| 8 9 9 9 1 9 9 9 41 27 27 20 7 7 41 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * V9FS cache definitions. * * Copyright (C) 2009 by Abhishek Kulkarni <adkulkar@umail.iu.edu> */ #include <linux/jiffies.h> #include <linux/file.h> #include <linux/slab.h> #include <linux/stat.h> #include <linux/sched.h> #include <linux/fs.h> #include <net/9p/9p.h> #include "v9fs.h" #include "cache.h" int v9fs_cache_session_get_cookie(struct v9fs_session_info *v9ses, const char *dev_name) { struct fscache_volume *vcookie; char *name, *p; name = kasprintf(GFP_KERNEL, "9p,%s,%s", dev_name, v9ses->cachetag ?: v9ses->aname); if (!name) return -ENOMEM; for (p = name; *p; p++) if (*p == '/') *p = ';'; vcookie = fscache_acquire_volume(name, NULL, NULL, 0); p9_debug(P9_DEBUG_FSC, "session %p get volume %p (%s)\n", v9ses, vcookie, name); if (IS_ERR(vcookie)) { if (vcookie != ERR_PTR(-EBUSY)) { kfree(name); return PTR_ERR(vcookie); } pr_err("Cache volume key already in use (%s)\n", name); vcookie = NULL; } v9ses->fscache = vcookie; kfree(name); return 0; } void v9fs_cache_inode_get_cookie(struct inode *inode) { struct v9fs_inode *v9inode = V9FS_I(inode); struct v9fs_session_info *v9ses; __le32 version; __le64 path; if (!S_ISREG(inode->i_mode)) return; if (WARN_ON(v9fs_inode_cookie(v9inode))) return; version = cpu_to_le32(v9inode->qid.version); path = cpu_to_le64(v9inode->qid.path); v9ses = v9fs_inode2v9ses(inode); v9inode->netfs.cache = fscache_acquire_cookie(v9fs_session_cache(v9ses), 0, &path, sizeof(path), &version, sizeof(version), i_size_read(&v9inode->netfs.inode)); if (v9inode->netfs.cache) mapping_set_release_always(inode->i_mapping); p9_debug(P9_DEBUG_FSC, "inode %p get cookie %p\n", inode, v9fs_inode_cookie(v9inode)); } |
| 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 | // SPDX-License-Identifier: GPL-2.0-or-later // // core.c -- Voltage/Current Regulator framework. // // Copyright 2007, 2008 Wolfson Microelectronics PLC. // Copyright 2008 SlimLogic Ltd. // // Author: Liam Girdwood <lrg@slimlogic.co.uk> #include <linux/kernel.h> #include <linux/init.h> #include <linux/debugfs.h> #include <linux/device.h> #include <linux/slab.h> #include <linux/async.h> #include <linux/err.h> #include <linux/mutex.h> #include <linux/suspend.h> #include <linux/delay.h> #include <linux/gpio/consumer.h> #include <linux/of.h> #include <linux/reboot.h> #include <linux/regmap.h> #include <linux/regulator/of_regulator.h> #include <linux/regulator/consumer.h> #include <linux/regulator/coupler.h> #include <linux/regulator/driver.h> #include <linux/regulator/machine.h> #include <linux/module.h> #define CREATE_TRACE_POINTS #include <trace/events/regulator.h> #include "dummy.h" #include "internal.h" #include "regnl.h" static DEFINE_WW_CLASS(regulator_ww_class); static DEFINE_MUTEX(regulator_nesting_mutex); static DEFINE_MUTEX(regulator_list_mutex); static LIST_HEAD(regulator_map_list); static LIST_HEAD(regulator_ena_gpio_list); static LIST_HEAD(regulator_supply_alias_list); static LIST_HEAD(regulator_coupler_list); static bool has_full_constraints; static struct dentry *debugfs_root; /* * struct regulator_map * * Used to provide symbolic supply names to devices. */ struct regulator_map { struct list_head list; const char *dev_name; /* The dev_name() for the consumer */ const char *supply; struct regulator_dev *regulator; }; /* * struct regulator_enable_gpio * * Management for shared enable GPIO pin */ struct regulator_enable_gpio { struct list_head list; struct gpio_desc *gpiod; u32 enable_count; /* a number of enabled shared GPIO */ u32 request_count; /* a number of requested shared GPIO */ }; /* * struct regulator_supply_alias * * Used to map lookups for a supply onto an alternative device. */ struct regulator_supply_alias { struct list_head list; struct device *src_dev; const char *src_supply; struct device *alias_dev; const char *alias_supply; }; static int _regulator_is_enabled(struct regulator_dev *rdev); static int _regulator_disable(struct regulator *regulator); static int _regulator_get_error_flags(struct regulator_dev *rdev, unsigned int *flags); static int _regulator_get_current_limit(struct regulator_dev *rdev); static unsigned int _regulator_get_mode(struct regulator_dev *rdev); static int _notifier_call_chain(struct regulator_dev *rdev, unsigned long event, void *data); static int _regulator_do_set_voltage(struct regulator_dev *rdev, int min_uV, int max_uV); static int regulator_balance_voltage(struct regulator_dev *rdev, suspend_state_t state); static struct regulator *create_regulator(struct regulator_dev *rdev, struct device *dev, const char *supply_name); static void destroy_regulator(struct regulator *regulator); static void _regulator_put(struct regulator *regulator); const char *rdev_get_name(struct regulator_dev *rdev) { if (rdev->constraints && rdev->constraints->name) return rdev->constraints->name; else if (rdev->desc->name) return rdev->desc->name; else return ""; } EXPORT_SYMBOL_GPL(rdev_get_name); static bool have_full_constraints(void) { return has_full_constraints || of_have_populated_dt(); } static bool regulator_ops_is_valid(struct regulator_dev *rdev, int ops) { if (!rdev->constraints) { rdev_err(rdev, "no constraints\n"); return false; } if (rdev->constraints->valid_ops_mask & ops) return true; return false; } /** * regulator_lock_nested - lock a single regulator * @rdev: regulator source * @ww_ctx: w/w mutex acquire context * * This function can be called many times by one task on * a single regulator and its mutex will be locked only * once. If a task, which is calling this function is other * than the one, which initially locked the mutex, it will * wait on mutex. * * Return: 0 on success or a negative error number on failure. */ static inline int regulator_lock_nested(struct regulator_dev *rdev, struct ww_acquire_ctx *ww_ctx) { bool lock = false; int ret = 0; mutex_lock(®ulator_nesting_mutex); if (!ww_mutex_trylock(&rdev->mutex, ww_ctx)) { if (rdev->mutex_owner == current) rdev->ref_cnt++; else lock = true; if (lock) { mutex_unlock(®ulator_nesting_mutex); ret = ww_mutex_lock(&rdev->mutex, ww_ctx); mutex_lock(®ulator_nesting_mutex); } } else { lock = true; } if (lock && ret != -EDEADLK) { rdev->ref_cnt++; rdev->mutex_owner = current; } mutex_unlock(®ulator_nesting_mutex); return ret; } /** * regulator_lock - lock a single regulator * @rdev: regulator source * * This function can be called many times by one task on * a single regulator and its mutex will be locked only * once. If a task, which is calling this function is other * than the one, which initially locked the mutex, it will * wait on mutex. */ static void regulator_lock(struct regulator_dev *rdev) { regulator_lock_nested(rdev, NULL); } /** * regulator_unlock - unlock a single regulator * @rdev: regulator_source * * This function unlocks the mutex when the * reference counter reaches 0. */ static void regulator_unlock(struct regulator_dev *rdev) { mutex_lock(®ulator_nesting_mutex); if (--rdev->ref_cnt == 0) { rdev->mutex_owner = NULL; ww_mutex_unlock(&rdev->mutex); } WARN_ON_ONCE(rdev->ref_cnt < 0); mutex_unlock(®ulator_nesting_mutex); } /** * regulator_lock_two - lock two regulators * @rdev1: first regulator * @rdev2: second regulator * @ww_ctx: w/w mutex acquire context * * Locks both rdevs using the regulator_ww_class. */ static void regulator_lock_two(struct regulator_dev *rdev1, struct regulator_dev *rdev2, struct ww_acquire_ctx *ww_ctx) { struct regulator_dev *held, *contended; int ret; ww_acquire_init(ww_ctx, ®ulator_ww_class); /* Try to just grab both of them */ ret = regulator_lock_nested(rdev1, ww_ctx); WARN_ON(ret); ret = regulator_lock_nested(rdev2, ww_ctx); if (ret != -EDEADLOCK) { WARN_ON(ret); goto exit; } held = rdev1; contended = rdev2; while (true) { regulator_unlock(held); ww_mutex_lock_slow(&contended->mutex, ww_ctx); contended->ref_cnt++; contended->mutex_owner = current; swap(held, contended); ret = regulator_lock_nested(contended, ww_ctx); if (ret != -EDEADLOCK) { WARN_ON(ret); break; } } exit: ww_acquire_done(ww_ctx); } /** * regulator_unlock_two - unlock two regulators * @rdev1: first regulator * @rdev2: second regulator * @ww_ctx: w/w mutex acquire context * * The inverse of regulator_lock_two(). */ static void regulator_unlock_two(struct regulator_dev *rdev1, struct regulator_dev *rdev2, struct ww_acquire_ctx *ww_ctx) { regulator_unlock(rdev2); regulator_unlock(rdev1); ww_acquire_fini(ww_ctx); } static bool regulator_supply_is_couple(struct regulator_dev *rdev) { struct regulator_dev *c_rdev; int i; for (i = 1; i < rdev->coupling_desc.n_coupled; i++) { c_rdev = rdev->coupling_desc.coupled_rdevs[i]; if (rdev->supply->rdev == c_rdev) return true; } return false; } static void regulator_unlock_recursive(struct regulator_dev *rdev, unsigned int n_coupled) { struct regulator_dev *c_rdev, *supply_rdev; int i, supply_n_coupled; for (i = n_coupled; i > 0; i--) { c_rdev = rdev->coupling_desc.coupled_rdevs[i - 1]; if (!c_rdev) continue; if (c_rdev->supply && !regulator_supply_is_couple(c_rdev)) { supply_rdev = c_rdev->supply->rdev; supply_n_coupled = supply_rdev->coupling_desc.n_coupled; regulator_unlock_recursive(supply_rdev, supply_n_coupled); } regulator_unlock(c_rdev); } } static int regulator_lock_recursive(struct regulator_dev *rdev, struct regulator_dev **new_contended_rdev, struct regulator_dev **old_contended_rdev, struct ww_acquire_ctx *ww_ctx) { struct regulator_dev *c_rdev; int i, err; for (i = 0; i < rdev->coupling_desc.n_coupled; i++) { c_rdev = rdev->coupling_desc.coupled_rdevs[i]; if (!c_rdev) continue; if (c_rdev != *old_contended_rdev) { err = regulator_lock_nested(c_rdev, ww_ctx); if (err) { if (err == -EDEADLK) { *new_contended_rdev = c_rdev; goto err_unlock; } /* shouldn't happen */ WARN_ON_ONCE(err != -EALREADY); } } else { *old_contended_rdev = NULL; } if (c_rdev->supply && !regulator_supply_is_couple(c_rdev)) { err = regulator_lock_recursive(c_rdev->supply->rdev, new_contended_rdev, old_contended_rdev, ww_ctx); if (err) { regulator_unlock(c_rdev); goto err_unlock; } } } return 0; err_unlock: regulator_unlock_recursive(rdev, i); return err; } /** * regulator_unlock_dependent - unlock regulator's suppliers and coupled * regulators * @rdev: regulator source * @ww_ctx: w/w mutex acquire context * * Unlock all regulators related with rdev by coupling or supplying. */ static void regulator_unlock_dependent(struct regulator_dev *rdev, struct ww_acquire_ctx *ww_ctx) { regulator_unlock_recursive(rdev, rdev->coupling_desc.n_coupled); ww_acquire_fini(ww_ctx); } /** * regulator_lock_dependent - lock regulator's suppliers and coupled regulators * @rdev: regulator source * @ww_ctx: w/w mutex acquire context * * This function as a wrapper on regulator_lock_recursive(), which locks * all regulators related with rdev by coupling or supplying. */ static void regulator_lock_dependent(struct regulator_dev *rdev, struct ww_acquire_ctx *ww_ctx) { struct regulator_dev *new_contended_rdev = NULL; struct regulator_dev *old_contended_rdev = NULL; int err; mutex_lock(®ulator_list_mutex); ww_acquire_init(ww_ctx, ®ulator_ww_class); do { if (new_contended_rdev) { ww_mutex_lock_slow(&new_contended_rdev->mutex, ww_ctx); old_contended_rdev = new_contended_rdev; old_contended_rdev->ref_cnt++; old_contended_rdev->mutex_owner = current; } err = regulator_lock_recursive(rdev, &new_contended_rdev, &old_contended_rdev, ww_ctx); if (old_contended_rdev) regulator_unlock(old_contended_rdev); } while (err == -EDEADLK); ww_acquire_done(ww_ctx); mutex_unlock(®ulator_list_mutex); } /* Platform voltage constraint check */ int regulator_check_voltage(struct regulator_dev *rdev, int *min_uV, int *max_uV) { BUG_ON(*min_uV > *max_uV); if (!regulator_ops_is_valid(rdev, REGULATOR_CHANGE_VOLTAGE)) { rdev_err(rdev, "voltage operation not allowed\n"); return -EPERM; } if (*max_uV > rdev->constraints->max_uV) *max_uV = rdev->constraints->max_uV; if (*min_uV < rdev->constraints->min_uV) *min_uV = rdev->constraints->min_uV; if (*min_uV > *max_uV) { rdev_err(rdev, "unsupportable voltage range: %d-%duV\n", *min_uV, *max_uV); return -EINVAL; } return 0; } /* return 0 if the state is valid */ static int regulator_check_states(suspend_state_t state) { return (state > PM_SUSPEND_MAX || state == PM_SUSPEND_TO_IDLE); } /* Make sure we select a voltage that suits the needs of all * regulator consumers */ int regulator_check_consumers(struct regulator_dev *rdev, int *min_uV, int *max_uV, suspend_state_t state) { struct regulator *regulator; struct regulator_voltage *voltage; list_for_each_entry(regulator, &rdev->consumer_list, list) { voltage = ®ulator->voltage[state]; /* * Assume consumers that didn't say anything are OK * with anything in the constraint range. */ if (!voltage->min_uV && !voltage->max_uV) continue; if (*max_uV > voltage->max_uV) *max_uV = voltage->max_uV; if (*min_uV < voltage->min_uV) *min_uV = voltage->min_uV; } if (*min_uV > *max_uV) { rdev_err(rdev, "Restricting voltage, %u-%uuV\n", *min_uV, *max_uV); return -EINVAL; } return 0; } /* current constraint check */ static int regulator_check_current_limit(struct regulator_dev *rdev, int *min_uA, int *max_uA) { BUG_ON(*min_uA > *max_uA); if (!regulator_ops_is_valid(rdev, REGULATOR_CHANGE_CURRENT)) { rdev_err(rdev, "current operation not allowed\n"); return -EPERM; } if (*max_uA > rdev->constraints->max_uA && rdev->constraints->max_uA) *max_uA = rdev->constraints->max_uA; if (*min_uA < rdev->constraints->min_uA) *min_uA = rdev->constraints->min_uA; if (*min_uA > *max_uA) { rdev_err(rdev, "unsupportable current range: %d-%duA\n", *min_uA, *max_uA); return -EINVAL; } return 0; } /* operating mode constraint check */ static int regulator_mode_constrain(struct regulator_dev *rdev, unsigned int *mode) { switch (*mode) { case REGULATOR_MODE_FAST: case REGULATOR_MODE_NORMAL: case REGULATOR_MODE_IDLE: case REGULATOR_MODE_STANDBY: break; default: rdev_err(rdev, "invalid mode %x specified\n", *mode); return -EINVAL; } if (!regulator_ops_is_valid(rdev, REGULATOR_CHANGE_MODE)) { rdev_err(rdev, "mode operation not allowed\n"); return -EPERM; } /* The modes are bitmasks, the most power hungry modes having * the lowest values. If the requested mode isn't supported * try higher modes. */ while (*mode) { if (rdev->constraints->valid_modes_mask & *mode) return 0; *mode /= 2; } return -EINVAL; } static inline struct regulator_state * regulator_get_suspend_state(struct regulator_dev *rdev, suspend_state_t state) { if (rdev->constraints == NULL) return NULL; switch (state) { case PM_SUSPEND_STANDBY: return &rdev->constraints->state_standby; case PM_SUSPEND_MEM: return &rdev->constraints->state_mem; case PM_SUSPEND_MAX: return &rdev->constraints->state_disk; default: return NULL; } } static const struct regulator_state * regulator_get_suspend_state_check(struct regulator_dev *rdev, suspend_state_t state) { const struct regulator_state *rstate; rstate = regulator_get_suspend_state(rdev, state); if (rstate == NULL) return NULL; /* If we have no suspend mode configuration don't set anything; * only warn if the driver implements set_suspend_voltage or * set_suspend_mode callback. */ if (rstate->enabled != ENABLE_IN_SUSPEND && rstate->enabled != DISABLE_IN_SUSPEND) { if (rdev->desc->ops->set_suspend_voltage || rdev->desc->ops->set_suspend_mode) rdev_warn(rdev, "No configuration\n"); return NULL; } return rstate; } static ssize_t microvolts_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); int uV; regulator_lock(rdev); uV = regulator_get_voltage_rdev(rdev); regulator_unlock(rdev); if (uV < 0) return uV; return sprintf(buf, "%d\n", uV); } static DEVICE_ATTR_RO(microvolts); static ssize_t microamps_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); return sprintf(buf, "%d\n", _regulator_get_current_limit(rdev)); } static DEVICE_ATTR_RO(microamps); static ssize_t name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); return sprintf(buf, "%s\n", rdev_get_name(rdev)); } static DEVICE_ATTR_RO(name); static const char *regulator_opmode_to_str(int mode) { switch (mode) { case REGULATOR_MODE_FAST: return "fast"; case REGULATOR_MODE_NORMAL: return "normal"; case REGULATOR_MODE_IDLE: return "idle"; case REGULATOR_MODE_STANDBY: return "standby"; } return "unknown"; } static ssize_t regulator_print_opmode(char *buf, int mode) { return sprintf(buf, "%s\n", regulator_opmode_to_str(mode)); } static ssize_t opmode_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); return regulator_print_opmode(buf, _regulator_get_mode(rdev)); } static DEVICE_ATTR_RO(opmode); static ssize_t regulator_print_state(char *buf, int state) { if (state > 0) return sprintf(buf, "enabled\n"); else if (state == 0) return sprintf(buf, "disabled\n"); else return sprintf(buf, "unknown\n"); } static ssize_t state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); ssize_t ret; regulator_lock(rdev); ret = regulator_print_state(buf, _regulator_is_enabled(rdev)); regulator_unlock(rdev); return ret; } static DEVICE_ATTR_RO(state); static ssize_t status_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); int status; char *label; status = rdev->desc->ops->get_status(rdev); if (status < 0) return status; switch (status) { case REGULATOR_STATUS_OFF: label = "off"; break; case REGULATOR_STATUS_ON: label = "on"; break; case REGULATOR_STATUS_ERROR: label = "error"; break; case REGULATOR_STATUS_FAST: label = "fast"; break; case REGULATOR_STATUS_NORMAL: label = "normal"; break; case REGULATOR_STATUS_IDLE: label = "idle"; break; case REGULATOR_STATUS_STANDBY: label = "standby"; break; case REGULATOR_STATUS_BYPASS: label = "bypass"; break; case REGULATOR_STATUS_UNDEFINED: label = "undefined"; break; default: return -ERANGE; } return sprintf(buf, "%s\n", label); } static DEVICE_ATTR_RO(status); static ssize_t min_microamps_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); if (!rdev->constraints) return sprintf(buf, "constraint not defined\n"); return sprintf(buf, "%d\n", rdev->constraints->min_uA); } static DEVICE_ATTR_RO(min_microamps); static ssize_t max_microamps_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); if (!rdev->constraints) return sprintf(buf, "constraint not defined\n"); return sprintf(buf, "%d\n", rdev->constraints->max_uA); } static DEVICE_ATTR_RO(max_microamps); static ssize_t min_microvolts_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); if (!rdev->constraints) return sprintf(buf, "constraint not defined\n"); return sprintf(buf, "%d\n", rdev->constraints->min_uV); } static DEVICE_ATTR_RO(min_microvolts); static ssize_t max_microvolts_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); if (!rdev->constraints) return sprintf(buf, "constraint not defined\n"); return sprintf(buf, "%d\n", rdev->constraints->max_uV); } static DEVICE_ATTR_RO(max_microvolts); static ssize_t requested_microamps_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); struct regulator *regulator; int uA = 0; regulator_lock(rdev); list_for_each_entry(regulator, &rdev->consumer_list, list) { if (regulator->enable_count) uA += regulator->uA_load; } regulator_unlock(rdev); return sprintf(buf, "%d\n", uA); } static DEVICE_ATTR_RO(requested_microamps); static ssize_t num_users_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); return sprintf(buf, "%d\n", rdev->use_count); } static DEVICE_ATTR_RO(num_users); static ssize_t type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); switch (rdev->desc->type) { case REGULATOR_VOLTAGE: return sprintf(buf, "voltage\n"); case REGULATOR_CURRENT: return sprintf(buf, "current\n"); } return sprintf(buf, "unknown\n"); } static DEVICE_ATTR_RO(type); static ssize_t suspend_mem_microvolts_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); return sprintf(buf, "%d\n", rdev->constraints->state_mem.uV); } static DEVICE_ATTR_RO(suspend_mem_microvolts); static ssize_t suspend_disk_microvolts_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); return sprintf(buf, "%d\n", rdev->constraints->state_disk.uV); } static DEVICE_ATTR_RO(suspend_disk_microvolts); static ssize_t suspend_standby_microvolts_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); return sprintf(buf, "%d\n", rdev->constraints->state_standby.uV); } static DEVICE_ATTR_RO(suspend_standby_microvolts); static ssize_t suspend_mem_mode_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); return regulator_print_opmode(buf, rdev->constraints->state_mem.mode); } static DEVICE_ATTR_RO(suspend_mem_mode); static ssize_t suspend_disk_mode_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); return regulator_print_opmode(buf, rdev->constraints->state_disk.mode); } static DEVICE_ATTR_RO(suspend_disk_mode); static ssize_t suspend_standby_mode_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); return regulator_print_opmode(buf, rdev->constraints->state_standby.mode); } static DEVICE_ATTR_RO(suspend_standby_mode); static ssize_t suspend_mem_state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); return regulator_print_state(buf, rdev->constraints->state_mem.enabled); } static DEVICE_ATTR_RO(suspend_mem_state); static ssize_t suspend_disk_state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); return regulator_print_state(buf, rdev->constraints->state_disk.enabled); } static DEVICE_ATTR_RO(suspend_disk_state); static ssize_t suspend_standby_state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); return regulator_print_state(buf, rdev->constraints->state_standby.enabled); } static DEVICE_ATTR_RO(suspend_standby_state); static ssize_t bypass_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); const char *report; bool bypass; int ret; ret = rdev->desc->ops->get_bypass(rdev, &bypass); if (ret != 0) report = "unknown"; else if (bypass) report = "enabled"; else report = "disabled"; return sprintf(buf, "%s\n", report); } static DEVICE_ATTR_RO(bypass); static ssize_t power_budget_milliwatt_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); return sprintf(buf, "%d\n", rdev->constraints->pw_budget_mW); } static DEVICE_ATTR_RO(power_budget_milliwatt); static ssize_t power_requested_milliwatt_show(struct device *dev, struct device_attribute *attr, char *buf) { struct regulator_dev *rdev = dev_get_drvdata(dev); return sprintf(buf, "%d\n", rdev->pw_requested_mW); } static DEVICE_ATTR_RO(power_requested_milliwatt); #define REGULATOR_ERROR_ATTR(name, bit) \ static ssize_t name##_show(struct device *dev, struct device_attribute *attr, \ char *buf) \ { \ int ret; \ unsigned int flags; \ struct regulator_dev *rdev = dev_get_drvdata(dev); \ ret = _regulator_get_error_flags(rdev, &flags); \ if (ret) \ return ret; \ return sysfs_emit(buf, "%d\n", !!(flags & (bit))); \ } \ static DEVICE_ATTR_RO(name) REGULATOR_ERROR_ATTR(under_voltage, REGULATOR_ERROR_UNDER_VOLTAGE); REGULATOR_ERROR_ATTR(over_current, REGULATOR_ERROR_OVER_CURRENT); REGULATOR_ERROR_ATTR(regulation_out, REGULATOR_ERROR_REGULATION_OUT); REGULATOR_ERROR_ATTR(fail, REGULATOR_ERROR_FAIL); REGULATOR_ERROR_ATTR(over_temp, REGULATOR_ERROR_OVER_TEMP); REGULATOR_ERROR_ATTR(under_voltage_warn, REGULATOR_ERROR_UNDER_VOLTAGE_WARN); REGULATOR_ERROR_ATTR(over_current_warn, REGULATOR_ERROR_OVER_CURRENT_WARN); REGULATOR_ERROR_ATTR(over_voltage_warn, REGULATOR_ERROR_OVER_VOLTAGE_WARN); REGULATOR_ERROR_ATTR(over_temp_warn, REGULATOR_ERROR_OVER_TEMP_WARN); /* Calculate the new optimum regulator operating mode based on the new total * consumer load. All locks held by caller */ static int drms_uA_update(struct regulator_dev *rdev) { struct regulator *sibling; int current_uA = 0, output_uV, input_uV, err; unsigned int mode; /* * first check to see if we can set modes at all, otherwise just * tell the consumer everything is OK. */ if (!regulator_ops_is_valid(rdev, REGULATOR_CHANGE_DRMS)) { rdev_dbg(rdev, "DRMS operation not allowed\n"); return 0; } if (!rdev->desc->ops->get_optimum_mode && !rdev->desc->ops->set_load) return 0; if (!rdev->desc->ops->set_mode && !rdev->desc->ops->set_load) return -EINVAL; /* calc total requested load */ list_for_each_entry(sibling, &rdev->consumer_list, list) { if (sibling->enable_count) current_uA += sibling->uA_load; } current_uA += rdev->constraints->system_load; if (rdev->desc->ops->set_load) { /* set the optimum mode for our new total regulator load */ err = rdev->desc->ops->set_load(rdev, current_uA); if (err < 0) rdev_err(rdev, "failed to set load %d: %pe\n", current_uA, ERR_PTR(err)); } else { /* * Unfortunately in some cases the constraints->valid_ops has * REGULATOR_CHANGE_DRMS but there are no valid modes listed. * That's not really legit but we won't consider it a fatal * error here. We'll treat it as if REGULATOR_CHANGE_DRMS * wasn't set. */ if (!rdev->constraints->valid_modes_mask) { rdev_dbg(rdev, "Can change modes; but no valid mode\n"); return 0; } /* get output voltage */ output_uV = regulator_get_voltage_rdev(rdev); /* * Don't return an error; if regulator driver cares about * output_uV then it's up to the driver to validate. */ if (output_uV <= 0) rdev_dbg(rdev, "invalid output voltage found\n"); /* get input voltage */ input_uV = 0; if (rdev->supply) input_uV = regulator_get_voltage_rdev(rdev->supply->rdev); if (input_uV <= 0) input_uV = rdev->constraints->input_uV; /* * Don't return an error; if regulator driver cares about * input_uV then it's up to the driver to validate. */ if (input_uV <= 0) rdev_dbg(rdev, "invalid input voltage found\n"); /* now get the optimum mode for our new total regulator load */ mode = rdev->desc->ops->get_optimum_mode(rdev, input_uV, output_uV, current_uA); /* check the new mode is allowed */ err = regulator_mode_constrain(rdev, &mode); if (err < 0) { rdev_err(rdev, "failed to get optimum mode @ %d uA %d -> %d uV: %pe\n", current_uA, input_uV, output_uV, ERR_PTR(err)); return err; } err = rdev->desc->ops->set_mode(rdev, mode); if (err < 0) rdev_err(rdev, "failed to set optimum mode %x: %pe\n", mode, ERR_PTR(err)); } return err; } static int __suspend_set_state(struct regulator_dev *rdev, const struct regulator_state *rstate) { int ret = 0; if (rstate->enabled == ENABLE_IN_SUSPEND && rdev->desc->ops->set_suspend_enable) ret = rdev->desc->ops->set_suspend_enable(rdev); else if (rstate->enabled == DISABLE_IN_SUSPEND && rdev->desc->ops->set_suspend_disable) ret = rdev->desc->ops->set_suspend_disable(rdev); else /* OK if set_suspend_enable or set_suspend_disable is NULL */ ret = 0; if (ret < 0) { rdev_err(rdev, "failed to enabled/disable: %pe\n", ERR_PTR(ret)); return ret; } if (rdev->desc->ops->set_suspend_voltage && rstate->uV > 0) { ret = rdev->desc->ops->set_suspend_voltage(rdev, rstate->uV); if (ret < 0) { rdev_err(rdev, "failed to set voltage: %pe\n", ERR_PTR(ret)); return ret; } } if (rdev->desc->ops->set_suspend_mode && rstate->mode > 0) { ret = rdev->desc->ops->set_suspend_mode(rdev, rstate->mode); if (ret < 0) { rdev_err(rdev, "failed to set mode: %pe\n", ERR_PTR(ret)); return ret; } } return ret; } static int suspend_set_initial_state(struct regulator_dev *rdev) { const struct regulator_state *rstate; rstate = regulator_get_suspend_state_check(rdev, rdev->constraints->initial_state); if (!rstate) return 0; return __suspend_set_state(rdev, rstate); } #if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG) static void print_constraints_debug(struct regulator_dev *rdev) { struct regulation_constraints *constraints = rdev->constraints; char buf[160] = ""; size_t len = sizeof(buf) - 1; int count = 0; int ret; if (constraints->min_uV && constraints->max_uV) { if (constraints->min_uV == constraints->max_uV) count += scnprintf(buf + count, len - count, "%d mV ", constraints->min_uV / 1000); else count += scnprintf(buf + count, len - count, "%d <--> %d mV ", constraints->min_uV / 1000, constraints->max_uV / 1000); } if (!constraints->min_uV || constraints->min_uV != constraints->max_uV) { ret = regulator_get_voltage_rdev(rdev); if (ret > 0) count += scnprintf(buf + count, len - count, "at %d mV ", ret / 1000); } if (constraints->uV_offset) count += scnprintf(buf + count, len - count, "%dmV offset ", constraints->uV_offset / 1000); if (constraints->min_uA && constraints->max_uA) { if (constraints->min_uA == constraints->max_uA) count += scnprintf(buf + count, len - count, "%d mA ", constraints->min_uA / 1000); else count += scnprintf(buf + count, len - count, "%d <--> %d mA ", constraints->min_uA / 1000, constraints->max_uA / 1000); } if (!constraints->min_uA || constraints->min_uA != constraints->max_uA) { ret = _regulator_get_current_limit(rdev); if (ret > 0) count += scnprintf(buf + count, len - count, "at %d mA ", ret / 1000); } if (constraints->valid_modes_mask & REGULATOR_MODE_FAST) count += scnprintf(buf + count, len - count, "fast "); if (constraints->valid_modes_mask & REGULATOR_MODE_NORMAL) count += scnprintf(buf + count, len - count, "normal "); if (constraints->valid_modes_mask & REGULATOR_MODE_IDLE) count += scnprintf(buf + count, len - count, "idle "); if (constraints->valid_modes_mask & REGULATOR_MODE_STANDBY) count += scnprintf(buf + count, len - count, "standby "); if (constraints->pw_budget_mW) count += scnprintf(buf + count, len - count, "%d mW budget", constraints->pw_budget_mW); if (!count) count = scnprintf(buf, len, "no parameters"); else --count; count += scnprintf(buf + count, len - count, ", %s", _regulator_is_enabled(rdev) ? "enabled" : "disabled"); rdev_dbg(rdev, "%s\n", buf); } #else /* !DEBUG && !CONFIG_DYNAMIC_DEBUG */ static inline void print_constraints_debug(struct regulator_dev *rdev) {} #endif /* !DEBUG && !CONFIG_DYNAMIC_DEBUG */ static void print_constraints(struct regulator_dev *rdev) { struct regulation_constraints *constraints = rdev->constraints; print_constraints_debug(rdev); if ((constraints->min_uV != constraints->max_uV) && !regulator_ops_is_valid(rdev, REGULATOR_CHANGE_VOLTAGE)) rdev_warn(rdev, "Voltage range but no REGULATOR_CHANGE_VOLTAGE\n"); } static int machine_constraints_voltage(struct regulator_dev *rdev, struct regulation_constraints *constraints) { const struct regulator_ops *ops = rdev->desc->ops; int ret; /* do we need to apply the constraint voltage */ if (rdev->constraints->apply_uV && rdev->constraints->min_uV && rdev->constraints->max_uV) { int target_min, target_max; int current_uV = regulator_get_voltage_rdev(rdev); if (current_uV == -ENOTRECOVERABLE) { /* This regulator can't be read and must be initialized */ rdev_info(rdev, "Setting %d-%duV\n", rdev->constraints->min_uV, rdev->constraints->max_uV); _regulator_do_set_voltage(rdev, rdev->constraints->min_uV, rdev->constraints->max_uV); current_uV = regulator_get_voltage_rdev(rdev); } if (current_uV < 0) { if (current_uV != -EPROBE_DEFER) rdev_err(rdev, "failed to get the current voltage: %pe\n", ERR_PTR(current_uV)); return current_uV; } /* * If we're below the minimum voltage move up to the * minimum voltage, if we're above the maximum voltage * then move down to the maximum. */ target_min = current_uV; target_max = current_uV; if (current_uV < rdev->constraints->min_uV) { target_min = rdev->constraints->min_uV; target_max = rdev->constraints->min_uV; } if (current_uV > rdev->constraints->max_uV) { target_min = rdev->constraints->max_uV; target_max = rdev->constraints->max_uV; } if (target_min != current_uV || target_max != current_uV) { rdev_info(rdev, "Bringing %duV into %d-%duV\n", current_uV, target_min, target_max); ret = _regulator_do_set_voltage( rdev, target_min, target_max); if (ret < 0) { rdev_err(rdev, "failed to apply %d-%duV constraint: %pe\n", target_min, target_max, ERR_PTR(ret)); return ret; } } } /* constrain machine-level voltage specs to fit * the actual range supported by this regulator. */ if (ops->list_voltage && rdev->desc->n_voltages) { int count = rdev->desc->n_voltages; int i; int min_uV = INT_MAX; int max_uV = INT_MIN; int cmin = constraints->min_uV; int cmax = constraints->max_uV; /* it's safe to autoconfigure fixed-voltage supplies * and the constraints are used by list_voltage. */ if (count == 1 && !cmin) { cmin = 1; cmax = INT_MAX; constraints->min_uV = cmin; constraints->max_uV = cmax; } /* voltage constraints are optional */ if ((cmin == 0) && (cmax == 0)) return 0; /* else require explicit machine-level constraints */ if (cmin <= 0 || cmax <= 0 || cmax < cmin) { rdev_err(rdev, "invalid voltage constraints\n"); return -EINVAL; } /* no need to loop voltages if range is continuous */ if (rdev->desc->continuous_voltage_range) return 0; /* initial: [cmin..cmax] valid, [min_uV..max_uV] not */ for (i = 0; i < count; i++) { int value; value = ops->list_voltage(rdev, i); if (value <= 0) continue; /* maybe adjust [min_uV..max_uV] */ if (value >= cmin && value < min_uV) min_uV = value; if (value <= cmax && value > max_uV) max_uV = value; } /* final: [min_uV..max_uV] valid iff constraints valid */ if (max_uV < min_uV) { rdev_err(rdev, "unsupportable voltage constraints %u-%uuV\n", min_uV, max_uV); return -EINVAL; } /* use regulator's subset of machine constraints */ if (constraints->min_uV < min_uV) { rdev_dbg(rdev, "override min_uV, %d -> %d\n", constraints->min_uV, min_uV); constraints->min_uV = min_uV; } if (constraints->max_uV > max_uV) { rdev_dbg(rdev, "override max_uV, %d -> %d\n", constraints->max_uV, max_uV); constraints->max_uV = max_uV; } } return 0; } static int machine_constraints_current(struct regulator_dev *rdev, struct regulation_constraints *constraints) { const struct regulator_ops *ops = rdev->desc->ops; int ret; if (!constraints->min_uA && !constraints->max_uA) return 0; if (constraints->min_uA > constraints->max_uA) { rdev_err(rdev, "Invalid current constraints\n"); return -EINVAL; } if (!ops->set_current_limit || !ops->get_current_limit) { rdev_warn(rdev, "Operation of current configuration missing\n"); return 0; } /* Set regulator current in constraints range */ ret = ops->set_current_limit(rdev, constraints->min_uA, constraints->max_uA); if (ret < 0) { rdev_err(rdev, "Failed to set current constraint, %d\n", ret); return ret; } return 0; } static int _regulator_do_enable(struct regulator_dev *rdev); static int notif_set_limit(struct regulator_dev *rdev, int (*set)(struct regulator_dev *, int, int, bool), int limit, int severity) { bool enable; if (limit == REGULATOR_NOTIF_LIMIT_DISABLE) { enable = false; limit = 0; } else { enable = true; } if (limit == REGULATOR_NOTIF_LIMIT_ENABLE) limit = 0; return set(rdev, limit, severity, enable); } static int handle_notify_limits(struct regulator_dev *rdev, int (*set)(struct regulator_dev *, int, int, bool), struct notification_limit *limits) { int ret = 0; if (!set) return -EOPNOTSUPP; if (limits->prot) ret = notif_set_limit(rdev, set, limits->prot, REGULATOR_SEVERITY_PROT); if (ret) return ret; if (limits->err) ret = notif_set_limit(rdev, set, limits->err, REGULATOR_SEVERITY_ERR); if (ret) return ret; if (limits->warn) ret = notif_set_limit(rdev, set, limits->warn, REGULATOR_SEVERITY_WARN); return ret; } /** * set_machine_constraints - sets regulator constraints * @rdev: regulator source * * Allows platform initialisation code to define and constrain * regulator circuits e.g. valid voltage/current ranges, etc. NOTE: * Constraints *must* be set by platform code in order for some * regulator operations to proceed i.e. set_voltage, set_current_limit, * set_mode. * * Return: 0 on success or a negative error number on failure. */ static int set_machine_constraints(struct regulator_dev *rdev) { int ret = 0; const struct regulator_ops *ops = rdev->desc->ops; ret = machine_constraints_voltage(rdev, rdev->constraints); if (ret != 0) return ret; ret = machine_constraints_current(rdev, rdev->constraints); if (ret != 0) return ret; if (rdev->constraints->ilim_uA && ops->set_input_current_limit) { ret = ops->set_input_current_limit(rdev, rdev->constraints->ilim_uA); if (ret < 0) { rdev_err(rdev, "failed to set input limit: %pe\n", ERR_PTR(ret)); return ret; } } /* do we need to setup our suspend state */ if (rdev->constraints->initial_state) { ret = suspend_set_initial_state(rdev); if (ret < 0) { rdev_err(rdev, "failed to set suspend state: %pe\n", ERR_PTR(ret)); return ret; } } if (rdev->constraints->initial_mode) { if (!ops->set_mode) { rdev_err(rdev, "no set_mode operation\n"); return -EINVAL; } ret = ops->set_mode(rdev, rdev->constraints->initial_mode); if (ret < 0) { rdev_err(rdev, "failed to set initial mode: %pe\n", ERR_PTR(ret)); return ret; } } else if (rdev->constraints->system_load) { /* * We'll only apply the initial system load if an * initial mode wasn't specified. */ drms_uA_update(rdev); } if ((rdev->constraints->ramp_delay || rdev->constraints->ramp_disable) && ops->set_ramp_delay) { ret = ops->set_ramp_delay(rdev, rdev->constraints->ramp_delay); if (ret < 0) { rdev_err(rdev, "failed to set ramp_delay: %pe\n", ERR_PTR(ret)); return ret; } } if (rdev->constraints->pull_down && ops->set_pull_down) { ret = ops->set_pull_down(rdev); if (ret < 0) { rdev_err(rdev, "failed to set pull down: %pe\n", ERR_PTR(ret)); return ret; } } if (rdev->constraints->soft_start && ops->set_soft_start) { ret = ops->set_soft_start(rdev); if (ret < 0) { rdev_err(rdev, "failed to set soft start: %pe\n", ERR_PTR(ret)); return ret; } } /* * Existing logic does not warn if over_current_protection is given as * a constraint but driver does not support that. I think we should * warn about this type of issues as it is possible someone changes * PMIC on board to another type - and the another PMIC's driver does * not support setting protection. Board composer may happily believe * the DT limits are respected - especially if the new PMIC HW also * supports protection but the driver does not. I won't change the logic * without hearing more experienced opinion on this though. * * If warning is seen as a good idea then we can merge handling the * over-curret protection and detection and get rid of this special * handling. */ if (rdev->constraints->over_current_protection && ops->set_over_current_protection) { int lim = rdev->constraints->over_curr_limits.prot; ret = ops->set_over_current_protection(rdev, lim, REGULATOR_SEVERITY_PROT, true); if (ret < 0) { rdev_err(rdev, "failed to set over current protection: %pe\n", ERR_PTR(ret)); return ret; } } if (rdev->constraints->over_current_detection) ret = handle_notify_limits(rdev, ops->set_over_current_protection, &rdev->constraints->over_curr_limits); if (ret) { if (ret != -EOPNOTSUPP) { rdev_err(rdev, "failed to set over current limits: %pe\n", ERR_PTR(ret)); return ret; } rdev_warn(rdev, "IC does not support requested over-current limits\n"); } if (rdev->constraints->over_voltage_detection) ret = handle_notify_limits(rdev, ops->set_over_voltage_protection, &rdev->constraints->over_voltage_limits); if (ret) { if (ret != -EOPNOTSUPP) { rdev_err(rdev, "failed to set over voltage limits %pe\n", ERR_PTR(ret)); return ret; } rdev_warn(rdev, "IC does not support requested over voltage limits\n"); } if (rdev->constraints->under_voltage_detection) ret = handle_notify_limits(rdev, ops->set_under_voltage_protection, &rdev->constraints->under_voltage_limits); if (ret) { if (ret != -EOPNOTSUPP) { rdev_err(rdev, "failed to set under voltage limits %pe\n", ERR_PTR(ret)); return ret; } rdev_warn(rdev, "IC does not support requested under voltage limits\n"); } if (rdev->constraints->over_temp_detection) ret = handle_notify_limits(rdev, ops->set_thermal_protection, &rdev->constraints->temp_limits); if (ret) { if (ret != -EOPNOTSUPP) { rdev_err(rdev, "failed to set temperature limits %pe\n", ERR_PTR(ret)); return ret; } rdev_warn(rdev, "IC does not support requested temperature limits\n"); } if (rdev->constraints->active_discharge && ops->set_active_discharge) { bool ad_state = (rdev->constraints->active_discharge == REGULATOR_ACTIVE_DISCHARGE_ENABLE) ? true : false; ret = ops->set_active_discharge(rdev, ad_state); if (ret < 0) { rdev_err(rdev, "failed to set active discharge: %pe\n", ERR_PTR(ret)); return ret; } } /* * If there is no mechanism for controlling the regulator then * flag it as always_on so we don't end up duplicating checks * for this so much. Note that we could control the state of * a supply to control the output on a regulator that has no * direct control. */ if (!rdev->ena_pin && !ops->enable) { if (rdev->supply_name && !rdev->supply) return -EPROBE_DEFER; if (rdev->supply) rdev->constraints->always_on = rdev->supply->rdev->constraints->always_on; else rdev->constraints->always_on = true; } /* If the constraints say the regulator should be on at this point * and we have control then make sure it is enabled. */ if (rdev->constraints->always_on || rdev->constraints->boot_on) { /* If we want to enable this regulator, make sure that we know * the supplying regulator. */ if (rdev->supply_name && !rdev->supply) return -EPROBE_DEFER; /* If supplying regulator has already been enabled, * it's not intended to have use_count increment * when rdev is only boot-on. */ if (rdev->supply && (rdev->constraints->always_on || !regulator_is_enabled(rdev->supply))) { ret = regulator_enable(rdev->supply); if (ret < 0) { _regulator_put(rdev->supply); rdev->supply = NULL; return ret; } } ret = _regulator_do_enable(rdev); if (ret < 0 && ret != -EINVAL) { rdev_err(rdev, "failed to enable: %pe\n", ERR_PTR(ret)); return ret; } if (rdev->constraints->always_on) rdev->use_count++; } else if (rdev->desc->off_on_delay) { rdev->last_off = ktime_get(); } if (!rdev->constraints->pw_budget_mW) rdev->constraints->pw_budget_mW = INT_MAX; print_constraints(rdev); return 0; } /** * set_supply - set regulator supply regulator * @rdev: regulator (locked) * @supply_rdev: supply regulator (locked)) * * Called by platform initialisation code to set the supply regulator for this * regulator. This ensures that a regulators supply will also be enabled by the * core if it's child is enabled. * * Return: 0 on success or a negative error number on failure. */ static int set_supply(struct regulator_dev *rdev, struct regulator_dev *supply_rdev) { int err; rdev_dbg(rdev, "supplied by %s\n", rdev_get_name(supply_rdev)); if (!try_module_get(supply_rdev->owner)) return -ENODEV; rdev->supply = create_regulator(supply_rdev, &rdev->dev, "SUPPLY"); if (rdev->supply == NULL) { module_put(supply_rdev->owner); err = -ENOMEM; return err; } supply_rdev->open_count++; return 0; } /** * set_consumer_device_supply - Bind a regulator to a symbolic supply * @rdev: regulator source * @consumer_dev_name: dev_name() string for device supply applies to * @supply: symbolic name for supply * * Allows platform initialisation code to map physical regulator * sources to symbolic names for supplies for use by devices. Devices * should use these symbolic names to request regulators, avoiding the * need to provide board-specific regulator names as platform data. * * Return: 0 on success or a negative error number on failure. */ static int set_consumer_device_supply(struct regulator_dev *rdev, const char *consumer_dev_name, const char *supply) { struct regulator_map *node, *new_node; int has_dev; if (supply == NULL) return -EINVAL; if (consumer_dev_name != NULL) has_dev = 1; else has_dev = 0; new_node = kzalloc(sizeof(struct regulator_map), GFP_KERNEL); if (new_node == NULL) return -ENOMEM; new_node->regulator = rdev; new_node->supply = supply; if (has_dev) { new_node->dev_name = kstrdup(consumer_dev_name, GFP_KERNEL); if (new_node->dev_name == NULL) { kfree(new_node); return -ENOMEM; } } mutex_lock(®ulator_list_mutex); list_for_each_entry(node, ®ulator_map_list, list) { if (node->dev_name && consumer_dev_name) { if (strcmp(node->dev_name, consumer_dev_name) != 0) continue; } else if (node->dev_name || consumer_dev_name) { continue; } if (strcmp(node->supply, supply) != 0) continue; pr_debug("%s: %s/%s is '%s' supply; fail %s/%s\n", consumer_dev_name, dev_name(&node->regulator->dev), node->regulator->desc->name, supply, dev_name(&rdev->dev), rdev_get_name(rdev)); goto fail; } list_add(&new_node->list, ®ulator_map_list); mutex_unlock(®ulator_list_mutex); return 0; fail: mutex_unlock(®ulator_list_mutex); kfree(new_node->dev_name); kfree(new_node); return -EBUSY; } static void unset_regulator_supplies(struct regulator_dev *rdev) { struct regulator_map *node, *n; list_for_each_entry_safe(node, n, ®ulator_map_list, list) { if (rdev == node->regulator) { list_del(&node->list); kfree(node->dev_name); kfree(node); } } } #ifdef CONFIG_DEBUG_FS static ssize_t constraint_flags_read_file(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { const struct regulator *regulator = file->private_data; const struct regulation_constraints *c = regulator->rdev->constraints; char *buf; ssize_t ret; if (!c) return 0; buf = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!buf) return -ENOMEM; ret = snprintf(buf, PAGE_SIZE, "always_on: %u\n" "boot_on: %u\n" "apply_uV: %u\n" "ramp_disable: %u\n" "soft_start: %u\n" "pull_down: %u\n" "over_current_protection: %u\n", c->always_on, c->boot_on, c->apply_uV, c->ramp_disable, c->soft_start, c->pull_down, c->over_current_protection); ret = simple_read_from_buffer(user_buf, count, ppos, buf, ret); kfree(buf); return ret; } #endif static const struct file_operations constraint_flags_fops = { #ifdef CONFIG_DEBUG_FS .open = simple_open, .read = constraint_flags_read_file, .llseek = default_llseek, #endif }; #define REG_STR_SIZE 64 static struct regulator *create_regulator(struct regulator_dev *rdev, struct device *dev, const char *supply_name) { struct regulator *regulator; int err = 0; lockdep_assert_held_once(&rdev->mutex.base); if (dev) { char buf[REG_STR_SIZE]; int size; size = snprintf(buf, REG_STR_SIZE, "%s-%s", dev->kobj.name, supply_name); if (size >= REG_STR_SIZE) return NULL; supply_name = kstrdup(buf, GFP_KERNEL); if (supply_name == NULL) return NULL; } else { supply_name = kstrdup_const(supply_name, GFP_KERNEL); if (supply_name == NULL) return NULL; } regulator = kzalloc(sizeof(*regulator), GFP_KERNEL); if (regulator == NULL) { kfree_const(supply_name); return NULL; } regulator->rdev = rdev; regulator->supply_name = supply_name; list_add(®ulator->list, &rdev->consumer_list); if (dev) { regulator->dev = dev; /* Add a link to the device sysfs entry */ err = sysfs_create_link_nowarn(&rdev->dev.kobj, &dev->kobj, supply_name); if (err) { rdev_dbg(rdev, "could not add device link %s: %pe\n", dev->kobj.name, ERR_PTR(err)); /* non-fatal */ } } if (err != -EEXIST) { regulator->debugfs = debugfs_create_dir(supply_name, rdev->debugfs); if (IS_ERR(regulator->debugfs)) { rdev_dbg(rdev, "Failed to create debugfs directory\n"); regulator->debugfs = NULL; } } if (regulator->debugfs) { debugfs_create_u32("uA_load", 0444, regulator->debugfs, ®ulator->uA_load); debugfs_create_u32("min_uV", 0444, regulator->debugfs, ®ulator->voltage[PM_SUSPEND_ON].min_uV); debugfs_create_u32("max_uV", 0444, regulator->debugfs, ®ulator->voltage[PM_SUSPEND_ON].max_uV); debugfs_create_file("constraint_flags", 0444, regulator->debugfs, regulator, &constraint_flags_fops); } /* * Check now if the regulator is an always on regulator - if * it is then we don't need to do nearly so much work for * enable/disable calls. */ if (!regulator_ops_is_valid(rdev, REGULATOR_CHANGE_STATUS) && _regulator_is_enabled(rdev)) regulator->always_on = true; return regulator; } static int _regulator_get_enable_time(struct regulator_dev *rdev) { if (rdev->constraints && rdev->constraints->enable_time) return rdev->constraints->enable_time; if (rdev->desc->ops->enable_time) return rdev->desc->ops->enable_time(rdev); return rdev->desc->enable_time; } static struct regulator_supply_alias *regulator_find_supply_alias( struct device *dev, const char *supply) { struct regulator_supply_alias *map; list_for_each_entry(map, ®ulator_supply_alias_list, list) if (map->src_dev == dev && strcmp(map->src_supply, supply) == 0) return map; return NULL; } static void regulator_supply_alias(struct device **dev, const char **supply) { struct regulator_supply_alias *map; map = regulator_find_supply_alias(*dev, *supply); if (map) { dev_dbg(*dev, "Mapping supply %s to %s,%s\n", *supply, map->alias_supply, dev_name(map->alias_dev)); *dev = map->alias_dev; *supply = map->alias_supply; } } static int regulator_match(struct device *dev, const void *data) { struct regulator_dev *r = dev_to_rdev(dev); return strcmp(rdev_get_name(r), data) == 0; } static struct regulator_dev *regulator_lookup_by_name(const char *name) { struct device *dev; dev = class_find_device(®ulator_class, NULL, name, regulator_match); return dev ? dev_to_rdev(dev) : NULL; } static struct regulator_dev *regulator_dt_lookup(struct device *dev, const char *supply) { struct regulator_dev *r = NULL; if (dev_of_node(dev)) { r = of_regulator_dev_lookup(dev, dev_of_node(dev), supply); if (PTR_ERR(r) == -ENODEV) r = NULL; } return r; } /** * regulator_dev_lookup - lookup a regulator device. * @dev: device for regulator "consumer". * @supply: Supply name or regulator ID. * * Return: pointer to &struct regulator_dev or ERR_PTR() encoded negative error number. * * If successful, returns a struct regulator_dev that corresponds to the name * @supply and with the embedded struct device refcount incremented by one. * The refcount must be dropped by calling put_device(). * On failure one of the following ERR_PTR() encoded values is returned: * -%ENODEV if lookup fails permanently, -%EPROBE_DEFER if lookup could succeed * in the future. */ static struct regulator_dev *regulator_dev_lookup(struct device *dev, const char *supply) { struct regulator_dev *r = NULL; struct regulator_map *map; const char *devname = NULL; regulator_supply_alias(&dev, &supply); /* first do a dt based lookup */ r = regulator_dt_lookup(dev, supply); if (r) return r; /* if not found, try doing it non-dt way */ if (dev) devname = dev_name(dev); mutex_lock(®ulator_list_mutex); list_for_each_entry(map, ®ulator_map_list, list) { /* If the mapping has a device set up it must match */ if (map->dev_name && (!devname || strcmp(map->dev_name, devname))) continue; if (strcmp(map->supply, supply) == 0 && get_device(&map->regulator->dev)) { r = map->regulator; break; } } mutex_unlock(®ulator_list_mutex); if (r) return r; r = regulator_lookup_by_name(supply); if (r) return r; return ERR_PTR(-ENODEV); } static int regulator_resolve_supply(struct regulator_dev *rdev) { struct regulator_dev *r; struct device *dev = rdev->dev.parent; struct ww_acquire_ctx ww_ctx; int ret = 0; /* No supply to resolve? */ if (!rdev->supply_name) return 0; /* Supply already resolved? (fast-path without locking contention) */ if (rdev->supply) return 0; /* first do a dt based lookup on the node described in the virtual * device. */ r = regulator_dt_lookup(&rdev->dev, rdev->supply_name); /* If regulator not found use usual search path in the parent * device. */ if (!r) r = regulator_dev_lookup(dev, rdev->supply_name); if (IS_ERR(r)) { ret = PTR_ERR(r); /* Did the lookup explicitly defer for us? */ if (ret == -EPROBE_DEFER) goto out; if (have_full_constraints()) { r = dummy_regulator_rdev; get_device(&r->dev); } else { dev_err(dev, "Failed to resolve %s-supply for %s\n", rdev->supply_name, rdev->desc->name); ret = -EPROBE_DEFER; goto out; } } if (r == rdev) { dev_err(dev, "Supply for %s (%s) resolved to itself\n", rdev->desc->name, rdev->supply_name); if (!have_full_constraints()) { ret = -EINVAL; goto out; } r = dummy_regulator_rdev; get_device(&r->dev); } /* * If the supply's parent device is not the same as the * regulator's parent device, then ensure the parent device * is bound before we resolve the supply, in case the parent * device get probe deferred and unregisters the supply. */ if (r->dev.parent && r->dev.parent != rdev->dev.parent) { if (!device_is_bound(r->dev.parent)) { put_device(&r->dev); ret = -EPROBE_DEFER; goto out; } } /* Recursively resolve the supply of the supply */ ret = regulator_resolve_supply(r); if (ret < 0) { put_device(&r->dev); goto out; } /* * Recheck rdev->supply with rdev->mutex lock held to avoid a race * between rdev->supply null check and setting rdev->supply in * set_supply() from concurrent tasks. */ regulator_lock_two(rdev, r, &ww_ctx); /* Supply just resolved by a concurrent task? */ if (rdev->supply) { regulator_unlock_two(rdev, r, &ww_ctx); put_device(&r->dev); goto out; } ret = set_supply(rdev, r); if (ret < 0) { regulator_unlock_two(rdev, r, &ww_ctx); put_device(&r->dev); goto out; } regulator_unlock_two(rdev, r, &ww_ctx); /* * In set_machine_constraints() we may have turned this regulator on * but we couldn't propagate to the supply if it hadn't been resolved * yet. Do it now. */ if (rdev->use_count) { ret = regulator_enable(rdev->supply); if (ret < 0) { _regulator_put(rdev->supply); rdev->supply = NULL; goto out; } } out: return ret; } /* common pre-checks for regulator requests */ int _regulator_get_common_check(struct device *dev, const char *id, enum regulator_get_type get_type) { if (get_type >= MAX_GET_TYPE) { dev_err(dev, "invalid type %d in %s\n", get_type, __func__); return -EINVAL; } if (id == NULL) { dev_err(dev, "regulator request with no identifier\n"); return -EINVAL; } return 0; } /** * _regulator_get_common - Common code for regulator requests * @rdev: regulator device pointer as returned by *regulator_dev_lookup() * Its reference count is expected to have been incremented. * @dev: device used for dev_printk messages * @id: Supply name or regulator ID * @get_type: enum regulator_get_type value corresponding to type of request * * Returns: pointer to struct regulator corresponding to @rdev, or ERR_PTR() * encoded error. * * This function should be chained with *regulator_dev_lookup() functions. */ struct regulator *_regulator_get_common(struct regulator_dev *rdev, struct device *dev, const char *id, enum regulator_get_type get_type) { struct regulator *regulator; struct device_link *link; int ret; if (IS_ERR(rdev)) { ret = PTR_ERR(rdev); /* * If regulator_dev_lookup() fails with error other * than -ENODEV our job here is done, we simply return it. */ if (ret != -ENODEV) return ERR_PTR(ret); if (!have_full_constraints()) { dev_warn(dev, "incomplete constraints, dummy supplies not allowed (id=%s)\n", id); return ERR_PTR(-ENODEV); } switch (get_type) { case NORMAL_GET: /* * Assume that a regulator is physically present and * enabled, even if it isn't hooked up, and just * provide a dummy. */ dev_warn(dev, "supply %s not found, using dummy regulator\n", id); rdev = dummy_regulator_rdev; get_device(&rdev->dev); break; case EXCLUSIVE_GET: dev_warn(dev, "dummy supplies not allowed for exclusive requests (id=%s)\n", id); fallthrough; default: return ERR_PTR(-ENODEV); } } if (rdev->exclusive) { regulator = ERR_PTR(-EPERM); put_device(&rdev->dev); return regulator; } if (get_type == EXCLUSIVE_GET && rdev->open_count) { regulator = ERR_PTR(-EBUSY); put_device(&rdev->dev); return regulator; } mutex_lock(®ulator_list_mutex); ret = (rdev->coupling_desc.n_resolved != rdev->coupling_desc.n_coupled); mutex_unlock(®ulator_list_mutex); if (ret != 0) { regulator = ERR_PTR(-EPROBE_DEFER); put_device(&rdev->dev); return regulator; } ret = regulator_resolve_supply(rdev); if (ret < 0) { regulator = ERR_PTR(ret); put_device(&rdev->dev); return regulator; } if (!try_module_get(rdev->owner)) { regulator = ERR_PTR(-EPROBE_DEFER); put_device(&rdev->dev); return regulator; } regulator_lock(rdev); regulator = create_regulator(rdev, dev, id); regulator_unlock(rdev); if (regulator == NULL) { regulator = ERR_PTR(-ENOMEM); module_put(rdev->owner); put_device(&rdev->dev); return regulator; } rdev->open_count++; if (get_type == EXCLUSIVE_GET) { rdev->exclusive = 1; ret = _regulator_is_enabled(rdev); if (ret > 0) { rdev->use_count = 1; regulator->enable_count = 1; /* Propagate the regulator state to its supply */ if (rdev->supply) { ret = regulator_enable(rdev->supply); if (ret < 0) { destroy_regulator(regulator); module_put(rdev->owner); put_device(&rdev->dev); return ERR_PTR(ret); } } } else { rdev->use_count = 0; regulator->enable_count = 0; } } link = device_link_add(dev, &rdev->dev, DL_FLAG_STATELESS); if (!IS_ERR_OR_NULL(link)) regulator->device_link = true; return regulator; } /* Internal regulator request function */ struct regulator *_regulator_get(struct device *dev, const char *id, enum regulator_get_type get_type) { struct regulator_dev *rdev; int ret; ret = _regulator_get_common_check(dev, id, get_type); if (ret) return ERR_PTR(ret); rdev = regulator_dev_lookup(dev, id); return _regulator_get_common(rdev, dev, id, get_type); } /** * regulator_get - lookup and obtain a reference to a regulator. * @dev: device for regulator "consumer" * @id: Supply name or regulator ID. * * Use of supply names configured via set_consumer_device_supply() is * strongly encouraged. It is recommended that the supply name used * should match the name used for the supply and/or the relevant * device pins in the datasheet. * * Return: Pointer to a &struct regulator corresponding to the regulator * producer, or an ERR_PTR() encoded negative error number. */ struct regulator *regulator_get(struct device *dev, const char *id) { return _regulator_get(dev, id, NORMAL_GET); } EXPORT_SYMBOL_GPL(regulator_get); /** * regulator_get_exclusive - obtain exclusive access to a regulator. * @dev: device for regulator "consumer" * @id: Supply name or regulator ID. * * Other consumers will be unable to obtain this regulator while this * reference is held and the use count for the regulator will be * initialised to reflect the current state of the regulator. * * This is intended for use by consumers which cannot tolerate shared * use of the regulator such as those which need to force the * regulator off for correct operation of the hardware they are * controlling. * * Use of supply names configured via set_consumer_device_supply() is * strongly encouraged. It is recommended that the supply name used * should match the name used for the supply and/or the relevant * device pins in the datasheet. * * Return: Pointer to a &struct regulator corresponding to the regulator * producer, or an ERR_PTR() encoded negative error number. */ struct regulator *regulator_get_exclusive(struct device *dev, const char *id) { return _regulator_get(dev, id, EXCLUSIVE_GET); } EXPORT_SYMBOL_GPL(regulator_get_exclusive); /** * regulator_get_optional - obtain optional access to a regulator. * @dev: device for regulator "consumer" * @id: Supply name or regulator ID. * * This is intended for use by consumers for devices which can have * some supplies unconnected in normal use, such as some MMC devices. * It can allow the regulator core to provide stub supplies for other * supplies requested using normal regulator_get() calls without * disrupting the operation of drivers that can handle absent * supplies. * * Use of supply names configured via set_consumer_device_supply() is * strongly encouraged. It is recommended that the supply name used * should match the name used for the supply and/or the relevant * device pins in the datasheet. * * Return: Pointer to a &struct regulator corresponding to the regulator * producer, or an ERR_PTR() encoded negative error number. */ struct regulator *regulator_get_optional(struct device *dev, const char *id) { return _regulator_get(dev, id, OPTIONAL_GET); } EXPORT_SYMBOL_GPL(regulator_get_optional); static void destroy_regulator(struct regulator *regulator) { struct regulator_dev *rdev = regulator->rdev; debugfs_remove_recursive(regulator->debugfs); if (regulator->dev) { if (regulator->device_link) device_link_remove(regulator->dev, &rdev->dev); /* remove any sysfs entries */ sysfs_remove_link(&rdev->dev.kobj, regulator->supply_name); } regulator_lock(rdev); list_del(®ulator->list); rdev->open_count--; rdev->exclusive = 0; regulator_unlock(rdev); kfree_const(regulator->supply_name); kfree(regulator); } /* regulator_list_mutex lock held by regulator_put() */ static void _regulator_put(struct regulator *regulator) { struct regulator_dev *rdev; if (IS_ERR_OR_NULL(regulator)) return; lockdep_assert_held_once(®ulator_list_mutex); /* Docs say you must disable before calling regulator_put() */ WARN_ON(regulator->enable_count); rdev = regulator->rdev; destroy_regulator(regulator); module_put(rdev->owner); put_device(&rdev->dev); } /** * regulator_put - "free" the regulator source * @regulator: regulator source * * Note: drivers must ensure that all regulator_enable calls made on this * regulator source are balanced by regulator_disable calls prior to calling * this function. */ void regulator_put(struct regulator *regulator) { mutex_lock(®ulator_list_mutex); _regulator_put(regulator); mutex_unlock(®ulator_list_mutex); } EXPORT_SYMBOL_GPL(regulator_put); /** * regulator_register_supply_alias - Provide device alias for supply lookup * * @dev: device that will be given as the regulator "consumer" * @id: Supply name or regulator ID * @alias_dev: device that should be used to lookup the supply * @alias_id: Supply name or regulator ID that should be used to lookup the * supply * * All lookups for id on dev will instead be conducted for alias_id on * alias_dev. * * Return: 0 on success or a negative error number on failure. */ int regulator_register_supply_alias(struct device *dev, const char *id, struct device *alias_dev, const char *alias_id) { struct regulator_supply_alias *map; map = regulator_find_supply_alias(dev, id); if (map) return -EEXIST; map = kzalloc(sizeof(struct regulator_supply_alias), GFP_KERNEL); if (!map) return -ENOMEM; map->src_dev = dev; map->src_supply = id; map->alias_dev = alias_dev; map->alias_supply = alias_id; list_add(&map->list, ®ulator_supply_alias_list); pr_info("Adding alias for supply %s,%s -> %s,%s\n", id, dev_name(dev), alias_id, dev_name(alias_dev)); return 0; } EXPORT_SYMBOL_GPL(regulator_register_supply_alias); /** * regulator_unregister_supply_alias - Remove device alias * * @dev: device that will be given as the regulator "consumer" * @id: Supply name or regulator ID * * Remove a lookup alias if one exists for id on dev. */ void regulator_unregister_supply_alias(struct device *dev, const char *id) { struct regulator_supply_alias *map; map = regulator_find_supply_alias(dev, id); if (map) { list_del(&map->list); kfree(map); } } EXPORT_SYMBOL_GPL(regulator_unregister_supply_alias); /** * regulator_bulk_register_supply_alias - register multiple aliases * * @dev: device that will be given as the regulator "consumer" * @id: List of supply names or regulator IDs * @alias_dev: device that should be used to lookup the supply * @alias_id: List of supply names or regulator IDs that should be used to * lookup the supply * @num_id: Number of aliases to register * * This helper function allows drivers to register several supply * aliases in one operation. If any of the aliases cannot be * registered any aliases that were registered will be removed * before returning to the caller. * * Return: 0 on success or a negative error number on failure. */ int regulator_bulk_register_supply_alias(struct device *dev, const char *const *id, struct device *alias_dev, const char *const *alias_id, int num_id) { int i; int ret; for (i = 0; i < num_id; ++i) { ret = regulator_register_supply_alias(dev, id[i], alias_dev, alias_id[i]); if (ret < 0) goto err; } return 0; err: dev_err(dev, "Failed to create supply alias %s,%s -> %s,%s\n", id[i], dev_name(dev), alias_id[i], dev_name(alias_dev)); while (--i >= 0) regulator_unregister_supply_alias(dev, id[i]); return ret; } EXPORT_SYMBOL_GPL(regulator_bulk_register_supply_alias); /** * regulator_bulk_unregister_supply_alias - unregister multiple aliases * * @dev: device that will be given as the regulator "consumer" * @id: List of supply names or regulator IDs * @num_id: Number of aliases to unregister * * This helper function allows drivers to unregister several supply * aliases in one operation. */ void regulator_bulk_unregister_supply_alias(struct device *dev, const char *const *id, int num_id) { int i; for (i = 0; i < num_id; ++i) regulator_unregister_supply_alias(dev, id[i]); } EXPORT_SYMBOL_GPL(regulator_bulk_unregister_supply_alias); /* Manage enable GPIO list. Same GPIO pin can be shared among regulators */ static int regulator_ena_gpio_request(struct regulator_dev *rdev, const struct