_DMT_1360X768P120_RB, V4L2_DV_BT_DMT_1366X768P60, V4L2_DV_BT_DMT_1366X768P60_RB, V4L2_DV_BT_DMT_1400X1050P60_RB, V4L2_DV_BT_DMT_1400X1050P60, V4L2_DV_BT_DMT_1400X1050P75, V4L2_DV_BT_DMT_1400X1050P85, V4L2_DV_BT_DMT_1400X1050P120_RB, V4L2_DV_BT_DMT_1440X900P60_RB, V4L2_DV_BT_DMT_1440X900P60, V4L2_DV_BT_DMT_1440X900P75, V4L2_DV_BT_DMT_1440X900P85, V4L2_DV_BT_DMT_1440X900P120_RB, V4L2_DV_BT_DMT_1600X900P60_RB, V4L2_DV_BT_DMT_1600X1200P60, V4L2_DV_BT_DMT_1600X1200P65, V4L2_DV_BT_DMT_1600X1200P70, V4L2_DV_BT_DMT_1600X1200P75, V4L2_DV_BT_DMT_1600X1200P85, V4L2_DV_BT_DMT_1600X1200P120_RB, V4L2_DV_BT_DMT_1680X1050P60_RB, V4L2_DV_BT_DMT_1680X1050P60, V4L2_DV_BT_DMT_1680X1050P75, V4L2_DV_BT_DMT_1680X1050P85, V4L2_DV_BT_DMT_1680X1050P120_RB, V4L2_DV_BT_DMT_1792X1344P60, V4L2_DV_BT_DMT_1792X1344P75, V4L2_DV_BT_DMT_1792X1344P120_RB, V4L2_DV_BT_DMT_1856X1392P60, V4L2_DV_BT_DMT_1856X1392P75, V4L2_DV_BT_DMT_1856X1392P120_RB, V4L2_DV_BT_DMT_1920X1200P60_RB, V4L2_DV_BT_DMT_1920X1200P60, V4L2_DV_BT_DMT_1920X1200P75, V4L2_DV_BT_DMT_1920X1200P85, V4L2_DV_BT_DMT_1920X1200P120_RB, V4L2_DV_BT_DMT_1920X1440P60, V4L2_DV_BT_DMT_1920X1440P75, V4L2_DV_BT_DMT_1920X1440P120_RB, V4L2_DV_BT_DMT_2048X1152P60_RB, V4L2_DV_BT_DMT_2560X1600P60_RB, V4L2_DV_BT_DMT_2560X1600P60, V4L2_DV_BT_DMT_2560X1600P75, V4L2_DV_BT_DMT_2560X1600P85, V4L2_DV_BT_DMT_2560X1600P120_RB, V4L2_DV_BT_CEA_3840X2160P24, V4L2_DV_BT_CEA_3840X2160P25, V4L2_DV_BT_CEA_3840X2160P30, V4L2_DV_BT_CEA_3840X2160P50, V4L2_DV_BT_CEA_3840X2160P60, V4L2_DV_BT_CEA_4096X2160P24, V4L2_DV_BT_CEA_4096X2160P25, V4L2_DV_BT_CEA_4096X2160P30, V4L2_DV_BT_CEA_4096X2160P50, V4L2_DV_BT_DMT_4096X2160P59_94_RB, V4L2_DV_BT_CEA_4096X2160P60, { } }; EXPORT_SYMBOL_GPL(v4l2_dv_timings_presets); bool v4l2_valid_dv_timings(const struct v4l2_dv_timings *t, const struct v4l2_dv_timings_cap *dvcap, v4l2_check_dv_timings_fnc fnc, void *fnc_handle) { const struct v4l2_bt_timings *bt = &t->bt; const struct v4l2_bt_timings_cap *cap = &dvcap->bt; u32 caps = cap->capabilities; const u32 max_vert = 10240; u32 max_hor = 3 * bt->width; if (t->type != V4L2_DV_BT_656_1120) return false; if (t->type != dvcap->type || bt->height < cap->min_height || bt->height > cap->max_height || bt->width < cap->min_width || bt->width > cap->max_width || bt->pixelclock < cap->min_pixelclock || bt->pixelclock > cap->max_pixelclock || (!(caps & V4L2_DV_BT_CAP_CUSTOM) && cap->standards && bt->standards && !(bt->standards & cap->standards)) || (bt->interlaced && !(caps & V4L2_DV_BT_CAP_INTERLACED)) || (!bt->interlaced && !(caps & V4L2_DV_BT_CAP_PROGRESSIVE))) return false; /* sanity checks for the blanking timings */ if (!bt->interlaced && (bt->il_vbackporch || bt->il_vsync || bt->il_vfrontporch)) return false; /* * Some video receivers cannot properly separate the frontporch, * backporch and sync values, and instead they only have the total * blanking. That can be assigned to any of these three fields. * So just check that none of these are way out of range. */ if (bt->hfrontporch > max_hor || bt->hsync > max_hor || bt->hbackporch > max_hor) return false; if (bt->vfrontporch > max_vert || bt->vsync > max_vert || bt->vbackporch > max_vert) return false; if (bt->interlaced && (bt->il_vfrontporch > max_vert || bt->il_vsync > max_vert || bt->il_vbackporch > max_vert)) return false; return fnc == NULL || fnc(t, fnc_handle); } EXPORT_SYMBOL_GPL(v4l2_valid_dv_timings); int v4l2_enum_dv_timings_cap(struct v4l2_enum_dv_timings *t, const struct v4l2_dv_timings_cap *cap, v4l2_check_dv_timings_fnc fnc, void *fnc_handle) { u32 i, idx; memset(t->reserved, 0, sizeof(t->reserved)); for (i = idx = 0; v4l2_dv_timings_presets[i].bt.width; i++) { if (v4l2_valid_dv_timings(v4l2_dv_timings_presets + i, cap, fnc, fnc_handle) && idx++ == t->index) { t->timings = v4l2_dv_timings_presets[i]; return 0; } } return -EINVAL; } EXPORT_SYMBOL_GPL(v4l2_enum_dv_timings_cap); bool v4l2_find_dv_timings_cap(struct v4l2_dv_timings *t, const struct v4l2_dv_timings_cap *cap, unsigned pclock_delta, v4l2_check_dv_timings_fnc fnc, void *fnc_handle) { int i; if (!v4l2_valid_dv_timings(t, cap, fnc, fnc_handle)) return false; for (i = 0; v4l2_dv_timings_presets[i].bt.width; i++) { if (v4l2_valid_dv_timings(v4l2_dv_timings_presets + i, cap, fnc, fnc_handle) && v4l2_match_dv_timings(t, v4l2_dv_timings_presets + i, pclock_delta, false)) { u32 flags = t->bt.flags & V4L2_DV_FL_REDUCED_FPS; *t = v4l2_dv_timings_presets[i]; if (can_reduce_fps(&t->bt)) t->bt.flags |= flags; return true; } } return false; } EXPORT_SYMBOL_GPL(v4l2_find_dv_timings_cap); bool v4l2_find_dv_timings_cea861_vic(struct v4l2_dv_timings *t, u8 vic) { unsigned int i; for (i = 0; v4l2_dv_timings_presets[i].bt.width; i++) { const struct v4l2_bt_timings *bt = &v4l2_dv_timings_presets[i].bt; if ((bt->flags & V4L2_DV_FL_HAS_CEA861_VIC) && bt->cea861_vic == vic) { *t = v4l2_dv_timings_presets[i]; return true; } } return false; } EXPORT_SYMBOL_GPL(v4l2_find_dv_timings_cea861_vic); /** * v4l2_match_dv_timings - check if two timings match * @t1: compare this v4l2_dv_timings struct... * @t2: with this struct. * @pclock_delta: the allowed pixelclock deviation. * @match_reduced_fps: if true, then fail if V4L2_DV_FL_REDUCED_FPS does not * match. * * Compare t1 with t2 with a given margin of error for the pixelclock. */ bool v4l2_match_dv_timings(const struct v4l2_dv_timings *t1, const struct v4l2_dv_timings *t2, unsigned pclock_delta, bool match_reduced_fps) { if (t1->type != t2->type || t1->type != V4L2_DV_BT_656_1120) return false; if (t1->bt.width == t2->bt.width && t1->bt.height == t2->bt.height && t1->bt.interlaced == t2->bt.interlaced && t1->bt.polarities == t2->bt.polarities && t1->bt.pixelclock >= t2->bt.pixelclock - pclock_delta && t1->bt.pixelclock <= t2->bt.pixelclock + pclock_delta && t1->bt.hfrontporch == t2->bt.hfrontporch && t1->bt.hsync == t2->bt.hsync && t1->bt.hbackporch == t2->bt.hbackporch && t1->bt.vfrontporch == t2->bt.vfrontporch && t1->bt.vsync == t2->bt.vsync && t1->bt.vbackporch == t2->bt.vbackporch && (!match_reduced_fps || (t1->bt.flags & V4L2_DV_FL_REDUCED_FPS) == (t2->bt.flags & V4L2_DV_FL_REDUCED_FPS)) && (!t1->bt.interlaced || (t1->bt.il_vfrontporch == t2->bt.il_vfrontporch && t1->bt.il_vsync == t2->bt.il_vsync && t1->bt.il_vbackporch == t2->bt.il_vbackporch))) return true; return false; } EXPORT_SYMBOL_GPL(v4l2_match_dv_timings); void v4l2_print_dv_timings(const char *dev_prefix, const char *prefix, const struct v4l2_dv_timings *t, bool detailed) { const struct v4l2_bt_timings *bt = &t->bt; u32 htot, vtot; u32 fps; if (t->type != V4L2_DV_BT_656_1120) return; htot = V4L2_DV_BT_FRAME_WIDTH(bt); vtot = V4L2_DV_BT_FRAME_HEIGHT(bt); if (bt->interlaced) vtot /= 2; fps = (htot * vtot) > 0 ? div_u64((100 * (u64)bt->pixelclock), (htot * vtot)) : 0; if (prefix == NULL) prefix = ""; pr_info("%s: %s%ux%u%s%u.%02u (%ux%u)\n", dev_prefix, prefix, bt->width, bt->height, bt->interlaced ? "i" : "p", fps / 100, fps % 100, htot, vtot); if (!detailed) return; pr_info("%s: horizontal: fp = %u, %ssync = %u, bp = %u\n", dev_prefix, bt->hfrontporch, (bt->polarities & V4L2_DV_HSYNC_POS_POL) ? "+" : "-", bt->hsync, bt->hbackporch); pr_info("%s: vertical: fp = %u, %ssync = %u, bp = %u\n", dev_prefix, bt->vfrontporch, (bt->polarities & V4L2_DV_VSYNC_POS_POL) ? "+" : "-", bt->vsync, bt->vbackporch); if (bt->interlaced) pr_info("%s: vertical bottom field: fp = %u, %ssync = %u, bp = %u\n", dev_prefix, bt->il_vfrontporch, (bt->polarities & V4L2_DV_VSYNC_POS_POL) ? "+" : "-", bt->il_vsync, bt->il_vbackporch); pr_info("%s: pixelclock: %llu\n", dev_prefix, bt->pixelclock); pr_info("%s: flags (0x%x):%s%s%s%s%s%s%s%s%s%s\n", dev_prefix, bt->flags, (bt->flags & V4L2_DV_FL_REDUCED_BLANKING) ? " REDUCED_BLANKING" : "", ((bt->flags & V4L2_DV_FL_REDUCED_BLANKING) && bt->vsync == 8) ? " (V2)" : "", (bt->flags & V4L2_DV_FL_CAN_REDUCE_FPS) ? " CAN_REDUCE_FPS" : "", (bt->flags & V4L2_DV_FL_REDUCED_FPS) ? " REDUCED_FPS" : "", (bt->flags & V4L2_DV_FL_HALF_LINE) ? " HALF_LINE" : "", (bt->flags & V4L2_DV_FL_IS_CE_VIDEO) ? " CE_VIDEO" : "", (bt->flags & V4L2_DV_FL_FIRST_FIELD_EXTRA_LINE) ? " FIRST_FIELD_EXTRA_LINE" : "", (bt->flags & V4L2_DV_FL_HAS_PICTURE_ASPECT) ? " HAS_PICTURE_ASPECT" : "", (bt->flags & V4L2_DV_FL_HAS_CEA861_VIC) ? " HAS_CEA861_VIC" : "", (bt->flags & V4L2_DV_FL_HAS_HDMI_VIC) ? " HAS_HDMI_VIC" : ""); pr_info("%s: standards (0x%x):%s%s%s%s%s\n", dev_prefix, bt->standards, (bt->standards & V4L2_DV_BT_STD_CEA861) ? " CEA" : "", (bt->standards & V4L2_DV_BT_STD_DMT) ? " DMT" : "", (bt->standards & V4L2_DV_BT_STD_CVT) ? " CVT" : "", (bt->standards & V4L2_DV_BT_STD_GTF) ? " GTF" : "", (bt->standards & V4L2_DV_BT_STD_SDI) ? " SDI" : ""); if (bt->flags & V4L2_DV_FL_HAS_PICTURE_ASPECT) pr_info("%s: picture aspect (hor:vert): %u:%u\n", dev_prefix, bt->picture_aspect.numerator, bt->picture_aspect.denominator); if (bt->flags & V4L2_DV_FL_HAS_CEA861_VIC) pr_info("%s: CEA-861 VIC: %u\n", dev_prefix, bt->cea861_vic); if (bt->flags & V4L2_DV_FL_HAS_HDMI_VIC) pr_info("%s: HDMI VIC: %u\n", dev_prefix, bt->hdmi_vic); } EXPORT_SYMBOL_GPL(v4l2_print_dv_timings); struct v4l2_fract v4l2_dv_timings_aspect_ratio(const struct v4l2_dv_timings *t) { struct v4l2_fract ratio = { 1, 1 }; unsigned long n, d; if (t->type != V4L2_DV_BT_656_1120) return ratio; if (!(t->bt.flags & V4L2_DV_FL_HAS_PICTURE_ASPECT)) return ratio; ratio.numerator = t->bt.width * t->bt.picture_aspect.denominator; ratio.denominator = t->bt.height * t->bt.picture_aspect.numerator; rational_best_approximation(ratio.numerator, ratio.denominator, ratio.numerator, ratio.denominator, &n, &d); ratio.numerator = n; ratio.denominator = d; return ratio; } EXPORT_SYMBOL_GPL(v4l2_dv_timings_aspect_ratio); /** v4l2_calc_timeperframe - helper function to calculate timeperframe based * v4l2_dv_timings fields. * @t - Timings for the video mode. * * Calculates the expected timeperframe using the pixel clock value and * horizontal/vertical measures. This means that v4l2_dv_timings structure * must be correctly and fully filled. */ struct v4l2_fract v4l2_calc_timeperframe(const struct v4l2_dv_timings *t) { const struct v4l2_bt_timings *bt = &t->bt; struct v4l2_fract fps_fract = { 1, 1 }; unsigned long n, d; u32 htot, vtot, fps; u64 pclk; if (t->type != V4L2_DV_BT_656_1120) return fps_fract; htot = V4L2_DV_BT_FRAME_WIDTH(bt); vtot = V4L2_DV_BT_FRAME_HEIGHT(bt); pclk = bt->pixelclock; if ((bt->flags & V4L2_DV_FL_CAN_DETECT_REDUCED_FPS) && (bt->flags & V4L2_DV_FL_REDUCED_FPS)) pclk = div_u64(pclk * 1000ULL, 1001); fps = (htot * vtot) > 0 ? div_u64((100 * pclk), (htot * vtot)) : 0; if (!fps) return fps_fract; rational_best_approximation(fps, 100, fps, 100, &n, &d); fps_fract.numerator = d; fps_fract.denominator = n; return fps_fract; } EXPORT_SYMBOL_GPL(v4l2_calc_timeperframe); /* * CVT defines * Based on Coordinated Video Timings Standard * version 1.1 September 10, 2003 */ #define CVT_PXL_CLK_GRAN 250000 /* pixel clock granularity */ #define CVT_PXL_CLK_GRAN_RB_V2 1000 /* granularity for reduced blanking v2*/ /* Normal blanking */ #define CVT_MIN_V_BPORCH 7 /* lines */ #define CVT_MIN_V_PORCH_RND 3 /* lines */ #define CVT_MIN_VSYNC_BP 550 /* min time of vsync + back porch (us) */ #define CVT_HSYNC_PERCENT 8 /* nominal hsync as percentage of line */ /* Normal blanking for CVT uses GTF to calculate horizontal blanking */ #define CVT_CELL_GRAN 8 /* character cell granularity */ #define CVT_M 600 /* blanking formula gradient */ #define CVT_C 40 /* blanking formula offset */ #define CVT_K 128 /* blanking formula scaling factor */ #define CVT_J 20 /* blanking formula scaling factor */ #define CVT_C_PRIME (((CVT_C - CVT_J) * CVT_K / 256) + CVT_J) #define CVT_M_PRIME (CVT_K * CVT_M / 256) /* Reduced Blanking */ #define CVT_RB_MIN_V_BPORCH 7 /* lines */ #define CVT_RB_V_FPORCH 3 /* lines */ #define CVT_RB_MIN_V_BLANK 460 /* us */ #define CVT_RB_H_SYNC 32 /* pixels */ #define CVT_RB_H_BLANK 160 /* pixels */ /* Reduce blanking Version 2 */ #define CVT_RB_V2_H_BLANK 80 /* pixels */ #define CVT_RB_MIN_V_FPORCH 3 /* lines */ #define CVT_RB_V2_MIN_V_FPORCH 1 /* lines */ #define CVT_RB_V_BPORCH 6 /* lines */ /** v4l2_detect_cvt - detect if the given timings follow the CVT standard * @frame_height - the total height of the frame (including blanking) in lines. * @hfreq - the horizontal frequency in Hz. * @vsync - the height of the vertical sync in lines. * @active_width - active width of image (does not include blanking). This * information is needed only in case of version 2 of reduced blanking. * In other cases, this parameter does not have any effect on timings. * @polarities - the horizontal and vertical polarities (same as struct * v4l2_bt_timings polarities). * @interlaced - if this flag is true, it indicates interlaced format * @cap - the v4l2_dv_timings_cap capabilities. * @timings - the resulting timings. * * This function will attempt to detect if the given values correspond to a * valid CVT format. If so, then it will return true, and fmt will be filled * in with the found CVT timings. */ bool v4l2_detect_cvt(unsigned int frame_height, unsigned int hfreq, unsigned int vsync, unsigned int active_width, u32 polarities, bool interlaced, const struct v4l2_dv_timings_cap *cap, struct v4l2_dv_timings *timings) { struct v4l2_dv_timings t = {}; int v_fp, v_bp, h_fp, h_bp, hsync; int frame_width, image_height, image_width; bool reduced_blanking; bool rb_v2 = false; unsigned int pix_clk; if (vsync < 4 || vsync > 8) return false; if (polarities == V4L2_DV_VSYNC_POS_POL) reduced_blanking = false; else if (polarities == V4L2_DV_HSYNC_POS_POL) reduced_blanking = true; else return false; if (reduced_blanking && vsync == 8) rb_v2 = true; if (rb_v2 && active_width == 0) return false; if (!rb_v2 && vsync > 7) return false; if (hfreq == 0) return false; /* Vertical */ if (reduced_blanking) { if (rb_v2) { v_bp = CVT_RB_V_BPORCH; v_fp = (CVT_RB_MIN_V_BLANK * hfreq) / 1000000 + 1; v_fp -= vsync + v_bp; if (v_fp < CVT_RB_V2_MIN_V_FPORCH) v_fp = CVT_RB_V2_MIN_V_FPORCH; } else { v_fp = CVT_RB_V_FPORCH; v_bp = (CVT_RB_MIN_V_BLANK * hfreq) / 1000000 + 1; v_bp -= vsync + v_fp; if (v_bp < CVT_RB_MIN_V_BPORCH) v_bp = CVT_RB_MIN_V_BPORCH; } } else { v_fp = CVT_MIN_V_PORCH_RND; v_bp = (CVT_MIN_VSYNC_BP * hfreq) / 1000000 + 1 - vsync; if (v_bp < CVT_MIN_V_BPORCH) v_bp = CVT_MIN_V_BPORCH; } if (interlaced) image_height = (frame_height - 2 * v_fp - 2 * vsync - 2 * v_bp) & ~0x1; else image_height = (frame_height - v_fp - vsync - v_bp + 1) & ~0x1; if (image_height < 0) return false; /* Aspect ratio based on vsync */ switch (vsync) { case 4: image_width = (image_height * 4) / 3; break; case 5: image_width = (image_height * 16) / 9; break; case 6: image_width = (image_height * 16) / 10; break; case 7: /* special case */ if (image_height == 1024) image_width = (image_height * 5) / 4; else if (image_height == 768) image_width = (image_height * 15) / 9; else return false; break; case 8: image_width = active_width; break; default: return false; } if (!rb_v2) image_width = image_width & ~7; /* Horizontal */ if (reduced_blanking) { int h_blank; int clk_gran; h_blank = rb_v2 ? CVT_RB_V2_H_BLANK : CVT_RB_H_BLANK; clk_gran = rb_v2 ? CVT_PXL_CLK_GRAN_RB_V2 : CVT_PXL_CLK_GRAN; pix_clk = (image_width + h_blank) * hfreq; pix_clk = (pix_clk / clk_gran) * clk_gran; h_bp = h_blank / 2; hsync = CVT_RB_H_SYNC; h_fp = h_blank - h_bp - hsync; frame_width = image_width + h_blank; } else { unsigned ideal_duty_cycle_per_myriad = 100 * CVT_C_PRIME - (CVT_M_PRIME * 100000) / hfreq; int h_blank; if (ideal_duty_cycle_per_myriad < 2000) ideal_duty_cycle_per_myriad = 2000; h_blank = image_width * ideal_duty_cycle_per_myriad / (10000 - ideal_duty_cycle_per_myriad); h_blank = (h_blank / (2 * CVT_CELL_GRAN)) * 2 * CVT_CELL_GRAN; pix_clk = (image_width + h_blank) * hfreq; pix_clk = (pix_clk / CVT_PXL_CLK_GRAN) * CVT_PXL_CLK_GRAN; h_bp = h_blank / 2; frame_width = image_width + h_blank; hsync = frame_width * CVT_HSYNC_PERCENT / 100; hsync = (hsync / CVT_CELL_GRAN) * CVT_CELL_GRAN; h_fp = h_blank - hsync - h_bp; } t.type = V4L2_DV_BT_656_1120; t.bt.polarities = polarities; t.bt.width = image_width; t.bt.height = image_height; t.bt.hfrontporch = h_fp; t.bt.vfrontporch = v_fp; t.bt.hsync = hsync; t.bt.vsync = vsync; t.bt.hbackporch = frame_width - image_width - h_fp - hsync; if (!interlaced) { t.bt.vbackporch = frame_height - image_height - v_fp - vsync; t.bt.interlaced = V4L2_DV_PROGRESSIVE; } else { t.bt.vbackporch = (frame_height - image_height - 2 * v_fp - 2 * vsync) / 2; t.bt.il_vbackporch = frame_height - image_height - 2 * v_fp - 2 * vsync - t.bt.vbackporch; t.bt.il_vfrontporch = v_fp; t.bt.il_vsync = vsync; t.bt.flags |= V4L2_DV_FL_HALF_LINE; t.bt.interlaced = V4L2_DV_INTERLACED; } t.bt.pixelclock = pix_clk; t.bt.standards = V4L2_DV_BT_STD_CVT; if (reduced_blanking) t.bt.flags |= V4L2_DV_FL_REDUCED_BLANKING; if (!v4l2_valid_dv_timings(&t, cap, NULL, NULL)) return false; *timings = t; return true; } EXPORT_SYMBOL_GPL(v4l2_detect_cvt); /* * GTF defines * Based on Generalized Timing Formula Standard * Version 1.1 September 2, 1999 */ #define GTF_PXL_CLK_GRAN 250000 /* pixel clock granularity */ #define GTF_MIN_VSYNC_BP 550 /* min time of vsync + back porch (us) */ #define GTF_V_FP 1 /* vertical front porch (lines) */ #define GTF_CELL_GRAN 8 /* character cell granularity */ /* Default */ #define GTF_D_M 600 /* blanking formula gradient */ #define GTF_D_C 40 /* blanking formula offset */ #define GTF_D_K 128 /* blanking formula scaling factor */ #define GTF_D_J 20 /* blanking formula scaling factor */ #define GTF_D_C_PRIME ((((GTF_D_C - GTF_D_J) * GTF_D_K) / 256) + GTF_D_J) #define GTF_D_M_PRIME ((GTF_D_K * GTF_D_M) / 256) /* Secondary */ #define GTF_S_M 3600 /* blanking formula gradient */ #define GTF_S_C 40 /* blanking formula offset */ #define GTF_S_K 128 /* blanking formula scaling factor */ #define GTF_S_J 35 /* blanking formula scaling factor */ #define GTF_S_C_PRIME ((((GTF_S_C - GTF_S_J) * GTF_S_K) / 256) + GTF_S_J) #define GTF_S_M_PRIME ((GTF_S_K * GTF_S_M) / 256) /** v4l2_detect_gtf - detect if the given timings follow the GTF standard * @frame_height - the total height of the frame (including blanking) in lines. * @hfreq - the horizontal frequency in Hz. * @vsync - the height of the vertical sync in lines. * @polarities - the horizontal and vertical polarities (same as struct * v4l2_bt_timings polarities). * @interlaced - if this flag is true, it indicates interlaced format * @aspect - preferred aspect ratio. GTF has no method of determining the * aspect ratio in order to derive the image width from the * image height, so it has to be passed explicitly. Usually * the native screen aspect ratio is used for this. If it * is not filled in correctly, then 16:9 will be assumed. * @cap - the v4l2_dv_timings_cap capabilities. * @timings - the resulting timings. * * This function will attempt to detect if the given values correspond to a * valid GTF format. If so, then it will return true, and fmt will be filled * in with the found GTF timings. */ bool v4l2_detect_gtf(unsigned int frame_height, unsigned int hfreq, unsigned int vsync, u32 polarities, bool interlaced, struct v4l2_fract aspect, const struct v4l2_dv_timings_cap *cap, struct v4l2_dv_timings *timings) { struct v4l2_dv_timings t = {}; int pix_clk; int v_fp, v_bp, h_fp, hsync; int frame_width, image_height, image_width; bool default_gtf; int h_blank; if (vsync != 3) return false; if (polarities == V4L2_DV_VSYNC_POS_POL) default_gtf = true; else if (polarities == V4L2_DV_HSYNC_POS_POL) default_gtf = false; else return false; if (hfreq == 0) return false; /* Vertical */ v_fp = GTF_V_FP; v_bp = (GTF_MIN_VSYNC_BP * hfreq + 500000) / 1000000 - vsync; if (interlaced) image_height = (frame_height - 2 * v_fp - 2 * vsync - 2 * v_bp) & ~0x1; else image_height = (frame_height - v_fp - vsync - v_bp + 1) & ~0x1; if (image_height < 0) return false; if (aspect.numerator == 0 || aspect.denominator == 0) { aspect.numerator = 16; aspect.denominator = 9; } image_width = ((image_height * aspect.numerator) / aspect.denominator); image_width = (image_width + GTF_CELL_GRAN/2) & ~(GTF_CELL_GRAN - 1); /* Horizontal */ if (default_gtf) { u64 num; u32 den; num = (((u64)image_width * GTF_D_C_PRIME * hfreq) - ((u64)image_width * GTF_D_M_PRIME * 1000)); den = (hfreq * (100 - GTF_D_C_PRIME) + GTF_D_M_PRIME * 1000) * (2 * GTF_CELL_GRAN); h_blank = div_u64((num + (den >> 1)), den); h_blank *= (2 * GTF_CELL_GRAN); } else { u64 num; u32 den; num = (((u64)image_width * GTF_S_C_PRIME * hfreq) - ((u64)image_width * GTF_S_M_PRIME * 1000)); den = (hfreq * (100 - GTF_S_C_PRIME) + GTF_S_M_PRIME * 1000) * (2 * GTF_CELL_GRAN); h_blank = div_u64((num + (den >> 1)), den); h_blank *= (2 * GTF_CELL_GRAN); } frame_width = image_width + h_blank; pix_clk = (image_width + h_blank) * hfreq; pix_clk = pix_clk / GTF_PXL_CLK_GRAN * GTF_PXL_CLK_GRAN; hsync = (frame_width * 8 + 50) / 100; hsync = DIV_ROUND_CLOSEST(hsync, GTF_CELL_GRAN) * GTF_CELL_GRAN; h_fp = h_blank / 2 - hsync; t.type = V4L2_DV_BT_656_1120; t.bt.polarities = polarities; t.bt.width = image_width; t.bt.height = image_height; t.bt.hfrontporch = h_fp; t.bt.vfrontporch = v_fp; t.bt.hsync = hsync; t.bt.vsync = vsync; t.bt.hbackporch = frame_width - image_width - h_fp - hsync; if (!interlaced) { t.bt.vbackporch = frame_height - image_height - v_fp - vsync; t.bt.interlaced = V4L2_DV_PROGRESSIVE; } else { t.bt.vbackporch = (frame_height - image_height - 2 * v_fp - 2 * vsync) / 2; t.bt.il_vbackporch = frame_height - image_height - 2 * v_fp - 2 * vsync - t.bt.vbackporch; t.bt.il_vfrontporch = v_fp; t.bt.il_vsync = vsync; t.bt.flags |= V4L2_DV_FL_HALF_LINE; t.bt.interlaced = V4L2_DV_INTERLACED; } t.bt.pixelclock = pix_clk; t.bt.standards = V4L2_DV_BT_STD_GTF; if (!default_gtf) t.bt.flags |= V4L2_DV_FL_REDUCED_BLANKING; if (!v4l2_valid_dv_timings(&t, cap, NULL, NULL)) return false; *timings = t; return true; } EXPORT_SYMBOL_GPL(v4l2_detect_gtf); /** v4l2_calc_aspect_ratio - calculate the aspect ratio based on bytes * 0x15 and 0x16 from the EDID. * @hor_landscape - byte 0x15 from the EDID. * @vert_portrait - byte 0x16 from the EDID. * * Determines the aspect ratio from the EDID. * See VESA Enhanced EDID standard, release A, rev 2, section 3.6.2: * "Horizontal and Vertical Screen Size or Aspect Ratio" */ struct v4l2_fract v4l2_calc_aspect_ratio(u8 hor_landscape, u8 vert_portrait) { struct v4l2_fract aspect = { 16, 9 }; u8 ratio; /* Nothing filled in, fallback to 16:9 */ if (!hor_landscape && !vert_portrait) return aspect; /* Both filled in, so they are interpreted as the screen size in cm */ if (hor_landscape && vert_portrait) { aspect.numerator = hor_landscape; aspect.denominator = vert_portrait; return aspect; } /* Only one is filled in, so interpret them as a ratio: (val + 99) / 100 */ ratio = hor_landscape | vert_portrait; /* Change some rounded values into the exact aspect ratio */ if (ratio == 79) { aspect.numerator = 16; aspect.denominator = 9; } else if (ratio == 34) { aspect.numerator = 4; aspect.denominator = 3; } else if (ratio == 68) { aspect.numerator = 15; aspect.denominator = 9; } else { aspect.numerator = hor_landscape + 99; aspect.denominator = 100; } if (hor_landscape) return aspect; /* The aspect ratio is for portrait, so swap numerator and denominator */ swap(aspect.denominator, aspect.numerator); return aspect; } EXPORT_SYMBOL_GPL(v4l2_calc_aspect_ratio); /** v4l2_hdmi_rx_colorimetry - determine HDMI colorimetry information * based on various InfoFrames. * @avi: the AVI InfoFrame * @hdmi: the HDMI Vendor InfoFrame, may be NULL * @height: the frame height * * Determines the HDMI colorimetry information, i.e. how the HDMI * pixel color data should be interpreted. * * Note that some of the newer features (DCI-P3, HDR) are not yet * implemented: the hdmi.h header needs to be updated to the HDMI 2.0 * and CTA-861-G standards. */ struct v4l2_hdmi_colorimetry v4l2_hdmi_rx_colorimetry(const struct hdmi_avi_infoframe *avi, const struct hdmi_vendor_infoframe *hdmi, unsigned int height) { struct v4l2_hdmi_colorimetry c = { V4L2_COLORSPACE_SRGB, V4L2_YCBCR_ENC_DEFAULT, V4L2_QUANTIZATION_FULL_RANGE, V4L2_XFER_FUNC_SRGB }; bool is_ce = avi->video_code || (hdmi && hdmi->vic); bool is_sdtv = height <= 576; bool default_is_lim_range_rgb = avi->video_code > 1; switch (avi->colorspace) { case HDMI_COLORSPACE_RGB: /* RGB pixel encoding */ switch (avi->colorimetry) { case HDMI_COLORIMETRY_EXTENDED: switch (avi->extended_colorimetry) { case HDMI_EXTENDED_COLORIMETRY_OPRGB: c.colorspace = V4L2_COLORSPACE_OPRGB; c.xfer_func = V4L2_XFER_FUNC_OPRGB; break; case HDMI_EXTENDED_COLORIMETRY_BT2020: c.colorspace = V4L2_COLORSPACE_BT2020; c.xfer_func = V4L2_XFER_FUNC_709; break; default: break; } break; default: break; } switch (avi->quantization_range) { case HDMI_QUANTIZATION_RANGE_LIMITED: c.quantization = V4L2_QUANTIZATION_LIM_RANGE; break; case HDMI_QUANTIZATION_RANGE_FULL: break; default: if (default_is_lim_range_rgb) c.quantization = V4L2_QUANTIZATION_LIM_RANGE; break; } break; default: /* YCbCr pixel encoding */ c.quantization = V4L2_QUANTIZATION_LIM_RANGE; switch (avi->colorimetry) { case HDMI_COLORIMETRY_NONE: if (!is_ce) break; if (is_sdtv) { c.colorspace = V4L2_COLORSPACE_SMPTE170M; c.ycbcr_enc = V4L2_YCBCR_ENC_601; } else { c.colorspace = V4L2_COLORSPACE_REC709; c.ycbcr_enc = V4L2_YCBCR_ENC_709; } c.xfer_func = V4L2_XFER_FUNC_709; break; case HDMI_COLORIMETRY_ITU_601: c.colorspace = V4L2_COLORSPACE_SMPTE170M; c.ycbcr_enc = V4L2_YCBCR_ENC_601; c.xfer_func = V4L2_XFER_FUNC_709; break; case HDMI_COLORIMETRY_ITU_709: c.colorspace = V4L2_COLORSPACE_REC709; c.ycbcr_enc = V4L2_YCBCR_ENC_709; c.xfer_func = V4L2_XFER_FUNC_709; break; case HDMI_COLORIMETRY_EXTENDED: switch (avi->extended_colorimetry) { case HDMI_EXTENDED_COLORIMETRY_XV_YCC_601: c.colorspace = V4L2_COLORSPACE_REC709; c.ycbcr_enc = V4L2_YCBCR_ENC_XV709; c.xfer_func = V4L2_XFER_FUNC_709; break; case HDMI_EXTENDED_COLORIMETRY_XV_YCC_709: c.colorspace = V4L2_COLORSPACE_REC709; c.ycbcr_enc = V4L2_YCBCR_ENC_XV601; c.xfer_func = V4L2_XFER_FUNC_709; break; case HDMI_EXTENDED_COLORIMETRY_S_YCC_601: c.colorspace = V4L2_COLORSPACE_SRGB; c.ycbcr_enc = V4L2_YCBCR_ENC_601; c.xfer_func = V4L2_XFER_FUNC_SRGB; break; case HDMI_EXTENDED_COLORIMETRY_OPYCC_601: c.colorspace = V4L2_COLORSPACE_OPRGB; c.ycbcr_enc = V4L2_YCBCR_ENC_601; c.xfer_func = V4L2_XFER_FUNC_OPRGB; break; case HDMI_EXTENDED_COLORIMETRY_BT2020: c.colorspace = V4L2_COLORSPACE_BT2020; c.ycbcr_enc = V4L2_YCBCR_ENC_BT2020; c.xfer_func = V4L2_XFER_FUNC_709; break; case HDMI_EXTENDED_COLORIMETRY_BT2020_CONST_LUM: c.colorspace = V4L2_COLORSPACE_BT2020; c.ycbcr_enc = V4L2_YCBCR_ENC_BT2020_CONST_LUM; c.xfer_func = V4L2_XFER_FUNC_709; break; default: /* fall back to ITU_709 */ c.colorspace = V4L2_COLORSPACE_REC709; c.ycbcr_enc = V4L2_YCBCR_ENC_709; c.xfer_func = V4L2_XFER_FUNC_709; break; } break; default: break; } /* * YCC Quantization Range signaling is more-or-less broken, * let's just ignore this. */ break; } return c; } EXPORT_SYMBOL_GPL(v4l2_hdmi_rx_colorimetry); /** * v4l2_num_edid_blocks() - return the number of EDID blocks * * @edid: pointer to the EDID data * @max_blocks: maximum number of supported EDID blocks * * Return: the number of EDID blocks based on the contents of the EDID. * This supports the HDMI Forum EDID Extension Override Data Block. */ unsigned int v4l2_num_edid_blocks(const u8 *edid, unsigned int max_blocks) { unsigned int blocks; if (!edid || !max_blocks) return 0; // The number of extension blocks is recorded at byte 126 of the // first 128-byte block in the EDID. // // If there is an HDMI Forum EDID Extension Override Data Block // present, then it is in bytes 4-6 of the first CTA-861 extension // block of the EDID. blocks = edid[126] + 1; // Check for HDMI Forum EDID Extension Override Data Block if (blocks >= 2 && // The EDID must be at least 2 blocks max_blocks >= 3 && // The caller supports at least 3 blocks edid[128] == 2 && // The first extension block is type CTA-861 edid[133] == 0x78 && // Identifier for the EEODB (edid[132] & 0xe0) == 0xe0 && // Tag Code == 7 (edid[132] & 0x1f) >= 2 && // Length >= 2 edid[134] > 1) // Number of extension blocks is sane blocks = edid[134] + 1; return blocks > max_blocks ? max_blocks : blocks; } EXPORT_SYMBOL_GPL(v4l2_num_edid_blocks); /** * v4l2_get_edid_phys_addr() - find and return the physical address * * @edid: pointer to the EDID data * @size: size in bytes of the EDID data * @offset: If not %NULL then the location of the physical address * bytes in the EDID will be returned here. This is set to 0 * if there is no physical address found. * * Return: the physical address or CEC_PHYS_ADDR_INVALID if there is none. */ u16 v4l2_get_edid_phys_addr(const u8 *edid, unsigned int size, unsigned int *offset) { unsigned int loc = cec_get_edid_spa_location(edid, size); if (offset) *offset = loc; if (loc == 0) return CEC_PHYS_ADDR_INVALID; return (edid[loc] << 8) | edid[loc + 1]; } EXPORT_SYMBOL_GPL(v4l2_get_edid_phys_addr); /** * v4l2_set_edid_phys_addr() - find and set the physical address * * @edid: pointer to the EDID data * @size: size in bytes of the EDID data * @phys_addr: the new physical address * * This function finds the location of the physical address in the EDID * and fills in the given physical address and updates the checksum * at the end of the EDID block. It does nothing if the EDID doesn't * contain a physical address. */ void v4l2_set_edid_phys_addr(u8 *edid, unsigned int size, u16 phys_addr) { unsigned int loc = cec_get_edid_spa_location(edid, size); u8 sum = 0; unsigned int i; if (loc == 0) return; edid[loc] = phys_addr >> 8; edid[loc + 1] = phys_addr & 0xff; loc &= ~0x7f; /* update the checksum */ for (i = loc; i < loc + 127; i++) sum += edid[i]; edid[i] = 256 - sum; } EXPORT_SYMBOL_GPL(v4l2_set_edid_phys_addr); /** * v4l2_phys_addr_for_input() - calculate the PA for an input * * @phys_addr: the physical address of the parent * @input: the number of the input port, must be between 1 and 15 * * This function calculates a new physical address based on the input * port number. For example: * * PA = 0.0.0.0 and input = 2 becomes 2.0.0.0 * * PA = 3.0.0.0 and input = 1 becomes 3.1.0.0 * * PA = 3.2.1.0 and input = 5 becomes 3.2.1.5 * * PA = 3.2.1.3 and input = 5 becomes f.f.f.f since it maxed out the depth. * * Return: the new physical address or CEC_PHYS_ADDR_INVALID. */ u16 v4l2_phys_addr_for_input(u16 phys_addr, u8 input) { /* Check if input is sane */ if (WARN_ON(input == 0 || input > 0xf)) return CEC_PHYS_ADDR_INVALID; if (phys_addr == 0) return input << 12; if ((phys_addr & 0x0fff) == 0) return phys_addr | (input << 8); if ((phys_addr & 0x00ff) == 0) return phys_addr | (input << 4); if ((phys_addr & 0x000f) == 0) return phys_addr | input; /* * All nibbles are used so no valid physical addresses can be assigned * to the input. */ return CEC_PHYS_ADDR_INVALID; } EXPORT_SYMBOL_GPL(v4l2_phys_addr_for_input); /** * v4l2_phys_addr_validate() - validate a physical address from an EDID * * @phys_addr: the physical address to validate * @parent: if not %NULL, then this is filled with the parents PA. * @port: if not %NULL, then this is filled with the input port. * * This validates a physical address as read from an EDID. If the * PA is invalid (such as 1.0.1.0 since '0' is only allowed at the end), * then it will return -EINVAL. * * The parent PA is passed into %parent and the input port is passed into * %port. For example: * * PA = 0.0.0.0: has parent 0.0.0.0 and input port 0. * * PA = 1.0.0.0: has parent 0.0.0.0 and input port 1. * * PA = 3.2.0.0: has parent 3.0.0.0 and input port 2. * * PA = f.f.f.f: has parent f.f.f.f and input port 0. * * Return: 0 if the PA is valid, -EINVAL if not. */ int v4l2_phys_addr_validate(u16 phys_addr, u16 *parent, u16 *port) { int i; if (parent) *parent = phys_addr; if (port) *port = 0; if (phys_addr == CEC_PHYS_ADDR_INVALID) return 0; for (i = 0; i < 16; i += 4) if (phys_addr & (0xf << i)) break; if (i == 16) return 0; if (parent) *parent = phys_addr & (0xfff0 << i); if (port) *port = (phys_addr >> i) & 0xf; for (i += 4; i < 16; i += 4) if ((phys_addr & (0xf << i)) == 0) return -EINVAL; return 0; } EXPORT_SYMBOL_GPL(v4l2_phys_addr_validate); #ifdef CONFIG_DEBUG_FS #define DEBUGFS_FOPS(type, flag) \ static ssize_t \ infoframe_read_##type(struct file *filp, \ char __user *ubuf, size_t count, loff_t *ppos) \ { \ struct v4l2_debugfs_if *infoframes = filp->private_data; \ \ return infoframes->if_read((flag), infoframes->priv, filp, \ ubuf, count, ppos); \ } \ \ static const struct file_operations infoframe_##type##_fops = { \ .owner = THIS_MODULE, \ .open = simple_open, \ .read = infoframe_read_##type, \ } DEBUGFS_FOPS(avi, V4L2_DEBUGFS_IF_AVI); DEBUGFS_FOPS(audio, V4L2_DEBUGFS_IF_AUDIO); DEBUGFS_FOPS(spd, V4L2_DEBUGFS_IF_SPD); DEBUGFS_FOPS(hdmi, V4L2_DEBUGFS_IF_HDMI); struct v4l2_debugfs_if *v4l2_debugfs_if_alloc(struct dentry *root, u32 if_types, void *priv, v4l2_debugfs_if_read_t if_read) { struct v4l2_debugfs_if *infoframes; if (IS_ERR_OR_NULL(root) || !if_types || !if_read) return NULL; infoframes = kzalloc(sizeof(*infoframes), GFP_KERNEL); if (!infoframes) return NULL; infoframes->if_dir = debugfs_create_dir("infoframes", root); infoframes->priv = priv; infoframes->if_read = if_read; if (if_types & V4L2_DEBUGFS_IF_AVI) debugfs_create_file("avi", 0400, infoframes->if_dir, infoframes, &infoframe_avi_fops); if (if_types & V4L2_DEBUGFS_IF_AUDIO) debugfs_create_file("audio", 0400, infoframes->if_dir, infoframes, &infoframe_audio_fops); if (if_types & V4L2_DEBUGFS_IF_SPD) debugfs_create_file("spd", 0400, infoframes->if_dir, infoframes, &infoframe_spd_fops); if (if_types & V4L2_DEBUGFS_IF_HDMI) debugfs_create_file("hdmi", 0400, infoframes->if_dir, infoframes, &infoframe_hdmi_fops); return infoframes; } EXPORT_SYMBOL_GPL(v4l2_debugfs_if_alloc); void v4l2_debugfs_if_free(struct v4l2_debugfs_if *infoframes) { if (infoframes) { debugfs_remove_recursive(infoframes->if_dir); kfree(infoframes); } } EXPORT_SYMBOL_GPL(v4l2_debugfs_if_free); #endif |
| 19 1 1 1 1 1 1 1 20 20 20 2 2 2 20 20 19 20 20 20 4 1 1 1 1 19 19 19 19 18 19 14 19 8 9 8 8 20 18 19 19 19 10 19 19 1 19 13 19 20 20 19 1 20 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2005 Silicon Graphics, Inc. * Copyright (c) 2016-2025 Christoph Hellwig. * All Rights Reserved. */ #include "xfs.h" #include "xfs_shared.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_iomap.h" #include "xfs_trace.h" #include "xfs_bmap.h" #include "xfs_bmap_util.h" #include "xfs_reflink.h" #include "xfs_errortag.h" #include "xfs_error.h" #include "xfs_icache.h" #include "xfs_zone_alloc.h" #include "xfs_rtgroup.h" struct xfs_writepage_ctx { struct iomap_writepage_ctx ctx; unsigned int data_seq; unsigned int cow_seq; }; static inline struct xfs_writepage_ctx * XFS_WPC(struct iomap_writepage_ctx *ctx) { return container_of(ctx, struct xfs_writepage_ctx, ctx); } /* * Fast and loose check if this write could update the on-disk inode size. */ static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend) { return ioend->io_offset + ioend->io_size > XFS_I(ioend->io_inode)->i_disk_size; } /* * Update on-disk file size now that data has been written to disk. */ int xfs_setfilesize( struct xfs_inode *ip, xfs_off_t offset, size_t size) { struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp; xfs_fsize_t isize; int error; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp); if (error) return error; xfs_ilock(ip, XFS_ILOCK_EXCL); isize = xfs_new_eof(ip, offset + size); if (!isize) { xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_trans_cancel(tp); return 0; } trace_xfs_setfilesize(ip, offset, size); ip->i_disk_size = isize; xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); return xfs_trans_commit(tp); } static void xfs_ioend_put_open_zones( struct iomap_ioend *ioend) { struct iomap_ioend *tmp; /* * Put the open zone for all ioends merged into this one (if any). */ list_for_each_entry(tmp, &ioend->io_list, io_list) xfs_open_zone_put(tmp->io_private); /* * The main ioend might not have an open zone if the submission failed * before xfs_zone_alloc_and_submit got called. */ if (ioend->io_private) xfs_open_zone_put(ioend->io_private); } /* * IO write completion. */ STATIC void xfs_end_ioend( struct iomap_ioend *ioend) { struct xfs_inode *ip = XFS_I(ioend->io_inode); struct xfs_mount *mp = ip->i_mount; bool is_zoned = xfs_is_zoned_inode(ip); xfs_off_t offset = ioend->io_offset; size_t size = ioend->io_size; unsigned int nofs_flag; int error; /* * We can allocate memory here while doing writeback on behalf of * memory reclaim. To avoid memory allocation deadlocks set the * task-wide nofs context for the following operations. */ nofs_flag = memalloc_nofs_save(); /* * Just clean up the in-memory structures if the fs has been shut down. */ if (xfs_is_shutdown(mp)) { error = -EIO; goto done; } /* * Clean up all COW blocks and underlying data fork delalloc blocks on * I/O error. The delalloc punch is required because this ioend was * mapped to blocks in the COW fork and the associated pages are no * longer dirty. If we don't remove delalloc blocks here, they become * stale and can corrupt free space accounting on unmount. */ error = blk_status_to_errno(ioend->io_bio.bi_status); if (unlikely(error)) { if (ioend->io_flags & IOMAP_IOEND_SHARED) { ASSERT(!is_zoned); xfs_reflink_cancel_cow_range(ip, offset, size, true); xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, offset, offset + size, NULL); } goto done; } /* * Success: commit the COW or unwritten blocks if needed. */ if (is_zoned) error = xfs_zoned_end_io(ip, offset, size, ioend->io_sector, ioend->io_private, NULLFSBLOCK); else if (ioend->io_flags & IOMAP_IOEND_SHARED) error = xfs_reflink_end_cow(ip, offset, size); else if (ioend->io_flags & IOMAP_IOEND_UNWRITTEN) error = xfs_iomap_write_unwritten(ip, offset, size, false); if (!error && !(ioend->io_flags & IOMAP_IOEND_DIRECT) && xfs_ioend_is_append(ioend)) error = xfs_setfilesize(ip, offset, size); done: if (is_zoned) xfs_ioend_put_open_zones(ioend); iomap_finish_ioends(ioend, error); memalloc_nofs_restore(nofs_flag); } /* * Finish all pending IO completions that require transactional modifications. * * We try to merge physical and logically contiguous ioends before completion to * minimise the number of transactions we need to perform during IO completion. * Both unwritten extent conversion and COW remapping need to iterate and modify * one physical extent at a time, so we gain nothing by merging physically * discontiguous extents here. * * The ioend chain length that we can be processing here is largely unbound in * length and we may have to perform significant amounts of work on each ioend * to complete it. Hence we have to be careful about holding the CPU for too * long in this loop. */ void xfs_end_io( struct work_struct *work) { struct xfs_inode *ip = container_of(work, struct xfs_inode, i_ioend_work); struct iomap_ioend *ioend; struct list_head tmp; unsigned long flags; spin_lock_irqsave(&ip->i_ioend_lock, flags); list_replace_init(&ip->i_ioend_list, &tmp); spin_unlock_irqrestore(&ip->i_ioend_lock, flags); iomap_sort_ioends(&tmp); while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend, io_list))) { list_del_init(&ioend->io_list); iomap_ioend_try_merge(ioend, &tmp); xfs_end_ioend(ioend); cond_resched(); } } void xfs_end_bio( struct bio *bio) { struct iomap_ioend *ioend = iomap_ioend_from_bio(bio); struct xfs_inode *ip = XFS_I(ioend->io_inode); struct xfs_mount *mp = ip->i_mount; unsigned long flags; /* * For Appends record the actually written block number and set the * boundary flag if needed. */ if (IS_ENABLED(CONFIG_XFS_RT) && bio_is_zone_append(bio)) { ioend->io_sector = bio->bi_iter.bi_sector; xfs_mark_rtg_boundary(ioend); } spin_lock_irqsave(&ip->i_ioend_lock, flags); if (list_empty(&ip->i_ioend_list)) WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue, &ip->i_ioend_work)); list_add_tail(&ioend->io_list, &ip->i_ioend_list); spin_unlock_irqrestore(&ip->i_ioend_lock, flags); } /* * We cannot cancel the ioend directly on error. We may have already set other * pages under writeback and hence we have to run I/O completion to mark the * error state of the pages under writeback appropriately. * * If the folio has delalloc blocks on it, the caller is asking us to punch them * out. If we don't, we can leave a stale delalloc mapping covered by a clean * page that needs to be dirtied again before the delalloc mapping can be * converted. This stale delalloc mapping can trip up a later direct I/O read * operation on the same region. * * We prevent this by truncating away the delalloc regions on the folio. Because * they are delalloc, we can do this without needing a transaction. Indeed - if * we get ENOSPC errors, we have to be able to do this truncation without a * transaction as there is no space left for block reservation (typically why * we see a ENOSPC in writeback). */ static void xfs_discard_folio( struct folio *folio, loff_t pos) { struct xfs_inode *ip = XFS_I(folio->mapping->host); struct xfs_mount *mp = ip->i_mount; if (xfs_is_shutdown(mp)) return; xfs_alert_ratelimited(mp, "page discard on page "PTR_FMT", inode 0x%llx, pos %llu.", folio, ip->i_ino, pos); /* * The end of the punch range is always the offset of the first * byte of the next folio. Hence the end offset is only dependent on the * folio itself and not the start offset that is passed in. */ xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, pos, folio_pos(folio) + folio_size(folio), NULL); } /* * Fast revalidation of the cached writeback mapping. Return true if the current * mapping is valid, false otherwise. */ static bool xfs_imap_valid( struct iomap_writepage_ctx *wpc, struct xfs_inode *ip, loff_t offset) { if (offset < wpc->iomap.offset || offset >= wpc->iomap.offset + wpc->iomap.length) return false; /* * If this is a COW mapping, it is sufficient to check that the mapping * covers the offset. Be careful to check this first because the caller * can revalidate a COW mapping without updating the data seqno. */ if (wpc->iomap.flags & IOMAP_F_SHARED) return true; /* * This is not a COW mapping. Check the sequence number of the data fork * because concurrent changes could have invalidated the extent. Check * the COW fork because concurrent changes since the last time we * checked (and found nothing at this offset) could have added * overlapping blocks. */ if (XFS_WPC(wpc)->data_seq != READ_ONCE(ip->i_df.if_seq)) { trace_xfs_wb_data_iomap_invalid(ip, &wpc->iomap, XFS_WPC(wpc)->data_seq, XFS_DATA_FORK); return false; } if (xfs_inode_has_cow_data(ip) && XFS_WPC(wpc)->cow_seq != READ_ONCE(ip->i_cowfp->if_seq)) { trace_xfs_wb_cow_iomap_invalid(ip, &wpc->iomap, XFS_WPC(wpc)->cow_seq, XFS_COW_FORK); return false; } return true; } static int xfs_map_blocks( struct iomap_writepage_ctx *wpc, loff_t