regulator_config *config) { struct regulator_enable_gpio *pin, *new_pin; struct gpio_desc *gpiod; gpiod = config->ena_gpiod; new_pin = kzalloc(sizeof(*new_pin), GFP_KERNEL); mutex_lock(®ulator_list_mutex); list_for_each_entry(pin, ®ulator_ena_gpio_list, list) { if (pin->gpiod == gpiod) { rdev_dbg(rdev, "GPIO is already used\n"); goto update_ena_gpio_to_rdev; } } if (new_pin == NULL) { mutex_unlock(®ulator_list_mutex); return -ENOMEM; } pin = new_pin; new_pin = NULL; pin->gpiod = gpiod; list_add(&pin->list, ®ulator_ena_gpio_list); update_ena_gpio_to_rdev: pin->request_count++; rdev->ena_pin = pin; mutex_unlock(®ulator_list_mutex); kfree(new_pin); return 0; } static void regulator_ena_gpio_free(struct regulator_dev *rdev) { struct regulator_enable_gpio *pin, *n; if (!rdev->ena_pin) return; /* Free the GPIO only in case of no use */ list_for_each_entry_safe(pin, n, ®ulator_ena_gpio_list, list) { if (pin != rdev->ena_pin) continue; if (--pin->request_count) break; gpiod_put(pin->gpiod); list_del(&pin->list); kfree(pin); break; } rdev->ena_pin = NULL; } /** * regulator_ena_gpio_ctrl - balance enable_count of each GPIO and actual GPIO pin control * @rdev: regulator_dev structure * @enable: enable GPIO at initial use? * * GPIO is enabled in case of initial use. (enable_count is 0) * GPIO is disabled when it is not shared any more. (enable_count <= 1) * * Return: 0 on success or a negative error number on failure. */ static int regulator_ena_gpio_ctrl(struct regulator_dev *rdev, bool enable) { struct regulator_enable_gpio *pin = rdev->ena_pin; if (!pin) return -EINVAL; if (enable) { /* Enable GPIO at initial use */ if (pin->enable_count == 0) gpiod_set_value_cansleep(pin->gpiod, 1); pin->enable_count++; } else { if (pin->enable_count > 1) { pin->enable_count--; return 0; } /* Disable GPIO if not used */ if (pin->enable_count <= 1) { gpiod_set_value_cansleep(pin->gpiod, 0); pin->enable_count = 0; } } return 0; } /** * _regulator_check_status_enabled - check if regulator status can be * interpreted as "regulator is enabled" * @rdev: the regulator device to check * * Return: * * 1 - if status shows regulator is in enabled state * * 0 - if not enabled state * * Error Value - as received from ops->get_status() */ static inline int _regulator_check_status_enabled(struct regulator_dev *rdev) { int ret = rdev->desc->ops->get_status(rdev); if (ret < 0) { rdev_info(rdev, "get_status returned error: %d\n", ret); return ret; } switch (ret) { case REGULATOR_STATUS_OFF: case REGULATOR_STATUS_ERROR: case REGULATOR_STATUS_UNDEFINED: return 0; default: return 1; } } static int _regulator_do_enable(struct regulator_dev *rdev) { int ret, delay; /* Query before enabling in case configuration dependent. */ ret = _regulator_get_enable_time(rdev); if (ret >= 0) { delay = ret; } else { rdev_warn(rdev, "enable_time() failed: %pe\n", ERR_PTR(ret)); delay = 0; } trace_regulator_enable(rdev_get_name(rdev)); if (rdev->desc->off_on_delay) { /* if needed, keep a distance of off_on_delay from last time * this regulator was disabled. */ ktime_t end = ktime_add_us(rdev->last_off, rdev->desc->off_on_delay); s64 remaining = ktime_us_delta(end, ktime_get_boottime()); if (remaining > 0) fsleep(remaining); } if (rdev->ena_pin) { if (!rdev->ena_gpio_state) { ret = regulator_ena_gpio_ctrl(rdev, true); if (ret < 0) return ret; rdev->ena_gpio_state = 1; } } else if (rdev->desc->ops->enable) { ret = rdev->desc->ops->enable(rdev); if (ret < 0) return ret; } else { return -EINVAL; } /* Allow the regulator to ramp; it would be useful to extend * this for bulk operations so that the regulators can ramp * together. */ trace_regulator_enable_delay(rdev_get_name(rdev)); /* If poll_enabled_time is set, poll upto the delay calculated * above, delaying poll_enabled_time uS to check if the regulator * actually got enabled. * If the regulator isn't enabled after our delay helper has expired, * return -ETIMEDOUT. */ if (rdev->desc->poll_enabled_time) { int time_remaining = delay; while (time_remaining > 0) { fsleep(rdev->desc->poll_enabled_time); if (rdev->desc->ops->get_status) { ret = _regulator_check_status_enabled(rdev); if (ret < 0) return ret; else if (ret) break; } else if (rdev->desc->ops->is_enabled(rdev)) break; time_remaining -= rdev->desc->poll_enabled_time; } if (time_remaining <= 0) { rdev_err(rdev, "Enabled check timed out\n"); return -ETIMEDOUT; } } else { fsleep(delay); } trace_regulator_enable_complete(rdev_get_name(rdev)); return 0; } /** * _regulator_handle_consumer_enable - handle that a consumer enabled * @regulator: regulator source * * Some things on a regulator consumer (like the contribution towards total * load on the regulator) only have an effect when the consumer wants the * regulator enabled. Explained in example with two consumers of the same * regulator: * consumer A: set_load(100); => total load = 0 * consumer A: regulator_enable(); => total load = 100 * consumer B: set_load(1000); => total load = 100 * consumer B: regulator_enable(); => total load = 1100 * consumer A: regulator_disable(); => total_load = 1000 * * This function (together with _regulator_handle_consumer_disable) is * responsible for keeping track of the refcount for a given regulator consumer * and applying / unapplying these things. * * Return: 0 on success or negative error number on failure. */ static int _regulator_handle_consumer_enable(struct regulator *regulator) { int ret; struct regulator_dev *rdev = regulator->rdev; lockdep_assert_held_once(&rdev->mutex.base); regulator->enable_count++; if (regulator->uA_load && regulator->enable_count == 1) { ret = drms_uA_update(rdev); if (ret) regulator->enable_count--; return ret; } return 0; } /** * _regulator_handle_consumer_disable - handle that a consumer disabled * @regulator: regulator source * * The opposite of _regulator_handle_consumer_enable(). * * Return: 0 on success or a negative error number on failure. */ static int _regulator_handle_consumer_disable(struct regulator *regulator) { struct regulator_dev *rdev = regulator->rdev; lockdep_assert_held_once(&rdev->mutex.base); if (!regulator->enable_count) { rdev_err(rdev, "Underflow of regulator enable count\n"); return -EINVAL; } regulator->enable_count--; if (regulator->uA_load && regulator->enable_count == 0) return drms_uA_update(rdev); return 0; } /* locks held by regulator_enable() */ static int _regulator_enable(struct regulator *regulator) { struct regulator_dev *rdev = regulator->rdev; int ret; lockdep_assert_held_once(&rdev->mutex.base); if (rdev->use_count == 0 && rdev->supply) { ret = _regulator_enable(rdev->supply); if (ret < 0) return ret; } /* balance only if there are regulators coupled */ if (rdev->coupling_desc.n_coupled > 1) { ret = regulator_balance_voltage(rdev, PM_SUSPEND_ON); if (ret < 0) goto err_disable_supply; } ret = _regulator_handle_consumer_enable(regulator); if (ret < 0) goto err_disable_supply; if (rdev->use_count == 0) { /* * The regulator may already be enabled if it's not switchable * or was left on */ ret = _regulator_is_enabled(rdev); if (ret == -EINVAL || ret == 0) { if (!regulator_ops_is_valid(rdev, REGULATOR_CHANGE_STATUS)) { ret = -EPERM; goto err_consumer_disable; } ret = _regulator_do_enable(rdev); if (ret < 0) goto err_consumer_disable; _notifier_call_chain(rdev, REGULATOR_EVENT_ENABLE, NULL); } else if (ret < 0) { rdev_err(rdev, "is_enabled() failed: %pe\n", ERR_PTR(ret)); goto err_consumer_disable; } /* Fallthrough on positive return values - already enabled */ } if (regulator->enable_count == 1) rdev->use_count++; return 0; err_consumer_disable: _regulator_handle_consumer_disable(regulator); err_disable_supply: if (rdev->use_count == 0 && rdev->supply) _regulator_disable(rdev->supply); return ret; } /** * regulator_enable - enable regulator output * @regulator: regulator source * * Request that the regulator be enabled with the regulator output at * the predefined voltage or current value. Calls to regulator_enable() * must be balanced with calls to regulator_disable(). * * NOTE: the output value can be set by other drivers, boot loader or may be * hardwired in the regulator. * * Return: 0 on success or a negative error number on failure. */ int regulator_enable(struct regulator *regulator) { struct regulator_dev *rdev = regulator->rdev; struct ww_acquire_ctx ww_ctx; int ret; regulator_lock_dependent(rdev, &ww_ctx); ret = _regulator_enable(regulator); regulator_unlock_dependent(rdev, &ww_ctx); return ret; } EXPORT_SYMBOL_GPL(regulator_enable); static int _regulator_do_disable(struct regulator_dev *rdev) { int ret; trace_regulator_disable(rdev_get_name(rdev)); if (rdev->ena_pin) { if (rdev->ena_gpio_state) { ret = regulator_ena_gpio_ctrl(rdev, false); if (ret < 0) return ret; rdev->ena_gpio_state = 0; } } else if (rdev->desc->ops->disable) { ret = rdev->desc->ops->disable(rdev); if (ret != 0) return ret; } if (rdev->desc->off_on_delay) rdev->last_off = ktime_get_boottime(); trace_regulator_disable_complete(rdev_get_name(rdev)); return 0; } /* locks held by regulator_disable() */ static int _regulator_disable(struct regulator *regulator) { struct regulator_dev *rdev = regulator->rdev; int ret = 0; lockdep_assert_held_once(&rdev->mutex.base); if (WARN(regulator->enable_count == 0, "unbalanced disables for %s\n", rdev_get_name(rdev))) return -EIO; if (regulator->enable_count == 1) { /* disabling last enable_count from this regulator */ /* are we the last user and permitted to disable ? */ if (rdev->use_count == 1 && (rdev->constraints && !rdev->constraints->always_on)) { /* we are last user */ if (regulator_ops_is_valid(rdev, REGULATOR_CHANGE_STATUS)) { ret = _notifier_call_chain(rdev, REGULATOR_EVENT_PRE_DISABLE, NULL); if (ret & NOTIFY_STOP_MASK) return -EINVAL; ret = _regulator_do_disable(rdev); if (ret < 0) { rdev_err(rdev, "failed to disable: %pe\n", ERR_PTR(ret)); _notifier_call_chain(rdev, REGULATOR_EVENT_ABORT_DISABLE, NULL); return ret; } _notifier_call_chain(rdev, REGULATOR_EVENT_DISABLE, NULL); } rdev->use_count = 0; } else if (rdev->use_count > 1) { rdev->use_count--; } } if (ret == 0) ret = _regulator_handle_consumer_disable(regulator); if (ret == 0 && rdev->coupling_desc.n_coupled > 1) ret = regulator_balance_voltage(rdev, PM_SUSPEND_ON); if (ret == 0 && rdev->use_count == 0 && rdev->supply) ret = _regulator_disable(rdev->supply); return ret; } /** * regulator_disable - disable regulator output * @regulator: regulator source * * Disable the regulator output voltage or current. Calls to * regulator_enable() must be balanced with calls to * regulator_disable(). * * NOTE: this will only disable the regulator output if no other consumer * devices have it enabled, the regulator device supports disabling and * machine constraints permit this operation. * * Return: 0 on success or a negative error number on failure. */ int regulator_disable(struct regulator *regulator) { struct regulator_dev *rdev = regulator->rdev; struct ww_acquire_ctx ww_ctx; int ret; regulator_lock_dependent(rdev, &ww_ctx); ret = _regulator_disable(regulator); regulator_unlock_dependent(rdev, &ww_ctx); return ret; } EXPORT_SYMBOL_GPL(regulator_disable); /* locks held by regulator_force_disable() */ static int _regulator_force_disable(struct regulator_dev *rdev) { int ret = 0; lockdep_assert_held_once(&rdev->mutex.base); ret = _notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE | REGULATOR_EVENT_PRE_DISABLE, NULL); if (ret & NOTIFY_STOP_MASK) return -EINVAL; ret = _regulator_do_disable(rdev); if (ret < 0) { rdev_err(rdev, "failed to force disable: %pe\n", ERR_PTR(ret)); _notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE | REGULATOR_EVENT_ABORT_DISABLE, NULL); return ret; } _notifier_call_chain(rdev, REGULATOR_EVENT_FORCE_DISABLE | REGULATOR_EVENT_DISABLE, NULL); return 0; } /** * regulator_force_disable - force disable regulator output * @regulator: regulator source * * Forcibly disable the regulator output voltage or current. * NOTE: this *will* disable the regulator output even if other consumer * devices have it enabled. This should be used for situations when device * damage will likely occur if the regulator is not disabled (e.g. over temp). * * Return: 0 on success or a negative error number on failure. */ int regulator_force_disable(struct regulator *regulator) { struct regulator_dev *rdev = regulator->rdev; struct ww_acquire_ctx ww_ctx; int ret; regulator_lock_dependent(rdev, &ww_ctx); ret = _regulator_force_disable(regulator->rdev); if (rdev->coupling_desc.n_coupled > 1) regulator_balance_voltage(rdev, PM_SUSPEND_ON); if (regulator->uA_load) { regulator->uA_load = 0; ret = drms_uA_update(rdev); } if (rdev->use_count != 0 && rdev->supply) _regulator_disable(rdev->supply); regulator_unlock_dependent(rdev, &ww_ctx); return ret; } EXPORT_SYMBOL_GPL(regulator_force_disable); static void regulator_disable_work(struct work_struct *work) { struct regulator_dev *rdev = container_of(work, struct regulator_dev, disable_work.work); struct ww_acquire_ctx ww_ctx; int count, i, ret; struct regulator *regulator; int total_count = 0; regulator_lock_dependent(rdev, &ww_ctx); /* * Workqueue functions queue the new work instance while the previous * work instance is being processed. Cancel the queued work instance * as the work instance under processing does the job of the queued * work instance. */ cancel_delayed_work(&rdev->disable_work); list_for_each_entry(regulator, &rdev->consumer_list, list) { count = regulator->deferred_disables; if (!count) continue; total_count += count; regulator->deferred_disables = 0; for (i = 0; i < count; i++) { ret = _regulator_disable(regulator); if (ret != 0) rdev_err(rdev, "Deferred disable failed: %pe\n", ERR_PTR(ret)); } } WARN_ON(!total_count); if (rdev->coupling_desc.n_coupled > 1) regulator_balance_voltage(rdev, PM_SUSPEND_ON); regulator_unlock_dependent(rdev, &ww_ctx); } /** * regulator_disable_deferred - disable regulator output with delay * @regulator: regulator source * @ms: milliseconds until the regulator is disabled * * Execute regulator_disable() on the regulator after a delay. This * is intended for use with devices that require some time to quiesce. * * NOTE: this will only disable the regulator output if no other consumer * devices have it enabled, the regulator device supports disabling and * machine constraints permit this operation. * * Return: 0 on success or a negative error number on failure. */ int regulator_disable_deferred(struct regulator *regulator, int ms) { struct regulator_dev *rdev = regulator->rdev; if (!ms) return regulator_disable(regulator); regulator_lock(rdev); regulator->deferred_disables++; mod_delayed_work(system_power_efficient_wq, &rdev->disable_work, msecs_to_jiffies(ms)); regulator_unlock(rdev); return 0; } EXPORT_SYMBOL_GPL(regulator_disable_deferred); static int _regulator_is_enabled(struct regulator_dev *rdev) { /* A GPIO control always takes precedence */ if (rdev->ena_pin) return rdev->ena_gpio_state; /* If we don't know then assume that the regulator is always on */ if (!rdev->desc->ops->is_enabled) return 1; return rdev->desc->ops->is_enabled(rdev); } static int _regulator_list_voltage(struct regulator_dev *rdev, unsigned selector, int lock) { const struct regulator_ops *ops = rdev->desc->ops; int ret; if (rdev->desc->fixed_uV && rdev->desc->n_voltages == 1 && !selector) return rdev->desc->fixed_uV; if (ops->list_voltage) { if (selector >= rdev->desc->n_voltages) return -EINVAL; if (selector < rdev->desc->linear_min_sel) return 0; if (lock) regulator_lock(rdev); ret = ops->list_voltage(rdev, selector); if (lock) regulator_unlock(rdev); } else if (rdev->is_switch && rdev->supply) { ret = _regulator_list_voltage(rdev->supply->rdev, selector, lock); } else { return -EINVAL; } if (ret > 0) { if (ret < rdev->constraints->min_uV) ret = 0; else if (ret > rdev->constraints->max_uV) ret = 0; } return ret; } /** * regulator_is_enabled - is the regulator output enabled * @regulator: regulator source * * Note that the device backing this regulator handle can have multiple * users, so it might be enabled even if regulator_enable() was never * called for this particular source. * * Return: Positive if the regulator driver backing the source/client * has requested that the device be enabled, zero if it hasn't, * else a negative error number. */ int regulator_is_enabled(struct regulator *regulator) { int ret; if (regulator->always_on) return 1; regulator_lock(regulator->rdev); ret = _regulator_is_enabled(regulator->rdev); regulator_unlock(regulator->rdev); return ret; } EXPORT_SYMBOL_GPL(regulator_is_enabled); /** * regulator_count_voltages - count regulator_list_voltage() selectors * @regulator: regulator source * * Return: Number of selectors for @regulator, or negative error number. * * Selectors are numbered starting at zero, and typically correspond to * bitfields in hardware registers. */ int regulator_count_voltages(struct regulator *regulator) { struct regulator_dev *rdev = regulator->rdev; if (rdev->desc->n_voltages) return rdev->desc->n_voltages; if (!rdev->is_switch || !rdev->supply) return -EINVAL; return regulator_count_voltages(rdev->supply); } EXPORT_SYMBOL_GPL(regulator_count_voltages); /** * regulator_list_voltage - enumerate supported voltages * @regulator: regulator source * @selector: identify voltage to list * Context: can sleep * * Return: Voltage for @selector that can be passed to regulator_set_voltage(), * 0 if @selector can't be used on this system, or a negative error * number on failure. */ int regulator_list_voltage(struct regulator *regulator, unsigned selector) { return _regulator_list_voltage(regulator->rdev, selector, 1); } EXPORT_SYMBOL_GPL(regulator_list_voltage); /** * regulator_get_regmap - get the regulator's register map * @regulator: regulator source * * Return: Pointer to the &struct regmap for @regulator, or ERR_PTR() * encoded -%EOPNOTSUPP if @regulator doesn't use regmap. */ struct regmap *regulator_get_regmap(struct regulator *regulator) { struct regmap *map = regulator->rdev->regmap; return map ? map : ERR_PTR(-EOPNOTSUPP); } EXPORT_SYMBOL_GPL(regulator_get_regmap); /** * regulator_get_hardware_vsel_register - get the HW voltage selector register * @regulator: regulator source * @vsel_reg: voltage selector register, output parameter * @vsel_mask: mask for voltage selector bitfield, output parameter * * Returns the hardware register offset and bitmask used for setting the * regulator voltage. This might be useful when configuring voltage-scaling * hardware or firmware that can make I2C requests behind the kernel's back, * for example. * * Return: 0 on success, or -%EOPNOTSUPP if the regulator does not support * voltage selectors. * * On success, the output parameters @vsel_reg and @vsel_mask are filled in * and 0 is returned, otherwise a negative error number is returned. */ int regulator_get_hardware_vsel_register(struct regulator *regulator, unsigned *vsel_reg, unsigned *vsel_mask) { struct regulator_dev *rdev = regulator->rdev; const struct regulator_ops *ops = rdev->desc->ops; if (ops->set_voltage_sel != regulator_set_voltage_sel_regmap) return -EOPNOTSUPP; *vsel_reg = rdev->desc->vsel_reg; *vsel_mask = rdev->desc->vsel_mask; return 0; } EXPORT_SYMBOL_GPL(regulator_get_hardware_vsel_register); /** * regulator_list_hardware_vsel - get the HW-specific register value for a selector * @regulator: regulator source * @selector: identify voltage to list * * Converts the selector to a hardware-specific voltage selector that can be * directly written to the regulator registers. The address of the voltage * register can be determined by calling @regulator_get_hardware_vsel_register. * * Return: 0 on success, -%EINVAL if the selector is outside the supported * range, or -%EOPNOTSUPP if the regulator does not support voltage * selectors. */ int regulator_list_hardware_vsel(struct regulator *regulator, unsigned selector) { struct regulator_dev *rdev = regulator->rdev; const struct regulator_ops *ops = rdev->desc->ops; if (selector >= rdev->desc->n_voltages) return -EINVAL; if (selector < rdev->desc->linear_min_sel) return 0; if (ops->set_voltage_sel != regulator_set_voltage_sel_regmap) return -EOPNOTSUPP; return selector; } EXPORT_SYMBOL_GPL(regulator_list_hardware_vsel); /** * regulator_hardware_enable - access the HW for enable/disable regulator * @regulator: regulator source * @enable: true for enable, false for disable * * Request that the regulator be enabled/disabled with the regulator output at * the predefined voltage or current value. * * Return: 0 on success or a negative error number on failure. */ int regulator_hardware_enable(struct regulator *regulator, bool enable) { struct regulator_dev *rdev = regulator->rdev; const struct regulator_ops *ops = rdev->desc->ops; int ret = -EOPNOTSUPP; if (!rdev->exclusive || !ops || !ops->enable || !ops->disable) return ret; if (enable) ret = ops->enable(rdev); else ret = ops->disable(rdev); return ret; } EXPORT_SYMBOL_GPL(regulator_hardware_enable); /** * regulator_get_linear_step - return the voltage step size between VSEL values * @regulator: regulator source * * Return: The voltage step size between VSEL values for linear regulators, * or 0 if the regulator isn't a linear regulator. */ unsigned int regulator_get_linear_step(struct regulator *regulator) { struct regulator_dev *rdev = regulator->rdev; return rdev->desc->uV_step; } EXPORT_SYMBOL_GPL(regulator_get_linear_step); /** * regulator_is_supported_voltage - check if a voltage range can be supported * * @regulator: Regulator to check. * @min_uV: Minimum required voltage in uV. * @max_uV: Maximum required voltage in uV. * * Return: 1 if the voltage range is supported, 0 if not, or a negative error * number if @regulator's voltage can't be changed and voltage readback * failed. */ int regulator_is_supported_voltage(struct regulator *regulator, int min_uV, int max_uV) { struct regulator_dev *rdev = regulator->rdev; int i, voltages, ret; /* If we can't change voltage check the current voltage */ if (!regulator_ops_is_valid(rdev, REGULATOR_CHANGE_VOLTAGE)) { ret = regulator_get_voltage(regulator); if (ret >= 0) return min_uV <= ret && ret <= max_uV; else return ret; } /* Any voltage within constrains range is fine? */ if (rdev->desc->continuous_voltage_range) return min_uV >= rdev->constraints->min_uV && max_uV <= rdev->constraints->max_uV; ret = regulator_count_voltages(regulator); if (ret < 0) return 0; voltages = ret; for (i = 0; i < voltages; i++) { ret = regulator_list_voltage(regulator, i); if (ret >= min_uV && ret <= max_uV) return 1; } return 0; } EXPORT_SYMBOL_GPL(regulator_is_supported_voltage); static int regulator_map_voltage(struct regulator_dev *rdev, int min_uV, int max_uV) { const struct regulator_desc *desc = rdev->desc; if (desc->ops->map_voltage) return desc->ops->map_voltage(rdev, min_uV, max_uV); if (desc->ops->list_voltage == regulator_list_voltage_linear) return regulator_map_voltage_linear(rdev, min_uV, max_uV); if (desc->ops->list_voltage == regulator_list_voltage_linear_range) return regulator_map_voltage_linear_range(rdev, min_uV, max_uV); if (desc->ops->list_voltage == regulator_list_voltage_pickable_linear_range) return regulator_map_voltage_pickable_linear_range(rdev, min_uV, max_uV); return regulator_map_voltage_iterate(rdev, min_uV, max_uV); } static int _regulator_call_set_voltage(struct regulator_dev *rdev, int min_uV, int max_uV, unsigned *selector) { struct pre_voltage_change_data data; int ret; data.old_uV = regulator_get_voltage_rdev(rdev); data.min_uV = min_uV; data.max_uV = max_uV; ret = _notifier_call_chain(rdev, REGULATOR_EVENT_PRE_VOLTAGE_CHANGE, &data); if (ret & NOTIFY_STOP_MASK) return -EINVAL; ret = rdev->desc->ops->set_voltage(rdev, min_uV, max_uV, selector); if (ret >= 0) return ret; _notifier_call_chain(rdev, REGULATOR_EVENT_ABORT_VOLTAGE_CHANGE, (void *)data.old_uV); return ret; } static int _regulator_call_set_voltage_sel(struct regulator_dev *rdev, int uV, unsigned selector) { struct pre_voltage_change_data data; int ret; data.old_uV = regulator_get_voltage_rdev(rdev); data.min_uV = uV; data.max_uV = uV; ret = _notifier_call_chain(rdev, REGULATOR_EVENT_PRE_VOLTAGE_CHANGE, &data); if (ret & NOTIFY_STOP_MASK) return -EINVAL; ret = rdev->desc->ops->set_voltage_sel(rdev, selector); if (ret >= 0) return ret; _notifier_call_chain(rdev, REGULATOR_EVENT_ABORT_VOLTAGE_CHANGE, (void *)data.old_uV); return ret; } static int _regulator_set_voltage_sel_step(struct regulator_dev *rdev, int uV, int new_selector) { const struct regulator_ops *ops = rdev->desc->ops; int diff, old_sel, curr_sel, ret; /* Stepping is only needed if the regulator is enabled. */ if (!_regulator_is_enabled(rdev)) goto final_set; if (!ops->get_voltage_sel) return -EINVAL; old_sel = ops->get_voltage_sel(rdev); if (old_sel < 0) return old_sel; diff = new_selector - old_sel; if (diff == 0) return 0; /* No change needed. */ if (diff > 0) { /* Stepping up. */ for (curr_sel = old_sel + rdev->desc->vsel_step; curr_sel < new_selector; curr_sel += rdev->desc->vsel_step) { /* * Call the callback directly instead of using * _regulator_call_set_voltage_sel() as we don't * want to notify anyone yet. Same in the branch * below. */ ret = ops->set_voltage_sel(rdev, curr_sel); if (ret) goto try_revert; } } else { /* Stepping down. */ for (curr_sel = old_sel - rdev->desc->vsel_step; curr_sel > new_selector; curr_sel -= rdev->desc->vsel_step) { ret = ops->set_voltage_sel(rdev, curr_sel); if (ret) goto try_revert; } } final_set: /* The final selector will trigger the notifiers. */ return _regulator_call_set_voltage_sel(rdev, uV, new_selector); try_revert: /* * At least try to return to the previous voltage if setting a new * one failed. */ (void)ops->set_voltage_sel(rdev, old_sel); return ret; } static int _regulator_set_voltage_time(struct regulator_dev *rdev, int old_uV, int new_uV) { unsigned int ramp_delay = 0; if (rdev->constraints->ramp_delay) ramp_delay = rdev->constraints->ramp_delay; else if (rdev->desc->ramp_delay) ramp_delay = rdev->desc->ramp_delay; else if (rdev->constraints->settling_time) return rdev->constraints->settling_time; else if (rdev->constraints->settling_time_up && (new_uV > old_uV)) return rdev->constraints->settling_time_up; else if (rdev->constraints->settling_time_down && (new_uV < old_uV)) return rdev->constraints->settling_time_down; if (ramp_delay == 0) return 0; return DIV_ROUND_UP(abs(new_uV - old_uV), ramp_delay); } static int _regulator_do_set_voltage(struct regulator_dev *rdev, int min_uV, int max_uV) { int ret; int delay = 0; int best_val = 0; unsigned int selector; int old_selector = -1; const struct regulator_ops *ops = rdev->desc->ops; int old_uV = regulator_get_voltage_rdev(rdev); trace_regulator_set_voltage(rdev_get_name(rdev), min_uV, max_uV); min_uV += rdev->constraints->uV_offset; max_uV += rdev->constraints->uV_offset; /* * If we can't obtain the old selector there is not enough * info to call set_voltage_time_sel(). */ if (_regulator_is_enabled(rdev) && ops->set_voltage_time_sel && ops->get_voltage_sel) { old_selector = ops->get_voltage_sel(rdev); if (old_selector < 0) return old_selector; } if (ops->set_voltage) { ret = _regulator_call_set_voltage(rdev, min_uV, max_uV, &selector); if (ret >= 0) { if (ops->list_voltage) best_val = ops->list_voltage(rdev, selector); else best_val = regulator_get_voltage_rdev(rdev); } } else if (ops->set_voltage_sel) { ret = regulator_map_voltage(rdev, min_uV, max_uV); if (ret >= 0) { best_val = ops->list_voltage(rdev, ret); if (min_uV <= best_val && max_uV >= best_val) { selector = ret; if (old_selector == selector) ret = 0; else if (rdev->desc->vsel_step) ret = _regulator_set_voltage_sel_step( rdev, best_val, selector); else ret = _regulator_call_set_voltage_sel( rdev, best_val, selector); } else { ret = -EINVAL; } } } else { ret = -EINVAL; } if (ret) goto out; if (ops->set_voltage_time_sel) { /* * Call set_voltage_time_sel if successfully obtained * old_selector */ if (old_selector >= 0 && old_selector != selector) delay = ops->set_voltage_time_sel(rdev, old_selector, selector); } else { if (old_uV != best_val) { if (ops->set_voltage_time) delay = ops->set_voltage_time(rdev, old_uV, best_val); else delay = _regulator_set_voltage_time(rdev, old_uV, best_val); } } if (delay < 0) { rdev_warn(rdev, "failed to get delay: %pe\n", ERR_PTR(delay)); delay = 0; } /* Insert any necessary delays */ fsleep(delay); if (best_val >= 0) { unsigned long data = best_val; _notifier_call_chain(rdev, REGULATOR_EVENT_VOLTAGE_CHANGE, (void *)data); } out: trace_regulator_set_voltage_complete(rdev_get_name(rdev), best_val); return ret; } static int _regulator_do_set_suspend_voltage(struct regulator_dev *rdev, int min_uV, int max_uV, suspend_state_t state) { struct regulator_state *rstate; int uV, sel; rstate = regulator_get_suspend_state(rdev, state); if (rstate == NULL) return -EINVAL; if (min_uV < rstate->min_uV) min_uV = rstate->min_uV; if (max_uV > rstate->max_uV) max_uV = rstate->max_uV; sel = regulator_map_voltage(rdev, min_uV, max_uV); if (sel < 0) return sel; uV = rdev->desc->ops->list_voltage(rdev, sel); if (uV >= min_uV && uV <= max_uV) rstate->uV = uV; return 0; } static int regulator_set_voltage_unlocked(struct regulator *regulator, int min_uV, int max_uV, suspend_state_t state) { struct regulator_dev *rdev = regulator->rdev; struct regulator_voltage *voltage = ®ulator->voltage[state]; int ret = 0; int old_min_uV, old_max_uV; int current_uV; /* If we're setting the same range as last time the change * should be a noop (some cpufreq implementations use the same * voltage for multiple frequencies, for example). */ if (voltage->min_uV == min_uV && voltage->max_uV == max_uV) goto out; /* If we're trying to set a range that overlaps the current voltage, * return successfully even though the regulator does not support * changing the voltage. */ if (!regulator_ops_is_valid(rdev, REGULATOR_CHANGE_VOLTAGE)) { current_uV = regulator_get_voltage_rdev(rdev); if (min_uV <= current_uV && current_uV <= max_uV) { voltage->min_uV = min_uV; voltage->max_uV = max_uV; goto out; } } /* sanity check */ if (!rdev->desc->ops->set_voltage && !rdev->desc->ops->set_voltage_sel) { ret = -EINVAL; goto out; } /* constraints check */ ret = regulator_check_voltage(rdev, &min_uV, &max_uV); if (ret < 0) goto out; /* restore original values in case of error */ old_min_uV = voltage->min_uV; old_max_uV = voltage->max_uV; voltage->min_uV = min_uV; voltage->max_uV = max_uV; /* for not coupled regulators this will just set the voltage */ ret = regulator_balance_voltage(rdev, state); if (ret < 0) { voltage->min_uV = old_min_uV; voltage->max_uV = old_max_uV; } out: return ret; } int regulator_set_voltage_rdev(struct regulator_dev *rdev, int min_uV, int max_uV, suspend_state_t state) { int best_supply_uV = 0; int supply_change_uV = 0; int ret; if (rdev->supply && regulator_ops_is_valid(rdev->supply->rdev, REGULATOR_CHANGE_VOLTAGE) && (rdev->desc->min_dropout_uV || !(rdev->desc->ops->get_voltage || rdev->desc->ops->get_voltage_sel))) { int current_supply_uV; int selector; selector = regulator_map_voltage(rdev, min_uV, max_uV); if (selector < 0) { ret = selector; goto out; } best_supply_uV = _regulator_list_voltage(rdev, selector, 0); if (best_supply_uV < 0) { ret = best_supply_uV; goto out; } best_supply_uV += rdev->desc->min_dropout_uV; current_supply_uV = regulator_get_voltage_rdev(rdev->supply->rdev); if (current_supply_uV < 0) { ret = current_supply_uV; goto out; } supply_change_uV = best_supply_uV - current_supply_uV; } if (supply_change_uV > 0) { ret = regulator_set_voltage_unlocked(rdev->supply, best_supply_uV, INT_MAX, state); if (ret) { dev_err(&rdev->dev, "Failed to increase supply voltage: %pe\n", ERR_PTR(ret)); goto out; } } if (state == PM_SUSPEND_ON) ret = _regulator_do_set_voltage(rdev, min_uV, max_uV); else ret = _regulator_do_set_suspend_voltage(rdev, min_uV, max_uV, state); if (ret < 0) goto out; if (supply_change_uV < 0) { ret = regulator_set_voltage_unlocked(rdev->supply, best_supply_uV, INT_MAX, state); if (ret) dev_warn(&rdev->dev, "Failed to decrease supply voltage: %pe\n", ERR_PTR(ret)); /* No need to fail here */ ret = 0; } out: return ret; } EXPORT_SYMBOL_GPL(regulator_set_voltage_rdev); static int regulator_limit_voltage_step(struct regulator_dev *rdev, int *current_uV, int *min_uV) { struct regulation_constraints *constraints = rdev->constraints; /* Limit voltage change only if necessary */ if (!constraints->max_uV_step || !_regulator_is_enabled(rdev)) return 1; if (*current_uV < 0) { *current_uV = regulator_get_voltage_rdev(rdev); if (*current_uV < 0) return *current_uV; } if (abs(*current_uV - *min_uV) <= constraints->max_uV_step) return 1; /* Clamp target voltage within the given step */ if (*current_uV < *min_uV) *min_uV = min(*current_uV + constraints->max_uV_step, *min_uV); else *min_uV = max(*current_uV - constraints->max_uV_step, *min_uV); return 0; } static int regulator_get_optimal_voltage(struct regulator_dev *rdev, int *current_uV, int *min_uV, int *max_uV, suspend_state_t state, int n_coupled) { struct coupling_desc *c_desc = &rdev->coupling_desc; struct regulator_dev **c_rdevs = c_desc->coupled_rdevs; struct regulation_constraints *constraints = rdev->constraints; int desired_min_uV = 0, desired_max_uV = INT_MAX; int max_current_uV = 0, min_current_uV = INT_MAX; int highest_min_uV = 0, target_uV, possible_uV; int i, ret, max_spread; bool done; *current_uV = -1; /* * If there are no coupled regulators, simply set the voltage * demanded by consumers. */ if (n_coupled == 1) { /* * If consumers don't provide any demands, set voltage * to min_uV */ desired_min_uV = constraints->min_uV; desired_max_uV = constraints->max_uV; ret = regulator_check_consumers(rdev, &desired_min_uV, &desired_max_uV, state); if (ret < 0) return ret; done = true; goto finish; } /* Find highest min desired voltage */ for (i = 0; i < n_coupled; i++) { int tmp_min = 0; int tmp_max = INT_MAX; lockdep_assert_held_once(&c_rdevs[i]->mutex.base); ret = regulator_check_consumers(c_rdevs[i], &tmp_min, &tmp_max, state); if (ret < 0) return ret; ret = regulator_check_voltage(c_rdevs[i], &tmp_min, &tmp_max); if (ret < 0) return ret; highest_min_uV = max(highest_min_uV, tmp_min); if (i == 0) { desired_min_uV = tmp_min; desired_max_uV = tmp_max; } } max_spread = constraints->max_spread[0]; /* * Let target_uV be equal to the desired one if possible. * If not, set it to minimum voltage, allowed by other coupled * regulators. */ target_uV = max(desired_min_uV, highest_min_uV - max_spread); /* * Find min and max voltages, which currently aren't violating * max_spread. */ for (i = 1; i < n_coupled; i++) { int tmp_act; if (!_regulator_is_enabled(c_rdevs[i])) continue; tmp_act = regulator_get_voltage_rdev(c_rdevs[i]); if (tmp_act < 0) return tmp_act; min_current_uV = min(tmp_act, min_current_uV); max_current_uV = max(tmp_act, max_current_uV); } /* There aren't any other regulators enabled */ if (max_current_uV == 0) { possible_uV = target_uV; } else { /* * Correct target voltage, so as it currently isn't * violating max_spread */ possible_uV = max(target_uV, max_current_uV - max_spread); possible_uV = min(possible_uV, min_current_uV + max_spread); } if (possible_uV > desired_max_uV) return -EINVAL; done = (possible_uV == target_uV); desired_min_uV = possible_uV; finish: /* Apply max_uV_step constraint if necessary */ if (state == PM_SUSPEND_ON) { ret = regulator_limit_voltage_step(rdev, current_uV, &desired_min_uV); if (ret < 0) return ret; if (ret == 0) done = false; } /* Set current_uV if wasn't done earlier in the code and if necessary */ if (n_coupled > 1 && *current_uV == -1) { if (_regulator_is_enabled(rdev)) { ret = regulator_get_voltage_rdev(rdev); if (ret < 0) return ret; *current_uV = ret; } else { *current_uV = desired_min_uV; } } *min_uV = desired_min_uV; *max_uV = desired_max_uV; return done; } int regulator_do_balance_voltage(struct regulator_dev *rdev, suspend_state_t state, bool skip_coupled) { struct regulator_dev **c_rdevs; struct regulator_dev *best_rdev; struct coupling_desc *c_desc = &rdev->coupling_desc; int i, ret, n_coupled, best_min_uV, best_max_uV, best_c_rdev; unsigned int delta, best_delta; unsigned long c_rdev_done = 0; bool best_c_rdev_done; c_rdevs = c_desc->coupled_rdevs; n_coupled = skip_coupled ? 1 : c_desc->n_coupled; /* * Find the best possible voltage change on each loop. Leave the loop * if there isn't any possible change. */ do { best_c_rdev_done = false; best_delta = 0; best_min_uV = 0; best_max_uV = 0; best_c_rdev = 0; best_rdev = NULL; /* * Find highest difference between optimal voltage * and current voltage. */ for (i = 0; i < n_coupled; i++) { /* * optimal_uV is the best voltage that can be set for * i-th regulator at the moment without violating * max_spread constraint in order to balance * the coupled voltages. */ int optimal_uV = 0, optimal_max_uV = 0, current_uV = 0; if (test_bit(i, &c_rdev_done)) continue; ret = regulator_get_optimal_voltage(c_rdevs[i], ¤t_uV, &optimal_uV, &optimal_max_uV, state, n_coupled); if (ret < 0) goto out; delta = abs(optimal_uV - current_uV); if (delta && best_delta <= delta) { best_c_rdev_done = ret; best_delta = delta; best_rdev = c_rdevs[i]; best_min_uV = optimal_uV; best_max_uV = optimal_max_uV; best_c_rdev = i; } } /* Nothing to change, return successfully */ if (!best_rdev) { ret = 0; goto out; } ret = regulator_set_voltage_rdev(best_rdev, best_min_uV, best_max_uV, state); if (ret < 0) goto out; if (best_c_rdev_done) set_bit(best_c_rdev, &c_rdev_done); } while (n_coupled > 1); out: return ret; } static int regulator_balance_voltage(struct regulator_dev *rdev, suspend_state_t state) { struct coupling_desc *c_desc = &rdev->coupling_desc; struct regulator_coupler *coupler = c_desc->coupler; bool skip_coupled = false; /* * If system is in a state other than PM_SUSPEND_ON, don't check * other coupled regulators. */ if (state != PM_SUSPEND_ON) skip_coupled = true; if (c_desc->n_resolved < c_desc->n_coupled) { rdev_err(rdev, "Not all coupled regulators registered\n"); return -EPERM; } /* Invoke custom balancer for customized couplers */ if (coupler && coupler->balance_voltage) return coupler->balance_voltage(coupler, rdev, state); return regulator_do_balance_voltage(rdev, state, skip_coupled); } /** * regulator_set_voltage - set regulator output voltage * @regulator: regulator source * @min_uV: Minimum required voltage in uV * @max_uV: Maximum acceptable voltage in uV * * Sets a voltage regulator to the desired output voltage. This can be set * during any regulator state. IOW, regulator can be disabled or enabled. * * If the regulator is enabled then the voltage will change to the new value * immediately otherwise if the regulator is disabled the regulator will * output at the new voltage when enabled. * * NOTE: If the regulator is shared between several devices then the lowest * request voltage that meets the system constraints will be used. * Regulator system constraints must be set for this regulator before * calling this function otherwise this call will fail. * * Return: 0 on success or a negative error number on failure. */ int regulator_set_voltage(struct regulator *regulator, int min_uV, int max_uV) { struct ww_acquire_ctx ww_ctx; int ret; regulator_lock_dependent(regulator->rdev, &ww_ctx); ret = regulator_set_voltage_unlocked(regulator, min_uV, max_uV, PM_SUSPEND_ON); regulator_unlock_dependent(regulator->rdev, &ww_ctx); return ret; } EXPORT_SYMBOL_GPL(regulator_set_voltage); static inline int regulator_suspend_toggle(struct regulator_dev *rdev, suspend_state_t state, bool en) { struct regulator_state *rstate; rstate = regulator_get_suspend_state(rdev, state); if (rstate == NULL) return -EINVAL; if (!rstate->changeable) return -EPERM; rstate->enabled = (en) ? ENABLE_IN_SUSPEND : DISABLE_IN_SUSPEND; return 0; } int regulator_suspend_enable(struct regulator_dev *rdev, suspend_state_t state) { return regulator_suspend_toggle(rdev, state, true); } EXPORT_SYMBOL_GPL(regulator_suspend_enable); int regulator_suspend_disable(struct regulator_dev *rdev, suspend_state_t state) { struct regulator *regulator; struct regulator_voltage *voltage; /* * if any consumer wants this regulator device keeping on in * suspend states, don't set it as disabled. */ list_for_each_entry(regulator, &rdev->consumer_list, list) { voltage = ®ulator->voltage[state]; if (voltage->min_uV || voltage->max_uV) return 0; } return regulator_suspend_toggle(rdev, state, false); } EXPORT_SYMBOL_GPL(regulator_suspend_disable); static int _regulator_set_suspend_voltage(struct regulator *regulator, int min_uV, int max_uV, suspend_state_t state) { struct regulator_dev *rdev = regulator->rdev; struct regulator_state *rstate; rstate = regulator_get_suspend_state(rdev, state); if (rstate == NULL) return -EINVAL; if (rstate->min_uV == rstate->max_uV) { rdev_err(rdev, "The suspend voltage can't be changed!\n"); return -EPERM; } return regulator_set_voltage_unlocked(regulator, min_uV, max_uV, state); } int regulator_set_suspend_voltage(struct regulator *regulator, int min_uV, int max_uV, suspend_state_t state) { struct ww_acquire_ctx ww_ctx; int ret; /* PM_SUSPEND_ON is handled by regulator_set_voltage() */ if (regulator_check_states(state) || state == PM_SUSPEND_ON) return -EINVAL; regulator_lock_dependent(regulator->rdev, &ww_ctx); ret = _regulator_set_suspend_voltage(regulator, min_uV, max_uV, state); regulator_unlock_dependent(regulator->rdev, &ww_ctx); return ret; } EXPORT_SYMBOL_GPL(regulator_set_suspend_voltage); /** * regulator_set_voltage_time - get raise/fall time * @regulator: regulator source * @old_uV: starting voltage in microvolts * @new_uV: target voltage in microvolts * * Provided with the starting and ending voltage, this function attempts to * calculate the time in microseconds required to rise or fall to this new * voltage. * * Return: ramp time in microseconds, or a negative error number if calculation failed. */ int regulator_set_voltage_time(struct regulator *regulator, int old_uV, int new_uV) { struct regulator_dev *rdev = regulator->rdev; const struct regulator_ops *ops = rdev->desc->ops; int old_sel = -1; int new_sel = -1; int voltage; int i; if (ops->set_voltage_time) return ops->set_voltage_time(rdev, old_uV, new_uV); else if (!ops->set_voltage_time_sel) return _regulator_set_voltage_time(rdev, old_uV, new_uV); /* Currently requires operations to do this */ if (!ops->list_voltage || !rdev->desc->n_voltages) return -EINVAL; for (i = 0; i < rdev->desc->n_voltages; i++) { /* We only look for exact voltage matches here */ if (i < rdev->desc->linear_min_sel) continue; if (old_sel >= 0 && new_sel >= 0) break; voltage = regulator_list_voltage(regulator, i); if (voltage < 0) return -EINVAL; if (voltage == 0) continue; if (voltage == old_uV) old_sel = i; if (voltage == new_uV) new_sel = i; } if (old_sel < 0 || new_sel < 0) return -EINVAL; return ops->set_voltage_time_sel(rdev, old_sel, new_sel); } EXPORT_SYMBOL_GPL(regulator_set_voltage_time); /** * regulator_set_voltage_time_sel - get raise/fall time * @rdev: regulator source device * @old_selector: selector for starting voltage * @new_selector: selector for target voltage * * Provided with the starting and target voltage selectors, this function * returns time in microseconds required to rise or fall to this new voltage * * Drivers providing ramp_delay in regulation_constraints can use this as their * set_voltage_time_sel() operation. * * Return: ramp time in microseconds, or a negative error number if calculation failed. */ int regulator_set_voltage_time_sel(struct regulator_dev *rdev, unsigned int old_selector, unsigned int new_selector) { int old_volt, new_volt; /* sanity check */ if (!rdev->desc->ops->list_voltage) return -EINVAL; old_volt = rdev->desc->ops->list_voltage(rdev, old_selector); new_volt = rdev->desc->ops->list_voltage(rdev, new_selector); if (rdev->desc->ops->set_voltage_time) return rdev->desc->ops->set_voltage_time(rdev, old_volt, new_volt); else return _regulator_set_voltage_time(rdev, old_volt, new_volt); } EXPORT_SYMBOL_GPL(regulator_set_voltage_time_sel); int regulator_sync_voltage_rdev(struct regulator_dev *rdev) { int ret; regulator_lock(rdev); if (!rdev->desc->ops->set_voltage && !rdev->desc->ops->set_voltage_sel) { ret = -EINVAL; goto out; } /* balance only, if regulator is coupled */ if (rdev->coupling_desc.n_coupled > 1) ret = regulator_balance_voltage(rdev, PM_SUSPEND_ON); else ret = -EOPNOTSUPP; out: regulator_unlock(rdev); return ret; } /** * regulator_sync_voltage - re-apply last regulator output voltage * @regulator: regulator source * * Re-apply the last configured voltage. This is intended to be used * where some external control source the consumer is cooperating with * has caused the configured voltage to change. * * Return: 0 on success or a negative error number on failure. */ int regulator_sync_voltage(struct regulator *regulator) { struct regulator_dev *rdev = regulator->rdev; struct regulator_voltage *voltage = ®ulator->voltage[PM_SUSPEND_ON]; int ret, min_uV, max_uV; if (!regulator_ops_is_valid(rdev, REGULATOR_CHANGE_VOLTAGE)) return 0; regulator_lock(rdev); if (!rdev->desc->ops->set_voltage && !rdev->desc->ops->set_voltage_sel) { ret = -EINVAL; goto out; } /* This is only going to work if we've had a voltage configured. */ if (!voltage->min_uV && !voltage->max_uV) { ret = -EINVAL; goto out; } min_uV = voltage->min_uV; max_uV = voltage->max_uV; /* This should be a paranoia check... */ ret = regulator_check_voltage(rdev, &min_uV, &max_uV); if (ret < 0) goto out; ret = regulator_check_consumers(rdev, &min_uV, &max_uV, 0); if (ret < 0) goto out; /* balance only, if regulator is coupled */ if (rdev->coupling_desc.n_coupled > 1) ret = regulator_balance_voltage(rdev, PM_SUSPEND_ON); else ret = _regulator_do_set_voltage(rdev, min_uV, max_uV); out: regulator_unlock(rdev); return ret; } EXPORT_SYMBOL_GPL(regulator_sync_voltage); int regulator_get_voltage_rdev(struct regulator_dev *rdev) { int sel, ret; bool bypassed; if (rdev->desc->ops->get_bypass) { ret = rdev->desc->ops->get_bypass(rdev, &bypassed); if (ret < 0) return ret; if (bypassed) { /* if bypassed the regulator must have a supply */ if (!rdev->supply) { rdev_err(rdev, "bypassed regulator has no supply!\n"); return -EPROBE_DEFER; } return regulator_get_voltage_rdev(rdev->supply->rdev); } } if (rdev->desc->ops->get_voltage_sel) { sel = rdev->desc->ops->get_voltage_sel(rdev); if (sel < 0) return sel; ret = rdev->desc->ops->list_voltage(rdev, sel); } else if (rdev->desc->ops->get_voltage) { ret = rdev->desc->ops->get_voltage(rdev); } else if (rdev->desc->ops->list_voltage) { ret = rdev->desc->ops->list_voltage(rdev, 0); } else if (rdev->desc->fixed_uV && (rdev->desc->n_voltages == 1)) { ret = rdev->desc->fixed_uV; } else if (rdev->supply) { ret = regulator_get_voltage_rdev(rdev->supply->rdev); } else if (rdev->supply_name) { return -EPROBE_DEFER; } else { return -EINVAL; } if (ret < 0) return ret; return ret - rdev->constraints->uV_offset; } EXPORT_SYMBOL_GPL(regulator_get_voltage_rdev); /** * regulator_get_voltage - get regulator output voltage * @regulator: regulator source * * Return: Current regulator voltage in uV, or a negative error number on failure. * * NOTE: If the regulator is disabled it will return the voltage value. This * function should not be used to determine regulator state. */ int regulator_get_voltage(struct regulator *regulator) { struct ww_acquire_ctx ww_ctx; int ret; regulator_lock_dependent(regulator->rdev, &ww_ctx); ret = regulator_get_voltage_rdev(regulator->rdev); regulator_unlock_dependent(regulator->rdev, &ww_ctx); return ret; } EXPORT_SYMBOL_GPL(regulator_get_voltage); /** * regulator_set_current_limit - set regulator output current limit * @regulator: regulator source * @min_uA: Minimum supported current in uA * @max_uA: Maximum supported current in uA * * Sets current sink to the desired output current. This can be set during * any regulator state. IOW, regulator can be disabled or enabled. * * If the regulator is enabled then the current will change to the new value * immediately otherwise if the regulator is disabled the regulator will * output at the new current when enabled. * * NOTE: Regulator system constraints must be set for this regulator before * calling this function otherwise this call will fail. * * Return: 0 on success or a negative error number on failure. */ int regulator_set_current_limit(struct regulator *regulator, int min_uA, int max_uA) { struct regulator_dev *rdev = regulator->rdev; int ret; regulator_lock(rdev); /* sanity check */ if (!rdev->desc->ops->set_current_limit) { ret = -EINVAL; goto out; } /* constraints check */ ret = regulator_check_current_limit(rdev, &min_uA, &max_uA); if (ret < 0) goto out; ret = rdev->desc->ops->set_current_limit(rdev, min_uA, max_uA); out: regulator_unlock(rdev); return ret; } EXPORT_SYMBOL_GPL(regulator_set_current_limit); static int _regulator_get_current_limit_unlocked(struct regulator_dev *rdev) { /* sanity check */ if (!rdev->desc->ops->get_current_limit) return -EINVAL; return rdev->desc->ops->get_current_limit(rdev); } static int _regulator_get_current_limit(struct regulator_dev *rdev) { int ret; regulator_lock(rdev); ret = _regulator_get_current_limit_unlocked(rdev); regulator_unlock(rdev); return ret; } /** * regulator_get_current_limit - get regulator output current * @regulator: regulator source * * Return: Current supplied by the specified current sink in uA, * or a negative error number on failure. * * NOTE: If the regulator is disabled it will return the current value. This * function should not be used to determine regulator state. */ int regulator_get_current_limit(struct regulator *regulator) { return _regulator_get_current_limit(regulator->rdev); } EXPORT_SYMBOL_GPL(regulator_get_current_limit); /** * regulator_get_unclaimed_power_budget - get regulator unclaimed power budget * @regulator: regulator source * * Return: Unclaimed power budget of the regulator in mW. */ int regulator_get_unclaimed_power_budget(struct regulator *regulator) { return regulator->rdev->constraints->pw_budget_mW - regulator->rdev->pw_requested_mW; } EXPORT_SYMBOL_GPL(regulator_get_unclaimed_power_budget); /** * regulator_request_power_budget - request power budget on a regulator * @regulator: regulator source * @pw_req: Power requested * * Return: 0 on success or a negative error number on failure. */ int regulator_request_power_budget(struct regulator *regulator, unsigned int pw_req) { struct regulator_dev *rdev = regulator->rdev; int ret = 0, pw_tot_req; regulator_lock(rdev); if (rdev->supply) { ret = regulator_request_power_budget(rdev->supply, pw_req); if (ret < 0) goto out; } pw_tot_req = rdev->pw_requested_mW + pw_req; if (pw_tot_req > rdev->constraints->pw_budget_mW) { rdev_warn(rdev, "power requested %d mW out of budget %d mW", pw_req, rdev->constraints->pw_budget_mW - rdev->pw_requested_mW); regulator_notifier_call_chain(rdev, REGULATOR_EVENT_OVER_CURRENT_WARN, NULL); ret = -ERANGE; goto out; } rdev->pw_requested_mW = pw_tot_req; out: regulator_unlock(rdev); return ret; } EXPORT_SYMBOL_GPL(regulator_request_power_budget); /** * regulator_free_power_budget - free power budget on a regulator * @regulator: regulator source * @pw: Power to be released. * * Return: Power budget of the regulator in mW. */ void regulator_free_power_budget(struct regulator *regulator, unsigned int pw) { struct regulator_dev *rdev = regulator->rdev; int pw_tot_req; regulator_lock(rdev); if (rdev->supply) regulator_free_power_budget(rdev->supply, pw); pw_tot_req = rdev->pw_requested_mW - pw; if (pw_tot_req >= 0) rdev->pw_requested_mW = pw_tot_req; else rdev_warn(rdev, "too much power freed %d mW (already requested %d mW)", pw, rdev->pw_requested_mW); regulator_unlock(rdev); } EXPORT_SYMBOL_GPL(regulator_free_power_budget); /** * regulator_set_mode - set regulator operating mode * @regulator: regulator source * @mode: operating mode - one of the REGULATOR_MODE constants * * Set regulator operating mode to increase regulator efficiency or improve * regulation performance. * * NOTE: Regulator system constraints must be set for this regulator before * calling this function otherwise this call will fail. * * Return: 0 on success or a negative error number on failure. */ int regulator_set_mode(struct regulator *regulator, unsigned int mode) { struct regulator_dev *rdev = regulator->rdev; int ret; int regulator_curr_mode; regulator_lock(rdev); /* sanity check */ if (!rdev->desc->ops->set_mode) { ret = -EINVAL; goto out; } /* return if the same mode is requested */ if (rdev->desc->ops->get_mode) { regulator_curr_mode = rdev->desc->ops->get_mode(rdev); if (regulator_curr_mode == mode) { ret = 0; goto out; } } /* constraints check */ ret = regulator_mode_constrain(rdev, &mode); if (ret < 0) goto out; ret = rdev->desc->ops->set_mode(rdev, mode); out: regulator_unlock(rdev); return ret; } EXPORT_SYMBOL_GPL(regulator_set_mode); static unsigned int _regulator_get_mode_unlocked(struct regulator_dev *rdev) { /* sanity check */ if (!rdev->desc->ops->get_mode) return -EINVAL; return rdev->desc->ops->get_mode(rdev); } static unsigned int _regulator_get_mode(struct regulator_dev *rdev) { int ret; regulator_lock(rdev); ret = _regulator_get_mode_unlocked(rdev); regulator_unlock(rdev); return ret; } /** * regulator_get_mode - get regulator operating mode * @regulator: regulator source * * Get the current regulator operating mode. * * Return: Current operating mode as %REGULATOR_MODE_* values, * or a negative error number on failure. */ unsigned int regulator_get_mode(struct regulator *regulator) { return _regulator_get_mode(regulator->rdev); } EXPORT_SYMBOL_GPL(regulator_get_mode); static int rdev_get_cached_err_flags(struct regulator_dev *rdev) { int ret = 0; if (rdev->use_cached_err) { spin_lock(&rdev->err_lock); ret = rdev->cached_err; spin_unlock(&rdev->err_lock); } return ret; } static int _regulator_get_error_flags(struct regulator_dev *rdev, unsigned int *flags) { int cached_flags, ret = 0; regulator_lock(rdev); cached_flags = rdev_get_cached_err_flags(rdev); if (rdev->desc->ops->get_error_flags) ret = rdev->desc->ops->get_error_flags(rdev, flags); else if (!rdev->use_cached_err) ret = -EINVAL; *flags |= cached_flags; regulator_unlock(rdev); return ret; } /** * regulator_get_error_flags - get regulator error information * @regulator: regulator source * @flags: pointer to store error flags * * Get the current regulator error information. * * Return: 0 on success or a negative error number on failure. */ int regulator_get_error_flags(struct regulator *regulator, unsigned int *flags) { return _regulator_get_error_flags(regulator->rdev, flags); } EXPORT_SYMBOL_GPL(regulator_get_error_flags); /** * regulator_set_load - set regulator load * @regulator: regulator source * @uA_load: load current * * Notifies the regulator core of a new device load. This is then used by * DRMS (if enabled by constraints) to set the most efficient regulator * operating mode for the new regulator loading. * * Consumer devices notify their supply regulator of the maximum power * they will require (can be taken from device datasheet in the power * consumption tables) when they change operational status and hence power * state. Examples of operational state changes that can affect power * consumption are :- * * o Device is opened / closed. * o Device I/O is about to begin or has just finished. * o Device is idling in between work. * * This information is also exported via sysfs to userspace. * * DRMS will sum the total requested load on the regulator and change * to the most efficient operating mode if platform constraints allow. * * NOTE: when a regulator consumer requests to have a regulator * disabled then any load that consumer requested no longer counts * toward the total requested load. If the regulator is re-enabled * then the previously requested load will start counting again. * * If a regulator is an always-on regulator then an individual consumer's * load will still be removed if that consumer is fully disabled. * * Return: 0 on success or a negative error number on failure. */ int regulator_set_load(struct regulator *regulator, int uA_load) { struct regulator_dev *rdev = regulator->rdev; int old_uA_load; int ret = 0; regulator_lock(rdev); old_uA_load = regulator->uA_load; regulator->uA_load = uA_load; if (regulator->enable_count && old_uA_load != uA_load) { ret = drms_uA_update(rdev); if (ret < 0) regulator->uA_load = old_uA_load; } regulator_unlock(rdev); return ret; } EXPORT_SYMBOL_GPL(regulator_set_load); /** * regulator_allow_bypass - allow the regulator to go into bypass mode * * @regulator: Regulator to configure * @enable: enable or disable bypass mode * * Allow the regulator to go into bypass mode if all other consumers * for the regulator also enable bypass mode and the machine * constraints allow this. Bypass mode means that the regulator is * simply passing the input directly to the output with no regulation. * * Return: 0 on success or if changing bypass is not possible, or * a negative error number on failure. */ int regulator_allow_bypass(struct regulator *regulator, bool enable) { struct regulator_dev *rdev = regulator->rdev; const char *name = rdev_get_name(rdev); int ret = 0; if (!rdev->desc->ops->set_bypass) return 0; if (!regulator_ops_is_valid(rdev, REGULATOR_CHANGE_BYPASS)) return 0; regulator_lock(rdev); if (enable && !regulator->bypass) { rdev->bypass_count++; if (rdev->bypass_count == rdev->open_count) { trace_regulator_bypass_enable(name); ret = rdev->desc->ops->set_bypass(rdev, enable); if (ret != 0) rdev->bypass_count--; else trace_regulator_bypass_enable_complete(name); } } else if (!enable && regulator->bypass) { rdev->bypass_count--; if (rdev->bypass_count != rdev->open_count) { trace_regulator_bypass_disable(name); ret = rdev->desc->ops->set_bypass(rdev, enable); if (ret != 0) rdev->bypass_count++; else trace_regulator_bypass_disable_complete(name); } } if (ret == 0) regulator->bypass = enable; regulator_unlock(rdev); return ret; } EXPORT_SYMBOL_GPL(regulator_allow_bypass); /** * regulator_register_notifier - register regulator event notifier * @regulator: regulator source * @nb: notifier block * * Register notifier block to receive regulator events. * * Return: 0 on success or a negative error number on failure. */ int regulator_register_notifier(struct regulator *regulator, struct notifier_block *nb) { return blocking_notifier_chain_register(®ulator->rdev->notifier, nb); } EXPORT_SYMBOL_GPL(regulator_register_notifier); /** * regulator_unregister_notifier - unregister regulator event notifier * @regulator: regulator source * @nb: notifier block * * Unregister regulator event notifier block. * * Return: 0 on success or a negative error number on failure. */ int regulator_unregister_notifier(struct regulator *regulator, struct notifier_block *nb) { return blocking_notifier_chain_unregister(®ulator->rdev->notifier, nb); } EXPORT_SYMBOL_GPL(regulator_unregister_notifier); /* notify regulator consumers and downstream regulator consumers. * Note mutex must be held by caller. */ static int _notifier_call_chain(struct regulator_dev *rdev, unsigned long event, void *data) { /* call rdev chain first */ int ret = blocking_notifier_call_chain(&rdev->notifier, event, data); if (IS_REACHABLE(CONFIG_REGULATOR_NETLINK_EVENTS)) { struct device *parent = rdev->dev.parent; const char *rname = rdev_get_name(rdev); char name[32]; /* Avoid duplicate debugfs directory names */ if (parent && rname == rdev->desc->name) { snprintf(name, sizeof(name), "%s-%s", dev_name(parent), rname); rname = name; } reg_generate_netlink_event(rname, event); } return ret; } int _regulator_bulk_get(struct device *dev, int num_consumers, struct regulator_bulk_data *consumers, enum regulator_get_type get_type) { int i; int ret; for (i = 0; i < num_consumers; i++) consumers[i].consumer = NULL; for (i = 0; i < num_consumers; i++) { consumers[i].consumer = _regulator_get(dev, consumers[i].supply, get_type); if (IS_ERR(consumers[i].consumer)) { ret = dev_err_probe(dev, PTR_ERR(consumers[i].consumer), "Failed to get supply '%s'", consumers[i].supply); consumers[i].consumer = NULL; goto err; } if (consumers[i].init_load_uA > 0) { ret = regulator_set_load(consumers[i].consumer, consumers[i].init_load_uA); if (ret) { i++; goto err; } } } return 0; err: while (--i >= 0) regulator_put(consumers[i].consumer); return ret; } /** * regulator_bulk_get - get multiple regulator consumers * * @dev: Device to supply * @num_consumers: Number of consumers to register * @consumers: Configuration of consumers; clients are stored here. * * This helper function allows drivers to get several regulator * consumers in one operation. If any of the regulators cannot be * acquired then any regulators that were allocated will be freed * before returning to the caller. * * Return: 0 on success or a negative error number on failure. */ int regulator_bulk_get(struct device *dev, int num_consumers, struct regulator_bulk_data *consumers) { return _regulator_bulk_get(dev, num_consumers, consumers, NORMAL_GET); } EXPORT_SYMBOL_GPL(regulator_bulk_get); static void regulator_bulk_enable_async(void *data, async_cookie_t cookie) { struct regulator_bulk_data *bulk = data; bulk->ret = regulator_enable(bulk->consumer); } /** * regulator_bulk_enable - enable multiple regulator consumers * * @num_consumers: Number of consumers * @consumers: Consumer data; clients are stored here. * * This convenience API allows consumers to enable multiple regulator * clients in a single API call. If any consumers cannot be enabled * then any others that were enabled will be disabled again prior to * return. * * Return: 0 on success or a negative error number on failure. */ int regulator_bulk_enable(int num_consumers, struct regulator_bulk_data *consumers) { ASYNC_DOMAIN_EXCLUSIVE(async_domain); int i; int ret = 0; for (i = 0; i < num_consumers; i++) { async_schedule_domain(regulator_bulk_enable_async, &consumers[i], &async_domain); } async_synchronize_full_domain(&async_domain); /* If any consumer failed we need to unwind any that succeeded */ for (i = 0; i < num_consumers; i++) { if (consumers[i].ret != 0) { ret = consumers[i].ret; goto err; } } return 0; err: for (i = 0; i < num_consumers; i++) { if (consumers[i].ret < 0) pr_err("Failed to enable %s: %pe\n", consumers[i].supply, ERR_PTR(consumers[i].ret)); else regulator_disable(consumers[i].consumer); } return ret; } EXPORT_SYMBOL_GPL(regulator_bulk_enable); /** * regulator_bulk_disable - disable multiple regulator consumers * * @num_consumers: Number of consumers * @consumers: Consumer data; clients are stored here. * * This convenience API allows consumers to disable multiple regulator * clients in a single API call. If any consumers cannot be disabled * then any others that were disabled will be enabled again prior to * return. * * Return: 0 on success or a negative error number on failure. */ int regulator_bulk_disable(int num_consumers, struct regulator_bulk_data *consumers) { int i; int ret, r; for (i = num_consumers - 1; i >= 0; --i) { ret = regulator_disable(consumers[i].consumer); if (ret != 0) goto err; } return 0; err: pr_err("Failed to disable %s: %pe\n", consumers[i].supply, ERR_PTR(ret)); for (++i; i < num_consumers; ++i) { r = regulator_enable(consumers[i].consumer); if (r != 0) pr_err("Failed to re-enable %s: %pe\n", consumers[i].supply, ERR_PTR(r)); } return ret; } EXPORT_SYMBOL_GPL(regulator_bulk_disable); /** * regulator_bulk_force_disable - force disable multiple regulator consumers * * @num_consumers: Number of consumers * @consumers: Consumer data; clients are stored here. * * This convenience API allows consumers to forcibly disable multiple regulator * clients in a single API call. * NOTE: This should be used for situations when device damage will * likely occur if the regulators are not disabled (e.g. over temp). * Although regulator_force_disable function call for some consumers can * return error numbers, the function is called for all consumers. * * Return: 0 on success or a negative error number on failure. */ int regulator_bulk_force_disable(int num_consumers, struct regulator_bulk_data *consumers) { int i; int ret = 0; for (i = 0; i < num_consumers; i++) { consumers[i].ret = regulator_force_disable(consumers[i].consumer); /* Store first error for reporting */ if (consumers[i].ret && !ret) ret = consumers[i].ret; } return ret; } EXPORT_SYMBOL_GPL(regulator_bulk_force_disable); /** * regulator_bulk_free - free multiple regulator consumers * * @num_consumers: Number of consumers * @consumers: Consumer data; clients are stored here. * * This convenience API allows consumers to free multiple regulator * clients in a single API call. */ void regulator_bulk_free(int num_consumers, struct regulator_bulk_data *consumers) { int i; for (i = 0; i < num_consumers; i++) { regulator_put(consumers[i].consumer); consumers[i].consumer = NULL; } } EXPORT_SYMBOL_GPL(regulator_bulk_free); /** * regulator_handle_critical - Handle events for system-critical regulators. * @rdev: The regulator device. * @event: The event being handled. * * This function handles critical events such as under-voltage, over-current, * and unknown errors for regulators deemed system-critical. On detecting such * events, it triggers a hardware protection shutdown with a defined timeout. */ static void regulator_handle_critical(struct regulator_dev *rdev, unsigned long event) { const char *reason = NULL; if (!rdev->constraints->system_critical) return; switch (event) { case REGULATOR_EVENT_UNDER_VOLTAGE: reason = "System critical regulator: voltage drop detected"; break; case REGULATOR_EVENT_OVER_CURRENT: reason = "System critical regulator: over-current detected"; break; case REGULATOR_EVENT_FAIL: reason = "System critical regulator: unknown error"; } if (!reason) return; hw_protection_shutdown(reason, rdev->constraints->uv_less_critical_window_ms); } /** * regulator_notifier_call_chain - call regulator event notifier * @rdev: regulator source * @event: notifier block * @data: callback-specific data. * * Called by regulator drivers to notify clients a regulator event has * occurred. * * Return: %NOTIFY_DONE. */ int regulator_notifier_call_chain(struct regulator_dev *rdev, unsigned long event, void *data) { regulator_handle_critical(rdev, event); _notifier_call_chain(rdev, event, data); return NOTIFY_DONE; } EXPORT_SYMBOL_GPL(regulator_notifier_call_chain); /** * regulator_mode_to_status - convert a regulator mode into a status * * @mode: Mode to convert * * Convert a regulator mode into a status. * * Return: %REGULATOR_STATUS_* value corresponding to given mode. */ int regulator_mode_to_status(unsigned int mode) { switch (mode) { case REGULATOR_MODE_FAST: return REGULATOR_STATUS_FAST; case REGULATOR_MODE_NORMAL: return REGULATOR_STATUS_NORMAL; case REGULATOR_MODE_IDLE: return REGULATOR_STATUS_IDLE; case REGULATOR_MODE_STANDBY: return REGULATOR_STATUS_STANDBY; default: return REGULATOR_STATUS_UNDEFINED; } } EXPORT_SYMBOL_GPL(regulator_mode_to_status); static struct attribute *regulator_dev_attrs[] = { &dev_attr_name.attr, &dev_attr_num_users.attr, &dev_attr_type.attr, &dev_attr_microvolts.attr, &dev_attr_microamps.attr, &dev_attr_opmode.attr, &dev_attr_state.attr, &dev_attr_status.attr, &dev_attr_bypass.attr, &dev_attr_requested_microamps.attr, &dev_attr_min_microvolts.attr, &dev_attr_max_microvolts.attr, &dev_attr_min_microamps.attr, &dev_attr_max_microamps.attr, &dev_attr_under_voltage.attr, &dev_attr_over_current.attr, &dev_attr_regulation_out.attr, &dev_attr_fail.attr, &dev_attr_over_temp.attr, &dev_attr_under_voltage_warn.attr, &dev_attr_over_current_warn.attr, &dev_attr_over_voltage_warn.attr, &dev_attr_over_temp_warn.attr, &dev_attr_suspend_standby_state.attr, &dev_attr_suspend_mem_state.attr, &dev_attr_suspend_disk_state.attr, &dev_attr_suspend_standby_microvolts.attr, &dev_attr_suspend_mem_microvolts.attr, &dev_attr_suspend_disk_microvolts.attr, &dev_attr_suspend_standby_mode.attr, &dev_attr_suspend_mem_mode.attr, &dev_attr_suspend_disk_mode.attr, &dev_attr_power_budget_milliwatt.attr, &dev_attr_power_requested_milliwatt.attr, NULL }; /* * To avoid cluttering sysfs (and memory) with useless state, only * create attributes that can be meaningfully displayed. */ static umode_t regulator_attr_is_visible(struct kobject *kobj, struct attribute *attr, int idx) { struct device *dev = kobj_to_dev(kobj); struct regulator_dev *rdev = dev_to_rdev(dev); const struct regulator_ops *ops = rdev->desc->ops; umode_t mode = attr->mode; /* these three are always present */ if (attr == &dev_attr_name.attr || attr == &dev_attr_num_users.attr || attr == &dev_attr_type.attr) return mode; /* some attributes need specific methods to be displayed */ if (attr == &dev_attr_microvolts.attr) { if ((ops->get_voltage && ops->get_voltage(rdev) >= 0) || (ops->get_voltage_sel && ops->get_voltage_sel(rdev) >= 0) || (ops->list_voltage && ops->list_voltage(rdev, 0) >= 0) || (rdev->desc->fixed_uV && rdev->desc->n_voltages == 1)) return mode; return 0; } if (attr == &dev_attr_microamps.attr) return ops->get_current_limit ? mode : 0; if (attr == &dev_attr_opmode.attr) return ops->get_mode ? mode : 0; if (attr == &dev_attr_state.attr) return (rdev->ena_pin || ops->is_enabled) ? mode : 0; if (attr == &dev_attr_status.attr) return ops->get_status ? mode : 0; if (attr == &dev_attr_bypass.attr) return ops->get_bypass ? mode : 0; if (attr == &dev_attr_under_voltage.attr || attr == &dev_attr_over_current.attr || attr == &dev_attr_regulation_out.attr || attr == &dev_attr_fail.attr || attr == &dev_attr_over_temp.attr || attr == &dev_attr_under_voltage_warn.attr || attr == &dev_attr_over_current_warn.attr || attr == &dev_attr_over_voltage_warn.attr || attr == &dev_attr_over_temp_warn.attr) return ops->get_error_flags ? mode : 0; /* constraints need specific supporting methods */ if (attr == &dev_attr_min_microvolts.attr || attr == &dev_attr_max_microvolts.attr) return (ops->set_voltage || ops->set_voltage_sel) ? mode : 0; if (attr == &dev_attr_min_microamps.attr || attr == &dev_attr_max_microamps.attr) return ops->set_current_limit ? mode : 0; if (attr == &dev_attr_suspend_standby_state.attr || attr == &dev_attr_suspend_mem_state.attr || attr == &dev_attr_suspend_disk_state.attr) return mode; if (attr == &dev_attr_suspend_standby_microvolts.attr || attr == &dev_attr_suspend_mem_microvolts.attr || attr == &dev_attr_suspend_disk_microvolts.attr) return ops->set_suspend_voltage ? mode : 0; if (attr == &dev_attr_suspend_standby_mode.attr || attr == &dev_attr_suspend_mem_mode.attr || attr == &dev_attr_suspend_disk_mode.attr) return ops->set_suspend_mode ? mode : 0; if (attr == &dev_attr_power_budget_milliwatt.attr || attr == &dev_attr_power_requested_milliwatt.attr) return rdev->constraints->pw_budget_mW != INT_MAX ? mode : 0; return mode; } static const struct attribute_group regulator_dev_group = { .attrs = regulator_dev_attrs, .is_visible = regulator_attr_is_visible, }; static const struct attribute_group *regulator_dev_groups[] = { ®ulator_dev_group, NULL }; static void regulator_dev_release(struct device *dev) { struct regulator_dev *rdev = dev_get_drvdata(dev); debugfs_remove_recursive(rdev->debugfs); kfree(rdev->constraints); of_node_put(rdev->dev.of_node); kfree(rdev); } static void rdev_init_debugfs(struct regulator_dev *rdev) { struct device *parent = rdev->dev.parent; const char *rname = rdev_get_name(rdev); char name[NAME_MAX]; /* Avoid duplicate debugfs directory names */ if (parent && rname == rdev->desc->name) { snprintf(name, sizeof(name), "%s-%s", dev_name(parent), rname); rname = name; } rdev->debugfs = debugfs_create_dir(rname, debugfs_root); if (IS_ERR(rdev->debugfs)) rdev_dbg(rdev, "Failed to create debugfs directory\n"); debugfs_create_u32("use_count", 0444, rdev->debugfs, &rdev->use_count); debugfs_create_u32("open_count", 0444, rdev->debugfs, &rdev->open_count); debugfs_create_u32("bypass_count", 0444, rdev->debugfs, &rdev->bypass_count); } static int regulator_register_resolve_supply(struct device *dev, void *data) { struct regulator_dev *rdev = dev_to_rdev(dev); if (regulator_resolve_supply(rdev)) rdev_dbg(rdev, "unable to resolve supply\n"); return 0; } int regulator_coupler_register(struct regulator_coupler *coupler) { mutex_lock(®ulator_list_mutex); list_add_tail(&coupler->list, ®ulator_coupler_list); mutex_unlock(®ulator_list_mutex); return 0; } static struct regulator_coupler * regulator_find_coupler(struct regulator_dev *rdev) { struct regulator_coupler *coupler; int err; /* * Note that regulators are appended to the list and the generic * coupler is registered first, hence it will be attached at last * if nobody cared. */ list_for_each_entry_reverse(coupler, ®ulator_coupler_list, list) { err = coupler->attach_regulator(coupler, rdev); if (!err) { if (!coupler->balance_voltage && rdev->coupling_desc.n_coupled > 2) goto err_unsupported; return coupler; } if (err < 0) return ERR_PTR(err); if (err == 1) continue; break; } return ERR_PTR(-EINVAL); err_unsupported: if (coupler->detach_regulator) coupler->detach_regulator(coupler, rdev); rdev_err(rdev, "Voltage balancing for multiple regulator couples is unimplemented\n"); return ERR_PTR(-EPERM); } static void regulator_resolve_coupling(struct regulator_dev *rdev) { struct regulator_coupler *coupler = rdev->coupling_desc.coupler; struct coupling_desc *c_desc = &rdev->coupling_desc; int n_coupled = c_desc->n_coupled; struct regulator_dev *c_rdev; int i; for (i = 1; i < n_coupled; i++) { /* already resolved */ if (c_desc->coupled_rdevs[i]) continue; c_rdev = of_parse_coupled_regulator(rdev, i - 1); if (!c_rdev) continue; if (c_rdev->coupling_desc.coupler != coupler) { rdev_err(rdev, "coupler mismatch with %s\n", rdev_get_name(c_rdev)); return; } c_desc->coupled_rdevs[i] = c_rdev; c_desc->n_resolved++; regulator_resolve_coupling(c_rdev); } } static void regulator_remove_coupling(struct regulator_dev *rdev) { struct regulator_coupler *coupler = rdev->coupling_desc.coupler; struct coupling_desc *__c_desc, *c_desc = &rdev->coupling_desc; struct regulator_dev *__c_rdev, *c_rdev; unsigned int __n_coupled, n_coupled; int i, k; int err; n_coupled = c_desc->n_coupled; for (i = 1; i < n_coupled; i++) { c_rdev = c_desc->coupled_rdevs[i]; if (!c_rdev) continue; regulator_lock(c_rdev); __c_desc = &c_rdev->coupling_desc; __n_coupled = __c_desc->n_coupled; for (k = 1; k < __n_coupled; k++) { __c_rdev = __c_desc->coupled_rdevs[k]; if (__c_rdev == rdev) { __c_desc->coupled_rdevs[k] = NULL; __c_desc->n_resolved--; break; } } regulator_unlock(c_rdev); c_desc->coupled_rdevs[i] = NULL; c_desc->n_resolved--; } if (coupler && coupler->detach_regulator) { err = coupler->detach_regulator(coupler, rdev); if (err) rdev_err(rdev, "failed to detach from coupler: %pe\n", ERR_PTR(err)); } kfree(rdev->coupling_desc.coupled_rdevs); rdev->coupling_desc.coupled_rdevs = NULL; } static int regulator_init_coupling(struct regulator_dev *rdev) { struct regulator_dev **coupled; int err, n_phandles; if (!IS_ENABLED(CONFIG_OF)) n_phandles = 0; else n_phandles = of_get_n_coupled(rdev); coupled = kcalloc(n_phandles + 1, sizeof(*coupled), GFP_KERNEL); if (!coupled) return -ENOMEM; rdev->coupling_desc.coupled_rdevs = coupled; /* * Every regulator should always have coupling descriptor filled with * at least pointer to itself. */ rdev->coupling_desc.coupled_rdevs[0] = rdev; rdev->coupling_desc.n_coupled = n_phandles + 1; rdev->coupling_desc.n_resolved++; /* regulator isn't coupled */ if (n_phandles == 0) return 0; if (!of_check_coupling_data(rdev)) return -EPERM; mutex_lock(®ulator_list_mutex); rdev->coupling_desc.coupler = regulator_find_coupler(rdev); mutex_unlock(®ulator_list_mutex); if (IS_ERR(rdev->coupling_desc.coupler)) { err = PTR_ERR(rdev->coupling_desc.coupler); rdev_err(rdev, "failed to get coupler: %pe\n", ERR_PTR(err)); return err; } return 0; } static int generic_coupler_attach(struct regulator_coupler *coupler, struct regulator_dev *rdev) { if (rdev->coupling_desc.n_coupled > 2) { rdev_err(rdev, "Voltage balancing for multiple regulator couples is unimplemented\n"); return -EPERM; } if (!rdev->constraints->always_on) { rdev_err(rdev, "Coupling of a non always-on regulator is unimplemented\n"); return -ENOTSUPP; } return 0; } static struct regulator_coupler generic_regulator_coupler = { .attach_regulator = generic_coupler_attach, }; /** * regulator_register - register regulator * @dev: the device that drive the regulator * @regulator_desc: regulator to register * @cfg: runtime configuration for regulator * * Called by regulator drivers to register a regulator. * * Return: Pointer to a valid &struct regulator_dev on success or * an ERR_PTR() encoded negative error number on failure. */ struct regulator_dev * regulator_register(struct device *dev, const struct regulator_desc *regulator_desc, const struct regulator_config *cfg) { const struct regulator_init_data *init_data; struct regulator_config *config = NULL; static atomic_t regulator_no = ATOMIC_INIT(-1); struct regulator_dev *rdev; bool dangling_cfg_gpiod = false; bool dangling_of_gpiod = false; int ret, i; bool resolved_early = false; if (cfg == NULL) return ERR_PTR(-EINVAL); if (cfg->ena_gpiod) dangling_cfg_gpiod = true; if (regulator_desc == NULL) { ret = -EINVAL; goto rinse; } WARN_ON(!dev || !cfg->dev); if (regulator_desc->name == NULL || regulator_desc->ops == NULL) { ret = -EINVAL; goto rinse; } if (regulator_desc->type != REGULATOR_VOLTAGE && regulator_desc->type != REGULATOR_CURRENT) { ret = -EINVAL; goto rinse; } /* Only one of each should be implemented */ WARN_ON(regulator_desc->ops->get_voltage && regulator_desc->ops->get_voltage_sel); WARN_ON(regulator_desc->ops->set_voltage && regulator_desc->ops->set_voltage_sel); /* If we're using selectors we must implement list_voltage. */ if (regulator_desc->ops->get_voltage_sel && !regulator_desc->ops->list_voltage) { ret = -EINVAL; goto rinse; } if (regulator_desc->ops->set_voltage_sel && !regulator_desc->ops->list_voltage) { ret = -EINVAL; goto rinse; } rdev = kzalloc(sizeof(struct regulator_dev), GFP_KERNEL); if (rdev == NULL) { ret = -ENOMEM; goto rinse; } device_initialize(&rdev->dev); dev_set_drvdata(&rdev->dev, rdev); rdev->dev.class = ®ulator_class; spin_lock_init(&rdev->err_lock); /* * Duplicate the config so the driver could override it after * parsing init data. */ config = kmemdup(cfg, sizeof(*cfg), GFP_KERNEL); if (config == NULL) { ret = -ENOMEM; goto clean; } if (config->init_data) { /* * Providing of_match means the framework is expected to parse * DT to get the init_data. This would conflict with provided * init_data, if set. Warn if it happens. */ if (regulator_desc->of_match) dev_warn(dev, "Using provided init data - OF match ignored\n"); init_data = config->init_data; rdev->dev.of_node = of_node_get(config->of_node); } else { init_data = regulator_of_get_init_data(dev, regulator_desc, config, &rdev->dev.of_node); /* * Sometimes not all resources are probed already so we need to * take that into account. This happens most the time if the * ena_gpiod comes from a gpio extender or something else. */ if (PTR_ERR(init_data) == -EPROBE_DEFER) { ret = -EPROBE_DEFER; goto clean; } /* * We need to keep track of any GPIO descriptor coming from the * device tree until we have handled it over to the core. If the * config that was passed in to this function DOES NOT contain a * descriptor, and the config after this call DOES contain a * descriptor, we definitely got one from parsing the device * tree. */ if (!cfg->ena_gpiod && config->ena_gpiod) dangling_of_gpiod = true; } ww_mutex_init(&rdev->mutex, ®ulator_ww_class); rdev->reg_data = config->driver_data; rdev->owner = regulator_desc->owner; rdev->desc = regulator_desc; if (config->regmap) rdev->regmap = config->regmap; else if (dev_get_regmap(dev, NULL)) rdev->regmap = dev_get_regmap(dev, NULL); else if (dev->parent) rdev->regmap = dev_get_regmap(dev->parent, NULL); INIT_LIST_HEAD(&rdev->consumer_list); INIT_LIST_HEAD(&rdev->list); BLOCKING_INIT_NOTIFIER_HEAD(&rdev->notifier); INIT_DELAYED_WORK(&rdev->disable_work, regulator_disable_work); if (init_data && init_data->supply_regulator) rdev->supply_name = init_data->supply_regulator; else if (regulator_desc->supply_name) rdev->supply_name = regulator_desc->supply_name; /* register with sysfs */ rdev->dev.parent = config->dev; dev_set_name(&rdev->dev, "regulator.%lu", (unsigned long) atomic_inc_return(®ulator_no)); /* set regulator constraints */ if (init_data) rdev->constraints = kmemdup(&init_data->constraints, sizeof(*rdev->constraints), GFP_KERNEL); else rdev->constraints = kzalloc(sizeof(*rdev->constraints), GFP_KERNEL); if (!rdev->constraints) { ret = -ENOMEM; goto wash; } if (regulator_desc->init_cb) { ret = regulator_desc->init_cb(rdev, config); if (ret < 0) goto wash; } if ((rdev->supply_name && !rdev->supply) && (rdev->constraints->always_on || rdev->constraints->boot_on)) { ret = regulator_resolve_supply(rdev); if (ret) rdev_dbg(rdev, "unable to resolve supply early: %pe\n", ERR_PTR(ret)); resolved_early = true; } if (config->ena_gpiod) { ret = regulator_ena_gpio_request(rdev, config); if (ret != 0) { rdev_err(rdev, "Failed to request enable GPIO: %pe\n", ERR_PTR(ret)); goto wash; } /* The regulator core took over the GPIO descriptor */ dangling_cfg_gpiod = false; dangling_of_gpiod = false; } ret = set_machine_constraints(rdev); if (ret == -EPROBE_DEFER && !resolved_early) { /* Regulator might be in bypass mode and so needs its supply * to set the constraints */ /* FIXME: this currently triggers a chicken-and-egg problem * when creating -SUPPLY symlink in sysfs to a regulator * that is just being created */ rdev_dbg(rdev, "will resolve supply early: %s\n", rdev->supply_name); ret = regulator_resolve_supply(rdev); if (!ret) ret = set_machine_constraints(rdev); else rdev_dbg(rdev, "unable to resolve supply early: %pe\n", ERR_PTR(ret)); } if (ret < 0) goto wash; ret = regulator_init_coupling(rdev); if (ret < 0) goto wash; /* add consumers devices */ if (init_data) { for (i = 0; i < init_data->num_consumer_supplies; i++) { ret = set_consumer_device_supply(rdev, init_data->consumer_supplies[i].dev_name, init_data->consumer_supplies[i].supply); if (ret < 0) { dev_err(dev, "Failed to set supply %s\n", init_data->consumer_supplies[i].supply); goto unset_supplies; } } } if (!rdev->desc->ops->get_voltage && !rdev->desc->ops->list_voltage && !rdev->desc->fixed_uV) rdev->is_switch = true; ret = device_add(&rdev->dev); if (ret != 0) goto unset_supplies; rdev_init_debugfs(rdev); /* try to resolve regulators coupling since a new one was registered */ mutex_lock(®ulator_list_mutex); regulator_resolve_coupling(rdev); mutex_unlock(®ulator_list_mutex); /* try to resolve regulators supply since a new one was registered */ class_for_each_device(®ulator_class, NULL, NULL, regulator_register_resolve_supply); kfree(config); return rdev; unset_supplies: mutex_lock(®ulator_list_mutex); unset_regulator_supplies(rdev); regulator_remove_coupling(rdev); mutex_unlock(®ulator_list_mutex); wash: regulator_put(rdev->supply); kfree(rdev->coupling_desc.coupled_rdevs); mutex_lock(®ulator_list_mutex); regulator_ena_gpio_free(rdev); mutex_unlock(®ulator_list_mutex); clean: if (dangling_of_gpiod) gpiod_put(config->ena_gpiod); kfree(config); put_device(&rdev->dev); rinse: if (dangling_cfg_gpiod) gpiod_put(cfg->ena_gpiod); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(regulator_register); /** * regulator_unregister - unregister regulator * @rdev: regulator to unregister * * Called by regulator drivers to unregister a regulator. */ void regulator_unregister(struct regulator_dev *rdev) { if (rdev == NULL) return; if (rdev->supply) { while (rdev->use_count--) regulator_disable(rdev->supply); regulator_put(rdev->supply); } flush_work(&rdev->disable_work.work); mutex_lock(®ulator_list_mutex); WARN_ON(rdev->open_count); regulator_remove_coupling(rdev); unset_regulator_supplies(rdev); list_del(&rdev->list); regulator_ena_gpio_free(rdev); device_unregister(&rdev->dev); mutex_unlock(®ulator_list_mutex); } EXPORT_SYMBOL_GPL(regulator_unregister); #ifdef CONFIG_SUSPEND /** * regulator_suspend - prepare regulators for system wide suspend * @dev: ``&struct device`` pointer that is passed to _regulator_suspend() * * Configure each regulator with it's suspend operating parameters for state. * * Return: 0 on success or a negative error number on failure. */ static int regulator_suspend(struct device *dev) { struct regulator_dev *rdev = dev_to_rdev(dev); suspend_state_t state = pm_suspend_target_state; int ret; const struct regulator_state *rstate; rstate = regulator_get_suspend_state_check(rdev, state); if (!rstate) return 0; regulator_lock(rdev); ret = __suspend_set_state(rdev, rstate); regulator_unlock(rdev); return ret; } static int regulator_resume(struct device *dev) { suspend_state_t state = pm_suspend_target_state; struct regulator_dev *rdev = dev_to_rdev(dev); struct regulator_state *rstate; int ret = 0; rstate = regulator_get_suspend_state(rdev, state); if (rstate == NULL) return 0; /* Avoid grabbing the lock if we don't need to */ if (!rdev->desc->ops->resume) return 0; regulator_lock(rdev); if (rstate->enabled == ENABLE_IN_SUSPEND || rstate->enabled == DISABLE_IN_SUSPEND) ret = rdev->desc->ops->resume(rdev); regulator_unlock(rdev); return ret; } #else /* !CONFIG_SUSPEND */ #define regulator_suspend NULL #define regulator_resume NULL #endif /* !CONFIG_SUSPEND */ #ifdef CONFIG_PM static const struct dev_pm_ops __maybe_unused regulator_pm_ops = { .suspend = regulator_suspend, .resume = regulator_resume, }; #endif const struct class regulator_class = { .name = "regulator", .dev_release = regulator_dev_release, .dev_groups = regulator_dev_groups, #ifdef CONFIG_PM .pm = ®ulator_pm_ops, #endif }; /** * regulator_has_full_constraints - the system has fully specified constraints * * Calling this function will cause the regulator API to disable all * regulators which have a zero use count and don't have an always_on * constraint in a late_initcall. * * The intention is that this will become the default behaviour in a * future kernel release so users are encouraged to use this facility * now. */ void regulator_has_full_constraints(void) { has_full_constraints = 1; } EXPORT_SYMBOL_GPL(regulator_has_full_constraints); /** * rdev_get_drvdata - get rdev regulator driver data * @rdev: regulator * * Get rdev regulator driver private data. This call can be used in the * regulator driver context. * * Return: Pointer to regulator driver private data. */ void *rdev_get_drvdata(struct regulator_dev *rdev) { return rdev->reg_data; } EXPORT_SYMBOL_GPL(rdev_get_drvdata); /** * regulator_get_drvdata - get regulator driver data * @regulator: regulator * * Get regulator driver private data. This call can be used in the consumer * driver context when non API regulator specific functions need to be called. * * Return: Pointer to regulator driver private data. */ void *regulator_get_drvdata(struct regulator *regulator) { return regulator->rdev->reg_data; } EXPORT_SYMBOL_GPL(regulator_get_drvdata); /** * regulator_set_drvdata - set regulator driver data * @regulator: regulator * @data: data */ void regulator_set_drvdata(struct regulator *regulator, void *data) { regulator->rdev->reg_data = data; } EXPORT_SYMBOL_GPL(regulator_set_drvdata); /** * rdev_get_id - get regulator ID * @rdev: regulator * * Return: Regulator ID for @rdev. */ int rdev_get_id(struct regulator_dev *rdev) { return rdev->desc->id; } EXPORT_SYMBOL_GPL(rdev_get_id); struct device *rdev_get_dev(struct regulator_dev *rdev) { return &rdev->dev; } EXPORT_SYMBOL_GPL(rdev_get_dev); struct regmap *rdev_get_regmap(struct regulator_dev *rdev) { return rdev->regmap; } EXPORT_SYMBOL_GPL(rdev_get_regmap); void *regulator_get_init_drvdata(struct regulator_init_data *reg_init_data) { return reg_init_data->driver_data; } EXPORT_SYMBOL_GPL(regulator_get_init_drvdata); #ifdef CONFIG_DEBUG_FS static int supply_map_show(struct seq_file *sf, void *data) { struct regulator_map *map; list_for_each_entry(map, ®ulator_map_list, list) { seq_printf(sf, "%s -> %s.%s\n", rdev_get_name(map->regulator), map->dev_name, map->supply); } return 0; } DEFINE_SHOW_ATTRIBUTE(supply_map); struct summary_data { struct seq_file *s; struct regulator_dev *parent; int level; }; static void regulator_summary_show_subtree(struct seq_file *s, struct regulator_dev *rdev, int level); static int regulator_summary_show_children(struct device *dev, void *data) { struct regulator_dev *rdev = dev_to_rdev(dev); struct summary_data *summary_data = data; if (rdev->supply && rdev->supply->rdev == summary_data->parent) regulator_summary_show_subtree(summary_data->s, rdev, summary_data->level + 1); return 0; } static void regulator_summary_show_subtree(struct seq_file *s, struct regulator_dev *rdev, int level) { struct regulation_constraints *c; struct regulator *consumer; struct summary_data summary_data; unsigned int opmode; if (!rdev) return; opmode = _regulator_get_mode_unlocked(rdev); seq_printf(s, "%*s%-*s %3d %4d %6d %7s ", level * 3 + 1, "", 30 - level * 3, rdev_get_name(rdev), rdev->use_count, rdev->open_count, rdev->bypass_count, regulator_opmode_to_str(opmode)); seq_printf(s, "%5dmV ", regulator_get_voltage_rdev(rdev) / 1000); seq_printf(s, "%5dmA ", _regulator_get_current_limit_unlocked(rdev) / 1000); c = rdev->constraints; if (c) { switch (rdev->desc->type) { case REGULATOR_VOLTAGE: seq_printf(s, "%5dmV %5dmV ", c->min_uV / 1000, c->max_uV / 1000); break; case REGULATOR_CURRENT: seq_printf(s, "%5dmA %5dmA ", c->min_uA / 1000, c->max_uA / 1000); break; } } seq_puts(s, "\n"); list_for_each_entry(consumer, &rdev->consumer_list, list) { if (consumer->dev && consumer->dev->class == ®ulator_class) continue; seq_printf(s, "%*s%-*s ", (level + 1) * 3 + 1, "", 30 - (level + 1) * 3, consumer->supply_name ? consumer->supply_name : consumer->dev ? dev_name(consumer->dev) : "deviceless"); switch (rdev->desc->type) { case REGULATOR_VOLTAGE: seq_printf(s, "%3d %33dmA%c%5dmV %5dmV", consumer->enable_count, consumer->uA_load / 1000, consumer->uA_load && !consumer->enable_count ? '*' : ' ', consumer->voltage[PM_SUSPEND_ON].min_uV / 1000, consumer->voltage[PM_SUSPEND_ON].max_uV / 1000); break; case REGULATOR_CURRENT: break; } seq_puts(s, "\n"); } summary_data.s = s; summary_data.level = level; summary_data.parent = rdev; class_for_each_device(®ulator_class, NULL, &summary_data, regulator_summary_show_children); } struct summary_lock_data { struct ww_acquire_ctx *ww_ctx; struct regulator_dev **new_contended_rdev; struct regulator_dev **old_contended_rdev; }; static int regulator_summary_lock_one(struct device *dev, void *data) { struct regulator_dev *rdev = dev_to_rdev(dev); struct summary_lock_data *lock_data = data; int ret = 0; if (rdev != *lock_data->old_contended_rdev) { ret = regulator_lock_nested(rdev, lock_data->ww_ctx); if (ret == -EDEADLK) *lock_data->new_contended_rdev = rdev; else WARN_ON_ONCE(ret); } else { *lock_data->old_contended_rdev = NULL; } return ret; } static int regulator_summary_unlock_one(struct device *dev, void *data) { struct regulator_dev *rdev = dev_to_rdev(dev); struct summary_lock_data *lock_data = data; if (lock_data) { if (rdev == *lock_data->new_contended_rdev) return -EDEADLK; } regulator_unlock(rdev); return 0; } static int regulator_summary_lock_all(struct ww_acquire_ctx *ww_ctx, struct regulator_dev **new_contended_rdev, struct regulator_dev **old_contended_rdev) { struct summary_lock_data lock_data; int ret; lock_data.ww_ctx = ww_ctx; lock_data.new_contended_rdev = new_contended_rdev; lock_data.old_contended_rdev = old_contended_rdev; ret = class_for_each_device(®ulator_class, NULL, &lock_data, regulator_summary_lock_one); if (ret) class_for_each_device(®ulator_class, NULL, &lock_data, regulator_summary_unlock_one); return ret; } static void regulator_summary_lock(struct ww_acquire_ctx *ww_ctx) { struct regulator_dev *new_contended_rdev = NULL; struct regulator_dev *old_contended_rdev = NULL; int err; mutex_lock(®ulator_list_mutex); ww_acquire_init(ww_ctx, ®ulator_ww_class); do { if (new_contended_rdev) { ww_mutex_lock_slow(&new_contended_rdev->mutex, ww_ctx); old_contended_rdev = new_contended_rdev; old_contended_rdev->ref_cnt++; old_contended_rdev->mutex_owner = current; } err = regulator_summary_lock_all(ww_ctx, &new_contended_rdev, &old_contended_rdev); if (old_contended_rdev) regulator_unlock(old_contended_rdev); } while (err == -EDEADLK); ww_acquire_done(ww_ctx); } static void regulator_summary_unlock(struct ww_acquire_ctx *ww_ctx) { class_for_each_device(®ulator_class, NULL, NULL, regulator_summary_unlock_one); ww_acquire_fini(ww_ctx); mutex_unlock(®ulator_list_mutex); } static int regulator_summary_show_roots(struct device *dev, void *data) { struct regulator_dev *rdev = dev_to_rdev(dev); struct seq_file *s = data; if (!rdev->supply) regulator_summary_show_subtree(s, rdev, 0); return 0; } static int regulator_summary_show(struct seq_file *s, void *data) { struct ww_acquire_ctx ww_ctx; seq_puts(s, " regulator use open bypass opmode voltage current min max\n"); seq_puts(s, "---------------------------------------------------------------------------------------\n"); regulator_summary_lock(&ww_ctx); class_for_each_device(®ulator_class, NULL, s, regulator_summary_show_roots); regulator_summary_unlock(&ww_ctx); return 0; } DEFINE_SHOW_ATTRIBUTE(regulator_summary); #endif /* CONFIG_DEBUG_FS */ static int __init regulator_init(void) { int ret; ret = class_register(®ulator_class); debugfs_root = debugfs_create_dir("regulator", NULL); if (IS_ERR(debugfs_root)) pr_debug("regulator: Failed to create debugfs directory\n"); #ifdef CONFIG_DEBUG_FS debugfs_create_file("supply_map", 0444, debugfs_root, NULL, &supply_map_fops); debugfs_create_file("regulator_summary", 0444, debugfs_root, NULL, ®ulator_summary_fops); #endif regulator_dummy_init(); regulator_coupler_register(&generic_regulator_coupler); return ret; } /* init early to allow our consumers to complete system booting */ core_initcall(regulator_init); static int regulator_late_cleanup(struct device *dev, void *data) { struct regulator_dev *rdev = dev_to_rdev(dev); struct regulation_constraints *c = rdev->constraints; int ret; if (c && c->always_on) return 0; if (!regulator_ops_is_valid(rdev, REGULATOR_CHANGE_STATUS)) return 0; regulator_lock(rdev); if (rdev->use_count) goto unlock; /* If reading the status failed, assume that it's off. */ if (_regulator_is_enabled(rdev) <= 0) goto unlock; if (have_full_constraints()) { /* We log since this may kill the system if it goes * wrong. */ rdev_info(rdev, "disabling\n"); ret = _regulator_do_disable(rdev); if (ret != 0) rdev_err(rdev, "couldn't disable: %pe\n", ERR_PTR(ret)); } else { /* The intention is that in future we will * assume that full constraints are provided * so warn even if we aren't going to do * anything here. */ rdev_warn(rdev, "incomplete constraints, leaving on\n"); } unlock: regulator_unlock(rdev); return 0; } static bool regulator_ignore_unused; static int __init regulator_ignore_unused_setup(char *__unused) { regulator_ignore_unused = true; return 1; } __setup("regulator_ignore_unused", regulator_ignore_unused_setup); static void regulator_init_complete_work_function(struct work_struct *work) { /* * Regulators may had failed to resolve their input supplies * when were registered, either because the input supply was * not registered yet or because its parent device was not * bound yet. So attempt to resolve the input supplies for * pending regulators before trying to disable unused ones. */ class_for_each_device(®ulator_class, NULL, NULL, regulator_register_resolve_supply); /* * For debugging purposes, it may be useful to prevent unused * regulators from being disabled. */ if (regulator_ignore_unused) { pr_warn("regulator: Not disabling unused regulators\n"); return; } /* If we have a full configuration then disable any regulators * we have permission to change the status for and which are * not in use or always_on. This is effectively the default * for DT and ACPI as they have full constraints. */ class_for_each_device(®ulator_class, NULL, NULL, regulator_late_cleanup); } static DECLARE_DELAYED_WORK(regulator_init_complete_work, regulator_init_complete_work_function); static int __init regulator_init_complete(void) { /* * Since DT doesn't provide an idiomatic mechanism for * enabling full constraints and since it's much more natural * with DT to provide them just assume that a DT enabled * system has full constraints. */ if (of_have_populated_dt()) has_full_constraints = true; /* * We punt completion for an arbitrary amount of time since * systems like distros will load many drivers from userspace * so consumers might not always be ready yet, this is * particularly an issue with laptops where this might bounce * the display off then on. Ideally we'd get a notification * from userspace when this happens but we don't so just wait * a bit and hope we waited long enough. It'd be better if * we'd only do this on systems that need it, and a kernel * command line option might be useful. */ schedule_delayed_work(®ulator_init_complete_work, msecs_to_jiffies(30000)); return 0; } late_initcall_sync(regulator_init_complete); |
| 11 12 10 2 8 10 12 11 13 4 1 1 13 27 27 1 1 1 1 1 1 3 3 1 2 2 3 3 3 3 3 3 2 26 1 27 1 26 25 25 26 1 26 1 26 11 11 10 10 10 10 10 10 10 10 10 10 10 10 6 6 6 6 6 5 5 5 5 6 6 7 7 7 27 27 27 27 1 1 1 1 1 1 1 1 1 5 5 3 3 9 25 25 25 25 26 26 26 2 26 25 25 23 22 40 1 6 6 7 2 2 2 2 2 4 4 3 3 2 1 2 2 2 1 3 5 4 3 3 3 3 1 2 90 30 35 4 31 3 2 2 2 3 5 2 1 1 2 4 1 4 9 9 9 9 9 8 8 6 6 2 2 3 2 1 1 4 3 2 2 1 20 19 18 17 10 10 18 8 18 7 4 4 3 4 4 3 3 18 18 12 11 10 10 6 9 1 9 4 2 10 10 5 1 1 3 3 3 3 92 2 2 26 3 4 5 6 1 90 10 3 21 12 5 2 1 8 6 40 110 | 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES. * * Kernel side components to support tools/testing/selftests/iommu */ #include <linux/anon_inodes.h> #include <linux/debugfs.h> #include <linux/fault-inject.h> #include <linux/file.h> #include <linux/iommu.h> #include <linux/platform_device.h> #include <linux/slab.h> #include <linux/xarray.h> #include <uapi/linux/iommufd.h> #include "../iommu-priv.h" #include "io_pagetable.h" #include "iommufd_private.h" #include "iommufd_test.h" static DECLARE_FAULT_ATTR(fail_iommufd); static struct dentry *dbgfs_root; static struct platform_device *selftest_iommu_dev; static const struct iommu_ops mock_ops; static struct iommu_domain_ops domain_nested_ops; size_t iommufd_test_memory_limit = 65536; struct mock_bus_type { struct bus_type bus; struct notifier_block nb; }; static struct mock_bus_type iommufd_mock_bus_type = { .bus = { .name = "iommufd_mock", }, }; static DEFINE_IDA(mock_dev_ida); enum { MOCK_DIRTY_TRACK = 1, MOCK_IO_PAGE_SIZE = PAGE_SIZE / 2, MOCK_HUGE_PAGE_SIZE = 512 * MOCK_IO_PAGE_SIZE, /* * Like a real page table alignment requires the low bits of the address * to be zero. xarray also requires the high bit to be zero, so we store * the pfns shifted. The upper bits are used for metadata. */ MOCK_PFN_MASK = ULONG_MAX / MOCK_IO_PAGE_SIZE, _MOCK_PFN_START = MOCK_PFN_MASK + 1, MOCK_PFN_START_IOVA = _MOCK_PFN_START, MOCK_PFN_LAST_IOVA = _MOCK_PFN_START, MOCK_PFN_DIRTY_IOVA = _MOCK_PFN_START << 1, MOCK_PFN_HUGE_IOVA = _MOCK_PFN_START << 2, }; /* * Syzkaller has trouble randomizing the correct iova to use since it is linked * to the map ioctl's output, and it has no ide about that. So, simplify things. * In syzkaller mode the 64 bit IOVA is converted into an nth area and offset * value. This has a much smaller randomization space and syzkaller can hit it. */ static unsigned long __iommufd_test_syz_conv_iova(struct io_pagetable *iopt, u64 *iova) { struct syz_layout { __u32 nth_area; __u32 offset; }; struct syz_layout *syz = (void *)iova; unsigned int nth = syz->nth_area; struct iopt_area *area; down_read(&iopt->iova_rwsem); for (area = iopt_area_iter_first(iopt, 0, ULONG_MAX); area; area = iopt_area_iter_next(area, 0, ULONG_MAX)) { if (nth == 0) { up_read(&iopt->iova_rwsem); return iopt_area_iova(area) + syz->offset; } nth--; } up_read(&iopt->iova_rwsem); return 0; } static unsigned long iommufd_test_syz_conv_iova(struct iommufd_access *access, u64 *iova) { unsigned long ret; mutex_lock(&access->ioas_lock); if (!access->ioas) { mutex_unlock(&access->ioas_lock); return 0; } ret = __iommufd_test_syz_conv_iova(&access->ioas->iopt, iova); mutex_unlock(&access->ioas_lock); return ret; } void iommufd_test_syz_conv_iova_id(struct iommufd_ucmd *ucmd, unsigned int ioas_id, u64 *iova, u32 *flags) { struct iommufd_ioas *ioas; if (!(*flags & MOCK_FLAGS_ACCESS_SYZ)) return; *flags &= ~(u32)MOCK_FLAGS_ACCESS_SYZ; ioas = iommufd_get_ioas(ucmd->ictx, ioas_id); if (IS_ERR(ioas)) return; *iova = __iommufd_test_syz_conv_iova(&ioas->iopt, iova); iommufd_put_object(ucmd->ictx, &ioas->obj); } struct mock_iommu_domain { unsigned long flags; struct iommu_domain domain; struct xarray pfns; }; static inline struct mock_iommu_domain * to_mock_domain(struct iommu_domain *domain) { return container_of(domain, struct mock_iommu_domain, domain); } struct mock_iommu_domain_nested { struct iommu_domain domain; struct mock_viommu *mock_viommu; struct mock_iommu_domain *parent; u32 iotlb[MOCK_NESTED_DOMAIN_IOTLB_NUM]; }; static inline struct mock_iommu_domain_nested * to_mock_nested(struct iommu_domain *domain) { return container_of(domain, struct mock_iommu_domain_nested, domain); } struct mock_viommu { struct iommufd_viommu core; struct mock_iommu_domain *s2_parent; }; static inline struct mock_viommu *to_mock_viommu(struct iommufd_viommu *viommu) { return container_of(viommu, struct mock_viommu, core); } enum selftest_obj_type { TYPE_IDEV, }; struct mock_dev { struct device dev; unsigned long flags; int id; u32 cache[MOCK_DEV_CACHE_NUM]; }; static inline struct mock_dev *to_mock_dev(struct device *dev) { return container_of(dev, struct mock_dev, dev); } struct selftest_obj { struct iommufd_object obj; enum selftest_obj_type type; union { struct { struct iommufd_device *idev; struct iommufd_ctx *ictx; struct mock_dev *mock_dev; } idev; }; }; static inline struct selftest_obj *to_selftest_obj(struct iommufd_object *obj) { return container_of(obj, struct selftest_obj, obj); } static int mock_domain_nop_attach(struct iommu_domain *domain, struct device *dev) { struct mock_dev *mdev = to_mock_dev(dev); if (domain->dirty_ops && (mdev->flags & MOCK_FLAGS_DEVICE_NO_DIRTY)) return -EINVAL; return 0; } static const struct iommu_domain_ops mock_blocking_ops = { .attach_dev = mock_domain_nop_attach, }; static struct iommu_domain mock_blocking_domain = { .type = IOMMU_DOMAIN_BLOCKED, .ops = &mock_blocking_ops, }; static void *mock_domain_hw_info(struct device *dev, u32 *length, u32 *type) { struct iommu_test_hw_info *info; info = kzalloc(sizeof(*info), GFP_KERNEL); if (!info) return ERR_PTR(-ENOMEM); info->test_reg = IOMMU_HW_INFO_SELFTEST_REGVAL; *length = sizeof(*info); *type = IOMMU_HW_INFO_TYPE_SELFTEST; return info; } static int mock_domain_set_dirty_tracking(struct iommu_domain *domain, bool enable) { struct mock_iommu_domain *mock = to_mock_domain(domain); unsigned long flags = mock->flags; if (enable && !domain->dirty_ops) return -EINVAL; /* No change? */ if (!(enable ^ !!(flags & MOCK_DIRTY_TRACK))) return 0; flags = (enable ? flags | MOCK_DIRTY_TRACK : flags & ~MOCK_DIRTY_TRACK); mock->flags = flags; return 0; } static bool mock_test_and_clear_dirty(struct mock_iommu_domain *mock, unsigned long iova, size_t page_size, unsigned long flags) { unsigned long cur, end = iova + page_size - 1; bool dirty = false; void *ent, *old; for (cur = iova; cur < end; cur += MOCK_IO_PAGE_SIZE) { ent = xa_load(&mock->pfns, cur / MOCK_IO_PAGE_SIZE); if (!ent || !(xa_to_value(ent) & MOCK_PFN_DIRTY_IOVA)) continue; dirty = true; /* Clear dirty */ if (!(flags & IOMMU_DIRTY_NO_CLEAR)) { unsigned long val; val = xa_to_value(ent) & ~MOCK_PFN_DIRTY_IOVA; old = xa_store(&mock->pfns, cur / MOCK_IO_PAGE_SIZE, xa_mk_value(val), GFP_KERNEL); WARN_ON_ONCE(ent != old); } } return dirty; } static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain, unsigned long iova, size_t size, unsigned long flags, struct iommu_dirty_bitmap *dirty) { struct mock_iommu_domain *mock = to_mock_domain(domain); unsigned long end = iova + size; void *ent; if (!(mock->flags & MOCK_DIRTY_TRACK) && dirty->bitmap) return -EINVAL; do { unsigned long pgsize = MOCK_IO_PAGE_SIZE; unsigned long head; ent = xa_load(&mock->pfns, iova / MOCK_IO_PAGE_SIZE); if (!ent) { iova += pgsize; continue; } if (xa_to_value(ent) & MOCK_PFN_HUGE_IOVA) pgsize = MOCK_HUGE_PAGE_SIZE; head = iova & ~(pgsize - 1); /* Clear dirty */ if (mock_test_and_clear_dirty(mock, head, pgsize, flags)) iommu_dirty_bitmap_record(dirty, iova, pgsize); iova += pgsize; } while (iova < end); return 0; } static const struct iommu_dirty_ops dirty_ops = { .set_dirty_tracking = mock_domain_set_dirty_tracking, .read_and_clear_dirty = mock_domain_read_and_clear_dirty, }; static struct mock_iommu_domain_nested * __mock_domain_alloc_nested(const struct iommu_user_data *user_data) { struct mock_iommu_domain_nested *mock_nested; struct iommu_hwpt_selftest user_cfg; int rc, i; if (user_data->type != IOMMU_HWPT_DATA_SELFTEST) return ERR_PTR(-EOPNOTSUPP); rc = iommu_copy_struct_from_user(&user_cfg, user_data, IOMMU_HWPT_DATA_SELFTEST, iotlb); if (rc) return ERR_PTR(rc); mock_nested = kzalloc(sizeof(*mock_nested), GFP_KERNEL); if (!mock_nested) return ERR_PTR(-ENOMEM); mock_nested->domain.ops = &domain_nested_ops; mock_nested->domain.type = IOMMU_DOMAIN_NESTED; for (i = 0; i < MOCK_NESTED_DOMAIN_IOTLB_NUM; i++) mock_nested->iotlb[i] = user_cfg.iotlb; return mock_nested; } static struct iommu_domain * mock_domain_alloc_nested(struct device *dev, struct iommu_domain *parent, u32 flags, const struct iommu_user_data *user_data) { struct mock_iommu_domain_nested *mock_nested; struct mock_iommu_domain *mock_parent; if (flags) return ERR_PTR(-EOPNOTSUPP); if (!parent || parent->ops != mock_ops.default_domain_ops) return ERR_PTR(-EINVAL); mock_parent = to_mock_domain(parent); if (!mock_parent) return ERR_PTR(-EINVAL); mock_nested = __mock_domain_alloc_nested(user_data); if (IS_ERR(mock_nested)) return ERR_CAST(mock_nested); mock_nested->parent = mock_parent; return &mock_nested->domain; } static struct iommu_domain * mock_domain_alloc_paging_flags(struct device *dev, u32 flags, const struct iommu_user_data *user_data) { bool has_dirty_flag = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING; const u32 PAGING_FLAGS = IOMMU_HWPT_ALLOC_DIRTY_TRACKING | IOMMU_HWPT_ALLOC_NEST_PARENT; struct mock_dev *mdev = to_mock_dev(dev); bool no_dirty_ops = mdev->flags & MOCK_FLAGS_DEVICE_NO_DIRTY; struct mock_iommu_domain *mock; if (user_data) return ERR_PTR(-EOPNOTSUPP); if ((flags & ~PAGING_FLAGS) || (has_dirty_flag && no_dirty_ops)) return ERR_PTR(-EOPNOTSUPP); mock = kzalloc(sizeof(*mock), GFP_KERNEL); if (!mock) return ERR_PTR(-ENOMEM); mock->domain.geometry.aperture_start = MOCK_APERTURE_START; mock->domain.geometry.aperture_end = MOCK_APERTURE_LAST; mock->domain.pgsize_bitmap = MOCK_IO_PAGE_SIZE; if (dev && mdev->flags & MOCK_FLAGS_DEVICE_HUGE_IOVA) mock->domain.pgsize_bitmap |= MOCK_HUGE_PAGE_SIZE; mock->domain.ops = mock_ops.default_domain_ops; mock->domain.type = IOMMU_DOMAIN_UNMANAGED; xa_init(&mock->pfns); if (has_dirty_flag) mock->domain.dirty_ops = &dirty_ops; return &mock->domain; } static void mock_domain_free(struct iommu_domain *domain) { struct mock_iommu_domain *mock = to_mock_domain(domain); WARN_ON(!xa_empty(&mock->pfns)); kfree(mock); } static int mock_domain_map_pages(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t pgsize, size_t pgcount, int prot, gfp_t gfp, size_t *mapped) { struct mock_iommu_domain *mock = to_mock_domain(domain); unsigned long flags = MOCK_PFN_START_IOVA; unsigned long start_iova = iova; /* * xarray does not reliably work with fault injection because it does a * retry allocation, so put our own failure point. */ if (iommufd_should_fail()) return -ENOENT; WARN_ON(iova % MOCK_IO_PAGE_SIZE); WARN_ON(pgsize % MOCK_IO_PAGE_SIZE); for (; pgcount; pgcount--) { size_t cur; for (cur = 0; cur != pgsize; cur += MOCK_IO_PAGE_SIZE) { void *old; if (pgcount == 1 && cur + MOCK_IO_PAGE_SIZE == pgsize) flags = MOCK_PFN_LAST_IOVA; if (pgsize != MOCK_IO_PAGE_SIZE) { flags |= MOCK_PFN_HUGE_IOVA; } old = xa_store(&mock->pfns, iova / MOCK_IO_PAGE_SIZE, xa_mk_value((paddr / MOCK_IO_PAGE_SIZE) | flags), gfp); if (xa_is_err(old)) { for (; start_iova != iova; start_iova += MOCK_IO_PAGE_SIZE) xa_erase(&mock->pfns, start_iova / MOCK_IO_PAGE_SIZE); return xa_err(old); } WARN_ON(old); iova += MOCK_IO_PAGE_SIZE; paddr += MOCK_IO_PAGE_SIZE; *mapped += MOCK_IO_PAGE_SIZE; flags = 0; } } return 0; } static size_t mock_domain_unmap_pages(struct iommu_domain *domain, unsigned long iova, size_t pgsize, size_t pgcount, struct iommu_iotlb_gather *iotlb_gather) { struct mock_iommu_domain *mock = to_mock_domain(domain); bool first = true; size_t ret = 0; void *ent; WARN_ON(iova % MOCK_IO_PAGE_SIZE); WARN_ON(pgsize % MOCK_IO_PAGE_SIZE); for (; pgcount; pgcount--) { size_t cur; for (cur = 0; cur != pgsize; cur += MOCK_IO_PAGE_SIZE) { ent = xa_erase(&mock->pfns, iova / MOCK_IO_PAGE_SIZE); /* * iommufd generates unmaps that must be a strict * superset of the map's performend So every * starting/ending IOVA should have been an iova passed * to map. * * This simple logic doesn't work when the HUGE_PAGE is * turned on since the core code will automatically * switch between the two page sizes creating a break in * the unmap calls. The break can land in the middle of * contiguous IOVA. */ if (!(domain->pgsize_bitmap & MOCK_HUGE_PAGE_SIZE)) { if (first) { WARN_ON(ent && !(xa_to_value(ent) & MOCK_PFN_START_IOVA)); first = false; } if (pgcount == 1 && cur + MOCK_IO_PAGE_SIZE == pgsize) WARN_ON(ent && !(xa_to_value(ent) & MOCK_PFN_LAST_IOVA)); } iova += MOCK_IO_PAGE_SIZE; ret += MOCK_IO_PAGE_SIZE; } } return ret; } static phys_addr_t mock_domain_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { struct mock_iommu_domain *mock = to_mock_domain(domain); void *ent; WARN_ON(iova % MOCK_IO_PAGE_SIZE); ent = xa_load(&mock->pfns, iova / MOCK_IO_PAGE_SIZE); WARN_ON(!ent); return (xa_to_value(ent) & MOCK_PFN_MASK) * MOCK_IO_PAGE_SIZE; } static bool mock_domain_capable(struct device *dev, enum iommu_cap cap) { struct mock_dev *mdev = to_mock_dev(dev); switch (cap) { case IOMMU_CAP_CACHE_COHERENCY: return true; case IOMMU_CAP_DIRTY_TRACKING: return !(mdev->flags & MOCK_FLAGS_DEVICE_NO_DIRTY); default: break; } return false; } static struct iopf_queue *mock_iommu_iopf_queue; static struct mock_iommu_device { struct iommu_device iommu_dev; struct completion complete; refcount_t users; } mock_iommu; static struct iommu_device *mock_probe_device(struct device *dev) { if (dev->bus != &iommufd_mock_bus_type.bus) return ERR_PTR(-ENODEV); return &mock_iommu.iommu_dev; } static void mock_domain_page_response(struct device *dev, struct iopf_fault *evt, struct iommu_page_response *msg) { } static int mock_dev_enable_feat(struct device *dev, enum iommu_dev_features feat) { if (feat != IOMMU_DEV_FEAT_IOPF || !mock_iommu_iopf_queue) return -ENODEV; return iopf_queue_add_device(mock_iommu_iopf_queue, dev); } static int mock_dev_disable_feat(struct device *dev, enum iommu_dev_features feat) { if (feat != IOMMU_DEV_FEAT_IOPF || !mock_iommu_iopf_queue) return -ENODEV; iopf_queue_remove_device(mock_iommu_iopf_queue, dev); return 0; } static void mock_viommu_destroy(struct iommufd_viommu *viommu) { struct mock_iommu_device *mock_iommu = container_of( viommu->iommu_dev, struct mock_iommu_device, iommu_dev); if (refcount_dec_and_test(&mock_iommu->users)) complete(&mock_iommu->complete); /* iommufd core frees mock_viommu and viommu */ } static struct iommu_domain * mock_viommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, const struct iommu_user_data *user_data) { struct mock_viommu *mock_viommu = to_mock_viommu(viommu); struct mock_iommu_domain_nested *mock_nested; if (flags) return ERR_PTR(-EOPNOTSUPP); mock_nested = __mock_domain_alloc_nested(user_data); if (IS_ERR(mock_nested)) return ERR_CAST(mock_nested); mock_nested->mock_viommu = mock_viommu; mock_nested->parent = mock_viommu->s2_parent; return &mock_nested->domain; } static int mock_viommu_cache_invalidate(struct iommufd_viommu *viommu, struct iommu_user_data_array *array) { struct iommu_viommu_invalidate_selftest *cmds; struct iommu_viommu_invalidate_selftest *cur; struct iommu_viommu_invalidate_selftest *end; int rc; /* A zero-length array is allowed to validate the array type */ if (array->entry_num == 0 && array->type == IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST) { array->entry_num = 0; return 0; } cmds = kcalloc(array->entry_num, sizeof(*cmds), GFP_KERNEL); if (!cmds) return -ENOMEM; cur = cmds; end = cmds + array->entry_num; static_assert(sizeof(*cmds) == 3 * sizeof(u32)); rc = iommu_copy_struct_from_full_user_array( cmds, sizeof(*cmds), array, IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST); if (rc) goto out; while (cur != end) { struct mock_dev *mdev; struct device *dev; int i; if (cur->flags & ~IOMMU_TEST_INVALIDATE_FLAG_ALL) { rc = -EOPNOTSUPP; goto out; } if (cur->cache_id > MOCK_DEV_CACHE_ID_MAX) { rc = -EINVAL; goto out; } xa_lock(&viommu->vdevs); dev = iommufd_viommu_find_dev(viommu, (unsigned long)cur->vdev_id); if (!dev) { xa_unlock(&viommu->vdevs); rc = -EINVAL; goto out; } mdev = container_of(dev, struct mock_dev, dev); if (cur->flags & IOMMU_TEST_INVALIDATE_FLAG_ALL) { /* Invalidate all cache entries and ignore cache_id */ for (i = 0; i < MOCK_DEV_CACHE_NUM; i++) mdev->cache[i] = 0; } else { mdev->cache[cur->cache_id] = 0; } xa_unlock(&viommu->vdevs); cur++; } out: array->entry_num = cur - cmds; kfree(cmds); return rc; } static struct iommufd_viommu_ops mock_viommu_ops = { .destroy = mock_viommu_destroy, .alloc_domain_nested = mock_viommu_alloc_domain_nested, .cache_invalidate = mock_viommu_cache_invalidate, }; static struct iommufd_viommu *mock_viommu_alloc(struct device *dev, struct iommu_domain *domain, struct iommufd_ctx *ictx, unsigned int viommu_type) { struct mock_iommu_device *mock_iommu = iommu_get_iommu_dev(dev, struct mock_iommu_device, iommu_dev); struct mock_viommu *mock_viommu; if (viommu_type != IOMMU_VIOMMU_TYPE_SELFTEST) return ERR_PTR(-EOPNOTSUPP); mock_viommu = iommufd_viommu_alloc(ictx, struct mock_viommu, core, &mock_viommu_ops); if (IS_ERR(mock_viommu)) return ERR_CAST(mock_viommu); refcount_inc(&mock_iommu->users); return &mock_viommu->core; } static const struct iommu_ops mock_ops = { /* * IOMMU_DOMAIN_BLOCKED cannot be returned from def_domain_type() * because it is zero. */ .default_domain = &mock_blocking_domain, .blocked_domain = &mock_blocking_domain, .owner = THIS_MODULE, .pgsize_bitmap = MOCK_IO_PAGE_SIZE, .hw_info = mock_domain_hw_info, .domain_alloc_paging_flags = mock_domain_alloc_paging_flags, .domain_alloc_nested = mock_domain_alloc_nested, .capable = mock_domain_capable, .device_group = generic_device_group, .probe_device = mock_probe_device, .page_response = mock_domain_page_response, .dev_enable_feat = mock_dev_enable_feat, .dev_disable_feat = mock_dev_disable_feat, .user_pasid_table = true, .viommu_alloc = mock_viommu_alloc, .default_domain_ops = &(struct iommu_domain_ops){ .free = mock_domain_free, .attach_dev = mock_domain_nop_attach, .map_pages = mock_domain_map_pages, .unmap_pages = mock_domain_unmap_pages, .iova_to_phys = mock_domain_iova_to_phys, }, }; static void mock_domain_free_nested(struct iommu_domain *domain) { kfree(to_mock_nested(domain)); } static int mock_domain_cache_invalidate_user(struct iommu_domain *domain, struct iommu_user_data_array *array) { struct mock_iommu_domain_nested *mock_nested = to_mock_nested(domain); struct iommu_hwpt_invalidate_selftest inv; u32 processed = 0; int i = 0, j; int rc = 0; if (array->type != IOMMU_HWPT_INVALIDATE_DATA_SELFTEST) { rc = -EINVAL; goto out; } for ( ; i < array->entry_num; i++) { rc = iommu_copy_struct_from_user_array(&inv, array, IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, i, iotlb_id); if (rc) break; if (inv.flags & ~IOMMU_TEST_INVALIDATE_FLAG_ALL) { rc = -EOPNOTSUPP; break; } if (inv.iotlb_id > MOCK_NESTED_DOMAIN_IOTLB_ID_MAX) { rc = -EINVAL; break; } if (inv.flags & IOMMU_TEST_INVALIDATE_FLAG_ALL) { /* Invalidate all mock iotlb entries and ignore iotlb_id */ for (j = 0; j < MOCK_NESTED_DOMAIN_IOTLB_NUM; j++) mock_nested->iotlb[j] = 0; } else { mock_nested->iotlb[inv.iotlb_id] = 0; } processed++; } out: array->entry_num = processed; return rc; } static struct iommu_domain_ops domain_nested_ops = { .free = mock_domain_free_nested, .attach_dev = mock_domain_nop_attach, .cache_invalidate_user = mock_domain_cache_invalidate_user, }; static inline struct iommufd_hw_pagetable * __get_md_pagetable(struct iommufd_ucmd *ucmd, u32 mockpt_id, u32 hwpt_type) { struct iommufd_object *obj; obj = iommufd_get_object(ucmd->ictx, mockpt_id, hwpt_type); if (IS_ERR(obj)) return ERR_CAST(obj); return container_of(obj, struct iommufd_hw_pagetable, obj); } static inline struct iommufd_hw_pagetable * get_md_pagetable(struct iommufd_ucmd *ucmd, u32 mockpt_id, struct mock_iommu_domain **mock) { struct iommufd_hw_pagetable *hwpt; hwpt = __get_md_pagetable(ucmd, mockpt_id, IOMMUFD_OBJ_HWPT_PAGING); if (IS_ERR(hwpt)) return hwpt; if (hwpt->domain->type != IOMMU_DOMAIN_UNMANAGED || hwpt->domain->ops != mock_ops.default_domain_ops) { iommufd_put_object(ucmd->ictx, &hwpt->obj); return ERR_PTR(-EINVAL); } *mock = to_mock_domain(hwpt->domain); return hwpt; } static inline struct iommufd_hw_pagetable * get_md_pagetable_nested(struct iommufd_ucmd *ucmd, u32 mockpt_id, struct mock_iommu_domain_nested **mock_nested) { struct iommufd_hw_pagetable *hwpt; hwpt = __get_md_pagetable(ucmd, mockpt_id, IOMMUFD_OBJ_HWPT_NESTED); if (IS_ERR(hwpt)) return hwpt; if (hwpt->domain->type != IOMMU_DOMAIN_NESTED || hwpt->domain->ops != &domain_nested_ops) { iommufd_put_object(ucmd->ictx, &hwpt->obj); return ERR_PTR(-EINVAL); } *mock_nested = to_mock_nested(hwpt->domain); return hwpt; } static void mock_dev_release(struct device *dev) { struct mock_dev *mdev = to_mock_dev(dev); ida_free(&mock_dev_ida, mdev->id); kfree(mdev); } static struct mock_dev *mock_dev_create(unsigned long dev_flags) { struct mock_dev *mdev; int rc, i; if (dev_flags & ~(MOCK_FLAGS_DEVICE_NO_DIRTY | MOCK_FLAGS_DEVICE_HUGE_IOVA)) return ERR_PTR(-EINVAL); mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); if (!mdev) return ERR_PTR(-ENOMEM); device_initialize(&mdev->dev); mdev->flags = dev_flags; mdev->dev.release = mock_dev_release; mdev->dev.bus = &iommufd_mock_bus_type.bus; for (i = 0; i < MOCK_DEV_CACHE_NUM; i++) mdev->cache[i] = IOMMU_TEST_DEV_CACHE_DEFAULT; rc = ida_alloc(&mock_dev_ida, GFP_KERNEL); if (rc < 0) goto err_put; mdev->id = rc; rc = dev_set_name(&mdev->dev, "iommufd_mock%u", mdev->id); if (rc) goto err_put; rc = device_add(&mdev->dev); if (rc) goto err_put; return mdev; err_put: put_device(&mdev->dev); return ERR_PTR(rc); } static void mock_dev_destroy(struct mock_dev *mdev) { device_unregister(&mdev->dev); } bool iommufd_selftest_is_mock_dev(struct device *dev) { return dev->release == mock_dev_release; } /* Create an hw_pagetable with the mock domain so we can test the domain ops */ static int iommufd_test_mock_domain(struct iommufd_ucmd *ucmd, struct iommu_test_cmd *cmd) { struct iommufd_device *idev; struct selftest_obj *sobj; u32 pt_id = cmd->id; u32 dev_flags = 0; u32 idev_id; int rc; sobj = iommufd_object_alloc(ucmd->ictx, sobj, IOMMUFD_OBJ_SELFTEST); if (IS_ERR(sobj)) return PTR_ERR(sobj); sobj->idev.ictx = ucmd->ictx; sobj->type = TYPE_IDEV; if (cmd->op == IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS) dev_flags = cmd->mock_domain_flags.dev_flags; sobj->idev.mock_dev = mock_dev_create(dev_flags); if (IS_ERR(sobj->idev.mock_dev)) { rc = PTR_ERR(sobj->idev.mock_dev); goto out_sobj; } idev = iommufd_device_bind(ucmd->ictx, &sobj->idev.mock_dev->dev, &idev_id); if (IS_ERR(idev)) { rc = PTR_ERR(idev); goto out_mdev; } sobj->idev.idev = idev; rc = iommufd_device_attach(idev, &pt_id); if (rc) goto out_unbind; /* Userspace must destroy the device_id to destroy the object */ cmd->mock_domain.out_hwpt_id = pt_id; cmd->mock_domain.out_stdev_id = sobj->obj.id; cmd->mock_domain.out_idev_id = idev_id; rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); if (rc) goto out_detach; iommufd_object_finalize(ucmd->ictx, &sobj->obj); return 0; out_detach: iommufd_device_detach(idev); out_unbind: iommufd_device_unbind(idev); out_mdev: mock_dev_destroy(sobj->idev.mock_dev); out_sobj: iommufd_object_abort(ucmd->ictx, &sobj->obj); return rc; } /* Replace the mock domain with a manually allocated hw_pagetable */ static int iommufd_test_mock_domain_replace(struct iommufd_ucmd *ucmd, unsigned int device_id, u32 pt_id, struct iommu_test_cmd *cmd) { struct iommufd_object *dev_obj; struct selftest_obj *sobj; int rc; /* * Prefer to use the OBJ_SELFTEST because the destroy_rwsem will ensure * it doesn't race with detach, which is not allowed. */ dev_obj = iommufd_get_object(ucmd->ictx, device_id, IOMMUFD_OBJ_SELFTEST); if (IS_ERR(dev_obj)) return PTR_ERR(dev_obj); sobj = to_selftest_obj(dev_obj); if (sobj->type != TYPE_IDEV) { rc = -EINVAL; goto out_dev_obj; } rc = iommufd_device_replace(sobj->idev.idev, &pt_id); if (rc) goto out_dev_obj; cmd->mock_domain_replace.pt_id = pt_id; rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); out_dev_obj: iommufd_put_object(ucmd->ictx, dev_obj); return rc; } /* Add an additional reserved IOVA to the IOAS */ static int iommufd_test_add_reserved(struct iommufd_ucmd *ucmd, unsigned int mockpt_id, unsigned long start, size_t length) { struct iommufd_ioas *ioas; int rc; ioas = iommufd_get_ioas(ucmd->ictx, mockpt_id); if (IS_ERR(ioas)) return PTR_ERR(ioas); down_write(&ioas->iopt.iova_rwsem); rc = iopt_reserve_iova(&ioas->iopt, start, start + length - 1, NULL); up_write(&ioas->iopt.iova_rwsem); iommufd_put_object(ucmd->ictx, &ioas->obj); return rc; } /* Check that every pfn under each iova matches the pfn under a user VA */ static int iommufd_test_md_check_pa(struct iommufd_ucmd *ucmd, unsigned int mockpt_id, unsigned long iova, size_t length, void __user *uptr) { struct iommufd_hw_pagetable *hwpt; struct mock_iommu_domain *mock; uintptr_t end; int rc; if (iova % MOCK_IO_PAGE_SIZE || length % MOCK_IO_PAGE_SIZE || (uintptr_t)uptr % MOCK_IO_PAGE_SIZE || check_add_overflow((uintptr_t)uptr, (uintptr_t)length, &end)) return -EINVAL; hwpt = get_md_pagetable(ucmd, mockpt_id, &mock); if (IS_ERR(hwpt)) return PTR_ERR(hwpt); for (; length; length -= MOCK_IO_PAGE_SIZE) { struct page *pages[1]; unsigned long pfn; long npages; void *ent; npages = get_user_pages_fast((uintptr_t)uptr & PAGE_MASK, 1, 0, pages); if (npages < 0) { rc = npages; goto out_put; } if (WARN_ON(npages != 1)) { rc = -EFAULT; goto out_put; } pfn = page_to_pfn(pages[0]); put_page(pages[0]); ent = xa_load(&mock->pfns, iova / MOCK_IO_PAGE_SIZE); if (!ent || (xa_to_value(ent) & MOCK_PFN_MASK) * MOCK_IO_PAGE_SIZE != pfn * PAGE_SIZE + ((uintptr_t)uptr % PAGE_SIZE)) { rc = -EINVAL; goto out_put; } iova += MOCK_IO_PAGE_SIZE; uptr += MOCK_IO_PAGE_SIZE; } rc = 0; out_put: iommufd_put_object(ucmd->ictx, &hwpt->obj); return rc; } /* Check that the page ref count matches, to look for missing pin/unpins */ static int iommufd_test_md_check_refs(struct iommufd_ucmd *ucmd, void __user *uptr, size_t length, unsigned int refs) { uintptr_t end; if (length % PAGE_SIZE || (uintptr_t)uptr % PAGE_SIZE || check_add_overflow((uintptr_t)uptr, (uintptr_t)length, &end)) return -EINVAL; for (; length; length -= PAGE_SIZE) { struct page *pages[1]; long npages; npages = get_user_pages_fast((uintptr_t)uptr, 1, 0, pages); if (npages < 0) return npages; if (WARN_ON(npages != 1)) return -EFAULT; if (!PageCompound(pages[0])) { unsigned int count; count = page_ref_count(pages[0]); if (count / GUP_PIN_COUNTING_BIAS != refs) { put_page(pages[0]); return -EIO; } } put_page(pages[0]); uptr += PAGE_SIZE; } return 0; } static int iommufd_test_md_check_iotlb(struct iommufd_ucmd *ucmd, u32 mockpt_id, unsigned int iotlb_id, u32 iotlb) { struct mock_iommu_domain_nested *mock_nested; struct iommufd_hw_pagetable *hwpt; int rc = 0; hwpt = get_md_pagetable_nested(ucmd, mockpt_id, &mock_nested); if (IS_ERR(hwpt)) return PTR_ERR(hwpt); mock_nested = to_mock_nested(hwpt->domain); if (iotlb_id > MOCK_NESTED_DOMAIN_IOTLB_ID_MAX || mock_nested->iotlb[iotlb_id] != iotlb) rc = -EINVAL; iommufd_put_object(ucmd->ictx, &hwpt->obj); return rc; } static int iommufd_test_dev_check_cache(struct iommufd_ucmd *ucmd, u32 idev_id, unsigned int cache_id, u32 cache) { struct iommufd_device *idev; struct mock_dev *mdev; int rc = 0; idev = iommufd_get_device(ucmd, idev_id); if (IS_ERR(idev)) return PTR_ERR(idev); mdev = container_of(idev->dev, struct mock_dev, dev); if (cache_id > MOCK_DEV_CACHE_ID_MAX || mdev->cache[cache_id] != cache) rc = -EINVAL; iommufd_put_object(ucmd->ictx, &idev->obj); return rc; } struct selftest_access { struct iommufd_access *access; struct file *file; struct mutex lock; struct list_head items; unsigned int next_id; bool destroying; }; struct selftest_access_item { struct list_head items_elm; unsigned long iova; size_t length; unsigned int id; }; static const struct file_operations iommfd_test_staccess_fops; static struct selftest_access *iommufd_access_get(int fd) { struct file *file; file = fget(fd); if (!file) return ERR_PTR(-EBADFD); if (file->f_op != &iommfd_test_staccess_fops) { fput(file); return ERR_PTR(-EBADFD); } return file->private_data; } static void iommufd_test_access_unmap(void *data, unsigned long iova, unsigned long length) { unsigned long iova_last = iova + length - 1; struct selftest_access *staccess = data; struct selftest_access_item *item; struct selftest_access_item *tmp; mutex_lock(&staccess->lock); list_for_each_entry_safe(item, tmp, &staccess->items, items_elm) { if (iova > item->iova + item->length - 1 || iova_last < item->iova) continue; list_del(&item->items_elm); iommufd_access_unpin_pages(staccess->access, item->iova, item->length); kfree(item); } mutex_unlock(&staccess->lock); } static int iommufd_test_access_item_destroy(struct iommufd_ucmd *ucmd, unsigned int access_id, unsigned int item_id) { struct selftest_access_item *item; struct selftest_access *staccess; staccess = iommufd_access_get(access_id); if (IS_ERR(staccess)) return PTR_ERR(staccess); mutex_lock(&staccess->lock); list_for_each_entry(item, &staccess->items, items_elm) { if (item->id == item_id) { list_del(&item->items_elm); iommufd_access_unpin_pages(staccess->access, item->iova, item->length); mutex_unlock(&staccess->lock); kfree(item); fput(staccess->file); return 0; } } mutex_unlock(&staccess->lock); fput(staccess->file); return -ENOENT; } static int iommufd_test_staccess_release(struct inode *inode, struct file *filep) { struct selftest_access *staccess = filep->private_data; if (staccess->access) { iommufd_test_access_unmap(staccess, 0, ULONG_MAX); iommufd_access_destroy(staccess->access); } mutex_destroy(&staccess->lock); kfree(staccess); return 0; } static const struct iommufd_access_ops selftest_access_ops_pin = { .needs_pin_pages = 1, .unmap = iommufd_test_access_unmap, }; static const struct iommufd_access_ops selftest_access_ops = { .unmap = iommufd_test_access_unmap, }; static const struct file_operations iommfd_test_staccess_fops = { .release = iommufd_test_staccess_release, }; static struct selftest_access *iommufd_test_alloc_access(void) { struct selftest_access *staccess; struct file *filep; staccess = kzalloc(sizeof(*staccess), GFP_KERNEL_ACCOUNT); if (!staccess) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&staccess->items); mutex_init(&staccess->lock); filep = anon_inode_getfile("[iommufd_test_staccess]", &iommfd_test_staccess_fops, staccess, O_RDWR); if (IS_ERR(filep)) { kfree(staccess); return ERR_CAST(filep); } staccess->file = filep; return staccess; } static int iommufd_test_create_access(struct iommufd_ucmd *ucmd, unsigned int ioas_id, unsigned int flags) { struct iommu_test_cmd *cmd = ucmd->cmd; struct selftest_access *staccess; struct iommufd_access *access; u32 id; int fdno; int rc; if (flags & ~MOCK_FLAGS_ACCESS_CREATE_NEEDS_PIN_PAGES) return -EOPNOTSUPP; staccess = iommufd_test_alloc_access(); if (IS_ERR(staccess)) return PTR_ERR(staccess); fdno = get_unused_fd_flags(O_CLOEXEC); if (fdno < 0) { rc = -ENOMEM; goto out_free_staccess; } access = iommufd_access_create( ucmd->ictx, (flags & MOCK_FLAGS_ACCESS_CREATE_NEEDS_PIN_PAGES) ? &selftest_access_ops_pin : &selftest_access_ops, staccess, &id); if (IS_ERR(access)) { rc = PTR_ERR(access); goto out_put_fdno; } rc = iommufd_access_attach(access, ioas_id); if (rc) goto out_destroy; cmd->create_access.out_access_fd = fdno; rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); if (rc) goto out_destroy; staccess->access = access; fd_install(fdno, staccess->file); return 0; out_destroy: iommufd_access_destroy(access); out_put_fdno: put_unused_fd(fdno); out_free_staccess: fput(staccess->file); return rc; } static int iommufd_test_access_replace_ioas(struct iommufd_ucmd *ucmd, unsigned int access_id, unsigned int ioas_id) { struct selftest_access *staccess; int rc; staccess = iommufd_access_get(access_id); if (IS_ERR(staccess)) return PTR_ERR(staccess); rc = iommufd_access_replace(staccess->access, ioas_id); fput(staccess->file); return rc; } /* Check that the pages in a page array match the pages in the user VA */ static int iommufd_test_check_pages(void __user *uptr, struct page **pages, size_t npages) { for (; npages; npages--) { struct page *tmp_pages[1]; long rc; rc = get_user_pages_fast((uintptr_t)uptr, 1, 0, tmp_pages); if (rc < 0) return rc; if (WARN_ON(rc != 1)) return -EFAULT; put_page(tmp_pages[0]); if (tmp_pages[0] != *pages) return -EBADE; pages++; uptr += PAGE_SIZE; } return 0; } static int iommufd_test_access_pages(struct iommufd_ucmd *ucmd, unsigned int access_id, unsigned long iova, size_t length, void __user *uptr, u32 flags) { struct iommu_test_cmd *cmd = ucmd->cmd; struct selftest_access_item *item; struct selftest_access *staccess; struct page **pages; size_t npages; int rc; /* Prevent syzkaller from triggering a WARN_ON in kvzalloc() */ if (length > 16*1024*1024) return -ENOMEM; if (flags & ~(MOCK_FLAGS_ACCESS_WRITE | MOCK_FLAGS_ACCESS_SYZ)) return -EOPNOTSUPP; staccess = iommufd_access_get(access_id); if (IS_ERR(staccess)) return PTR_ERR(staccess); if (staccess->access->ops != &selftest_access_ops_pin) { rc = -EOPNOTSUPP; goto out_put; } if (flags & MOCK_FLAGS_ACCESS_SYZ) iova = iommufd_test_syz_conv_iova(staccess->access, &cmd->access_pages.iova); npages = (ALIGN(iova + length, PAGE_SIZE) - ALIGN_DOWN(iova, PAGE_SIZE)) / PAGE_SIZE; pages = kvcalloc(npages, sizeof(*pages), GFP_KERNEL_ACCOUNT); if (!pages) { rc = -ENOMEM; goto out_put; } /* * Drivers will need to think very carefully about this locking. The * core code can do multiple unmaps instantaneously after * iommufd_access_pin_pages() and *all* the unmaps must not return until * the range is unpinned. This simple implementation puts a global lock * around the pin, which may not suit drivers that want this to be a * performance path. drivers that get this wrong will trigger WARN_ON * races and cause EDEADLOCK failures to userspace. */ mutex_lock(&staccess->lock); rc = iommufd_access_pin_pages(staccess->access, iova, length, pages, flags & MOCK_FLAGS_ACCESS_WRITE); if (rc) goto out_unlock; /* For syzkaller allow uptr to be NULL to skip this check */ if (uptr) { rc = iommufd_test_check_pages( uptr - (iova - ALIGN_DOWN(iova, PAGE_SIZE)), pages, npages); if (rc) goto out_unaccess; } item = kzalloc(sizeof(*item), GFP_KERNEL_ACCOUNT); if (!item) { rc = -ENOMEM; goto out_unaccess; } item->iova = iova; item->length = length; item->id = staccess->next_id++; list_add_tail(&item->items_elm, &staccess->items); cmd->access_pages.out_access_pages_id = item->id; rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); if (rc) goto out_free_item; goto out_unlock; out_free_item: list_del(&item->items_elm); kfree(item); out_unaccess: iommufd_access_unpin_pages(staccess->access, iova, length); out_unlock: mutex_unlock(&staccess->lock); kvfree(pages); out_put: fput(staccess->file); return rc; } static int iommufd_test_access_rw(struct iommufd_ucmd *ucmd, unsigned int access_id, unsigned long iova, size_t length, void __user *ubuf, unsigned int flags) { struct iommu_test_cmd *cmd = ucmd->cmd; struct selftest_access *staccess; void *tmp; int rc; /* Prevent syzkaller from triggering a WARN_ON in kvzalloc() */ if (length > 16*1024*1024) return -ENOMEM; if (flags & ~(MOCK_ACCESS_RW_WRITE | MOCK_ACCESS_RW_SLOW_PATH | MOCK_FLAGS_ACCESS_SYZ)) return -EOPNOTSUPP; staccess = iommufd_access_get(access_id); if (IS_ERR(staccess)) return PTR_ERR(staccess); tmp = kvzalloc(length, GFP_KERNEL_ACCOUNT); if (!tmp) { rc = -ENOMEM; goto out_put; } if (flags & MOCK_ACCESS_RW_WRITE) { if (copy_from_user(tmp, ubuf, length)) { rc = -EFAULT; goto out_free; } } if (flags & MOCK_FLAGS_ACCESS_SYZ) iova = iommufd_test_syz_conv_iova(staccess->access, &cmd->access_rw.iova); rc = iommufd_access_rw(staccess->access, iova, tmp, length, flags); if (rc) goto out_free; if (!