offset, unsigned int len) { struct xfs_inode *ip = XFS_I(wpc->inode); struct xfs_mount *mp = ip->i_mount; ssize_t count = i_blocksize(wpc->inode); xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + count); xfs_fileoff_t cow_fsb; int whichfork; struct xfs_bmbt_irec imap; struct xfs_iext_cursor icur; int retries = 0; int error = 0; unsigned int *seq; if (xfs_is_shutdown(mp)) return -EIO; XFS_ERRORTAG_DELAY(mp, XFS_ERRTAG_WB_DELAY_MS); /* * COW fork blocks can overlap data fork blocks even if the blocks * aren't shared. COW I/O always takes precedent, so we must always * check for overlap on reflink inodes unless the mapping is already a * COW one, or the COW fork hasn't changed from the last time we looked * at it. * * It's safe to check the COW fork if_seq here without the ILOCK because * we've indirectly protected against concurrent updates: writeback has * the page locked, which prevents concurrent invalidations by reflink * and directio and prevents concurrent buffered writes to the same * page. Changes to if_seq always happen under i_lock, which protects * against concurrent updates and provides a memory barrier on the way * out that ensures that we always see the current value. */ if (xfs_imap_valid(wpc, ip, offset)) return 0; /* * If we don't have a valid map, now it's time to get a new one for this * offset. This will convert delayed allocations (including COW ones) * into real extents. If we return without a valid map, it means we * landed in a hole and we skip the block. */ retry: cow_fsb = NULLFILEOFF; whichfork = XFS_DATA_FORK; xfs_ilock(ip, XFS_ILOCK_SHARED); ASSERT(!xfs_need_iread_extents(&ip->i_df)); /* * Check if this is offset is covered by a COW extents, and if yes use * it directly instead of looking up anything in the data fork. */ if (xfs_inode_has_cow_data(ip) && xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap)) cow_fsb = imap.br_startoff; if (cow_fsb != NULLFILEOFF && cow_fsb <= offset_fsb) { XFS_WPC(wpc)->cow_seq = READ_ONCE(ip->i_cowfp->if_seq); xfs_iunlock(ip, XFS_ILOCK_SHARED); whichfork = XFS_COW_FORK; goto allocate_blocks; } /* * No COW extent overlap. Revalidate now that we may have updated * ->cow_seq. If the data mapping is still valid, we're done. */ if (xfs_imap_valid(wpc, ip, offset)) { xfs_iunlock(ip, XFS_ILOCK_SHARED); return 0; } /* * If we don't have a valid map, now it's time to get a new one for this * offset. This will convert delayed allocations (including COW ones) * into real extents. */ if (!xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap)) imap.br_startoff = end_fsb; /* fake a hole past EOF */ XFS_WPC(wpc)->data_seq = READ_ONCE(ip->i_df.if_seq); xfs_iunlock(ip, XFS_ILOCK_SHARED); /* landed in a hole or beyond EOF? */ if (imap.br_startoff > offset_fsb) { imap.br_blockcount = imap.br_startoff - offset_fsb; imap.br_startoff = offset_fsb; imap.br_startblock = HOLESTARTBLOCK; imap.br_state = XFS_EXT_NORM; } /* * Truncate to the next COW extent if there is one. This is the only * opportunity to do this because we can skip COW fork lookups for the * subsequent blocks in the mapping; however, the requirement to treat * the COW range separately remains. */ if (cow_fsb != NULLFILEOFF && cow_fsb < imap.br_startoff + imap.br_blockcount) imap.br_blockcount = cow_fsb - imap.br_startoff; /* got a delalloc extent? */ if (imap.br_startblock != HOLESTARTBLOCK && isnullstartblock(imap.br_startblock)) goto allocate_blocks; xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, 0, XFS_WPC(wpc)->data_seq); trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap); return 0; allocate_blocks: /* * Convert a dellalloc extent to a real one. The current page is held * locked so nothing could have removed the block backing offset_fsb, * although it could have moved from the COW to the data fork by another * thread. */ if (whichfork == XFS_COW_FORK) seq = &XFS_WPC(wpc)->cow_seq; else seq = &XFS_WPC(wpc)->data_seq; error = xfs_bmapi_convert_delalloc(ip, whichfork, offset, &wpc->iomap, seq); if (error) { /* * If we failed to find the extent in the COW fork we might have * raced with a COW to data fork conversion or truncate. * Restart the lookup to catch the extent in the data fork for * the former case, but prevent additional retries to avoid * looping forever for the latter case. */ if (error == -EAGAIN && whichfork == XFS_COW_FORK && !retries++) goto retry; ASSERT(error != -EAGAIN); return error; } /* * Due to merging the return real extent might be larger than the * original delalloc one. Trim the return extent to the next COW * boundary again to force a re-lookup. */ if (whichfork != XFS_COW_FORK && cow_fsb != NULLFILEOFF) { loff_t cow_offset = XFS_FSB_TO_B(mp, cow_fsb); if (cow_offset < wpc->iomap.offset + wpc->iomap.length) wpc->iomap.length = cow_offset - wpc->iomap.offset; } ASSERT(wpc->iomap.offset <= offset); ASSERT(wpc->iomap.offset + wpc->iomap.length > offset); trace_xfs_map_blocks_alloc(ip, offset, count, whichfork, &imap); return 0; } static ssize_t xfs_writeback_range( struct iomap_writepage_ctx *wpc, struct folio *folio, u64 offset, unsigned int len, u64 end_pos) { ssize_t ret; ret = xfs_map_blocks(wpc, offset, len); if (!ret) ret = iomap_add_to_ioend(wpc, folio, offset, end_pos, len); if (ret < 0) xfs_discard_folio(folio, offset); return ret; } static bool xfs_ioend_needs_wq_completion( struct iomap_ioend *ioend) { /* Changing inode size requires a transaction. */ if (xfs_ioend_is_append(ioend)) return true; /* Extent manipulation requires a transaction. */ if (ioend->io_flags & (IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_SHARED)) return true; /* Page cache invalidation cannot be done in irq context. */ if (ioend->io_flags & IOMAP_IOEND_DONTCACHE) return true; return false; } static int xfs_writeback_submit( struct iomap_writepage_ctx *wpc, int error) { struct iomap_ioend *ioend = wpc->wb_ctx; /* * Convert CoW extents to regular. * * We can allocate memory here while doing writeback on behalf of memory * reclaim. To avoid memory allocation deadlocks, set the task-wide * nofs context. */ if (!error && (ioend->io_flags & IOMAP_IOEND_SHARED)) { unsigned int nofs_flag; nofs_flag = memalloc_nofs_save(); error = xfs_reflink_convert_cow(XFS_I(ioend->io_inode), ioend->io_offset, ioend->io_size); memalloc_nofs_restore(nofs_flag); } /* * Send ioends that might require a transaction to the completion wq. */ if (xfs_ioend_needs_wq_completion(ioend)) ioend->io_bio.bi_end_io = xfs_end_bio; return iomap_ioend_writeback_submit(wpc, error); } static const struct iomap_writeback_ops xfs_writeback_ops = { .writeback_range = xfs_writeback_range, .writeback_submit = xfs_writeback_submit, }; struct xfs_zoned_writepage_ctx { struct iomap_writepage_ctx ctx; struct xfs_open_zone *open_zone; }; static inline struct xfs_zoned_writepage_ctx * XFS_ZWPC(struct iomap_writepage_ctx *ctx) { return container_of(ctx, struct xfs_zoned_writepage_ctx, ctx); } static int xfs_zoned_map_blocks( struct iomap_writepage_ctx *wpc, loff_t offset, unsigned int len) { struct xfs_inode *ip = XFS_I(wpc->inode); struct xfs_mount *mp = ip->i_mount; xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + len); xfs_filblks_t count_fsb; struct xfs_bmbt_irec imap, del; struct xfs_iext_cursor icur; if (xfs_is_shutdown(mp)) return -EIO; XFS_ERRORTAG_DELAY(mp, XFS_ERRTAG_WB_DELAY_MS); /* * All dirty data must be covered by delalloc extents. But truncate can * remove delalloc extents underneath us or reduce their size. * Returning a hole tells iomap to not write back any data from this * range, which is the right thing to do in that case. * * Otherwise just tell iomap to treat ranges previously covered by a * delalloc extent as mapped. The actual block allocation will be done * just before submitting the bio. * * This implies we never map outside folios that are locked or marked * as under writeback, and thus there is no need check the fork sequence * count here. */ xfs_ilock(ip, XFS_ILOCK_EXCL); if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap)) imap.br_startoff = end_fsb; /* fake a hole past EOF */ if (imap.br_startoff > offset_fsb) { imap.br_blockcount = imap.br_startoff - offset_fsb; imap.br_startoff = offset_fsb; imap.br_startblock = HOLESTARTBLOCK; imap.br_state = XFS_EXT_NORM; xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, 0, 0); return 0; } end_fsb = min(end_fsb, imap.br_startoff + imap.br_blockcount); count_fsb = end_fsb - offset_fsb; del = imap; xfs_trim_extent(&del, offset_fsb, count_fsb); xfs_bmap_del_extent_delay(ip, XFS_COW_FORK, &icur, &imap, &del, XFS_BMAPI_REMAP); xfs_iunlock(ip, XFS_ILOCK_EXCL); wpc->iomap.type = IOMAP_MAPPED; wpc->iomap.flags = IOMAP_F_DIRTY; wpc->iomap.bdev = mp->m_rtdev_targp->bt_bdev; wpc->iomap.offset = offset; wpc->iomap.length = XFS_FSB_TO_B(mp, count_fsb); wpc->iomap.flags = IOMAP_F_ANON_WRITE; trace_xfs_zoned_map_blocks(ip, offset, wpc->iomap.length); return 0; } static ssize_t xfs_zoned_writeback_range( struct iomap_writepage_ctx *wpc, struct folio *folio, u64 offset, unsigned int len, u64 end_pos) { ssize_t ret; ret = xfs_zoned_map_blocks(wpc, offset, len); if (!ret) ret = iomap_add_to_ioend(wpc, folio, offset, end_pos, len); if (ret < 0) xfs_discard_folio(folio, offset); return ret; } static int xfs_zoned_writeback_submit( struct iomap_writepage_ctx *wpc, int error) { struct iomap_ioend *ioend = wpc->wb_ctx; ioend->io_bio.bi_end_io = xfs_end_bio; if (error) { ioend->io_bio.bi_status = errno_to_blk_status(error); bio_endio(&ioend->io_bio); return error; } xfs_zone_alloc_and_submit(ioend, &XFS_ZWPC(wpc)->open_zone); return 0; } static const struct iomap_writeback_ops xfs_zoned_writeback_ops = { .writeback_range = xfs_zoned_writeback_range, .writeback_submit = xfs_zoned_writeback_submit, }; STATIC int xfs_vm_writepages( struct address_space *mapping, struct writeback_control *wbc) { struct xfs_inode *ip = XFS_I(mapping->host); xfs_iflags_clear(ip, XFS_ITRUNCATED); if (xfs_is_zoned_inode(ip)) { struct xfs_zoned_writepage_ctx xc = { .ctx = { .inode = mapping->host, .wbc = wbc, .ops = &xfs_zoned_writeback_ops }, }; int error; error = iomap_writepages(&xc.ctx); if (xc.open_zone) xfs_open_zone_put(xc.open_zone); return error; } else { struct xfs_writepage_ctx wpc = { .ctx = { .inode = mapping->host, .wbc = wbc, .ops = &xfs_writeback_ops }, }; return iomap_writepages(&wpc.ctx); } } STATIC int xfs_dax_writepages( struct address_space *mapping, struct writeback_control *wbc) { struct xfs_inode *ip = XFS_I(mapping->host); xfs_iflags_clear(ip, XFS_ITRUNCATED); return dax_writeback_mapping_range(mapping, xfs_inode_buftarg(ip)->bt_daxdev, wbc); } STATIC sector_t xfs_vm_bmap( struct address_space *mapping, sector_t block) { struct xfs_inode *ip = XFS_I(mapping->host); trace_xfs_vm_bmap(ip); /* * The swap code (ab-)uses ->bmap to get a block mapping and then * bypasses the file system for actual I/O. We really can't allow * that on reflinks inodes, so we have to skip out here. And yes, * 0 is the magic code for a bmap error. * * Since we don't pass back blockdev info, we can't return bmap * information for rt files either. */ if (xfs_is_cow_inode(ip) || XFS_IS_REALTIME_INODE(ip)) return 0; return iomap_bmap(mapping, block, &xfs_read_iomap_ops); } STATIC int xfs_vm_read_folio( struct file *unused, struct folio *folio) { return iomap_read_folio(folio, &xfs_read_iomap_ops); } STATIC void xfs_vm_readahead( struct readahead_control *rac) { iomap_readahead(rac, &xfs_read_iomap_ops); } static int xfs_vm_swap_activate( struct swap_info_struct *sis, struct file *swap_file, sector_t *span) { struct xfs_inode *ip = XFS_I(file_inode(swap_file)); /* * Swap file activation can race against concurrent shared extent * removal in files that have been cloned. If this happens, * iomap_swapfile_iter() can fail because it encountered a shared * extent even though an operation is in progress to remove those * shared extents. * * This race becomes problematic when we defer extent removal * operations beyond the end of a syscall (i.e. use async background * processing algorithms). Users think the extents are no longer * shared, but iomap_swapfile_iter() still sees them as shared * because the refcountbt entries for the extents being removed have * not yet been updated. Hence the swapon call fails unexpectedly. * * The race condition is currently most obvious from the unlink() * operation as extent removal is deferred until after the last * reference to the inode goes away. We then process the extent * removal asynchronously, hence triggers the "syscall completed but * work not done" condition mentioned above. To close this race * window, we need to flush any pending inodegc operations to ensure * they have updated the refcountbt records before we try to map the * swapfile. */ xfs_inodegc_flush(ip->i_mount); /* * Direct the swap code to the correct block device when this file * sits on the RT device. */ sis->bdev = xfs_inode_buftarg(ip)->bt_bdev; return iomap_swapfile_activate(sis, swap_file, span, &xfs_read_iomap_ops); } const struct address_space_operations xfs_address_space_operations = { .read_folio = xfs_vm_read_folio, .readahead = xfs_vm_readahead, .writepages = xfs_vm_writepages, .dirty_folio = iomap_dirty_folio, .release_folio = iomap_release_folio, .invalidate_folio = iomap_invalidate_folio, .bmap = xfs_vm_bmap, .migrate_folio = filemap_migrate_folio, .is_partially_uptodate = iomap_is_partially_uptodate, .error_remove_folio = generic_error_remove_folio, .swap_activate = xfs_vm_swap_activate, }; const struct address_space_operations xfs_dax_aops = { .writepages = xfs_dax_writepages, .dirty_folio = noop_dirty_folio, .swap_activate = xfs_vm_swap_activate, }; |
| 22 261 262 261 251 261 261 134 133 134 134 134 176 2 188 4 4 4 4 4 3 4 4 226 225 227 82 82 85 189 187 188 9 188 189 177 177 169 185 186 186 2 186 177 176 172 183 185 185 185 183 185 185 185 180 180 180 178 175 184 16 174 175 175 178 181 177 174 170 174 166 167 6 174 171 170 169 3 2 175 173 171 176 176 168 167 175 175 176 177 187 188 171 190 170 190 175 187 185 178 7 17 16 9 8 165 165 180 180 179 82 71 205 29 29 29 164 165 164 164 164 165 163 164 164 165 165 163 163 185 184 185 172 156 60 157 170 170 170 170 168 169 4 169 169 165 165 163 67 66 163 98 165 165 165 164 163 165 164 66 67 67 165 25 165 163 5 3 5 167 169 11 2 1 2 46 19 46 19 2 2 2 2 1 1 1 1 2 169 169 169 169 168 167 3 168 168 1 167 166 166 166 3 165 164 3 4 3 4 7 7 7 12 24 36 10 11 11 7 7 11 9 5 6 3 2 3 2 2 2 9 9 9 3 7 6 4 7 8 7 6 6 8 2 2 2 1 1 2 3 2 3 127 128 128 128 128 166 160 160 3 13 28 153 153 153 153 153 153 32 32 137 136 137 137 82 82 44 80 84 82 82 82 25 3 25 80 44 42 82 56 30 91 90 89 91 91 91 89 71 71 91 89 5 1 1 1 1 1 2 2 2 1 3 3 134 134 133 134 134 134 2 2 2 2 1 3 135 133 133 135 132 133 133 133 134 1 134 135 134 134 30 30 30 30 30 17 2 2 15 13 30 15 13 30 31 30 2 28 30 30 30 30 28 28 27 28 28 28 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 30 182 166 181 79 79 79 79 3 3 2 2 4 6 6 1 1 1 1 1 170 173 171 172 169 171 170 170 171 4 171 169 168 170 169 170 169 170 170 169 165 172 172 171 170 170 171 172 86 86 86 86 86 86 86 86 86 86 85 86 86 86 86 86 86 86 86 86 86 86 86 85 86 86 86 23 86 86 86 85 23 86 85 86 86 86 86 86 86 86 86 86 86 86 5 46 50 50 50 45 49 49 43 49 48 49 95 88 2 95 86 86 86 86 25 86 34 27 27 25 27 24 24 24 24 10 10 10 10 34 34 33 34 34 3 2 1 7 7 7 34 6 6 6 5 6 6 6 46 6 24 46 2 2 1 2 2 1 1 1 4 3 2 2 2 3 1 4 3 3 2 2 3 2 41 40 38 33 41 41 2 4 4 4 3 2 1 2 2 2 2 1 15 5 2 2 2 5 6 6 1 5 5 5 1 4 1 4 4 3 4 2 1 1 1 1 1 1 2 1 2 2 2 2 1 1 1 4 4 4 7 4 4 4 4 8 102 103 104 102 102 102 1 1 3 2 17 12 2 7 1 7 1 6 3 1 3 1 7 1 1 2 1 2 1 6 9 4 27 3 2 1 1 15 4 8 1 105 105 185 186 165 165 134 29 28 171 37 1 1 1 1 3 3 3 2 2 2 2 2 2 2 2 3 3 3 3 3 1 1 1 12 12 12 12 12 12 12 12 2 10 1 1 1 3 2 1 1 9 1 1 1 3 2 1 1 3 3 3 3 3 2 1 3 3 2 1 1 1 2 2 3 7 1 7 7 12 5 7 11 9 9 8 7 7 7 12 7 9 9 9 9 2 3 9 2 3 3 3 4 4 4 4 7 3 4 4 4 3 27 7 4 4 1 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Digital Audio (PCM) abstract layer * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/compat.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/file.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/time.h> #include <linux/pm_qos.h> #include <linux/io.h> #include <linux/dma-mapping.h> #include <linux/vmalloc.h> #include <sound/core.h> #include <sound/control.h> #include <sound/info.h> #include <sound/pcm.h> #include <sound/pcm_params.h> #include <sound/timer.h> #include <sound/minors.h> #include <linux/uio.h> #include <linux/delay.h> #include <linux/bitops.h> #include "pcm_local.h" #ifdef CONFIG_SND_DEBUG #define CREATE_TRACE_POINTS #include "pcm_param_trace.h" #else #define trace_hw_mask_param_enabled() 0 #define trace_hw_interval_param_enabled() 0 #define trace_hw_mask_param(substream, type, index, prev, curr) #define trace_hw_interval_param(substream, type, index, prev, curr) #endif /* * Compatibility */ struct snd_pcm_hw_params_old { unsigned int flags; unsigned int masks[SNDRV_PCM_HW_PARAM_SUBFORMAT - SNDRV_PCM_HW_PARAM_ACCESS + 1]; struct snd_interval intervals[SNDRV_PCM_HW_PARAM_TICK_TIME - SNDRV_PCM_HW_PARAM_SAMPLE_BITS + 1]; unsigned int rmask; unsigned int cmask; unsigned int info; unsigned int msbits; unsigned int rate_num; unsigned int rate_den; snd_pcm_uframes_t fifo_size; unsigned char reserved[64]; }; #ifdef CONFIG_SND_SUPPORT_OLD_API #define SNDRV_PCM_IOCTL_HW_REFINE_OLD _IOWR('A', 0x10, struct snd_pcm_hw_params_old) #define SNDRV_PCM_IOCTL_HW_PARAMS_OLD _IOWR('A', 0x11, struct snd_pcm_hw_params_old) static int snd_pcm_hw_refine_old_user(struct snd_pcm_substream *substream, struct snd_pcm_hw_params_old __user * _oparams); static int snd_pcm_hw_params_old_user(struct snd_pcm_substream *substream, struct snd_pcm_hw_params_old __user * _oparams); #endif static int snd_pcm_open(struct file *file, struct snd_pcm *pcm, int stream); /* * */ static DECLARE_RWSEM(snd_pcm_link_rwsem); void snd_pcm_group_init(struct snd_pcm_group *group) { spin_lock_init(&group->lock); mutex_init(&group->mutex); INIT_LIST_HEAD(&group->substreams); refcount_set(&group->refs, 1); } /* define group lock helpers */ #define DEFINE_PCM_GROUP_LOCK(action, mutex_action) \ static void snd_pcm_group_ ## action(struct snd_pcm_group *group, bool nonatomic) \ { \ if (nonatomic) \ mutex_ ## mutex_action(&group->mutex); \ else \ spin_ ## action(&group->lock); \ } DEFINE_PCM_GROUP_LOCK(lock, lock); DEFINE_PCM_GROUP_LOCK(unlock, unlock); DEFINE_PCM_GROUP_LOCK(lock_irq, lock); DEFINE_PCM_GROUP_LOCK(unlock_irq, unlock); /** * snd_pcm_stream_lock - Lock the PCM stream * @substream: PCM substream * * This locks the PCM stream's spinlock or mutex depending on the nonatomic * flag of the given substream. This also takes the global link rw lock * (or rw sem), too, for avoiding the race with linked streams. */ void snd_pcm_stream_lock(struct snd_pcm_substream *substream) { snd_pcm_group_lock(&substream->self_group, substream->pcm->nonatomic); } EXPORT_SYMBOL_GPL(snd_pcm_stream_lock); /** * snd_pcm_stream_unlock - Unlock the PCM stream * @substream: PCM substream * * This unlocks the PCM stream that has been locked via snd_pcm_stream_lock(). */ void snd_pcm_stream_unlock(struct snd_pcm_substream *substream) { snd_pcm_group_unlock(&substream->self_group, substream->pcm->nonatomic); } EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock); /** * snd_pcm_stream_lock_irq - Lock the PCM stream * @substream: PCM substream * * This locks the PCM stream like snd_pcm_stream_lock() and disables the local * IRQ (only when nonatomic is false). In nonatomic case, this is identical * as snd_pcm_stream_lock(). */ void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream) { snd_pcm_group_lock_irq(&substream->self_group, substream->pcm->nonatomic); } EXPORT_SYMBOL_GPL(snd_pcm_stream_lock_irq); static void snd_pcm_stream_lock_nested(struct snd_pcm_substream *substream) { struct snd_pcm_group *group = &substream->self_group; if (substream->pcm->nonatomic) mutex_lock_nested(&group->mutex, SINGLE_DEPTH_NESTING); else spin_lock_nested(&group->lock, SINGLE_DEPTH_NESTING); } /** * snd_pcm_stream_unlock_irq - Unlock the PCM stream * @substream: PCM substream * * This is a counter-part of snd_pcm_stream_lock_irq(). */ void snd_pcm_stream_unlock_irq(struct snd_pcm_substream *substream) { snd_pcm_group_unlock_irq(&substream->self_group, substream->pcm->nonatomic); } EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irq); unsigned long _snd_pcm_stream_lock_irqsave(struct snd_pcm_substream *substream) { unsigned long flags = 0; if (substream->pcm->nonatomic) mutex_lock(&substream->self_group.mutex); else spin_lock_irqsave(&substream->self_group.lock, flags); return flags; } EXPORT_SYMBOL_GPL(_snd_pcm_stream_lock_irqsave); unsigned long _snd_pcm_stream_lock_irqsave_nested(struct snd_pcm_substream *substream) { unsigned long flags = 0; if (substream->pcm->nonatomic) mutex_lock_nested(&substream->self_group.mutex, SINGLE_DEPTH_NESTING); else spin_lock_irqsave_nested(&substream->self_group.lock, flags, SINGLE_DEPTH_NESTING); return flags; } EXPORT_SYMBOL_GPL(_snd_pcm_stream_lock_irqsave_nested); /** * snd_pcm_stream_unlock_irqrestore - Unlock the PCM stream * @substream: PCM substream * @flags: irq flags * * This is a counter-part of snd_pcm_stream_lock_irqsave(). */ void snd_pcm_stream_unlock_irqrestore(struct snd_pcm_substream *substream, unsigned long flags) { if (substream->pcm->nonatomic) mutex_unlock(&substream->self_group.mutex); else spin_unlock_irqrestore(&substream->self_group.lock, flags); } EXPORT_SYMBOL_GPL(snd_pcm_stream_unlock_irqrestore); /* Run PCM ioctl ops */ static int snd_pcm_ops_ioctl(struct snd_pcm_substream *substream, unsigned cmd, void *arg) { if (substream->ops->ioctl) return substream->ops->ioctl(substream, cmd, arg); else return snd_pcm_lib_ioctl(substream, cmd, arg); } int snd_pcm_info(struct snd_pcm_substream *substream, struct snd_pcm_info *info) { struct snd_pcm *pcm = substream->pcm; struct snd_pcm_str *pstr = substream->pstr; memset(info, 0, sizeof(*info)); info->card = pcm->card->number; info->device = pcm->device; info->stream = substream->stream; info->subdevice = substream->number; strscpy(info->id, pcm->id, sizeof(info->id)); strscpy(info->name, pcm->name, sizeof(info->name)); info->dev_class = pcm->dev_class; info->dev_subclass = pcm->dev_subclass; info->subdevices_count = pstr->substream_count; info->subdevices_avail = pstr->substream_count - pstr->substream_opened; strscpy(info->subname, substream->name, sizeof(info->subname)); return 0; } int snd_pcm_info_user(struct snd_pcm_substream *substream, struct snd_pcm_info __user * _info) { struct snd_pcm_info *info __free(kfree) = NULL; int err; info = kmalloc(sizeof(*info), GFP_KERNEL); if (! info) return -ENOMEM; err = snd_pcm_info(substream, info); if (err >= 0) { if (copy_to_user(_info, info, sizeof(*info))) err = -EFAULT; } return err; } /* macro for simplified cast */ #define PARAM_MASK_BIT(b) (1U << (__force int)(b)) static bool hw_support_mmap(struct snd_pcm_substream *substream) { struct snd_dma_buffer *dmabuf; if (!