(flags & MOCK_ACCESS_RW_WRITE)) { if (copy_to_user(ubuf, tmp, length)) { rc = -EFAULT; goto out_free; } } out_free: kvfree(tmp); out_put: fput(staccess->file); return rc; } static_assert((unsigned int)MOCK_ACCESS_RW_WRITE == IOMMUFD_ACCESS_RW_WRITE); static_assert((unsigned int)MOCK_ACCESS_RW_SLOW_PATH == __IOMMUFD_ACCESS_RW_SLOW_PATH); static int iommufd_test_dirty(struct iommufd_ucmd *ucmd, unsigned int mockpt_id, unsigned long iova, size_t length, unsigned long page_size, void __user *uptr, u32 flags) { unsigned long i, max; struct iommu_test_cmd *cmd = ucmd->cmd; struct iommufd_hw_pagetable *hwpt; struct mock_iommu_domain *mock; int rc, count = 0; void *tmp; if (!page_size || !length || iova % page_size || length % page_size || !uptr) return -EINVAL; hwpt = get_md_pagetable(ucmd, mockpt_id, &mock); if (IS_ERR(hwpt)) return PTR_ERR(hwpt); if (!(mock->flags & MOCK_DIRTY_TRACK)) { rc = -EINVAL; goto out_put; } max = length / page_size; tmp = kvzalloc(DIV_ROUND_UP(max, BITS_PER_LONG) * sizeof(unsigned long), GFP_KERNEL_ACCOUNT); if (!tmp) { rc = -ENOMEM; goto out_put; } if (copy_from_user(tmp, uptr,DIV_ROUND_UP(max, BITS_PER_BYTE))) { rc = -EFAULT; goto out_free; } for (i = 0; i < max; i++) { unsigned long cur = iova + i * page_size; void *ent, *old; if (!test_bit(i, (unsigned long *)tmp)) continue; ent = xa_load(&mock->pfns, cur / page_size); if (ent) { unsigned long val; val = xa_to_value(ent) | MOCK_PFN_DIRTY_IOVA; old = xa_store(&mock->pfns, cur / page_size, xa_mk_value(val), GFP_KERNEL); WARN_ON_ONCE(ent != old); count++; } } cmd->dirty.out_nr_dirty = count; rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); out_free: kvfree(tmp); out_put: iommufd_put_object(ucmd->ictx, &hwpt->obj); return rc; } static int iommufd_test_trigger_iopf(struct iommufd_ucmd *ucmd, struct iommu_test_cmd *cmd) { struct iopf_fault event = { }; struct iommufd_device *idev; idev = iommufd_get_device(ucmd, cmd->trigger_iopf.dev_id); if (IS_ERR(idev)) return PTR_ERR(idev); event.fault.prm.flags = IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE; if (cmd->trigger_iopf.pasid != IOMMU_NO_PASID) event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PASID_VALID; event.fault.type = IOMMU_FAULT_PAGE_REQ; event.fault.prm.addr = cmd->trigger_iopf.addr; event.fault.prm.pasid = cmd->trigger_iopf.pasid; event.fault.prm.grpid = cmd->trigger_iopf.grpid; event.fault.prm.perm = cmd->trigger_iopf.perm; iommu_report_device_fault(idev->dev, &event); iommufd_put_object(ucmd->ictx, &idev->obj); return 0; } void iommufd_selftest_destroy(struct iommufd_object *obj) { struct selftest_obj *sobj = to_selftest_obj(obj); switch (sobj->type) { case TYPE_IDEV: iommufd_device_detach(sobj->idev.idev); iommufd_device_unbind(sobj->idev.idev); mock_dev_destroy(sobj->idev.mock_dev); break; } } int iommufd_test(struct iommufd_ucmd *ucmd) { struct iommu_test_cmd *cmd = ucmd->cmd; switch (cmd->op) { case IOMMU_TEST_OP_ADD_RESERVED: return iommufd_test_add_reserved(ucmd, cmd->id, cmd->add_reserved.start, cmd->add_reserved.length); case IOMMU_TEST_OP_MOCK_DOMAIN: case IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS: return iommufd_test_mock_domain(ucmd, cmd); case IOMMU_TEST_OP_MOCK_DOMAIN_REPLACE: return iommufd_test_mock_domain_replace( ucmd, cmd->id, cmd->mock_domain_replace.pt_id, cmd); case IOMMU_TEST_OP_MD_CHECK_MAP: return iommufd_test_md_check_pa( ucmd, cmd->id, cmd->check_map.iova, cmd->check_map.length, u64_to_user_ptr(cmd->check_map.uptr)); case IOMMU_TEST_OP_MD_CHECK_REFS: return iommufd_test_md_check_refs( ucmd, u64_to_user_ptr(cmd->check_refs.uptr), cmd->check_refs.length, cmd->check_refs.refs); case IOMMU_TEST_OP_MD_CHECK_IOTLB: return iommufd_test_md_check_iotlb(ucmd, cmd->id, cmd->check_iotlb.id, cmd->check_iotlb.iotlb); case IOMMU_TEST_OP_DEV_CHECK_CACHE: return iommufd_test_dev_check_cache(ucmd, cmd->id, cmd->check_dev_cache.id, cmd->check_dev_cache.cache); case IOMMU_TEST_OP_CREATE_ACCESS: return iommufd_test_create_access(ucmd, cmd->id, cmd->create_access.flags); case IOMMU_TEST_OP_ACCESS_REPLACE_IOAS: return iommufd_test_access_replace_ioas( ucmd, cmd->id, cmd->access_replace_ioas.ioas_id); case IOMMU_TEST_OP_ACCESS_PAGES: return iommufd_test_access_pages( ucmd, cmd->id, cmd->access_pages.iova, cmd->access_pages.length, u64_to_user_ptr(cmd->access_pages.uptr), cmd->access_pages.flags); case IOMMU_TEST_OP_ACCESS_RW: return iommufd_test_access_rw( ucmd, cmd->id, cmd->access_rw.iova, cmd->access_rw.length, u64_to_user_ptr(cmd->access_rw.uptr), cmd->access_rw.flags); case IOMMU_TEST_OP_DESTROY_ACCESS_PAGES: return iommufd_test_access_item_destroy( ucmd, cmd->id, cmd->destroy_access_pages.access_pages_id); case IOMMU_TEST_OP_SET_TEMP_MEMORY_LIMIT: /* Protect _batch_init(), can not be less than elmsz */ if (cmd->memory_limit.limit < sizeof(unsigned long) + sizeof(u32)) return -EINVAL; iommufd_test_memory_limit = cmd->memory_limit.limit; return 0; case IOMMU_TEST_OP_DIRTY: return iommufd_test_dirty(ucmd, cmd->id, cmd->dirty.iova, cmd->dirty.length, cmd->dirty.page_size, u64_to_user_ptr(cmd->dirty.uptr), cmd->dirty.flags); case IOMMU_TEST_OP_TRIGGER_IOPF: return iommufd_test_trigger_iopf(ucmd, cmd); default: return -EOPNOTSUPP; } } bool iommufd_should_fail(void) { return should_fail(&fail_iommufd, 1); } int __init iommufd_test_init(void) { struct platform_device_info pdevinfo = { .name = "iommufd_selftest_iommu", }; int rc; dbgfs_root = fault_create_debugfs_attr("fail_iommufd", NULL, &fail_iommufd); selftest_iommu_dev = platform_device_register_full(&pdevinfo); if (IS_ERR(selftest_iommu_dev)) { rc = PTR_ERR(selftest_iommu_dev); goto err_dbgfs; } rc = bus_register(&iommufd_mock_bus_type.bus); if (rc) goto err_platform; rc = iommu_device_sysfs_add(&mock_iommu.iommu_dev, &selftest_iommu_dev->dev, NULL, "%s", dev_name(&selftest_iommu_dev->dev)); if (rc) goto err_bus; rc = iommu_device_register_bus(&mock_iommu.iommu_dev, &mock_ops, &iommufd_mock_bus_type.bus, &iommufd_mock_bus_type.nb); if (rc) goto err_sysfs; refcount_set(&mock_iommu.users, 1); init_completion(&mock_iommu.complete); mock_iommu_iopf_queue = iopf_queue_alloc("mock-iopfq"); return 0; err_sysfs: iommu_device_sysfs_remove(&mock_iommu.iommu_dev); err_bus: bus_unregister(&iommufd_mock_bus_type.bus); err_platform: platform_device_unregister(selftest_iommu_dev); err_dbgfs: debugfs_remove_recursive(dbgfs_root); return rc; } static void iommufd_test_wait_for_users(void) { if (refcount_dec_and_test(&mock_iommu.users)) return; /* * Time out waiting for iommu device user count to become 0. * * Note that this is just making an example here, since the selftest is * built into the iommufd module, i.e. it only unplugs the iommu device * when unloading the module. So, it is expected that this WARN_ON will * not trigger, as long as any iommufd FDs are open. */ WARN_ON(!wait_for_completion_timeout(&mock_iommu.complete, msecs_to_jiffies(10000))); } void iommufd_test_exit(void) { if (mock_iommu_iopf_queue) { iopf_queue_free(mock_iommu_iopf_queue); mock_iommu_iopf_queue = NULL; } iommufd_test_wait_for_users(); iommu_device_sysfs_remove(&mock_iommu.iommu_dev); iommu_device_unregister_bus(&mock_iommu.iommu_dev, &iommufd_mock_bus_type.bus, &iommufd_mock_bus_type.nb); bus_unregister(&iommufd_mock_bus_type.bus); platform_device_unregister(selftest_iommu_dev); debugfs_remove_recursive(dbgfs_root); } |
| 12 1 11 9 1 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2011 Florian Westphal <fw@strlen.de> * * based on fib_frontend.c; Author: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <net/inet_dscp.h> #include <linux/ip.h> #include <net/ip.h> #include <net/ip_fib.h> #include <net/route.h> #include <linux/netfilter/xt_rpfilter.h> #include <linux/netfilter/x_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); MODULE_DESCRIPTION("iptables: ipv4 reverse path filter match"); /* don't try to find route from mcast/bcast/zeronet */ static __be32 rpfilter_get_saddr(__be32 addr) { if (ipv4_is_multicast(addr) || ipv4_is_lbcast(addr) || ipv4_is_zeronet(addr)) return 0; return addr; } static bool rpfilter_lookup_reverse(struct net *net, struct flowi4 *fl4, const struct net_device *dev, u8 flags) { struct fib_result res; if (fib_lookup(net, fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE)) return false; if (res.type != RTN_UNICAST) { if (res.type != RTN_LOCAL || !(flags & XT_RPFILTER_ACCEPT_LOCAL)) return false; } return fib_info_nh_uses_dev(res.fi, dev) || flags & XT_RPFILTER_LOOSE; } static bool rpfilter_is_loopback(const struct sk_buff *skb, const struct net_device *in) { return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK; } static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_rpfilter_info *info; const struct iphdr *iph; struct flowi4 flow; bool invert; info = par->matchinfo; invert = info->flags & XT_RPFILTER_INVERT; if (rpfilter_is_loopback(skb, xt_in(par))) return true ^ invert; iph = ip_hdr(skb); if (ipv4_is_zeronet(iph->saddr)) { if (ipv4_is_lbcast(iph->daddr) || ipv4_is_local_multicast(iph->daddr)) return true ^ invert; } memset(&flow, 0, sizeof(flow)); flow.flowi4_iif = LOOPBACK_IFINDEX; flow.daddr = iph->saddr; flow.saddr = rpfilter_get_saddr(iph->daddr); flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; flow.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(iph)); flow.flowi4_scope = RT_SCOPE_UNIVERSE; flow.flowi4_l3mdev = l3mdev_master_ifindex_rcu(xt_in(par)); flow.flowi4_uid = sock_net_uid(xt_net(par), NULL); return rpfilter_lookup_reverse(xt_net(par), &flow, xt_in(par), info->flags) ^ invert; } static int rpfilter_check(const struct xt_mtchk_param *par) { const struct xt_rpfilter_info *info = par->matchinfo; unsigned int options = ~XT_RPFILTER_OPTION_MASK; if (info->flags & options) { pr_info_ratelimited("unknown options\n"); return -EINVAL; } if (strcmp(par->table, "mangle") != 0 && strcmp(par->table, "raw") != 0) { pr_info_ratelimited("only valid in \'raw\' or \'mangle\' table, not \'%s\'\n", par->table); return -EINVAL; } return 0; } static struct xt_match rpfilter_mt_reg __read_mostly = { .name = "rpfilter", .family = NFPROTO_IPV4, .checkentry = rpfilter_check, .match = rpfilter_mt, .matchsize = sizeof(struct xt_rpfilter_info), .hooks = (1 << NF_INET_PRE_ROUTING), .me = THIS_MODULE }; static int __init rpfilter_mt_init(void) { return xt_register_match(&rpfilter_mt_reg); } static void __exit rpfilter_mt_exit(void) { xt_unregister_match(&rpfilter_mt_reg); } module_init(rpfilter_mt_init); module_exit(rpfilter_mt_exit); |
| 1873 1505 1866 1861 577 1622 1041 1036 988 971 846 580 191 20 9 344 163 202 203 203 203 203 203 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * IPv6 library code, needed by static components when full IPv6 support is * not configured or static. */ #include <linux/export.h> #include <net/ipv6.h> #include <net/ipv6_stubs.h> #include <net/addrconf.h> #include <net/ip.h> /* if ipv6 module registers this function is used by xfrm to force all * sockets to relookup their nodes - this is fairly expensive, be * careful */ void (*__fib6_flush_trees)(struct net *); EXPORT_SYMBOL(__fib6_flush_trees); #define IPV6_ADDR_SCOPE_TYPE(scope) ((scope) << 16) static inline unsigned int ipv6_addr_scope2type(unsigned int scope) { switch (scope) { case IPV6_ADDR_SCOPE_NODELOCAL: return (IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_NODELOCAL) | IPV6_ADDR_LOOPBACK); case IPV6_ADDR_SCOPE_LINKLOCAL: return (IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_LINKLOCAL) | IPV6_ADDR_LINKLOCAL); case IPV6_ADDR_SCOPE_SITELOCAL: return (IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_SITELOCAL) | IPV6_ADDR_SITELOCAL); } return IPV6_ADDR_SCOPE_TYPE(scope); } int __ipv6_addr_type(const struct in6_addr *addr) { __be32 st; st = addr->s6_addr32[0]; /* Consider all addresses with the first three bits different of 000 and 111 as unicasts. */ if ((st & htonl(0xE0000000)) != htonl(0x00000000) && (st & htonl(0xE0000000)) != htonl(0xE0000000)) return (IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); if ((st & htonl(0xFF000000)) == htonl(0xFF000000)) { /* multicast */ /* addr-select 3.1 */ return (IPV6_ADDR_MULTICAST | ipv6_addr_scope2type(IPV6_ADDR_MC_SCOPE(addr))); } if ((st & htonl(0xFFC00000)) == htonl(0xFE800000)) return (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_LINKLOCAL)); /* addr-select 3.1 */ if ((st & htonl(0xFFC00000)) == htonl(0xFEC00000)) return (IPV6_ADDR_SITELOCAL | IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_SITELOCAL)); /* addr-select 3.1 */ if ((st & htonl(0xFE000000)) == htonl(0xFC000000)) return (IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* RFC 4193 */ if ((addr->s6_addr32[0] | addr->s6_addr32[1]) == 0) { if (addr->s6_addr32[2] == 0) { if (addr->s6_addr32[3] == 0) return IPV6_ADDR_ANY; if (addr->s6_addr32[3] == htonl(0x00000001)) return (IPV6_ADDR_LOOPBACK | IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_LINKLOCAL)); /* addr-select 3.4 */ return (IPV6_ADDR_COMPATv4 | IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.3 */ } if (addr->s6_addr32[2] == htonl(0x0000ffff)) return (IPV6_ADDR_MAPPED | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.3 */ } return (IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.4 */ } EXPORT_SYMBOL(__ipv6_addr_type); static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); static BLOCKING_NOTIFIER_HEAD(inet6addr_validator_chain); int register_inet6addr_notifier(struct notifier_block *nb) { return atomic_notifier_chain_register(&inet6addr_chain, nb); } EXPORT_SYMBOL(register_inet6addr_notifier); int unregister_inet6addr_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(&inet6addr_chain, nb); } EXPORT_SYMBOL(unregister_inet6addr_notifier); int inet6addr_notifier_call_chain(unsigned long val, void *v) { return atomic_notifier_call_chain(&inet6addr_chain, val, v); } EXPORT_SYMBOL(inet6addr_notifier_call_chain); int register_inet6addr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&inet6addr_validator_chain, nb); } EXPORT_SYMBOL(register_inet6addr_validator_notifier); int unregister_inet6addr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&inet6addr_validator_chain, nb); } EXPORT_SYMBOL(unregister_inet6addr_validator_notifier); int inet6addr_validator_notifier_call_chain(unsigned long val, void *v) { return blocking_notifier_call_chain(&inet6addr_validator_chain, val, v); } EXPORT_SYMBOL(inet6addr_validator_notifier_call_chain); static struct dst_entry *eafnosupport_ipv6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst) { return ERR_PTR(-EAFNOSUPPORT); } static int eafnosupport_ipv6_route_input(struct sk_buff *skb) { return -EAFNOSUPPORT; } static struct fib6_table *eafnosupport_fib6_get_table(struct net *net, u32 id) { return NULL; } static int eafnosupport_fib6_table_lookup(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags) { return -EAFNOSUPPORT; } static int eafnosupport_fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags) { return -EAFNOSUPPORT; } static void eafnosupport_fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict) { } static u32 eafnosupport_ip6_mtu_from_fib6(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { return 0; } static int eafnosupport_fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel"); return -EAFNOSUPPORT; } static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt, bool skip_notify) { return -EAFNOSUPPORT; } static int eafnosupport_ipv6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { kfree_skb(skb); return -EAFNOSUPPORT; } static struct net_device *eafnosupport_ipv6_dev_find(struct net *net, const struct in6_addr *addr, struct net_device *dev) { return ERR_PTR(-EAFNOSUPPORT); } const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { .ipv6_dst_lookup_flow = eafnosupport_ipv6_dst_lookup_flow, .ipv6_route_input = eafnosupport_ipv6_route_input, .fib6_get_table = eafnosupport_fib6_get_table, .fib6_table_lookup = eafnosupport_fib6_table_lookup, .fib6_lookup = eafnosupport_fib6_lookup, .fib6_select_path = eafnosupport_fib6_select_path, .ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6, .fib6_nh_init = eafnosupport_fib6_nh_init, .ip6_del_rt = eafnosupport_ip6_del_rt, .ipv6_fragment = eafnosupport_ipv6_fragment, .ipv6_dev_find = eafnosupport_ipv6_dev_find, }; EXPORT_SYMBOL_GPL(ipv6_stub); /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ const struct in6_addr in6addr_loopback __aligned(BITS_PER_LONG/8) = IN6ADDR_LOOPBACK_INIT; EXPORT_SYMBOL(in6addr_loopback); const struct in6_addr in6addr_any __aligned(BITS_PER_LONG/8) = IN6ADDR_ANY_INIT; EXPORT_SYMBOL(in6addr_any); const struct in6_addr in6addr_linklocal_allnodes __aligned(BITS_PER_LONG/8) = IN6ADDR_LINKLOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_linklocal_allnodes); const struct in6_addr in6addr_linklocal_allrouters __aligned(BITS_PER_LONG/8) = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_linklocal_allrouters); const struct in6_addr in6addr_interfacelocal_allnodes __aligned(BITS_PER_LONG/8) = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allnodes); const struct in6_addr in6addr_interfacelocal_allrouters __aligned(BITS_PER_LONG/8) = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allrouters); const struct in6_addr in6addr_sitelocal_allrouters __aligned(BITS_PER_LONG/8) = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_sitelocal_allrouters); static void snmp6_free_dev(struct inet6_dev *idev) { kfree(idev->stats.icmpv6msgdev); kfree(idev->stats.icmpv6dev); free_percpu(idev->stats.ipv6); } static void in6_dev_finish_destroy_rcu(struct rcu_head *head) { struct inet6_dev *idev = container_of(head, struct inet6_dev, rcu); snmp6_free_dev(idev); kfree(idev); } /* Nobody refers to this device, we may destroy it. */ void in6_dev_finish_destroy(struct inet6_dev *idev) { struct net_device *dev = idev->dev; WARN_ON(!list_empty(&idev->addr_list)); WARN_ON(rcu_access_pointer(idev->mc_list)); WARN_ON(timer_pending(&idev->rs_timer)); #ifdef NET_REFCNT_DEBUG pr_debug("%s: %s\n", __func__, dev ? dev->name : "NIL"); #endif netdev_put(dev, &idev->dev_tracker); if (!idev->dead) { pr_warn("Freeing alive inet6 device %p\n", idev); return; } call_rcu(&idev->rcu, in6_dev_finish_destroy_rcu); } EXPORT_SYMBOL(in6_dev_finish_destroy); |
| 1 13 16 16 13 14 9 6 6 5 5 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * V9FS FID Management * * Copyright (C) 2005 by Eric Van Hensbergen <ericvh@gmail.com> */ #ifndef FS_9P_FID_H #define FS_9P_FID_H #include <linux/list.h> #include "v9fs.h" struct p9_fid *v9fs_fid_find_inode(struct inode *inode, bool want_writeable, kuid_t uid, bool any); struct p9_fid *v9fs_fid_lookup(struct dentry *dentry); static inline struct p9_fid *v9fs_parent_fid(struct dentry *dentry) { return v9fs_fid_lookup(dentry->d_parent); } void v9fs_fid_add(struct dentry *dentry, struct p9_fid **fid); void v9fs_open_fid_add(struct inode *inode, struct p9_fid **fid); static inline struct p9_fid *clone_fid(struct p9_fid *fid) { return IS_ERR(fid) ? fid : p9_client_walk(fid, 0, NULL, 1); } static inline struct p9_fid *v9fs_fid_clone(struct dentry *dentry) { struct p9_fid *fid, *nfid; fid = v9fs_fid_lookup(dentry); if (!fid || IS_ERR(fid)) return fid; nfid = clone_fid(fid); p9_fid_put(fid); return nfid; } /** * v9fs_fid_addmodes - add cache flags to fid mode (for client use only) * @fid: fid to augment * @s_flags: session info mount flags * @s_cache: session info cache flags * @f_flags: unix open flags * * make sure mode reflects flags of underlying mounts * also qid.version == 0 reflects a synthetic or legacy file system * NOTE: these are set after open so only reflect 9p client not * underlying file system on server. */ static inline void v9fs_fid_add_modes(struct p9_fid *fid, unsigned int s_flags, unsigned int s_cache, unsigned int f_flags) { if ((!s_cache) || ((fid->qid.version == 0) && !(s_flags & V9FS_IGNORE_QV)) || (s_flags & V9FS_DIRECT_IO) || (f_flags & O_DIRECT)) { fid->mode |= P9L_DIRECT; /* no read or write cache */ } else if ((!(s_cache & CACHE_WRITEBACK)) || (f_flags & O_DSYNC) || (s_flags & V9FS_SYNC)) { fid->mode |= P9L_NOWRITECACHE; } } #endif |
| 40 40 57 27 39 39 39 39 37 993 28 174 2 58 2 58 1 58 57 26 26 26 4 389 387 4 391 26 25 24 26 14 12 12 14 58 59 59 58 59 887 895 889 887 12 11 11 11 12 58 58 58 1 57 57 57 57 27 28 25 3 27 27 40 40 40 40 39 32 8 32 40 31 40 40 5 35 5 35 5 35 5 35 5 35 5 35 5 34 5 35 40 40 40 39 40 39 40 40 8 40 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 31 32 32 32 32 32 32 40 40 40 40 3 3 3 3 39 34 35 35 35 35 35 35 35 35 35 31 40 32 32 32 32 32 32 32 31 32 32 32 32 31 32 32 32 32 32 32 32 32 39 2 2 40 38 38 38 40 40 40 40 40 40 40 40 40 40 40 14 40 39 40 40 39 40 40 2 39 40 40 40 40 39 40 40 40 40 40 39 39 39 39 18 39 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Video capture interface for Linux version 2 * * A generic video device interface for the LINUX operating system * using a set of device structures/vectors for low level operations. * * Authors: Alan Cox, <alan@lxorguk.ukuu.org.uk> (version 1) * Mauro Carvalho Chehab <mchehab@kernel.org> (version 2) * * Fixes: 20000516 Claudio Matsuoka <claudio@conectiva.com> * - Added procfs support */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/debugfs.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <media/v4l2-common.h> #include <media/v4l2-device.h> #include <media/v4l2-ioctl.h> #include <media/v4l2-event.h> #define VIDEO_NUM_DEVICES 256 #define VIDEO_NAME "video4linux" #define dprintk(fmt, arg...) do { \ printk(KERN_DEBUG pr_fmt("%s: " fmt), \ __func__, ##arg); \ } while (0) /* * sysfs stuff */ static ssize_t index_show(struct device *cd, struct device_attribute *attr, char *buf) { struct video_device *vdev = to_video_device(cd); return sprintf(buf, "%i\n", vdev->index); } static DEVICE_ATTR_RO(index); static ssize_t dev_debug_show(struct device *cd, struct device_attribute *attr, char *buf) { struct video_device *vdev = to_video_device(cd); return sprintf(buf, "%i\n", vdev->dev_debug); } static ssize_t dev_debug_store(struct device *cd, struct device_attribute *attr, const char *buf, size_t len) { struct video_device *vdev = to_video_device(cd); int res = 0; u16 value; res = kstrtou16(buf, 0, &value); if (res) return res; vdev->dev_debug = value; return len; } static DEVICE_ATTR_RW(dev_debug); static ssize_t name_show(struct device *cd, struct device_attribute *attr, char *buf) { struct video_device *vdev = to_video_device(cd); return sprintf(buf, "%.*s\n", (int)sizeof(vdev->name), vdev->name); } static DEVICE_ATTR_RO(name); static struct attribute *video_device_attrs[] = { &dev_attr_name.attr, &dev_attr_dev_debug.attr, &dev_attr_index.attr, NULL, }; ATTRIBUTE_GROUPS(video_device); static struct dentry *v4l2_debugfs_root_dir; /* * Active devices */ static struct video_device *video_devices[VIDEO_NUM_DEVICES]; static DEFINE_MUTEX(videodev_lock); static DECLARE_BITMAP(devnode_nums[VFL_TYPE_MAX], VIDEO_NUM_DEVICES); /* Device node utility functions */ /* Note: these utility functions all assume that vfl_type is in the range [0, VFL_TYPE_MAX-1]. */ #ifdef CONFIG_VIDEO_FIXED_MINOR_RANGES /* Return the bitmap corresponding to vfl_type. */ static inline unsigned long *devnode_bits(enum vfl_devnode_type vfl_type) { /* Any types not assigned to fixed minor ranges must be mapped to one single bitmap for the purposes of finding a free node number since all those unassigned types use the same minor range. */ int idx = (vfl_type > VFL_TYPE_RADIO) ? VFL_TYPE_MAX - 1 : vfl_type; return devnode_nums[idx]; } #else /* Return the bitmap corresponding to vfl_type. */ static inline unsigned long *devnode_bits(enum vfl_devnode_type vfl_type) { return devnode_nums[vfl_type]; } #endif /* Mark device node number vdev->num as used */ static inline void devnode_set(struct video_device *vdev) { set_bit(vdev->num, devnode_bits(vdev->vfl_type)); } /* Mark device node number vdev->num as unused */ static inline void devnode_clear(struct video_device *vdev) { clear_bit(vdev->num, devnode_bits(vdev->vfl_type)); } /* Try to find a free device node number in the range [from, to> */ static inline int devnode_find(struct video_device *vdev, int from, int to) { return find_next_zero_bit(devnode_bits(vdev->vfl_type), to, from); } struct video_device *video_device_alloc(void) { return kzalloc(sizeof(struct video_device), GFP_KERNEL); } EXPORT_SYMBOL(video_device_alloc); void video_device_release(struct video_device *vdev) { kfree(vdev); } EXPORT_SYMBOL(video_device_release); void video_device_release_empty(struct video_device *vdev) { /* Do nothing */ /* Only valid when the video_device struct is a static. */ } EXPORT_SYMBOL(video_device_release_empty); static inline void video_get(struct video_device *vdev) { get_device(&vdev->dev); } static inline void video_put(struct video_device *vdev) { put_device(&vdev->dev); } /* Called when the last user of the video device exits. */ static void v4l2_device_release(struct device *cd) { struct video_device *vdev = to_video_device(cd); struct v4l2_device *v4l2_dev = vdev->v4l2_dev; mutex_lock(&videodev_lock); if (WARN_ON(video_devices[vdev->minor] != vdev)) { /* should not happen */ mutex_unlock(&videodev_lock); return; } /* Free up this device for reuse */ video_devices[vdev->minor] = NULL; /* Delete the cdev on this minor as well */ cdev_del(vdev->cdev); /* Just in case some driver tries to access this from the release() callback. */ vdev->cdev = NULL; /* Mark device node number as free */ devnode_clear(vdev); mutex_unlock(&videodev_lock); #if defined(CONFIG_MEDIA_CONTROLLER) if (v4l2_dev->mdev && vdev->vfl_dir != VFL_DIR_M2M) { /* Remove interfaces and interface links */ media_devnode_remove(vdev->intf_devnode); if (vdev->entity.function != MEDIA_ENT_F_UNKNOWN) media_device_unregister_entity(&vdev->entity); } #endif /* Do not call v4l2_device_put if there is no release callback set. * Drivers that have no v4l2_device release callback might free the * v4l2_dev instance in the video_device release callback below, so we * must perform this check here. * * TODO: In the long run all drivers that use v4l2_device should use the * v4l2_device release callback. This check will then be unnecessary. */ if (v4l2_dev->release == NULL) v4l2_dev = NULL; /* Release video_device and perform other cleanups as needed. */ vdev->release(vdev); /* Decrease v4l2_device refcount */ if (v4l2_dev) v4l2_device_put(v4l2_dev); } static const struct class video_class = { .name = VIDEO_NAME, .dev_groups = video_device_groups, }; struct video_device *video_devdata(struct file *file) { return video_devices[iminor(file_inode(file))]; } EXPORT_SYMBOL(video_devdata); /* Priority handling */ static inline bool prio_is_valid(enum v4l2_priority prio) { return prio == V4L2_PRIORITY_BACKGROUND || prio == V4L2_PRIORITY_INTERACTIVE || prio == V4L2_PRIORITY_RECORD; } void v4l2_prio_init(struct v4l2_prio_state *global) { memset(global, 0, sizeof(*global)); } EXPORT_SYMBOL(v4l2_prio_init); int v4l2_prio_change(struct v4l2_prio_state *global, enum v4l2_priority *local, enum v4l2_priority new) { if (!prio_is_valid(new)) return -EINVAL; if (*local == new) return 0; atomic_inc(&global->prios[new]); if (prio_is_valid(*local)) atomic_dec(&global->prios[*local]); *local = new; return 0; } EXPORT_SYMBOL(v4l2_prio_change); void v4l2_prio_open(struct v4l2_prio_state *global, enum v4l2_priority *local) { v4l2_prio_change(global, local, V4L2_PRIORITY_DEFAULT); } EXPORT_SYMBOL(v4l2_prio_open); void v4l2_prio_close(struct v4l2_prio_state *global, enum v4l2_priority local) { if (prio_is_valid(local)) atomic_dec(&global->prios[local]); } EXPORT_SYMBOL(v4l2_prio_close); enum v4l2_priority v4l2_prio_max(struct v4l2_prio_state *global) { if (atomic_read(&global->prios[V4L2_PRIORITY_RECORD]) > 0) return V4L2_PRIORITY_RECORD; if (atomic_read(&global->prios[V4L2_PRIORITY_INTERACTIVE]) > 0) return V4L2_PRIORITY_INTERACTIVE; if (atomic_read(&global->prios[V4L2_PRIORITY_BACKGROUND]) > 0) return V4L2_PRIORITY_BACKGROUND; return V4L2_PRIORITY_UNSET; } EXPORT_SYMBOL(v4l2_prio_max); int v4l2_prio_check(struct v4l2_prio_state *global, enum v4l2_priority local) { return (local < v4l2_prio_max(global)) ? -EBUSY : 0; } EXPORT_SYMBOL(v4l2_prio_check); static ssize_t v4l2_read(struct file *filp, char __user *buf, size_t sz, loff_t *off) { struct video_device *vdev = video_devdata(filp); int ret = -ENODEV; if (!vdev->fops->read) return -EINVAL; if (video_is_registered(vdev)) ret = vdev->fops->read(filp, buf, sz, off); if ((vdev->dev_debug & V4L2_DEV_DEBUG_FOP) && (vdev->dev_debug & V4L2_DEV_DEBUG_STREAMING)) dprintk("%s: read: %zd (%d)\n", video_device_node_name(vdev), sz, ret); return ret; } static ssize_t v4l2_write(struct file *filp, const char __user *buf, size_t sz, loff_t *off) { struct video_device *vdev = video_devdata(filp); int ret = -ENODEV; if (!vdev->fops->write) return -EINVAL; if (video_is_registered(vdev)) ret = vdev->fops->write(filp, buf, sz, off); if ((vdev->dev_debug & V4L2_DEV_DEBUG_FOP) && (vdev->dev_debug & V4L2_DEV_DEBUG_STREAMING)) dprintk("%s: write: %zd (%d)\n", video_device_node_name(vdev), sz, ret); return ret; } static __poll_t v4l2_poll(struct file *filp, struct poll_table_struct *poll) { struct video_device *vdev = video_devdata(filp); __poll_t res = EPOLLERR | EPOLLHUP | EPOLLPRI; if (video_is_registered(vdev)) { if (!vdev->fops->poll) res = DEFAULT_POLLMASK; else res = vdev->fops->poll(filp, poll); } if (vdev->dev_debug & V4L2_DEV_DEBUG_POLL) dprintk("%s: poll: %08x %08x\n", video_device_node_name(vdev), res, poll_requested_events(poll)); return res; } static long v4l2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct video_device *vdev = video_devdata(filp); int ret = -ENODEV; if (vdev->fops->unlocked_ioctl) { if (video_is_registered(vdev)) ret = vdev->fops->unlocked_ioctl(filp, cmd, arg); } else ret = -ENOTTY; return ret; } #ifdef CONFIG_MMU #define v4l2_get_unmapped_area NULL #else static unsigned long v4l2_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct video_device *vdev = video_devdata(filp); int ret; if (!vdev->fops->get_unmapped_area) return -ENOSYS; if (!video_is_registered(vdev)) return -ENODEV; ret = vdev->fops->get_unmapped_area(filp, addr, len, pgoff, flags); if (vdev->dev_debug & V4L2_DEV_DEBUG_FOP) dprintk("%s: get_unmapped_area (%d)\n", video_device_node_name(vdev), ret); return ret; } #endif static int v4l2_mmap(struct file *filp, struct vm_area_struct *vm) { struct video_device *vdev = video_devdata(filp); int ret = -ENODEV; if (!vdev->fops->mmap) return -ENODEV; if (video_is_registered(vdev)) ret = vdev->fops->mmap(filp, vm); if (vdev->dev_debug & V4L2_DEV_DEBUG_FOP) dprintk("%s: mmap (%d)\n", video_device_node_name(vdev), ret); return ret; } /* Override for the open function */ static int v4l2_open(struct inode *inode, struct file *filp) { struct video_device *vdev; int ret = 0; /* Check if the video device is available */ mutex_lock(&videodev_lock); vdev = video_devdata(filp); /* return ENODEV if the video device has already been removed. */ if (vdev == NULL || !video_is_registered(vdev)) { mutex_unlock(&videodev_lock); return -ENODEV; } /* and increase the device refcount */ video_get(vdev); mutex_unlock(&videodev_lock); if (vdev->fops->open) { if (video_is_registered(vdev)) ret = vdev->fops->open(filp); else ret = -ENODEV; } if (vdev->dev_debug & V4L2_DEV_DEBUG_FOP) dprintk("%s: open (%d)\n", video_device_node_name(vdev), ret); /* decrease the refcount in case of an error */ if (ret) video_put(vdev); return ret; } /* Override for the release function */ static int v4l2_release(struct inode *inode, struct file *filp) { struct video_device *vdev = video_devdata(filp); int ret = 0; /* * We need to serialize the release() with queueing new requests. * The release() may trigger the cancellation of a streaming * operation, and that should not be mixed with queueing a new * request at the same time. */ if (vdev->fops->release) { if (v4l2_device_supports_requests(vdev->v4l2_dev)) { mutex_lock(&vdev->v4l2_dev->mdev->req_queue_mutex); ret = vdev->fops->release(filp); mutex_unlock(&vdev->v4l2_dev->mdev->req_queue_mutex); } else { ret = vdev->fops->release(filp); } } if (vdev->dev_debug & V4L2_DEV_DEBUG_FOP) dprintk("%s: release\n", video_device_node_name(vdev)); /* decrease the refcount unconditionally since the release() return value is ignored. */ video_put(vdev); return ret; } static const struct file_operations v4l2_fops = { .owner = THIS_MODULE, .read = v4l2_read, .write = v4l2_write, .open = v4l2_open, .get_unmapped_area = v4l2_get_unmapped_area, .mmap = v4l2_mmap, .unlocked_ioctl = v4l2_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = v4l2_compat_ioctl32, #endif .release = v4l2_release, .poll = v4l2_poll, }; /** * get_index - assign stream index number based on v4l2_dev * @vdev: video_device to assign index number to, vdev->v4l2_dev should be assigned * * Note that when this is called the new device has not yet been registered * in the video_device array, but it was able to obtain a minor number. * * This means that we can always obtain a free stream index number since * the worst case scenario is that there are VIDEO_NUM_DEVICES - 1 slots in * use of the video_device array. * * Returns a free index number. */ static int get_index(struct video_device *vdev) { /* This can be static since this function is called with the global videodev_lock held. */ static DECLARE_BITMAP(used, VIDEO_NUM_DEVICES); int i; bitmap_zero(used, VIDEO_NUM_DEVICES); for (i = 0; i < VIDEO_NUM_DEVICES; i++) { if (video_devices[i] != NULL && video_devices[i]->v4l2_dev == vdev->v4l2_dev) { __set_bit(video_devices[i]->index, used); } } return find_first_zero_bit(used, VIDEO_NUM_DEVICES); } #define SET_VALID_IOCTL(ops, cmd, op) \ do { if ((ops)->op) __set_bit(_IOC_NR(cmd), valid_ioctls); } while (0) /* This determines which ioctls are actually implemented in the driver. It's a one-time thing which simplifies video_ioctl2 as it can just do a bit test. Note that drivers can override this by setting bits to 1 in vdev->valid_ioctls. If an ioctl is marked as 1 when this function is called, then that ioctl will actually be marked as unimplemented. It does that by first setting up the local valid_ioctls bitmap, and at the end do a: vdev->valid_ioctls = valid_ioctls & ~(vdev->valid_ioctls) */ static void determine_valid_ioctls(struct video_device *vdev) { const u32 vid_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_VIDEO_CAPTURE_MPLANE | V4L2_CAP_VIDEO_OUTPUT | V4L2_CAP_VIDEO_OUTPUT_MPLANE | V4L2_CAP_VIDEO_M2M | V4L2_CAP_VIDEO_M2M_MPLANE; const u32 meta_caps = V4L2_CAP_META_CAPTURE | V4L2_CAP_META_OUTPUT; DECLARE_BITMAP(valid_ioctls, BASE_VIDIOC_PRIVATE); const struct v4l2_ioctl_ops *ops = vdev->ioctl_ops; bool is_vid = vdev->vfl_type == VFL_TYPE_VIDEO && (vdev->device_caps & vid_caps); bool is_vbi = vdev->vfl_type == VFL_TYPE_VBI; bool is_radio = vdev->vfl_type == VFL_TYPE_RADIO; bool is_sdr = vdev->vfl_type == VFL_TYPE_SDR; bool is_tch = vdev->vfl_type == VFL_TYPE_TOUCH; bool is_meta = vdev->vfl_type == VFL_TYPE_VIDEO && (vdev->device_caps & meta_caps); bool is_rx = vdev->vfl_dir != VFL_DIR_TX; bool is_tx = vdev->vfl_dir != VFL_DIR_RX; bool is_io_mc = vdev->device_caps & V4L2_CAP_IO_MC; bool has_streaming = vdev->device_caps & V4L2_CAP_STREAMING; bool is_edid = vdev->device_caps & V4L2_CAP_EDID; bitmap_zero(valid_ioctls, BASE_VIDIOC_PRIVATE); /* vfl_type and vfl_dir independent ioctls */ SET_VALID_IOCTL(ops, VIDIOC_QUERYCAP, vidioc_querycap); __set_bit(_IOC_NR(VIDIOC_G_PRIORITY), valid_ioctls); __set_bit(_IOC_NR(VIDIOC_S_PRIORITY), valid_ioctls); /* Note: the control handler can also be passed through the filehandle, and that can't be tested here. If the bit for these control ioctls is set, then the ioctl is valid. But if it is 0, then it can still be valid if the filehandle passed the control handler. */ if (vdev->ctrl_handler || ops->vidioc_queryctrl) __set_bit(_IOC_NR(VIDIOC_QUERYCTRL), valid_ioctls); if (vdev->ctrl_handler || ops->vidioc_query_ext_ctrl) __set_bit(_IOC_NR(VIDIOC_QUERY_EXT_CTRL), valid_ioctls); if (vdev->ctrl_handler || ops->vidioc_g_ctrl || ops->vidioc_g_ext_ctrls) __set_bit(_IOC_NR(VIDIOC_G_CTRL), valid_ioctls); if (vdev->ctrl_handler || ops->vidioc_s_ctrl || ops->vidioc_s_ext_ctrls) __set_bit(_IOC_NR(VIDIOC_S_CTRL), valid_ioctls); if (vdev->ctrl_handler || ops->vidioc_g_ext_ctrls) __set_bit(_IOC_NR(VIDIOC_G_EXT_CTRLS), valid_ioctls); if (vdev->ctrl_handler || ops->vidioc_s_ext_ctrls) __set_bit(_IOC_NR(VIDIOC_S_EXT_CTRLS), valid_ioctls); if (vdev->ctrl_handler || ops->vidioc_try_ext_ctrls) __set_bit(_IOC_NR(VIDIOC_TRY_EXT_CTRLS), valid_ioctls); if (vdev->ctrl_handler || ops->vidioc_querymenu) __set_bit(_IOC_NR(VIDIOC_QUERYMENU), valid_ioctls); if (!is_tch) { SET_VALID_IOCTL(ops, VIDIOC_G_FREQUENCY, vidioc_g_frequency); SET_VALID_IOCTL(ops, VIDIOC_S_FREQUENCY, vidioc_s_frequency); } SET_VALID_IOCTL(ops, VIDIOC_LOG_STATUS, vidioc_log_status); #ifdef CONFIG_VIDEO_ADV_DEBUG __set_bit(_IOC_NR(VIDIOC_DBG_G_CHIP_INFO), valid_ioctls); __set_bit(_IOC_NR(VIDIOC_DBG_G_REGISTER), valid_ioctls); __set_bit(_IOC_NR(VIDIOC_DBG_S_REGISTER), valid_ioctls); #endif /* yes, really vidioc_subscribe_event */ SET_VALID_IOCTL(ops, VIDIOC_DQEVENT, vidioc_subscribe_event); SET_VALID_IOCTL(ops, VIDIOC_SUBSCRIBE_EVENT, vidioc_subscribe_event); SET_VALID_IOCTL(ops, VIDIOC_UNSUBSCRIBE_EVENT, vidioc_unsubscribe_event); if (ops->vidioc_enum_freq_bands || ops->vidioc_g_tuner || ops->vidioc_g_modulator) __set_bit(_IOC_NR(VIDIOC_ENUM_FREQ_BANDS), valid_ioctls); if (is_vid) { /* video specific ioctls */ if ((is_rx && (ops->vidioc_enum_fmt_vid_cap || ops->vidioc_enum_fmt_vid_overlay)) || (is_tx && ops->vidioc_enum_fmt_vid_out)) __set_bit(_IOC_NR(VIDIOC_ENUM_FMT), valid_ioctls); if ((is_rx && (ops->vidioc_g_fmt_vid_cap || ops->vidioc_g_fmt_vid_cap_mplane || ops->vidioc_g_fmt_vid_overlay)) || (is_tx && (ops->vidioc_g_fmt_vid_out || ops->vidioc_g_fmt_vid_out_mplane || ops->vidioc_g_fmt_vid_out_overlay))) __set_bit(_IOC_NR(VIDIOC_G_FMT), valid_ioctls); if ((is_rx && (ops->vidioc_s_fmt_vid_cap || ops->vidioc_s_fmt_vid_cap_mplane || ops->vidioc_s_fmt_vid_overlay)) || (is_tx && (ops->vidioc_s_fmt_vid_out || ops->vidioc_s_fmt_vid_out_mplane || ops->vidioc_s_fmt_vid_out_overlay))) __set_bit(_IOC_NR(VIDIOC_S_FMT), valid_ioctls); if ((is_rx && (ops->vidioc_try_fmt_vid_cap || ops->vidioc_try_fmt_vid_cap_mplane || ops->vidioc_try_fmt_vid_overlay)) || (is_tx && (ops->vidioc_try_fmt_vid_out || ops->vidioc_try_fmt_vid_out_mplane || ops->vidioc_try_fmt_vid_out_overlay))) __set_bit(_IOC_NR(VIDIOC_TRY_FMT), valid_ioctls); SET_VALID_IOCTL(ops, VIDIOC_OVERLAY, vidioc_overlay); SET_VALID_IOCTL(ops, VIDIOC_G_FBUF, vidioc_g_fbuf); SET_VALID_IOCTL(ops, VIDIOC_S_FBUF, vidioc_s_fbuf); SET_VALID_IOCTL(ops, VIDIOC_G_JPEGCOMP, vidioc_g_jpegcomp); SET_VALID_IOCTL(ops, VIDIOC_S_JPEGCOMP, vidioc_s_jpegcomp); SET_VALID_IOCTL(ops, VIDIOC_G_ENC_INDEX, vidioc_g_enc_index); SET_VALID_IOCTL(ops, VIDIOC_ENCODER_CMD, vidioc_encoder_cmd); SET_VALID_IOCTL(ops, VIDIOC_TRY_ENCODER_CMD, vidioc_try_encoder_cmd); SET_VALID_IOCTL(ops, VIDIOC_DECODER_CMD, vidioc_decoder_cmd); SET_VALID_IOCTL(ops, VIDIOC_TRY_DECODER_CMD, vidioc_try_decoder_cmd); SET_VALID_IOCTL(ops, VIDIOC_ENUM_FRAMESIZES, vidioc_enum_framesizes); SET_VALID_IOCTL(ops, VIDIOC_ENUM_FRAMEINTERVALS, vidioc_enum_frameintervals); if (ops->vidioc_g_selection && !test_bit(_IOC_NR(VIDIOC_G_SELECTION), vdev->valid_ioctls)) { __set_bit(_IOC_NR(VIDIOC_G_CROP), valid_ioctls); __set_bit(_IOC_NR(VIDIOC_CROPCAP), valid_ioctls); } if (ops->vidioc_s_selection && !test_bit(_IOC_NR(VIDIOC_S_SELECTION), vdev->valid_ioctls)) __set_bit(_IOC_NR(VIDIOC_S_CROP), valid_ioctls); SET_VALID_IOCTL(ops, VIDIOC_G_SELECTION, vidioc_g_selection); SET_VALID_IOCTL(ops, VIDIOC_S_SELECTION, vidioc_s_selection); } if (is_meta && is_rx) { /* metadata capture specific ioctls */ SET_VALID_IOCTL(ops, VIDIOC_ENUM_FMT, vidioc_enum_fmt_meta_cap); SET_VALID_IOCTL(ops, VIDIOC_G_FMT, vidioc_g_fmt_meta_cap); SET_VALID_IOCTL(ops, VIDIOC_S_FMT, vidioc_s_fmt_meta_cap); SET_VALID_IOCTL(ops, VIDIOC_TRY_FMT, vidioc_try_fmt_meta_cap); } else if (is_meta && is_tx) { /* metadata output specific ioctls */ SET_VALID_IOCTL(ops, VIDIOC_ENUM_FMT, vidioc_enum_fmt_meta_out); SET_VALID_IOCTL(ops, VIDIOC_G_FMT, vidioc_g_fmt_meta_out); SET_VALID_IOCTL(ops, VIDIOC_S_FMT, vidioc_s_fmt_meta_out); SET_VALID_IOCTL(ops, VIDIOC_TRY_FMT, vidioc_try_fmt_meta_out); } if (is_vbi) { /* vbi specific ioctls */ if ((is_rx && (ops->vidioc_g_fmt_vbi_cap || ops->vidioc_g_fmt_sliced_vbi_cap)) || (is_tx && (ops->vidioc_g_fmt_vbi_out || ops->vidioc_g_fmt_sliced_vbi_out))) __set_bit(_IOC_NR(VIDIOC_G_FMT), valid_ioctls); if ((is_rx && (ops->vidioc_s_fmt_vbi_cap || ops->vidioc_s_fmt_sliced_vbi_cap)) || (is_tx && (ops->vidioc_s_fmt_vbi_out || ops->vidioc_s_fmt_sliced_vbi_out))) __set_bit(_IOC_NR(VIDIOC_S_FMT), valid_ioctls); if ((is_rx && (ops->vidioc_try_fmt_vbi_cap || ops->vidioc_try_fmt_sliced_vbi_cap)) || (is_tx && (ops->vidioc_try_fmt_vbi_out || ops->vidioc_try_fmt_sliced_vbi_out))) __set_bit(_IOC_NR(VIDIOC_TRY_FMT), valid_ioctls); SET_VALID_IOCTL(ops, VIDIOC_G_SLICED_VBI_CAP, vidioc_g_sliced_vbi_cap); } else if (is_tch) { /* touch specific ioctls */ SET_VALID_IOCTL(ops, VIDIOC_ENUM_FMT, vidioc_enum_fmt_vid_cap); SET_VALID_IOCTL(ops, VIDIOC_G_FMT, vidioc_g_fmt_vid_cap); SET_VALID_IOCTL(ops, VIDIOC_S_FMT, vidioc_s_fmt_vid_cap); SET_VALID_IOCTL(ops, VIDIOC_TRY_FMT, vidioc_try_fmt_vid_cap); SET_VALID_IOCTL(ops, VIDIOC_ENUM_FRAMESIZES, vidioc_enum_framesizes); SET_VALID_IOCTL(ops, VIDIOC_ENUM_FRAMEINTERVALS, vidioc_enum_frameintervals); SET_VALID_IOCTL(ops, VIDIOC_ENUMINPUT, vidioc_enum_input); SET_VALID_IOCTL(ops, VIDIOC_G_INPUT, vidioc_g_input); SET_VALID_IOCTL(ops, VIDIOC_S_INPUT, vidioc_s_input); SET_VALID_IOCTL(ops, VIDIOC_G_PARM, vidioc_g_parm); SET_VALID_IOCTL(ops, VIDIOC_S_PARM, vidioc_s_parm); } else if (is_sdr && is_rx) { /* SDR receiver specific ioctls */ SET_VALID_IOCTL(ops, VIDIOC_ENUM_FMT, vidioc_enum_fmt_sdr_cap); SET_VALID_IOCTL(ops, VIDIOC_G_FMT, vidioc_g_fmt_sdr_cap); SET_VALID_IOCTL(ops, VIDIOC_S_FMT, vidioc_s_fmt_sdr_cap); SET_VALID_IOCTL(ops, VIDIOC_TRY_FMT, vidioc_try_fmt_sdr_cap); } else if (is_sdr && is_tx) { /* SDR transmitter specific ioctls */ SET_VALID_IOCTL(ops, VIDIOC_ENUM_FMT, vidioc_enum_fmt_sdr_out); SET_VALID_IOCTL(ops, VIDIOC_G_FMT, vidioc_g_fmt_sdr_out); SET_VALID_IOCTL(ops, VIDIOC_S_FMT, vidioc_s_fmt_sdr_out); SET_VALID_IOCTL(ops, VIDIOC_TRY_FMT, vidioc_try_fmt_sdr_out); } if (has_streaming) { /* ioctls valid for streaming I/O */ SET_VALID_IOCTL(ops, VIDIOC_REQBUFS, vidioc_reqbufs); SET_VALID_IOCTL(ops, VIDIOC_QUERYBUF, vidioc_querybuf); SET_VALID_IOCTL(ops, VIDIOC_QBUF, vidioc_qbuf); SET_VALID_IOCTL(ops, VIDIOC_EXPBUF, vidioc_expbuf); SET_VALID_IOCTL(ops, VIDIOC_DQBUF, vidioc_dqbuf); SET_VALID_IOCTL(ops, VIDIOC_CREATE_BUFS, vidioc_create_bufs); SET_VALID_IOCTL(ops, VIDIOC_PREPARE_BUF, vidioc_prepare_buf); SET_VALID_IOCTL(ops, VIDIOC_STREAMON, vidioc_streamon); SET_VALID_IOCTL(ops, VIDIOC_STREAMOFF, vidioc_streamoff); /* VIDIOC_CREATE_BUFS support is mandatory to enable VIDIOC_REMOVE_BUFS */ if (ops->vidioc_create_bufs) SET_VALID_IOCTL(ops, VIDIOC_REMOVE_BUFS, vidioc_remove_bufs); } if (is_vid || is_vbi || is_meta) { /* ioctls valid for video, vbi and metadata */ if (ops->vidioc_s_std) __set_bit(_IOC_NR(VIDIOC_ENUMSTD), valid_ioctls); SET_VALID_IOCTL(ops, VIDIOC_S_STD, vidioc_s_std); SET_VALID_IOCTL(ops, VIDIOC_G_STD, vidioc_g_std); if (is_rx) { SET_VALID_IOCTL(ops, VIDIOC_QUERYSTD, vidioc_querystd); if (is_io_mc) { __set_bit(_IOC_NR(VIDIOC_ENUMINPUT), valid_ioctls); __set_bit(_IOC_NR(VIDIOC_G_INPUT), valid_ioctls); __set_bit(_IOC_NR(VIDIOC_S_INPUT), valid_ioctls); } else { SET_VALID_IOCTL(ops, VIDIOC_ENUMINPUT, vidioc_enum_input); SET_VALID_IOCTL(ops, VIDIOC_G_INPUT, vidioc_g_input); SET_VALID_IOCTL(ops, VIDIOC_S_INPUT, vidioc_s_input); } SET_VALID_IOCTL(ops, VIDIOC_ENUMAUDIO, vidioc_enumaudio); SET_VALID_IOCTL(ops, VIDIOC_G_AUDIO, vidioc_g_audio); SET_VALID_IOCTL(ops, VIDIOC_S_AUDIO, vidioc_s_audio); SET_VALID_IOCTL(ops, VIDIOC_QUERY_DV_TIMINGS, vidioc_query_dv_timings); SET_VALID_IOCTL(ops, VIDIOC_S_EDID, vidioc_s_edid); } if (is_tx) { if (is_io_mc) { __set_bit(_IOC_NR(VIDIOC_ENUMOUTPUT), valid_ioctls); __set_bit(_IOC_NR(VIDIOC_G_OUTPUT), valid_ioctls); __set_bit(_IOC_NR(VIDIOC_S_OUTPUT), valid_ioctls); } else { SET_VALID_IOCTL(ops, VIDIOC_ENUMOUTPUT, vidioc_enum_output); SET_VALID_IOCTL(ops, VIDIOC_G_OUTPUT, vidioc_g_output); SET_VALID_IOCTL(ops, VIDIOC_S_OUTPUT, vidioc_s_output); } SET_VALID_IOCTL(ops, VIDIOC_ENUMAUDOUT, vidioc_enumaudout); SET_VALID_IOCTL(ops, VIDIOC_G_AUDOUT, vidioc_g_audout); SET_VALID_IOCTL(ops, VIDIOC_S_AUDOUT, vidioc_s_audout); } if (ops->vidioc_g_parm || ops->vidioc_g_std) __set_bit(_IOC_NR(VIDIOC_G_PARM), valid_ioctls); SET_VALID_IOCTL(ops, VIDIOC_S_PARM, vidioc_s_parm); SET_VALID_IOCTL(ops, VIDIOC_S_DV_TIMINGS, vidioc_s_dv_timings); SET_VALID_IOCTL(ops, VIDIOC_G_DV_TIMINGS, vidioc_g_dv_timings); SET_VALID_IOCTL(ops, VIDIOC_ENUM_DV_TIMINGS, vidioc_enum_dv_timings); SET_VALID_IOCTL(ops, VIDIOC_DV_TIMINGS_CAP, vidioc_dv_timings_cap); SET_VALID_IOCTL(ops, VIDIOC_G_EDID, vidioc_g_edid); } if (is_tx && (is_radio || is_sdr)) { /* radio transmitter only ioctls */ SET_VALID_IOCTL(ops, VIDIOC_G_MODULATOR, vidioc_g_modulator); SET_VALID_IOCTL(ops, VIDIOC_S_MODULATOR, vidioc_s_modulator); } if (is_rx && !is_tch) { /* receiver only ioctls */ SET_VALID_IOCTL(ops, VIDIOC_G_TUNER, vidioc_g_tuner); SET_VALID_IOCTL(ops, VIDIOC_S_TUNER, vidioc_s_tuner); SET_VALID_IOCTL(ops, VIDIOC_S_HW_FREQ_SEEK, vidioc_s_hw_freq_seek); } if (is_edid) { SET_VALID_IOCTL(ops, VIDIOC_G_EDID, vidioc_g_edid); if (is_tx) { SET_VALID_IOCTL(ops, VIDIOC_G_OUTPUT, vidioc_g_output); SET_VALID_IOCTL(ops, VIDIOC_S_OUTPUT, vidioc_s_output); SET_VALID_IOCTL(ops, VIDIOC_ENUMOUTPUT, vidioc_enum_output); } if (is_rx) { SET_VALID_IOCTL(ops, VIDIOC_ENUMINPUT, vidioc_enum_input); SET_VALID_IOCTL(ops, VIDIOC_G_INPUT, vidioc_g_input); SET_VALID_IOCTL(ops, VIDIOC_S_INPUT, vidioc_s_input); SET_VALID_IOCTL(ops, VIDIOC_S_EDID, vidioc_s_edid); } } bitmap_andnot(vdev->valid_ioctls, valid_ioctls, vdev->valid_ioctls, BASE_VIDIOC_PRIVATE); } static int video_register_media_controller(struct video_device *vdev) { #if defined(CONFIG_MEDIA_CONTROLLER) u32 intf_type; int ret; /* Memory-to-memory devices are more complex and use * their own function to register its mc entities. */ if (!vdev->v4l2_dev->mdev || vdev->vfl_dir == VFL_DIR_M2M) return 0; vdev->entity.obj_type = MEDIA_ENTITY_TYPE_VIDEO_DEVICE; vdev->entity.function = MEDIA_ENT_F_UNKNOWN; switch (vdev->vfl_type) { case VFL_TYPE_VIDEO: intf_type = MEDIA_INTF_T_V4L_VIDEO; vdev->entity.function = MEDIA_ENT_F_IO_V4L; break; case VFL_TYPE_VBI: intf_type = MEDIA_INTF_T_V4L_VBI; vdev->entity.function = MEDIA_ENT_F_IO_VBI; break; case VFL_TYPE_SDR: intf_type = MEDIA_INTF_T_V4L_SWRADIO; vdev->entity.function = MEDIA_ENT_F_IO_SWRADIO; break; case VFL_TYPE_TOUCH: intf_type = MEDIA_INTF_T_V4L_TOUCH; vdev->entity.function = MEDIA_ENT_F_IO_V4L; break; case VFL_TYPE_RADIO: intf_type = MEDIA_INTF_T_V4L_RADIO; /* * Radio doesn't have an entity at the V4L2 side to represent * radio input or output. Instead, the audio input/output goes * via either physical wires or ALSA. */ break; case VFL_TYPE_SUBDEV: intf_type = MEDIA_INTF_T_V4L_SUBDEV; /* Entity will be created via v4l2_device_register_subdev() */ break; default: return 0; } if (vdev->entity.function != MEDIA_ENT_F_UNKNOWN) { vdev->entity.name = vdev->name; /* Needed just for backward compatibility with legacy MC API */ vdev->entity.info.dev.major = VIDEO_MAJOR; vdev->entity.info.dev.minor = vdev->minor; ret = media_device_register_entity(vdev->v4l2_dev->mdev, &vdev->entity); if (ret < 0) { pr_warn("%s: media_device_register_entity failed\n", __func__); return ret; } } vdev->intf_devnode = media_devnode_create(vdev->v4l2_dev->mdev, intf_type, 0, VIDEO_MAJOR, vdev->minor); if (!vdev->intf_devnode) { media_device_unregister_entity(&vdev->entity); return -ENOMEM; } if (vdev->entity.function != MEDIA_ENT_F_UNKNOWN) { struct media_link *link; link = media_create_intf_link(&vdev->entity, &vdev->intf_devnode->intf, MEDIA_LNK_FL_ENABLED | MEDIA_LNK_FL_IMMUTABLE); if (!link) { media_devnode_remove(vdev->intf_devnode); media_device_unregister_entity(&vdev->entity); return -ENOMEM; } } /* FIXME: how to create the other interface links? */ #endif return 0; } int __video_register_device(struct video_device *vdev, enum vfl_devnode_type type, int nr, int warn_if_nr_in_use, struct module *owner) { int i = 0; int ret; int minor_offset = 0; int minor_cnt = VIDEO_NUM_DEVICES; const char *name_base; /* A minor value of -1 marks this video device as never having been registered */ vdev->minor = -1; /* the release callback MUST be present */ if (WARN_ON(!vdev->release)) return -EINVAL; /* the v4l2_dev pointer MUST be present */ if (WARN_ON(!vdev->v4l2_dev)) return -EINVAL; /* the device_caps field MUST be set for all but subdevs */ if (WARN_ON(type != VFL_TYPE_SUBDEV && !vdev->device_caps)) return -EINVAL; /* v4l2_fh support */ spin_lock_init(&vdev->fh_lock); INIT_LIST_HEAD(&vdev->fh_list); /* Part 1: check device type */ switch (type) { case VFL_TYPE_VIDEO: name_base = "video"; break; case VFL_TYPE_VBI: name_base = "vbi"; break; case VFL_TYPE_RADIO: name_base = "radio"; break; case VFL_TYPE_SUBDEV: name_base = "v4l-subdev"; break; case VFL_TYPE_SDR: /* Use device name 'swradio' because 'sdr' was already taken. */ name_base = "swradio"; break; case VFL_TYPE_TOUCH: name_base = "v4l-touch"; break; default: pr_err("%s called with unknown type: %d\n", __func__, type); return -EINVAL; } vdev->vfl_type = type; vdev->cdev = NULL; if (vdev->dev_parent == NULL) vdev->dev_parent = vdev->v4l2_dev->dev; if (vdev->ctrl_handler == NULL) vdev->ctrl_handler = vdev->v4l2_dev->ctrl_handler; /* If the prio state pointer is NULL, then use the v4l2_device prio state. */ if (vdev->prio == NULL) vdev->prio = &vdev->v4l2_dev->prio; /* Part 2: find a free minor, device node number and device index. */ #ifdef CONFIG_VIDEO_FIXED_MINOR_RANGES /* Keep the ranges for the first four types for historical * reasons. * Newer devices (not yet in place) should use the range * of 128-191 and just pick the first free minor there * (new style). */ switch (type) { case VFL_TYPE_VIDEO: minor_offset = 0; minor_cnt = 64; break; case VFL_TYPE_RADIO: minor_offset = 64; minor_cnt = 64; break; case VFL_TYPE_VBI: minor_offset = 224; minor_cnt = 32; break; default: minor_offset = 128; minor_cnt = 64; break; } #endif /* Pick a device node number */ mutex_lock(&videodev_lock); nr = devnode_find(vdev, nr == -1 ? 0 : nr, minor_cnt); if (nr == minor_cnt) nr = devnode_find(vdev, 0, minor_cnt); if (nr == minor_cnt) { pr_err("could not get a free device node number\n"); mutex_unlock(&videodev_lock); return -ENFILE; } #ifdef CONFIG_VIDEO_FIXED_MINOR_RANGES /* 1-on-1 mapping of device node number to minor number */ i = nr; #else /* The device node number and minor numbers are independent, so we just find the first free minor number. */ for (i = 0; i < VIDEO_NUM_DEVICES; i++) if (video_devices[i] == NULL) break; if (i == VIDEO_NUM_DEVICES) { mutex_unlock(&videodev_lock); pr_err("could not get a free minor\n"); return -ENFILE; } #endif vdev->minor = i + minor_offset; vdev->num = nr; /* Should not happen since we thought this minor was free */ if (WARN_ON(video_devices[vdev->minor])) { mutex_unlock(&videodev_lock); pr_err("video_device not empty!\n"); return -ENFILE; } devnode_set(vdev); vdev->index = get_index(vdev); video_devices[vdev->minor] = vdev; mutex_unlock(&videodev_lock); if (vdev->ioctl_ops) determine_valid_ioctls(vdev); /* Part 3: Initialize the character device */ vdev->cdev = cdev_alloc(); if (vdev->cdev == NULL) { ret = -ENOMEM; goto cleanup; } vdev->cdev->ops = &v4l2_fops; vdev->cdev->owner = owner; ret = cdev_add(vdev->cdev, MKDEV(VIDEO_MAJOR, vdev->minor), 1); if (ret < 0) { pr_err("%s: cdev_add failed\n", __func__); kfree(vdev->cdev); vdev->cdev = NULL; goto cleanup; } /* Part 4: register the device with sysfs */ vdev->dev.class = &video_class; vdev->dev.devt = MKDEV(VIDEO_MAJOR, vdev->minor); vdev->dev.parent = vdev->dev_parent; dev_set_name(&vdev->dev, "%s%d", name_base, vdev->num); mutex_lock(&videodev_lock); ret = device_register(&vdev->dev); if (ret < 0) { mutex_unlock(&videodev_lock); pr_err("%s: device_register failed\n", __func__); goto cleanup; } /* Register the release callback that will be called when the last reference to the device goes away. */ vdev->dev.release = v4l2_device_release; if (nr != -1 && nr != vdev->num && warn_if_nr_in_use) pr_warn("%s: requested %s%d, got %s\n", __func__, name_base, nr, video_device_node_name(vdev)); /* Increase v4l2_device refcount */ v4l2_device_get(vdev->v4l2_dev); /* Part 5: Register the entity. */ ret = video_register_media_controller(vdev); /* Part 6: Activate this minor. The char device can now be used. */ set_bit(V4L2_FL_REGISTERED, &vdev->flags); mutex_unlock(&videodev_lock); return 0; cleanup: mutex_lock(&videodev_lock); if (vdev->cdev) cdev_del(vdev->cdev); video_devices[vdev->minor] = NULL; devnode_clear(vdev); mutex_unlock(&videodev_lock); /* Mark this video device as never having been registered. */ vdev->minor = -1; return ret; } EXPORT_SYMBOL(__video_register_device); /** * video_unregister_device - unregister a video4linux device * @vdev: the device to unregister * * This unregisters the passed device. Future open calls will * be met with errors. */ void video_unregister_device(struct video_device *vdev) { /* Check if vdev was ever registered at all */ if (!vdev || !video_is_registered(vdev)) return; mutex_lock(&videodev_lock); /* This must be in a critical section to prevent a race with v4l2_open. * Once this bit has been cleared video_get may never be called again. */ clear_bit(V4L2_FL_REGISTERED, &vdev->flags); mutex_unlock(&videodev_lock); if (test_bit(V4L2_FL_USES_V4L2_FH, &vdev->flags)) v4l2_event_wake_all(vdev); device_unregister(&vdev->dev); } EXPORT_SYMBOL(video_unregister_device); #ifdef CONFIG_DEBUG_FS struct dentry *v4l2_debugfs_root(void) { if (!v4l2_debugfs_root_dir) v4l2_debugfs_root_dir = debugfs_create_dir("v4l2", NULL); return v4l2_debugfs_root_dir; } EXPORT_SYMBOL_GPL(v4l2_debugfs_root); #endif #if defined(CONFIG_MEDIA_CONTROLLER) __must_check int video_device_pipeline_start(struct video_device *vdev, struct media_pipeline *pipe) { struct media_entity *entity = &vdev->entity; if (entity->num_pads != 1) return -ENODEV; return media_pipeline_start(&entity->pads[0], pipe); } EXPORT_SYMBOL_GPL(video_device_pipeline_start); __must_check int __video_device_pipeline_start(struct video_device *vdev, struct media_pipeline *pipe) { struct media_entity *entity = &vdev->entity; if (entity->num_pads != 1) return -ENODEV; return __media_pipeline_start(&entity->pads[0], pipe); } EXPORT_SYMBOL_GPL(__video_device_pipeline_start); void video_device_pipeline_stop(struct video_device *vdev) { struct media_entity *entity = &vdev->entity; if (WARN_ON(entity->num_pads != 1)) return; return media_pipeline_stop(&entity->pads[0]); } EXPORT_SYMBOL_GPL(video_device_pipeline_stop); void __video_device_pipeline_stop(struct video_device *vdev) { struct media_entity *entity = &vdev->entity; if (WARN_ON(entity->num_pads != 1)) return; return __media_pipeline_stop(&entity->pads[0]); } EXPORT_SYMBOL_GPL(__video_device_pipeline_stop); __must_check int video_device_pipeline_alloc_start(struct video_device *vdev) { struct media_entity *entity = &vdev->entity; if (entity->num_pads != 1) return -ENODEV; return media_pipeline_alloc_start(&entity->pads[0]); } EXPORT_SYMBOL_GPL(video_device_pipeline_alloc_start); struct media_pipeline *video_device_pipeline(struct video_device *vdev) { struct media_entity *entity = &vdev->entity; if (WARN_ON(entity->num_pads != 1)) return NULL; return media_pad_pipeline(&entity->pads[0]); } EXPORT_SYMBOL_GPL(video_device_pipeline); #endif /* CONFIG_MEDIA_CONTROLLER */ /* * Initialise video for linux */ static int __init videodev_init(void) { dev_t dev = MKDEV(VIDEO_MAJOR, 0); int ret; pr_info("Linux video capture interface: v2.00\n"); ret = register_chrdev_region(dev, VIDEO_NUM_DEVICES, VIDEO_NAME); if (ret < 0) { pr_warn("videodev: unable to get major %d\n", VIDEO_MAJOR); return ret; } ret = class_register(&video_class); if (ret < 0) { unregister_chrdev_region(dev, VIDEO_NUM_DEVICES); pr_warn("video_dev: class_register failed\n"); return -EIO; } return 0; } static void __exit videodev_exit(void) { dev_t dev = MKDEV(VIDEO_MAJOR, 0); class_unregister(&video_class); unregister_chrdev_region(dev, VIDEO_NUM_DEVICES); debugfs_remove_recursive(v4l2_debugfs_root_dir); v4l2_debugfs_root_dir = NULL; } subsys_initcall(videodev_init); module_exit(videodev_exit) MODULE_AUTHOR("Alan Cox, Mauro Carvalho Chehab <mchehab@kernel.org>, Bill Dirks, Justin Schoeman, Gerd Knorr"); MODULE_DESCRIPTION("Video4Linux2 core driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_CHARDEV_MAJOR(VIDEO_MAJOR); |
| 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 | // SPDX-License-Identifier: GPL-2.0 #include <linux/module.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_ipv4.h> #include <net/netfilter/nf_tables_ipv6.h> static unsigned int nft_nat_do_chain(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; nft_set_pktinfo(&pkt, skb, state); switch (state->pf) { #ifdef CONFIG_NF_TABLES_IPV4 case NFPROTO_IPV4: nft_set_pktinfo_ipv4(&pkt); break; #endif #ifdef CONFIG_NF_TABLES_IPV6 case NFPROTO_IPV6: nft_set_pktinfo_ipv6(&pkt); break; #endif default: break; } return nft_do_chain(&pkt, priv); } #ifdef CONFIG_NF_TABLES_IPV4 static const struct nft_chain_type nft_chain_nat_ipv4 = { .name = "nat", .type = NFT_CHAIN_T_NAT, .family = NFPROTO_IPV4, .owner = THIS_MODULE, .hook_mask = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_LOCAL_IN), .hooks = { [NF_INET_PRE_ROUTING] = nft_nat_do_chain, [NF_INET_POST_ROUTING] = nft_nat_do_chain, [NF_INET_LOCAL_OUT] = nft_nat_do_chain, [NF_INET_LOCAL_IN] = nft_nat_do_chain, }, .ops_register = nf_nat_ipv4_register_fn, .ops_unregister = nf_nat_ipv4_unregister_fn, }; #endif #ifdef CONFIG_NF_TABLES_IPV6 static const struct nft_chain_type nft_chain_nat_ipv6 = { .name = "nat", .type = NFT_CHAIN_T_NAT, .family = NFPROTO_IPV6, .owner = THIS_MODULE, .hook_mask = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_LOCAL_IN), .hooks = { [NF_INET_PRE_ROUTING] = nft_nat_do_chain, [NF_INET_POST_ROUTING] = nft_nat_do_chain, [NF_INET_LOCAL_OUT] = nft_nat_do_chain, [NF_INET_LOCAL_IN] = nft_nat_do_chain, }, .ops_register = nf_nat_ipv6_register_fn, .ops_unregister = nf_nat_ipv6_unregister_fn, }; #endif #ifdef CONFIG_NF_TABLES_INET static int nft_nat_inet_reg(struct net *net, const struct nf_hook_ops *ops) { return nf_nat_inet_register_fn(net, ops); } static void nft_nat_inet_unreg(struct net *net, const struct nf_hook_ops *ops) { nf_nat_inet_unregister_fn(net, ops); } static const struct nft_chain_type nft_chain_nat_inet = { .name = "nat", .type = NFT_CHAIN_T_NAT, .family = NFPROTO_INET, .owner = THIS_MODULE, .hook_mask = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_POST_ROUTING), .hooks = { [NF_INET_PRE_ROUTING] = nft_nat_do_chain, [NF_INET_LOCAL_IN] = nft_nat_do_chain, [NF_INET_LOCAL_OUT] = nft_nat_do_chain, [NF_INET_POST_ROUTING] = nft_nat_do_chain, }, .ops_register = nft_nat_inet_reg, .ops_unregister = nft_nat_inet_unreg, }; #endif static int __init nft_chain_nat_init(void) { #ifdef CONFIG_NF_TABLES_IPV6 nft_register_chain_type(&nft_chain_nat_ipv6); #endif #ifdef CONFIG_NF_TABLES_IPV4 nft_register_chain_type(&nft_chain_nat_ipv4); #endif #ifdef CONFIG_NF_TABLES_INET nft_register_chain_type(&nft_chain_nat_inet); #endif return 0; } static void __exit nft_chain_nat_exit(void) { #ifdef CONFIG_NF_TABLES_IPV4 nft_unregister_chain_type(&nft_chain_nat_ipv4); #endif #ifdef CONFIG_NF_TABLES_IPV6 nft_unregister_chain_type(&nft_chain_nat_ipv6); #endif #ifdef CONFIG_NF_TABLES_INET nft_unregister_chain_type(&nft_chain_nat_inet); #endif } module_init(nft_chain_nat_init); module_exit(nft_chain_nat_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("nftables network address translation support"); #ifdef CONFIG_NF_TABLES_IPV4 MODULE_ALIAS_NFT_CHAIN(AF_INET, "nat"); #endif #ifdef CONFIG_NF_TABLES_IPV6 MODULE_ALIAS_NFT_CHAIN(AF_INET6, "nat"); #endif #ifdef CONFIG_NF_TABLES_INET MODULE_ALIAS_NFT_CHAIN(1, "nat"); /* NFPROTO_INET */ #endif |
| 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic GPIO card-detect helper * * Copyright (C) 2011, Guennadi Liakhovetski <g.liakhovetski@gmx.de> */ #include <linux/err.h> #include <linux/gpio/consumer.h> #include <linux/interrupt.h> #include <linux/jiffies.h> #include <linux/mmc/host.h> #include <linux/mmc/slot-gpio.h> #include <linux/module.h> #include <linux/slab.h> #include "slot-gpio.h" struct mmc_gpio { struct gpio_desc *ro_gpio; struct gpio_desc *cd_gpio; irq_handler_t cd_gpio_isr; char *ro_label; char *cd_label; u32 cd_debounce_delay_ms; int cd_irq; }; static irqreturn_t mmc_gpio_cd_irqt(int irq, void *dev_id) { /* Schedule a card detection after a debounce timeout */ struct mmc_host *host = dev_id; struct mmc_gpio *ctx = host->slot.handler_priv; host->trigger_card_event = true; mmc_detect_change(host, msecs_to_jiffies(ctx->cd_debounce_delay_ms)); return IRQ_HANDLED; } int mmc_gpio_alloc(struct mmc_host *host) { const char *devname = dev_name(host->parent); struct mmc_gpio *ctx; ctx = devm_kzalloc(host->parent, sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->cd_debounce_delay_ms = 200; ctx->cd_label = devm_kasprintf(host->parent, GFP_KERNEL, "%s cd", devname); if (!ctx->cd_label) return -ENOMEM; ctx->ro_label = devm_kasprintf(host->parent, GFP_KERNEL, "%s ro", devname); if (!ctx->ro_label) return -ENOMEM; ctx->cd_irq = -EINVAL; host->slot.handler_priv = ctx; host->slot.cd_irq = -EINVAL; return 0; } void mmc_gpio_set_cd_irq(struct mmc_host *host, int irq) { struct mmc_gpio *ctx = host->slot.handler_priv; if (!ctx || irq < 0) return; ctx->cd_irq = irq; } EXPORT_SYMBOL(mmc_gpio_set_cd_irq); int mmc_gpio_get_ro(struct mmc_host *host) { struct mmc_gpio *ctx = host->slot.handler_priv; int cansleep; if (!ctx || !ctx->ro_gpio) return -ENOSYS; cansleep = gpiod_cansleep(ctx->ro_gpio); return cansleep ? gpiod_get_value_cansleep(ctx->ro_gpio) : gpiod_get_value(ctx->ro_gpio); } EXPORT_SYMBOL(mmc_gpio_get_ro); int mmc_gpio_get_cd(struct mmc_host *host) { struct mmc_gpio *ctx = host->slot.handler_priv; int cansleep; if (!ctx || !ctx->cd_gpio) return -ENOSYS; cansleep = gpiod_cansleep(ctx->cd_gpio); return cansleep ? gpiod_get_value_cansleep(ctx->cd_gpio) : gpiod_get_value(ctx->cd_gpio); } EXPORT_SYMBOL(mmc_gpio_get_cd); void mmc_gpiod_request_cd_irq(struct mmc_host *host) { struct mmc_gpio *ctx = host->slot.handler_priv; int irq = -EINVAL; int ret; if (host->slot.cd_irq >= 0 || !ctx || !ctx->cd_gpio) return; /* * Do not use IRQ if the platform prefers to poll, e.g., because that * IRQ number is already used by another unit and cannot be shared. */ if (ctx->cd_irq >= 0) irq = ctx->cd_irq; else if (!(host->caps & MMC_CAP_NEEDS_POLL)) irq = gpiod_to_irq(ctx->cd_gpio); if (irq >= 0) { if (!ctx->cd_gpio_isr) ctx->cd_gpio_isr = mmc_gpio_cd_irqt; ret = devm_request_threaded_irq(host->parent, irq, NULL, ctx->cd_gpio_isr, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING | IRQF_ONESHOT, ctx->cd_label, host); if (ret < 0) irq = ret; } host->slot.cd_irq = irq; if (irq < 0) host->caps |= MMC_CAP_NEEDS_POLL; } EXPORT_SYMBOL(mmc_gpiod_request_cd_irq); int mmc_gpio_set_cd_wake(struct mmc_host *host, bool on) { int ret = 0; if (!(host->caps & MMC_CAP_CD_WAKE) || host->slot.cd_irq < 0 || on == host->slot.cd_wake_enabled) return 0; if (on) { ret = enable_irq_wake(host->slot.cd_irq); host->slot.cd_wake_enabled = !ret; } else { disable_irq_wake(host->slot.cd_irq); host->slot.cd_wake_enabled = false; } return ret; } EXPORT_SYMBOL(mmc_gpio_set_cd_wake); /* Register an alternate interrupt service routine for * the card-detect GPIO. */ void mmc_gpio_set_cd_isr(struct mmc_host *host, irq_handler_t isr) { struct mmc_gpio *ctx = host->slot.handler_priv; WARN_ON(ctx->cd_gpio_isr); ctx->cd_gpio_isr = isr; } EXPORT_SYMBOL(mmc_gpio_set_cd_isr); /** * mmc_gpiod_request_cd - request a gpio descriptor for card-detection * @host: mmc host * @con_id: function within the GPIO consumer * @idx: index of the GPIO to obtain in the consumer * @override_active_level: ignore %GPIO_ACTIVE_LOW flag * @debounce: debounce time in microseconds * * Note that this must be called prior to mmc_add_host() * otherwise the caller must also call mmc_gpiod_request_cd_irq(). * * Returns zero on success, else an error. */ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, unsigned int idx, bool override_active_level, unsigned int debounce) { struct mmc_gpio *ctx = host->slot.handler_priv; struct gpio_desc *desc; int ret; desc = devm_gpiod_get_index(host->parent, con_id, idx, GPIOD_IN); if (IS_ERR(desc)) return PTR_ERR(desc); /* Update default label if no con_id provided */ if (!con_id) gpiod_set_consumer_name(desc, ctx->cd_label); if (debounce) { ret = gpiod_set_debounce(desc, debounce); if (ret < 0) ctx->cd_debounce_delay_ms = debounce / 1000; } /* override forces default (active-low) polarity ... */ if (override_active_level && !gpiod_is_active_low(desc)) gpiod_toggle_active_low(desc); /* ... or active-high */ if (host->caps2 & MMC_CAP2_CD_ACTIVE_HIGH) gpiod_toggle_active_low(desc); ctx->cd_gpio = desc; return 0; } EXPORT_SYMBOL(mmc_gpiod_request_cd); /** * mmc_gpiod_set_cd_config - set config for card-detection GPIO * @host: mmc host * @config: Generic pinconf config (from pinconf_to_config_packed()) * * This can be used by mmc host drivers to fixup a card-detection GPIO's config * (e.g. set PIN_CONFIG_BIAS_PULL_UP) after acquiring the GPIO descriptor * through mmc_gpiod_request_cd(). * * Returns: * 0 on success, or a negative errno value on error. */ int mmc_gpiod_set_cd_config(struct mmc_host *host, unsigned long config) { struct mmc_gpio *ctx = host->slot.handler_priv; return gpiod_set_config(ctx->cd_gpio, config); } EXPORT_SYMBOL(mmc_gpiod_set_cd_config); bool mmc_can_gpio_cd(struct mmc_host *host) { struct mmc_gpio *ctx = host->slot.handler_priv; return ctx->cd_gpio ? true : false; } EXPORT_SYMBOL(mmc_can_gpio_cd); /** * mmc_gpiod_request_ro - request a gpio descriptor for write protection * @host: mmc host * @con_id: function within the GPIO consumer * @idx: index of the GPIO to obtain in the consumer * @debounce: debounce time in microseconds * * Returns zero on success, else an error. */ int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id, unsigned int idx, unsigned int debounce) { struct mmc_gpio *ctx = host->slot.handler_priv; struct gpio_desc *desc; int ret; desc = devm_gpiod_get_index(host->parent, con_id, idx, GPIOD_IN); if (IS_ERR(desc)) return PTR_ERR(desc); /* Update default label if no con_id provided */ if (!con_id) gpiod_set_consumer_name(desc, ctx->ro_label); if (debounce) { ret = gpiod_set_debounce(desc, debounce); if (ret < 0) return ret; } if (host->caps2 & MMC_CAP2_RO_ACTIVE_HIGH) gpiod_toggle_active_low(desc); ctx->ro_gpio = desc; return 0; } EXPORT_SYMBOL(mmc_gpiod_request_ro); bool mmc_can_gpio_ro(struct mmc_host *host) { struct mmc_gpio *ctx = host->slot.handler_priv; return ctx->ro_gpio ? true : false; } EXPORT_SYMBOL(mmc_can_gpio_ro); |
| 12 13 13 2 17 3 1 11 16 14 2 1 13 1 8 8 48 523 214 2552 7 5860 5 3103 10 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_H #define _LINUX_SCHED_H /* * Define 'struct task_struct' and provide the main scheduler * APIs (schedule(), wakeup variants, etc.) */ #include <uapi/linux/sched.h> #include <asm/current.h> #include <asm/processor.h> #include <linux/thread_info.h> #include <linux/preempt.h> #include <linux/cpumask_types.h> #include <linux/cache.h> #include <linux/irqflags_types.h> #include <linux/smp_types.h> #include <linux/pid_types.h> #include <linux/sem_types.h> #include <linux/shm.h> #include <linux/kmsan_types.h> #include <linux/mutex_types.h> #include <linux/plist_types.h> #include <linux/hrtimer_types.h> #include <linux/timer_types.h> #include <linux/seccomp_types.h> #include <linux/nodemask_types.h> #include <linux/refcount_types.h> #include <linux/resource.h> #include <linux/latencytop.h> #include <linux/sched/prio.h> #include <linux/sched/types.h> #include <linux/signal_types.h> #include <linux/syscall_user_dispatch_types.h> #include <linux/mm_types_task.h> #include <linux/netdevice_xmit.h> #include <linux/task_io_accounting.h> #include <linux/posix-timers_types.h> #include <linux/restart_block.h> #include <uapi/linux/rseq.h> #include <linux/seqlock_types.h> #include <linux/kcsan.h> #include <linux/rv.h> #include <linux/livepatch_sched.h> #include <linux/uidgid_types.h> #include <asm/kmap_size.h> /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; struct bio_list; struct blk_plug; struct bpf_local_storage; struct bpf_run_ctx; struct bpf_net_context; struct capture_control; struct cfs_rq; struct fs_struct; struct futex_pi_state; struct io_context; struct io_uring_task; struct mempolicy; struct nameidata; struct nsproxy; struct perf_event_context; struct pid_namespace; struct pipe_inode_info; struct rcu_node; struct reclaim_state; struct robust_list_head; struct root_domain; struct rq; struct sched_attr; struct sched_dl_entity; struct seq_file; struct sighand_struct; struct signal_struct; struct task_delay_info; struct task_group; struct task_struct; struct user_event_mm; #include <linux/sched/ext.h> /* * Task state bitmask. NOTE! These bits are also * encoded in fs/proc/array.c: get_task_state(). * * We have two separate sets of flags: task->__state * is about runnability, while task->exit_state are * about the task exiting. Confusing, but this way * modifying one set can't modify the other one by * mistake. */ /* Used in tsk->__state: */ #define TASK_RUNNING 0x00000000 #define TASK_INTERRUPTIBLE 0x00000001 #define TASK_UNINTERRUPTIBLE 0x00000002 #define __TASK_STOPPED 0x00000004 #define __TASK_TRACED 0x00000008 /* Used in tsk->exit_state: */ #define EXIT_DEAD 0x00000010 #define EXIT_ZOMBIE 0x00000020 #define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD) /* Used in tsk->__state again: */ #define TASK_PARKED 0x00000040 #define TASK_DEAD 0x00000080 #define TASK_WAKEKILL 0x00000100 #define TASK_WAKING 0x00000200 #define TASK_NOLOAD 0x00000400 #define TASK_NEW 0x00000800 #define TASK_RTLOCK_WAIT 0x00001000 #define TASK_FREEZABLE 0x00002000 #define __TASK_FREEZABLE_UNSAFE (0x00004000 * IS_ENABLED(CONFIG_LOCKDEP)) #define TASK_FROZEN 0x00008000 #define TASK_STATE_MAX 0x00010000 #define TASK_ANY (TASK_STATE_MAX-1) /* * DO NOT ADD ANY NEW USERS ! */ #define TASK_FREEZABLE_UNSAFE (TASK_FREEZABLE | __TASK_FREEZABLE_UNSAFE) /* Convenience macros for the sake of set_current_state: */ #define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE) #define TASK_STOPPED (TASK_WAKEKILL | __TASK_STOPPED) #define TASK_TRACED __TASK_TRACED #define TASK_IDLE (TASK_UNINTERRUPTIBLE | TASK_NOLOAD) /* Convenience macros for the sake of wake_up(): */ #define TASK_NORMAL (TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE) /* get_task_state(): */ #define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \ TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \ __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ TASK_PARKED) #define task_is_running(task) (READ_ONCE((task)->__state) == TASK_RUNNING) #define task_is_traced(task) ((READ_ONCE(task->jobctl) & JOBCTL_TRACED) != 0) #define task_is_stopped(task) ((READ_ONCE(task->jobctl) & JOBCTL_STOPPED) != 0) #define task_is_stopped_or_traced(task) ((READ_ONCE(task->jobctl) & (JOBCTL_STOPPED | JOBCTL_TRACED)) != 0) /* * Special states are those that do not use the normal wait-loop pattern. See * the comment with set_special_state(). */ #define is_special_task_state(state) \ ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | \ TASK_DEAD | TASK_FROZEN)) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP # define debug_normal_state_change(state_value) \ do { \ WARN_ON_ONCE(is_special_task_state(state_value)); \ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_special_state_change(state_value) \ do { \ WARN_ON_ONCE(!is_special_task_state(state_value)); \ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_rtlock_wait_set_state() \ do { \ current->saved_state_change = current->task_state_change;\ current->task_state_change = _THIS_IP_; \ } while (0) # define debug_rtlock_wait_restore_state() \ do { \ current->task_state_change = current->saved_state_change;\ } while (0) #else # define debug_normal_state_change(cond) do { } while (0) # define debug_special_state_change(cond) do { } while (0) # define debug_rtlock_wait_set_state() do { } while (0) # define debug_rtlock_wait_restore_state() do { } while (0) #endif /* * set_current_state() includes a barrier so that the write of current->__state * is correctly serialised wrt the caller's subsequent test of whether to * actually sleep: * * for (;;) { * set_current_state(TASK_UNINTERRUPTIBLE); * if (CONDITION) * break; * * schedule(); * } * __set_current_state(TASK_RUNNING); * * If the caller does not need such serialisation (because, for instance, the * CONDITION test and condition change and wakeup are under the same lock) then * use __set_current_state(). * * The above is typically ordered against the wakeup, which does: * * CONDITION = 1; * wake_up_state(p, TASK_UNINTERRUPTIBLE); * * where wake_up_state()/try_to_wake_up() executes a full memory barrier before * accessing p->__state. * * Wakeup will do: if (@state & p->__state) p->__state = TASK_RUNNING, that is, * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING). * * However, with slightly different timing the wakeup TASK_RUNNING store can * also collide with the TASK_UNINTERRUPTIBLE store. Losing that store is not * a problem either because that will result in one extra go around the loop * and our @cond test will save the day. * * Also see the comments of try_to_wake_up(). */ #define __set_current_state(state_value) \ do { \ debug_normal_state_change((state_value)); \ WRITE_ONCE(current->__state, (state_value)); \ } while (0) #define set_current_state(state_value) \ do { \ debug_normal_state_change((state_value)); \ smp_store_mb(current->__state, (state_value)); \ } while (0) /* * set_special_state() should be used for those states when the blocking task * can not use the regular condition based wait-loop. In that case we must * serialize against wakeups such that any possible in-flight TASK_RUNNING * stores will not collide with our state change. */ #define set_special_state(state_value) \ do { \ unsigned long flags; /* may shadow */ \ \ raw_spin_lock_irqsave(¤t->pi_lock, flags); \ debug_special_state_change((state_value)); \ WRITE_ONCE(current->__state, (state_value)); \ raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ } while (0) /* * PREEMPT_RT specific variants for "sleeping" spin/rwlocks * * RT's spin/rwlock substitutions are state preserving. The state of the * task when blocking on the lock is saved in task_struct::saved_state and * restored after the lock has been acquired. These operations are * serialized by task_struct::pi_lock against try_to_wake_up(). Any non RT * lock related wakeups while the task is blocked on the lock are * redirected to operate on task_struct::saved_state to ensure that these * are not dropped. On restore task_struct::saved_state is set to * TASK_RUNNING so any wakeup attempt redirected to saved_state will fail. * * The lock operation looks like this: * * current_save_and_set_rtlock_wait_state(); * for (;;) { * if (try_lock()) * break; * raw_spin_unlock_irq(&lock->wait_lock); * schedule_rtlock(); * raw_spin_lock_irq(&lock->wait_lock); * set_current_state(TASK_RTLOCK_WAIT); * } * current_restore_rtlock_saved_state(); */ #define current_save_and_set_rtlock_wait_state() \ do { \ lockdep_assert_irqs_disabled(); \ raw_spin_lock(¤t->pi_lock); \ current->saved_state = current->__state; \ debug_rtlock_wait_set_state(); \ WRITE_ONCE(current->__state, TASK_RTLOCK_WAIT); \ raw_spin_unlock(¤t->pi_lock); \ } while (0); #define current_restore_rtlock_saved_state() \ do { \ lockdep_assert_irqs_disabled(); \ raw_spin_lock(¤t->pi_lock); \ debug_rtlock_wait_restore_state(); \ WRITE_ONCE(current->__state, current->saved_state); \ current->saved_state = TASK_RUNNING; \ raw_spin_unlock(¤t->pi_lock); \ } while (0); #define get_current_state() READ_ONCE(current->__state) /* * Define the task command name length as enum, then it can be visible to * BPF programs. */ enum { TASK_COMM_LEN = 16, }; extern void sched_tick(void); #define MAX_SCHEDULE_TIMEOUT LONG_MAX extern long schedule_timeout(long timeout); extern long schedule_timeout_interruptible(long timeout); extern long schedule_timeout_killable(long timeout); extern long schedule_timeout_uninterruptible(long timeout); extern long schedule_timeout_idle(long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); asmlinkage void preempt_schedule_irq(void); #ifdef CONFIG_PREEMPT_RT extern void schedule_rtlock(void); #endif extern int __must_check io_schedule_prepare(void); extern void io_schedule_finish(int token); extern long io_schedule_timeout(long timeout); extern void io_schedule(void); /** * struct prev_cputime - snapshot of system and user cputime * @utime: time spent in user mode * @stime: time spent in system mode * @lock: protects the above two fields * * Stores previous user/system time values such that we can guarantee * monotonicity. */ struct prev_cputime { #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE u64 utime; u64 stime; raw_spinlock_t lock; #endif }; enum vtime_state { /* Task is sleeping or running in a CPU with VTIME inactive: */ VTIME_INACTIVE = 0, /* Task is idle */ VTIME_IDLE, /* Task runs in kernelspace in a CPU with VTIME active: */ VTIME_SYS, /* Task runs in userspace in a CPU with VTIME active: */ VTIME_USER, /* Task runs as guests in a CPU with VTIME active: */ VTIME_GUEST, }; struct vtime { seqcount_t seqcount; unsigned long long starttime; enum vtime_state state; unsigned int cpu; u64 utime; u64 stime; u64 gtime; }; /* * Utilization clamp constraints. * @UCLAMP_MIN: Minimum utilization * @UCLAMP_MAX: Maximum utilization * @UCLAMP_CNT: Utilization clamp constraints count */ enum uclamp_id { UCLAMP_MIN = 0, UCLAMP_MAX, UCLAMP_CNT }; #ifdef CONFIG_SMP extern struct root_domain def_root_domain; extern struct mutex sched_domains_mutex; #endif struct sched_param { int sched_priority; }; struct sched_info { #ifdef CONFIG_SCHED_INFO /* Cumulative counters: */ /* # of times we have run on this CPU: */ unsigned long pcount; /* Time spent waiting on a runqueue: */ unsigned long long run_delay; /* Max time spent waiting on a runqueue: */ unsigned long long max_run_delay; /* Min time spent waiting on a runqueue: */ unsigned long long min_run_delay; /* Timestamps: */ /* When did we last run on a CPU? */ unsigned long long last_arrival; /* When were we last queued to run? */ unsigned long long last_queued; #endif /* CONFIG_SCHED_INFO */ }; /* * Integer metrics need fixed point arithmetic, e.g., sched/fair * has a few: load, load_avg, util_avg, freq, and capacity. * * We define a basic fixed point arithmetic range, and then formalize * all these metrics based on that basic range. */ # define SCHED_FIXEDPOINT_SHIFT 10 # define SCHED_FIXEDPOINT_SCALE (1L << SCHED_FIXEDPOINT_SHIFT) /* Increase resolution of cpu_capacity calculations */ # define SCHED_CAPACITY_SHIFT SCHED_FIXEDPOINT_SHIFT # define SCHED_CAPACITY_SCALE (1L << SCHED_CAPACITY_SHIFT) struct load_weight { unsigned long weight; u32 inv_weight; }; /* * The load/runnable/util_avg accumulates an infinite geometric series * (see __update_load_avg_cfs_rq() in kernel/sched/pelt.c). * * [load_avg definition] * * load_avg = runnable% * scale_load_down(load) * * [runnable_avg definition] * * runnable_avg = runnable% * SCHED_CAPACITY_SCALE * * [util_avg definition] * * util_avg = running% * SCHED_CAPACITY_SCALE * * where runnable% is the time ratio that a sched_entity is runnable and * running% the time ratio that a sched_entity is running. * * For cfs_rq, they are the aggregated values of all runnable and blocked * sched_entities. * * The load/runnable/util_avg doesn't directly factor frequency scaling and CPU * capacity scaling. The scaling is done through the rq_clock_pelt that is used * for computing those signals (see update_rq_clock_pelt()) * * N.B., the above ratios (runnable% and running%) themselves are in the * range of [0, 1]. To do fixed point arithmetics, we therefore scale them * to as large a range as necessary. This is for example reflected by * util_avg's SCHED_CAPACITY_SCALE. * * [Overflow issue] * * The 64-bit load_sum can have 4353082796 (=2^64/47742/88761) entities * with the highest load (=88761), always runnable on a single cfs_rq, * and should not overflow as the number already hits PID_MAX_LIMIT. * * For all other cases (including 32-bit kernels), struct load_weight's * weight will overflow first before we do, because: * * Max(load_avg) <= Max(load.weight) * * Then it is the load_weight's responsibility to consider overflow * issues. */ struct sched_avg { u64 last_update_time; u64 load_sum; u64 runnable_sum; u32 util_sum; u32 period_contrib; unsigned long load_avg; unsigned long runnable_avg; unsigned long util_avg; unsigned int util_est; } ____cacheline_aligned; /* * The UTIL_AVG_UNCHANGED flag is used to synchronize util_est with util_avg * updates. When a task is dequeued, its util_est should not be updated if its * util_avg has not been updated in the meantime. * This information is mapped into the MSB bit of util_est at dequeue time. * Since max value of util_est for a task is 1024 (PELT util_avg for a task) * it is safe to use MSB. */ #define UTIL_EST_WEIGHT_SHIFT 2 #define UTIL_AVG_UNCHANGED 0x80000000 struct sched_statistics { #ifdef CONFIG_SCHEDSTATS u64 wait_start; u64 wait_max; u64 wait_count; u64 wait_sum; u64 iowait_count; u64 iowait_sum; u64 sleep_start; u64 sleep_max; s64 sum_sleep_runtime; u64 block_start; u64 block_max; s64 sum_block_runtime; s64 exec_max; u64 slice_max; u64 nr_migrations_cold; u64 nr_failed_migrations_affine; u64 nr_failed_migrations_running; u64 nr_failed_migrations_hot; u64 nr_forced_migrations; u64 nr_wakeups; u64 nr_wakeups_sync; u64 nr_wakeups_migrate; u64 nr_wakeups_local; u64 nr_wakeups_remote; u64 nr_wakeups_affine; u64 nr_wakeups_affine_attempts; u64 nr_wakeups_passive; u64 nr_wakeups_idle; #ifdef CONFIG_SCHED_CORE u64 core_forceidle_sum; #endif #endif /* CONFIG_SCHEDSTATS */ } ____cacheline_aligned; struct sched_entity { /* For load-balancing: */ struct load_weight load; struct rb_node run_node; u64 deadline; u64 min_vruntime; u64 min_slice; struct list_head group_node; unsigned char on_rq; unsigned char sched_delayed; unsigned char rel_deadline; unsigned char custom_slice; /* hole */ u64 exec_start; u64 sum_exec_runtime; u64 prev_sum_exec_runtime; u64 vruntime; s64 vlag; u64 slice; u64 nr_migrations; #ifdef CONFIG_FAIR_GROUP_SCHED int depth; struct sched_entity *parent; /* rq on which this entity is (to be) queued: */ struct cfs_rq *cfs_rq; /* rq "owned" by this entity/group: */ struct cfs_rq *my_q; /* cached value of my_q->h_nr_running */ unsigned long runnable_weight; #endif #ifdef CONFIG_SMP /* * Per entity load average tracking. * * Put into separate cache line so it does not * collide with read-mostly values above. */ struct sched_avg avg; #endif }; struct sched_rt_entity { struct list_head run_list; unsigned long timeout; unsigned long watchdog_stamp; unsigned int time_slice; unsigned short on_rq; unsigned short on_list; struct sched_rt_entity *back; #ifdef CONFIG_RT_GROUP_SCHED struct sched_rt_entity *parent; /* rq on which this entity is (to be) queued: */ struct rt_rq *rt_rq; /* rq "owned" by this entity/group: */ struct rt_rq *my_q; #endif } __randomize_layout; typedef bool (*dl_server_has_tasks_f)(struct sched_dl_entity *); typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *); struct sched_dl_entity { struct rb_node rb_node; /* * Original scheduling parameters. Copied here from sched_attr * during sched_setattr(), they will remain the same until * the next sched_setattr(). */ u64 dl_runtime; /* Maximum runtime for each instance */ u64 dl_deadline; /* Relative deadline of each instance */ u64 dl_period; /* Separation of two instances (period) */ u64 dl_bw; /* dl_runtime / dl_period */ u64 dl_density; /* dl_runtime / dl_deadline */ /* * Actual scheduling parameters. Initialized with the values above, * they are continuously updated during task execution. Note that * the remaining runtime could be < 0 in case we are in overrun. */ s64 runtime; /* Remaining runtime for this instance */ u64 deadline; /* Absolute deadline for this instance */ unsigned int flags; /* Specifying the scheduler behaviour */ /* * Some bool flags: * * @dl_throttled tells if we exhausted the runtime. If so, the * task has to wait for a replenishment to be performed at the * next firing of dl_timer. * * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. * * @dl_non_contending tells if the task is inactive while still * contributing to the active utilization. In other words, it * indicates if the inactive timer has been armed and its handler * has not been executed yet. This flag is useful to avoid race * conditions between the inactive timer handler and the wakeup * code. * * @dl_overrun tells if the task asked to be informed about runtime * overruns. * * @dl_server tells if this is a server entity. * * @dl_defer tells if this is a deferred or regular server. For * now only defer server exists. * * @dl_defer_armed tells if the deferrable server is waiting * for the replenishment timer to activate it. * * @dl_server_active tells if the dlserver is active(started). * dlserver is started on first cfs enqueue on an idle runqueue * and is stopped when a dequeue results in 0 cfs tasks on the * runqueue. In other words, dlserver is active only when cpu's * runqueue has atleast one cfs task. * * @dl_defer_running tells if the deferrable server is actually * running, skipping the defer phase. */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; unsigned int dl_server : 1; unsigned int dl_server_active : 1; unsigned int dl_defer : 1; unsigned int dl_defer_armed : 1; unsigned int dl_defer_running : 1; /* * Bandwidth enforcement timer. Each -deadline task has its * own bandwidth to be enforced, thus we need one timer per task. */ struct hrtimer dl_timer; /* * Inactive timer, responsible for decreasing the active utilization * at the "0-lag time". When a -deadline task blocks, it contributes * to GRUB's active utilization until the "0-lag time", hence a * timer is needed to decrease the active utilization at the correct * time. */ struct hrtimer inactive_timer; /* * Bits for DL-server functionality. Also see the comment near * dl_server_update(). * * @rq the runqueue this server is for * * @server_has_tasks() returns true if @server_pick return a * runnable task. */ struct rq *rq; dl_server_has_tasks_f server_has_tasks; dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES /* * Priority Inheritance. When a DEADLINE scheduling entity is boosted * pi_se points to the donor, otherwise points to the dl_se it belongs * to (the original one/itself). */ struct sched_dl_entity *pi_se; #endif }; #ifdef CONFIG_UCLAMP_TASK /* Number of utilization clamp buckets (shorter alias) */ #define UCLAMP_BUCKETS CONFIG_UCLAMP_BUCKETS_COUNT /* * Utilization clamp for a scheduling entity * @value: clamp value "assigned" to a se * @bucket_id: bucket index corresponding to the "assigned" value * @active: the se is currently refcounted in a rq's bucket * @user_defined: the requested clamp value comes from user-space * * The bucket_id is the index of the clamp bucket matching the clamp value * which is pre-computed and stored to avoid expensive integer divisions from * the fast path. * * The active bit is set whenever a task has got an "effective" value assigned, * which can be different from the clamp value "requested" from user-space. * This allows to know a task is refcounted in the rq's bucket corresponding * to the "effective" bucket_id. * * The user_defined bit is set whenever a task has got a task-specific clamp * value requested from userspace, i.e. the system defaults apply to this task * just as a restriction. This allows to relax default clamps when a less * restrictive task-specific value has been requested, thus allowing to * implement a "nice" semantic. For example, a task running with a 20% * default boost can still drop its own boosting to 0%. */ struct uclamp_se { unsigned int value : bits_per(SCHED_CAPACITY_SCALE); unsigned int bucket_id : bits_per(UCLAMP_BUCKETS); unsigned int active : 1; unsigned int user_defined : 1; }; #endif /* CONFIG_UCLAMP_TASK */ union rcu_special { struct { u8 blocked; u8 need_qs; u8 exp_hint; /* Hint for performance. */ u8 need_mb; /* Readers need smp_mb(). */ } b; /* Bits. */ u32 s; /* Set of bits. */ }; enum perf_event_task_context { perf_invalid_context = -1, perf_hw_context = 0, perf_sw_context, perf_nr_task_contexts, }; /* * Number of contexts where an event can trigger: * task, softirq, hardirq, nmi. */ #define PERF_NR_CONTEXTS 4 struct wake_q_node { struct wake_q_node *next; }; struct kmap_ctrl { #ifdef CONFIG_KMAP_LOCAL int idx; pte_t pteval[KM_MAX_IDX]; #endif }; struct task_struct { #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For reasons of header soup (see current_thread_info()), this * must be the first element of task_struct. */ struct thread_info thread_info; #endif unsigned int __state; /* saved state for "spinlock sleepers" */ unsigned int saved_state; /* * This begins the randomizable portion of task_struct. Only * scheduling-critical items should be added above here. */ randomized_struct_fields_start void *stack; refcount_t usage; /* Per task flags (PF_*), defined further below: */ unsigned int flags; unsigned int ptrace; #ifdef CONFIG_MEM_ALLOC_PROFILING struct alloc_tag *alloc_tag; #endif #ifdef CONFIG_SMP int on_cpu; struct __call_single_node wake_entry; unsigned int wakee_flips; unsigned long wakee_flip_decay_ts; struct task_struct *last_wakee; /* * recent_used_cpu is initially set as the last CPU used by a task * that wakes affine another task. Waker/wakee relationships can * push tasks around a CPU where each wakeup moves to the next one. * Tracking a recently used CPU allows a quick search for a recently * used CPU that may be idle. */ int recent_used_cpu; int wake_cpu; #endif int on_rq; int prio; int static_prio; int normal_prio; unsigned int rt_priority; struct sched_entity se; struct sched_rt_entity rt; struct sched_dl_entity dl; struct sched_dl_entity *dl_server; #ifdef CONFIG_SCHED_CLASS_EXT struct sched_ext_entity scx; #endif const struct sched_class *sched_class; #ifdef CONFIG_SCHED_CORE struct rb_node core_node; unsigned long core_cookie; unsigned int core_occupation; #endif #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; #endif #ifdef CONFIG_UCLAMP_TASK /* * Clamp values requested for a scheduling entity. * Must be updated with task_rq_lock() held. */ struct uclamp_se uclamp_req[UCLAMP_CNT]; /* * Effective clamp values used for a scheduling entity. * Must be updated with task_rq_lock() held. */ struct uclamp_se uclamp[UCLAMP_CNT]; #endif struct sched_statistics stats; #ifdef CONFIG_PREEMPT_NOTIFIERS /* List of struct preempt_notifier: */ struct hlist_head preempt_notifiers; #endif #ifdef CONFIG_BLK_DEV_IO_TRACE unsigned int btrace_seq; #endif unsigned int policy; unsigned long max_allowed_capacity; int nr_cpus_allowed; const cpumask_t *cpus_ptr; cpumask_t *user_cpus_ptr; cpumask_t cpus_mask; void *migration_pending; #ifdef CONFIG_SMP unsigned short migration_disabled; #endif unsigned short migration_flags; #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; union rcu_special rcu_read_unlock_special; struct list_head rcu_node_entry; struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU unsigned long rcu_tasks_nvcsw; u8 rcu_tasks_holdout; u8 rcu_tasks_idx; int rcu_tasks_idle_cpu; struct list_head rcu_tasks_holdout_list; int rcu_tasks_exit_cpu; struct list_head rcu_tasks_exit_list; #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU int trc_reader_nesting; int trc_ipi_to_cpu; union rcu_special trc_reader_special; struct list_head trc_holdout_list; struct list_head trc_blkd_node; int trc_blkd_cpu; #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ struct sched_info sched_info; struct list_head tasks; #ifdef CONFIG_SMP struct plist_node pushable_tasks; struct rb_node pushable_dl_tasks; #endif struct mm_struct *mm; struct mm_struct *active_mm; struct address_space *faults_disabled_mapping; int exit_state; int exit_code; int exit_signal; /* The signal sent when the parent dies: */ int pdeath_signal; /* JOBCTL_*, siglock protected: */ unsigned long jobctl; /* Used for emulating ABI behavior of previous Linux versions: */ unsigned int personality; /* Scheduler bits, serialized by scheduler locks: */ unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; unsigned sched_task_hot:1; /* Force alignment to the next boundary: */ unsigned :0; /* Unserialized, strictly 'current' */ /* * This field must not be in the scheduler word above due to wakelist * queueing no longer being serialized by p->on_cpu. However: * * p->XXX = X; ttwu() * schedule() if (p->on_rq && ..) // false * smp_mb__after_spinlock(); if (smp_load_acquire(&p->on_cpu) && //true * deactivate_task() ttwu_queue_wakelist()) * p->on_rq = 0; p->sched_remote_wakeup = Y; * * guarantees all stores of 'current' are visible before * ->sched_remote_wakeup gets used, so it can be in this word. */ unsigned sched_remote_wakeup:1; #ifdef CONFIG_RT_MUTEXES unsigned sched_rt_mutex:1; #endif /* Bit to tell TOMOYO we're in execve(): */ unsigned in_execve:1; unsigned in_iowait:1; #ifndef TIF_RESTORE_SIGMASK unsigned restore_sigmask:1; #endif #ifdef CONFIG_MEMCG_V1 unsigned in_user_fault:1; #endif #ifdef CONFIG_LRU_GEN /* whether the LRU algorithm may apply to this access */ unsigned in_lru_fault:1; #endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; #endif #ifdef CONFIG_CGROUPS /* disallow userland-initiated cgroup migration */ unsigned no_cgroup_migration:1; /* task is frozen/stopped (used by the cgroup freezer) */ unsigned frozen:1; #endif #ifdef CONFIG_BLK_CGROUP unsigned use_memdelay:1; #endif #ifdef CONFIG_PSI /* Stalled due to lack of memory */ unsigned in_memstall:1; #endif #ifdef CONFIG_PAGE_OWNER /* Used by page_owner=on to detect recursion in page tracking. */ unsigned in_page_owner:1; #endif #ifdef CONFIG_EVENTFD /* Recursion prevention for eventfd_signal() */ unsigned in_eventfd:1; #endif #ifdef CONFIG_ARCH_HAS_CPU_PASID unsigned pasid_activated:1; #endif #ifdef CONFIG_X86_BUS_LOCK_DETECT unsigned reported_split_lock:1; #endif #ifdef CONFIG_TASK_DELAY_ACCT /* delay due to memory thrashing */ unsigned in_thrashing:1; #endif #ifdef CONFIG_PREEMPT_RT struct netdev_xmit net_xmit; #endif unsigned long atomic_flags; /* Flags requiring atomic access. */ struct restart_block restart_block; pid_t pid; pid_t tgid; #ifdef CONFIG_STACKPROTECTOR /* Canary value for the -fstack-protector GCC feature: */ unsigned long stack_canary; #endif /* * Pointers to the (original) parent process, youngest child, younger sibling, * older sibling, respectively. (p->father can be replaced with * p->real_parent->pid) */ /* Real parent process: */ struct task_struct __rcu *real_parent; /* Recipient of SIGCHLD, wait4() reports: */ struct task_struct __rcu *parent; /* * Children/sibling form the list of natural children: */ struct list_head children; struct list_head sibling; struct task_struct *group_leader; /* * 'ptraced' is the list of tasks this task is using ptrace() on. * * This includes both natural children and PTRACE_ATTACH targets. * 'ptrace_entry' is this task's link on the p->parent->ptraced list. */ struct list_head ptraced; struct list_head ptrace_entry; /* PID/PID hash table linkage. */ struct pid *thread_pid; struct hlist_node pid_links[PIDTYPE_MAX]; struct list_head thread_node; struct completion *vfork_done; /* CLONE_CHILD_SETTID: */ int __user *set_child_tid; /* CLONE_CHILD_CLEARTID: */ int __user *clear_child_tid; /* PF_KTHREAD | PF_IO_WORKER */ void *worker_private; u64 utime; u64 stime; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME u64 utimescaled; u64 stimescaled; #endif u64 gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN struct vtime vtime; #endif #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif /* Context switch counts: */ unsigned long nvcsw; unsigned long nivcsw; /* Monotonic time in nsecs: */ u64 start_time; /* Boot based time in nsecs: */ u64 start_boottime; /* MM fault and swap info: this can arguably be seen as either mm-specific or thread-specific: */ unsigned long min_flt; unsigned long maj_flt; /* Empty if CONFIG_POSIX_CPUTIMERS=n */ struct posix_cputimers posix_cputimers; #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK struct posix_cputimers_work posix_cputimers_work; #endif /* Process credentials: */ /* Tracer's credentials at attach: */ const struct cred __rcu *ptracer_cred; /* Objective and real subjective task credentials (COW): */ const struct cred __rcu *real_cred; /* Effective (overridable) subjective task credentials (COW): */ const struct cred __rcu *cred; #ifdef CONFIG_KEYS /* Cached requested key. */ struct key *cached_requested_key; #endif /* * executable name, excluding path. * * - normally initialized begin_new_exec() * - set it with set_task_comm() * - strscpy_pad() to ensure it is always NUL-terminated and * zero-padded * - task_lock() to ensure the operation is atomic and the name is * fully updated. */ char comm[TASK_COMM_LEN]; struct nameidata *nameidata; #ifdef CONFIG_SYSVIPC struct sysv_sem sysvsem; struct sysv_shm sysvshm; #endif #ifdef CONFIG_DETECT_HUNG_TASK unsigned long last_switch_count; unsigned long last_switch_time; #endif /* Filesystem information: */ struct fs_struct *fs; /* Open file information: */ struct files_struct *files; #ifdef CONFIG_IO_URING struct io_uring_task *io_uring; #endif /* Namespaces: */ struct nsproxy *nsproxy; /* Signal handlers: */ struct signal_struct *signal; struct sighand_struct __rcu *sighand; sigset_t blocked; sigset_t real_blocked; /* Restored if set_restore_sigmask() was used: */ sigset_t saved_sigmask; struct sigpending pending; unsigned long sas_ss_sp; size_t sas_ss_size; unsigned int sas_ss_flags; struct callback_head *task_works; #ifdef CONFIG_AUDIT #ifdef CONFIG_AUDITSYSCALL struct audit_context *audit_context; #endif kuid_t loginuid; unsigned int sessionid; #endif struct seccomp seccomp; struct syscall_user_dispatch syscall_dispatch; /* Thread group tracking: */ u64 parent_exec_id; u64 self_exec_id; /* Protection against (de-)allocation: mm, files, fs, tty, keyrings, mems_allowed, mempolicy: */ spinlock_t alloc_lock; /* Protection of the PI data structures: */ raw_spinlock_t pi_lock; struct wake_q_node wake_q; #ifdef CONFIG_RT_MUTEXES /* PI waiters blocked on a rt_mutex held by this task: */ struct rb_root_cached pi_waiters; /* Updated under owner's pi_lock and rq lock */ struct task_struct *pi_top_task; /* Deadlock detection and priority inheritance handling: */ struct rt_mutex_waiter *pi_blocked_on; #endif #ifdef CONFIG_DEBUG_MUTEXES /* Mutex deadlock detection: */ struct mutex_waiter *blocked_on; #endif #ifdef CONFIG_DEBUG_ATOMIC_SLEEP int non_block_count; #endif #ifdef CONFIG_TRACE_IRQFLAGS struct irqtrace_events irqtrace; unsigned int hardirq_threaded; u64 hardirq_chain_key; int softirqs_enabled; int softirq_context; int irq_config; #endif #ifdef CONFIG_PREEMPT_RT int softirq_disable_cnt; #endif #ifdef CONFIG_LOCKDEP # define MAX_LOCK_DEPTH 48UL u64 curr_chain_key; int lockdep_depth; unsigned int lockdep_recursion; struct held_lock held_locks[MAX_LOCK_DEPTH]; #endif #if defined(CONFIG_UBSAN) && !defined(CONFIG_UBSAN_TRAP) unsigned int in_ubsan; #endif /* Journalling filesystem info: */ void *journal_info; /* Stacked block device info: */ struct bio_list *bio_list; /* Stack plugging: */ struct blk_plug *plug; /* VM state: */ struct reclaim_state *reclaim_state; struct io_context *io_context; #ifdef CONFIG_COMPACTION struct capture_control *capture_control; #endif /* Ptrace state: */ unsigned long ptrace_message; kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; #ifdef CONFIG_PSI /* Pressure stall state */ unsigned int psi_flags; #endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; /* Accumulated virtual memory usage: */ u64 acct_vm_mem1; /* stime + utime since last update: */ u64 acct_timexpd; #endif #ifdef CONFIG_CPUSETS /* Protected by ->alloc_lock: */ nodemask_t mems_allowed; /* Sequence number to catch updates: */ seqcount_spinlock_t mems_allowed_seq; int cpuset_mem_spread_rotor; #endif #ifdef CONFIG_CGROUPS /* Control Group info protected by css_set_lock: */ struct css_set __rcu *cgroups; /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif #ifdef CONFIG_X86_CPU_RESCTRL u32 closid; u32 rmid; #endif #ifdef CONFIG_FUTEX struct robust_list_head __user *robust_list; #ifdef CONFIG_COMPAT struct compat_robust_list_head __user *compat_robust_list; #endif struct list_head pi_state_list; struct futex_pi_state *pi_state_cache; struct mutex futex_exit_mutex; unsigned int futex_state; #endif #ifdef CONFIG_PERF_EVENTS u8 perf_recursion[PERF_NR_CONTEXTS]; struct perf_event_context *perf_event_ctxp; struct mutex perf_event_mutex; struct list_head perf_event_list; #endif #ifdef CONFIG_DEBUG_PREEMPT unsigned long preempt_disable_ip; #endif #ifdef CONFIG_NUMA /* Protected by alloc_lock: */ struct mempolicy *mempolicy; short il_prev; u8 il_weight; short pref_node_fork; #endif #ifdef CONFIG_NUMA_BALANCING int numa_scan_seq; unsigned int numa_scan_period; unsigned int numa_scan_period_max; int numa_preferred_nid; unsigned long numa_migrate_retry; /* Migration stamp: */ u64 node_stamp; u64 last_task_numa_placement; u64 last_sum_exec_runtime; struct callback_head numa_work; /* * This pointer is only modified for current in syscall and * pagefault context (and for tasks being destroyed), so it can be read * from any of the following contexts: * - RCU read-side critical section * - current->numa_group from everywhere * - task's runqueue locked, task not running */ struct numa_group __rcu *numa_group; /* * numa_faults is an array split into four regions: * faults_memory, faults_cpu, faults_memory_buffer, faults_cpu_buffer * in this precise order. * * faults_memory: Exponential decaying average of faults on a per-node * basis. Scheduling placement decisions are made based on these * counts. The values remain static for the duration of a PTE scan. * faults_cpu: Track the nodes the process was running on when a NUMA * hinting fault was incurred. * faults_memory_buffer and faults_cpu_buffer: Record faults per node * during the current scan window. When the scan completes, the counts * in faults_memory and faults_cpu decay and these values are copied. */ unsigned long *numa_faults; unsigned long total_numa_faults; /* * numa_faults_locality tracks if faults recorded during the last * scan window were remote/local or failed to migrate. The task scan * period is adapted based on the locality of the faults with different * weights depending on whether they were shared or private faults */ unsigned long numa_faults_locality[3]; unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_RSEQ struct rseq __user *rseq; u32 rseq_len; u32 rseq_sig; /* * RmW on rseq_event_mask must be performed atomically * with respect to preemption. */ unsigned long rseq_event_mask; # ifdef CONFIG_DEBUG_RSEQ /* * This is a place holder to save a copy of the rseq fields for * validation of read-only fields. The struct rseq has a * variable-length array at the end, so it cannot be used * directly. Reserve a size large enough for the known fields. */ char rseq_fields[sizeof(struct rseq)]; # endif #endif #ifdef CONFIG_SCHED_MM_CID int mm_cid; /* Current cid in mm */ int last_mm_cid; /* Most recent cid in mm */ int migrate_from_cpu; int mm_cid_active; /* Whether cid bitmap is active */ struct callback_head cid_work; #endif struct tlbflush_unmap_batch tlb_ubc; /* Cache last used pipe for splice(): */ struct pipe_inode_info *splice_pipe; struct page_frag task_frag; #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info *delays; #endif #ifdef CONFIG_FAULT_INJECTION int make_it_fail; unsigned int fail_nth; #endif /* * When (nr_dirtied >= nr_dirtied_pause), it's time to call * balance_dirty_pages() for a dirty throttling pause: */ int nr_dirtied; int nr_dirtied_pause; /* Start of a write-and-pause period: */ unsigned long dirty_paused_when; #ifdef CONFIG_LATENCYTOP int latency_record_count; struct latency_record latency_record[LT_SAVECOUNT]; #endif /* * Time slack values; these are used to round up poll() and * select() etc timeout values. These are in nanoseconds. */ u64 timer_slack_ns; u64 default_timer_slack_ns; #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) unsigned int kasan_depth; #endif #ifdef CONFIG_KCSAN struct kcsan_ctx kcsan_ctx; #ifdef CONFIG_TRACE_IRQFLAGS struct irqtrace_events kcsan_save_irqtrace; #endif #ifdef CONFIG_KCSAN_WEAK_MEMORY int kcsan_stack_depth; #endif #endif #ifdef CONFIG_KMSAN struct kmsan_ctx kmsan_ctx; #endif #if IS_ENABLED(CONFIG_KUNIT) struct kunit *kunit_test; #endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack: */ int curr_ret_stack; int curr_ret_depth; /* Stack of return addresses for return function tracing: */ unsigned long *ret_stack; /* Timestamp for last schedule: */ unsigned long long ftrace_timestamp; unsigned long long ftrace_sleeptime; /* * Number of functions that haven't been traced * because of depth overrun: */ atomic_t trace_overrun; /* Pause tracing: */ atomic_t tracing_graph_pause; #endif #ifdef CONFIG_TRACING /* Bitmask and counter of trace recursion: */ unsigned long trace_recursion; #endif /* CONFIG_TRACING */ #ifdef CONFIG_KCOV /* See kernel/kcov.c for more details. */ /* Coverage collection mode enabled for this task (0 if disabled): */ unsigned int kcov_mode; /* Size of the kcov_area: */ unsigned int kcov_size; /* Buffer for coverage collection: */ void *kcov_area; /* KCOV descriptor wired with this task or NULL: */ struct kcov *kcov; /* KCOV common handle for remote coverage collection: */ u64 kcov_handle; /* KCOV sequence number: */ int kcov_sequence; /* Collect coverage from softirq context: */ unsigned int kcov_softirq; #endif #ifdef CONFIG_MEMCG_V1 struct mem_cgroup *memcg_in_oom; #endif #ifdef CONFIG_MEMCG /* Number of pages to reclaim on returning to userland: */ unsigned int memcg_nr_pages_over_high; /* Used by memcontrol for targeted memcg charge: */ struct mem_cgroup *active_memcg; /* Cache for current->cgroups->memcg->objcg lookups: */ struct obj_cgroup *objcg; #endif #ifdef CONFIG_BLK_CGROUP struct gendisk *throttle_disk; #endif #ifdef CONFIG_UPROBES struct uprobe_task *utask; #endif #if defined(CONFIG_BCACHE) || defined(CONFIG_BCACHE_MODULE) unsigned int sequential_io; unsigned int sequential_io_avg; #endif struct kmap_ctrl kmap_ctrl; #ifdef CONFIG_DEBUG_ATOMIC_SLEEP unsigned long task_state_change; # ifdef CONFIG_PREEMPT_RT unsigned long saved_state_change; # endif #endif struct rcu_head rcu; refcount_t rcu_users; int pagefault_disabled; #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; struct timer_list oom_reaper_timer; #endif #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; #endif #ifdef CONFIG_THREAD_INFO_IN_TASK /* A live task holds one reference: */ refcount_t stack_refcount; #endif #ifdef CONFIG_LIVEPATCH int patch_state; #endif #ifdef CONFIG_SECURITY /* Used by LSM modules for access restriction: */ void *security; #endif #ifdef CONFIG_BPF_SYSCALL /* Used by BPF task local storage */ struct bpf_local_storage __rcu *bpf_storage; /* Used for BPF run context */ struct bpf_run_ctx *bpf_ctx; #endif /* Used by BPF for per-TASK xdp storage */ struct bpf_net_context *bpf_net_context; #ifdef CONFIG_GCC_PLUGIN_STACKLEAK unsigned long lowest_stack; unsigned long prev_lowest_stack; #endif #ifdef CONFIG_X86_MCE void __user *mce_vaddr; __u64 mce_kflags; u64 mce_addr; __u64 mce_ripv : 1, mce_whole_page : 1, __mce_reserved : 62; struct callback_head mce_kill_me; int mce_count; #endif #ifdef CONFIG_KRETPROBES struct llist_head kretprobe_instances; #endif #ifdef CONFIG_RETHOOK struct llist_head rethooks; #endif #ifdef CONFIG_ARCH_HAS_PARANOID_L1D_FLUSH /* * If L1D flush is supported on mm context switch * then we use this callback head to queue kill work * to kill tasks that are not running on SMT disabled * cores */ struct callback_head l1d_flush_kill; #endif #ifdef CONFIG_RV /* * Per-task RV monitor. Nowadays fixed in RV_PER_TASK_MONITORS. * If we find justification for more monitors, we can think * about adding more or developing a dynamic method. So far, * none of these are justified. */ union rv_task_monitor rv[RV_PER_TASK_MONITORS]; #endif #ifdef CONFIG_USER_EVENTS struct user_event_mm *user_event_mm; #endif /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. */ randomized_struct_fields_end /* CPU-specific state of this task: */ struct thread_struct thread; /* * WARNING: on x86, 'thread_struct' contains a variable-sized * structure. It *MUST* be at the end of 'task_struct'. * * Do not put anything below here! */ }; #define TASK_REPORT_IDLE (TASK_REPORT + 1) #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1) static inline unsigned int __task_state_index(unsigned int tsk_state, unsigned int tsk_exit_state) { unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT; BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX); if ((tsk_state & TASK_IDLE) == TASK_IDLE) state = TASK_REPORT_IDLE; /* * We're lying here, but rather than expose a completely new task state * to userspace, we can make this appear as if the task has gone through * a regular rt_mutex_lock() call. * Report frozen tasks as uninterruptible. */ if ((tsk_state & TASK_RTLOCK_WAIT) || (tsk_state & TASK_FROZEN)) state = TASK_UNINTERRUPTIBLE; return fls(state); } static inline unsigned int task_state_index(struct task_struct *tsk) { return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state); } static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; BUILD_BUG_ON(TASK_REPORT_MAX * 2 != 1 << (sizeof(state_char) - 1)); return state_char[state]; } static inline char task_state_to_char(struct task_struct *tsk) { return task_index_to_char(task_state_index(tsk)); } extern struct pid *cad_pid; /* * Per process flags */ #define PF_VCPU 0x00000001 /* I'm a virtual CPU */ #define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* Getting shut down */ #define PF_POSTCOREDUMP 0x00000008 /* Coredumps should ignore this task */ #define PF_IO_WORKER 0x00000010 /* Task is an IO worker */ #define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* Forked but didn't exec */ #define PF_MCE_PROCESS 0x00000080 /* Process policy on mce errors */ #define PF_SUPERPRIV 0x00000100 /* Used super-user privileges */ #define PF_DUMPCORE 0x00000200 /* Dumped core */ #define PF_SIGNALED 0x00000400 /* Killed by a signal */ #define PF_MEMALLOC 0x00000800 /* Allocating memory to free memory. See memalloc_noreclaim_save() */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ #define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ #define PF__HOLE__00010000 0x00010000 #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */ #define PF_LOCAL_THROTTLE 0x00100000 /* Throttle writes only against the bdi I write to, * I am cleaning dirty pages from some other bdi. */ #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF__HOLE__00800000 0x00800000 #define PF__HOLE__01000000 0x01000000 #define PF__HOLE__02000000 0x02000000 #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_PIN 0x10000000 /* Allocations constrained to zones which allow long term pinning. * See memalloc_pin_save() */ #define PF_BLOCK_TS 0x20000000 /* plug has ts that needs updating */ #define PF__HOLE__40000000 0x40000000 #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ /* * Only the _current_ task can read/write to tsk->flags, but other * tasks can access tsk->flags in readonly mode for example * with tsk_used_math (like during threaded core dumping). * There is however an exception to this rule during ptrace * or during fork: the ptracer task is allowed to write to the * child->flags of its traced child (same goes for fork, the parent * can write to the child->flags), because we're guaranteed the * child is not running and in turn not changing child->flags * at the same time the parent does it. */ #define clear_stopped_child_used_math(child) do { (child)->flags &= ~PF_USED_MATH; } while (0) #define set_stopped_child_used_math(child) do { (child)->flags |= PF_USED_MATH; } while (0) #define clear_used_math() clear_stopped_child_used_math(current) #define set_used_math() set_stopped_child_used_math(current) #define conditional_stopped_child_used_math(condition, child) \ do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= (condition) ? PF_USED_MATH : 0; } while (0) #define conditional_used_math(condition) conditional_stopped_child_used_math(condition, current) #define copy_to_stopped_child_used_math(child) \ do { (child)->flags &= ~PF_USED_MATH, (child)->flags |= current->flags & PF_USED_MATH; } while (0) /* NOTE: this will return 0 or PF_USED_MATH, it will never return 1 */ #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) static __always_inline bool is_percpu_thread(void) { #ifdef CONFIG_SMP return (current->flags & PF_NO_SETAFFINITY) && (current->nr_cpus_allowed == 1); #else return true; #endif } /* Per-process atomic flags. */ #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ #define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ #define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ #define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ #define PFA_SPEC_SSB_NOEXEC 7 /* Speculative Store Bypass clear on execve() */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ { return test_bit(PFA_##name, &p->atomic_flags); } #define TASK_PFA_SET(name, func) \ static inline void task_set_##func(struct task_struct *p) \ { set_bit(PFA_##name, &p->atomic_flags); } #define TASK_PFA_CLEAR(name, func) \ static inline void task_clear_##func(struct task_struct *p) \ { clear_bit(PFA_##name, &p->atomic_flags); } TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs) TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs) TASK_PFA_TEST(SPREAD_PAGE, spread_page) TASK_PFA_SET(SPREAD_PAGE, spread_page) TASK_PFA_CLEAR(SPREAD_PAGE, spread_page) TASK_PFA_TEST(SPREAD_SLAB, spread_slab) TASK_PFA_SET(SPREAD_SLAB, spread_slab) TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) TASK_PFA_TEST(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_SET(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_TEST(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_SET(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_CLEAR(SPEC_SSB_NOEXEC, spec_ssb_noexec) TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable) TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { current->flags &= ~flags; current->flags |= orig_flags & flags; } extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial); extern int task_can_attach(struct task_struct *p); extern int dl_bw_alloc(int cpu, u64 dl_bw); extern void dl_bw_free(int cpu, u64 dl_bw); #ifdef CONFIG_SMP /* do_set_cpus_allowed() - consider using set_cpus_allowed_ptr() instead */ extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); /** * set_cpus_allowed_ptr - set CPU affinity mask of a task * @p: the task * @new_mask: CPU affinity mask * * Return: zero if successful, or a negative error code */ extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask); extern int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node); extern void release_user_cpus_ptr(struct task_struct *p); extern int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask); extern void force_compatible_cpus_allowed_ptr(struct task_struct *p); extern void relax_compatible_cpus_allowed_ptr(struct task_struct *p); #else static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) { } static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { /* Opencoded cpumask_test_cpu(0, new_mask) to avoid dependency on cpumask.h */ if ((*cpumask_bits(new_mask) & 1) == 0) return -EINVAL; return 0; } static inline int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node) { if (src->user_cpus_ptr) return -EINVAL; return 0; } static inline void release_user_cpus_ptr(struct task_struct *p) { WARN_ON(p->user_cpus_ptr); } static inline int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask) { return 0; } #endif extern int yield_to(struct task_struct *p, bool preempt); extern void set_user_nice(struct task_struct *p, long nice); extern int task_prio(const struct task_struct *p); /** * task_nice - return the nice value of a given task. * @p: the task in question. * * Return: The nice value [ -20 ... 0 ... 19 ]. */ static inline int task_nice(const struct task_struct *p) { return PRIO_TO_NICE((p)->static_prio); } extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); extern int available_idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern void sched_set_fifo(struct task_struct *p); extern void sched_set_fifo_low(struct task_struct *p); extern void sched_set_normal(struct task_struct *p, int nice); extern int sched_setattr(struct task_struct *, const struct sched_attr *); extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *); extern struct task_struct *idle_task(int cpu); /** * is_idle_task - is the specified task an idle task? * @p: the task in question. * * Return: 1 if @p is an idle task. 0 otherwise. */ static __always_inline bool is_idle_task(const struct task_struct *p) { return !!(p->flags & PF_IDLE); } extern struct task_struct *curr_task(int cpu); extern void ia64_set_curr_task(int cpu, struct task_struct *p); void yield(void); union thread_union { struct task_struct task; #ifndef CONFIG_THREAD_INFO_IN_TASK struct thread_info thread_info; #endif unsigned long stack[THREAD_SIZE/sizeof(long)]; }; #ifndef CONFIG_THREAD_INFO_IN_TASK extern struct thread_info init_thread_info; #endif extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)]; #ifdef CONFIG_THREAD_INFO_IN_TASK # define task_thread_info(task) (&(task)->thread_info) #else # define task_thread_info(task) ((struct thread_info *)(task)->stack) #endif /* * find a task by one of its numerical ids * * find_task_by_pid_ns(): * finds a task by its pid in the specified namespace * find_task_by_vpid(): * finds a task by its virtual pid * * see also find_vpid() etc in include/linux/pid.h */ extern struct task_struct *find_task_by_vpid(pid_t nr); extern struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns); /* * find a task by its virtual pid and get the task struct */ extern struct task_struct *find_get_task_by_vpid(pid_t nr); extern int wake_up_state(struct task_struct *tsk, unsigned int state); extern int wake_up_process(struct task_struct *tsk); extern void wake_up_new_task(struct task_struct *tsk); #ifdef CONFIG_SMP extern void kick_process(struct task_struct *tsk); #else static inline void kick_process(struct task_struct *tsk) { } #endif extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec); #define set_task_comm(tsk, from) ({ \ BUILD_BUG_ON(sizeof(from) != TASK_COMM_LEN); \ __set_task_comm(tsk, from, false); \ }) /* * - Why not use task_lock()? * User space can randomly change their names anyway, so locking for readers * doesn't make sense. For writers, locking is probably necessary, as a race * condition could lead to long-term mixed results. * The strscpy_pad() in __set_task_comm() can ensure that the task comm is * always NUL-terminated and zero-padded. Therefore the race condition between * reader and writer is not an issue. * * - BUILD_BUG_ON() can help prevent the buf from being truncated. * Since the callers don't perform any return value checks, this safeguard is * necessary. */ #define get_task_comm(buf, tsk) ({ \ BUILD_BUG_ON(sizeof(buf) < TASK_COMM_LEN); \ strscpy_pad(buf, (tsk)->comm); \ buf; \ }) #ifdef CONFIG_SMP static __always_inline void scheduler_ipi(void) { /* * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting * TIF_NEED_RESCHED remotely (for the first time) will also send * this IPI. */ preempt_fold_need_resched(); } #else static inline void scheduler_ipi(void) { } #endif extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state); /* * Set thread flags in other task's structures. * See asm/thread_info.h for TIF_xxxx flags available: */ static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag) { set_ti_thread_flag(task_thread_info(tsk), flag); } static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag) { clear_ti_thread_flag(task_thread_info(tsk), flag); } static inline void update_tsk_thread_flag(struct task_struct *tsk, int flag, bool value) { update_ti_thread_flag(task_thread_info(tsk), flag, value); } static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_set_ti_thread_flag(task_thread_info(tsk), flag); } static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag); } static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_ti_thread_flag(task_thread_info(tsk), flag); } static inline void set_tsk_need_resched(struct task_struct *tsk) { set_tsk_thread_flag(tsk,TIF_NEED_RESCHED); } static inline void clear_tsk_need_resched(struct task_struct *tsk) { atomic_long_andnot(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY, (atomic_long_t *)&task_thread_info(tsk)->flags); } static inline int test_tsk_need_resched(struct task_struct *tsk) { return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); } /* * cond_resched() and cond_resched_lock(): latency reduction via * explicit rescheduling in places that are safe. The return * value indicates whether a reschedule was done in fact. * cond_resched_lock() will drop the spinlock before scheduling, */ #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) extern int __cond_resched(void); #if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) void sched_dynamic_klp_enable(void); void sched_dynamic_klp_disable(void); DECLARE_STATIC_CALL(cond_resched, __cond_resched); static __always_inline int _cond_resched(void) { return static_call_mod(cond_resched)(); } #elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) extern int dynamic_cond_resched(void); static __always_inline int _cond_resched(void) { return dynamic_cond_resched(); } #else /* !CONFIG_PREEMPTION */ static inline int _cond_resched(void) { klp_sched_try_switch(); return __cond_resched(); } #endif /* PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ #else /* CONFIG_PREEMPTION && !CONFIG_PREEMPT_DYNAMIC */ static inline int _cond_resched(void) { klp_sched_try_switch(); return 0; } #endif /* !CONFIG_PREEMPTION || CONFIG_PREEMPT_DYNAMIC */ #define cond_resched() ({ \ __might_resched(__FILE__, __LINE__, 0); \ _cond_resched(); \ }) extern int __cond_resched_lock(spinlock_t *lock); extern int __cond_resched_rwlock_read(rwlock_t *lock); extern int __cond_resched_rwlock_write(rwlock_t *lock); #define MIGHT_RESCHED_RCU_SHIFT 8 #define MIGHT_RESCHED_PREEMPT_MASK ((1U << MIGHT_RESCHED_RCU_SHIFT) - 1) #ifndef CONFIG_PREEMPT_RT /* * Non RT kernels have an elevated preempt count due to the held lock, * but are not allowed to be inside a RCU read side critical section */ # define PREEMPT_LOCK_RESCHED_OFFSETS PREEMPT_LOCK_OFFSET #else /* * spin/rw_lock() on RT implies rcu_read_lock(). The might_sleep() check in * cond_resched*lock() has to take that into account because it checks for * preempt_count() and rcu_preempt_depth(). */ # define PREEMPT_LOCK_RESCHED_OFFSETS \ (PREEMPT_LOCK_OFFSET + (1U << MIGHT_RESCHED_RCU_SHIFT)) #endif #define cond_resched_lock(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_lock(lock); \ }) #define cond_resched_rwlock_read(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_rwlock_read(lock); \ }) #define cond_resched_rwlock_write(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ __cond_resched_rwlock_write(lock); \ }) static __always_inline bool need_resched(void) { return unlikely(tif_need_resched()); } /* * Wrappers for p->thread_info->cpu access. No-op on UP. */ #ifdef CONFIG_SMP static inline unsigned int task_cpu(const struct task_struct *p) { return READ_ONCE(task_thread_info(p)->cpu); } extern void set_task_cpu(struct task_struct *p, unsigned int cpu); #else static inline unsigned int task_cpu(const struct task_struct *p) { return 0; } static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) { } #endif /* CONFIG_SMP */ static inline bool task_is_runnable(struct task_struct *p) { return p->on_rq && !p->se.sched_delayed; } extern bool sched_task_on_rq(struct task_struct *p); extern unsigned long get_wchan(struct task_struct *p); extern struct task_struct *cpu_curr_snapshot(int cpu); #include <linux/spinlock.h> /* * In order to reduce various lock holder preemption latencies provide an * interface to see if a vCPU is currently running or not. * * This allows us to terminate optimistic spin loops and block, analogous to * the native optimistic spin heuristic of testing if the lock owner task is * running or not. */ #ifndef vcpu_is_preempted static inline bool vcpu_is_preempted(int cpu) { return false; } #endif extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask); extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #ifndef TASK_SIZE_OF #define TASK_SIZE_OF(tsk) TASK_SIZE #endif #ifdef CONFIG_SMP static inline bool owner_on_cpu(struct task_struct *owner) { /* * As lock holder preemption issue, we both skip spinning if * task is not on cpu or its cpu is preempted */ return READ_ONCE(owner->on_cpu) && !vcpu_is_preempted(task_cpu(owner)); } /* Returns effective CPU energy utilization, as seen by the scheduler */ unsigned long sched_cpu_util(int cpu); #endif /* CONFIG_SMP */ #ifdef CONFIG_SCHED_CORE extern void sched_core_free(struct task_struct *tsk); extern void sched_core_fork(struct task_struct *p); extern int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type, unsigned long uaddr); extern int sched_core_idle_cpu(int cpu); #else static inline void sched_core_free(struct task_struct *tsk) { } static inline void sched_core_fork(struct task_struct *p) { } static inline int sched_core_idle_cpu(int cpu) { return idle_cpu(cpu); } #endif extern void sched_set_stop_task(int cpu, struct task_struct *stop); #ifdef CONFIG_MEM_ALLOC_PROFILING static __always_inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag) { swap(current->alloc_tag, tag); return tag; } static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct alloc_tag *old) { #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG WARN(current->alloc_tag != tag, "current->alloc_tag was changed:\n"); #endif current->alloc_tag = old; } #else #define alloc_tag_save(_tag) NULL #define alloc_tag_restore(_tag, _old) do {} while (0) #endif #endif |