(substream->runtime->hw.info & SNDRV_PCM_INFO_MMAP)) return false; if (substream->ops->mmap || substream->ops->page) return true; dmabuf = snd_pcm_get_dma_buf(substream); if (!dmabuf) dmabuf = &substream->dma_buffer; switch (dmabuf->dev.type) { case SNDRV_DMA_TYPE_UNKNOWN: /* we can't know the device, so just assume that the driver does * everything right */ return true; case SNDRV_DMA_TYPE_CONTINUOUS: case SNDRV_DMA_TYPE_VMALLOC: return true; default: return dma_can_mmap(dmabuf->dev.dev); } } static int constrain_mask_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params) { struct snd_pcm_hw_constraints *constrs = &substream->runtime->hw_constraints; struct snd_mask *m; unsigned int k; struct snd_mask old_mask __maybe_unused; int changed; for (k = SNDRV_PCM_HW_PARAM_FIRST_MASK; k <= SNDRV_PCM_HW_PARAM_LAST_MASK; k++) { m = hw_param_mask(params, k); if (snd_mask_empty(m)) return -EINVAL; /* This parameter is not requested to change by a caller. */ if (!(params->rmask & PARAM_MASK_BIT(k))) continue; if (trace_hw_mask_param_enabled()) old_mask = *m; changed = snd_mask_refine(m, constrs_mask(constrs, k)); if (changed < 0) return changed; if (changed == 0) continue; /* Set corresponding flag so that the caller gets it. */ trace_hw_mask_param(substream, k, 0, &old_mask, m); params->cmask |= PARAM_MASK_BIT(k); } return 0; } static int constrain_interval_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params) { struct snd_pcm_hw_constraints *constrs = &substream->runtime->hw_constraints; struct snd_interval *i; unsigned int k; struct snd_interval old_interval __maybe_unused; int changed; for (k = SNDRV_PCM_HW_PARAM_FIRST_INTERVAL; k <= SNDRV_PCM_HW_PARAM_LAST_INTERVAL; k++) { i = hw_param_interval(params, k); if (snd_interval_empty(i)) return -EINVAL; /* This parameter is not requested to change by a caller. */ if (!(params->rmask & PARAM_MASK_BIT(k))) continue; if (trace_hw_interval_param_enabled()) old_interval = *i; changed = snd_interval_refine(i, constrs_interval(constrs, k)); if (changed < 0) return changed; if (changed == 0) continue; /* Set corresponding flag so that the caller gets it. */ trace_hw_interval_param(substream, k, 0, &old_interval, i); params->cmask |= PARAM_MASK_BIT(k); } return 0; } static int constrain_params_by_rules(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params) { struct snd_pcm_hw_constraints *constrs = &substream->runtime->hw_constraints; unsigned int k; unsigned int *rstamps __free(kfree) = NULL; unsigned int vstamps[SNDRV_PCM_HW_PARAM_LAST_INTERVAL + 1]; unsigned int stamp; struct snd_pcm_hw_rule *r; unsigned int d; struct snd_mask old_mask __maybe_unused; struct snd_interval old_interval __maybe_unused; bool again; int changed, err = 0; /* * Each application of rule has own sequence number. * * Each member of 'rstamps' array represents the sequence number of * recent application of corresponding rule. */ rstamps = kcalloc(constrs->rules_num, sizeof(unsigned int), GFP_KERNEL); if (!rstamps) return -ENOMEM; /* * Each member of 'vstamps' array represents the sequence number of * recent application of rule in which corresponding parameters were * changed. * * In initial state, elements corresponding to parameters requested by * a caller is 1. For unrequested parameters, corresponding members * have 0 so that the parameters are never changed anymore. */ for (k = 0; k <= SNDRV_PCM_HW_PARAM_LAST_INTERVAL; k++) vstamps[k] = (params->rmask & PARAM_MASK_BIT(k)) ? 1 : 0; /* Due to the above design, actual sequence number starts at 2. */ stamp = 2; retry: /* Apply all rules in order. */ again = false; for (k = 0; k < constrs->rules_num; k++) { r = &constrs->rules[k]; /* * Check condition bits of this rule. When the rule has * some condition bits, parameter without the bits is * never processed. SNDRV_PCM_HW_PARAMS_NO_PERIOD_WAKEUP * is an example of the condition bits. */ if (r->cond && !(r->cond & params->flags)) continue; /* * The 'deps' array includes maximum four dependencies * to SNDRV_PCM_HW_PARAM_XXXs for this rule. The fifth * member of this array is a sentinel and should be * negative value. * * This rule should be processed in this time when dependent * parameters were changed at former applications of the other * rules. */ for (d = 0; r->deps[d] >= 0; d++) { if (vstamps[r->deps[d]] > rstamps[k]) break; } if (r->deps[d] < 0) continue; if (trace_hw_mask_param_enabled()) { if (hw_is_mask(r->var)) old_mask = *hw_param_mask(params, r->var); } if (trace_hw_interval_param_enabled()) { if (hw_is_interval(r->var)) old_interval = *hw_param_interval(params, r->var); } changed = r->func(params, r); if (changed < 0) return changed; /* * When the parameter is changed, notify it to the caller * by corresponding returned bit, then preparing for next * iteration. */ if (changed && r->var >= 0) { if (hw_is_mask(r->var)) { trace_hw_mask_param(substream, r->var, k + 1, &old_mask, hw_param_mask(params, r->var)); } if (hw_is_interval(r->var)) { trace_hw_interval_param(substream, r->var, k + 1, &old_interval, hw_param_interval(params, r->var)); } params->cmask |= PARAM_MASK_BIT(r->var); vstamps[r->var] = stamp; again = true; } rstamps[k] = stamp++; } /* Iterate to evaluate all rules till no parameters are changed. */ if (again) goto retry; return err; } static int fixup_unreferenced_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params) { const struct snd_interval *i; const struct snd_mask *m; struct snd_mask *m_rw; int err; if (!params->msbits) { i = hw_param_interval_c(params, SNDRV_PCM_HW_PARAM_SAMPLE_BITS); if (snd_interval_single(i)) params->msbits = snd_interval_value(i); m = hw_param_mask_c(params, SNDRV_PCM_HW_PARAM_FORMAT); if (snd_mask_single(m)) { snd_pcm_format_t format = (__force snd_pcm_format_t)snd_mask_min(m); params->msbits = snd_pcm_format_width(format); } } if (params->msbits) { m = hw_param_mask_c(params, SNDRV_PCM_HW_PARAM_FORMAT); if (snd_mask_single(m)) { snd_pcm_format_t format = (__force snd_pcm_format_t)snd_mask_min(m); if (snd_pcm_format_linear(format) && snd_pcm_format_width(format) != params->msbits) { m_rw = hw_param_mask(params, SNDRV_PCM_HW_PARAM_SUBFORMAT); snd_mask_reset(m_rw, (__force unsigned)SNDRV_PCM_SUBFORMAT_MSBITS_MAX); if (snd_mask_empty(m_rw)) return -EINVAL; } } } if (!params->rate_den) { i = hw_param_interval_c(params, SNDRV_PCM_HW_PARAM_RATE); if (snd_interval_single(i)) { params->rate_num = snd_interval_value(i); params->rate_den = 1; } } if (!params->fifo_size) { m = hw_param_mask_c(params, SNDRV_PCM_HW_PARAM_FORMAT); i = hw_param_interval_c(params, SNDRV_PCM_HW_PARAM_CHANNELS); if (snd_mask_single(m) && snd_interval_single(i)) { err = snd_pcm_ops_ioctl(substream, SNDRV_PCM_IOCTL1_FIFO_SIZE, params); if (err < 0) return err; } } if (!params->info) { params->info = substream->runtime->hw.info; params->info &= ~(SNDRV_PCM_INFO_FIFO_IN_FRAMES | SNDRV_PCM_INFO_DRAIN_TRIGGER); if (!hw_support_mmap(substream)) params->info &= ~(SNDRV_PCM_INFO_MMAP | SNDRV_PCM_INFO_MMAP_VALID); } err = snd_pcm_ops_ioctl(substream, SNDRV_PCM_IOCTL1_SYNC_ID, params); if (err < 0) return err; return 0; } int snd_pcm_hw_refine(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params) { int err; params->info = 0; params->fifo_size = 0; if (params->rmask & PARAM_MASK_BIT(SNDRV_PCM_HW_PARAM_SAMPLE_BITS)) params->msbits = 0; if (params->rmask & PARAM_MASK_BIT(SNDRV_PCM_HW_PARAM_RATE)) { params->rate_num = 0; params->rate_den = 0; } err = constrain_mask_params(substream, params); if (err < 0) return err; err = constrain_interval_params(substream, params); if (err < 0) return err; err = constrain_params_by_rules(substream, params); if (err < 0) return err; params->rmask = 0; return 0; } EXPORT_SYMBOL(snd_pcm_hw_refine); static int snd_pcm_hw_refine_user(struct snd_pcm_substream *substream, struct snd_pcm_hw_params __user * _params) { struct snd_pcm_hw_params *params __free(kfree) = NULL; int err; params = memdup_user(_params, sizeof(*params)); if (IS_ERR(params)) return PTR_ERR(params); err = snd_pcm_hw_refine(substream, params); if (err < 0) return err; err = fixup_unreferenced_params(substream, params); if (err < 0) return err; if (copy_to_user(_params, params, sizeof(*params))) return -EFAULT; return 0; } static int period_to_usecs(struct snd_pcm_runtime *runtime) { int usecs; if (! runtime->rate) return -1; /* invalid */ /* take 75% of period time as the deadline */ usecs = (750000 / runtime->rate) * runtime->period_size; usecs += ((750000 % runtime->rate) * runtime->period_size) / runtime->rate; return usecs; } static void snd_pcm_set_state(struct snd_pcm_substream *substream, snd_pcm_state_t state) { guard(pcm_stream_lock_irq)(substream); if (substream->runtime->state != SNDRV_PCM_STATE_DISCONNECTED) __snd_pcm_set_state(substream->runtime, state); } static inline void snd_pcm_timer_notify(struct snd_pcm_substream *substream, int event) { #ifdef CONFIG_SND_PCM_TIMER if (substream->timer) snd_timer_notify(substream->timer, event, &substream->runtime->trigger_tstamp); #endif } void snd_pcm_sync_stop(struct snd_pcm_substream *substream, bool sync_irq) { if (substream->runtime && substream->runtime->stop_operating) { substream->runtime->stop_operating = false; if (substream->ops && substream->ops->sync_stop) substream->ops->sync_stop(substream); else if (sync_irq && substream->pcm->card->sync_irq > 0) synchronize_irq(substream->pcm->card->sync_irq); } } /** * snd_pcm_hw_params_choose - choose a configuration defined by @params * @pcm: PCM instance * @params: the hw_params instance * * Choose one configuration from configuration space defined by @params. * The configuration chosen is that obtained fixing in this order: * first access, first format, first subformat, min channels, * min rate, min period time, max buffer size, min tick time * * Return: Zero if successful, or a negative error code on failure. */ static int snd_pcm_hw_params_choose(struct snd_pcm_substream *pcm, struct snd_pcm_hw_params *params) { static const int vars[] = { SNDRV_PCM_HW_PARAM_ACCESS, SNDRV_PCM_HW_PARAM_FORMAT, SNDRV_PCM_HW_PARAM_SUBFORMAT, SNDRV_PCM_HW_PARAM_CHANNELS, SNDRV_PCM_HW_PARAM_RATE, SNDRV_PCM_HW_PARAM_PERIOD_TIME, SNDRV_PCM_HW_PARAM_BUFFER_SIZE, SNDRV_PCM_HW_PARAM_TICK_TIME, -1 }; const int *v; struct snd_mask old_mask __maybe_unused; struct snd_interval old_interval __maybe_unused; int changed; for (v = vars; *v != -1; v++) { /* Keep old parameter to trace. */ if (trace_hw_mask_param_enabled()) { if (hw_is_mask(*v)) old_mask = *hw_param_mask(params, *v); } if (trace_hw_interval_param_enabled()) { if (hw_is_interval(*v)) old_interval = *hw_param_interval(params, *v); } if (*v != SNDRV_PCM_HW_PARAM_BUFFER_SIZE) changed = snd_pcm_hw_param_first(pcm, params, *v, NULL); else changed = snd_pcm_hw_param_last(pcm, params, *v, NULL); if (changed < 0) return changed; if (changed == 0) continue; /* Trace the changed parameter. */ if (hw_is_mask(*v)) { trace_hw_mask_param(pcm, *v, 0, &old_mask, hw_param_mask(params, *v)); } if (hw_is_interval(*v)) { trace_hw_interval_param(pcm, *v, 0, &old_interval, hw_param_interval(params, *v)); } } return 0; } /* acquire buffer_mutex; if it's in r/w operation, return -EBUSY, otherwise * block the further r/w operations */ static int snd_pcm_buffer_access_lock(struct snd_pcm_runtime *runtime) { if (!atomic_dec_unless_positive(&runtime->buffer_accessing)) return -EBUSY; mutex_lock(&runtime->buffer_mutex); return 0; /* keep buffer_mutex, unlocked by below */ } /* release buffer_mutex and clear r/w access flag */ static void snd_pcm_buffer_access_unlock(struct snd_pcm_runtime *runtime) { mutex_unlock(&runtime->buffer_mutex); atomic_inc(&runtime->buffer_accessing); } /* fill the PCM buffer with the current silence format; called from pcm_oss.c */ void snd_pcm_runtime_buffer_set_silence(struct snd_pcm_runtime *runtime) { snd_pcm_buffer_access_lock(runtime); if (runtime->dma_area) snd_pcm_format_set_silence(runtime->format, runtime->dma_area, bytes_to_samples(runtime, runtime->dma_bytes)); snd_pcm_buffer_access_unlock(runtime); } EXPORT_SYMBOL_GPL(snd_pcm_runtime_buffer_set_silence); #if IS_ENABLED(CONFIG_SND_PCM_OSS) #define is_oss_stream(substream) ((substream)->oss.oss) #else #define is_oss_stream(substream) false #endif static int snd_pcm_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params) { struct snd_pcm_runtime *runtime; int err, usecs; unsigned int bits; snd_pcm_uframes_t frames; if (PCM_RUNTIME_CHECK(substream)) return -ENXIO; runtime = substream->runtime; err = snd_pcm_buffer_access_lock(runtime); if (err < 0) return err; scoped_guard(pcm_stream_lock_irq, substream) { switch (runtime->state) { case SNDRV_PCM_STATE_OPEN: case SNDRV_PCM_STATE_SETUP: case SNDRV_PCM_STATE_PREPARED: if (!is_oss_stream(substream) && atomic_read(&substream->mmap_count)) err = -EBADFD; break; default: err = -EBADFD; break; } } if (err) goto unlock; snd_pcm_sync_stop(substream, true); params->rmask = ~0U; err = snd_pcm_hw_refine(substream, params); if (err < 0) goto _error; err = snd_pcm_hw_params_choose(substream, params); if (err < 0) goto _error; err = fixup_unreferenced_params(substream, params); if (err < 0) goto _error; if (substream->managed_buffer_alloc) { err = snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(params)); if (err < 0) goto _error; runtime->buffer_changed = err > 0; } if (substream->ops->hw_params != NULL) { err = substream->ops->hw_params(substream, params); if (err < 0) goto _error; } runtime->access = params_access(params); runtime->format = params_format(params); runtime->subformat = params_subformat(params); runtime->channels = params_channels(params); runtime->rate = params_rate(params); runtime->period_size = params_period_size(params); runtime->periods = params_periods(params); runtime->buffer_size = params_buffer_size(params); runtime->info = params->info; runtime->rate_num = params->rate_num; runtime->rate_den = params->rate_den; runtime->no_period_wakeup = (params->info & SNDRV_PCM_INFO_NO_PERIOD_WAKEUP) && (params->flags & SNDRV_PCM_HW_PARAMS_NO_PERIOD_WAKEUP); bits = snd_pcm_format_physical_width(runtime->format); runtime->sample_bits = bits; bits *= runtime->channels; runtime->frame_bits = bits; frames = 1; while (bits % 8 != 0) { bits *= 2; frames *= 2; } runtime->byte_align = bits / 8; runtime->min_align = frames; /* Default sw params */ runtime->tstamp_mode = SNDRV_PCM_TSTAMP_NONE; runtime->period_step = 1; runtime->control->avail_min = runtime->period_size; runtime->start_threshold = 1; runtime->stop_threshold = runtime->buffer_size; runtime->silence_threshold = 0; runtime->silence_size = 0; runtime->boundary = runtime->buffer_size; while (runtime->boundary * 2 <= LONG_MAX - runtime->buffer_size) runtime->boundary *= 2; /* clear the buffer for avoiding possible kernel info leaks */ if (runtime->dma_area && !substream->ops->copy) { size_t size = runtime->dma_bytes; if (runtime->info & SNDRV_PCM_INFO_MMAP) size = PAGE_ALIGN(size); memset(runtime->dma_area, 0, size); } snd_pcm_timer_resolution_change(substream); snd_pcm_set_state(substream, SNDRV_PCM_STATE_SETUP); if (cpu_latency_qos_request_active(&substream->latency_pm_qos_req)) cpu_latency_qos_remove_request(&substream->latency_pm_qos_req); usecs = period_to_usecs(runtime); if (usecs >= 0) cpu_latency_qos_add_request(&substream->latency_pm_qos_req, usecs); err = 0; _error: if (err) { /* hardware might be unusable from this time, * so we force application to retry to set * the correct hardware parameter settings */ snd_pcm_set_state(substream, SNDRV_PCM_STATE_OPEN); if (substream->ops->hw_free != NULL) substream->ops->hw_free(substream); if (substream->managed_buffer_alloc) snd_pcm_lib_free_pages(substream); } unlock: snd_pcm_buffer_access_unlock(runtime); return err; } static int snd_pcm_hw_params_user(struct snd_pcm_substream *substream, struct snd_pcm_hw_params __user * _params) { struct snd_pcm_hw_params *params __free(kfree) = NULL; int err; params = memdup_user(_params, sizeof(*params)); if (IS_ERR(params)) return PTR_ERR(params); err = snd_pcm_hw_params(substream, params); if (err < 0) return err; if (copy_to_user(_params, params, sizeof(*params))) return -EFAULT; return err; } static int do_hw_free(struct snd_pcm_substream *substream) { int result = 0; snd_pcm_sync_stop(substream, true); if (substream->ops->hw_free) result = substream->ops->hw_free(substream); if (substream->managed_buffer_alloc) snd_pcm_lib_free_pages(substream); return result; } static int snd_pcm_hw_free(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime; int result = 0; if (PCM_RUNTIME_CHECK(substream)) return -ENXIO; runtime = substream->runtime; result = snd_pcm_buffer_access_lock(runtime); if (result < 0) return result; scoped_guard(pcm_stream_lock_irq, substream) { switch (runtime->state) { case SNDRV_PCM_STATE_SETUP: case SNDRV_PCM_STATE_PREPARED: if (atomic_read(&substream->mmap_count)) result = -EBADFD; break; default: result = -EBADFD; break; } } if (result) goto unlock; result = do_hw_free(substream); snd_pcm_set_state(substream, SNDRV_PCM_STATE_OPEN); cpu_latency_qos_remove_request(&substream->latency_pm_qos_req); unlock: snd_pcm_buffer_access_unlock(runtime); return result; } static int snd_pcm_sw_params(struct snd_pcm_substream *substream, struct snd_pcm_sw_params *params) { struct snd_pcm_runtime *runtime; int err; if (PCM_RUNTIME_CHECK(substream)) return -ENXIO; runtime = substream->runtime; scoped_guard(pcm_stream_lock_irq, substream) { if (runtime->state == SNDRV_PCM_STATE_OPEN) return -EBADFD; } if (params->tstamp_mode < 0 || params->tstamp_mode > SNDRV_PCM_TSTAMP_LAST) return -EINVAL; if (params->proto >= SNDRV_PROTOCOL_VERSION(2, 0, 12) && params->tstamp_type > SNDRV_PCM_TSTAMP_TYPE_LAST) return -EINVAL; if (params->avail_min == 0) return -EINVAL; if (params->silence_size >= runtime->boundary) { if (params->silence_threshold != 0) return -EINVAL; } else { if (params->silence_size > params->silence_threshold) return -EINVAL; if (params->silence_threshold > runtime->buffer_size) return -EINVAL; } err = 0; scoped_guard(pcm_stream_lock_irq, substream) { runtime->tstamp_mode = params->tstamp_mode; if (params->proto >= SNDRV_PROTOCOL_VERSION(2, 0, 12)) runtime->tstamp_type = params->tstamp_type; runtime->period_step = params->period_step; runtime->control->avail_min = params->avail_min; runtime->start_threshold = params->start_threshold; runtime->stop_threshold = params->stop_threshold; runtime->silence_threshold = params->silence_threshold; runtime->silence_size = params->silence_size; params->boundary = runtime->boundary; if (snd_pcm_running(substream)) { if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK && runtime->silence_size > 0) snd_pcm_playback_silence(substream, ULONG_MAX); err = snd_pcm_update_state(substream, runtime); } } return err; } static int snd_pcm_sw_params_user(struct snd_pcm_substream *substream, struct snd_pcm_sw_params __user * _params) { struct snd_pcm_sw_params params; int err; if (copy_from_user(¶ms, _params, sizeof(params))) return -EFAULT; err = snd_pcm_sw_params(substream, ¶ms); if (copy_to_user(_params, ¶ms, sizeof(params))) return -EFAULT; return err; } static inline snd_pcm_uframes_t snd_pcm_calc_delay(struct snd_pcm_substream *substream) { snd_pcm_uframes_t delay; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) delay = snd_pcm_playback_hw_avail(substream->runtime); else delay = snd_pcm_capture_avail(substream->runtime); return delay + substream->runtime->delay; } int snd_pcm_status64(struct snd_pcm_substream *substream, struct snd_pcm_status64 *status) { struct snd_pcm_runtime *runtime = substream->runtime; guard(pcm_stream_lock_irq)(substream); snd_pcm_unpack_audio_tstamp_config(status->audio_tstamp_data, &runtime->audio_tstamp_config); /* backwards compatible behavior */ if (runtime->audio_tstamp_config.type_requested == SNDRV_PCM_AUDIO_TSTAMP_TYPE_COMPAT) { if (runtime->hw.info & SNDRV_PCM_INFO_HAS_WALL_CLOCK) runtime->audio_tstamp_config.type_requested = SNDRV_PCM_AUDIO_TSTAMP_TYPE_LINK; else runtime->audio_tstamp_config.type_requested = SNDRV_PCM_AUDIO_TSTAMP_TYPE_DEFAULT; runtime->audio_tstamp_report.valid = 0; } else runtime->audio_tstamp_report.valid = 1; status->state = runtime->state; status->suspended_state = runtime->suspended_state; if (status->state == SNDRV_PCM_STATE_OPEN) return 0; status->trigger_tstamp_sec = runtime->trigger_tstamp.tv_sec; status->trigger_tstamp_nsec = runtime->trigger_tstamp.tv_nsec; if (snd_pcm_running(substream)) { snd_pcm_update_hw_ptr(substream); if (runtime->tstamp_mode == SNDRV_PCM_TSTAMP_ENABLE) { status->tstamp_sec = runtime->status->tstamp.tv_sec; status->tstamp_nsec = runtime->status->tstamp.tv_nsec; status->driver_tstamp_sec = runtime->driver_tstamp.tv_sec; status->driver_tstamp_nsec = runtime->driver_tstamp.tv_nsec; status->audio_tstamp_sec = runtime->status->audio_tstamp.tv_sec; status->audio_tstamp_nsec = runtime->status->audio_tstamp.tv_nsec; if (runtime->audio_tstamp_report.valid == 1) /* backwards compatibility, no report provided in COMPAT mode */ snd_pcm_pack_audio_tstamp_report(&status->audio_tstamp_data, &status->audio_tstamp_accuracy, &runtime->audio_tstamp_report); goto _tstamp_end; } } else { /* get tstamp only in fallback mode and only if enabled */ if (runtime->tstamp_mode == SNDRV_PCM_TSTAMP_ENABLE) { struct timespec64 tstamp; snd_pcm_gettime(runtime, &tstamp); status->tstamp_sec = tstamp.tv_sec; status->tstamp_nsec = tstamp.tv_nsec; } } _tstamp_end: status->appl_ptr = runtime->control->appl_ptr; status->hw_ptr = runtime->status->hw_ptr; status->avail = snd_pcm_avail(substream); status->delay = snd_pcm_running(substream) ? snd_pcm_calc_delay(substream) : 0; status->avail_max = runtime->avail_max; status->overrange = runtime->overrange; runtime->avail_max = 0; runtime->overrange = 0; return 0; } static int snd_pcm_status_user64(struct snd_pcm_substream *substream, struct snd_pcm_status64 __user * _status, bool ext) { struct snd_pcm_status64 status; int res; memset(&status, 0, sizeof(status)); /* * with extension, parameters are read/write, * get audio_tstamp_data from user, * ignore rest of status structure */ if (ext && get_user(status.audio_tstamp_data, (u32 __user *)(&_status->audio_tstamp_data))) return -EFAULT; res = snd_pcm_status64(substream, &status); if (res < 0) return res; if (copy_to_user(_status, &status, sizeof(status))) return -EFAULT; return 0; } static int snd_pcm_status_user32(struct snd_pcm_substream *substream, struct snd_pcm_status32 __user * _status, bool ext) { struct snd_pcm_status64 status64; struct snd_pcm_status32 status32; int res; memset(&status64, 0, sizeof(status64)); memset(&status32, 0, sizeof(status32)); /* * with extension, parameters are read/write, * get audio_tstamp_data from user, * ignore rest of status structure */ if (ext && get_user(status64.audio_tstamp_data, (u32 __user *)(&_status->audio_tstamp_data))) return -EFAULT; res = snd_pcm_status64(substream, &status64); if (res < 0) return res; status32 = (struct snd_pcm_status32) { .state = status64.state, .trigger_tstamp_sec = status64.trigger_tstamp_sec, .trigger_tstamp_nsec = status64.trigger_tstamp_nsec, .tstamp_sec = status64.tstamp_sec, .tstamp_nsec = status64.tstamp_nsec, .appl_ptr = status64.appl_ptr, .hw_ptr = status64.hw_ptr, .delay = status64.delay, .avail = status64.avail, .avail_max = status64.avail_max, .overrange = status64.overrange, .suspended_state = status64.suspended_state, .audio_tstamp_data = status64.audio_tstamp_data, .audio_tstamp_sec = status64.audio_tstamp_sec, .audio_tstamp_nsec = status64.audio_tstamp_nsec, .driver_tstamp_sec = status64.audio_tstamp_sec, .driver_tstamp_nsec = status64.audio_tstamp_nsec, .audio_tstamp_accuracy = status64.audio_tstamp_accuracy, }; if (copy_to_user(_status, &status32, sizeof(status32))) return -EFAULT; return 0; } static int snd_pcm_channel_info(struct snd_pcm_substream *substream, struct snd_pcm_channel_info * info) { struct snd_pcm_runtime *runtime; unsigned int channel; channel = info->channel; runtime = substream->runtime; scoped_guard(pcm_stream_lock_irq, substream) { if (runtime->state == SNDRV_PCM_STATE_OPEN) return -EBADFD; } if (channel >= runtime->channels) return -EINVAL; memset(info, 0, sizeof(*info)); info->channel = channel; return snd_pcm_ops_ioctl(substream, SNDRV_PCM_IOCTL1_CHANNEL_INFO, info); } static int snd_pcm_channel_info_user(struct snd_pcm_substream *substream, struct snd_pcm_channel_info __user * _info) { struct snd_pcm_channel_info info; int res; if (copy_from_user(&info, _info, sizeof(info))) return -EFAULT; res = snd_pcm_channel_info(substream, &info); if (res < 0) return res; if (copy_to_user(_info, &info, sizeof(info))) return -EFAULT; return 0; } static void snd_pcm_trigger_tstamp(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; if (runtime->trigger_master == NULL) return; if (runtime->trigger_master == substream) { if (!runtime->trigger_tstamp_latched) snd_pcm_gettime(runtime, &runtime->trigger_tstamp); } else { snd_pcm_trigger_tstamp(runtime->trigger_master); runtime->trigger_tstamp = runtime->trigger_master->runtime->trigger_tstamp; } runtime->trigger_master = NULL; } #define ACTION_ARG_IGNORE (__force snd_pcm_state_t)0 struct action_ops { int (*pre_action)(struct snd_pcm_substream *substream, snd_pcm_state_t state); int (*do_action)(struct snd_pcm_substream *substream, snd_pcm_state_t state); void (*undo_action)(struct snd_pcm_substream *substream, snd_pcm_state_t state); void (*post_action)(struct snd_pcm_substream *substream, snd_pcm_state_t state); }; /* * this functions is core for handling of linked stream * Note: the stream state might be changed also on failure * Note2: call with calling stream lock + link lock */ static int snd_pcm_action_group(const struct action_ops *ops, struct snd_pcm_substream *substream, snd_pcm_state_t state, bool stream_lock) { struct snd_pcm_substream *s = NULL; struct snd_pcm_substream *s1; int res = 0, depth = 1; snd_pcm_group_for_each_entry(s, substream) { if (s != substream) { if (!stream_lock) mutex_lock_nested(&s->runtime->buffer_mutex, depth); else if (s->pcm->nonatomic) mutex_lock_nested(&s->self_group.mutex, depth); else spin_lock_nested(&s->self_group.lock, depth); depth++; } res = ops->pre_action(s, state); if (res < 0) goto _unlock; } snd_pcm_group_for_each_entry(s, substream) { res = ops->do_action(s, state); if (res < 0) { if (ops->undo_action) { snd_pcm_group_for_each_entry(s1, substream) { if (s1 == s) /* failed stream */ break; ops->undo_action(s1, state); } } s = NULL; /* unlock all */ goto _unlock; } } snd_pcm_group_for_each_entry(s, substream) { ops->post_action(s, state); } _unlock: /* unlock streams */ snd_pcm_group_for_each_entry(s1, substream) { if (s1 != substream) { if (!stream_lock) mutex_unlock(&s1->runtime->buffer_mutex); else if (s1->pcm->nonatomic) mutex_unlock(&s1->self_group.mutex); else spin_unlock(&s1->self_group.lock); } if (s1 == s) /* end */ break; } return res; } /* * Note: call with stream lock */ static int snd_pcm_action_single(const struct action_ops *ops, struct snd_pcm_substream *substream, snd_pcm_state_t state) { int res; res = ops->pre_action(substream, state); if (res < 0) return res; res = ops->do_action(substream, state); if (res == 0) ops->post_action(substream, state); else if (ops->undo_action) ops->undo_action(substream, state); return res; } static void snd_pcm_group_assign(struct snd_pcm_substream *substream, struct snd_pcm_group *new_group) { substream->group = new_group; list_move(&substream->link_list, &new_group->substreams); } /* * Unref and unlock the group, but keep the stream lock; * when the group becomes empty and no longer referred, destroy itself */ static void snd_pcm_group_unref(struct snd_pcm_group *group, struct snd_pcm_substream *substream) { bool do_free; if (!group) return; do_free = refcount_dec_and_test(&group->refs); snd_pcm_group_unlock(group, substream->pcm->nonatomic); if (do_free) kfree(group); } /* * Lock the group inside a stream lock and reference it; * return the locked group object, or NULL if not linked */ static struct snd_pcm_group * snd_pcm_stream_group_ref(struct snd_pcm_substream *substream) { bool nonatomic = substream->pcm->nonatomic; struct snd_pcm_group *group; bool trylock; for (;;) { if (!snd_pcm_stream_linked(substream)) return NULL; group = substream->group; /* block freeing the group object */ refcount_inc(&group->refs); trylock = nonatomic ? mutex_trylock(&group->mutex) : spin_trylock(&group->lock); if (trylock) break; /* OK */ /* re-lock for avoiding ABBA deadlock */ snd_pcm_stream_unlock(substream); snd_pcm_group_lock(group, nonatomic); snd_pcm_stream_lock(substream); /* check the group again; the above opens a small race window */ if (substream->group == group) break; /* OK */ /* group changed, try again */ snd_pcm_group_unref(group, substream); } return group; } /* * Note: call with stream lock */ static int snd_pcm_action(const struct action_ops *ops, struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_group *group; int res; group = snd_pcm_stream_group_ref(substream); if (group) res = snd_pcm_action_group(ops, substream, state, true); else res = snd_pcm_action_single(ops, substream, state); snd_pcm_group_unref(group, substream); return res; } /* * Note: don't use any locks before */ static int snd_pcm_action_lock_irq(const struct action_ops *ops, struct snd_pcm_substream *substream, snd_pcm_state_t state) { guard(pcm_stream_lock_irq)(substream); return snd_pcm_action(ops, substream, state); } /* */ static int snd_pcm_action_nonatomic(const struct action_ops *ops, struct snd_pcm_substream *substream, snd_pcm_state_t state) { int res; /* Guarantee the group members won't change during non-atomic action */ guard(rwsem_read)(&snd_pcm_link_rwsem); res = snd_pcm_buffer_access_lock(substream->runtime); if (res < 0) return res; if (snd_pcm_stream_linked(substream)) res = snd_pcm_action_group(ops, substream, state, false); else res = snd_pcm_action_single(ops, substream, state); snd_pcm_buffer_access_unlock(substream->runtime); return res; } /* * start callbacks */ static int snd_pcm_pre_start(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; if (runtime->state != SNDRV_PCM_STATE_PREPARED) return -EBADFD; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK && !snd_pcm_playback_data(substream)) return -EPIPE; runtime->trigger_tstamp_latched = false; runtime->trigger_master = substream; return 0; } static int snd_pcm_do_start(struct snd_pcm_substream *substream, snd_pcm_state_t state) { int err; if (substream->runtime->trigger_master != substream) return 0; err = substream->ops->trigger(substream, SNDRV_PCM_TRIGGER_START); /* XRUN happened during the start */ if (err == -EPIPE) __snd_pcm_set_state(substream->runtime, SNDRV_PCM_STATE_XRUN); return err; } static void snd_pcm_undo_start(struct snd_pcm_substream *substream, snd_pcm_state_t state) { if (substream->runtime->trigger_master == substream) { substream->ops->trigger(substream, SNDRV_PCM_TRIGGER_STOP); substream->runtime->stop_operating = true; } } static void snd_pcm_post_start(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; snd_pcm_trigger_tstamp(substream); runtime->hw_ptr_jiffies = jiffies; runtime->hw_ptr_buffer_jiffies = (runtime->buffer_size * HZ) / runtime->rate; __snd_pcm_set_state(runtime, state); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK && runtime->silence_size > 0) snd_pcm_playback_silence(substream, ULONG_MAX); snd_pcm_timer_notify(substream, SNDRV_TIMER_EVENT_MSTART); } static const struct action_ops snd_pcm_action_start = { .pre_action = snd_pcm_pre_start, .do_action = snd_pcm_do_start, .undo_action = snd_pcm_undo_start, .post_action = snd_pcm_post_start }; /** * snd_pcm_start - start all linked streams * @substream: the PCM substream instance * * Return: Zero if successful, or a negative error code. * The stream lock must be acquired before calling this function. */ int snd_pcm_start(struct snd_pcm_substream *substream) { return snd_pcm_action(&snd_pcm_action_start, substream, SNDRV_PCM_STATE_RUNNING); } /* take the stream lock and start the streams */ static int snd_pcm_start_lock_irq(struct snd_pcm_substream *substream) { return snd_pcm_action_lock_irq(&snd_pcm_action_start, substream, SNDRV_PCM_STATE_RUNNING); } /* * stop callbacks */ static int snd_pcm_pre_stop(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; if (runtime->state == SNDRV_PCM_STATE_OPEN) return -EBADFD; runtime->trigger_master = substream; return 0; } static int snd_pcm_do_stop(struct snd_pcm_substream *substream, snd_pcm_state_t state) { if (substream->runtime->trigger_master == substream && snd_pcm_running(substream)) { substream->ops->trigger(substream, SNDRV_PCM_TRIGGER_STOP); substream->runtime->stop_operating = true; } return 0; /* unconditionally stop all substreams */ } static void snd_pcm_post_stop(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; if (runtime->state != state) { snd_pcm_trigger_tstamp(substream); __snd_pcm_set_state(runtime, state); snd_pcm_timer_notify(substream, SNDRV_TIMER_EVENT_MSTOP); } wake_up(&runtime->sleep); wake_up(&runtime->tsleep); } static const struct action_ops snd_pcm_action_stop = { .pre_action = snd_pcm_pre_stop, .do_action = snd_pcm_do_stop, .post_action = snd_pcm_post_stop }; /** * snd_pcm_stop - try to stop all running streams in the substream group * @substream: the PCM substream instance * @state: PCM state after stopping the stream * * The state of each stream is then changed to the given state unconditionally. * * Return: Zero if successful, or a negative error code. */ int snd_pcm_stop(struct snd_pcm_substream *substream, snd_pcm_state_t state) { return snd_pcm_action(&snd_pcm_action_stop, substream, state); } EXPORT_SYMBOL(snd_pcm_stop); /** * snd_pcm_drain_done - stop the DMA only when the given stream is playback * @substream: the PCM substream * * After stopping, the state is changed to SETUP. * Unlike snd_pcm_stop(), this affects only the given stream. * * Return: Zero if successful, or a negative error code. */ int snd_pcm_drain_done(struct snd_pcm_substream *substream) { return snd_pcm_action_single(&snd_pcm_action_stop, substream, SNDRV_PCM_STATE_SETUP); } /** * snd_pcm_stop_xrun - stop the running streams as XRUN * @substream: the PCM substream instance * * This stops the given running substream (and all linked substreams) as XRUN. * Unlike snd_pcm_stop(), this function takes the substream lock by itself. * * Return: Zero if successful, or a negative error code. */ int snd_pcm_stop_xrun(struct snd_pcm_substream *substream) { guard(pcm_stream_lock_irqsave)(substream); if (substream->runtime && snd_pcm_running(substream)) __snd_pcm_xrun(substream); return 0; } EXPORT_SYMBOL_GPL(snd_pcm_stop_xrun); /* * pause callbacks: pass boolean (to start pause or resume) as state argument */ #define pause_pushed(state) (__force bool)(state) static int snd_pcm_pre_pause(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; if (!(runtime->info & SNDRV_PCM_INFO_PAUSE)) return -ENOSYS; if (pause_pushed(state)) { if (runtime->state != SNDRV_PCM_STATE_RUNNING) return -EBADFD; } else if (runtime->state != SNDRV_PCM_STATE_PAUSED) return -EBADFD; runtime->trigger_master = substream; return 0; } static int snd_pcm_do_pause(struct snd_pcm_substream *substream, snd_pcm_state_t state) { if (substream->runtime->trigger_master != substream) return 0; /* The jiffies check in snd_pcm_update_hw_ptr*() is done by * a delta between the current jiffies, this gives a large enough * delta, effectively to skip the check once. */ substream->runtime->hw_ptr_jiffies = jiffies - HZ * 1000; return substream->ops->trigger(substream, pause_pushed(state) ? SNDRV_PCM_TRIGGER_PAUSE_PUSH : SNDRV_PCM_TRIGGER_PAUSE_RELEASE); } static void snd_pcm_undo_pause(struct snd_pcm_substream *substream, snd_pcm_state_t state) { if (substream->runtime->trigger_master == substream) substream->ops->trigger(substream, pause_pushed(state) ? SNDRV_PCM_TRIGGER_PAUSE_RELEASE : SNDRV_PCM_TRIGGER_PAUSE_PUSH); } static void snd_pcm_post_pause(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; snd_pcm_trigger_tstamp(substream); if (pause_pushed(state)) { __snd_pcm_set_state(runtime, SNDRV_PCM_STATE_PAUSED); snd_pcm_timer_notify(substream, SNDRV_TIMER_EVENT_MPAUSE); wake_up(&runtime->sleep); wake_up(&runtime->tsleep); } else { __snd_pcm_set_state(runtime, SNDRV_PCM_STATE_RUNNING); snd_pcm_timer_notify(substream, SNDRV_TIMER_EVENT_MCONTINUE); } } static const struct action_ops snd_pcm_action_pause = { .pre_action = snd_pcm_pre_pause, .do_action = snd_pcm_do_pause, .undo_action = snd_pcm_undo_pause, .post_action = snd_pcm_post_pause }; /* * Push/release the pause for all linked streams. */ static int snd_pcm_pause(struct snd_pcm_substream *substream, bool push) { return snd_pcm_action(&snd_pcm_action_pause, substream, (__force snd_pcm_state_t)push); } static int snd_pcm_pause_lock_irq(struct snd_pcm_substream *substream, bool push) { return snd_pcm_action_lock_irq(&snd_pcm_action_pause, substream, (__force snd_pcm_state_t)push); } #ifdef CONFIG_PM /* suspend callback: state argument ignored */ static int snd_pcm_pre_suspend(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; switch (runtime->state) { case SNDRV_PCM_STATE_SUSPENDED: return -EBUSY; /* unresumable PCM state; return -EBUSY for skipping suspend */ case SNDRV_PCM_STATE_OPEN: case SNDRV_PCM_STATE_SETUP: case SNDRV_PCM_STATE_DISCONNECTED: return -EBUSY; } runtime->trigger_master = substream; return 0; } static int snd_pcm_do_suspend(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; if (runtime->trigger_master != substream) return 0; if (! snd_pcm_running(substream)) return 0; substream->ops->trigger(substream, SNDRV_PCM_TRIGGER_SUSPEND); runtime->stop_operating = true; return 0; /* suspend unconditionally */ } static void snd_pcm_post_suspend(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; snd_pcm_trigger_tstamp(substream); runtime->suspended_state = runtime->state; runtime->status->suspended_state = runtime->suspended_state; __snd_pcm_set_state(runtime, SNDRV_PCM_STATE_SUSPENDED); snd_pcm_timer_notify(substream, SNDRV_TIMER_EVENT_MSUSPEND); wake_up(&runtime->sleep); wake_up(&runtime->tsleep); } static const struct action_ops snd_pcm_action_suspend = { .pre_action = snd_pcm_pre_suspend, .do_action = snd_pcm_do_suspend, .post_action = snd_pcm_post_suspend }; /* * snd_pcm_suspend - trigger SUSPEND to all linked streams * @substream: the PCM substream * * After this call, all streams are changed to SUSPENDED state. * * Return: Zero if successful, or a negative error code. */ static int snd_pcm_suspend(struct snd_pcm_substream *substream) { guard(pcm_stream_lock_irqsave)(substream); return snd_pcm_action(&snd_pcm_action_suspend, substream, ACTION_ARG_IGNORE); } /** * snd_pcm_suspend_all - trigger SUSPEND to all substreams in the given pcm * @pcm: the PCM instance * * After this call, all streams are changed to SUSPENDED state. * * Return: Zero if successful (or @pcm is %NULL), or a negative error code. */ int snd_pcm_suspend_all(struct snd_pcm *pcm) { struct snd_pcm_substream *substream; int stream, err = 0; if (! pcm) return 0; for_each_pcm_substream(pcm, stream, substream) { /* FIXME: the open/close code should lock this as well */ if (!substream->runtime) continue; /* * Skip BE dai link PCM's that are internal and may * not have their substream ops set. */ if (!substream->ops) continue; err = snd_pcm_suspend(substream); if (err < 0 && err != -EBUSY) return err; } for_each_pcm_substream(pcm, stream, substream) snd_pcm_sync_stop(substream, false); return 0; } EXPORT_SYMBOL(snd_pcm_suspend_all); /* resume callbacks: state argument ignored */ static int snd_pcm_pre_resume(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; if (runtime->state != SNDRV_PCM_STATE_SUSPENDED) return -EBADFD; if (!