| 6 1 5 2 6 26 20 1 25 21 1 20 20 20 6 1 5 1 4 2 3 5 4 3 4 1 3 2 1 2 2 4 1 1 8 8 8 8 8 8 8 8 8 8 12 26 14 2 3 3 3 1 3 1 3 3 1 3 3 3 3 8 6 2 1 3 8 6 8 2 1 3 21 21 | 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 | // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) /* Copyright (C) 2019 Netronome Systems, Inc. */ #include <linux/if_arp.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/mpls.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <linux/tc_act/tc_mpls.h> #include <net/mpls.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/tc_act/tc_mpls.h> #include <net/tc_wrapper.h> static struct tc_action_ops act_mpls_ops; #define ACT_MPLS_TTL_DEFAULT 255 static __be32 tcf_mpls_get_lse(struct mpls_shim_hdr *lse, struct tcf_mpls_params *p, bool set_bos) { u32 new_lse = 0; if (lse) new_lse = be32_to_cpu(lse->label_stack_entry); if (p->tcfm_label != ACT_MPLS_LABEL_NOT_SET) { new_lse &= ~MPLS_LS_LABEL_MASK; new_lse |= p->tcfm_label << MPLS_LS_LABEL_SHIFT; } if (p->tcfm_ttl) { new_lse &= ~MPLS_LS_TTL_MASK; new_lse |= p->tcfm_ttl << MPLS_LS_TTL_SHIFT; } if (p->tcfm_tc != ACT_MPLS_TC_NOT_SET) { new_lse &= ~MPLS_LS_TC_MASK; new_lse |= p->tcfm_tc << MPLS_LS_TC_SHIFT; } if (p->tcfm_bos != ACT_MPLS_BOS_NOT_SET) { new_lse &= ~MPLS_LS_S_MASK; new_lse |= p->tcfm_bos << MPLS_LS_S_SHIFT; } else if (set_bos) { new_lse |= 1 << MPLS_LS_S_SHIFT; } return cpu_to_be32(new_lse); } TC_INDIRECT_SCOPE int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_mpls *m = to_mpls(a); struct tcf_mpls_params *p; __be32 new_lse; int ret, mac_len; tcf_lastuse_update(&m->tcf_tm); bstats_update(this_cpu_ptr(m->common.cpu_bstats), skb); /* Ensure 'data' points at mac_header prior calling mpls manipulating * functions. */ if (skb_at_tc_ingress(skb)) { skb_push_rcsum(skb, skb->mac_len); mac_len = skb->mac_len; } else { mac_len = skb_network_offset(skb); } ret = READ_ONCE(m->tcf_action); p = rcu_dereference_bh(m->mpls_p); switch (p->tcfm_action) { case TCA_MPLS_ACT_POP: if (skb_mpls_pop(skb, p->tcfm_proto, mac_len, skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; break; case TCA_MPLS_ACT_PUSH: new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb_protocol(skb, true))); if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len, skb->dev && skb->dev->type == ARPHRD_ETHER)) goto drop; break; case TCA_MPLS_ACT_MAC_PUSH: if (skb_vlan_tag_present(skb)) { if (__vlan_insert_inner_tag(skb, skb->vlan_proto, skb_vlan_tag_get(skb), ETH_HLEN) < 0) goto drop; skb->protocol = skb->vlan_proto; __vlan_hwaccel_clear_tag(skb); } new_lse = tcf_mpls_get_lse(NULL, p, mac_len || !eth_p_mpls(skb->protocol)); if (skb_mpls_push(skb, new_lse, p->tcfm_proto, 0, false)) goto drop; break; case TCA_MPLS_ACT_MODIFY: if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN)) goto drop; new_lse = tcf_mpls_get_lse(mpls_hdr(skb), p, false); if (skb_mpls_update_lse(skb, new_lse)) goto drop; break; case TCA_MPLS_ACT_DEC_TTL: if (skb_mpls_dec_ttl(skb)) goto drop; break; } if (skb_at_tc_ingress(skb)) skb_pull_rcsum(skb, skb->mac_len); return ret; drop: qstats_drop_inc(this_cpu_ptr(m->common.cpu_qstats)); return TC_ACT_SHOT; } static int valid_label(const struct nlattr *attr, struct netlink_ext_ack *extack) { const u32 *label = nla_data(attr); if (nla_len(attr) != sizeof(*label)) { NL_SET_ERR_MSG_MOD(extack, "Invalid MPLS label length"); return -EINVAL; } if (*label & ~MPLS_LABEL_MASK || *label == MPLS_LABEL_IMPLNULL) { NL_SET_ERR_MSG_MOD(extack, "MPLS label out of range"); return -EINVAL; } return 0; } static const struct nla_policy mpls_policy[TCA_MPLS_MAX + 1] = { [TCA_MPLS_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_mpls)), [TCA_MPLS_PROTO] = { .type = NLA_U16 }, [TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_BINARY, valid_label), [TCA_MPLS_TC] = NLA_POLICY_RANGE(NLA_U8, 0, 7), [TCA_MPLS_TTL] = NLA_POLICY_MIN(NLA_U8, 1), [TCA_MPLS_BOS] = NLA_POLICY_RANGE(NLA_U8, 0, 1), }; static int tcf_mpls_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_mpls_ops.net_id); bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_MPLS_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tcf_mpls_params *p; struct tc_mpls *parm; bool exists = false; struct tcf_mpls *m; int ret = 0, err; u8 mpls_ttl = 0; u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Missing netlink attributes"); return -EINVAL; } err = nla_parse_nested(tb, TCA_MPLS_MAX, nla, mpls_policy, extack); if (err < 0) return err; if (!tb[TCA_MPLS_PARMS]) { NL_SET_ERR_MSG_MOD(extack, "No MPLS params"); return -EINVAL; } parm = nla_data(tb[TCA_MPLS_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return ACT_P_BOUND; if (!exists) { ret = tcf_idr_create(tn, index, est, a, &act_mpls_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } /* Verify parameters against action type. */ switch (parm->m_action) { case TCA_MPLS_ACT_POP: if (!tb[TCA_MPLS_PROTO]) { NL_SET_ERR_MSG_MOD(extack, "Protocol must be set for MPLS pop"); err = -EINVAL; goto release_idr; } if (!eth_proto_is_802_3(nla_get_be16(tb[TCA_MPLS_PROTO]))) { NL_SET_ERR_MSG_MOD(extack, "Invalid protocol type for MPLS pop"); err = -EINVAL; goto release_idr; } if (tb[TCA_MPLS_LABEL] || tb[TCA_MPLS_TTL] || tb[TCA_MPLS_TC] || tb[TCA_MPLS_BOS]) { NL_SET_ERR_MSG_MOD(extack, "Label, TTL, TC or BOS cannot be used with MPLS pop"); err = -EINVAL; goto release_idr; } break; case TCA_MPLS_ACT_DEC_TTL: if (tb[TCA_MPLS_PROTO] || tb[TCA_MPLS_LABEL] || tb[TCA_MPLS_TTL] || tb[TCA_MPLS_TC] || tb[TCA_MPLS_BOS]) { NL_SET_ERR_MSG_MOD(extack, "Label, TTL, TC, BOS or protocol cannot be used with MPLS dec_ttl"); err = -EINVAL; goto release_idr; } break; case TCA_MPLS_ACT_PUSH: case TCA_MPLS_ACT_MAC_PUSH: if (!tb[TCA_MPLS_LABEL]) { NL_SET_ERR_MSG_MOD(extack, "Label is required for MPLS push"); err = -EINVAL; goto release_idr; } if (tb[TCA_MPLS_PROTO] && !eth_p_mpls(nla_get_be16(tb[TCA_MPLS_PROTO]))) { NL_SET_ERR_MSG_MOD(extack, "Protocol must be an MPLS type for MPLS push"); err = -EPROTONOSUPPORT; goto release_idr; } /* Push needs a TTL - if not specified, set a default value. */ if (!tb[TCA_MPLS_TTL]) { #if IS_ENABLED(CONFIG_MPLS) mpls_ttl = net->mpls.default_ttl ? net->mpls.default_ttl : ACT_MPLS_TTL_DEFAULT; #else mpls_ttl = ACT_MPLS_TTL_DEFAULT; #endif } break; case TCA_MPLS_ACT_MODIFY: if (tb[TCA_MPLS_PROTO]) { NL_SET_ERR_MSG_MOD(extack, "Protocol cannot be used with MPLS modify"); err = -EINVAL; goto release_idr; } break; default: NL_SET_ERR_MSG_MOD(extack, "Unknown MPLS action"); err = -EINVAL; goto release_idr; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; m = to_mpls(*a); p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) { err = -ENOMEM; goto put_chain; } p->tcfm_action = parm->m_action; p->tcfm_label = nla_get_u32_default(tb[TCA_MPLS_LABEL], ACT_MPLS_LABEL_NOT_SET); p->tcfm_tc = nla_get_u8_default(tb[TCA_MPLS_TC], ACT_MPLS_TC_NOT_SET); p->tcfm_ttl = nla_get_u8_default(tb[TCA_MPLS_TTL], mpls_ttl); p->tcfm_bos = nla_get_u8_default(tb[TCA_MPLS_BOS], ACT_MPLS_BOS_NOT_SET); p->tcfm_proto = nla_get_be16_default(tb[TCA_MPLS_PROTO], htons(ETH_P_MPLS_UC)); spin_lock_bh(&m->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); p = rcu_replace_pointer(m->mpls_p, p, lockdep_is_held(&m->tcf_lock)); spin_unlock_bh(&m->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (p) kfree_rcu(p, rcu); return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static void tcf_mpls_cleanup(struct tc_action *a) { struct tcf_mpls *m = to_mpls(a); struct tcf_mpls_params *p; p = rcu_dereference_protected(m->mpls_p, 1); if (p) kfree_rcu(p, rcu); } static int tcf_mpls_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_mpls *m = to_mpls(a); struct tcf_mpls_params *p; struct tc_mpls opt = { .index = m->tcf_index, .refcnt = refcount_read(&m->tcf_refcnt) - ref, .bindcnt = atomic_read(&m->tcf_bindcnt) - bind, }; struct tcf_t t; spin_lock_bh(&m->tcf_lock); opt.action = m->tcf_action; p = rcu_dereference_protected(m->mpls_p, lockdep_is_held(&m->tcf_lock)); opt.m_action = p->tcfm_action; if (nla_put(skb, TCA_MPLS_PARMS, sizeof(opt), &opt)) goto nla_put_failure; if (p->tcfm_label != ACT_MPLS_LABEL_NOT_SET && nla_put_u32(skb, TCA_MPLS_LABEL, p->tcfm_label)) goto nla_put_failure; if (p->tcfm_tc != ACT_MPLS_TC_NOT_SET && nla_put_u8(skb, TCA_MPLS_TC, p->tcfm_tc)) goto nla_put_failure; if (p->tcfm_ttl && nla_put_u8(skb, TCA_MPLS_TTL, p->tcfm_ttl)) goto nla_put_failure; if (p->tcfm_bos != ACT_MPLS_BOS_NOT_SET && nla_put_u8(skb, TCA_MPLS_BOS, p->tcfm_bos)) goto nla_put_failure; if (nla_put_be16(skb, TCA_MPLS_PROTO, p->tcfm_proto)) goto nla_put_failure; tcf_tm_dump(&t, &m->tcf_tm); if (nla_put_64bit(skb, TCA_MPLS_TM, sizeof(t), &t, TCA_MPLS_PAD)) goto nla_put_failure; spin_unlock_bh(&m->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&m->tcf_lock); nlmsg_trim(skb, b); return -EMSGSIZE; } static int tcf_mpls_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; switch (tcf_mpls_action(act)) { case TCA_MPLS_ACT_PUSH: entry->id = FLOW_ACTION_MPLS_PUSH; entry->mpls_push.proto = tcf_mpls_proto(act); entry->mpls_push.label = tcf_mpls_label(act); entry->mpls_push.tc = tcf_mpls_tc(act); entry->mpls_push.bos = tcf_mpls_bos(act); entry->mpls_push.ttl = tcf_mpls_ttl(act); break; case TCA_MPLS_ACT_POP: entry->id = FLOW_ACTION_MPLS_POP; entry->mpls_pop.proto = tcf_mpls_proto(act); break; case TCA_MPLS_ACT_MODIFY: entry->id = FLOW_ACTION_MPLS_MANGLE; entry->mpls_mangle.label = tcf_mpls_label(act); entry->mpls_mangle.tc = tcf_mpls_tc(act); entry->mpls_mangle.bos = tcf_mpls_bos(act); entry->mpls_mangle.ttl = tcf_mpls_ttl(act); break; case TCA_MPLS_ACT_DEC_TTL: NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"dec_ttl\" option is used"); return -EOPNOTSUPP; case TCA_MPLS_ACT_MAC_PUSH: NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"mac_push\" option is used"); return -EOPNOTSUPP; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported MPLS mode offload"); return -EOPNOTSUPP; } *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; switch (tcf_mpls_action(act)) { case TCA_MPLS_ACT_PUSH: fl_action->id = FLOW_ACTION_MPLS_PUSH; break; case TCA_MPLS_ACT_POP: fl_action->id = FLOW_ACTION_MPLS_POP; break; case TCA_MPLS_ACT_MODIFY: fl_action->id = FLOW_ACTION_MPLS_MANGLE; break; default: return -EOPNOTSUPP; } } return 0; } static struct tc_action_ops act_mpls_ops = { .kind = "mpls", .id = TCA_ID_MPLS, .owner = THIS_MODULE, .act = tcf_mpls_act, .dump = tcf_mpls_dump, .init = tcf_mpls_init, .cleanup = tcf_mpls_cleanup, .offload_act_setup = tcf_mpls_offload_act_setup, .size = sizeof(struct tcf_mpls), }; MODULE_ALIAS_NET_ACT("mpls"); static __net_init int mpls_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_mpls_ops.net_id); return tc_action_net_init(net, tn, &act_mpls_ops); } static void __net_exit mpls_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_mpls_ops.net_id); } static struct pernet_operations mpls_net_ops = { .init = mpls_init_net, .exit_batch = mpls_exit_net, .id = &act_mpls_ops.net_id, .size = sizeof(struct tc_action_net), }; static int __init mpls_init_module(void) { return tcf_register_action(&act_mpls_ops, &mpls_net_ops); } static void __exit mpls_cleanup_module(void) { tcf_unregister_action(&act_mpls_ops, &mpls_net_ops); } module_init(mpls_init_module); module_exit(mpls_cleanup_module); MODULE_SOFTDEP("post: mpls_gso"); MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MPLS manipulation actions"); |
| 7 4 6 5 4 4 1 3 3 2 2 2 1 2 7 1 1 1 1 1 2 1 21 21 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_connmark.c netfilter connmark retriever action * skb mark is over-written * * Copyright (c) 2011 Felix Fietkau <nbd@openwrt.org> */ #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/pkt_cls.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/act_api.h> #include <net/pkt_cls.h> #include <uapi/linux/tc_act/tc_connmark.h> #include <net/tc_act/tc_connmark.h> #include <net/tc_wrapper.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_zones.h> static struct tc_action_ops act_connmark_ops; TC_INDIRECT_SCOPE int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { const struct nf_conntrack_tuple_hash *thash; struct nf_conntrack_tuple tuple; enum ip_conntrack_info ctinfo; struct tcf_connmark_info *ca = to_connmark(a); struct tcf_connmark_parms *parms; struct nf_conntrack_zone zone; struct nf_conn *c; int proto; tcf_lastuse_update(&ca->tcf_tm); tcf_action_update_bstats(&ca->common, skb); parms = rcu_dereference_bh(ca->parms); switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): if (skb->len < sizeof(struct iphdr)) goto out; proto = NFPROTO_IPV4; break; case htons(ETH_P_IPV6): if (skb->len < sizeof(struct ipv6hdr)) goto out; proto = NFPROTO_IPV6; break; default: goto out; } c = nf_ct_get(skb, &ctinfo); if (c) { skb->mark = READ_ONCE(c->mark); goto count; } if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, parms->net, &tuple)) goto out; zone.id = parms->zone; zone.dir = NF_CT_DEFAULT_ZONE_DIR; thash = nf_conntrack_find_get(parms->net, &zone, &tuple); if (!thash) goto out; c = nf_ct_tuplehash_to_ctrack(thash); skb->mark = READ_ONCE(c->mark); nf_ct_put(c); count: /* using overlimits stats to count how many packets marked */ tcf_action_inc_overlimit_qstats(&ca->common); out: return READ_ONCE(ca->tcf_action); } static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = { [TCA_CONNMARK_PARMS] = { .len = sizeof(struct tc_connmark) }, }; static int tcf_connmark_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_connmark_ops.net_id); struct tcf_connmark_parms *nparms, *oparms; struct nlattr *tb[TCA_CONNMARK_MAX + 1]; bool bind = flags & TCA_ACT_FLAGS_BIND; struct tcf_chain *goto_ch = NULL; struct tcf_connmark_info *ci; struct tc_connmark *parm; int ret = 0, err; u32 index; if (!nla) return -EINVAL; ret = nla_parse_nested_deprecated(tb, TCA_CONNMARK_MAX, nla, connmark_policy, NULL); if (ret < 0) return ret; if (!tb[TCA_CONNMARK_PARMS]) return -EINVAL; nparms = kzalloc(sizeof(*nparms), GFP_KERNEL); if (!nparms) return -ENOMEM; parm = nla_data(tb[TCA_CONNMARK_PARMS]); index = parm->index; ret = tcf_idr_check_alloc(tn, &index, a, bind); if (!ret) { ret = tcf_idr_create_from_flags(tn, index, est, a, &act_connmark_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); err = ret; goto out_free; } ci = to_connmark(*a); nparms->net = net; nparms->zone = parm->zone; ret = ACT_P_CREATED; } else if (ret > 0) { ci = to_connmark(*a); if (bind) { err = ACT_P_BOUND; goto out_free; } if (!(flags & TCA_ACT_FLAGS_REPLACE)) { err = -EEXIST; goto release_idr; } nparms->net = rtnl_dereference(ci->parms)->net; nparms->zone = parm->zone; ret = 0; } else { err = ret; goto out_free; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; spin_lock_bh(&ci->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); oparms = rcu_replace_pointer(ci->parms, nparms, lockdep_is_held(&ci->tcf_lock)); spin_unlock_bh(&ci->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (oparms) kfree_rcu(oparms, rcu); return ret; release_idr: tcf_idr_release(*a, bind); out_free: kfree(nparms); return err; } static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_connmark_info *ci = to_connmark(a); struct tc_connmark opt = { .index = ci->tcf_index, .refcnt = refcount_read(&ci->tcf_refcnt) - ref, .bindcnt = atomic_read(&ci->tcf_bindcnt) - bind, }; struct tcf_connmark_parms *parms; struct tcf_t t; spin_lock_bh(&ci->tcf_lock); parms = rcu_dereference_protected(ci->parms, lockdep_is_held(&ci->tcf_lock)); opt.action = ci->tcf_action; opt.zone = parms->zone; if (nla_put(skb, TCA_CONNMARK_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &ci->tcf_tm); if (nla_put_64bit(skb, TCA_CONNMARK_TM, sizeof(t), &t, TCA_CONNMARK_PAD)) goto nla_put_failure; spin_unlock_bh(&ci->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&ci->tcf_lock); nlmsg_trim(skb, b); return -1; } static void tcf_connmark_cleanup(struct tc_action *a) { struct tcf_connmark_info *ci = to_connmark(a); struct tcf_connmark_parms *parms; parms = rcu_dereference_protected(ci->parms, 1); if (parms) kfree_rcu(parms, rcu); } static struct tc_action_ops act_connmark_ops = { .kind = "connmark", .id = TCA_ID_CONNMARK, .owner = THIS_MODULE, .act = tcf_connmark_act, .dump = tcf_connmark_dump, .init = tcf_connmark_init, .cleanup = tcf_connmark_cleanup, .size = sizeof(struct tcf_connmark_info), }; MODULE_ALIAS_NET_ACT("connmark"); static __net_init int connmark_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_connmark_ops.net_id); return tc_action_net_init(net, tn, &act_connmark_ops); } static void __net_exit connmark_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_connmark_ops.net_id); } static struct pernet_operations connmark_net_ops = { .init = connmark_init_net, .exit_batch = connmark_exit_net, .id = &act_connmark_ops.net_id, .size = sizeof(struct tc_action_net), }; static int __init connmark_init_module(void) { return tcf_register_action(&act_connmark_ops, &connmark_net_ops); } static void __exit connmark_cleanup_module(void) { tcf_unregister_action(&act_connmark_ops, &connmark_net_ops); } module_init(connmark_init_module); module_exit(connmark_cleanup_module); MODULE_AUTHOR("Felix Fietkau <nbd@openwrt.org>"); MODULE_DESCRIPTION("Connection tracking mark restoring"); MODULE_LICENSE("GPL"); |
| 2 2 2 2 2 1 151 1 1 2 4 3 2 1 3 3 3 207 85 78 5 5 1 5 4 5 5 31 28 33 33 33 1 31 31 31 14 1 32 32 3 2 1 32 5 32 31 3 3 1 30 32 2 1 32 31 32 24 6 5 5 5 2 1 3 2 1 2 1 1 10 138 66 143 143 144 142 143 1 144 141 31 141 92 93 40 1 142 141 140 134 141 141 1 1 1 140 137 9 9 9 16 16 16 16 16 5 16 14 9 7 6 1 7 6 5 4 3 3 1 9 7 6 5 4 4 16 16 7 301 304 302 98 302 304 130 130 130 113 130 163 164 99 70 6 4 6 13 1 1 1 1 12 130 124 124 126 126 110 108 125 125 125 4 1 125 115 115 123 233 35 24 25 127 13 12 1 205 19 234 98 97 54 42 184 183 57 56 166 30 13 17 143 5 140 142 142 142 124 82 83 68 123 122 50 122 122 120 6 124 91 123 103 103 103 102 103 18 103 1 1 103 103 103 103 103 103 103 22 9 8 10 2 10 10 4 10 9 12 12 12 4 4 12 12 12 12 123 123 123 72 16 75 53 50 49 50 61 59 60 44 108 86 86 132 11 132 61 122 5 122 76 2 232 1 1 1 1 7 4 4 3 2 3 3 1 1 3 1 1 2 1 1 1 62 29 12 6 3 58 34 22 21 29 60 26 61 33 33 34 30 30 30 3 34 16 15 12 11 4 2 10 2 10 10 10 10 2 2 8 8 7 15 10 16 4 4 4 4 4 4 4 4 5 1 4 5 4 4 2 5 7 7 7 7 4 3 3 4 9 8 8 8 5 2 9 3 7 7 7 5 5 6 7 6 6 1 2 1 1 3 4 4 4 3 3 2 7 6 4 7 8 7 1 7 8 1 1 2 2 1 1 1 9 1 1 1 1 22 22 22 21 1 21 20 20 4 11 8 22 10 8 7 6 8 3 7 7 1 1 7 7 7 1 7 7 6 5 5 2 2 2 2 7 1 8 8 8 8 8 5 1 3 8 7 7 1 4 1 1 1 7 2 5 7 2 1 1 7 11 23 23 23 23 59 58 1 58 51 12 5 3 34 39 7 40 39 3 1 1 39 39 29 29 29 6 2 32 30 13 13 13 13 13 23 22 1 21 15 8 8 1 18 18 55 16 1 1 1 23 6 2 1 1 22 22 14 22 23 1 22 4 19 23 24 1 1 24 4 23 18 17 16 5 4 26 37 9 3 59 4 55 3 3 1 54 51 5 4 5 2 56 1 337 335 174 174 10 195 45 161 193 127 337 110 335 74 54 58 55 54 54 1 1 1 7 2 7 2 7 1 7 125 15 119 4 9 117 35 8 7 4 23 2 22 16 35 125 125 124 15 121 1 1 1 121 7 1 7 121 118 118 124 111 5 111 43 374 101 101 373 12 12 374 373 101 56 8 93 9 40 17 71 71 25 101 6 101 35 2 101 101 12 100 19 100 100 24 23 3 2 2 2 2 2 1 8 5 5 5 5 5 4 4 4 3 3 3 3 15 18 17 1 17 21 21 4 13 14 14 3 5 1 4 4 3 2 1 1 1 17 3 2 1 1 17 15 2 15 15 2 15 3 1 1 2 3 2 1 1 163 18 162 17 16 17 17 17 6 2 6 5 129 127 125 2 2 2 2 3 1 2 1 1 5 109 3 3 3 1 1 1 22 21 6 15 12 3 2 5 4 3 5 4 1 1 3 2 1 5 5 5 4 2 2 2 3 5 1 27 4 3 4 3 3 2 2 1 1 2 2 2 8 5 2 1 107 468 469 165 20 20 4 20 20 32 32 22 17 7 18 7 18 7 18 2 18 1 18 18 1 18 3 18 32 2 2 2 2 2 71 74 72 71 3 1 1 1 3 1 1 1 2 1 2 1 2 5 3 3 1 2 2 2 5 6 6 6 5 6 6 1 1 1 74 1 1 1 1 2 2 2 1 1 1 2 1 2 2 2 2 1 2 2 1 1 1 1 1 2 1 1 1 1 1 1 1 1 23 23 23 23 2 1 1 22 21 22 22 5 17 1 17 19 15 6 34 1 1 29 28 75 152 153 75 10 10 10 1 12 3 3 1 1 3 2 1 1 2 2 2 116 116 3 1 1 1 113 116 111 1 1 116 114 124 72 55 123 125 125 115 10 3 3 3 3 2 3 3 1 3 3 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 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Implementation of the Transmission Control Protocol(TCP). * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche, <flla@stud.uni-sb.de> * Charles Hedrick, <hedrick@klinzhai.rutgers.edu> * Linus Torvalds, <torvalds@cs.helsinki.fi> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Matthew Dillon, <dillon@apollo.west.oic.com> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Jorge Cwik, <jorge@laser.satlink.net> * * Fixes: * Alan Cox : Numerous verify_area() calls * Alan Cox : Set the ACK bit on a reset * Alan Cox : Stopped it crashing if it closed while * sk->inuse=1 and was trying to connect * (tcp_err()). * Alan Cox : All icmp error handling was broken * pointers passed where wrong and the * socket was looked up backwards. Nobody * tested any icmp error code obviously. * Alan Cox : tcp_err() now handled properly. It * wakes people on errors. poll * behaves and the icmp error race * has gone by moving it into sock.c * Alan Cox : tcp_send_reset() fixed to work for * everything not just packets for * unknown sockets. * Alan Cox : tcp option processing. * Alan Cox : Reset tweaked (still not 100%) [Had * syn rule wrong] * Herp Rosmanith : More reset fixes * Alan Cox : No longer acks invalid rst frames. * Acking any kind of RST is right out. * Alan Cox : Sets an ignore me flag on an rst * receive otherwise odd bits of prattle * escape still * Alan Cox : Fixed another acking RST frame bug. * Should stop LAN workplace lockups. * Alan Cox : Some tidyups using the new skb list * facilities * Alan Cox : sk->keepopen now seems to work * Alan Cox : Pulls options out correctly on accepts * Alan Cox : Fixed assorted sk->rqueue->next errors * Alan Cox : PSH doesn't end a TCP read. Switched a * bit to skb ops. * Alan Cox : Tidied tcp_data to avoid a potential * nasty. * Alan Cox : Added some better commenting, as the * tcp is hard to follow * Alan Cox : Removed incorrect check for 20 * psh * Michael O'Reilly : ack < copied bug fix. * Johannes Stille : Misc tcp fixes (not all in yet). * Alan Cox : FIN with no memory -> CRASH * Alan Cox : Added socket option proto entries. * Also added awareness of them to accept. * Alan Cox : Added TCP options (SOL_TCP) * Alan Cox : Switched wakeup calls to callbacks, * so the kernel can layer network * sockets. * Alan Cox : Use ip_tos/ip_ttl settings. * Alan Cox : Handle FIN (more) properly (we hope). * Alan Cox : RST frames sent on unsynchronised * state ack error. * Alan Cox : Put in missing check for SYN bit. * Alan Cox : Added tcp_select_window() aka NET2E * window non shrink trick. * Alan Cox : Added a couple of small NET2E timer * fixes * Charles Hedrick : TCP fixes * Toomas Tamm : TCP window fixes * Alan Cox : Small URG fix to rlogin ^C ack fight * Charles Hedrick : Rewrote most of it to actually work * Linus : Rewrote tcp_read() and URG handling * completely * Gerhard Koerting: Fixed some missing timer handling * Matthew Dillon : Reworked TCP machine states as per RFC * Gerhard Koerting: PC/TCP workarounds * Adam Caldwell : Assorted timer/timing errors * Matthew Dillon : Fixed another RST bug * Alan Cox : Move to kernel side addressing changes. * Alan Cox : Beginning work on TCP fastpathing * (not yet usable) * Arnt Gulbrandsen: Turbocharged tcp_check() routine. * Alan Cox : TCP fast path debugging * Alan Cox : Window clamping * Michael Riepe : Bug in tcp_check() * Matt Dillon : More TCP improvements and RST bug fixes * Matt Dillon : Yet more small nasties remove from the * TCP code (Be very nice to this man if * tcp finally works 100%) 8) * Alan Cox : BSD accept semantics. * Alan Cox : Reset on closedown bug. * Peter De Schrijver : ENOTCONN check missing in tcp_sendto(). * Michael Pall : Handle poll() after URG properly in * all cases. * Michael Pall : Undo the last fix in tcp_read_urg() * (multi URG PUSH broke rlogin). * Michael Pall : Fix the multi URG PUSH problem in * tcp_readable(), poll() after URG * works now. * Michael Pall : recv(...,MSG_OOB) never blocks in the * BSD api. * Alan Cox : Changed the semantics of sk->socket to * fix a race and a signal problem with * accept() and async I/O. * Alan Cox : Relaxed the rules on tcp_sendto(). * Yury Shevchuk : Really fixed accept() blocking problem. * Craig I. Hagan : Allow for BSD compatible TIME_WAIT for * clients/servers which listen in on * fixed ports. * Alan Cox : Cleaned the above up and shrank it to * a sensible code size. * Alan Cox : Self connect lockup fix. * Alan Cox : No connect to multicast. * Ross Biro : Close unaccepted children on master * socket close. * Alan Cox : Reset tracing code. * Alan Cox : Spurious resets on shutdown. * Alan Cox : Giant 15 minute/60 second timer error * Alan Cox : Small whoops in polling before an * accept. * Alan Cox : Kept the state trace facility since * it's handy for debugging. * Alan Cox : More reset handler fixes. * Alan Cox : Started rewriting the code based on * the RFC's for other useful protocol * references see: Comer, KA9Q NOS, and * for a reference on the difference * between specifications and how BSD * works see the 4.4lite source. * A.N.Kuznetsov : Don't time wait on completion of tidy * close. * Linus Torvalds : Fin/Shutdown & copied_seq changes. * Linus Torvalds : Fixed BSD port reuse to work first syn * Alan Cox : Reimplemented timers as per the RFC * and using multiple timers for sanity. * Alan Cox : Small bug fixes, and a lot of new * comments. * Alan Cox : Fixed dual reader crash by locking * the buffers (much like datagram.c) * Alan Cox : Fixed stuck sockets in probe. A probe * now gets fed up of retrying without * (even a no space) answer. * Alan Cox : Extracted closing code better * Alan Cox : Fixed the closing state machine to * resemble the RFC. * Alan Cox : More 'per spec' fixes. * Jorge Cwik : Even faster checksumming. * Alan Cox : tcp_data() doesn't ack illegal PSH * only frames. At least one pc tcp stack * generates them. * Alan Cox : Cache last socket. * Alan Cox : Per route irtt. * Matt Day : poll()->select() match BSD precisely on error * Alan Cox : New buffers * Marc Tamsky : Various sk->prot->retransmits and * sk->retransmits misupdating fixed. * Fixed tcp_write_timeout: stuck close, * and TCP syn retries gets used now. * Mark Yarvis : In tcp_read_wakeup(), don't send an * ack if state is TCP_CLOSED. * Alan Cox : Look up device on a retransmit - routes may * change. Doesn't yet cope with MSS shrink right * but it's a start! * Marc Tamsky : Closing in closing fixes. * Mike Shaver : RFC1122 verifications. * Alan Cox : rcv_saddr errors. * Alan Cox : Block double connect(). * Alan Cox : Small hooks for enSKIP. * Alexey Kuznetsov: Path MTU discovery. * Alan Cox : Support soft errors. * Alan Cox : Fix MTU discovery pathological case * when the remote claims no mtu! * Marc Tamsky : TCP_CLOSE fix. * Colin (G3TNE) : Send a reset on syn ack replies in * window but wrong (fixes NT lpd problems) * Pedro Roque : Better TCP window handling, delayed ack. * Joerg Reuter : No modification of locked buffers in * tcp_do_retransmit() * Eric Schenk : Changed receiver side silly window * avoidance algorithm to BSD style * algorithm. This doubles throughput * against machines running Solaris, * and seems to result in general * improvement. * Stefan Magdalinski : adjusted tcp_readable() to fix FIONREAD * Willy Konynenberg : Transparent proxying support. * Mike McLagan : Routing by source * Keith Owens : Do proper merging with partial SKB's in * tcp_do_sendmsg to avoid burstiness. * Eric Schenk : Fix fast close down bug with * shutdown() followed by close(). * Andi Kleen : Make poll agree with SIGIO * Salvatore Sanfilippo : Support SO_LINGER with linger == 1 and * lingertime == 0 (RFC 793 ABORT Call) * Hirokazu Takahashi : Use copy_from_user() instead of * csum_and_copy_from_user() if possible. * * Description of States: * * TCP_SYN_SENT sent a connection request, waiting for ack * * TCP_SYN_RECV received a connection request, sent ack, * waiting for final ack in three-way handshake. * * TCP_ESTABLISHED connection established * * TCP_FIN_WAIT1 our side has shutdown, waiting to complete * transmission of remaining buffered data * * TCP_FIN_WAIT2 all buffered data sent, waiting for remote * to shutdown * * TCP_CLOSING both sides have shutdown but we still have * data we have to finish sending * * TCP_TIME_WAIT timeout to catch resent junk before entering * closed, can only be entered from FIN_WAIT2 * or CLOSING. Required because the other end * may not have gotten our last ACK causing it * to retransmit the data packet (which we ignore) * * TCP_CLOSE_WAIT remote side has shutdown and is waiting for * us to finish writing our data and to shutdown * (we have to close() to move on to LAST_ACK) * * TCP_LAST_ACK out side has shutdown after remote has * shutdown. There may still be data in our * buffer that we have to finish sending * * TCP_CLOSE socket is finished */ #define pr_fmt(fmt) "TCP: " fmt #include <crypto/hash.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/poll.h> #include <linux/inet_diag.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/skbuff.h> #include <linux/scatterlist.h> #include <linux/splice.h> #include <linux/net.h> #include <linux/socket.h> #include <linux/random.h> #include <linux/memblock.h> #include <linux/highmem.h> #include <linux/cache.h> #include <linux/err.h> #include <linux/time.h> #include <linux/slab.h> #include <linux/errqueue.h> #include <linux/static_key.h> #include <linux/btf.h> #include <net/icmp.h> #include <net/inet_common.h> #include <net/tcp.h> #include <net/mptcp.h> #include <net/proto_memory.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/sock.h> #include <net/rstreason.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/busy_poll.h> #include <net/hotdata.h> #include <trace/events/tcp.h> #include <net/rps.h> #include "../core/devmem.h" /* Track pending CMSGs. */ enum { TCP_CMSG_INQ = 1, TCP_CMSG_TS = 2 }; DEFINE_PER_CPU(unsigned int, tcp_orphan_count); EXPORT_PER_CPU_SYMBOL_GPL(tcp_orphan_count); DEFINE_PER_CPU(u32, tcp_tw_isn); EXPORT_PER_CPU_SYMBOL_GPL(tcp_tw_isn); long sysctl_tcp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_tcp_mem); atomic_long_t tcp_memory_allocated ____cacheline_aligned_in_smp; /* Current allocated memory. */ EXPORT_SYMBOL(tcp_memory_allocated); DEFINE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); EXPORT_PER_CPU_SYMBOL_GPL(tcp_memory_per_cpu_fw_alloc); #if IS_ENABLED(CONFIG_SMC) DEFINE_STATIC_KEY_FALSE(tcp_have_smc); EXPORT_SYMBOL(tcp_have_smc); #endif /* * Current number of TCP sockets. */ struct percpu_counter tcp_sockets_allocated ____cacheline_aligned_in_smp; EXPORT_SYMBOL(tcp_sockets_allocated); /* * TCP splice context */ struct tcp_splice_state { struct pipe_inode_info *pipe; size_t len; unsigned int flags; }; /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. * All the __sk_mem_schedule() is of this nature: accounting * is strict, actions are advisory and have some latency. */ unsigned long tcp_memory_pressure __read_mostly; EXPORT_SYMBOL_GPL(tcp_memory_pressure); void tcp_enter_memory_pressure(struct sock *sk) { unsigned long val; if (READ_ONCE(tcp_memory_pressure)) return; val = jiffies; if (!val) val--; if (!cmpxchg(&tcp_memory_pressure, 0, val)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES); } EXPORT_SYMBOL_GPL(tcp_enter_memory_pressure); void tcp_leave_memory_pressure(struct sock *sk) { unsigned long val; if (!READ_ONCE(tcp_memory_pressure)) return; val = xchg(&tcp_memory_pressure, 0); if (val) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURESCHRONO, jiffies_to_msecs(jiffies - val)); } EXPORT_SYMBOL_GPL(tcp_leave_memory_pressure); /* Convert seconds to retransmits based on initial and max timeout */ static u8 secs_to_retrans(int seconds, int timeout, int rto_max) { u8 res = 0; if (seconds > 0) { int period = timeout; res = 1; while (seconds > period && res < 255) { res++; timeout <<= 1; if (timeout > rto_max) timeout = rto_max; period += timeout; } } return res; } /* Convert retransmits to seconds based on initial and max timeout */ static int retrans_to_secs(u8 retrans, int timeout, int rto_max) { int period = 0; if (retrans > 0) { period = timeout; while (--retrans) { timeout <<= 1; if (timeout > rto_max) timeout = rto_max; period += timeout; } } return period; } static u64 tcp_compute_delivery_rate(const struct tcp_sock *tp) { u32 rate = READ_ONCE(tp->rate_delivered); u32 intv = READ_ONCE(tp->rate_interval_us); u64 rate64 = 0; if (rate && intv) { rate64 = (u64)rate * tp->mss_cache * USEC_PER_SEC; do_div(rate64, intv); } return rate64; } /* Address-family independent initialization for a tcp_sock. * * NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ void tcp_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int rto_min_us; tp->out_of_order_queue = RB_ROOT; sk->tcp_rtx_queue = RB_ROOT; tcp_init_xmit_timers(sk); INIT_LIST_HEAD(&tp->tsq_node); INIT_LIST_HEAD(&tp->tsorted_sent_queue); icsk->icsk_rto = TCP_TIMEOUT_INIT; rto_min_us = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rto_min_us); icsk->icsk_rto_min = usecs_to_jiffies(rto_min_us); icsk->icsk_delack_max = TCP_DELACK_MAX; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control * algorithms that we must have the following bandaid to talk * efficiently to them. -DaveM */ tcp_snd_cwnd_set(tp, TCP_INIT_CWND); /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; tp->rate_app_limited = 1; /* See draft-stevens-tcpca-spec-01 for discussion of the * initialization of these values. */ tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_clamp = ~0; tp->mss_cache = TCP_MSS_DEFAULT; tp->reordering = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering); tcp_assign_congestion_control(sk); tp->tsoffset = 0; tp->rack.reo_wnd_steps = 1; sk->sk_write_space = sk_stream_write_space; sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); icsk->icsk_sync_mss = tcp_sync_mss; WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1])); WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1])); tcp_scaling_ratio_init(sk); set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); sk_sockets_allocated_inc(sk); xa_init_flags(&sk->sk_user_frags, XA_FLAGS_ALLOC1); } EXPORT_SYMBOL(tcp_init_sock); static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc) { struct sk_buff *skb = tcp_write_queue_tail(sk); u32 tsflags = sockc->tsflags; if (tsflags && skb) { struct skb_shared_info *shinfo = skb_shinfo(skb); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); sock_tx_timestamp(sk, sockc, &shinfo->tx_flags); if (tsflags & SOF_TIMESTAMPING_TX_ACK) tcb->txstamp_ack = 1; if (tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1; } } static bool tcp_stream_is_readable(struct sock *sk, int target) { if (tcp_epollin_ready(sk, target)) return true; return sk_is_readable(sk); } /* * Wait for a TCP event. * * Note that we don't need to lock the socket, as the upper poll layers * take care of normal races (between the test and the event) and we don't * go look at any of the socket buffers directly. */ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) { __poll_t mask; struct sock *sk = sock->sk; const struct tcp_sock *tp = tcp_sk(sk); u8 shutdown; int state; sock_poll_wait(file, sock, wait); state = inet_sk_state_load(sk); if (state == TCP_LISTEN) return inet_csk_listen_poll(sk); /* Socket is not locked. We are protected from async events * by poll logic and correct handling of state changes * made by other threads is impossible in any case. */ mask = 0; /* * EPOLLHUP is certainly not done right. But poll() doesn't * have a notion of HUP in just one direction, and for a * socket the read side is more interesting. * * Some poll() documentation says that EPOLLHUP is incompatible * with the EPOLLOUT/POLLWR flags, so somebody should check this * all. But careful, it tends to be safer to return too many * bits than too few, and you can easily break real applications * if you don't tell them that something has hung up! * * Check-me. * * Check number 1. EPOLLHUP is _UNMASKABLE_ event (see UNIX98 and * our fs/select.c). It means that after we received EOF, * poll always returns immediately, making impossible poll() on write() * in state CLOSE_WAIT. One solution is evident --- to set EPOLLHUP * if and only if shutdown has been made in both directions. * Actually, it is interesting to look how Solaris and DUX * solve this dilemma. I would prefer, if EPOLLHUP were maskable, * then we could set it on SND_SHUTDOWN. BTW examples given * in Stevens' books assume exactly this behaviour, it explains * why EPOLLHUP is incompatible with EPOLLOUT. --ANK * * NOTE. Check for TCP_CLOSE is added. The goal is to prevent * blocking on fresh not-connected or disconnected socket. --ANK */ shutdown = READ_ONCE(sk->sk_shutdown); if (shutdown == SHUTDOWN_MASK || state == TCP_CLOSE) mask |= EPOLLHUP; if (shutdown & RCV_SHUTDOWN) mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; /* Connected or passive Fast Open socket? */ if (state != TCP_SYN_SENT && (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) { int target = sock_rcvlowat(sk, 0, INT_MAX); u16 urg_data = READ_ONCE(tp->urg_data); if (unlikely(urg_data) && READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) && !sock_flag(sk, SOCK_URGINLINE)) target++; if (tcp_stream_is_readable(sk, target)) mask |= EPOLLIN | EPOLLRDNORM; if (!(shutdown & SEND_SHUTDOWN)) { if (__sk_stream_is_writeable(sk, 1)) { mask |= EPOLLOUT | EPOLLWRNORM; } else { /* send SIGIO later */ sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); /* Race breaker. If space is freed after * wspace test but before the flags are set, * IO signal will be lost. Memory barrier * pairs with the input side. */ smp_mb__after_atomic(); if (__sk_stream_is_writeable(sk, 1)) mask |= EPOLLOUT | EPOLLWRNORM; } } else mask |= EPOLLOUT | EPOLLWRNORM; if (urg_data & TCP_URG_VALID) mask |= EPOLLPRI; } else if (state == TCP_SYN_SENT && inet_test_bit(DEFER_CONNECT, sk)) { /* Active TCP fastopen socket with defer_connect * Return EPOLLOUT so application can call write() * in order for kernel to generate SYN+data */ mask |= EPOLLOUT | EPOLLWRNORM; } /* This barrier is coupled with smp_wmb() in tcp_done_with_error() */ smp_rmb(); if (READ_ONCE(sk->sk_err) || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR; return mask; } EXPORT_SYMBOL(tcp_poll); int tcp_ioctl(struct sock *sk, int cmd, int *karg) { struct tcp_sock *tp = tcp_sk(sk); int answ; bool slow; switch (cmd) { case SIOCINQ: if (sk->sk_state == TCP_LISTEN) return -EINVAL; slow = lock_sock_fast(sk); answ = tcp_inq(sk); unlock_sock_fast(sk, slow); break; case SIOCATMARK: answ = READ_ONCE(tp->urg_data) && READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq); break; case SIOCOUTQ: if (sk->sk_state == TCP_LISTEN) return -EINVAL; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else answ = READ_ONCE(tp->write_seq) - tp->snd_una; break; case SIOCOUTQNSD: if (sk->sk_state == TCP_LISTEN) return -EINVAL; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else answ = READ_ONCE(tp->write_seq) - READ_ONCE(tp->snd_nxt); break; default: return -ENOIOCTLCMD; } *karg = answ; return 0; } EXPORT_SYMBOL(tcp_ioctl); void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; tp->pushed_seq = tp->write_seq; } static inline bool forced_push(const struct tcp_sock *tp) { return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1)); } void tcp_skb_entail(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); tcb->seq = tcb->end_seq = tp->write_seq; tcb->tcp_flags = TCPHDR_ACK; __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); if (tp->nonagle & TCP_NAGLE_PUSH) tp->nonagle &= ~TCP_NAGLE_PUSH; tcp_slow_start_after_idle_check(sk); } static inline void tcp_mark_urg(struct tcp_sock *tp, int flags) { if (flags & MSG_OOB) tp->snd_up = tp->write_seq; } /* If a not yet filled skb is pushed, do not send it if * we have data packets in Qdisc or NIC queues : * Because TX completion will happen shortly, it gives a chance * to coalesce future sendmsg() payload into this skb, without * need for a timer, and with no latency trade off. * As packets containing data payload have a bigger truesize * than pure acks (dataless) packets, the last checks prevent * autocorking if we only have an ACK in Qdisc/NIC queues, * or if TX completion was delayed after we processed ACK packet. */ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, int size_goal) { return skb->len < size_goal && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_autocorking) && !tcp_rtx_queue_empty(sk) && refcount_read(&sk->sk_wmem_alloc) > skb->truesize && tcp_skb_can_collapse_to(skb); } void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle, int size_goal) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; skb = tcp_write_queue_tail(sk); if (!skb) return; if (!(flags & MSG_MORE) || forced_push(tp)) tcp_mark_push(tp, skb); tcp_mark_urg(tp, flags); if (tcp_should_autocork(sk, skb, size_goal)) { /* avoid atomic op if TSQ_THROTTLED bit is already set */ if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING); set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); smp_mb__after_atomic(); } /* It is possible TX completion already happened * before we set TSQ_THROTTLED. */ if (refcount_read(&sk->sk_wmem_alloc) > skb->truesize) return; } if (flags & MSG_MORE) nonagle = TCP_NAGLE_CORK; __tcp_push_pending_frames(sk, mss_now, nonagle); } static int tcp_splice_data_recv(read_descriptor_t *rd_desc, struct sk_buff *skb, unsigned int offset, size_t len) { struct tcp_splice_state *tss = rd_desc->arg.data; int ret; ret = skb_splice_bits(skb, skb->sk, offset, tss->pipe, min(rd_desc->count, len), tss->flags); if (ret > 0) rd_desc->count -= ret; return ret; } static int __tcp_splice_read(struct sock *sk, struct tcp_splice_state *tss) { /* Store TCP splice context information in read_descriptor_t. */ read_descriptor_t rd_desc = { .arg.data = tss, .count = tss->len, }; return tcp_read_sock(sk, &rd_desc, tcp_splice_data_recv); } /** * tcp_splice_read - splice data from TCP socket to a pipe * @sock: socket to splice from * @ppos: position (not valid) * @pipe: pipe to splice to * @len: number of bytes to splice * @flags: splice modifier flags * * Description: * Will read pages from given socket and fill them into a pipe. * **/ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct sock *sk = sock->sk; struct tcp_splice_state tss = { .pipe = pipe, .len = len, .flags = flags, }; long timeo; ssize_t spliced; int ret; sock_rps_record_flow(sk); /* * We can't seek on a socket input */ if (unlikely(*ppos)) return -ESPIPE; ret = spliced = 0; lock_sock(sk); timeo = sock_rcvtimeo(sk, sock->file->f_flags & O_NONBLOCK); while (tss.len) { ret = __tcp_splice_read(sk, &tss); if (ret < 0) break; else if (!ret) { if (spliced) break; if (sock_flag(sk, SOCK_DONE)) break; if (sk->sk_err) { ret = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_state == TCP_CLOSE) { /* * This occurs when user tries to read * from never connected socket. */ ret = -ENOTCONN; break; } if (!timeo) { ret = -EAGAIN; break; } /* if __tcp_splice_read() got nothing while we have * an skb in receive queue, we do not want to loop. * This might happen with URG data. */ if (!skb_queue_empty(&sk->sk_receive_queue)) break; ret = sk_wait_data(sk, &timeo, NULL); if (ret < 0) break; if (signal_pending(current)) { ret = sock_intr_errno(timeo); break; } continue; } tss.len -= ret; spliced += ret; if (!tss.len || !timeo) break; release_sock(sk); lock_sock(sk); if (sk->sk_err || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || signal_pending(current)) break; } release_sock(sk); if (spliced) return spliced; return ret; } EXPORT_SYMBOL(tcp_splice_read); struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp, bool force_schedule) { struct sk_buff *skb; skb = alloc_skb_fclone(MAX_TCP_HEADER, gfp); if (likely(skb)) { bool mem_scheduled; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); if (force_schedule) { mem_scheduled = true; sk_forced_mem_schedule(sk, skb->truesize); } else { mem_scheduled = sk_wmem_schedule(sk, skb->truesize); } if (likely(mem_scheduled)) { skb_reserve(skb, MAX_TCP_HEADER); skb->ip_summed = CHECKSUM_PARTIAL; INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); return skb; } __kfree_skb(skb); } else { sk->sk_prot->enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); } return NULL; } static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, int large_allowed) { struct tcp_sock *tp = tcp_sk(sk); u32 new_size_goal, size_goal; if (!large_allowed) return mss_now; /* Note : tcp_tso_autosize() will eventually split this later */ new_size_goal = tcp_bound_to_half_wnd(tp, sk->sk_gso_max_size); /* We try hard to avoid divides here */ size_goal = tp->gso_segs * mss_now; if (unlikely(new_size_goal < size_goal || new_size_goal >= size_goal + mss_now)) { tp->gso_segs = min_t(u16, new_size_goal / mss_now, sk->sk_gso_max_segs); size_goal = tp->gso_segs * mss_now; } return max(size_goal, mss_now); } int tcp_send_mss(struct sock *sk, int *size_goal, int flags) { int mss_now; mss_now = tcp_current_mss(sk); *size_goal = tcp_xmit_size_goal(sk, mss_now, !(flags & MSG_OOB)); return mss_now; } /* In some cases, sendmsg() could have added an skb to the write queue, * but failed adding payload on it. We need to remove it to consume less * memory, but more importantly be able to generate EPOLLOUT for Edge Trigger * epoll() users. Another reason is that tcp_write_xmit() does not like * finding an empty skb in the write queue. */ void tcp_remove_empty_skb(struct sock *sk) { struct sk_buff *skb = tcp_write_queue_tail(sk); if (skb && TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { tcp_unlink_write_queue(skb, sk); if (tcp_write_queue_empty(sk)) tcp_chrono_stop(sk, TCP_CHRONO_BUSY); tcp_wmem_free_skb(sk, skb); } } /* skb changing from pure zc to mixed, must charge zc */ static int tcp_downgrade_zcopy_pure(struct sock *sk, struct sk_buff *skb) { if (unlikely(skb_zcopy_pure(skb))) { u32 extra = skb->truesize - SKB_TRUESIZE(skb_end_offset(skb)); if (!sk_wmem_schedule(sk, extra)) return -ENOMEM; sk_mem_charge(sk, extra); skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY; } return 0; } int tcp_wmem_schedule(struct sock *sk, int copy) { int left; if (likely(sk_wmem_schedule(sk, copy))) return copy; /* We could be in trouble if we have nothing queued. * Use whatever is left in sk->sk_forward_alloc and tcp_wmem[0] * to guarantee some progress. */ left = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[0]) - sk->sk_wmem_queued; if (left > 0) sk_forced_mem_schedule(sk, min(left, copy)); return min(copy, sk->sk_forward_alloc); } void tcp_free_fastopen_req(struct tcp_sock *tp) { if (tp->fastopen_req) { kfree(tp->fastopen_req); tp->fastopen_req = NULL; } } int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, size_t size, struct ubuf_info *uarg) { struct tcp_sock *tp = tcp_sk(sk); struct inet_sock *inet = inet_sk(sk); struct sockaddr *uaddr = msg->msg_name; int err, flags; if (!(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & TFO_CLIENT_ENABLE) || (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) && uaddr->sa_family == AF_UNSPEC)) return -EOPNOTSUPP; if (tp->fastopen_req) return -EALREADY; /* Another Fast Open is in progress */ tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request), sk->sk_allocation); if (unlikely(!tp->fastopen_req)) return -ENOBUFS; tp->fastopen_req->data = msg; tp->fastopen_req->size = size; tp->fastopen_req->uarg = uarg; if (inet_test_bit(DEFER_CONNECT, sk)) { err = tcp_connect(sk); /* Same failure procedure as in tcp_v4/6_connect */ if (err) { tcp_set_state(sk, TCP_CLOSE); inet->inet_dport = 0; sk->sk_route_caps = 0; } } flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; err = __inet_stream_connect(sk->sk_socket, uaddr, msg->msg_namelen, flags, 1); /* fastopen_req could already be freed in __inet_stream_connect * if the connection times out or gets rst */ if (tp->fastopen_req) { *copied = tp->fastopen_req->copied; tcp_free_fastopen_req(tp); inet_clear_bit(DEFER_CONNECT, sk); } return err; } int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) { struct tcp_sock *tp = tcp_sk(sk); struct ubuf_info *uarg = NULL; struct sk_buff *skb; struct sockcm_cookie sockc; int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; int process_backlog = 0; int zc = 0; long timeo; flags = msg->msg_flags; if ((flags & MSG_ZEROCOPY) && size) { if (msg->msg_ubuf) { uarg = msg->msg_ubuf; if (sk->sk_route_caps & NETIF_F_SG) zc = MSG_ZEROCOPY; } else if (sock_flag(sk, SOCK_ZEROCOPY)) { skb = tcp_write_queue_tail(sk); uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb)); if (!uarg) { err = -ENOBUFS; goto out_err; } if (sk->sk_route_caps & NETIF_F_SG) zc = MSG_ZEROCOPY; else uarg_to_msgzc(uarg)->zerocopy = 0; } } else if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES) && size) { if (sk->sk_route_caps & NETIF_F_SG) zc = MSG_SPLICE_PAGES; } if (unlikely(flags & MSG_FASTOPEN || inet_test_bit(DEFER_CONNECT, sk)) && !tp->repair) { err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size, uarg); if (err == -EINPROGRESS && copied_syn > 0) goto out; else if (err) goto out_err; } timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); tcp_rate_check_app_limited(sk); /* is sending application-limited? */ /* Wait for a connection to finish. One exception is TCP Fast Open * (passive side) where data is allowed to be sent before a connection * is fully established. */ if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && !tcp_passive_fastopen(sk)) { err = sk_stream_wait_connect(sk, &timeo); if (err != 0) goto do_error; } if (unlikely(tp->repair)) { if (tp->repair_queue == TCP_RECV_QUEUE) { copied = tcp_send_rcvq(sk, msg, size); goto out_nopush; } err = -EINVAL; if (tp->repair_queue == TCP_NO_QUEUE) goto out_err; /* 'common' sending to sendq */ } sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) { err = -EINVAL; goto out_err; } } /* This should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); /* Ok commence sending. */ copied = 0; restart: mss_now = tcp_send_mss(sk, &size_goal, flags); err = -EPIPE; if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; while (msg_data_left(msg)) { ssize_t copy = 0; skb = tcp_write_queue_tail(sk); if (skb) copy = size_goal - skb->len; if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) { bool first_skb; new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_space; if (unlikely(process_backlog >= 16)) { process_backlog = 0; if (sk_flush_backlog(sk)) goto restart; } first_skb = tcp_rtx_and_write_queues_empty(sk); skb = tcp_stream_alloc_skb(sk, sk->sk_allocation, first_skb); if (!skb) goto wait_for_space; process_backlog++; #ifdef CONFIG_SKB_DECRYPTED skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED); #endif tcp_skb_entail(sk, skb); copy = size_goal; /* All packets are restored as if they have * already been sent. skb_mstamp_ns isn't set to * avoid wrong rtt estimation. */ if (tp->repair) TCP_SKB_CB(skb)->sacked |= TCPCB_REPAIRED; } /* Try to append data to the end of skb. */ if (copy > msg_data_left(msg)) copy = msg_data_left(msg); if (zc == 0) { bool merge = true; int i = skb_shinfo(skb)->nr_frags; struct page_frag *pfrag = sk_page_frag(sk); if (!sk_page_frag_refill(sk, pfrag)) goto wait_for_space; if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { if (i >= READ_ONCE(net_hotdata.sysctl_max_skb_frags)) { tcp_mark_push(tp, skb); goto new_segment; } merge = false; } copy = min_t(int, copy, pfrag->size - pfrag->offset); if (unlikely(skb_zcopy_pure(skb) || skb_zcopy_managed(skb))) { if (tcp_downgrade_zcopy_pure(sk, skb)) goto wait_for_space; skb_zcopy_downgrade_managed(skb); } copy = tcp_wmem_schedule(sk, copy); if (!copy) goto wait_for_space; err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, pfrag->page, pfrag->offset, copy); if (err) goto do_error; /* Update the skb. */ if (merge) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, copy); page_ref_inc(pfrag->page); } pfrag->offset += copy; } else if (zc == MSG_ZEROCOPY) { /* First append to a fragless skb builds initial * pure zerocopy skb */ if (!skb->len) skb_shinfo(skb)->flags |= SKBFL_PURE_ZEROCOPY; if (!skb_zcopy_pure(skb)) { copy = tcp_wmem_schedule(sk, copy); if (!copy) goto wait_for_space; } err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg); if (err == -EMSGSIZE || err == -EEXIST) { tcp_mark_push(tp, skb); goto new_segment; } if (err < 0) goto do_error; copy = err; } else if (zc == MSG_SPLICE_PAGES) { /* Splice in data if we can; copy if we can't. */ if (tcp_downgrade_zcopy_pure(sk, skb)) goto wait_for_space; copy = tcp_wmem_schedule(sk, copy); if (!copy) goto wait_for_space; err = skb_splice_from_iter(skb, &msg->msg_iter, copy, sk->sk_allocation); if (err < 0) { if (err == -EMSGSIZE) { tcp_mark_push(tp, skb); goto new_segment; } goto do_error; } copy = err; if (!(flags & MSG_NO_SHARED_FRAGS)) skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG; sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); } if (!copied) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); copied += copy; if (!msg_data_left(msg)) { if (unlikely(flags & MSG_EOR)) TCP_SKB_CB(skb)->eor = 1; goto out; } if (skb->len < size_goal || (flags & MSG_OOB) || unlikely(tp->repair)) continue; if (forced_push(tp)) { tcp_mark_push(tp, skb); __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH); } else if (skb == tcp_send_head(sk)) tcp_push_one(sk, mss_now); continue; wait_for_space: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); tcp_remove_empty_skb(sk); if (copied) tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); err = sk_stream_wait_memory(sk, &timeo); if (err != 0) goto do_error; mss_now = tcp_send_mss(sk, &size_goal, flags); } out: if (copied) { tcp_tx_timestamp(sk, &sockc); tcp_push(sk, flags, mss_now, tp->nonagle, size_goal); } out_nopush: /* msg->msg_ubuf is pinned by the caller so we don't take extra refs */ if (uarg && !msg->msg_ubuf) net_zcopy_put(uarg); return copied + copied_syn; do_error: tcp_remove_empty_skb(sk); if (copied + copied_syn) goto out; out_err: /* msg->msg_ubuf is pinned by the caller so we don't take extra refs */ if (uarg && !msg->msg_ubuf) net_zcopy_put_abort(uarg, true); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } return err; } EXPORT_SYMBOL_GPL(tcp_sendmsg_locked); int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { int ret; lock_sock(sk); ret = tcp_sendmsg_locked(sk, msg, size); release_sock(sk); return ret; } EXPORT_SYMBOL(tcp_sendmsg); void tcp_splice_eof(struct socket *sock) { struct sock *sk = sock->sk; struct tcp_sock *tp = tcp_sk(sk); int mss_now, size_goal; if (!tcp_write_queue_tail(sk)) return; lock_sock(sk); mss_now = tcp_send_mss(sk, &size_goal, 0); tcp_push(sk, 0, mss_now, tp->nonagle, size_goal); release_sock(sk); } EXPORT_SYMBOL_GPL(tcp_splice_eof); /* * Handle reading urgent data. BSD has very simple semantics for * this, no blocking and very strange errors 8) */ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags) { struct tcp_sock *tp = tcp_sk(sk); /* No URG data to read. */ if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data || tp->urg_data == TCP_URG_READ) return -EINVAL; /* Yes this is right ! */ if (sk->sk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DONE)) return -ENOTCONN; if (tp->urg_data & TCP_URG_VALID) { int err = 0; char c = tp->urg_data; if (!(flags & MSG_PEEK)) WRITE_ONCE(tp->urg_data, TCP_URG_READ); /* Read urgent data. */ msg->msg_flags |= MSG_OOB; if (len > 0) { if (!(flags & MSG_TRUNC)) err = memcpy_to_msg(msg, &c, 1); len = 1; } else msg->msg_flags |= MSG_TRUNC; return err ? -EFAULT : len; } if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN)) return 0; /* Fixed the recv(..., MSG_OOB) behaviour. BSD docs and * the available implementations agree in this case: * this call should never block, independent of the * blocking state of the socket. * Mike <pall@rz.uni-karlsruhe.de> */ return -EAGAIN; } static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len) { struct sk_buff *skb; int copied = 0, err = 0; skb_rbtree_walk(skb, &sk->tcp_rtx_queue) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) return err; copied += skb->len; } skb_queue_walk(&sk->sk_write_queue, skb) { err = skb_copy_datagram_msg(skb, 0, msg, skb->len); if (err) break; copied += skb->len; } return err ?: copied; } /* Clean up the receive buffer for full frames taken by the user, * then send an ACK if necessary. COPIED is the number of bytes * tcp_recvmsg has given to the user so far, it speeds up the * calculation of whether or not we must ACK for the sake of * a window update. */ void __tcp_cleanup_rbuf(struct sock *sk, int copied) { struct tcp_sock *tp = tcp_sk(sk); bool time_to_ack = false; if (inet_csk_ack_scheduled(sk)) { const struct inet_connection_sock *icsk = inet_csk(sk); if (/* Once-per-two-segments ACK was not sent by tcp_input.c */ tp->rcv_nxt - tp->rcv_wup > icsk->icsk_ack.rcv_mss || /* * If this read emptied read buffer, we send ACK, if * connection is not bidirectional, user drained * receive buffer and there was a small segment * in queue. */ (copied > 0 && ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED2) || ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) && !inet_csk_in_pingpong_mode(sk))) && !atomic_read(&sk->sk_rmem_alloc))) time_to_ack = true; } /* We send an ACK if we can now advertise a non-zero window * which has been raised "significantly". * * Even if window raised up to infinity, do not send window open ACK * in states, where we will not receive more. It is useless. */ if (copied > 0 && !time_to_ack && !(sk->sk_shutdown & RCV_SHUTDOWN)) { __u32 rcv_window_now = tcp_receive_window(tp); /* Optimize, __tcp_select_window() is not cheap. */ if (2*rcv_window_now <= tp->window_clamp) { __u32 new_window = __tcp_select_window(sk); /* Send ACK now, if this read freed lots of space * in our buffer. Certainly, new_window is new window. * We can advertise it now, if it is not less than current one. * "Lots" means "at least twice" here. */ if (new_window && new_window >= 2 * rcv_window_now) time_to_ack = true; } } if (time_to_ack) tcp_send_ack(sk); } void tcp_cleanup_rbuf(struct sock *sk, int copied) { struct sk_buff *skb = skb_peek(&sk->sk_receive_queue); struct tcp_sock *tp = tcp_sk(sk); WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq), "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n", tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt); __tcp_cleanup_rbuf(sk, copied); } static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); if (likely(skb->destructor == sock_rfree)) { sock_rfree(skb); skb->destructor = NULL; skb->sk = NULL; return skb_attempt_defer_free(skb); } __kfree_skb(skb); } struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) { struct sk_buff *skb; u32 offset; while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { offset = seq - TCP_SKB_CB(skb)->seq; if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { pr_err_once("%s: found a SYN, please report !\n", __func__); offset--; } if (offset < skb->len || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) { *off = offset; return skb; } /* This looks weird, but this can happen if TCP collapsing * splitted a fat GRO packet, while we released socket lock * in skb_splice_bits() */ tcp_eat_recv_skb(sk, skb); } return NULL; } EXPORT_SYMBOL(tcp_recv_skb); /* * This routine provides an alternative to tcp_recvmsg() for routines * that would like to handle copying from skbuffs directly in 'sendfile' * fashion. * Note: * - It is assumed that the socket was locked by the caller. * - The routine does not block. * - At present, there is no support for reading OOB data * or for 'peeking' the socket using this routine * (although both would be easy to implement). */ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor) { struct sk_buff *skb; struct tcp_sock *tp = tcp_sk(sk); u32 seq = tp->copied_seq; u32 offset; int copied = 0; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { if (offset < skb->len) { int used; size_t len; len = skb->len - offset; /* Stop reading if we hit a patch of urgent data */ if (unlikely(tp->urg_data)) { u32 urg_offset = tp->urg_seq - seq; if (urg_offset < len) len = urg_offset; if (!len) break; } used = recv_actor(desc, skb, offset, len); if (used <= 0) { if (!copied) copied = used; break; } if (WARN_ON_ONCE(used > len)) used = len; seq += used; copied += used; offset += used; /* If recv_actor drops the lock (e.g. TCP splice * receive) the skb pointer might be invalid when * getting here: tcp_collapse might have deleted it * while aggregating skbs from the socket queue. */ skb = tcp_recv_skb(sk, seq - 1, &offset); if (!skb) break; /* TCP coalescing might have appended data to the skb. * Try to splice more frags */ if (offset + 1 != skb->len) continue; } if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_eat_recv_skb(sk, skb); ++seq; break; } tcp_eat_recv_skb(sk, skb); if (!desc->count) break; WRITE_ONCE(tp->copied_seq, seq); } WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ if (copied > 0) { tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, copied); } return copied; } EXPORT_SYMBOL(tcp_read_sock); int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct sk_buff *skb; int copied = 0; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) { u8 tcp_flags; int used; __skb_unlink(skb, &sk->sk_receive_queue); WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); tcp_flags = TCP_SKB_CB(skb)->tcp_flags; used = recv_actor(sk, skb); if (used < 0) { if (!copied) copied = used; break; } copied += used; if (tcp_flags & TCPHDR_FIN) break; } return copied; } EXPORT_SYMBOL(tcp_read_skb); void tcp_read_done(struct sock *sk, size_t len) { struct tcp_sock *tp = tcp_sk(sk); u32 seq = tp->copied_seq; struct sk_buff *skb; size_t left; u32 offset; if (sk->sk_state == TCP_LISTEN) return; left = len; while (left && (skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { int used; used = min_t(size_t, skb->len - offset, left); seq += used; left -= used; if (skb->len > offset + used) break; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_eat_recv_skb(sk, skb); ++seq; break; } tcp_eat_recv_skb(sk, skb); } WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ if (left != len) tcp_cleanup_rbuf(sk, len - left); } EXPORT_SYMBOL(tcp_read_done); int tcp_peek_len(struct socket *sock) { return tcp_inq(sock->sk); } EXPORT_SYMBOL(tcp_peek_len); /* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */ int tcp_set_rcvlowat(struct sock *sk, int val) { int space, cap; if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) cap = sk->sk_rcvbuf >> 1; else cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1; val = min(val, cap); WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); /* Check if we need to signal EPOLLIN right now */ tcp_data_ready(sk); if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) return 0; space = tcp_space_from_win(sk, val); if (space > sk->sk_rcvbuf) { WRITE_ONCE(sk->sk_rcvbuf, space); WRITE_ONCE(tcp_sk(sk)->window_clamp, val); } return 0; } EXPORT_SYMBOL(tcp_set_rcvlowat); void tcp_update_recv_tstamps(struct sk_buff *skb, struct scm_timestamping_internal *tss) { if (skb->tstamp) tss->ts[0] = ktime_to_timespec64(skb->tstamp); else tss->ts[0] = (struct timespec64) {0}; if (skb_hwtstamps(skb)->hwtstamp) tss->ts[2] = ktime_to_timespec64(skb_hwtstamps(skb)->hwtstamp); else tss->ts[2] = (struct timespec64) {0}; } #ifdef CONFIG_MMU static const struct vm_operations_struct tcp_vm_ops = { }; int tcp_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { if (vma->vm_flags & (VM_WRITE | VM_EXEC)) return -EPERM; vm_flags_clear(vma, VM_MAYWRITE | VM_MAYEXEC); /* Instruct vm_insert_page() to not mmap_read_lock(mm) */ vm_flags_set(vma, VM_MIXEDMAP); vma->vm_ops = &tcp_vm_ops; return 0; } EXPORT_SYMBOL(tcp_mmap); static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, u32 *offset_frag) { skb_frag_t *frag; if (unlikely(offset_skb >= skb->len)) return NULL; offset_skb -= skb_headlen(skb); if ((int)offset_skb < 0 || skb_has_frag_list(skb)) return NULL; frag = skb_shinfo(skb)->frags; while (offset_skb) { if (skb_frag_size(frag) > offset_skb) { *offset_frag = offset_skb; return frag; } offset_skb -= skb_frag_size(frag); ++frag; } *offset_frag = 0; return frag; } static bool can_map_frag(const skb_frag_t *frag) { struct page *page; if (skb_frag_size(frag) != PAGE_SIZE || skb_frag_off(frag)) return false; page = skb_frag_page(frag); if (PageCompound(page) || page->mapping) return false; return true; } static int find_next_mappable_frag(const skb_frag_t *frag, int remaining_in_skb) { int offset = 0; if (likely(can_map_frag(frag))) return 0; while (offset < remaining_in_skb && !can_map_frag(frag)) { offset += skb_frag_size(frag); ++frag; } return offset; } static void tcp_zerocopy_set_hint_for_skb(struct sock *sk, struct tcp_zerocopy_receive *zc, struct sk_buff *skb, u32 offset) { u32 frag_offset, partial_frag_remainder = 0; int mappable_offset; skb_frag_t *frag; /* worst case: skip to next skb. try to improve on this case below */ zc->recv_skip_hint = skb->len - offset; /* Find the frag containing this offset (and how far into that frag) */ frag = skb_advance_to_frag(skb, offset, &frag_offset); if (!frag) return; if (frag_offset) { struct skb_shared_info *info = skb_shinfo(skb); /* We read part of the last frag, must recvmsg() rest of skb. */ if (frag == &info->frags[info->nr_frags - 1]) return; /* Else, we must at least read the remainder in this frag. */ partial_frag_remainder = skb_frag_size(frag) - frag_offset; zc->recv_skip_hint -= partial_frag_remainder; ++frag; } /* partial_frag_remainder: If part way through a frag, must read rest. * mappable_offset: Bytes till next mappable frag, *not* counting bytes * in partial_frag_remainder. */ mappable_offset = find_next_mappable_frag(frag, zc->recv_skip_hint); zc->recv_skip_hint = mappable_offset + partial_frag_remainder; } static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int flags, struct scm_timestamping_internal *tss, int *cmsg_flags); static int receive_fallback_to_copy(struct sock *sk, struct tcp_zerocopy_receive *zc, int inq, struct scm_timestamping_internal *tss) { unsigned long copy_address = (unsigned long)zc->copybuf_address; struct msghdr msg = {}; int err; zc->length = 0; zc->recv_skip_hint = 0; if (copy_address != zc->copybuf_address) return -EINVAL; err = import_ubuf(ITER_DEST, (void __user *)copy_address, inq, &msg.msg_iter); if (err) return err; err = tcp_recvmsg_locked(sk, &msg, inq, MSG_DONTWAIT, tss, &zc->msg_flags); if (err < 0) return err; zc->copybuf_len = err; if (likely(zc->copybuf_len)) { struct sk_buff *skb; u32 offset; skb = tcp_recv_skb(sk, tcp_sk(sk)->copied_seq, &offset); if (skb) tcp_zerocopy_set_hint_for_skb(sk, zc, skb, offset); } return 0; } static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, struct sk_buff *skb, u32 copylen, u32 *offset, u32 *seq) { unsigned long copy_address = (unsigned long)zc->copybuf_address; struct msghdr msg = {}; int err; if (copy_address != zc->copybuf_address) return -EINVAL; err = import_ubuf(ITER_DEST, (void __user *)copy_address, copylen, &msg.msg_iter); if (err) return err; err = skb_copy_datagram_msg(skb, *offset, &msg, copylen); if (err) return err; zc->recv_skip_hint -= copylen; *offset += copylen; *seq += copylen; return (__s32)copylen; } static int tcp_zc_handle_leftover(struct tcp_zerocopy_receive *zc, struct sock *sk, struct sk_buff *skb, u32 *seq, s32 copybuf_len, struct scm_timestamping_internal *tss) { u32 offset, copylen = min_t(u32, copybuf_len, zc->recv_skip_hint); if (!copylen) return 0; /* skb is null if inq < PAGE_SIZE. */ if (skb) { offset = *seq - TCP_SKB_CB(skb)->seq; } else { skb = tcp_recv_skb(sk, *seq, &offset); if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); zc->msg_flags |= TCP_CMSG_TS; } } zc->copybuf_len = tcp_copy_straggler_data(zc, skb, copylen, &offset, seq); return zc->copybuf_len < 0 ? 0 : copylen; } static int tcp_zerocopy_vm_insert_batch_error(struct vm_area_struct *vma, struct page **pending_pages, unsigned long pages_remaining, unsigned long *address, u32 *length, u32 *seq, struct tcp_zerocopy_receive *zc, u32 total_bytes_to_map, int err) { /* At least one page did not map. Try zapping if we skipped earlier. */ if (err == -EBUSY && zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT) { u32 maybe_zap_len; maybe_zap_len = total_bytes_to_map - /* All bytes to map */ *length + /* Mapped or pending */ (pages_remaining * PAGE_SIZE); /* Failed map. */ zap_page_range_single(vma, *address, maybe_zap_len, NULL); err = 0; } if (!err) { unsigned long leftover_pages = pages_remaining; int bytes_mapped; /* We called zap_page_range_single, try to reinsert. */ err = vm_insert_pages(vma, *address, pending_pages, &pages_remaining); bytes_mapped = PAGE_SIZE * (leftover_pages - pages_remaining); *seq += bytes_mapped; *address += bytes_mapped; } if (err) { /* Either we were unable to zap, OR we zapped, retried an * insert, and still had an issue. Either ways, pages_remaining * is the number of pages we were unable to map, and we unroll * some state we speculatively touched before. */ const int bytes_not_mapped = PAGE_SIZE * pages_remaining; *length -= bytes_not_mapped; zc->recv_skip_hint += bytes_not_mapped; } return err; } static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma, struct page **pages, unsigned int pages_to_map, unsigned long *address, u32 *length, u32 *seq, struct tcp_zerocopy_receive *zc, u32 total_bytes_to_map) { unsigned long pages_remaining = pages_to_map; unsigned int pages_mapped; unsigned int bytes_mapped; int err; err = vm_insert_pages(vma, *address, pages, &pages_remaining); pages_mapped = pages_to_map - (unsigned int)pages_remaining; bytes_mapped = PAGE_SIZE * pages_mapped; /* Even if vm_insert_pages fails, it may have partially succeeded in * mapping (some but not all of the pages). */ *seq += bytes_mapped; *address += bytes_mapped; if (likely(!err)) return 0; /* Error: maybe zap and retry + rollback state for failed inserts. */ return tcp_zerocopy_vm_insert_batch_error(vma, pages + pages_mapped, pages_remaining, address, length, seq, zc, total_bytes_to_map, err); } #define TCP_VALID_ZC_MSG_FLAGS (TCP_CMSG_TS) static void tcp_zc_finalize_rx_tstamp(struct sock *sk, struct tcp_zerocopy_receive *zc, struct scm_timestamping_internal *tss) { unsigned long msg_control_addr; struct msghdr cmsg_dummy; msg_control_addr = (unsigned long)zc->msg_control; cmsg_dummy.msg_control_user = (void __user *)msg_control_addr; cmsg_dummy.msg_controllen = (__kernel_size_t)zc->msg_controllen; cmsg_dummy.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0; cmsg_dummy.msg_control_is_user = true; zc->msg_flags = 0; if (zc->msg_control == msg_control_addr && zc->msg_controllen == cmsg_dummy.msg_controllen) { tcp_recv_timestamp(&cmsg_dummy, sk, tss); zc->msg_control = (__u64) ((uintptr_t)cmsg_dummy.msg_control_user); zc->msg_controllen = (__u64)cmsg_dummy.msg_controllen; zc->msg_flags = (__u32)cmsg_dummy.msg_flags; } } static struct vm_area_struct *find_tcp_vma(struct mm_struct *mm, unsigned long address, bool *mmap_locked) { struct vm_area_struct *vma = lock_vma_under_rcu(mm, address); if (vma) { if (vma->vm_ops != &tcp_vm_ops) { vma_end_read(vma); return NULL; } *mmap_locked = false; return vma; } mmap_read_lock(mm); vma = vma_lookup(mm, address); if (!vma || vma->vm_ops != &tcp_vm_ops) { mmap_read_unlock(mm); return NULL; } *mmap_locked = true; return vma; } #define TCP_ZEROCOPY_PAGE_BATCH_SIZE 32 static int tcp_zerocopy_receive(struct sock *sk, struct tcp_zerocopy_receive *zc, struct scm_timestamping_internal *tss) { u32 length = 0, offset, vma_len, avail_len, copylen = 0; unsigned long address = (unsigned long)zc->address; struct page *pages[TCP_ZEROCOPY_PAGE_BATCH_SIZE]; s32 copybuf_len = zc->copybuf_len; struct tcp_sock *tp = tcp_sk(sk); const skb_frag_t *frags = NULL; unsigned int pages_to_map = 0; struct vm_area_struct *vma; struct sk_buff *skb = NULL; u32 seq = tp->copied_seq; u32 total_bytes_to_map; int inq = tcp_inq(sk); bool mmap_locked; int ret; zc->copybuf_len = 0; zc->msg_flags = 0; if (address & (PAGE_SIZE - 1) || address != zc->address) return -EINVAL; if (sk->sk_state == TCP_LISTEN) return -ENOTCONN; sock_rps_record_flow(sk); if (inq && inq <= copybuf_len) return receive_fallback_to_copy(sk, zc, inq, tss); if (inq < PAGE_SIZE) { zc->length = 0; zc->recv_skip_hint = inq; if (!inq && sock_flag(sk, SOCK_DONE)) return -EIO; return 0; } vma = find_tcp_vma(current->mm, address, &mmap_locked); if (!vma) return -EINVAL; vma_len = min_t(unsigned long, zc->length, vma->vm_end - address); avail_len = min_t(u32, vma_len, inq); total_bytes_to_map = avail_len & ~(PAGE_SIZE - 1); if (total_bytes_to_map) { if (!(zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT)) zap_page_range_single(vma, address, total_bytes_to_map, NULL); zc->length = total_bytes_to_map; zc->recv_skip_hint = 0; } else { zc->length = avail_len; zc->recv_skip_hint = avail_len; } ret = 0; while (length + PAGE_SIZE <= zc->length) { int mappable_offset; struct page *page; if (zc->recv_skip_hint < PAGE_SIZE) { u32 offset_frag; if (skb) { if (zc->recv_skip_hint > 0) break; skb = skb->next; offset = seq - TCP_SKB_CB(skb)->seq; } else { skb = tcp_recv_skb(sk, seq, &offset); } if (!skb_frags_readable(skb)) break; if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); zc->msg_flags |= TCP_CMSG_TS; } zc->recv_skip_hint = skb->len - offset; frags = skb_advance_to_frag(skb, offset, &offset_frag); if (!frags || offset_frag) break; } mappable_offset = find_next_mappable_frag(frags, zc->recv_skip_hint); if (mappable_offset) { zc->recv_skip_hint = mappable_offset; break; } page = skb_frag_page(frags); if (WARN_ON_ONCE(!page)) break; prefetchw(page); pages[pages_to_map++] = page; length += PAGE_SIZE; zc->recv_skip_hint -= PAGE_SIZE; frags++; if (pages_to_map == TCP_ZEROCOPY_PAGE_BATCH_SIZE || zc->recv_skip_hint < PAGE_SIZE) { /* Either full batch, or we're about to go to next skb * (and we cannot unroll failed ops across skbs). */ ret = tcp_zerocopy_vm_insert_batch(vma, pages, pages_to_map, &address, &length, &seq, zc, total_bytes_to_map); if (ret) goto out; pages_to_map = 0; } } if (pages_to_map) { ret = tcp_zerocopy_vm_insert_batch(vma, pages, pages_to_map, &address, &length, &seq, zc, total_bytes_to_map); } out: if (mmap_locked) mmap_read_unlock(current->mm); else vma_end_read(vma); /* Try to copy straggler data. */ if (!ret) copylen = tcp_zc_handle_leftover(zc, sk, skb, &seq, copybuf_len, tss); if (length + copylen) { WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, length + copylen); ret = 0; if (length == zc->length) zc->recv_skip_hint = 0; } else { if (!zc->recv_skip_hint && sock_flag(sk, SOCK_DONE)) ret = -EIO; } zc->length = length; return ret; } #endif /* Similar to __sock_recv_timestamp, but does not require an skb */ void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, struct scm_timestamping_internal *tss) { int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); u32 tsflags = READ_ONCE(sk->sk_tsflags); bool has_timestamping = false; if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) { if (sock_flag(sk, SOCK_RCVTSTAMP)) { if (sock_flag(sk, SOCK_RCVTSTAMPNS)) { if (new_tstamp) { struct __kernel_timespec kts = { .tv_sec = tss->ts[0].tv_sec, .tv_nsec = tss->ts[0].tv_nsec, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, sizeof(kts), &kts); } else { struct __kernel_old_timespec ts_old = { .tv_sec = tss->ts[0].tv_sec, .tv_nsec = tss->ts[0].tv_nsec, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, sizeof(ts_old), &ts_old); } } else { if (new_tstamp) { struct __kernel_sock_timeval stv = { .tv_sec = tss->ts[0].tv_sec, .tv_usec = tss->ts[0].tv_nsec / 1000, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, sizeof(stv), &stv); } else { struct __kernel_old_timeval tv = { .tv_sec = tss->ts[0].tv_sec, .tv_usec = tss->ts[0].tv_nsec / 1000, }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(tv), &tv); } } } if (tsflags & SOF_TIMESTAMPING_SOFTWARE && (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE || !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER))) has_timestamping = true; else tss->ts[0] = (struct timespec64) {0}; } if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) { if (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE && (tsflags & SOF_TIMESTAMPING_RX_HARDWARE || !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER))) has_timestamping = true; else tss->ts[2] = (struct timespec64) {0}; } if (has_timestamping) { tss->ts[1] = (struct timespec64) {0}; if (sock_flag(sk, SOCK_TSTAMP_NEW)) put_cmsg_scm_timestamping64(msg, tss); else put_cmsg_scm_timestamping(msg, tss); } } static int tcp_inq_hint(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); u32 copied_seq = READ_ONCE(tp->copied_seq); u32 rcv_nxt = READ_ONCE(tp->rcv_nxt); int inq; inq = rcv_nxt - copied_seq; if (unlikely(inq < 0 || copied_seq != READ_ONCE(tp->copied_seq))) { lock_sock(sk); inq = tp->rcv_nxt - tp->copied_seq; release_sock(sk); } /* After receiving a FIN, tell the user-space to continue reading * by returning a non-zero inq. */ if (inq == 0 && sock_flag(sk, SOCK_DONE)) inq = 1; return inq; } /* batch __xa_alloc() calls and reduce xa_lock()/xa_unlock() overhead. */ struct tcp_xa_pool { u8 max; /* max <= MAX_SKB_FRAGS */ u8 idx; /* idx <= max */ __u32 tokens[MAX_SKB_FRAGS]; netmem_ref netmems[MAX_SKB_FRAGS]; }; static void tcp_xa_pool_commit_locked(struct sock *sk, struct tcp_xa_pool *p) { int i; /* Commit part that has been copied to user space. */ for (i = 0; i < p->idx; i++) __xa_cmpxchg(&sk->sk_user_frags, p->tokens[i], XA_ZERO_ENTRY, (__force void *)p->netmems[i], GFP_KERNEL); /* Rollback what has been pre-allocated and is no longer needed. */ for (; i < p->max; i++) __xa_erase(&sk->sk_user_frags, p->tokens[i]); p->max = 0; p->idx = 0; } static void tcp_xa_pool_commit(struct sock *sk, struct tcp_xa_pool *p) { if (!p->max) return; xa_lock_bh(&sk->sk_user_frags); tcp_xa_pool_commit_locked(sk, p); xa_unlock_bh(&sk->sk_user_frags); } static int tcp_xa_pool_refill(struct sock *sk, struct tcp_xa_pool *p, unsigned int max_frags) { int err, k; if (p->idx < p->max) return 0; xa_lock_bh(&sk->sk_user_frags); tcp_xa_pool_commit_locked(sk, p); for (k = 0; k < max_frags; k++) { err = __xa_alloc(&sk->sk_user_frags, &p->tokens[k], XA_ZERO_ENTRY, xa_limit_31b, GFP_KERNEL); if (err) break; } xa_unlock_bh(&sk->sk_user_frags); p->max = k; p->idx = 0; return k ? 0 : err; } /* On error, returns the -errno. On success, returns number of bytes sent to the * user. May not consume all of @remaining_len. */ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb, unsigned int offset, struct msghdr *msg, int remaining_len) { struct dmabuf_cmsg dmabuf_cmsg = { 0 }; struct tcp_xa_pool tcp_xa_pool; unsigned int start; int i, copy, n; int sent = 0; int err = 0; tcp_xa_pool.max = 0; tcp_xa_pool.idx = 0; do { start = skb_headlen(skb); if (skb_frags_readable(skb)) { err = -ENODEV; goto out; } /* Copy header. */ copy = start - offset; if (copy > 0) { copy = min(copy, remaining_len); n = copy_to_iter(skb->data + offset, copy, &msg->msg_iter); if (n != copy) { err = -EFAULT; goto out; } offset += copy; remaining_len -= copy; /* First a dmabuf_cmsg for # bytes copied to user * buffer. */ memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg)); dmabuf_cmsg.frag_size = copy; err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR, sizeof(dmabuf_cmsg), &dmabuf_cmsg); if (err || msg->msg_flags & MSG_CTRUNC) { msg->msg_flags &= ~MSG_CTRUNC; if (!err) err = -ETOOSMALL; goto out; } sent += copy; if (remaining_len == 0) goto out; } /* after that, send information of dmabuf pages through a * sequence of cmsg */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; struct net_iov *niov; u64 frag_offset; int end; /* !skb_frags_readable() should indicate that ALL the * frags in this skb are dmabuf net_iovs. We're checking * for that flag above, but also check individual frags * here. If the tcp stack is not setting * skb_frags_readable() correctly, we still don't want * to crash here. */ if (!skb_frag_net_iov(frag)) { net_err_ratelimited("Found non-dmabuf skb with net_iov"); err = -ENODEV; goto out; } niov = skb_frag_net_iov(frag); end = start + skb_frag_size(frag); copy = end - offset; if (copy > 0) { copy = min(copy, remaining_len); frag_offset = net_iov_virtual_addr(niov) + skb_frag_off(frag) + offset - start; dmabuf_cmsg.frag_offset = frag_offset; dmabuf_cmsg.frag_size = copy; err = tcp_xa_pool_refill(sk, &tcp_xa_pool, skb_shinfo(skb)->nr_frags - i); if (err) goto out; /* Will perform the exchange later */ dmabuf_cmsg.frag_token = tcp_xa_pool.tokens[tcp_xa_pool.idx]; dmabuf_cmsg.dmabuf_id = net_iov_binding_id(niov); offset += copy; remaining_len -= copy; err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_DMABUF, sizeof(dmabuf_cmsg), &dmabuf_cmsg); if (err || msg->msg_flags & MSG_CTRUNC) { msg->msg_flags &= ~MSG_CTRUNC; if (!err) err = -ETOOSMALL; goto out; } atomic_long_inc(&niov->pp_ref_count); tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag); sent += copy; if (remaining_len == 0) goto out; } start = end; } tcp_xa_pool_commit(sk, &tcp_xa_pool); if (!remaining_len) goto out; /* if remaining_len is not satisfied yet, we need to go to the * next frag in the frag_list to satisfy remaining_len. */ skb = skb_shinfo(skb)->frag_list ?: skb->next; offset = offset - start; } while (skb); if (remaining_len) { err = -EFAULT; goto out; } out: tcp_xa_pool_commit(sk, &tcp_xa_pool); if (!sent) sent = err; return sent; } /* * This routine copies from a sock struct into the user buffer. * * Technical note: in 2.3 we work on _locked_ socket, so that * tricks with *seq access order and skb->users are not required. * Probably, code can be easily improved even more. */ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, int flags, struct scm_timestamping_internal *tss, int *cmsg_flags) { struct tcp_sock *tp = tcp_sk(sk); int last_copied_dmabuf = -1; /* uninitialized */ int copied = 0; u32 peek_seq; u32 *seq; unsigned long used; int err; int target; /* Read at least this many bytes */ long timeo; struct sk_buff *skb, *last; u32 peek_offset = 0; u32 urg_hole = 0; err = -ENOTCONN; if (sk->sk_state == TCP_LISTEN) goto out; if (tp->recvmsg_inq) { *cmsg_flags = TCP_CMSG_INQ; msg->msg_get_inq = 1; } timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); /* Urgent data needs to be handled specially. */ if (flags & MSG_OOB) goto recv_urg; if (unlikely(tp->repair)) { err = -EPERM; if (!(flags & MSG_PEEK)) goto out; if (tp->repair_queue == TCP_SEND_QUEUE) goto recv_sndq; err = -EINVAL; if (tp->repair_queue == TCP_NO_QUEUE) goto out; /* 'common' recv queue MSG_PEEK-ing */ } seq = &tp->copied_seq; if (flags & MSG_PEEK) { peek_offset = max(sk_peek_offset(sk, flags), 0); peek_seq = tp->copied_seq + peek_offset; seq = &peek_seq; } target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); do { u32 offset; /* Are we at urgent data? Stop if we have read anything or have SIGURG pending. */ if (unlikely(tp->urg_data) && tp->urg_seq == *seq) { if (copied) break; if (signal_pending(current)) { copied = timeo ? sock_intr_errno(timeo) : -EAGAIN; break; } } /* Next get a buffer. */ last = skb_peek_tail(&sk->sk_receive_queue); skb_queue_walk(&sk->sk_receive_queue, skb) { last = skb; /* Now that we have two receive queues this * shouldn't happen. */ if (WARN(before(*seq, TCP_SKB_CB(skb)->seq), "TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n", *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags)) break; offset = *seq - TCP_SKB_CB(skb)->seq; if (unlikely(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { pr_err_once("%s: found a SYN, please report !\n", __func__); offset--; } if (offset < skb->len) goto found_ok_skb; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; WARN(!(flags & MSG_PEEK), "TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n", *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags); } /* Well, if we have backlog, try to process it now yet. */ if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break; if (copied) { if (!timeo || sk->sk_err || sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN) || signal_pending(current)) break; } else { if (sock_flag(sk, SOCK_DONE)) break; if (sk->sk_err) { copied = sock_error(sk); break; } if (sk->sk_shutdown & RCV_SHUTDOWN) break; if (sk->sk_state == TCP_CLOSE) { /* This occurs when user tries to read * from never connected socket. */ copied = -ENOTCONN; break; } if (!timeo) { copied = -EAGAIN; break; } if (signal_pending(current)) { copied = sock_intr_errno(timeo); break; } } if (copied >= target) { /* Do not sleep, just process backlog. */ __sk_flush_backlog(sk); } else { tcp_cleanup_rbuf(sk, copied); err = sk_wait_data(sk, &timeo, last); if (err < 0) { err = copied ? : err; goto out; } } if ((flags & MSG_PEEK) && (peek_seq - peek_offset - copied - urg_hole != tp->copied_seq)) { net_dbg_ratelimited("TCP(%s:%d): Application bug, race in MSG_PEEK\n", current->comm, task_pid_nr(current)); peek_seq = tp->copied_seq + peek_offset; } continue; found_ok_skb: /* Ok so how much can we use? */ used = skb->len - offset; if (len < used) used = len; /* Do we have urgent data here? */ if (unlikely(tp->urg_data)) { u32 urg_offset = tp->urg_seq - *seq; if (urg_offset < used) { if (!urg_offset) { if (!sock_flag(sk, SOCK_URGINLINE)) { WRITE_ONCE(*seq, *seq + 1); urg_hole++; offset++; used--; if (!used) goto skip_copy; } } else used = urg_offset; } } if (!(flags & MSG_TRUNC)) { if (last_copied_dmabuf != -1 && last_copied_dmabuf != !skb_frags_readable(skb)) break; if (skb_frags_readable(skb)) { err = skb_copy_datagram_msg(skb, offset, msg, used); if (err) { /* Exception. Bailout! */ if (!copied) copied = -EFAULT; break; } } else { if (!(flags & MSG_SOCK_DEVMEM)) { /* dmabuf skbs can only be received * with the MSG_SOCK_DEVMEM flag. */ if (!copied) copied = -EFAULT; break; } err = tcp_recvmsg_dmabuf(sk, skb, offset, msg, used); if (err <= 0) { if (!copied) copied = -EFAULT; break; } used = err; } } last_copied_dmabuf = !skb_frags_readable(skb); WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; if (flags & MSG_PEEK) sk_peek_offset_fwd(sk, used); else sk_peek_offset_bwd(sk, used); tcp_rcv_space_adjust(sk); skip_copy: if (unlikely(tp->urg_data) && after(tp->copied_seq, tp->urg_seq)) { WRITE_ONCE(tp->urg_data, 0); tcp_fast_path_check(sk); } if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, tss); *cmsg_flags |= TCP_CMSG_TS; } if (used + offset < skb->len) continue; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; if (!(flags & MSG_PEEK)) tcp_eat_recv_skb(sk, skb); continue; found_fin_ok: /* Process the FIN. */ WRITE_ONCE(*seq, *seq + 1); if (!(flags & MSG_PEEK)) tcp_eat_recv_skb(sk, skb); break; } while (len > 0); /* According to UNIX98, msg_name/msg_namelen are ignored * on connected socket. I was just happy when found this 8) --ANK */ /* Clean up data we have read: This will do ACK frames. */ tcp_cleanup_rbuf(sk, copied); return copied; out: return err; recv_urg: err = tcp_recv_urg(sk, msg, len, flags); goto out; recv_sndq: err = tcp_peek_sndq(sk, msg, len); goto out; } int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len) { int cmsg_flags = 0, ret; struct scm_timestamping_internal tss; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) && sk->sk_state == TCP_ESTABLISHED) sk_busy_loop(sk, flags & MSG_DONTWAIT); lock_sock(sk); ret = tcp_recvmsg_locked(sk, msg, len, flags, &tss, &cmsg_flags); release_sock(sk); if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) { if (cmsg_flags & TCP_CMSG_TS) tcp_recv_timestamp(msg, sk, &tss); if (msg->msg_get_inq) { msg->msg_inq = tcp_inq_hint(sk); if (cmsg_flags & TCP_CMSG_INQ) put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(msg->msg_inq), &msg->msg_inq); } } return ret; } EXPORT_SYMBOL(tcp_recvmsg); void tcp_set_state(struct sock *sk, int state) { int oldstate = sk->sk_state; /* We defined a new enum for TCP states that are exported in BPF * so as not force the internal TCP states to be frozen. The * following checks will detect if an internal state value ever * differs from the BPF value. If this ever happens, then we will * need to remap the internal value to the BPF value before calling * tcp_call_bpf_2arg. */ BUILD_BUG_ON((int)BPF_TCP_ESTABLISHED != (int)TCP_ESTABLISHED); BUILD_BUG_ON((int)BPF_TCP_SYN_SENT != (int)TCP_SYN_SENT); BUILD_BUG_ON((int)BPF_TCP_SYN_RECV != (int)TCP_SYN_RECV); BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT1 != (int)TCP_FIN_WAIT1); BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT2 != (int)TCP_FIN_WAIT2); BUILD_BUG_ON((int)BPF_TCP_TIME_WAIT != (int)TCP_TIME_WAIT); BUILD_BUG_ON((int)BPF_TCP_CLOSE != (int)TCP_CLOSE); BUILD_BUG_ON((int)BPF_TCP_CLOSE_WAIT != (int)TCP_CLOSE_WAIT); BUILD_BUG_ON((int)BPF_TCP_LAST_ACK != (int)TCP_LAST_ACK); BUILD_BUG_ON((int)BPF_TCP_LISTEN != (int)TCP_LISTEN); BUILD_BUG_ON((int)BPF_TCP_CLOSING != (int)TCP_CLOSING); BUILD_BUG_ON((int)BPF_TCP_NEW_SYN_RECV != (int)TCP_NEW_SYN_RECV); BUILD_BUG_ON((int)BPF_TCP_BOUND_INACTIVE != (int)TCP_BOUND_INACTIVE); BUILD_BUG_ON((int)BPF_TCP_MAX_STATES != (int)TCP_MAX_STATES); /* bpf uapi header bpf.h defines an anonymous enum with values * BPF_TCP_* used by bpf programs. Currently gcc built vmlinux * is able to emit this enum in DWARF due to the above BUILD_BUG_ON. * But clang built vmlinux does not have this enum in DWARF * since clang removes the above code before generating IR/debuginfo. * Let us explicitly emit the type debuginfo to ensure the * above-mentioned anonymous enum in the vmlinux DWARF and hence BTF * regardless of which compiler is used. */ BTF_TYPE_EMIT_ENUM(BPF_TCP_ESTABLISHED); if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_STATE_CB_FLAG)) tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_STATE_CB, oldstate, state); switch (state) { case TCP_ESTABLISHED: if (oldstate != TCP_ESTABLISHED) TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); break; case TCP_CLOSE_WAIT: if (oldstate == TCP_SYN_RECV) TCP_INC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); break; case TCP_CLOSE: if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED) TCP_INC_STATS(sock_net(sk), TCP_MIB_ESTABRESETS); sk->sk_prot->unhash(sk); if (inet_csk(sk)->icsk_bind_hash && !(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) inet_put_port(sk); fallthrough; default: if (oldstate == TCP_ESTABLISHED || oldstate == TCP_CLOSE_WAIT) TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); } /* Change state AFTER socket is unhashed to avoid closed * socket sitting in hash tables. */ inet_sk_state_store(sk, state); } EXPORT_SYMBOL_GPL(tcp_set_state); /* * State processing on a close. This implements the state shift for * sending our FIN frame. Note that we only send a FIN for some * states. A shutdown() may have already sent the FIN, or we may be * closed. */ static const unsigned char new_state[16] = { /* current state: new state: action: */ [0 /* (Invalid) */] = TCP_CLOSE, [TCP_ESTABLISHED] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, [TCP_SYN_SENT] = TCP_CLOSE, [TCP_SYN_RECV] = TCP_FIN_WAIT1 | TCP_ACTION_FIN, [TCP_FIN_WAIT1] = TCP_FIN_WAIT1, [TCP_FIN_WAIT2] = TCP_FIN_WAIT2, [TCP_TIME_WAIT] = TCP_CLOSE, [TCP_CLOSE] = TCP_CLOSE, [TCP_CLOSE_WAIT] = TCP_LAST_ACK | TCP_ACTION_FIN, [TCP_LAST_ACK] = TCP_LAST_ACK, [TCP_LISTEN] = TCP_CLOSE, [TCP_CLOSING] = TCP_CLOSING, [TCP_NEW_SYN_RECV] = TCP_CLOSE, /* should not happen ! */ }; static int tcp_close_state(struct sock *sk) { int next = (int)new_state[sk->sk_state]; int ns = next & TCP_STATE_MASK; tcp_set_state(sk, ns); return next & TCP_ACTION_FIN; } /* * Shutdown the sending side of a connection. Much like close except * that we don't receive shut down or sock_set_flag(sk, SOCK_DEAD). */ void tcp_shutdown(struct sock *sk, int how) { /* We need to grab some memory, and put together a FIN, * and then put it into the queue to be sent. * Tim MacKenzie(tym@dibbler.cs.monash.edu.au) 4 Dec '92. */ if (!(how & SEND_SHUTDOWN)) return; /* If we've already sent a FIN, or it's a closed state, skip this. */ if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_CLOSE_WAIT)) { /* Clear out any half completed packets. FIN if needed. */ if (tcp_close_state(sk)) tcp_send_fin(sk); } } EXPORT_SYMBOL(tcp_shutdown); int tcp_orphan_count_sum(void) { int i, total = 0; for_each_possible_cpu(i) total += per_cpu(tcp_orphan_count, i); return max(total, 0); } static int tcp_orphan_cache; static struct timer_list tcp_orphan_timer; #define TCP_ORPHAN_TIMER_PERIOD msecs_to_jiffies(100) static void tcp_orphan_update(struct timer_list *unused) { WRITE_ONCE(tcp_orphan_cache, tcp_orphan_count_sum()); mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD); } static bool tcp_too_many_orphans(int shift) { return READ_ONCE(tcp_orphan_cache) << shift > READ_ONCE(sysctl_tcp_max_orphans); } static bool tcp_out_of_memory(const struct sock *sk) { if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF && sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2)) return true; return false; } bool tcp_check_oom(const struct sock *sk, int shift) { bool too_many_orphans, out_of_socket_memory; too_many_orphans = tcp_too_many_orphans(shift); out_of_socket_memory = tcp_out_of_memory(sk); if (too_many_orphans) net_info_ratelimited("too many orphaned sockets\n"); if (out_of_socket_memory) net_info_ratelimited("out of memory -- consider tuning tcp_mem\n"); return too_many_orphans || out_of_socket_memory; } void __tcp_close(struct sock *sk, long timeout) { struct sk_buff *skb; int data_was_unread = 0; int state; WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); /* Special case. */ inet_csk_listen_stop(sk); goto adjudge_to_death; } /* We need to flush the recv. buffs. We do this only on the * descriptor close, not protocol-sourced closes, because the * reader process may not have drained the data yet! */ while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) { u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) len--; data_was_unread += len; __kfree_skb(skb); } /* If socket has been already reset (e.g. in tcp_reset()) - kill it. */ if (sk->sk_state == TCP_CLOSE) goto adjudge_to_death; /* As outlined in RFC 2525, section 2.17, we send a RST here because * data was lost. To witness the awful effects of the old behavior of * always doing a FIN, run an older 2.1.x kernel or 2.0.x, start a bulk * GET in an FTP client, suspend the process, wait for the client to * advertise a zero window, then kill -9 the FTP client, wheee... * Note: timeout is always zero in such a case. */ if (unlikely(tcp_sk(sk)->repair)) { sk->sk_prot->disconnect(sk, 0); } else if (data_was_unread) { /* Unread data was tossed, zap the connection. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONCLOSE); tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, sk->sk_allocation, SK_RST_REASON_TCP_ABORT_ON_CLOSE); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA); } else if (tcp_close_state(sk)) { /* We FIN if the application ate all the data before * zapping the connection. */ /* RED-PEN. Formally speaking, we have broken TCP state * machine. State transitions: * * TCP_ESTABLISHED -> TCP_FIN_WAIT1 * TCP_SYN_RECV -> TCP_FIN_WAIT1 (it is difficult) * TCP_CLOSE_WAIT -> TCP_LAST_ACK * * are legal only when FIN has been sent (i.e. in window), * rather than queued out of window. Purists blame. * * F.e. "RFC state" is ESTABLISHED, * if Linux state is FIN-WAIT-1, but FIN is still not sent. * * The visible declinations are that sometimes * we enter time-wait state, when it is not required really * (harmless), do not send active resets, when they are * required by specs (TCP_ESTABLISHED, TCP_CLOSE_WAIT, when * they look as CLOSING or LAST_ACK for Linux) * Probably, I missed some more holelets. * --ANK * XXX (TFO) - To start off we don't support SYN+ACK+FIN * in a single packet! (May consider it later but will * probably need API support or TCP_CORK SYN-ACK until * data is written and socket is closed.) */ tcp_send_fin(sk); } sk_stream_wait_close(sk, timeout); adjudge_to_death: state = sk->sk_state; sock_hold(sk); sock_orphan(sk); local_bh_disable(); bh_lock_sock(sk); /* remove backlog if any, without releasing ownership. */ __release_sock(sk); this_cpu_inc(tcp_orphan_count); /* Have we already been destroyed by a softirq or backlog? */ if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE) goto out; /* This is a (useful) BSD violating of the RFC. There is a * problem with TCP as specified in that the other end could * keep a socket open forever with no application left this end. * We use a 1 minute timeout (about the same as BSD) then kill * our end. If they send after that then tough - BUT: long enough * that we won't make the old 4*rto = almost no time - whoops * reset mistake. * * Nope, it was not mistake. It is really desired behaviour * f.e. on http servers, when such sockets are useless, but * consume significant resources. Let's do it with special * linger2 option. --ANK */ if (sk->sk_state == TCP_FIN_WAIT2) { struct tcp_sock *tp = tcp_sk(sk); if (READ_ONCE(tp->linger2) < 0) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_ABORT_ON_LINGER); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONLINGER); } else { const int tmo = tcp_fin_time(sk); if (tmo > TCP_TIMEWAIT_LEN) { inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN); } else { tcp_time_wait(sk, TCP_FIN_WAIT2, tmo); goto out; } } } if (sk->sk_state != TCP_CLOSE) { if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_ABORT_ON_MEMORY); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); } else if (!check_net(sock_net(sk))) { /* Not possible to send reset; just close */ tcp_set_state(sk, TCP_CLOSE); } } if (sk->sk_state == TCP_CLOSE) { struct request_sock *req; req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, lockdep_sock_is_held(sk)); /* We could get here with a non-NULL req if the socket is * aborted (e.g., closed with unread data) before 3WHS * finishes. */ if (req) reqsk_fastopen_remove(sk, req, false); inet_csk_destroy_sock(sk); } /* Otherwise, socket is reprieved until protocol close. */ out: bh_unlock_sock(sk); local_bh_enable(); } void tcp_close(struct sock *sk, long timeout) { lock_sock(sk); __tcp_close(sk, timeout); release_sock(sk); if (!sk->sk_net_refcnt) inet_csk_clear_xmit_timers_sync(sk); sock_put(sk); } EXPORT_SYMBOL(tcp_close); /* These states need RST on ABORT according to RFC793 */ static inline bool tcp_need_reset(int state) { return (1 << state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_SYN_RECV); } static void tcp_rtx_queue_purge(struct sock *sk) { struct rb_node *p = rb_first(&sk->tcp_rtx_queue); tcp_sk(sk)->highest_sack = NULL; while (p) { struct sk_buff *skb = rb_to_skb(p); p = rb_next(p); /* Since we are deleting whole queue, no need to * list_del(&skb->tcp_tsorted_anchor) */ tcp_rtx_queue_unlink(skb, sk); tcp_wmem_free_skb(sk, skb); } } void tcp_write_queue_purge(struct sock *sk) { struct sk_buff *skb; tcp_chrono_stop(sk, TCP_CHRONO_BUSY); while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) { tcp_skb_tsorted_anchor_cleanup(skb); tcp_wmem_free_skb(sk, skb); } tcp_rtx_queue_purge(sk); INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); tcp_clear_all_retrans_hints(tcp_sk(sk)); tcp_sk(sk)->packets_out = 0; inet_csk(sk)->icsk_backoff = 0; } int tcp_disconnect(struct sock *sk, int flags) { struct inet_sock *inet = inet_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int old_state = sk->sk_state; u32 seq; if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); /* ABORT function of RFC793 */ if (old_state == TCP_LISTEN) { inet_csk_listen_stop(sk); } else if (unlikely(tp->repair)) { WRITE_ONCE(sk->sk_err, ECONNABORTED); } else if (tcp_need_reset(old_state)) { tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_TCP_STATE); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (tp->snd_nxt != tp->write_seq && (1 << old_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) { /* The last check adjusts for discrepancy of Linux wrt. RFC * states */ tcp_send_active_reset(sk, gfp_any(), SK_RST_REASON_TCP_DISCONNECT_WITH_DATA); WRITE_ONCE(sk->sk_err, ECONNRESET); } else if (old_state == TCP_SYN_SENT) WRITE_ONCE(sk->sk_err, ECONNRESET); tcp_clear_xmit_timers(sk); __skb_queue_purge(&sk->sk_receive_queue); WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); WRITE_ONCE(tp->urg_data, 0); sk_set_peek_off(sk, -1); tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); skb_rbtree_purge(&tp->out_of_order_queue); inet->inet_dport = 0; inet_bhash2_reset_saddr(sk); WRITE_ONCE(sk->sk_shutdown, 0); sock_reset_flag(sk, SOCK_DONE); tp->srtt_us = 0; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); tp->rcv_rtt_last_tsecr = 0; seq = tp->write_seq + tp->max_window + 2; if (!seq) seq = 1; WRITE_ONCE(tp->write_seq, seq); icsk->icsk_backoff = 0; icsk->icsk_probes_out = 0; icsk->icsk_probes_tstamp = 0; icsk->icsk_rto = TCP_TIMEOUT_INIT; icsk->icsk_rto_min = TCP_RTO_MIN; icsk->icsk_delack_max = TCP_DELACK_MAX; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tcp_snd_cwnd_set(tp, TCP_INIT_CWND); tp->snd_cwnd_cnt = 0; tp->is_cwnd_limited = 0; tp->max_packets_out = 0; tp->window_clamp = 0; tp->delivered = 0; tp->delivered_ce = 0; if (icsk->icsk_ca_initialized && icsk->icsk_ca_ops->release) icsk->icsk_ca_ops->release(sk); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); icsk->icsk_ca_initialized = 0; tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); tp->total_retrans = 0; inet_csk_delack_init(sk); /* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0 * issue in __tcp_select_window() */ icsk->icsk_ack.rcv_mss = TCP_MIN_MSS; memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); dst_release(unrcu_pointer(xchg(&sk->sk_rx_dst, NULL))); tcp_saved_syn_free(tp); tp->compressed_ack = 0; tp->segs_in = 0; tp->segs_out = 0; tp->bytes_sent = 0; tp->bytes_acked = 0; tp->bytes_received = 0; tp->bytes_retrans = 0; tp->data_segs_in = 0; tp->data_segs_out = 0; tp->duplicate_sack[0].start_seq = 0; tp->duplicate_sack[0].end_seq = 0; tp->dsack_dups = 0; tp->reord_seen = 0; tp->retrans_out = 0; tp->sacked_out = 0; tp->tlp_high_seq = 0; tp->last_oow_ack_time = 0; tp->plb_rehash = 0; /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; tp->rate_app_limited = 1; tp->rack.mstamp = 0; tp->rack.advanced = 0; tp->rack.reo_wnd_steps = 1; tp->rack.last_delivered = 0; tp->rack.reo_wnd_persist = 0; tp->rack.dsack_seen = 0; tp->syn_data_acked = 0; tp->rx_opt.saw_tstamp = 0; tp->rx_opt.dsack = 0; tp->rx_opt.num_sacks = 0; tp->rcv_ooopack = 0; /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); inet_clear_bit(DEFER_CONNECT, sk); tp->fastopen_client_fail = 0; WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); if (sk->sk_frag.page) { put_page(sk->sk_frag.page); sk->sk_frag.page = NULL; sk->sk_frag.offset = 0; } sk_error_report(sk); return 0; } EXPORT_SYMBOL(tcp_disconnect); static inline bool tcp_can_repair_sock(const struct sock *sk) { return sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) && (sk->sk_state != TCP_LISTEN); } static int tcp_repair_set_window(struct tcp_sock *tp, sockptr_t optbuf, int len) { struct tcp_repair_window opt; if (!tp->repair) return -EPERM; if (len != sizeof(opt)) return -EINVAL; if (copy_from_sockptr(&opt, optbuf, sizeof(opt))) return -EFAULT; if (opt.max_window < opt.snd_wnd) return -EINVAL; if (after(opt.snd_wl1, tp->rcv_nxt + opt.rcv_wnd)) return -EINVAL; if (after(opt.rcv_wup, tp->rcv_nxt)) return -EINVAL; tp->snd_wl1 = opt.snd_wl1; tp->snd_wnd = opt.snd_wnd; tp->max_window = opt.max_window; tp->rcv_wnd = opt.rcv_wnd; tp->rcv_wup = opt.rcv_wup; return 0; } static int tcp_repair_options_est(struct sock *sk, sockptr_t optbuf, unsigned int len) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_repair_opt opt; size_t offset = 0; while (len >= sizeof(opt)) { if (copy_from_sockptr_offset(&opt, optbuf, offset, sizeof(opt))) return -EFAULT; offset += sizeof(opt); len -= sizeof(opt); switch (opt.opt_code) { case TCPOPT_MSS: tp->rx_opt.mss_clamp = opt.opt_val; tcp_mtup_init(sk); break; case TCPOPT_WINDOW: { u16 snd_wscale = opt.opt_val & 0xFFFF; u16 rcv_wscale = opt.opt_val >> 16; if (snd_wscale > TCP_MAX_WSCALE || rcv_wscale > TCP_MAX_WSCALE) return -EFBIG; tp->rx_opt.snd_wscale = snd_wscale; tp->rx_opt.rcv_wscale = rcv_wscale; tp->rx_opt.wscale_ok = 1; } break; case TCPOPT_SACK_PERM: if (opt.opt_val != 0) return -EINVAL; tp->rx_opt.sack_ok |= TCP_SACK_SEEN; break; case TCPOPT_TIMESTAMP: if (opt.opt_val != 0) return -EINVAL; tp->rx_opt.tstamp_ok = 1; break; } } return 0; } DEFINE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); EXPORT_SYMBOL(tcp_tx_delay_enabled); static void tcp_enable_tx_delay(void) { if (!static_branch_unlikely(&tcp_tx_delay_enabled)) { static int __tcp_tx_delay_enabled = 0; if (cmpxchg(&__tcp_tx_delay_enabled, 0, 1) == 0) { static_branch_enable(&tcp_tx_delay_enabled); pr_info("TCP_TX_DELAY enabled\n"); } } } /* When set indicates to always queue non-full frames. Later the user clears * this option and we transmit any pending partial frames in the queue. This is * meant to be used alongside sendfile() to get properly filled frames when the * user (for example) must write out headers with a write() call first and then * use sendfile to send out the data parts. * * TCP_CORK can be set together with TCP_NODELAY and it is stronger than * TCP_NODELAY. */ void __tcp_sock_set_cork(struct sock *sk, bool on) { struct tcp_sock *tp = tcp_sk(sk); if (on) { tp->nonagle |= TCP_NAGLE_CORK; } else { tp->nonagle &= ~TCP_NAGLE_CORK; if (tp->nonagle & TCP_NAGLE_OFF) tp->nonagle |= TCP_NAGLE_PUSH; tcp_push_pending_frames(sk); } } void tcp_sock_set_cork(struct sock *sk, bool on) { lock_sock(sk); __tcp_sock_set_cork(sk, on); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_cork); /* TCP_NODELAY is weaker than TCP_CORK, so that this option on corked socket is * remembered, but it is not activated until cork is cleared. * * However, when TCP_NODELAY is set we make an explicit push, which overrides * even TCP_CORK for currently queued segments. */ void __tcp_sock_set_nodelay(struct sock *sk, bool on) { if (on) { tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH; tcp_push_pending_frames(sk); } else { tcp_sk(sk)->nonagle &= ~TCP_NAGLE_OFF; } } void tcp_sock_set_nodelay(struct sock *sk) { lock_sock(sk); __tcp_sock_set_nodelay(sk, true); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_nodelay); static void __tcp_sock_set_quickack(struct sock *sk, int val) { if (!val) { inet_csk_enter_pingpong_mode(sk); return; } inet_csk_exit_pingpong_mode(sk); if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) && inet_csk_ack_scheduled(sk)) { inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_PUSHED; tcp_cleanup_rbuf(sk, 1); if (!(val & 1)) inet_csk_enter_pingpong_mode(sk); } } void tcp_sock_set_quickack(struct sock *sk, int val) { lock_sock(sk); __tcp_sock_set_quickack(sk, val); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_quickack); int tcp_sock_set_syncnt(struct sock *sk, int val) { if (val < 1 || val > MAX_TCP_SYNCNT) return -EINVAL; WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val); return 0; } EXPORT_SYMBOL(tcp_sock_set_syncnt); int tcp_sock_set_user_timeout(struct sock *sk, int val) { /* Cap the max time in ms TCP will retry or probe the window * before giving up and aborting (ETIMEDOUT) a connection. */ if (val < 0) return -EINVAL; WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val); return 0; } EXPORT_SYMBOL(tcp_sock_set_user_timeout); int tcp_sock_set_keepidle_locked(struct sock *sk, int val) { struct tcp_sock *tp = tcp_sk(sk); if (val < 1 || val > MAX_TCP_KEEPIDLE) return -EINVAL; /* Paired with WRITE_ONCE() in keepalive_time_when() */ WRITE_ONCE(tp->keepalive_time, val * HZ); if (sock_flag(sk, SOCK_KEEPOPEN) && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { u32 elapsed = keepalive_time_elapsed(tp); if (tp->keepalive_time > elapsed) elapsed = tp->keepalive_time - elapsed; else elapsed = 0; inet_csk_reset_keepalive_timer(sk, elapsed); } return 0; } int tcp_sock_set_keepidle(struct sock *sk, int val) { int err; lock_sock(sk); err = tcp_sock_set_keepidle_locked(sk, val); release_sock(sk); return err; } EXPORT_SYMBOL(tcp_sock_set_keepidle); int tcp_sock_set_keepintvl(struct sock *sk, int val) { if (val < 1 || val > MAX_TCP_KEEPINTVL) return -EINVAL; WRITE_ONCE(tcp_sk(sk)->keepalive_intvl, val * HZ); return 0; } EXPORT_SYMBOL(tcp_sock_set_keepintvl); int tcp_sock_set_keepcnt(struct sock *sk, int val) { if (val < 1 || val > MAX_TCP_KEEPCNT) return -EINVAL; /* Paired with READ_ONCE() in keepalive_probes() */ WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val); return 0; } EXPORT_SYMBOL(tcp_sock_set_keepcnt); int tcp_set_window_clamp(struct sock *sk, int val) { struct tcp_sock *tp = tcp_sk(sk); if (!val) { if (sk->sk_state != TCP_CLOSE) return -EINVAL; WRITE_ONCE(tp->window_clamp, 0); } else { u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp; u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ? SOCK_MIN_RCVBUF / 2 : val; if (new_window_clamp == old_window_clamp) return 0; WRITE_ONCE(tp->window_clamp, new_window_clamp); if (new_window_clamp < old_window_clamp) { /* need to apply the reserved mem provisioning only * when shrinking the window clamp */ __tcp_adjust_rcv_ssthresh(sk, tp->window_clamp); } else { new_rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp); tp->rcv_ssthresh = max(new_rcv_ssthresh, tp->rcv_ssthresh); } } return 0; } /* * Socket option code for TCP. */ int do_tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); int val; int err = 0; /* These are data/string values, all the others are ints */ switch (optname) { case TCP_CONGESTION: { char name[TCP_CA_NAME_MAX]; if (optlen < 1) return -EINVAL; val = strncpy_from_sockptr(name, optval, min_t(long, TCP_CA_NAME_MAX-1, optlen)); if (val < 0) return -EFAULT; name[val] = 0; sockopt_lock_sock(sk); err = tcp_set_congestion_control(sk, name, !has_current_bpf_ctx(), sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)); sockopt_release_sock(sk); return err; } case TCP_ULP: { char name[TCP_ULP_NAME_MAX]; if (optlen < 1) return -EINVAL; val = strncpy_from_sockptr(name, optval, min_t(long, TCP_ULP_NAME_MAX - 1, optlen)); if (val < 0) return -EFAULT; name[val] = 0; sockopt_lock_sock(sk); err = tcp_set_ulp(sk, name); sockopt_release_sock(sk); return err; } case TCP_FASTOPEN_KEY: { __u8 key[TCP_FASTOPEN_KEY_BUF_LENGTH]; __u8 *backup_key = NULL; /* Allow a backup key as well to facilitate key rotation * First key is the active one. */ if (optlen != TCP_FASTOPEN_KEY_LENGTH && optlen != TCP_FASTOPEN_KEY_BUF_LENGTH) return -EINVAL; if (copy_from_sockptr(key, optval, optlen)) return -EFAULT; if (optlen == TCP_FASTOPEN_KEY_BUF_LENGTH) backup_key = key + TCP_FASTOPEN_KEY_LENGTH; return tcp_fastopen_reset_cipher(net, sk, key, backup_key); } default: /* fallthru */ break; } if (optlen < sizeof(int)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; /* Handle options that can be set without locking the socket. */ switch (optname) { case TCP_SYNCNT: return tcp_sock_set_syncnt(sk, val); case TCP_USER_TIMEOUT: return tcp_sock_set_user_timeout(sk, val); case TCP_KEEPINTVL: return tcp_sock_set_keepintvl(sk, val); case TCP_KEEPCNT: return tcp_sock_set_keepcnt(sk, val); case TCP_LINGER2: if (val < 0) WRITE_ONCE(tp->linger2, -1); else if (val > TCP_FIN_TIMEOUT_MAX / HZ) WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX); else WRITE_ONCE(tp->linger2, val * HZ); return 0; case TCP_DEFER_ACCEPT: /* Translate value in seconds to number of retransmits */ WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept, secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ)); return 0; } sockopt_lock_sock(sk); switch (optname) { case TCP_MAXSEG: /* Values greater than interface MTU won't take effect. However * at the point when this call is done we typically don't yet * know which interface is going to be used */ if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) { err = -EINVAL; break; } tp->rx_opt.user_mss = val; break; case TCP_NODELAY: __tcp_sock_set_nodelay(sk, val); break; case TCP_THIN_LINEAR_TIMEOUTS: if (val < 0 || val > 1) err = -EINVAL; else tp->thin_lto = val; break; case TCP_THIN_DUPACK: if (val < 0 || val > 1) err = -EINVAL; break; case TCP_REPAIR: if (!tcp_can_repair_sock(sk)) err = -EPERM; else if (val == TCP_REPAIR_ON) { tp->repair = 1; sk->sk_reuse = SK_FORCE_REUSE; tp->repair_queue = TCP_NO_QUEUE; } else if (val == TCP_REPAIR_OFF) { tp->repair = 0; sk->sk_reuse = SK_NO_REUSE; tcp_send_window_probe(sk); } else if (val == TCP_REPAIR_OFF_NO_WP) { tp->repair = 0; sk->sk_reuse = SK_NO_REUSE; } else err = -EINVAL; break; case TCP_REPAIR_QUEUE: if (!tp->repair) err = -EPERM; else if ((unsigned int)val < TCP_QUEUES_NR) tp->repair_queue = val; else err = -EINVAL; break; case TCP_QUEUE_SEQ: if (sk->sk_state != TCP_CLOSE) { err = -EPERM; } else if (tp->repair_queue == TCP_SEND_QUEUE) { if (!tcp_rtx_queue_empty(sk)) err = -EPERM; else WRITE_ONCE(tp->write_seq, val); } else if (tp->repair_queue == TCP_RECV_QUEUE) { if (tp->rcv_nxt != tp->copied_seq) { err = -EPERM; } else { WRITE_ONCE(tp->rcv_nxt, val); WRITE_ONCE(tp->copied_seq, val); } } else { err = -EINVAL; } break; case TCP_REPAIR_OPTIONS: if (!tp->repair) err = -EINVAL; else if (sk->sk_state == TCP_ESTABLISHED && !tp->bytes_sent) err = tcp_repair_options_est(sk, optval, optlen); else err = -EPERM; break; case TCP_CORK: __tcp_sock_set_cork(sk, val); break; case TCP_KEEPIDLE: err = tcp_sock_set_keepidle_locked(sk, val); break; case TCP_SAVE_SYN: /* 0: disable, 1: enable, 2: start from ether_header */ if (val < 0 || val > 2) err = -EINVAL; else tp->save_syn = val; break; case TCP_WINDOW_CLAMP: err = tcp_set_window_clamp(sk, val); break; case TCP_QUICKACK: __tcp_sock_set_quickack(sk, val); break; case TCP_AO_REPAIR: if (!tcp_can_repair_sock(sk)) { err = -EPERM; break; } err = tcp_ao_set_repair(sk, optval, optlen); break; #ifdef CONFIG_TCP_AO case TCP_AO_ADD_KEY: case TCP_AO_DEL_KEY: case TCP_AO_INFO: { /* If this is the first TCP-AO setsockopt() on the socket, * sk_state has to be LISTEN or CLOSE. Allow TCP_REPAIR * in any state. */ if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) goto ao_parse; if (rcu_dereference_protected(tcp_sk(sk)->ao_info, lockdep_sock_is_held(sk))) goto ao_parse; if (tp->repair) goto ao_parse; err = -EISCONN; break; ao_parse: err = tp->af_specific->ao_parse(sk, optname, optval, optlen); break; } #endif #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: case TCP_MD5SIG_EXT: err = tp->af_specific->md5_parse(sk, optname, optval, optlen); break; #endif case TCP_FASTOPEN: if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { tcp_fastopen_init_key_once(net); fastopen_queue_tune(sk, val); } else { err = -EINVAL; } break; case TCP_FASTOPEN_CONNECT: if (val > 1 || val < 0) { err = -EINVAL; } else if (READ_ONCE(net->ipv4.sysctl_tcp_fastopen) & TFO_CLIENT_ENABLE) { if (sk->sk_state == TCP_CLOSE) tp->fastopen_connect = val; else err = -EINVAL; } else { err = -EOPNOTSUPP; } break; case TCP_FASTOPEN_NO_COOKIE: if (val > 1 || val < 0) err = -EINVAL; else if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) err = -EINVAL; else tp->fastopen_no_cookie = val; break; case TCP_TIMESTAMP: if (!tp->repair) { err = -EPERM; break; } /* val is an opaque field, * and low order bit contains usec_ts enable bit. * Its a best effort, and we do not care if user makes an error. */ tp->tcp_usec_ts = val & 1; WRITE_ONCE(tp->tsoffset, val - tcp_clock_ts(tp->tcp_usec_ts)); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); break; case TCP_NOTSENT_LOWAT: WRITE_ONCE(tp->notsent_lowat, val); sk->sk_write_space(sk); break; case TCP_INQ: if (val > 1 || val < 0) err = -EINVAL; else tp->recvmsg_inq = val; break; case TCP_TX_DELAY: if (val) tcp_enable_tx_delay(); WRITE_ONCE(tp->tcp_tx_delay, val); break; default: err = -ENOPROTOOPT; break; } sockopt_release_sock(sk); return err; } int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { const struct inet_connection_sock *icsk = inet_csk(sk); if (level != SOL_TCP) /* Paired with WRITE_ONCE() in do_ipv6_setsockopt() and tcp_v6_connect() */ return READ_ONCE(icsk->icsk_af_ops)->setsockopt(sk, level, optname, optval, optlen); return do_tcp_setsockopt(sk, level, optname, optval, optlen); } EXPORT_SYMBOL(tcp_setsockopt); static void tcp_get_info_chrono_stats(const struct tcp_sock *tp, struct tcp_info *info) { u64 stats[__TCP_CHRONO_MAX], total = 0; enum tcp_chrono i; for (i = TCP_CHRONO_BUSY; i < __TCP_CHRONO_MAX; ++i) { stats[i] = tp->chrono_stat[i - 1]; if (i == tp->chrono_type) stats[i] += tcp_jiffies32 - tp->chrono_start; stats[i] *= USEC_PER_SEC / HZ; total += stats[i]; } info->tcpi_busy_time = total; info->tcpi_rwnd_limited = stats[TCP_CHRONO_RWND_LIMITED]; info->tcpi_sndbuf_limited = stats[TCP_CHRONO_SNDBUF_LIMITED]; } /* Return information about state of tcp endpoint in API format. */ void tcp_get_info(struct sock *sk, struct tcp_info *info) { const struct tcp_sock *tp = tcp_sk(sk); /* iff sk_type == SOCK_STREAM */ const struct inet_connection_sock *icsk = inet_csk(sk); unsigned long rate; u32 now; u64 rate64; bool slow; memset(info, 0, sizeof(*info)); if (sk->sk_type != SOCK_STREAM) return; info->tcpi_state = inet_sk_state_load(sk); /* Report meaningful fields for all TCP states, including listeners */ rate = READ_ONCE(sk->sk_pacing_rate); rate64 = (rate != ~0UL) ? rate : ~0ULL; info->tcpi_pacing_rate = rate64; rate = READ_ONCE(sk->sk_max_pacing_rate); rate64 = (rate != ~0UL) ? rate : ~0ULL; info->tcpi_max_pacing_rate = rate64; info->tcpi_reordering = tp->reordering; info->tcpi_snd_cwnd = tcp_snd_cwnd(tp); if (info->tcpi_state == TCP_LISTEN) { /* listeners aliased fields : * tcpi_unacked -> Number of children ready for accept() * tcpi_sacked -> max backlog */ info->tcpi_unacked = READ_ONCE(sk->sk_ack_backlog); info->tcpi_sacked = READ_ONCE(sk->sk_max_ack_backlog); return; } slow = lock_sock_fast(sk); info->tcpi_ca_state = icsk->icsk_ca_state; info->tcpi_retransmits = icsk->icsk_retransmits; info->tcpi_probes = icsk->icsk_probes_out; info->tcpi_backoff = icsk->icsk_backoff; if (tp->rx_opt.tstamp_ok) info->tcpi_options |= TCPI_OPT_TIMESTAMPS; if (tcp_is_sack(tp)) info->tcpi_options |= TCPI_OPT_SACK; if (tp->rx_opt.wscale_ok) { info->tcpi_options |= TCPI_OPT_WSCALE; info->tcpi_snd_wscale = tp->rx_opt.snd_wscale; info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale; } if (tp->ecn_flags & TCP_ECN_OK) info->tcpi_options |= TCPI_OPT_ECN; if (tp->ecn_flags & TCP_ECN_SEEN) info->tcpi_options |= TCPI_OPT_ECN_SEEN; if (tp->syn_data_acked) info->tcpi_options |= TCPI_OPT_SYN_DATA; if (tp->tcp_usec_ts) info->tcpi_options |= TCPI_OPT_USEC_TS; info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto); info->tcpi_ato = jiffies_to_usecs(min_t(u32, icsk->icsk_ack.ato, tcp_delack_max(sk))); info->tcpi_snd_mss = tp->mss_cache; info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss; info->tcpi_unacked = tp->packets_out; info->tcpi_sacked = tp->sacked_out; info->tcpi_lost = tp->lost_out; info->tcpi_retrans = tp->retrans_out; now = tcp_jiffies32; info->tcpi_last_data_sent = jiffies_to_msecs(now - tp->lsndtime); info->tcpi_last_data_recv = jiffies_to_msecs(now - icsk->icsk_ack.lrcvtime); info->tcpi_last_ack_recv = jiffies_to_msecs(now - tp->rcv_tstamp); info->tcpi_pmtu = icsk->icsk_pmtu_cookie; info->tcpi_rcv_ssthresh = tp->rcv_ssthresh; info->tcpi_rtt = tp->srtt_us >> 3; info->tcpi_rttvar = tp->mdev_us >> 2; info->tcpi_snd_ssthresh = tp->snd_ssthresh; info->tcpi_advmss = tp->advmss; info->tcpi_rcv_rtt = tp->rcv_rtt_est.rtt_us >> 3; info->tcpi_rcv_space = tp->rcvq_space.space; info->tcpi_total_retrans = tp->total_retrans; info->tcpi_bytes_acked = tp->bytes_acked; info->tcpi_bytes_received = tp->bytes_received; info->tcpi_notsent_bytes = max_t(int, 0, tp->write_seq - tp->snd_nxt); tcp_get_info_chrono_stats(tp, info); info->tcpi_segs_out = tp->segs_out; /* segs_in and data_segs_in can be updated from tcp_segs_in() from BH */ info->tcpi_segs_in = READ_ONCE(tp->segs_in); info->tcpi_data_segs_in = READ_ONCE(tp->data_segs_in); info->tcpi_min_rtt = tcp_min_rtt(tp); info->tcpi_data_segs_out = tp->data_segs_out; info->tcpi_delivery_rate_app_limited = tp->rate_app_limited ? 1 : 0; rate64 = tcp_compute_delivery_rate(tp); if (rate64) info->tcpi_delivery_rate = rate64; info->tcpi_delivered = tp->delivered; info->tcpi_delivered_ce = tp->delivered_ce; info->tcpi_bytes_sent = tp->bytes_sent; info->tcpi_bytes_retrans = tp->bytes_retrans; info->tcpi_dsack_dups = tp->dsack_dups; info->tcpi_reord_seen = tp->reord_seen; info->tcpi_rcv_ooopack = tp->rcv_ooopack; info->tcpi_snd_wnd = tp->snd_wnd; info->tcpi_rcv_wnd = tp->rcv_wnd; info->tcpi_rehash = tp->plb_rehash + tp->timeout_rehash; info->tcpi_fastopen_client_fail = tp->fastopen_client_fail; info->tcpi_total_rto = tp->total_rto; info->tcpi_total_rto_recoveries = tp->total_rto_recoveries; info->tcpi_total_rto_time = tp->total_rto_time; if (tp->rto_stamp) info->tcpi_total_rto_time += tcp_clock_ms() - tp->rto_stamp; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); static size_t tcp_opt_stats_get_size(void) { return nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BUSY */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_RWND_LIMITED */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_SNDBUF_LIMITED */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DATA_SEGS_OUT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_TOTAL_RETRANS */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_PACING_RATE */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DELIVERY_RATE */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_CWND */ nla_total_size(sizeof(u32)) + /* TCP_NLA_REORDERING */ nla_total_size(sizeof(u32)) + /* TCP_NLA_MIN_RTT */ nla_total_size(sizeof(u8)) + /* TCP_NLA_RECUR_RETRANS */ nla_total_size(sizeof(u8)) + /* TCP_NLA_DELIVERY_RATE_APP_LMT */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SNDQ_SIZE */ nla_total_size(sizeof(u8)) + /* TCP_NLA_CA_STATE */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_SSTHRESH */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */ nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */ nla_total_size(sizeof(u32)) + /* TCP_NLA_REORD_SEEN */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SRTT */ nla_total_size(sizeof(u16)) + /* TCP_NLA_TIMEOUT_REHASH */ nla_total_size(sizeof(u32)) + /* TCP_NLA_BYTES_NOTSENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_EDT */ nla_total_size(sizeof(u8)) + /* TCP_NLA_TTL */ nla_total_size(sizeof(u32)) + /* TCP_NLA_REHASH */ 0; } /* Returns TTL or hop limit of an incoming packet from skb. */ static u8 tcp_skb_ttl_or_hop_limit(const struct sk_buff *skb) { if (skb->protocol == htons(ETH_P_IP)) return ip_hdr(skb)->ttl; else if (skb->protocol == htons(ETH_P_IPV6)) return ipv6_hdr(skb)->hop_limit; else return 0; } struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, const struct sk_buff *orig_skb, const struct sk_buff *ack_skb) { const struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *stats; struct tcp_info info; unsigned long rate; u64 rate64; stats = alloc_skb(tcp_opt_stats_get_size(), GFP_ATOMIC); if (!stats) return NULL; tcp_get_info_chrono_stats(tp, &info); nla_put_u64_64bit(stats, TCP_NLA_BUSY, info.tcpi_busy_time, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_RWND_LIMITED, info.tcpi_rwnd_limited, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_SNDBUF_LIMITED, info.tcpi_sndbuf_limited, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_DATA_SEGS_OUT, tp->data_segs_out, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_TOTAL_RETRANS, tp->total_retrans, TCP_NLA_PAD); rate = READ_ONCE(sk->sk_pacing_rate); rate64 = (rate != ~0UL) ? rate : ~0ULL; nla_put_u64_64bit(stats, TCP_NLA_PACING_RATE, rate64, TCP_NLA_PAD); rate64 = tcp_compute_delivery_rate(tp); nla_put_u64_64bit(stats, TCP_NLA_DELIVERY_RATE, rate64, TCP_NLA_PAD); nla_put_u32(stats, TCP_NLA_SND_CWND, tcp_snd_cwnd(tp)); nla_put_u32(stats, TCP_NLA_REORDERING, tp->reordering); nla_put_u32(stats, TCP_NLA_MIN_RTT, tcp_min_rtt(tp)); nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, inet_csk(sk)->icsk_retransmits); nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited); nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, tp->snd_ssthresh); nla_put_u32(stats, TCP_NLA_DELIVERED, tp->delivered); nla_put_u32(stats, TCP_NLA_DELIVERED_CE, tp->delivered_ce); nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una); nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state); nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, tp->bytes_sent, TCP_NLA_PAD); nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans, TCP_NLA_PAD); nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups); nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen); nla_put_u32(stats, TCP_NLA_SRTT, tp->srtt_us >> 3); nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash); nla_put_u32(stats, TCP_NLA_BYTES_NOTSENT, max_t(int, 0, tp->write_seq - tp->snd_nxt)); nla_put_u64_64bit(stats, TCP_NLA_EDT, orig_skb->skb_mstamp_ns, TCP_NLA_PAD); if (ack_skb) nla_put_u8(stats, TCP_NLA_TTL, tcp_skb_ttl_or_hop_limit(ack_skb)); nla_put_u32(stats, TCP_NLA_REHASH, tp->plb_rehash + tp->timeout_rehash); return stats; } int do_tcp_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); int val, len; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0) return -EINVAL; len = min_t(unsigned int, len, sizeof(int)); switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; if (tp->rx_opt.user_mss && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) val = tp->rx_opt.user_mss; if (tp->repair) val = tp->rx_opt.mss_clamp; break; case TCP_NODELAY: val = !!