(runtime->info & SNDRV_PCM_INFO_RESUME)) return -ENOSYS; runtime->trigger_master = substream; return 0; } static int snd_pcm_do_resume(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; if (runtime->trigger_master != substream) return 0; /* DMA not running previously? */ if (runtime->suspended_state != SNDRV_PCM_STATE_RUNNING && (runtime->suspended_state != SNDRV_PCM_STATE_DRAINING || substream->stream != SNDRV_PCM_STREAM_PLAYBACK)) return 0; return substream->ops->trigger(substream, SNDRV_PCM_TRIGGER_RESUME); } static void snd_pcm_undo_resume(struct snd_pcm_substream *substream, snd_pcm_state_t state) { if (substream->runtime->trigger_master == substream && snd_pcm_running(substream)) substream->ops->trigger(substream, SNDRV_PCM_TRIGGER_SUSPEND); } static void snd_pcm_post_resume(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; snd_pcm_trigger_tstamp(substream); __snd_pcm_set_state(runtime, runtime->suspended_state); snd_pcm_timer_notify(substream, SNDRV_TIMER_EVENT_MRESUME); } static const struct action_ops snd_pcm_action_resume = { .pre_action = snd_pcm_pre_resume, .do_action = snd_pcm_do_resume, .undo_action = snd_pcm_undo_resume, .post_action = snd_pcm_post_resume }; static int snd_pcm_resume(struct snd_pcm_substream *substream) { return snd_pcm_action_lock_irq(&snd_pcm_action_resume, substream, ACTION_ARG_IGNORE); } #else static int snd_pcm_resume(struct snd_pcm_substream *substream) { return -ENOSYS; } #endif /* CONFIG_PM */ /* * xrun ioctl * * Change the RUNNING stream(s) to XRUN state. */ static int snd_pcm_xrun(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; guard(pcm_stream_lock_irq)(substream); switch (runtime->state) { case SNDRV_PCM_STATE_XRUN: return 0; /* already there */ case SNDRV_PCM_STATE_RUNNING: __snd_pcm_xrun(substream); return 0; default: return -EBADFD; } } /* * reset ioctl */ /* reset callbacks: state argument ignored */ static int snd_pcm_pre_reset(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; switch (runtime->state) { case SNDRV_PCM_STATE_RUNNING: case SNDRV_PCM_STATE_PREPARED: case SNDRV_PCM_STATE_PAUSED: case SNDRV_PCM_STATE_SUSPENDED: return 0; default: return -EBADFD; } } static int snd_pcm_do_reset(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; int err = snd_pcm_ops_ioctl(substream, SNDRV_PCM_IOCTL1_RESET, NULL); if (err < 0) return err; guard(pcm_stream_lock_irq)(substream); runtime->hw_ptr_base = 0; runtime->hw_ptr_interrupt = runtime->status->hw_ptr - runtime->status->hw_ptr % runtime->period_size; runtime->silence_start = runtime->status->hw_ptr; runtime->silence_filled = 0; return 0; } static void snd_pcm_post_reset(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; guard(pcm_stream_lock_irq)(substream); runtime->control->appl_ptr = runtime->status->hw_ptr; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK && runtime->silence_size > 0) snd_pcm_playback_silence(substream, ULONG_MAX); } static const struct action_ops snd_pcm_action_reset = { .pre_action = snd_pcm_pre_reset, .do_action = snd_pcm_do_reset, .post_action = snd_pcm_post_reset }; static int snd_pcm_reset(struct snd_pcm_substream *substream) { return snd_pcm_action_nonatomic(&snd_pcm_action_reset, substream, ACTION_ARG_IGNORE); } /* * prepare ioctl */ /* pass f_flags as state argument */ static int snd_pcm_pre_prepare(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; int f_flags = (__force int)state; if (runtime->state == SNDRV_PCM_STATE_OPEN || runtime->state == SNDRV_PCM_STATE_DISCONNECTED) return -EBADFD; if (snd_pcm_running(substream)) return -EBUSY; substream->f_flags = f_flags; return 0; } static int snd_pcm_do_prepare(struct snd_pcm_substream *substream, snd_pcm_state_t state) { int err; snd_pcm_sync_stop(substream, true); err = substream->ops->prepare(substream); if (err < 0) return err; return snd_pcm_do_reset(substream, state); } static void snd_pcm_post_prepare(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; runtime->control->appl_ptr = runtime->status->hw_ptr; snd_pcm_set_state(substream, SNDRV_PCM_STATE_PREPARED); } static const struct action_ops snd_pcm_action_prepare = { .pre_action = snd_pcm_pre_prepare, .do_action = snd_pcm_do_prepare, .post_action = snd_pcm_post_prepare }; /** * snd_pcm_prepare - prepare the PCM substream to be triggerable * @substream: the PCM substream instance * @file: file to refer f_flags * * Return: Zero if successful, or a negative error code. */ static int snd_pcm_prepare(struct snd_pcm_substream *substream, struct file *file) { int f_flags; if (file) f_flags = file->f_flags; else f_flags = substream->f_flags; scoped_guard(pcm_stream_lock_irq, substream) { switch (substream->runtime->state) { case SNDRV_PCM_STATE_PAUSED: snd_pcm_pause(substream, false); fallthrough; case SNDRV_PCM_STATE_SUSPENDED: snd_pcm_stop(substream, SNDRV_PCM_STATE_SETUP); break; } } return snd_pcm_action_nonatomic(&snd_pcm_action_prepare, substream, (__force snd_pcm_state_t)f_flags); } /* * drain ioctl */ /* drain init callbacks: state argument ignored */ static int snd_pcm_pre_drain_init(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; switch (runtime->state) { case SNDRV_PCM_STATE_OPEN: case SNDRV_PCM_STATE_DISCONNECTED: case SNDRV_PCM_STATE_SUSPENDED: return -EBADFD; } runtime->trigger_master = substream; return 0; } static int snd_pcm_do_drain_init(struct snd_pcm_substream *substream, snd_pcm_state_t state) { struct snd_pcm_runtime *runtime = substream->runtime; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { switch (runtime->state) { case SNDRV_PCM_STATE_PREPARED: /* start playback stream if possible */ if (! snd_pcm_playback_empty(substream)) { snd_pcm_do_start(substream, SNDRV_PCM_STATE_DRAINING); snd_pcm_post_start(substream, SNDRV_PCM_STATE_DRAINING); } else { __snd_pcm_set_state(runtime, SNDRV_PCM_STATE_SETUP); } break; case SNDRV_PCM_STATE_RUNNING: __snd_pcm_set_state(runtime, SNDRV_PCM_STATE_DRAINING); break; case SNDRV_PCM_STATE_XRUN: __snd_pcm_set_state(runtime, SNDRV_PCM_STATE_SETUP); break; default: break; } } else { /* stop running stream */ if (runtime->state == SNDRV_PCM_STATE_RUNNING) { snd_pcm_state_t new_state; new_state = snd_pcm_capture_avail(runtime) > 0 ? SNDRV_PCM_STATE_DRAINING : SNDRV_PCM_STATE_SETUP; snd_pcm_do_stop(substream, new_state); snd_pcm_post_stop(substream, new_state); } } if (runtime->state == SNDRV_PCM_STATE_DRAINING && runtime->trigger_master == substream && (runtime->hw.info & SNDRV_PCM_INFO_DRAIN_TRIGGER)) return substream->ops->trigger(substream, SNDRV_PCM_TRIGGER_DRAIN); return 0; } static void snd_pcm_post_drain_init(struct snd_pcm_substream *substream, snd_pcm_state_t state) { } static const struct action_ops snd_pcm_action_drain_init = { .pre_action = snd_pcm_pre_drain_init, .do_action = snd_pcm_do_drain_init, .post_action = snd_pcm_post_drain_init }; /* * Drain the stream(s). * When the substream is linked, sync until the draining of all playback streams * is finished. * After this call, all streams are supposed to be either SETUP or DRAINING * (capture only) state. */ static int snd_pcm_drain(struct snd_pcm_substream *substream, struct file *file) { struct snd_card *card; struct snd_pcm_runtime *runtime; struct snd_pcm_substream *s; struct snd_pcm_group *group; wait_queue_entry_t wait; int result = 0; int nonblock = 0; card = substream->pcm->card; runtime = substream->runtime; if (runtime->state == SNDRV_PCM_STATE_OPEN) return -EBADFD; if (file) { if (file->f_flags & O_NONBLOCK) nonblock = 1; } else if (substream->f_flags & O_NONBLOCK) nonblock = 1; snd_pcm_stream_lock_irq(substream); /* resume pause */ if (runtime->state == SNDRV_PCM_STATE_PAUSED) snd_pcm_pause(substream, false); /* pre-start/stop - all running streams are changed to DRAINING state */ result = snd_pcm_action(&snd_pcm_action_drain_init, substream, ACTION_ARG_IGNORE); if (result < 0) goto unlock; /* in non-blocking, we don't wait in ioctl but let caller poll */ if (nonblock) { result = -EAGAIN; goto unlock; } for (;;) { long tout; struct snd_pcm_runtime *to_check; if (signal_pending(current)) { result = -ERESTARTSYS; break; } /* find a substream to drain */ to_check = NULL; group = snd_pcm_stream_group_ref(substream); snd_pcm_group_for_each_entry(s, substream) { if (s->stream != SNDRV_PCM_STREAM_PLAYBACK) continue; runtime = s->runtime; if (runtime->state == SNDRV_PCM_STATE_DRAINING) { to_check = runtime; break; } } snd_pcm_group_unref(group, substream); if (!to_check) break; /* all drained */ init_waitqueue_entry(&wait, current); set_current_state(TASK_INTERRUPTIBLE); add_wait_queue(&to_check->sleep, &wait); snd_pcm_stream_unlock_irq(substream); if (runtime->no_period_wakeup) tout = MAX_SCHEDULE_TIMEOUT; else { tout = 100; if (runtime->rate) { long t = runtime->buffer_size * 1100 / runtime->rate; tout = max(t, tout); } tout = msecs_to_jiffies(tout); } tout = schedule_timeout(tout); snd_pcm_stream_lock_irq(substream); group = snd_pcm_stream_group_ref(substream); snd_pcm_group_for_each_entry(s, substream) { if (s->runtime == to_check) { remove_wait_queue(&to_check->sleep, &wait); break; } } snd_pcm_group_unref(group, substream); if (card->shutdown) { result = -ENODEV; break; } if (tout == 0) { if (substream->runtime->state == SNDRV_PCM_STATE_SUSPENDED) result = -ESTRPIPE; else { dev_dbg(substream->pcm->card->dev, "playback drain timeout (DMA or IRQ trouble?)\n"); snd_pcm_stop(substream, SNDRV_PCM_STATE_SETUP); result = -EIO; } break; } } unlock: snd_pcm_stream_unlock_irq(substream); return result; } /* * drop ioctl * * Immediately put all linked substreams into SETUP state. */ static int snd_pcm_drop(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime; int result = 0; if (PCM_RUNTIME_CHECK(substream)) return -ENXIO; runtime = substream->runtime; if (runtime->state == SNDRV_PCM_STATE_OPEN || runtime->state == SNDRV_PCM_STATE_DISCONNECTED) return -EBADFD; guard(pcm_stream_lock_irq)(substream); /* resume pause */ if (runtime->state == SNDRV_PCM_STATE_PAUSED) snd_pcm_pause(substream, false); snd_pcm_stop(substream, SNDRV_PCM_STATE_SETUP); /* runtime->control->appl_ptr = runtime->status->hw_ptr; */ return result; } static bool is_pcm_file(struct file *file) { struct inode *inode = file_inode(file); struct snd_pcm *pcm; unsigned int minor; if (!S_ISCHR(inode->i_mode) || imajor(inode) != snd_major) return false; minor = iminor(inode); pcm = snd_lookup_minor_data(minor, SNDRV_DEVICE_TYPE_PCM_PLAYBACK); if (!pcm) pcm = snd_lookup_minor_data(minor, SNDRV_DEVICE_TYPE_PCM_CAPTURE); if (!pcm) return false; snd_card_unref(pcm->card); return true; } /* * PCM link handling */ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) { struct snd_pcm_file *pcm_file; struct snd_pcm_substream *substream1; struct snd_pcm_group *group __free(kfree) = NULL; struct snd_pcm_group *target_group; bool nonatomic = substream->pcm->nonatomic; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADFD; if (!is_pcm_file(fd_file(f))) return -EBADFD; pcm_file = fd_file(f)->private_data; substream1 = pcm_file->substream; if (substream == substream1) return -EINVAL; group = kzalloc(sizeof(*group), GFP_KERNEL); if (!group) return -ENOMEM; snd_pcm_group_init(group); guard(rwsem_write)(&snd_pcm_link_rwsem); if (substream->runtime->state == SNDRV_PCM_STATE_OPEN || substream->runtime->state != substream1->runtime->state || substream->pcm->nonatomic != substream1->pcm->nonatomic) return -EBADFD; if (snd_pcm_stream_linked(substream1)) return -EALREADY; scoped_guard(pcm_stream_lock_irq, substream) { if (!snd_pcm_stream_linked(substream)) { snd_pcm_group_assign(substream, group); group = NULL; /* assigned, don't free this one below */ } target_group = substream->group; } snd_pcm_group_lock_irq(target_group, nonatomic); snd_pcm_stream_lock_nested(substream1); snd_pcm_group_assign(substream1, target_group); refcount_inc(&target_group->refs); snd_pcm_stream_unlock(substream1); snd_pcm_group_unlock_irq(target_group, nonatomic); return 0; } static void relink_to_local(struct snd_pcm_substream *substream) { snd_pcm_stream_lock_nested(substream); snd_pcm_group_assign(substream, &substream->self_group); snd_pcm_stream_unlock(substream); } static int snd_pcm_unlink(struct snd_pcm_substream *substream) { struct snd_pcm_group *group; bool nonatomic = substream->pcm->nonatomic; bool do_free = false; guard(rwsem_write)(&snd_pcm_link_rwsem); if (!snd_pcm_stream_linked(substream)) return -EALREADY; group = substream->group; snd_pcm_group_lock_irq(group, nonatomic); relink_to_local(substream); refcount_dec(&group->refs); /* detach the last stream, too */ if (list_is_singular(&group->substreams)) { relink_to_local(list_first_entry(&group->substreams, struct snd_pcm_substream, link_list)); do_free = refcount_dec_and_test(&group->refs); } snd_pcm_group_unlock_irq(group, nonatomic); if (do_free) kfree(group); return 0; } /* * hw configurator */ static int snd_pcm_hw_rule_mul(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { struct snd_interval t; snd_interval_mul(hw_param_interval_c(params, rule->deps[0]), hw_param_interval_c(params, rule->deps[1]), &t); return snd_interval_refine(hw_param_interval(params, rule->var), &t); } static int snd_pcm_hw_rule_div(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { struct snd_interval t; snd_interval_div(hw_param_interval_c(params, rule->deps[0]), hw_param_interval_c(params, rule->deps[1]), &t); return snd_interval_refine(hw_param_interval(params, rule->var), &t); } static int snd_pcm_hw_rule_muldivk(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { struct snd_interval t; snd_interval_muldivk(hw_param_interval_c(params, rule->deps[0]), hw_param_interval_c(params, rule->deps[1]), (unsigned long) rule->private, &t); return snd_interval_refine(hw_param_interval(params, rule->var), &t); } static int snd_pcm_hw_rule_mulkdiv(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { struct snd_interval t; snd_interval_mulkdiv(hw_param_interval_c(params, rule->deps[0]), (unsigned long) rule->private, hw_param_interval_c(params, rule->deps[1]), &t); return snd_interval_refine(hw_param_interval(params, rule->var), &t); } static int snd_pcm_hw_rule_format(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { snd_pcm_format_t k; const struct snd_interval *i = hw_param_interval_c(params, rule->deps[0]); struct snd_mask m; struct snd_mask *mask = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT); snd_mask_any(&m); pcm_for_each_format(k) { int bits; if (!snd_mask_test_format(mask, k)) continue; bits = snd_pcm_format_physical_width(k); if (bits <= 0) continue; /* ignore invalid formats */ if ((unsigned)bits < i->min || (unsigned)bits > i->max) snd_mask_reset(&m, (__force unsigned)k); } return snd_mask_refine(mask, &m); } static int snd_pcm_hw_rule_sample_bits(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { struct snd_interval t; snd_pcm_format_t k; t.min = UINT_MAX; t.max = 0; t.openmin = 0; t.openmax = 0; pcm_for_each_format(k) { int bits; if (!snd_mask_test_format(hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT), k)) continue; bits = snd_pcm_format_physical_width(k); if (bits <= 0) continue; /* ignore invalid formats */ if (t.min > (unsigned)bits) t.min = bits; if (t.max < (unsigned)bits) t.max = bits; } t.integer = 1; return snd_interval_refine(hw_param_interval(params, rule->var), &t); } #if SNDRV_PCM_RATE_5512 != 1 << 0 || SNDRV_PCM_RATE_192000 != 1 << 12 ||\ SNDRV_PCM_RATE_128000 != 1 << 19 #error "Change this table" #endif /* NOTE: the list is unsorted! */ static const unsigned int rates[] = { 5512, 8000, 11025, 16000, 22050, 32000, 44100, 48000, 64000, 88200, 96000, 176400, 192000, 352800, 384000, 705600, 768000, /* extended */ 12000, 24000, 128000 }; const struct snd_pcm_hw_constraint_list snd_pcm_known_rates = { .count = ARRAY_SIZE(rates), .list = rates, }; static int snd_pcm_hw_rule_rate(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { struct snd_pcm_hardware *hw = rule->private; return snd_interval_list(hw_param_interval(params, rule->var), snd_pcm_known_rates.count, snd_pcm_known_rates.list, hw->rates); } static int snd_pcm_hw_rule_buffer_bytes_max(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { struct snd_interval t; struct snd_pcm_substream *substream = rule->private; t.min = 0; t.max = substream->buffer_bytes_max; t.openmin = 0; t.openmax = 0; t.integer = 1; return snd_interval_refine(hw_param_interval(params, rule->var), &t); } static int snd_pcm_hw_rule_subformats(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { struct snd_mask *sfmask = hw_param_mask(params, SNDRV_PCM_HW_PARAM_SUBFORMAT); struct snd_mask *fmask = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT); u32 *subformats = rule->private; snd_pcm_format_t f; struct snd_mask m; snd_mask_none(&m); /* All PCMs support at least the default STD subformat. */ snd_mask_set(&m, (__force unsigned)SNDRV_PCM_SUBFORMAT_STD); pcm_for_each_format(f) { if (!snd_mask_test(fmask, (__force unsigned)f)) continue; if (f == SNDRV_PCM_FORMAT_S32_LE && *subformats) m.bits[0] |= *subformats; else if (snd_pcm_format_linear(f)) snd_mask_set(&m, (__force unsigned)SNDRV_PCM_SUBFORMAT_MSBITS_MAX); } return snd_mask_refine(sfmask, &m); } static int snd_pcm_hw_constraint_subformats(struct snd_pcm_runtime *runtime, unsigned int cond, u32 *subformats) { return snd_pcm_hw_rule_add(runtime, cond, -1, snd_pcm_hw_rule_subformats, (void *)subformats, SNDRV_PCM_HW_PARAM_SUBFORMAT, SNDRV_PCM_HW_PARAM_FORMAT, -1); } static int snd_pcm_hw_constraints_init(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; struct snd_pcm_hw_constraints *constrs = &runtime->hw_constraints; int k, err; for (k = SNDRV_PCM_HW_PARAM_FIRST_MASK; k <= SNDRV_PCM_HW_PARAM_LAST_MASK; k++) { snd_mask_any(constrs_mask(constrs, k)); } for (k = SNDRV_PCM_HW_PARAM_FIRST_INTERVAL; k <= SNDRV_PCM_HW_PARAM_LAST_INTERVAL; k++) { snd_interval_any(constrs_interval(constrs, k)); } snd_interval_setinteger(constrs_interval(constrs, SNDRV_PCM_HW_PARAM_CHANNELS)); snd_interval_setinteger(constrs_interval(constrs, SNDRV_PCM_HW_PARAM_BUFFER_SIZE)); snd_interval_setinteger(constrs_interval(constrs, SNDRV_PCM_HW_PARAM_BUFFER_BYTES)); snd_interval_setinteger(constrs_interval(constrs, SNDRV_PCM_HW_PARAM_SAMPLE_BITS)); snd_interval_setinteger(constrs_interval(constrs, SNDRV_PCM_HW_PARAM_FRAME_BITS)); err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FORMAT, snd_pcm_hw_rule_format, NULL, SNDRV_PCM_HW_PARAM_SAMPLE_BITS, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_SAMPLE_BITS, snd_pcm_hw_rule_sample_bits, NULL, SNDRV_PCM_HW_PARAM_FORMAT, SNDRV_PCM_HW_PARAM_SAMPLE_BITS, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_SAMPLE_BITS, snd_pcm_hw_rule_div, NULL, SNDRV_PCM_HW_PARAM_FRAME_BITS, SNDRV_PCM_HW_PARAM_CHANNELS, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FRAME_BITS, snd_pcm_hw_rule_mul, NULL, SNDRV_PCM_HW_PARAM_SAMPLE_BITS, SNDRV_PCM_HW_PARAM_CHANNELS, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FRAME_BITS, snd_pcm_hw_rule_mulkdiv, (void*) 8, SNDRV_PCM_HW_PARAM_PERIOD_BYTES, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FRAME_BITS, snd_pcm_hw_rule_mulkdiv, (void*) 8, SNDRV_PCM_HW_PARAM_BUFFER_BYTES, SNDRV_PCM_HW_PARAM_BUFFER_SIZE, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS, snd_pcm_hw_rule_div, NULL, SNDRV_PCM_HW_PARAM_FRAME_BITS, SNDRV_PCM_HW_PARAM_SAMPLE_BITS, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, snd_pcm_hw_rule_mulkdiv, (void*) 1000000, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, SNDRV_PCM_HW_PARAM_PERIOD_TIME, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, snd_pcm_hw_rule_mulkdiv, (void*) 1000000, SNDRV_PCM_HW_PARAM_BUFFER_SIZE, SNDRV_PCM_HW_PARAM_BUFFER_TIME, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIODS, snd_pcm_hw_rule_div, NULL, SNDRV_PCM_HW_PARAM_BUFFER_SIZE, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, snd_pcm_hw_rule_div, NULL, SNDRV_PCM_HW_PARAM_BUFFER_SIZE, SNDRV_PCM_HW_PARAM_PERIODS, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, snd_pcm_hw_rule_mulkdiv, (void*) 8, SNDRV_PCM_HW_PARAM_PERIOD_BYTES, SNDRV_PCM_HW_PARAM_FRAME_BITS, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, snd_pcm_hw_rule_muldivk, (void*) 1000000, SNDRV_PCM_HW_PARAM_PERIOD_TIME, SNDRV_PCM_HW_PARAM_RATE, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_SIZE, snd_pcm_hw_rule_mul, NULL, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, SNDRV_PCM_HW_PARAM_PERIODS, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_SIZE, snd_pcm_hw_rule_mulkdiv, (void*) 8, SNDRV_PCM_HW_PARAM_BUFFER_BYTES, SNDRV_PCM_HW_PARAM_FRAME_BITS, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_SIZE, snd_pcm_hw_rule_muldivk, (void*) 1000000, SNDRV_PCM_HW_PARAM_BUFFER_TIME, SNDRV_PCM_HW_PARAM_RATE, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_BYTES, snd_pcm_hw_rule_muldivk, (void*) 8, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, SNDRV_PCM_HW_PARAM_FRAME_BITS, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_BYTES, snd_pcm_hw_rule_muldivk, (void*) 8, SNDRV_PCM_HW_PARAM_BUFFER_SIZE, SNDRV_PCM_HW_PARAM_FRAME_BITS, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_TIME, snd_pcm_hw_rule_mulkdiv, (void*) 1000000, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, SNDRV_PCM_HW_PARAM_RATE, -1); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_TIME, snd_pcm_hw_rule_mulkdiv, (void*) 1000000, SNDRV_PCM_HW_PARAM_BUFFER_SIZE, SNDRV_PCM_HW_PARAM_RATE, -1); if (err < 0) return err; return 0; } static int snd_pcm_hw_constraints_complete(struct snd_pcm_substream *substream) { struct snd_pcm_runtime *runtime = substream->runtime; struct snd_pcm_hardware *hw = &runtime->hw; int err; unsigned int mask = 0; if (hw->info & SNDRV_PCM_INFO_INTERLEAVED) mask |= PARAM_MASK_BIT(SNDRV_PCM_ACCESS_RW_INTERLEAVED); if (hw->info & SNDRV_PCM_INFO_NONINTERLEAVED) mask |= PARAM_MASK_BIT(SNDRV_PCM_ACCESS_RW_NONINTERLEAVED); if (hw_support_mmap(substream)) { if (hw->info & SNDRV_PCM_INFO_INTERLEAVED) mask |= PARAM_MASK_BIT(SNDRV_PCM_ACCESS_MMAP_INTERLEAVED); if (hw->info & SNDRV_PCM_INFO_NONINTERLEAVED) mask |= PARAM_MASK_BIT(SNDRV_PCM_ACCESS_MMAP_NONINTERLEAVED); if (hw->info & SNDRV_PCM_INFO_COMPLEX) mask |= PARAM_MASK_BIT(SNDRV_PCM_ACCESS_MMAP_COMPLEX); } err = snd_pcm_hw_constraint_mask(runtime, SNDRV_PCM_HW_PARAM_ACCESS, mask); if (err < 0) return err; err = snd_pcm_hw_constraint_mask64(runtime, SNDRV_PCM_HW_PARAM_FORMAT, hw->formats); if (err < 0) return err; err = snd_pcm_hw_constraint_subformats(runtime, 0, &hw->subformats); if (err < 0) return err; err = snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_CHANNELS, hw->channels_min, hw->channels_max); if (err < 0) return err; err = snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_RATE, hw->rate_min, hw->rate_max); if (err < 0) return err; err = snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_PERIOD_BYTES, hw->period_bytes_min, hw->period_bytes_max); if (err < 0) return err; err = snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_PERIODS, hw->periods_min, hw->periods_max); if (err < 0) return err; err = snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_BUFFER_BYTES, hw->period_bytes_min, hw->buffer_bytes_max); if (err < 0) return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_BYTES, snd_pcm_hw_rule_buffer_bytes_max, substream, SNDRV_PCM_HW_PARAM_BUFFER_BYTES, -1); if (err < 0) return err; /* FIXME: remove */ if (runtime->dma_bytes) { err = snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_BUFFER_BYTES, 0, runtime->dma_bytes); if (err < 0) return err; } if (!(hw->rates & (SNDRV_PCM_RATE_KNOT | SNDRV_PCM_RATE_CONTINUOUS))) { err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, snd_pcm_hw_rule_rate, hw, SNDRV_PCM_HW_PARAM_RATE, -1); if (err < 0) return err; } /* FIXME: this belong to lowlevel */ snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIOD_SIZE); return 0; } static void pcm_release_private(struct snd_pcm_substream *substream) { if (snd_pcm_stream_linked(substream)) snd_pcm_unlink(substream); } void snd_pcm_release_substream(struct snd_pcm_substream *substream) { substream->ref_count--; if (substream->ref_count > 0) return; snd_pcm_drop(substream); if (substream->hw_opened) { if (substream->runtime->state != SNDRV_PCM_STATE_OPEN) do_hw_free(substream); substream->ops->close(substream); substream->hw_opened = 0; } if (cpu_latency_qos_request_active(&substream->latency_pm_qos_req)) cpu_latency_qos_remove_request(&substream->latency_pm_qos_req); if (substream->pcm_release) { substream->pcm_release(substream); substream->pcm_release = NULL; } snd_pcm_detach_substream(substream); } EXPORT_SYMBOL(snd_pcm_release_substream); int snd_pcm_open_substream(struct snd_pcm *pcm, int stream, struct file *file, struct snd_pcm_substream **rsubstream) { struct snd_pcm_substream *substream; int err; err = snd_pcm_attach_substream(pcm, stream, file, &substream); if (err < 0) return err; if (substream->ref_count > 1) { *rsubstream = substream; return 0; } err = snd_pcm_hw_constraints_init(substream); if (err < 0) { pcm_dbg(pcm, "snd_pcm_hw_constraints_init failed\n"); goto error; } err = substream->ops->open(substream); if (err < 0) goto error; substream->hw_opened = 1; err = snd_pcm_hw_constraints_complete(substream); if (err < 0) { pcm_dbg(pcm, "snd_pcm_hw_constraints_complete failed\n"); goto error; } /* automatically set EXPLICIT_SYNC flag in the managed mode whenever * the DMA buffer requires it */ if (substream->managed_buffer_alloc && substream->dma_buffer.dev.need_sync) substream->runtime->hw.info |= SNDRV_PCM_INFO_EXPLICIT_SYNC; *rsubstream = substream; return 0; error: snd_pcm_release_substream(substream); return err; } EXPORT_SYMBOL(snd_pcm_open_substream); static int snd_pcm_open_file(struct file *file, struct snd_pcm *pcm, int stream) { struct snd_pcm_file *pcm_file; struct snd_pcm_substream *substream; int err; err = snd_pcm_open_substream(pcm, stream, file, &substream); if (err < 0) return err; pcm_file = kzalloc(sizeof(*pcm_file), GFP_KERNEL); if (pcm_file == NULL) { snd_pcm_release_substream(substream); return -ENOMEM; } pcm_file->substream = substream; if (substream->ref_count == 1) substream->pcm_release = pcm_release_private; file->private_data = pcm_file; return 0; } static int snd_pcm_playback_open(struct inode *inode, struct file *file) { struct snd_pcm *pcm; int err = nonseekable_open(inode, file); if (err < 0) return err; pcm = snd_lookup_minor_data(iminor(inode), SNDRV_DEVICE_TYPE_PCM_PLAYBACK); err = snd_pcm_open(file, pcm, SNDRV_PCM_STREAM_PLAYBACK); if (pcm) snd_card_unref(pcm->card); return err; } static int snd_pcm_capture_open(struct inode *inode, struct file *file) { struct snd_pcm *pcm; int err = nonseekable_open(inode, file); if (err < 0) return err; pcm = snd_lookup_minor_data(iminor(inode), SNDRV_DEVICE_TYPE_PCM_CAPTURE); err = snd_pcm_open(file, pcm, SNDRV_PCM_STREAM_CAPTURE); if (pcm) snd_card_unref(pcm->card); return err; } static int snd_pcm_open(struct file *file, struct snd_pcm *pcm, int stream) { int err; wait_queue_entry_t wait; if (pcm == NULL) { err = -ENODEV; goto __error1; } err = snd_card_file_add(pcm->card, file); if (err < 0) goto __error1; if (!try_module_get(pcm->card->module)) { err = -EFAULT; goto __error2; } init_waitqueue_entry(&wait, current); add_wait_queue(&pcm->open_wait, &wait); mutex_lock(&pcm->open_mutex); while (1) { err = snd_pcm_open_file(file, pcm, stream); if (err >= 0) break; if (err == -EAGAIN) { if (file->f_flags & O_NONBLOCK) { err = -EBUSY; break; } } else break; set_current_state(TASK_INTERRUPTIBLE); mutex_unlock(&pcm->open_mutex); schedule(); mutex_lock(&pcm->open_mutex); if (pcm->card->shutdown) { err = -ENODEV; break; } if (signal_pending(current)) { err = -ERESTARTSYS; break; } } remove_wait_queue(&pcm->open_wait, &wait); mutex_unlock(&pcm->open_mutex); if (err < 0) goto __error; return err; __error: module_put(pcm->card->module); __error2: snd_card_file_remove(pcm->card, file); __error1: return err; } static int snd_pcm_release(struct inode *inode, struct file *file) { struct snd_pcm *pcm; struct snd_pcm_substream *substream; struct snd_pcm_file *pcm_file; pcm_file = file->private_data; substream = pcm_file->substream; if (snd_BUG_ON(!substream)) return -ENXIO; pcm = substream->pcm; /* block until the device gets woken up as it may touch the hardware */ snd_power_wait(pcm->card); scoped_guard(mutex, &pcm->open_mutex) { snd_pcm_release_substream(substream); kfree(pcm_file); } wake_up(&pcm->open_wait); module_put(pcm->card->module); snd_card_file_remove(pcm->card, file); return 0; } /* check and update PCM state; return 0 or a negative error * call this inside PCM lock */ static int do_pcm_hwsync(struct snd_pcm_substream *substream) { switch (substream->runtime->state) { case SNDRV_PCM_STATE_DRAINING: if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) return -EBADFD; fallthrough; case SNDRV_PCM_STATE_RUNNING: return snd_pcm_update_hw_ptr(substream); case SNDRV_PCM_STATE_PREPARED: case SNDRV_PCM_STATE_PAUSED: return 0; case SNDRV_PCM_STATE_SUSPENDED: return -ESTRPIPE; case SNDRV_PCM_STATE_XRUN: return -EPIPE; default: return -EBADFD; } } /* increase the appl_ptr; returns the processed frames or a negative error */ static snd_pcm_sframes_t forward_appl_ptr(struct snd_pcm_substream *substream, snd_pcm_uframes_t frames, snd_pcm_sframes_t avail) { struct snd_pcm_runtime *runtime = substream->runtime; snd_pcm_sframes_t appl_ptr; int ret; if (avail <= 0) return 0; if (frames > (snd_pcm_uframes_t)avail) frames = avail; appl_ptr = runtime->control->appl_ptr + frames; if (appl_ptr >= (snd_pcm_sframes_t)runtime->boundary) appl_ptr -= runtime->boundary; ret = pcm_lib_apply_appl_ptr(substream, appl_ptr); return ret < 0 ? ret : frames; } /* decrease the appl_ptr; returns the processed frames or zero for error */ static snd_pcm_sframes_t rewind_appl_ptr(struct snd_pcm_substream *substream, snd_pcm_uframes_t frames, snd_pcm_sframes_t avail) { struct snd_pcm_runtime *runtime = substream->runtime; snd_pcm_sframes_t appl_ptr; int ret; if (avail <= 0) return 0; if (frames > (snd_pcm_uframes_t)avail) frames = avail; appl_ptr = runtime->control->appl_ptr - frames; if (appl_ptr < 0) appl_ptr += runtime->boundary; ret = pcm_lib_apply_appl_ptr(substream, appl_ptr); /* NOTE: we return zero for errors because PulseAudio gets depressed * upon receiving an error from rewind ioctl and stops processing * any longer. Returning zero means that no rewind is done, so * it's not absolutely wrong to answer like that. */ return ret < 0 ? 0 : frames; } static snd_pcm_sframes_t snd_pcm_rewind(struct snd_pcm_substream *substream, snd_pcm_uframes_t frames) { snd_pcm_sframes_t ret; if (frames == 0) return 0; scoped_guard(pcm_stream_lock_irq, substream) { ret = do_pcm_hwsync(substream); if (!ret) ret = rewind_appl_ptr(substream, frames, snd_pcm_hw_avail(substream)); } if (ret >= 0) snd_pcm_dma_buffer_sync(substream, SNDRV_DMA_SYNC_DEVICE); return ret; } static snd_pcm_sframes_t snd_pcm_forward(struct snd_pcm_substream *substream, snd_pcm_uframes_t frames) { snd_pcm_sframes_t ret; if (frames == 0) return 0; scoped_guard(pcm_stream_lock_irq, substream) { ret = do_pcm_hwsync(substream); if (!ret) ret = forward_appl_ptr(substream, frames, snd_pcm_avail(substream)); } if (ret >= 0) snd_pcm_dma_buffer_sync(substream, SNDRV_DMA_SYNC_DEVICE); return ret; } static int snd_pcm_delay(struct snd_pcm_substream *substream, snd_pcm_sframes_t *delay) { int err; scoped_guard(pcm_stream_lock_irq, substream) { err = do_pcm_hwsync(substream); if (delay && !err) *delay = snd_pcm_calc_delay(substream); } snd_pcm_dma_buffer_sync(substream, SNDRV_DMA_SYNC_CPU); return err; } static inline int snd_pcm_hwsync(struct snd_pcm_substream *substream) { return snd_pcm_delay(substream, NULL); } #define snd_pcm_sync_ptr_get_user(__f, __c, __ptr) ({ \ __label__ failed, failed_begin; \ int __err = -EFAULT; \ typeof(*(__ptr)) __user *__src = (__ptr); \ \ if (!user_read_access_begin(__src, sizeof(*__src))) \ goto failed_begin; \ unsafe_get_user(__f, &__src->flags, failed); \ unsafe_get_user(__c.appl_ptr, &__src->c.control.appl_ptr, failed); \ unsafe_get_user(__c.avail_min, &__src->c.control.avail_min, failed); \ __err = 0; \ failed: \ user_read_access_end(); \ failed_begin: \ __err; \ }) #define snd_pcm_sync_ptr_put_user(__s, __c, __ptr) ({ \ __label__ failed, failed_begin; \ int __err = -EFAULT; \ typeof(*(__ptr)) __user *__src = (__ptr); \ \ if (!user_write_access_begin(__src, sizeof(*__src))) \ goto failed_begin; \ unsafe_put_user(__s.state, &__src->s.status.state, failed); \ unsafe_put_user(__s.hw_ptr, &__src->s.status.hw_ptr, failed); \ unsafe_put_user(__s.tstamp.tv_sec, &__src->s.status.tstamp.tv_sec, failed); \ unsafe_put_user(__s.tstamp.tv_nsec, &__src->s.status.tstamp.tv_nsec, failed); \ unsafe_put_user(__s.suspended_state, &__src->s.status.suspended_state, failed); \ unsafe_put_user(__s.audio_tstamp.tv_sec, &__src->s.status.audio_tstamp.tv_sec, failed); \ unsafe_put_user(__s.audio_tstamp.tv_nsec, &__src->s.status.audio_tstamp.tv_nsec, failed);\ unsafe_put_user(__c.appl_ptr, &__src->c.control.appl_ptr, failed); \ unsafe_put_user(__c.avail_min, &__src->c.control.avail_min, failed); \ __err = 0; \ failed: \ user_write_access_end(); \ failed_begin: \ __err; \ }) static int snd_pcm_sync_ptr(struct snd_pcm_substream *substream, struct snd_pcm_sync_ptr __user *_sync_ptr) { struct snd_pcm_runtime *runtime = substream->runtime; volatile struct snd_pcm_mmap_status *status; volatile struct snd_pcm_mmap_control *control; u32 sflags; struct snd_pcm_mmap_control scontrol; struct snd_pcm_mmap_status sstatus; int err; if (snd_pcm_sync_ptr_get_user(sflags, scontrol, _sync_ptr)) return -EFAULT; status = runtime->status; control = runtime->control; if (sflags & SNDRV_PCM_SYNC_PTR_HWSYNC) { err = snd_pcm_hwsync(substream); if (err < 0) return err; } scoped_guard(pcm_stream_lock_irq, substream) { if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL)) { err = pcm_lib_apply_appl_ptr(substream, scontrol.appl_ptr); if (err < 0) return err; } else { scontrol.appl_ptr = control->appl_ptr; } if (!(sflags & SNDRV_PCM_SYNC_PTR_AVAIL_MIN)) control->avail_min = scontrol.avail_min; else scontrol.avail_min = control->avail_min; sstatus.state = status->state; sstatus.hw_ptr = status->hw_ptr; sstatus.tstamp = status->tstamp; sstatus.suspended_state = status->suspended_state; sstatus.audio_tstamp = status->audio_tstamp; } if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL)) snd_pcm_dma_buffer_sync(substream, SNDRV_DMA_SYNC_DEVICE); if (snd_pcm_sync_ptr_put_user(sstatus, scontrol, _sync_ptr)) return -EFAULT; return 0; } struct snd_pcm_mmap_status32 { snd_pcm_state_t state; s32 pad1; u32 hw_ptr; struct __snd_timespec tstamp; snd_pcm_state_t suspended_state; struct __snd_timespec audio_tstamp; } __packed; struct snd_pcm_mmap_control32 { u32 appl_ptr; u32 avail_min; }; struct snd_pcm_sync_ptr32 { u32 flags; union { struct snd_pcm_mmap_status32 status; unsigned char reserved[64]; } s; union { struct snd_pcm_mmap_control32 control; unsigned char reserved[64]; } c; } __packed; /* recalculate the boundary within 32bit */ static snd_pcm_uframes_t recalculate_boundary(struct snd_pcm_runtime *runtime) { snd_pcm_uframes_t boundary; snd_pcm_uframes_t border; int order; if (! runtime->buffer_size) return 0; border = 0x7fffffffUL - runtime->buffer_size; if (runtime->buffer_size > border) return runtime->buffer_size; order = __fls(border) - __fls(runtime->buffer_size); boundary = runtime->buffer_size << order; if (boundary <= border) return boundary; else return boundary / 2; } static int snd_pcm_ioctl_sync_ptr_compat(struct snd_pcm_substream *substream, struct snd_pcm_sync_ptr32 __user *src) { struct snd_pcm_runtime *runtime = substream->runtime; volatile struct snd_pcm_mmap_status *status; volatile struct snd_pcm_mmap_control *control; u32 sflags; struct snd_pcm_mmap_control scontrol; struct snd_pcm_mmap_status sstatus; snd_pcm_uframes_t boundary; int err; if (snd_BUG_ON(!runtime)) return -EINVAL; if (snd_pcm_sync_ptr_get_user(sflags, scontrol, src)) return -EFAULT; if (sflags & SNDRV_PCM_SYNC_PTR_HWSYNC) { err = snd_pcm_hwsync(substream); if (err < 0) return err; } status = runtime->status; control = runtime->control; boundary = recalculate_boundary(runtime); if (! boundary) boundary = 0x7fffffff; scoped_guard(pcm_stream_lock_irq, substream) { /* FIXME: we should consider the boundary for the sync from app */ if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL)) { err = pcm_lib_apply_appl_ptr(substream, scontrol.appl_ptr); if (err < 0) return err; } else scontrol.appl_ptr = control->appl_ptr % boundary; if (!(sflags & SNDRV_PCM_SYNC_PTR_AVAIL_MIN)) control->avail_min = scontrol.avail_min; else scontrol.avail_min = control->avail_min; sstatus.state = status->state; sstatus.hw_ptr = status->hw_ptr % boundary; sstatus.tstamp = status->tstamp; sstatus.suspended_state = status->suspended_state; sstatus.audio_tstamp = status->audio_tstamp; } if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL)) snd_pcm_dma_buffer_sync(substream, SNDRV_DMA_SYNC_DEVICE); if (snd_pcm_sync_ptr_put_user(sstatus, scontrol, src)) return -EFAULT; return 0; } #define __SNDRV_PCM_IOCTL_SYNC_PTR32 _IOWR('A', 0x23, struct snd_pcm_sync_ptr32) static int snd_pcm_tstamp(struct snd_pcm_substream *substream, int __user *_arg) { struct snd_pcm_runtime *runtime = substream->runtime; int arg; if (get_user(arg, _arg)) return -EFAULT; if (arg < 0 || arg > SNDRV_PCM_TSTAMP_TYPE_LAST) return -EINVAL; runtime->tstamp_type = arg; return 0; } static int snd_pcm_xferi_frames_ioctl(struct snd_pcm_substream *substream, struct snd_xferi __user *_xferi) { struct snd_xferi xferi; struct snd_pcm_runtime *runtime = substream->runtime; snd_pcm_sframes_t result; if (runtime->state == SNDRV_PCM_STATE_OPEN) return -EBADFD; if (put_user(0, &_xferi->result)) return -EFAULT; if (copy_from_user(&xferi, _xferi, sizeof(xferi))) return -EFAULT; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) result = snd_pcm_lib_write(substream, xferi.buf, xferi.frames); else result = snd_pcm_lib_read(substream, xferi.buf, xferi.frames); if (put_user(result, &_xferi->result)) return -EFAULT; return result < 0 ? result : 0; } static int snd_pcm_xfern_frames_ioctl(struct snd_pcm_substream *substream, struct snd_xfern __user *_xfern) { struct snd_xfern xfern; struct snd_pcm_runtime *runtime = substream->runtime; void *bufs __free(kfree) = NULL; snd_pcm_sframes_t result; if (runtime->state == SNDRV_PCM_STATE_OPEN) return -EBADFD; if (runtime->channels > 128) return -EINVAL; if (put_user(0, &_xfern->result)) return -EFAULT; if (copy_from_user(&xfern, _xfern, sizeof(xfern))) return -EFAULT; bufs = memdup_array_user(xfern.bufs, runtime->channels, sizeof(void *)); if (IS_ERR(bufs)) return PTR_ERR(bufs); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) result = snd_pcm_lib_writev(substream, bufs, xfern.frames); else result = snd_pcm_lib_readv(substream, bufs, xfern.frames); if (put_user(result, &_xfern->result)) return -EFAULT; return result < 0 ? result : 0; } static int snd_pcm_rewind_ioctl(struct snd_pcm_substream *substream, snd_pcm_uframes_t __user *_frames) { snd_pcm_uframes_t frames; snd_pcm_sframes_t result; if (get_user(frames, _frames)) return -EFAULT; if (put_user(0, _frames)) return -EFAULT; result = snd_pcm_rewind(substream, frames); if (put_user(result, _frames)) return -EFAULT; return result < 0 ? result : 0; } static int snd_pcm_forward_ioctl(struct snd_pcm_substream *substream, snd_pcm_uframes_t __user *_frames) { snd_pcm_uframes_t frames; snd_pcm_sframes_t result; if (get_user(frames, _frames)) return -EFAULT; if (put_user(0, _frames)) return -EFAULT; result = snd_pcm_forward(substream, frames); if (put_user(result, _frames)) return -EFAULT; return result < 0 ? result : 0; } static int snd_pcm_common_ioctl(struct file *file, struct snd_pcm_substream *substream, unsigned int cmd, void __user *arg) { struct snd_pcm_file *pcm_file = file->private_data; int res; if (PCM_RUNTIME_CHECK(substream)) return -ENXIO; if (substream->runtime->state == SNDRV_PCM_STATE_DISCONNECTED) return -EBADFD; res = snd_power_wait(substream->pcm->card); if (res < 0) return res; switch (cmd) { case SNDRV_PCM_IOCTL_PVERSION: return put_user(SNDRV_PCM_VERSION, (int __user *)arg) ? -EFAULT : 0; case SNDRV_PCM_IOCTL_INFO: return snd_pcm_info_user(substream, arg); case SNDRV_PCM_IOCTL_TSTAMP: /* just for compatibility */ return 0; case SNDRV_PCM_IOCTL_TTSTAMP: return snd_pcm_tstamp(substream, arg); case SNDRV_PCM_IOCTL_USER_PVERSION: if (get_user(pcm_file->user_pversion, (unsigned int __user *)arg)) return -EFAULT; return 0; case SNDRV_PCM_IOCTL_HW_REFINE: return snd_pcm_hw_refine_user(substream, arg); case SNDRV_PCM_IOCTL_HW_PARAMS: return snd_pcm_hw_params_user(substream, arg); case SNDRV_PCM_IOCTL_HW_FREE: return snd_pcm_hw_free(substream); case SNDRV_PCM_IOCTL_SW_PARAMS: return snd_pcm_sw_params_user(substream, arg); case SNDRV_PCM_IOCTL_STATUS32: return snd_pcm_status_user32(substream, arg, false); case SNDRV_PCM_IOCTL_STATUS_EXT32: return snd_pcm_status_user32(substream, arg, true); case SNDRV_PCM_IOCTL_STATUS64: return snd_pcm_status_user64(substream, arg, false); case SNDRV_PCM_IOCTL_STATUS_EXT64: return snd_pcm_status_user64(substream, arg, true); case SNDRV_PCM_IOCTL_CHANNEL_INFO: return snd_pcm_channel_info_user(substream, arg); case SNDRV_PCM_IOCTL_PREPARE: return snd_pcm_prepare(substream, file); case SNDRV_PCM_IOCTL_RESET: return snd_pcm_reset(substream); case SNDRV_PCM_IOCTL_START: return snd_pcm_start_lock_irq(substream); case SNDRV_PCM_IOCTL_LINK: return snd_pcm_link(substream, (int)(unsigned long) arg); case SNDRV_PCM_IOCTL_UNLINK: return snd_pcm_unlink(substream); case SNDRV_PCM_IOCTL_RESUME: return snd_pcm_resume(substream); case SNDRV_PCM_IOCTL_XRUN: return snd_pcm_xrun(substream); case SNDRV_PCM_IOCTL_HWSYNC: return snd_pcm_hwsync(substream); case SNDRV_PCM_IOCTL_DELAY: { snd_pcm_sframes_t delay = 0; snd_pcm_sframes_t __user *res = arg; int err; err = snd_pcm_delay(substream, &delay); if (err) return err; if (put_user(delay, res)) return -EFAULT; return 0; } case __SNDRV_PCM_IOCTL_SYNC_PTR32: return snd_pcm_ioctl_sync_ptr_compat(substream, arg); case __SNDRV_PCM_IOCTL_SYNC_PTR64: return snd_pcm_sync_ptr(substream, arg); #ifdef CONFIG_SND_SUPPORT_OLD_API case SNDRV_PCM_IOCTL_HW_REFINE_OLD: return snd_pcm_hw_refine_old_user(substream, arg); case SNDRV_PCM_IOCTL_HW_PARAMS_OLD: return snd_pcm_hw_params_old_user(substream, arg); #endif case SNDRV_PCM_IOCTL_DRAIN: return snd_pcm_drain(substream, file); case SNDRV_PCM_IOCTL_DROP: return snd_pcm_drop(substream); case SNDRV_PCM_IOCTL_PAUSE: return snd_pcm_pause_lock_irq(substream, (unsigned long)arg); case SNDRV_PCM_IOCTL_WRITEI_FRAMES: case SNDRV_PCM_IOCTL_READI_FRAMES: return snd_pcm_xferi_frames_ioctl(substream, arg); case SNDRV_PCM_IOCTL_WRITEN_FRAMES: case SNDRV_PCM_IOCTL_READN_FRAMES: return snd_pcm_xfern_frames_ioctl(substream, arg); case SNDRV_PCM_IOCTL_REWIND: return snd_pcm_rewind_ioctl(substream, arg); case SNDRV_PCM_IOCTL_FORWARD: return snd_pcm_forward_ioctl(substream, arg); } pcm_dbg(substream->pcm, "unknown ioctl = 0x%x\n", cmd); return -ENOTTY; } static long snd_pcm_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct snd_pcm_file *pcm_file; pcm_file = file->private_data; if (((cmd >> 8) & 0xff) != 'A') return -ENOTTY; return snd_pcm_common_ioctl(file, pcm_file->substream, cmd, (void __user *)arg); } /** * snd_pcm_kernel_ioctl - Execute PCM ioctl in the kernel-space * @substream: PCM substream * @cmd: IOCTL cmd * @arg: IOCTL argument * * The function is provided primarily for OSS layer and USB gadget drivers, * and it allows only the limited set of ioctls (hw_params, sw_params, * prepare, start, drain, drop, forward). * * Return: zero if successful, or a negative error code */ int snd_pcm_kernel_ioctl(struct snd_pcm_substream *substream, unsigned int cmd, void *arg) { snd_pcm_uframes_t *frames = arg; snd_pcm_sframes_t result; if (substream->runtime->state == SNDRV_PCM_STATE_DISCONNECTED) return -EBADFD; switch (cmd) { case SNDRV_PCM_IOCTL_FORWARD: { /* provided only for OSS; capture-only and no value returned */ if (substream->stream != SNDRV_PCM_STREAM_CAPTURE) return -EINVAL; result = snd_pcm_forward(substream, *frames); return result < 0 ? result : 0; } case SNDRV_PCM_IOCTL_HW_PARAMS: return snd_pcm_hw_params(substream, arg); case SNDRV_PCM_IOCTL_SW_PARAMS: return snd_pcm_sw_params(substream, arg); case SNDRV_PCM_IOCTL_PREPARE: return snd_pcm_prepare(substream, NULL); case SNDRV_PCM_IOCTL_START: return snd_pcm_start_lock_irq(substream); case SNDRV_PCM_IOCTL_DRAIN: return snd_pcm_drain(substream, NULL); case SNDRV_PCM_IOCTL_DROP: return snd_pcm_drop(substream); case SNDRV_PCM_IOCTL_DELAY: return snd_pcm_delay(substream, frames); default: return -EINVAL; } } EXPORT_SYMBOL(snd_pcm_kernel_ioctl); static ssize_t snd_pcm_read(struct file *file, char __user *buf, size_t count, loff_t * offset) { struct snd_pcm_file *pcm_file; struct snd_pcm_substream *substream; struct snd_pcm_runtime *runtime; snd_pcm_sframes_t result; pcm_file = file->private_data; substream = pcm_file->substream; if (PCM_RUNTIME_CHECK(substream)) return -ENXIO; runtime = substream->runtime; if (runtime->state == SNDRV_PCM_STATE_OPEN || runtime->state == SNDRV_PCM_STATE_DISCONNECTED) return -EBADFD; if (!frame_aligned(runtime, count)) return -EINVAL; count = bytes_to_frames(runtime, count); result = snd_pcm_lib_read(substream, buf, count); if (result > 0) result = frames_to_bytes(runtime, result); return result; } static ssize_t snd_pcm_write(struct file *file, const char __user *buf, size_t count, loff_t * offset) { struct snd_pcm_file *pcm_file; struct snd_pcm_substream *substream; struct snd_pcm_runtime *runtime; snd_pcm_sframes_t result; pcm_file = file->private_data; substream = pcm_file->substream; if (PCM_RUNTIME_CHECK(substream)) return -ENXIO; runtime = substream->runtime; if (runtime->state == SNDRV_PCM_STATE_OPEN || runtime->state == SNDRV_PCM_STATE_DISCONNECTED) return -EBADFD; if (!frame_aligned(runtime, count)) return -EINVAL; count = bytes_to_frames(runtime, count); result = snd_pcm_lib_write(substream, buf, count); if (result > 0) result = frames_to_bytes(runtime, result); return result; } static ssize_t snd_pcm_readv(struct kiocb *iocb, struct iov_iter *to) { struct snd_pcm_file *pcm_file; struct snd_pcm_substream *substream; struct snd_pcm_runtime *runtime; snd_pcm_sframes_t result; unsigned long i; void __user **bufs __free(kfree) = NULL; snd_pcm_uframes_t frames; const struct iovec *iov = iter_iov(to); pcm_file = iocb->ki_filp->private_data; substream = pcm_file->substream; if (PCM_RUNTIME_CHECK(substream)) return -ENXIO; runtime = substream->runtime; if (runtime->state == SNDRV_PCM_STATE_OPEN || runtime->state == SNDRV_PCM_STATE_DISCONNECTED) return -EBADFD; if (!user_backed_iter(to)) return -EINVAL; if (to->nr_segs > 1024 || to->nr_segs != runtime->channels) return -EINVAL; if (!frame_aligned(runtime, iov->iov_len)) return -EINVAL; frames = bytes_to_samples(runtime, iov->iov_len); bufs = kmalloc_array(to->nr_segs, sizeof(void *), GFP_KERNEL); if (bufs == NULL) return -ENOMEM; for (i = 0; i < to->nr_segs; ++i) { bufs[i] = iov->iov_base; iov++; } result = snd_pcm_lib_readv(substream, bufs, frames); if (result > 0) result = frames_to_bytes(runtime, result); return result; } static ssize_t snd_pcm_writev(struct kiocb *iocb, struct iov_iter *from) { struct snd_pcm_file *pcm_file; struct snd_pcm_substream *substream; struct snd_pcm_runtime *runtime; snd_pcm_sframes_t result; unsigned long i; void __user **bufs __free(kfree) = NULL; snd_pcm_uframes_t frames; const struct iovec *iov = iter_iov(from); pcm_file = iocb->ki_filp->private_data; substream = pcm_file->substream; if (PCM_RUNTIME_CHECK(substream)) return -ENXIO; runtime = substream->runtime; if (runtime->state == SNDRV_PCM_STATE_OPEN || runtime->state == SNDRV_PCM_STATE_DISCONNECTED) return -EBADFD; if (!user_backed_iter(from)) return -EINVAL; if (from->nr_segs > 128 || from->nr_segs != runtime->channels || !frame_aligned(runtime, iov->iov_len)) return -EINVAL; frames = bytes_to_samples(runtime, iov->iov_len); bufs = kmalloc_array(from->nr_segs, sizeof(void *), GFP_KERNEL); if (bufs == NULL) return -ENOMEM; for (i = 0; i < from->nr_segs; ++i) { bufs[i] = iov->iov_base; iov++; } result = snd_pcm_lib_writev(substream, bufs, frames); if (result > 0) result = frames_to_bytes(runtime, result); return result; } static __poll_t snd_pcm_poll(struct file *file, poll_table *wait) { struct snd_pcm_file *pcm_file; struct snd_pcm_substream *substream; struct snd_pcm_runtime *runtime; __poll_t mask, ok; snd_pcm_uframes_t avail; pcm_file = file->private_data; substream = pcm_file->substream; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ok = EPOLLOUT | EPOLLWRNORM; else ok = EPOLLIN | EPOLLRDNORM; if (PCM_RUNTIME_CHECK(substream)) return ok | EPOLLERR; runtime = substream->runtime; if (runtime->state == SNDRV_PCM_STATE_DISCONNECTED) return ok | EPOLLERR; poll_wait(file, &runtime->sleep, wait); mask = 0; guard(pcm_stream_lock_irq)(substream); avail = snd_pcm_avail(substream); switch (runtime->state) { case SNDRV_PCM_STATE_RUNNING: case SNDRV_PCM_STATE_PREPARED: case SNDRV_PCM_STATE_PAUSED: if (avail >= runtime->control->avail_min) mask = ok; break; case SNDRV_PCM_STATE_DRAINING: if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) { mask = ok; if (!avail) mask |= EPOLLERR; } break; default: mask = ok | EPOLLERR; break; } return mask; } /* * mmap support */ /* * Only on coherent architectures, we can mmap the status and the control records * for effcient data transfer. On others, we have to use HWSYNC ioctl... */ #if defined(CONFIG_X86) || defined(CONFIG_PPC) || defined(CONFIG_ALPHA) /* * mmap status record */ static vm_fault_t snd_pcm_mmap_status_fault(struct vm_fault *vmf) { struct snd_pcm_substream *substream = vmf->vma->vm_private_data; struct snd_pcm_runtime *runtime; if (substream == NULL) return VM_FAULT_SIGBUS; runtime = substream->runtime; vmf->page = virt_to_page(runtime->status); get_page(vmf->page); return 0; } static const struct vm_operations_struct snd_pcm_vm_ops_status = { .fault = snd_pcm_mmap_status_fault, }; static int snd_pcm_mmap_status(struct snd_pcm_substream *substream, struct file *file, struct vm_area_struct *area) { long size; if (!(area->vm_flags & VM_READ)) return -EINVAL; size = area->vm_end - area->vm_start; if (size != PAGE_ALIGN(sizeof(struct snd_pcm_mmap_status))) return -EINVAL; area->vm_ops = &snd_pcm_vm_ops_status; area->vm_private_data = substream; vm_flags_mod(area, VM_DONTEXPAND | VM_DONTDUMP, VM_WRITE | VM_MAYWRITE); return 0; } /* * mmap control record */ static vm_fault_t snd_pcm_mmap_control_fault(struct vm_fault *vmf) { struct snd_pcm_substream *substream = vmf->vma->vm_private_data; struct snd_pcm_runtime *runtime; if (substream == NULL) return VM_FAULT_SIGBUS; runtime = substream->runtime; vmf->page = virt_to_page(runtime->control); get_page(vmf->page); return 0; } static const struct vm_operations_struct snd_pcm_vm_ops_control = { .fault = snd_pcm_mmap_control_fault, }; static int snd_pcm_mmap_control(struct snd_pcm_substream *substream, struct file *file, struct vm_area_struct *area) { long size; if (!(area->vm_flags & VM_READ)) return -EINVAL; size = area->vm_end - area->vm_start; if (size != PAGE_ALIGN(sizeof(struct snd_pcm_mmap_control))) return -EINVAL; area->vm_ops = &snd_pcm_vm_ops_control; area->vm_private_data = substream; vm_flags_set(area, VM_DONTEXPAND | VM_DONTDUMP); return 0; } static bool pcm_status_mmap_allowed(struct snd_pcm_file *pcm_file) { /* If drivers require the explicit sync (typically for non-coherent * pages), we have to disable the mmap of status and control data * to enforce the control via SYNC_PTR ioctl. */ if (pcm_file->substream->runtime->hw.info & SNDRV_PCM_INFO_EXPLICIT_SYNC) return false; /* See pcm_control_mmap_allowed() below. * Since older alsa-lib requires both status and control mmaps to be * coupled, we have to disable the status mmap for old alsa-lib, too. */ if (pcm_file->user_pversion < SNDRV_PROTOCOL_VERSION(2, 0, 14) && (pcm_file->substream->runtime->hw.info & SNDRV_PCM_INFO_SYNC_APPLPTR)) return false; return true; } static bool pcm_control_mmap_allowed(struct snd_pcm_file *pcm_file) { if (pcm_file->no_compat_mmap) return false; /* see above */ if (pcm_file->substream->runtime->hw.info & SNDRV_PCM_INFO_EXPLICIT_SYNC) return false; /* Disallow the control mmap when SYNC_APPLPTR flag is set; * it enforces the user-space to fall back to snd_pcm_sync_ptr(), * thus it effectively assures the manual update of appl_ptr. */ if (pcm_file->substream->runtime->hw.info & SNDRV_PCM_INFO_SYNC_APPLPTR) return false; return true; } #else /* ! coherent mmap */ /* * don't support mmap for status and control records. */ #define pcm_status_mmap_allowed(pcm_file) false #define pcm_control_mmap_allowed(pcm_file) false static int snd_pcm_mmap_status(struct snd_pcm_substream *substream, struct file *file, struct vm_area_struct *area) { return -ENXIO; } static int snd_pcm_mmap_control(struct snd_pcm_substream *substream, struct file *file, struct vm_area_struct *area) { return -ENXIO; } #endif /* coherent mmap */ /* * snd_pcm_mmap_data_open - increase the mmap counter */ static void snd_pcm_mmap_data_open(struct vm_area_struct *area) { struct snd_pcm_substream *substream = area->vm_private_data; atomic_inc(&substream->mmap_count); } /* * snd_pcm_mmap_data_close - decrease the mmap counter */ static void snd_pcm_mmap_data_close(struct vm_area_struct *area) { struct snd_pcm_substream *substream = area->vm_private_data; atomic_dec(&substream->mmap_count); } /* * fault callback for mmapping a RAM page */ static vm_fault_t snd_pcm_mmap_data_fault(struct vm_fault *vmf) { struct snd_pcm_substream *substream = vmf->vma->vm_private_data; struct snd_pcm_runtime *runtime; unsigned long offset; struct page * page; size_t dma_bytes; if (substream == NULL) return VM_FAULT_SIGBUS; runtime = substream->runtime; offset = vmf->pgoff << PAGE_SHIFT; dma_bytes = PAGE_ALIGN(runtime->dma_bytes); if (offset > dma_bytes - PAGE_SIZE) return VM_FAULT_SIGBUS; if (substream->ops->page) page = substream->ops->page(substream, offset); else if (!snd_pcm_get_dma_buf(substream)) { if (WARN_ON_ONCE(!runtime->dma_area)) return VM_FAULT_SIGBUS; page = virt_to_page(runtime->dma_area + offset); } else page = snd_sgbuf_get_page(snd_pcm_get_dma_buf(substream), offset); if (!page) return VM_FAULT_SIGBUS; get_page(page); vmf->page = page; return 0; } static const struct vm_operations_struct snd_pcm_vm_ops_data = { .open = snd_pcm_mmap_data_open, .close = snd_pcm_mmap_data_close, }; static const struct vm_operations_struct snd_pcm_vm_ops_data_fault = { .open = snd_pcm_mmap_data_open, .close = snd_pcm_mmap_data_close, .fault = snd_pcm_mmap_data_fault, }; /* * mmap the DMA buffer on RAM */ /** * snd_pcm_lib_default_mmap - Default PCM data mmap function * @substream: PCM substream * @area: VMA * * This is the default mmap handler for PCM data. When mmap pcm_ops is NULL, * this function is invoked implicitly. * * Return: zero if successful, or a negative error code */ int snd_pcm_lib_default_mmap(struct snd_pcm_substream *substream, struct vm_area_struct *area) { vm_flags_set(area, VM_DONTEXPAND | VM_DONTDUMP); if (!substream->ops->page && !snd_dma_buffer_mmap(snd_pcm_get_dma_buf(substream), area)) return 0; /* mmap with fault handler */ area->vm_ops = &snd_pcm_vm_ops_data_fault; return 0; } EXPORT_SYMBOL_GPL(snd_pcm_lib_default_mmap); /* * mmap the DMA buffer on I/O memory area */ #if SNDRV_PCM_INFO_MMAP_IOMEM /** * snd_pcm_lib_mmap_iomem - Default PCM data mmap function for I/O mem * @substream: PCM substream * @area: VMA * * When your hardware uses the iomapped pages as the hardware buffer and * wants to mmap it, pass this function as mmap pcm_ops. Note that this * is supposed to work only on limited architectures. * * Return: zero if successful, or a negative error code */ int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream, struct vm_area_struct *area) { struct snd_pcm_runtime *runtime = substream->runtime; area->vm_page_prot = pgprot_noncached(area->vm_page_prot); return vm_iomap_memory(area, runtime->dma_addr, runtime->dma_bytes); } EXPORT_SYMBOL(snd_pcm_lib_mmap_iomem); #endif /* SNDRV_PCM_INFO_MMAP */ /* * mmap DMA buffer */ int snd_pcm_mmap_data(struct snd_pcm_substream *substream, struct file *file, struct vm_area_struct *area) { struct snd_pcm_runtime *runtime; long size; unsigned long offset; size_t dma_bytes; int err; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { if (!(area->vm_flags & (VM_WRITE|VM_READ))) return -EINVAL; } else { if (!(area->vm_flags & VM_READ)) return -EINVAL; } runtime = substream->runtime; if (runtime->state == SNDRV_PCM_STATE_OPEN) return -EBADFD; if (!(runtime->info & SNDRV_PCM_INFO_MMAP)) return -ENXIO; if (runtime->access == SNDRV_PCM_ACCESS_RW_INTERLEAVED || runtime->access == SNDRV_PCM_ACCESS_RW_NONINTERLEAVED) return -EINVAL; size = area->vm_end - area->vm_start; offset = area->vm_pgoff << PAGE_SHIFT; dma_bytes = PAGE_ALIGN(runtime->dma_bytes); if ((size_t)size > dma_bytes) return -EINVAL; if (offset > dma_bytes - size) return -EINVAL; area->vm_ops = &snd_pcm_vm_ops_data; area->vm_private_data = substream; if (substream->ops->mmap) err = substream->ops->mmap(substream, area); else err = snd_pcm_lib_default_mmap(substream, area); if (!err) atomic_inc(&substream->mmap_count); return err; } EXPORT_SYMBOL(snd_pcm_mmap_data); static int snd_pcm_mmap(struct file *file, struct vm_area_struct *area) { struct snd_pcm_file * pcm_file; struct snd_pcm_substream *substream; unsigned long offset; pcm_file = file->private_data; substream = pcm_file->substream; if (PCM_RUNTIME_CHECK(substream)) return -ENXIO; if (substream->runtime->state == SNDRV_PCM_STATE_DISCONNECTED) return -EBADFD; offset = area->vm_pgoff << PAGE_SHIFT; switch (offset) { case SNDRV_PCM_MMAP_OFFSET_STATUS_OLD: if (pcm_file->no_compat_mmap || !IS_ENABLED(CONFIG_64BIT)) return -ENXIO; fallthrough; case SNDRV_PCM_MMAP_OFFSET_STATUS_NEW: if (!pcm_status_mmap_allowed(pcm_file)) return -ENXIO; return snd_pcm_mmap_status(substream, file, area); case SNDRV_PCM_MMAP_OFFSET_CONTROL_OLD: if (pcm_file->no_compat_mmap || !IS_ENABLED(CONFIG_64BIT)) return -ENXIO; fallthrough; case SNDRV_PCM_MMAP_OFFSET_CONTROL_NEW: if (!pcm_control_mmap_allowed(pcm_file)) return -ENXIO; return snd_pcm_mmap_control(substream, file, area); default: return snd_pcm_mmap_data(substream, file, area); } return 0; } static int snd_pcm_fasync(int fd, struct file * file, int on) { struct snd_pcm_file * pcm_file; struct snd_pcm_substream *substream; struct snd_pcm_runtime *runtime; pcm_file = file->private_data; substream = pcm_file->substream; if (PCM_RUNTIME_CHECK(substream)) return -ENXIO; runtime = substream->runtime; if (runtime->state == SNDRV_PCM_STATE_DISCONNECTED) return -EBADFD; return snd_fasync_helper(fd, file, on, &runtime->fasync); } /* * ioctl32 compat */ #ifdef CONFIG_COMPAT #include "pcm_compat.c" #else #define snd_pcm_ioctl_compat NULL #endif /* * To be removed helpers to keep binary compatibility */ #ifdef CONFIG_SND_SUPPORT_OLD_API #define __OLD_TO_NEW_MASK(x) ((x&7)|((x&0x07fffff8)<<5)) #define __NEW_TO_OLD_MASK(x) ((x&7)|((x&0xffffff00)>>5)) static void snd_pcm_hw_convert_from_old_params(struct snd_pcm_hw_params *params, struct snd_pcm_hw_params_old *oparams) { unsigned int i; memset(params, 0, sizeof(*params)); params->flags = oparams->flags; for (i = 0; i < ARRAY_SIZE(oparams->masks); i++) params->masks[i].bits[0] = oparams->masks[i]; memcpy(params->intervals, oparams->intervals, sizeof(oparams->intervals)); params->rmask = __OLD_TO_NEW_MASK(oparams->rmask); params->cmask = __OLD_TO_NEW_MASK(oparams->cmask); params->info = oparams->info; params->msbits = oparams->msbits; params->rate_num = oparams->rate_num; params->rate_den = oparams->rate_den; params->fifo_size = oparams->fifo_size; } static void snd_pcm_hw_convert_to_old_params(struct snd_pcm_hw_params_old *oparams, struct snd_pcm_hw_params *params) { unsigned int i; memset(oparams, 0, sizeof(*oparams)); oparams->flags = params->flags; for (i = 0; i < ARRAY_SIZE(oparams->masks); i++) oparams->masks[i] = params->masks[i].bits[0]; memcpy(oparams->intervals, params->intervals, sizeof(oparams->intervals)); oparams->rmask = __NEW_TO_OLD_MASK(params->rmask); oparams->cmask = __NEW_TO_OLD_MASK(params->cmask); oparams->info = params->info; oparams->msbits = params->msbits; oparams->rate_num = params->rate_num; oparams->rate_den = params->rate_den; oparams->fifo_size = params->fifo_size; } static int snd_pcm_hw_refine_old_user(struct snd_pcm_substream *substream, struct snd_pcm_hw_params_old __user * _oparams) { struct snd_pcm_hw_params *params __free(kfree) = NULL; struct snd_pcm_hw_params_old *oparams __free(kfree) = NULL; int err; params = kmalloc(sizeof(*params), GFP_KERNEL); if (!params) return -ENOMEM; oparams = memdup_user(_oparams, sizeof(*oparams)); if (IS_ERR(oparams)) return PTR_ERR(oparams); snd_pcm_hw_convert_from_old_params(params, oparams); err = snd_pcm_hw_refine(substream, params); if (err < 0) return err; err = fixup_unreferenced_params(substream, params); if (err < 0) return err; snd_pcm_hw_convert_to_old_params(oparams, params); if (copy_to_user(_oparams, oparams, sizeof(*oparams))) return -EFAULT; return 0; } static int snd_pcm_hw_params_old_user(struct snd_pcm_substream *substream, struct snd_pcm_hw_params_old __user * _oparams) { struct snd_pcm_hw_params *params __free(kfree) = NULL; struct snd_pcm_hw_params_old *oparams __free(kfree) = NULL; int err; params = kmalloc(sizeof(*params), GFP_KERNEL); if (!params) return -ENOMEM; oparams = memdup_user(_oparams, sizeof(*oparams)); if (IS_ERR(oparams)) return PTR_ERR(oparams); snd_pcm_hw_convert_from_old_params(params, oparams); err = snd_pcm_hw_params(substream, params); if (err < 0) return err; snd_pcm_hw_convert_to_old_params(oparams, params); if (copy_to_user(_oparams, oparams, sizeof(*oparams))) return -EFAULT; return 0; } #endif /* CONFIG_SND_SUPPORT_OLD_API */ #ifndef CONFIG_MMU static unsigned long snd_pcm_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct snd_pcm_file *pcm_file = file->private_data; struct snd_pcm_substream *substream = pcm_file->substream; struct snd_pcm_runtime *runtime = substream->runtime; unsigned long offset = pgoff << PAGE_SHIFT; switch (offset) { case SNDRV_PCM_MMAP_OFFSET_STATUS_NEW: return (unsigned long)runtime->status; case SNDRV_PCM_MMAP_OFFSET_CONTROL_NEW: return (unsigned long)runtime->control; default: return (unsigned long)runtime->dma_area + offset; } } #else # define snd_pcm_get_unmapped_area NULL #endif /* * Register section */ const struct file_operations snd_pcm_f_ops[2] = { { .owner = THIS_MODULE, .write = snd_pcm_write, .write_iter = snd_pcm_writev, .open = snd_pcm_playback_open, .release = snd_pcm_release, .poll = snd_pcm_poll, .unlocked_ioctl = snd_pcm_ioctl, .compat_ioctl = snd_pcm_ioctl_compat, .mmap = snd_pcm_mmap, .fasync = snd_pcm_fasync, .get_unmapped_area = snd_pcm_get_unmapped_area, }, { .owner = THIS_MODULE, .read = snd_pcm_read, .read_iter = snd_pcm_readv, .open = snd_pcm_capture_open, .release = snd_pcm_release, .poll = snd_pcm_poll, .unlocked_ioctl = snd_pcm_ioctl, .compat_ioctl = snd_pcm_ioctl_compat, .mmap = snd_pcm_mmap, .fasync = snd_pcm_fasync, .get_unmapped_area = snd_pcm_get_unmapped_area, } }; |
| 3 3 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * locks.c * * Userspace file locking support * * Copyright (C) 2007 Oracle. All rights reserved. */ #include <linux/fs.h> #include <linux/filelock.h> #include <linux/fcntl.h> #include <cluster/masklog.h> #include "ocfs2.h" #include "dlmglue.h" #include "file.h" #include "inode.h" #include "locks.h" static int ocfs2_do_flock(struct file *file, struct inode *inode, int cmd, struct file_lock *fl) { int ret = 0, level = 0, trylock = 0; struct ocfs2_file_private *fp = file->private_data; struct ocfs2_lock_res *lockres = &fp->fp_flock; if (lock_is_write(fl)) level = 1; if (!IS_SETLKW(cmd)) trylock = 1; mutex_lock(&fp->fp_mutex); if (lockres->l_flags & OCFS2_LOCK_ATTACHED && lockres->l_level > LKM_NLMODE) { int old_level = 0; struct file_lock request; if (lockres->l_level == LKM_EXMODE) old_level = 1; if (level == old_level) goto out; /* * Converting an existing lock is not guaranteed to be * atomic, so we can get away with simply unlocking * here and allowing the lock code to try at the new * level. */ locks_init_lock(&request); request.c.flc_type = F_UNLCK; request.c.flc_flags = FL_FLOCK; locks_lock_file_wait(file, &request); ocfs2_file_unlock(file); } ret = ocfs2_file_lock(file, level, trylock); if (ret) { if (ret == -EAGAIN && trylock) ret = -EWOULDBLOCK; else mlog_errno(ret); goto out; } ret = locks_lock_file_wait(file, fl); if (ret) ocfs2_file_unlock(file); out: mutex_unlock(&fp->fp_mutex); return ret; } static int ocfs2_do_funlock(struct file *file, int cmd, struct file_lock *fl) { int ret; struct ocfs2_file_private *fp = file->private_data; mutex_lock(&fp->fp_mutex); ocfs2_file_unlock(file); ret = locks_lock_file_wait(file, fl); mutex_unlock(&fp->fp_mutex); return ret; } /* * Overall flow of ocfs2_flock() was influenced by gfs2_flock(). */ int ocfs2_flock(struct file *file, int cmd, struct file_lock *fl) { struct inode *inode = file->f_mapping->host; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); if (!(fl->c.flc_flags & FL_FLOCK)) return -ENOLCK; if ((osb->s_mount_opt & OCFS2_MOUNT_LOCALFLOCKS) || ocfs2_mount_local(osb)) return locks_lock_file_wait(file, fl); if (lock_is_unlock(fl)) return ocfs2_do_funlock(file, cmd, fl); else return ocfs2_do_flock(file, inode, cmd, fl); } int ocfs2_lock(struct file *file, int cmd, struct file_lock *fl) { struct inode *inode = file->f_mapping->host; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); if (!(fl->c.flc_flags & FL_POSIX)) return -ENOLCK; return ocfs2_plock(osb->cconn, OCFS2_I(inode)->ip_blkno, file, cmd, fl); } |