(tp->nonagle&TCP_NAGLE_OFF); break; case TCP_CORK: val = !!(tp->nonagle&TCP_NAGLE_CORK); break; case TCP_KEEPIDLE: val = keepalive_time_when(tp) / HZ; break; case TCP_KEEPINTVL: val = keepalive_intvl_when(tp) / HZ; break; case TCP_KEEPCNT: val = keepalive_probes(tp); break; case TCP_SYNCNT: val = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: val = READ_ONCE(tp->linger2); if (val >= 0) val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; case TCP_DEFER_ACCEPT: val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept); val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: val = READ_ONCE(tp->window_clamp); break; case TCP_INFO: { struct tcp_info info; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; tcp_get_info(sk, &info); len = min_t(unsigned int, len, sizeof(info)); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &info, len)) return -EFAULT; return 0; } case TCP_CC_INFO: { const struct tcp_congestion_ops *ca_ops; union tcp_cc_info info; size_t sz = 0; int attr; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; ca_ops = icsk->icsk_ca_ops; if (ca_ops && ca_ops->get_info) sz = ca_ops->get_info(sk, ~0U, &attr, &info); len = min_t(unsigned int, len, sz); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &info, len)) return -EFAULT; return 0; } case TCP_QUICKACK: val = !inet_csk_in_pingpong_mode(sk); break; case TCP_CONGESTION: if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; len = min_t(unsigned int, len, TCP_CA_NAME_MAX); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, icsk->icsk_ca_ops->name, len)) return -EFAULT; return 0; case TCP_ULP: if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; len = min_t(unsigned int, len, TCP_ULP_NAME_MAX); if (!icsk->icsk_ulp_ops) { len = 0; if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; return 0; } if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, icsk->icsk_ulp_ops->name, len)) return -EFAULT; return 0; case TCP_FASTOPEN_KEY: { u64 key[TCP_FASTOPEN_KEY_BUF_LENGTH / sizeof(u64)]; unsigned int key_len; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; key_len = tcp_fastopen_get_cipher(net, icsk, key) * TCP_FASTOPEN_KEY_LENGTH; len = min_t(unsigned int, len, key_len); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, key, len)) return -EFAULT; return 0; } case TCP_THIN_LINEAR_TIMEOUTS: val = tp->thin_lto; break; case TCP_THIN_DUPACK: val = 0; break; case TCP_REPAIR: val = tp->repair; break; case TCP_REPAIR_QUEUE: if (tp->repair) val = tp->repair_queue; else return -EINVAL; break; case TCP_REPAIR_WINDOW: { struct tcp_repair_window opt; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len != sizeof(opt)) return -EINVAL; if (!tp->repair) return -EPERM; opt.snd_wl1 = tp->snd_wl1; opt.snd_wnd = tp->snd_wnd; opt.max_window = tp->max_window; opt.rcv_wnd = tp->rcv_wnd; opt.rcv_wup = tp->rcv_wup; if (copy_to_sockptr(optval, &opt, len)) return -EFAULT; return 0; } case TCP_QUEUE_SEQ: if (tp->repair_queue == TCP_SEND_QUEUE) val = tp->write_seq; else if (tp->repair_queue == TCP_RECV_QUEUE) val = tp->rcv_nxt; else return -EINVAL; break; case TCP_USER_TIMEOUT: val = READ_ONCE(icsk->icsk_user_timeout); break; case TCP_FASTOPEN: val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen); break; case TCP_FASTOPEN_CONNECT: val = tp->fastopen_connect; break; case TCP_FASTOPEN_NO_COOKIE: val = tp->fastopen_no_cookie; break; case TCP_TX_DELAY: val = READ_ONCE(tp->tcp_tx_delay); break; case TCP_TIMESTAMP: val = tcp_clock_ts(tp->tcp_usec_ts) + READ_ONCE(tp->tsoffset); if (tp->tcp_usec_ts) val |= 1; else val &= ~1; break; case TCP_NOTSENT_LOWAT: val = READ_ONCE(tp->notsent_lowat); break; case TCP_INQ: val = tp->recvmsg_inq; break; case TCP_SAVE_SYN: val = tp->save_syn; break; case TCP_SAVED_SYN: { if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; sockopt_lock_sock(sk); if (tp->saved_syn) { if (len < tcp_saved_syn_len(tp->saved_syn)) { len = tcp_saved_syn_len(tp->saved_syn); if (copy_to_sockptr(optlen, &len, sizeof(int))) { sockopt_release_sock(sk); return -EFAULT; } sockopt_release_sock(sk); return -EINVAL; } len = tcp_saved_syn_len(tp->saved_syn); if (copy_to_sockptr(optlen, &len, sizeof(int))) { sockopt_release_sock(sk); return -EFAULT; } if (copy_to_sockptr(optval, tp->saved_syn->data, len)) { sockopt_release_sock(sk); return -EFAULT; } tcp_saved_syn_free(tp); sockopt_release_sock(sk); } else { sockopt_release_sock(sk); len = 0; if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; } return 0; } #ifdef CONFIG_MMU case TCP_ZEROCOPY_RECEIVE: { struct scm_timestamping_internal tss; struct tcp_zerocopy_receive zc = {}; int err; if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0 || len < offsetofend(struct tcp_zerocopy_receive, length)) return -EINVAL; if (unlikely(len > sizeof(zc))) { err = check_zeroed_sockptr(optval, sizeof(zc), len - sizeof(zc)); if (err < 1) return err == 0 ? -EINVAL : err; len = sizeof(zc); if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; } if (copy_from_sockptr(&zc, optval, len)) return -EFAULT; if (zc.reserved) return -EINVAL; if (zc.msg_flags & ~(TCP_VALID_ZC_MSG_FLAGS)) return -EINVAL; sockopt_lock_sock(sk); err = tcp_zerocopy_receive(sk, &zc, &tss); err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname, &zc, &len, err); sockopt_release_sock(sk); if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags)) goto zerocopy_rcv_cmsg; switch (len) { case offsetofend(struct tcp_zerocopy_receive, msg_flags): goto zerocopy_rcv_cmsg; case offsetofend(struct tcp_zerocopy_receive, msg_controllen): case offsetofend(struct tcp_zerocopy_receive, msg_control): case offsetofend(struct tcp_zerocopy_receive, flags): case offsetofend(struct tcp_zerocopy_receive, copybuf_len): case offsetofend(struct tcp_zerocopy_receive, copybuf_address): case offsetofend(struct tcp_zerocopy_receive, err): goto zerocopy_rcv_sk_err; case offsetofend(struct tcp_zerocopy_receive, inq): goto zerocopy_rcv_inq; case offsetofend(struct tcp_zerocopy_receive, length): default: goto zerocopy_rcv_out; } zerocopy_rcv_cmsg: if (zc.msg_flags & TCP_CMSG_TS) tcp_zc_finalize_rx_tstamp(sk, &zc, &tss); else zc.msg_flags = 0; zerocopy_rcv_sk_err: if (!err) zc.err = sock_error(sk); zerocopy_rcv_inq: zc.inq = tcp_inq_hint(sk); zerocopy_rcv_out: if (!err && copy_to_sockptr(optval, &zc, len)) err = -EFAULT; return err; } #endif case TCP_AO_REPAIR: if (!tcp_can_repair_sock(sk)) return -EPERM; return tcp_ao_get_repair(sk, optval, optlen); case TCP_AO_GET_KEYS: case TCP_AO_INFO: { int err; sockopt_lock_sock(sk); if (optname == TCP_AO_GET_KEYS) err = tcp_ao_get_mkts(sk, optval, optlen); else err = tcp_ao_get_sock_info(sk, optval, optlen); sockopt_release_sock(sk); return err; } case TCP_IS_MPTCP: val = 0; break; default: return -ENOPROTOOPT; } if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; if (copy_to_sockptr(optval, &val, len)) return -EFAULT; return 0; } bool tcp_bpf_bypass_getsockopt(int level, int optname) { /* TCP do_tcp_getsockopt has optimized getsockopt implementation * to avoid extra socket lock for TCP_ZEROCOPY_RECEIVE. */ if (level == SOL_TCP && optname == TCP_ZEROCOPY_RECEIVE) return true; return false; } EXPORT_SYMBOL(tcp_bpf_bypass_getsockopt); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct inet_connection_sock *icsk = inet_csk(sk); if (level != SOL_TCP) /* Paired with WRITE_ONCE() in do_ipv6_setsockopt() and tcp_v6_connect() */ return READ_ONCE(icsk->icsk_af_ops)->getsockopt(sk, level, optname, optval, optlen); return do_tcp_getsockopt(sk, level, optname, USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); } EXPORT_SYMBOL(tcp_getsockopt); #ifdef CONFIG_TCP_MD5SIG int tcp_md5_sigpool_id = -1; EXPORT_SYMBOL_GPL(tcp_md5_sigpool_id); int tcp_md5_alloc_sigpool(void) { size_t scratch_size; int ret; scratch_size = sizeof(union tcp_md5sum_block) + sizeof(struct tcphdr); ret = tcp_sigpool_alloc_ahash("md5", scratch_size); if (ret >= 0) { /* As long as any md5 sigpool was allocated, the return * id would stay the same. Re-write the id only for the case * when previously all MD5 keys were deleted and this call * allocates the first MD5 key, which may return a different * sigpool id than was used previously. */ WRITE_ONCE(tcp_md5_sigpool_id, ret); /* Avoids the compiler potentially being smart here */ return 0; } return ret; } void tcp_md5_release_sigpool(void) { tcp_sigpool_release(READ_ONCE(tcp_md5_sigpool_id)); } void tcp_md5_add_sigpool(void) { tcp_sigpool_get(READ_ONCE(tcp_md5_sigpool_id)); } int tcp_md5_hash_key(struct tcp_sigpool *hp, const struct tcp_md5sig_key *key) { u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */ struct scatterlist sg; sg_init_one(&sg, key->key, keylen); ahash_request_set_crypt(hp->req, &sg, NULL, keylen); /* We use data_race() because tcp_md5_do_add() might change * key->key under us */ return data_race(crypto_ahash_update(hp->req)); } EXPORT_SYMBOL(tcp_md5_hash_key); /* Called with rcu_read_lock() */ static enum skb_drop_reason tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int l3index, const __u8 *hash_location) { /* This gets called for each TCP segment that has TCP-MD5 option. * We have 3 drop cases: * o No MD5 hash and one expected. * o MD5 hash and we're not expecting one. * o MD5 hash and its wrong. */ const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; u8 newhash[16]; int genhash; key = tcp_md5_do_lookup(sk, l3index, saddr, family); if (!key && hash_location) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); trace_tcp_hash_md5_unexpected(sk, skb); return SKB_DROP_REASON_TCP_MD5UNEXPECTED; } /* Check the signature. * To support dual stack listeners, we need to handle * IPv4-mapped case. */ if (family == AF_INET) genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); else genhash = tp->af_specific->calc_md5_hash(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); trace_tcp_hash_md5_mismatch(sk, skb); return SKB_DROP_REASON_TCP_MD5FAILURE; } return SKB_NOT_DROPPED_YET; } #else static inline enum skb_drop_reason tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int l3index, const __u8 *hash_location) { return SKB_NOT_DROPPED_YET; } #endif /* Called with rcu_read_lock() */ enum skb_drop_reason tcp_inbound_hash(struct sock *sk, const struct request_sock *req, const struct sk_buff *skb, const void *saddr, const void *daddr, int family, int dif, int sdif) { const struct tcphdr *th = tcp_hdr(skb); const struct tcp_ao_hdr *aoh; const __u8 *md5_location; int l3index; /* Invalid option or two times meet any of auth options */ if (tcp_parse_auth_options(th, &md5_location, &aoh)) { trace_tcp_hash_bad_header(sk, skb); return SKB_DROP_REASON_TCP_AUTH_HDR; } if (req) { if (tcp_rsk_used_ao(req) != !!aoh) { u8 keyid, rnext, maclen; if (aoh) { keyid = aoh->keyid; rnext = aoh->rnext_keyid; maclen = tcp_ao_hdr_maclen(aoh); } else { keyid = rnext = maclen = 0; } NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); trace_tcp_ao_handshake_failure(sk, skb, keyid, rnext, maclen); return SKB_DROP_REASON_TCP_AOFAILURE; } } /* sdif set, means packet ingressed via a device * in an L3 domain and dif is set to the l3mdev */ l3index = sdif ? dif : 0; /* Fast path: unsigned segments */ if (likely(!md5_location && !aoh)) { /* Drop if there's TCP-MD5 or TCP-AO key with any rcvid/sndid * for the remote peer. On TCP-AO established connection * the last key is impossible to remove, so there's * always at least one current_key. */ if (tcp_ao_required(sk, saddr, family, l3index, true)) { trace_tcp_hash_ao_required(sk, skb); return SKB_DROP_REASON_TCP_AONOTFOUND; } if (unlikely(tcp_md5_do_lookup(sk, l3index, saddr, family))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); trace_tcp_hash_md5_required(sk, skb); return SKB_DROP_REASON_TCP_MD5NOTFOUND; } return SKB_NOT_DROPPED_YET; } if (aoh) return tcp_inbound_ao_hash(sk, skb, family, req, l3index, aoh); return tcp_inbound_md5_hash(sk, skb, saddr, daddr, family, l3index, md5_location); } EXPORT_SYMBOL_GPL(tcp_inbound_hash); void tcp_done(struct sock *sk) { struct request_sock *req; /* We might be called with a new socket, after * inet_csk_prepare_forced_close() has been called * so we can not use lockdep_sock_is_held(sk) */ req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, 1); if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); tcp_set_state(sk, TCP_CLOSE); tcp_clear_xmit_timers(sk); if (req) reqsk_fastopen_remove(sk, req, false); WRITE_ONCE(sk->sk_shutdown, SHUTDOWN_MASK); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_state_change(sk); else inet_csk_destroy_sock(sk); } EXPORT_SYMBOL_GPL(tcp_done); int tcp_abort(struct sock *sk, int err) { int state = inet_sk_state_load(sk); if (state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); local_bh_disable(); inet_csk_reqsk_queue_drop(req->rsk_listener, req); local_bh_enable(); return 0; } if (state == TCP_TIME_WAIT) { struct inet_timewait_sock *tw = inet_twsk(sk); refcount_inc(&tw->tw_refcnt); local_bh_disable(); inet_twsk_deschedule_put(tw); local_bh_enable(); return 0; } /* BPF context ensures sock locking. */ if (!has_current_bpf_ctx()) /* Don't race with userspace socket closes such as tcp_close. */ lock_sock(sk); /* Avoid closing the same socket twice. */ if (sk->sk_state == TCP_CLOSE) { if (!has_current_bpf_ctx()) release_sock(sk); return -ENOENT; } if (sk->sk_state == TCP_LISTEN) { tcp_set_state(sk, TCP_CLOSE); inet_csk_listen_stop(sk); } /* Don't race with BH socket closes such as inet_csk_listen_stop. */ local_bh_disable(); bh_lock_sock(sk); if (tcp_need_reset(sk->sk_state)) tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_STATE); tcp_done_with_error(sk, err); bh_unlock_sock(sk); local_bh_enable(); if (!has_current_bpf_ctx()) release_sock(sk); return 0; } EXPORT_SYMBOL_GPL(tcp_abort); extern struct tcp_congestion_ops tcp_reno; static __initdata unsigned long thash_entries; static int __init set_thash_entries(char *str) { ssize_t ret; if (!str) return 0; ret = kstrtoul(str, 0, &thash_entries); if (ret) return 0; return 1; } __setup("thash_entries=", set_thash_entries); static void __init tcp_init_mem(void) { unsigned long limit = nr_free_buffer_pages() / 16; limit = max(limit, 128UL); sysctl_tcp_mem[0] = limit / 4 * 3; /* 4.68 % */ sysctl_tcp_mem[1] = limit; /* 6.25 % */ sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2; /* 9.37 % */ } static void __init tcp_struct_check(void) { /* TX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, max_window); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, rcv_ssthresh); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, reordering); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, notsent_lowat); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, gso_segs); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, lost_skb_hint); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, retransmit_skb_hint); CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_tx, 40); /* TXRX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, tsoffset); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, snd_wnd); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, mss_cache); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, snd_cwnd); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, prr_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, scaling_ratio); CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 32); /* RX read-mostly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rcv_tstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_wl1); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, tlp_high_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rttvar_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, retrans_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, advmss); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, urg_data); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, lost); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rtt_min); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, out_of_order_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_ssthresh); CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_rx, 69); /* TX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, segs_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, data_segs_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, bytes_sent); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, snd_sml); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, chrono_start); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, chrono_stat); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, write_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, pushed_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, lsndtime); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, mdev_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tcp_wstamp_ns); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, rtt_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, tsorted_sent_queue); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, highest_sack); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, ecn_flags); CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_tx, 89); /* TXRX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, pred_flags); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, tcp_clock_cache); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, tcp_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_nxt); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_nxt); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_una); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, window_clamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, srtt_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, packets_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, snd_up); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, delivered_ce); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, app_limited); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rcv_wnd); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_txrx, rx_opt); /* 32bit arches with 8byte alignment on u64 fields might need padding * before tcp_clock_cache. */ CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_txrx, 92 + 4); /* RX read-write hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_received); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, segs_in); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, data_segs_in); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_wup); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, max_packets_out); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, cwnd_usage_seq); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_delivered); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_interval_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_last_tsecr); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, first_tx_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_acked); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_est); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcvq_space); CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_write_rx, 99); } void __init tcp_init(void) { int max_rshare, max_wshare, cnt; unsigned long limit; unsigned int i; BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE); BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof_field(struct sk_buff, cb)); tcp_struct_check(); percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); timer_setup(&tcp_orphan_timer, tcp_orphan_update, TIMER_DEFERRABLE); mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD); inet_hashinfo2_init(&tcp_hashinfo, "tcp_listen_portaddr_hash", thash_entries, 21, /* one slot per 2 MB*/ 0, 64 * 1024); tcp_hashinfo.bind_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct inet_bind_bucket), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); tcp_hashinfo.bind2_bucket_cachep = kmem_cache_create("tcp_bind2_bucket", sizeof(struct inet_bind2_bucket), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); /* Size and allocate the main established and bind bucket * hash tables. * * The methodology is similar to that of the buffer cache. */ tcp_hashinfo.ehash = alloc_large_system_hash("TCP established", sizeof(struct inet_ehash_bucket), thash_entries, 17, /* one slot per 128 KB of memory */ 0, NULL, &tcp_hashinfo.ehash_mask, 0, thash_entries ? 0 : 512 * 1024); for (i = 0; i <= tcp_hashinfo.ehash_mask; i++) INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i); if (inet_ehash_locks_alloc(&tcp_hashinfo)) panic("TCP: failed to alloc ehash_locks"); tcp_hashinfo.bhash = alloc_large_system_hash("TCP bind", 2 * sizeof(struct inet_bind_hashbucket), tcp_hashinfo.ehash_mask + 1, 17, /* one slot per 128 KB of memory */ 0, &tcp_hashinfo.bhash_size, NULL, 0, 64 * 1024); tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size; tcp_hashinfo.bhash2 = tcp_hashinfo.bhash + tcp_hashinfo.bhash_size; for (i = 0; i < tcp_hashinfo.bhash_size; i++) { spin_lock_init(&tcp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain); spin_lock_init(&tcp_hashinfo.bhash2[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash2[i].chain); } tcp_hashinfo.pernet = false; cnt = tcp_hashinfo.ehash_mask + 1; sysctl_tcp_max_orphans = cnt / 2; tcp_init_mem(); /* Set per-socket limits to no more than 1/128 the pressure threshold */ limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7); max_wshare = min(4UL*1024*1024, limit); max_rshare = min(6UL*1024*1024, limit); init_net.ipv4.sysctl_tcp_wmem[0] = PAGE_SIZE; init_net.ipv4.sysctl_tcp_wmem[1] = 16*1024; init_net.ipv4.sysctl_tcp_wmem[2] = max(64*1024, max_wshare); init_net.ipv4.sysctl_tcp_rmem[0] = PAGE_SIZE; init_net.ipv4.sysctl_tcp_rmem[1] = 131072; init_net.ipv4.sysctl_tcp_rmem[2] = max(131072, max_rshare); pr_info("Hash tables configured (established %u bind %u)\n", tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size); tcp_v4_init(); tcp_metrics_init(); BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0); tcp_tasklet_init(); mptcp_init(); } |
| 5 3 3 5 5 3 5 5 5 5 3 5 1 1 3 1 1 1 1 1 1 3 3 1 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 5 5 5 5 5 5 5 3 3 10 10 10 4 7 3 1 4 7 5 5 5 7 10 10 10 1 9 10 4 1 1 3 3 3 3 1 1 2 2 2 5 5 5 5 4 4 5 5 3 3 5 5 5 5 5 3 5 3 5 5 3 3 3 5 5 5 5 5 5 5 5 5 3 3 3 3 3 3 3 3 5 5 3 5 5 5 5 5 5 5 5 5 5 3 3 3 3 3 3 3 5 5 5 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/ceph/ceph_debug.h> #include <linux/crc32c.h> #include <linux/ctype.h> #include <linux/highmem.h> #include <linux/inet.h> #include <linux/kthread.h> #include <linux/net.h> #include <linux/nsproxy.h> #include <linux/sched/mm.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/string.h> #ifdef CONFIG_BLOCK #include <linux/bio.h> #endif /* CONFIG_BLOCK */ #include <linux/dns_resolver.h> #include <net/tcp.h> #include <trace/events/sock.h> #include <linux/ceph/ceph_features.h> #include <linux/ceph/libceph.h> #include <linux/ceph/messenger.h> #include <linux/ceph/decode.h> #include <linux/ceph/pagelist.h> #include <linux/export.h> /* * Ceph uses the messenger to exchange ceph_msg messages with other * hosts in the system. The messenger provides ordered and reliable * delivery. We tolerate TCP disconnects by reconnecting (with * exponential backoff) in the case of a fault (disconnection, bad * crc, protocol error). Acks allow sent messages to be discarded by * the sender. */ /* * We track the state of the socket on a given connection using * values defined below. The transition to a new socket state is * handled by a function which verifies we aren't coming from an * unexpected state. * * -------- * | NEW* | transient initial state * -------- * | con_sock_state_init() * v * ---------- * | CLOSED | initialized, but no socket (and no * ---------- TCP connection) * ^ \ * | \ con_sock_state_connecting() * | ---------------------- * | \ * + con_sock_state_closed() \ * |+--------------------------- \ * | \ \ \ * | ----------- \ \ * | | CLOSING | socket event; \ \ * | ----------- await close \ \ * | ^ \ | * | | \ | * | + con_sock_state_closing() \ | * | / \ | | * | / --------------- | | * | / \ v v * | / -------------- * | / -----------------| CONNECTING | socket created, TCP * | | / -------------- connect initiated * | | | con_sock_state_connected() * | | v * ------------- * | CONNECTED | TCP connection established * ------------- * * State values for ceph_connection->sock_state; NEW is assumed to be 0. */ #define CON_SOCK_STATE_NEW 0 /* -> CLOSED */ #define CON_SOCK_STATE_CLOSED 1 /* -> CONNECTING */ #define CON_SOCK_STATE_CONNECTING 2 /* -> CONNECTED or -> CLOSING */ #define CON_SOCK_STATE_CONNECTED 3 /* -> CLOSING or -> CLOSED */ #define CON_SOCK_STATE_CLOSING 4 /* -> CLOSED */ static bool con_flag_valid(unsigned long con_flag) { switch (con_flag) { case CEPH_CON_F_LOSSYTX: case CEPH_CON_F_KEEPALIVE_PENDING: case CEPH_CON_F_WRITE_PENDING: case CEPH_CON_F_SOCK_CLOSED: case CEPH_CON_F_BACKOFF: return true; default: return false; } } void ceph_con_flag_clear(struct ceph_connection *con, unsigned long con_flag) { BUG_ON(!con_flag_valid(con_flag)); clear_bit(con_flag, &con->flags); } void ceph_con_flag_set(struct ceph_connection *con, unsigned long con_flag) { BUG_ON(!con_flag_valid(con_flag)); set_bit(con_flag, &con->flags); } bool ceph_con_flag_test(struct ceph_connection *con, unsigned long con_flag) { BUG_ON(!con_flag_valid(con_flag)); return test_bit(con_flag, &con->flags); } bool ceph_con_flag_test_and_clear(struct ceph_connection *con, unsigned long con_flag) { BUG_ON(!con_flag_valid(con_flag)); return test_and_clear_bit(con_flag, &con->flags); } bool ceph_con_flag_test_and_set(struct ceph_connection *con, unsigned long con_flag) { BUG_ON(!con_flag_valid(con_flag)); return test_and_set_bit(con_flag, &con->flags); } /* Slab caches for frequently-allocated structures */ static struct kmem_cache *ceph_msg_cache; #ifdef CONFIG_LOCKDEP static struct lock_class_key socket_class; #endif static void queue_con(struct ceph_connection *con); static void cancel_con(struct ceph_connection *con); static void ceph_con_workfn(struct work_struct *); static void con_fault(struct ceph_connection *con); /* * Nicely render a sockaddr as a string. An array of formatted * strings is used, to approximate reentrancy. */ #define ADDR_STR_COUNT_LOG 5 /* log2(# address strings in array) */ #define ADDR_STR_COUNT (1 << ADDR_STR_COUNT_LOG) #define ADDR_STR_COUNT_MASK (ADDR_STR_COUNT - 1) #define MAX_ADDR_STR_LEN 64 /* 54 is enough */ static char addr_str[ADDR_STR_COUNT][MAX_ADDR_STR_LEN]; static atomic_t addr_str_seq = ATOMIC_INIT(0); struct page *ceph_zero_page; /* used in certain error cases */ const char *ceph_pr_addr(const struct ceph_entity_addr *addr) { int i; char *s; struct sockaddr_storage ss = addr->in_addr; /* align */ struct sockaddr_in *in4 = (struct sockaddr_in *)&ss; struct sockaddr_in6 *in6 = (struct sockaddr_in6 *)&ss; i = atomic_inc_return(&addr_str_seq) & ADDR_STR_COUNT_MASK; s = addr_str[i]; switch (ss.ss_family) { case AF_INET: snprintf(s, MAX_ADDR_STR_LEN, "(%d)%pI4:%hu", le32_to_cpu(addr->type), &in4->sin_addr, ntohs(in4->sin_port)); break; case AF_INET6: snprintf(s, MAX_ADDR_STR_LEN, "(%d)[%pI6c]:%hu", le32_to_cpu(addr->type), &in6->sin6_addr, ntohs(in6->sin6_port)); break; default: snprintf(s, MAX_ADDR_STR_LEN, "(unknown sockaddr family %hu)", ss.ss_family); } return s; } EXPORT_SYMBOL(ceph_pr_addr); void ceph_encode_my_addr(struct ceph_messenger *msgr) { if (!ceph_msgr2(from_msgr(msgr))) { memcpy(&msgr->my_enc_addr, &msgr->inst.addr, sizeof(msgr->my_enc_addr)); ceph_encode_banner_addr(&msgr->my_enc_addr); } } /* * work queue for all reading and writing to/from the socket. */ static struct workqueue_struct *ceph_msgr_wq; static int ceph_msgr_slab_init(void) { BUG_ON(ceph_msg_cache); ceph_msg_cache = KMEM_CACHE(ceph_msg, 0); if (!ceph_msg_cache) return -ENOMEM; return 0; } static void ceph_msgr_slab_exit(void) { BUG_ON(!ceph_msg_cache); kmem_cache_destroy(ceph_msg_cache); ceph_msg_cache = NULL; } static void _ceph_msgr_exit(void) { if (ceph_msgr_wq) { destroy_workqueue(ceph_msgr_wq); ceph_msgr_wq = NULL; } BUG_ON(!ceph_zero_page); put_page(ceph_zero_page); ceph_zero_page = NULL; ceph_msgr_slab_exit(); } int __init ceph_msgr_init(void) { if (ceph_msgr_slab_init()) return -ENOMEM; BUG_ON(ceph_zero_page); ceph_zero_page = ZERO_PAGE(0); get_page(ceph_zero_page); /* * The number of active work items is limited by the number of * connections, so leave @max_active at default. */ ceph_msgr_wq = alloc_workqueue("ceph-msgr", WQ_MEM_RECLAIM, 0); if (ceph_msgr_wq) return 0; pr_err("msgr_init failed to create workqueue\n"); _ceph_msgr_exit(); return -ENOMEM; } void ceph_msgr_exit(void) { BUG_ON(ceph_msgr_wq == NULL); _ceph_msgr_exit(); } void ceph_msgr_flush(void) { flush_workqueue(ceph_msgr_wq); } EXPORT_SYMBOL(ceph_msgr_flush); /* Connection socket state transition functions */ static void con_sock_state_init(struct ceph_connection *con) { int old_state; old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CLOSED); if (WARN_ON(old_state != CON_SOCK_STATE_NEW)) printk("%s: unexpected old state %d\n", __func__, old_state); dout("%s con %p sock %d -> %d\n", __func__, con, old_state, CON_SOCK_STATE_CLOSED); } static void con_sock_state_connecting(struct ceph_connection *con) { int old_state; old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CONNECTING); if (WARN_ON(old_state != CON_SOCK_STATE_CLOSED)) printk("%s: unexpected old state %d\n", __func__, old_state); dout("%s con %p sock %d -> %d\n", __func__, con, old_state, CON_SOCK_STATE_CONNECTING); } static void con_sock_state_connected(struct ceph_connection *con) { int old_state; old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CONNECTED); if (WARN_ON(old_state != CON_SOCK_STATE_CONNECTING)) printk("%s: unexpected old state %d\n", __func__, old_state); dout("%s con %p sock %d -> %d\n", __func__, con, old_state, CON_SOCK_STATE_CONNECTED); } static void con_sock_state_closing(struct ceph_connection *con) { int old_state; old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CLOSING); if (WARN_ON(old_state != CON_SOCK_STATE_CONNECTING && old_state != CON_SOCK_STATE_CONNECTED && old_state != CON_SOCK_STATE_CLOSING)) printk("%s: unexpected old state %d\n", __func__, old_state); dout("%s con %p sock %d -> %d\n", __func__, con, old_state, CON_SOCK_STATE_CLOSING); } static void con_sock_state_closed(struct ceph_connection *con) { int old_state; old_state = atomic_xchg(&con->sock_state, CON_SOCK_STATE_CLOSED); if (WARN_ON(old_state != CON_SOCK_STATE_CONNECTED && old_state != CON_SOCK_STATE_CLOSING && old_state != CON_SOCK_STATE_CONNECTING && old_state != CON_SOCK_STATE_CLOSED)) printk("%s: unexpected old state %d\n", __func__, old_state); dout("%s con %p sock %d -> %d\n", __func__, con, old_state, CON_SOCK_STATE_CLOSED); } /* * socket callback functions */ /* data available on socket, or listen socket received a connect */ static void ceph_sock_data_ready(struct sock *sk) { struct ceph_connection *con = sk->sk_user_data; trace_sk_data_ready(sk); if (atomic_read(&con->msgr->stopping)) { return; } if (sk->sk_state != TCP_CLOSE_WAIT) { dout("%s %p state = %d, queueing work\n", __func__, con, con->state); queue_con(con); } } /* socket has buffer space for writing */ static void ceph_sock_write_space(struct sock *sk) { struct ceph_connection *con = sk->sk_user_data; /* only queue to workqueue if there is data we want to write, * and there is sufficient space in the socket buffer to accept * more data. clear SOCK_NOSPACE so that ceph_sock_write_space() * doesn't get called again until try_write() fills the socket * buffer. See net/ipv4/tcp_input.c:tcp_check_space() * and net/core/stream.c:sk_stream_write_space(). */ if (ceph_con_flag_test(con, CEPH_CON_F_WRITE_PENDING)) { if (sk_stream_is_writeable(sk)) { dout("%s %p queueing write work\n", __func__, con); clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); queue_con(con); } } else { dout("%s %p nothing to write\n", __func__, con); } } /* socket's state has changed */ static void ceph_sock_state_change(struct sock *sk) { struct ceph_connection *con = sk->sk_user_data; dout("%s %p state = %d sk_state = %u\n", __func__, con, con->state, sk->sk_state); switch (sk->sk_state) { case TCP_CLOSE: dout("%s TCP_CLOSE\n", __func__); fallthrough; case TCP_CLOSE_WAIT: dout("%s TCP_CLOSE_WAIT\n", __func__); con_sock_state_closing(con); ceph_con_flag_set(con, CEPH_CON_F_SOCK_CLOSED); queue_con(con); break; case TCP_ESTABLISHED: dout("%s TCP_ESTABLISHED\n", __func__); con_sock_state_connected(con); queue_con(con); break; default: /* Everything else is uninteresting */ break; } } /* * set up socket callbacks */ static void set_sock_callbacks(struct socket *sock, struct ceph_connection *con) { struct sock *sk = sock->sk; sk->sk_user_data = con; sk->sk_data_ready = ceph_sock_data_ready; sk->sk_write_space = ceph_sock_write_space; sk->sk_state_change = ceph_sock_state_change; } /* * socket helpers */ /* * initiate connection to a remote socket. */ int ceph_tcp_connect(struct ceph_connection *con) { struct sockaddr_storage ss = con->peer_addr.in_addr; /* align */ struct socket *sock; unsigned int noio_flag; int ret; dout("%s con %p peer_addr %s\n", __func__, con, ceph_pr_addr(&con->peer_addr)); BUG_ON(con->sock); /* sock_create_kern() allocates with GFP_KERNEL */ noio_flag = memalloc_noio_save(); ret = sock_create_kern(read_pnet(&con->msgr->net), ss.ss_family, SOCK_STREAM, IPPROTO_TCP, &sock); memalloc_noio_restore(noio_flag); if (ret) return ret; sock->sk->sk_allocation = GFP_NOFS; sock->sk->sk_use_task_frag = false; #ifdef CONFIG_LOCKDEP lockdep_set_class(&sock->sk->sk_lock, &socket_class); #endif set_sock_callbacks(sock, con); con_sock_state_connecting(con); ret = kernel_connect(sock, (struct sockaddr *)&ss, sizeof(ss), O_NONBLOCK); if (ret == -EINPROGRESS) { dout("connect %s EINPROGRESS sk_state = %u\n", ceph_pr_addr(&con->peer_addr), sock->sk->sk_state); } else if (ret < 0) { pr_err("connect %s error %d\n", ceph_pr_addr(&con->peer_addr), ret); sock_release(sock); return ret; } if (ceph_test_opt(from_msgr(con->msgr), TCP_NODELAY)) tcp_sock_set_nodelay(sock->sk); con->sock = sock; return 0; } /* * Shutdown/close the socket for the given connection. */ int ceph_con_close_socket(struct ceph_connection *con) { int rc = 0; dout("%s con %p sock %p\n", __func__, con, con->sock); if (con->sock) { rc = con->sock->ops->shutdown(con->sock, SHUT_RDWR); sock_release(con->sock); con->sock = NULL; } /* * Forcibly clear the SOCK_CLOSED flag. It gets set * independent of the connection mutex, and we could have * received a socket close event before we had the chance to * shut the socket down. */ ceph_con_flag_clear(con, CEPH_CON_F_SOCK_CLOSED); con_sock_state_closed(con); return rc; } static void ceph_con_reset_protocol(struct ceph_connection *con) { dout("%s con %p\n", __func__, con); ceph_con_close_socket(con); if (con->in_msg) { WARN_ON(con->in_msg->con != con); ceph_msg_put(con->in_msg); con->in_msg = NULL; } if (con->out_msg) { WARN_ON(con->out_msg->con != con); ceph_msg_put(con->out_msg); con->out_msg = NULL; } if (con->bounce_page) { __free_page(con->bounce_page); con->bounce_page = NULL; } if (ceph_msgr2(from_msgr(con->msgr))) ceph_con_v2_reset_protocol(con); else ceph_con_v1_reset_protocol(con); } /* * Reset a connection. Discard all incoming and outgoing messages * and clear *_seq state. */ static void ceph_msg_remove(struct ceph_msg *msg) { list_del_init(&msg->list_head); ceph_msg_put(msg); } static void ceph_msg_remove_list(struct list_head *head) { while (!list_empty(head)) { struct ceph_msg *msg = list_first_entry(head, struct ceph_msg, list_head); ceph_msg_remove(msg); } } void ceph_con_reset_session(struct ceph_connection *con) { dout("%s con %p\n", __func__, con); WARN_ON(con->in_msg); WARN_ON(con->out_msg); ceph_msg_remove_list(&con->out_queue); ceph_msg_remove_list(&con->out_sent); con->out_seq = 0; con->in_seq = 0; con->in_seq_acked = 0; if (ceph_msgr2(from_msgr(con->msgr))) ceph_con_v2_reset_session(con); else ceph_con_v1_reset_session(con); } /* * mark a peer down. drop any open connections. */ void ceph_con_close(struct ceph_connection *con) { mutex_lock(&con->mutex); dout("con_close %p peer %s\n", con, ceph_pr_addr(&con->peer_addr)); con->state = CEPH_CON_S_CLOSED; ceph_con_flag_clear(con, CEPH_CON_F_LOSSYTX); /* so we retry next connect */ ceph_con_flag_clear(con, CEPH_CON_F_KEEPALIVE_PENDING); ceph_con_flag_clear(con, CEPH_CON_F_WRITE_PENDING); ceph_con_flag_clear(con, CEPH_CON_F_BACKOFF); ceph_con_reset_protocol(con); ceph_con_reset_session(con); cancel_con(con); mutex_unlock(&con->mutex); } EXPORT_SYMBOL(ceph_con_close); /* * Reopen a closed connection, with a new peer address. */ void ceph_con_open(struct ceph_connection *con, __u8 entity_type, __u64 entity_num, struct ceph_entity_addr *addr) { mutex_lock(&con->mutex); dout("con_open %p %s\n", con, ceph_pr_addr(addr)); WARN_ON(con->state != CEPH_CON_S_CLOSED); con->state = CEPH_CON_S_PREOPEN; con->peer_name.type = (__u8) entity_type; con->peer_name.num = cpu_to_le64(entity_num); memcpy(&con->peer_addr, addr, sizeof(*addr)); con->delay = 0; /* reset backoff memory */ mutex_unlock(&con->mutex); queue_con(con); } EXPORT_SYMBOL(ceph_con_open); /* * return true if this connection ever successfully opened */ bool ceph_con_opened(struct ceph_connection *con) { if (ceph_msgr2(from_msgr(con->msgr))) return ceph_con_v2_opened(con); return ceph_con_v1_opened(con); } /* * initialize a new connection. */ void ceph_con_init(struct ceph_connection *con, void *private, const struct ceph_connection_operations *ops, struct ceph_messenger *msgr) { dout("con_init %p\n", con); memset(con, 0, sizeof(*con)); con->private = private; con->ops = ops; con->msgr = msgr; con_sock_state_init(con); mutex_init(&con->mutex); INIT_LIST_HEAD(&con->out_queue); INIT_LIST_HEAD(&con->out_sent); INIT_DELAYED_WORK(&con->work, ceph_con_workfn); con->state = CEPH_CON_S_CLOSED; } EXPORT_SYMBOL(ceph_con_init); /* * We maintain a global counter to order connection attempts. Get * a unique seq greater than @gt. */ u32 ceph_get_global_seq(struct ceph_messenger *msgr, u32 gt) { u32 ret; spin_lock(&msgr->global_seq_lock); if (msgr->global_seq < gt) msgr->global_seq = gt; ret = ++msgr->global_seq; spin_unlock(&msgr->global_seq_lock); return ret; } /* * Discard messages that have been acked by the server. */ void ceph_con_discard_sent(struct ceph_connection *con, u64 ack_seq) { struct ceph_msg *msg; u64 seq; dout("%s con %p ack_seq %llu\n", __func__, con, ack_seq); while (!list_empty(&con->out_sent)) { msg = list_first_entry(&con->out_sent, struct ceph_msg, list_head); WARN_ON(msg->needs_out_seq); seq = le64_to_cpu(msg->hdr.seq); if (seq > ack_seq) break; dout("%s con %p discarding msg %p seq %llu\n", __func__, con, msg, seq); ceph_msg_remove(msg); } } /* * Discard messages that have been requeued in con_fault(), up to * reconnect_seq. This avoids gratuitously resending messages that * the server had received and handled prior to reconnect. */ void ceph_con_discard_requeued(struct ceph_connection *con, u64 reconnect_seq) { struct ceph_msg *msg; u64 seq; dout("%s con %p reconnect_seq %llu\n", __func__, con, reconnect_seq); while (!list_empty(&con->out_queue)) { msg = list_first_entry(&con->out_queue, struct ceph_msg, list_head); if (msg->needs_out_seq) break; seq = le64_to_cpu(msg->hdr.seq); if (seq > reconnect_seq) break; dout("%s con %p discarding msg %p seq %llu\n", __func__, con, msg, seq); ceph_msg_remove(msg); } } #ifdef CONFIG_BLOCK /* * For a bio data item, a piece is whatever remains of the next * entry in the current bio iovec, or the first entry in the next * bio in the list. */ static void ceph_msg_data_bio_cursor_init(struct ceph_msg_data_cursor *cursor, size_t length) { struct ceph_msg_data *data = cursor->data; struct ceph_bio_iter *it = &cursor->bio_iter; cursor->resid = min_t(size_t, length, data->bio_length); *it = data->bio_pos; if (cursor->resid < it->iter.bi_size) it->iter.bi_size = cursor->resid; BUG_ON(cursor->resid < bio_iter_len(it->bio, it->iter)); } static struct page *ceph_msg_data_bio_next(struct ceph_msg_data_cursor *cursor, size_t *page_offset, size_t *length) { struct bio_vec bv = bio_iter_iovec(cursor->bio_iter.bio, cursor->bio_iter.iter); *page_offset = bv.bv_offset; *length = bv.bv_len; return bv.bv_page; } static bool ceph_msg_data_bio_advance(struct ceph_msg_data_cursor *cursor, size_t bytes) { struct ceph_bio_iter *it = &cursor->bio_iter; struct page *page = bio_iter_page(it->bio, it->iter); BUG_ON(bytes > cursor->resid); BUG_ON(bytes > bio_iter_len(it->bio, it->iter)); cursor->resid -= bytes; bio_advance_iter(it->bio, &it->iter, bytes); if (!cursor->resid) return false; /* no more data */ if (!bytes || (it->iter.bi_size && it->iter.bi_bvec_done && page == bio_iter_page(it->bio, it->iter))) return false; /* more bytes to process in this segment */ if (!it->iter.bi_size) { it->bio = it->bio->bi_next; it->iter = it->bio->bi_iter; if (cursor->resid < it->iter.bi_size) it->iter.bi_size = cursor->resid; } BUG_ON(cursor->resid < bio_iter_len(it->bio, it->iter)); return true; } #endif /* CONFIG_BLOCK */ static void ceph_msg_data_bvecs_cursor_init(struct ceph_msg_data_cursor *cursor, size_t length) { struct ceph_msg_data *data = cursor->data; struct bio_vec *bvecs = data->bvec_pos.bvecs; cursor->resid = min_t(size_t, length, data->bvec_pos.iter.bi_size); cursor->bvec_iter = data->bvec_pos.iter; cursor->bvec_iter.bi_size = cursor->resid; BUG_ON(cursor->resid < bvec_iter_len(bvecs, cursor->bvec_iter)); } static struct page *ceph_msg_data_bvecs_next(struct ceph_msg_data_cursor *cursor, size_t *page_offset, size_t *length) { struct bio_vec bv = bvec_iter_bvec(cursor->data->bvec_pos.bvecs, cursor->bvec_iter); *page_offset = bv.bv_offset; *length = bv.bv_len; return bv.bv_page; } static bool ceph_msg_data_bvecs_advance(struct ceph_msg_data_cursor *cursor, size_t bytes) { struct bio_vec *bvecs = cursor->data->bvec_pos.bvecs; struct page *page = bvec_iter_page(bvecs, cursor->bvec_iter); BUG_ON(bytes > cursor->resid); BUG_ON(bytes > bvec_iter_len(bvecs, cursor->bvec_iter)); cursor->resid -= bytes; bvec_iter_advance(bvecs, &cursor->bvec_iter, bytes); if (!cursor->resid) return false; /* no more data */ if (!bytes || (cursor->bvec_iter.bi_bvec_done && page == bvec_iter_page(bvecs, cursor->bvec_iter))) return false; /* more bytes to process in this segment */ BUG_ON(cursor->resid < bvec_iter_len(bvecs, cursor->bvec_iter)); return true; } /* * For a page array, a piece comes from the first page in the array * that has not already been fully consumed. */ static void ceph_msg_data_pages_cursor_init(struct ceph_msg_data_cursor *cursor, size_t length) { struct ceph_msg_data *data = cursor->data; int page_count; BUG_ON(data->type != CEPH_MSG_DATA_PAGES); BUG_ON(!data->pages); BUG_ON(!data->length); cursor->resid = min(length, data->length); page_count = calc_pages_for(data->alignment, (u64)data->length); cursor->page_offset = data->alignment & ~PAGE_MASK; cursor->page_index = 0; BUG_ON(page_count > (int)USHRT_MAX); cursor->page_count = (unsigned short)page_count; BUG_ON(length > SIZE_MAX - cursor->page_offset); } static struct page * ceph_msg_data_pages_next(struct ceph_msg_data_cursor *cursor, size_t *page_offset, size_t *length) { struct ceph_msg_data *data = cursor->data; BUG_ON(data->type != CEPH_MSG_DATA_PAGES); BUG_ON(cursor->page_index >= cursor->page_count); BUG_ON(cursor->page_offset >= PAGE_SIZE); *page_offset = cursor->page_offset; *length = min_t(size_t, cursor->resid, PAGE_SIZE - *page_offset); return data->pages[cursor->page_index]; } static bool ceph_msg_data_pages_advance(struct ceph_msg_data_cursor *cursor, size_t bytes) { BUG_ON(cursor->data->type != CEPH_MSG_DATA_PAGES); BUG_ON(cursor->page_offset + bytes > PAGE_SIZE); /* Advance the cursor page offset */ cursor->resid -= bytes; cursor->page_offset = (cursor->page_offset + bytes) & ~PAGE_MASK; if (!bytes || cursor->page_offset) return false; /* more bytes to process in the current page */ if (!cursor->resid) return false; /* no more data */ /* Move on to the next page; offset is already at 0 */ BUG_ON(cursor->page_index >= cursor->page_count); cursor->page_index++; return true; } /* * For a pagelist, a piece is whatever remains to be consumed in the * first page in the list, or the front of the next page. */ static void ceph_msg_data_pagelist_cursor_init(struct ceph_msg_data_cursor *cursor, size_t length) { struct ceph_msg_data *data = cursor->data; struct ceph_pagelist *pagelist; struct page *page; BUG_ON(data->type != CEPH_MSG_DATA_PAGELIST); pagelist = data->pagelist; BUG_ON(!pagelist); if (!length) return; /* pagelist can be assigned but empty */ BUG_ON(list_empty(&pagelist->head)); page = list_first_entry(&pagelist->head, struct page, lru); cursor->resid = min(length, pagelist->length); cursor->page = page; cursor->offset = 0; } static struct page * ceph_msg_data_pagelist_next(struct ceph_msg_data_cursor *cursor, size_t *page_offset, size_t *length) { struct ceph_msg_data *data = cursor->data; struct ceph_pagelist *pagelist; BUG_ON(data->type != CEPH_MSG_DATA_PAGELIST); pagelist = data->pagelist; BUG_ON(!pagelist); BUG_ON(!cursor->page); BUG_ON(cursor->offset + cursor->resid != pagelist->length); /* offset of first page in pagelist is always 0 */ *page_offset = cursor->offset & ~PAGE_MASK; *length = min_t(size_t, cursor->resid, PAGE_SIZE - *page_offset); return cursor->page; } static bool ceph_msg_data_pagelist_advance(struct ceph_msg_data_cursor *cursor, size_t bytes) { struct ceph_msg_data *data = cursor->data; struct ceph_pagelist *pagelist; BUG_ON(data->type != CEPH_MSG_DATA_PAGELIST); pagelist = data->pagelist; BUG_ON(!pagelist); BUG_ON(cursor->offset + cursor->resid != pagelist->length); BUG_ON((cursor->offset & ~PAGE_MASK) + bytes > PAGE_SIZE); /* Advance the cursor offset */ cursor->resid -= bytes; cursor->offset += bytes; /* offset of first page in pagelist is always 0 */ if (!bytes || cursor->offset & ~PAGE_MASK) return false; /* more bytes to process in the current page */ if (!cursor->resid) return false; /* no more data */ /* Move on to the next page */ BUG_ON(list_is_last(&cursor->page->lru, &pagelist->head)); cursor->page = list_next_entry(cursor->page, lru); return true; } static void ceph_msg_data_iter_cursor_init(struct ceph_msg_data_cursor *cursor, size_t length) { struct ceph_msg_data *data = cursor->data; cursor->iov_iter = data->iter; cursor->lastlen = 0; iov_iter_truncate(&cursor->iov_iter, length); cursor->resid = iov_iter_count(&cursor->iov_iter); } static struct page *ceph_msg_data_iter_next(struct ceph_msg_data_cursor *cursor, size_t *page_offset, size_t *length) { struct page *page; ssize_t len; if (cursor->lastlen) iov_iter_revert(&cursor->iov_iter, cursor->lastlen); len = iov_iter_get_pages2(&cursor->iov_iter, &page, PAGE_SIZE, 1, page_offset); BUG_ON(len < 0); cursor->lastlen = len; /* * FIXME: The assumption is that the pages represented by the iov_iter * are pinned, with the references held by the upper-level * callers, or by virtue of being under writeback. Eventually, * we'll get an iov_iter_get_pages2 variant that doesn't take * page refs. Until then, just put the page ref. */ VM_BUG_ON_PAGE(!PageWriteback(page) && page_count(page) < 2, page); put_page(page); *length = min_t(size_t, len, cursor->resid); return page; } static bool ceph_msg_data_iter_advance(struct ceph_msg_data_cursor *cursor, size_t bytes) { BUG_ON(bytes > cursor->resid); cursor->resid -= bytes; if (bytes < cursor->lastlen) { cursor->lastlen -= bytes; } else { iov_iter_advance(&cursor->iov_iter, bytes - cursor->lastlen); cursor->lastlen = 0; } return cursor->resid; } /* * Message data is handled (sent or received) in pieces, where each * piece resides on a single page. The network layer might not * consume an entire piece at once. A data item's cursor keeps * track of which piece is next to process and how much remains to * be processed in that piece. It also tracks whether the current * piece is the last one in the data item. */ static void __ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor) { size_t length = cursor->total_resid; switch (cursor->data->type) { case CEPH_MSG_DATA_PAGELIST: ceph_msg_data_pagelist_cursor_init(cursor, length); break; case CEPH_MSG_DATA_PAGES: ceph_msg_data_pages_cursor_init(cursor, length); break; #ifdef CONFIG_BLOCK case CEPH_MSG_DATA_BIO: ceph_msg_data_bio_cursor_init(cursor, length); break; #endif /* CONFIG_BLOCK */ case CEPH_MSG_DATA_BVECS: ceph_msg_data_bvecs_cursor_init(cursor, length); break; case CEPH_MSG_DATA_ITER: ceph_msg_data_iter_cursor_init(cursor, length); break; case CEPH_MSG_DATA_NONE: default: /* BUG(); */ break; } cursor->need_crc = true; } void ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor, struct ceph_msg *msg, size_t length) { BUG_ON(!length); BUG_ON(length > msg->data_length); BUG_ON(!msg->num_data_items); cursor->total_resid = length; cursor->data = msg->data; cursor->sr_resid = 0; __ceph_msg_data_cursor_init(cursor); } /* * Return the page containing the next piece to process for a given * data item, and supply the page offset and length of that piece. * Indicate whether this is the last piece in this data item. */ struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor, size_t *page_offset, size_t *length) { struct page *page; switch (cursor->data->type) { case CEPH_MSG_DATA_PAGELIST: page = ceph_msg_data_pagelist_next(cursor, page_offset, length); break; case CEPH_MSG_DATA_PAGES: page = ceph_msg_data_pages_next(cursor, page_offset, length); break; #ifdef CONFIG_BLOCK case CEPH_MSG_DATA_BIO: page = ceph_msg_data_bio_next(cursor, page_offset, length); break; #endif /* CONFIG_BLOCK */ case CEPH_MSG_DATA_BVECS: page = ceph_msg_data_bvecs_next(cursor, page_offset, length); break; case CEPH_MSG_DATA_ITER: page = ceph_msg_data_iter_next(cursor, page_offset, length); break; case CEPH_MSG_DATA_NONE: default: page = NULL; break; } BUG_ON(!page); BUG_ON(*page_offset + *length > PAGE_SIZE); BUG_ON(!*length); BUG_ON(*length > cursor->resid); return page; } /* * Returns true if the result moves the cursor on to the next piece * of the data item. */ void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, size_t bytes) { bool new_piece; BUG_ON(bytes > cursor->resid); switch (cursor->data->type) { case CEPH_MSG_DATA_PAGELIST: new_piece = ceph_msg_data_pagelist_advance(cursor, bytes); break; case CEPH_MSG_DATA_PAGES: new_piece = ceph_msg_data_pages_advance(cursor, bytes); break; #ifdef CONFIG_BLOCK case CEPH_MSG_DATA_BIO: new_piece = ceph_msg_data_bio_advance(cursor, bytes); break; #endif /* CONFIG_BLOCK */ case CEPH_MSG_DATA_BVECS: new_piece = ceph_msg_data_bvecs_advance(cursor, bytes); break; case CEPH_MSG_DATA_ITER: new_piece = ceph_msg_data_iter_advance(cursor, bytes); break; case CEPH_MSG_DATA_NONE: default: BUG(); break; } cursor->total_resid -= bytes; if (!cursor->resid && cursor->total_resid) { cursor->data++; __ceph_msg_data_cursor_init(cursor); new_piece = true; } cursor->need_crc = new_piece; } u32 ceph_crc32c_page(u32 crc, struct page *page, unsigned int page_offset, unsigned int length) { char *kaddr; kaddr = kmap(page); BUG_ON(kaddr == NULL); crc = crc32c(crc, kaddr + page_offset, length); kunmap(page); return crc; } bool ceph_addr_is_blank(const struct ceph_entity_addr *addr) { struct sockaddr_storage ss = addr->in_addr; /* align */ struct in_addr *addr4 = &((struct sockaddr_in *)&ss)->sin_addr; struct in6_addr *addr6 = &((struct sockaddr_in6 *)&ss)->sin6_addr; switch (ss.ss_family) { case AF_INET: return addr4->s_addr == htonl(INADDR_ANY); case AF_INET6: return ipv6_addr_any(addr6); default: return true; } } EXPORT_SYMBOL(ceph_addr_is_blank); int ceph_addr_port(const struct ceph_entity_addr *addr) { switch (get_unaligned(&addr->in_addr.ss_family)) { case AF_INET: return ntohs(get_unaligned(&((struct sockaddr_in *)&addr->in_addr)->sin_port)); case AF_INET6: return ntohs(get_unaligned(&((struct sockaddr_in6 *)&addr->in_addr)->sin6_port)); } return 0; } void ceph_addr_set_port(struct ceph_entity_addr *addr, int p) { switch (get_unaligned(&addr->in_addr.ss_family)) { case AF_INET: put_unaligned(htons(p), &((struct sockaddr_in *)&addr->in_addr)->sin_port); break; case AF_INET6: put_unaligned(htons(p), &((struct sockaddr_in6 *)&addr->in_addr)->sin6_port); break; } } /* * Unlike other *_pton function semantics, zero indicates success. */ static int ceph_pton(const char *str, size_t len, struct ceph_entity_addr *addr, char delim, const char **ipend) { memset(&addr->in_addr, 0, sizeof(addr->in_addr)); if (in4_pton(str, len, (u8 *)&((struct sockaddr_in *)&addr->in_addr)->sin_addr.s_addr, delim, ipend)) { put_unaligned(AF_INET, &addr->in_addr.ss_family); return 0; } if (in6_pton(str, len, (u8 *)&((struct sockaddr_in6 *)&addr->in_addr)->sin6_addr.s6_addr, delim, ipend)) { put_unaligned(AF_INET6, &addr->in_addr.ss_family); return 0; } return -EINVAL; } /* * Extract hostname string and resolve using kernel DNS facility. */ #ifdef CONFIG_CEPH_LIB_USE_DNS_RESOLVER static int ceph_dns_resolve_name(const char *name, size_t namelen, struct ceph_entity_addr *addr, char delim, const char **ipend) { const char *end, *delim_p; char *colon_p, *ip_addr = NULL; int ip_len, ret; /* * The end of the hostname occurs immediately preceding the delimiter or * the port marker (':') where the delimiter takes precedence. */ delim_p = memchr(name, delim, namelen); colon_p = memchr(name, ':', namelen); if (delim_p && colon_p) end = min(delim_p, colon_p); else if (!delim_p && colon_p) end = colon_p; else { end = delim_p; if (!end) /* case: hostname:/ */ end = name + namelen; } if (end <= name) return -EINVAL; /* do dns_resolve upcall */ ip_len = dns_query(current->nsproxy->net_ns, NULL, name, end - name, NULL, &ip_addr, NULL, false); if (ip_len > 0) ret = ceph_pton(ip_addr, ip_len, addr, -1, NULL); else ret = -ESRCH; kfree(ip_addr); *ipend = end; pr_info("resolve '%.*s' (ret=%d): %s\n", (int)(end - name), name, ret, ret ? "failed" : ceph_pr_addr(addr)); return ret; } #else static inline int ceph_dns_resolve_name(const char *name, size_t namelen, struct ceph_entity_addr *addr, char delim, const char **ipend) { return -EINVAL; } #endif /* * Parse a server name (IP or hostname). If a valid IP address is not found * then try to extract a hostname to resolve using userspace DNS upcall. */ static int ceph_parse_server_name(const char *name, size_t namelen, struct ceph_entity_addr *addr, char delim, const char **ipend) { int ret; ret = ceph_pton(name, namelen, addr, delim, ipend); if (ret) ret = ceph_dns_resolve_name(name, namelen, addr, delim, ipend); return ret; } /* * Parse an ip[:port] list into an addr array. Use the default * monitor port if a port isn't specified. */ int ceph_parse_ips(const char *c, const char *end, struct ceph_entity_addr *addr, int max_count, int *count, char delim) { int i, ret = -EINVAL; const char *p = c; dout("parse_ips on '%.*s'\n", (int)(end-c), c); for (i = 0; i < max_count; i++) { char cur_delim = delim; const char *ipend; int port; if (*p == '[') { cur_delim = ']'; p++; } ret = ceph_parse_server_name(p, end - p, &addr[i], cur_delim, &ipend); if (ret) goto bad; ret = -EINVAL; p = ipend; if (cur_delim == ']') { if (*p != ']') { dout("missing matching ']'\n"); goto bad; } p++; } /* port? */ if (p < end && *p == ':') { port = 0; p++; while (p < end && *p >= '0' && *p <= '9') { port = (port * 10) + (*p - '0'); p++; } if (port == 0) port = CEPH_MON_PORT; else if (port > 65535) goto bad; } else { port = CEPH_MON_PORT; } ceph_addr_set_port(&addr[i], port); /* * We want the type to be set according to ms_mode * option, but options are normally parsed after mon * addresses. Rather than complicating parsing, set * to LEGACY and override in build_initial_monmap() * for mon addresses and ceph_messenger_init() for * ip option. */ addr[i].type = CEPH_ENTITY_ADDR_TYPE_LEGACY; addr[i].nonce = 0; dout("%s got %s\n", __func__, ceph_pr_addr(&addr[i])); if (p == end) break; if (*p != delim) goto bad; p++; } if (p != end) goto bad; if (count) *count = i + 1; return 0; bad: return ret; } /* * Process message. This happens in the worker thread. The callback should * be careful not to do anything that waits on other incoming messages or it * may deadlock. */ void ceph_con_process_message(struct ceph_connection *con) { struct ceph_msg *msg = con->in_msg; BUG_ON(con->in_msg->con != con); con->in_msg = NULL; /* if first message, set peer_name */ if (con->peer_name.type == 0) con->peer_name = msg->hdr.src; con->in_seq++; mutex_unlock(&con->mutex); dout("===== %p %llu from %s%lld %d=%s len %d+%d+%d (%u %u %u) =====\n", msg, le64_to_cpu(msg->hdr.seq), ENTITY_NAME(msg->hdr.src), le16_to_cpu(msg->hdr.type), ceph_msg_type_name(le16_to_cpu(msg->hdr.type)), le32_to_cpu(msg->hdr.front_len), le32_to_cpu(msg->hdr.middle_len), le32_to_cpu(msg->hdr.data_len), con->in_front_crc, con->in_middle_crc, con->in_data_crc); con->ops->dispatch(con, msg); mutex_lock(&con->mutex); } /* * Atomically queue work on a connection after the specified delay. * Bump @con reference to avoid races with connection teardown. * Returns 0 if work was queued, or an error code otherwise. */ static int queue_con_delay(struct ceph_connection *con, unsigned long delay) { if (!con->ops->get(con)) { dout("%s %p ref count 0\n", __func__, con); return -ENOENT; } if (delay >= HZ) delay = round_jiffies_relative(delay); dout("%s %p %lu\n", __func__, con, delay); if (!queue_delayed_work(ceph_msgr_wq, &con->work, delay)) { dout("%s %p - already queued\n", __func__, con); con->ops->put(con); return -EBUSY; } return 0; } static void queue_con(struct ceph_connection *con) { (void) queue_con_delay(con, 0); } static void cancel_con(struct ceph_connection *con) { if (cancel_delayed_work(&con->work)) { dout("%s %p\n", __func__, con); con->ops->put(con); } } static bool con_sock_closed(struct ceph_connection *con) { if (!ceph_con_flag_test_and_clear(con, CEPH_CON_F_SOCK_CLOSED)) return false; #define CASE(x) \ case CEPH_CON_S_ ## x: \ con->error_msg = "socket closed (con state " #x ")"; \ break; switch (con->state) { CASE(CLOSED); CASE(PREOPEN); CASE(V1_BANNER); CASE(V1_CONNECT_MSG); CASE(V2_BANNER_PREFIX); CASE(V2_BANNER_PAYLOAD); CASE(V2_HELLO); CASE(V2_AUTH); CASE(V2_AUTH_SIGNATURE); CASE(V2_SESSION_CONNECT); CASE(V2_SESSION_RECONNECT); CASE(OPEN); CASE(STANDBY); default: BUG(); } #undef CASE return true; } static bool con_backoff(struct ceph_connection *con) { int ret; if (!ceph_con_flag_test_and_clear(con, CEPH_CON_F_BACKOFF)) return false; ret = queue_con_delay(con, con->delay); if (ret) { dout("%s: con %p FAILED to back off %lu\n", __func__, con, con->delay); BUG_ON(ret == -ENOENT); ceph_con_flag_set(con, CEPH_CON_F_BACKOFF); } return true; } /* Finish fault handling; con->mutex must *not* be held here */ static void con_fault_finish(struct ceph_connection *con) { dout("%s %p\n", __func__, con); /* * in case we faulted due to authentication, invalidate our * current tickets so that we can get new ones. */ if (con->v1.auth_retry) { dout("auth_retry %d, invalidating\n", con->v1.auth_retry); if (con->ops->invalidate_authorizer) con->ops->invalidate_authorizer(con); con->v1.auth_retry = 0; } if (con->ops->fault) con->ops->fault(con); } /* * Do some work on a connection. Drop a connection ref when we're done. */ static void ceph_con_workfn(struct work_struct *work) { struct ceph_connection *con = container_of(work, struct ceph_connection, work.work); bool fault; mutex_lock(&con->mutex); while (true) { int ret; if ((fault = con_sock_closed(con))) { dout("%s: con %p SOCK_CLOSED\n", __func__, con); break; } if (con_backoff(con)) { dout("%s: con %p BACKOFF\n", __func__, con); break; } if (con->state == CEPH_CON_S_STANDBY) { dout("%s: con %p STANDBY\n", __func__, con); break; } if (con->state == CEPH_CON_S_CLOSED) { dout("%s: con %p CLOSED\n", __func__, con); BUG_ON(con->sock); break; } if (con->state == CEPH_CON_S_PREOPEN) { dout("%s: con %p PREOPEN\n", __func__, con); BUG_ON(con->sock); } if (ceph_msgr2(from_msgr(con->msgr))) ret = ceph_con_v2_try_read(con); else ret = ceph_con_v1_try_read(con); if (ret < 0) { if (ret == -EAGAIN) continue; if (!con->error_msg) con->error_msg = "socket error on read"; fault = true; break; } if (ceph_msgr2(from_msgr(con->msgr))) ret = ceph_con_v2_try_write(con); else ret = ceph_con_v1_try_write(con); if (ret < 0) { if (ret == -EAGAIN) continue; if (!con->error_msg) con->error_msg = "socket error on write"; fault = true; } break; /* If we make it to here, we're done */ } if (fault) con_fault(con); mutex_unlock(&con->mutex); if (fault) con_fault_finish(con); con->ops->put(con); } /* * Generic error/fault handler. A retry mechanism is used with * exponential backoff */ static void con_fault(struct ceph_connection *con) { dout("fault %p state %d to peer %s\n", con, con->state, ceph_pr_addr(&con->peer_addr)); pr_warn("%s%lld %s %s\n", ENTITY_NAME(con->peer_name), ceph_pr_addr(&con->peer_addr), con->error_msg); con->error_msg = NULL; WARN_ON(con->state == CEPH_CON_S_STANDBY || con->state == CEPH_CON_S_CLOSED); ceph_con_reset_protocol(con); if (ceph_con_flag_test(con, CEPH_CON_F_LOSSYTX)) { dout("fault on LOSSYTX channel, marking CLOSED\n"); con->state = CEPH_CON_S_CLOSED; return; } /* Requeue anything that hasn't been acked */ list_splice_init(&con->out_sent, &con->out_queue); /* If there are no messages queued or keepalive pending, place * the connection in a STANDBY state */ if (list_empty(&con->out_queue) && !ceph_con_flag_test(con, CEPH_CON_F_KEEPALIVE_PENDING)) { dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con); ceph_con_flag_clear(con, CEPH_CON_F_WRITE_PENDING); con->state = CEPH_CON_S_STANDBY; } else { /* retry after a delay. */ con->state = CEPH_CON_S_PREOPEN; if (!con->delay) { con->delay = BASE_DELAY_INTERVAL; } else if (con->delay < MAX_DELAY_INTERVAL) { con->delay *= 2; if (con->delay > MAX_DELAY_INTERVAL) con->delay = MAX_DELAY_INTERVAL; } ceph_con_flag_set(con, CEPH_CON_F_BACKOFF); queue_con(con); } } void ceph_messenger_reset_nonce(struct ceph_messenger *msgr) { u32 nonce = le32_to_cpu(msgr->inst.addr.nonce) + 1000000; msgr->inst.addr.nonce = cpu_to_le32(nonce); ceph_encode_my_addr(msgr); } /* * initialize a new messenger instance */ void ceph_messenger_init(struct ceph_messenger *msgr, struct ceph_entity_addr *myaddr) { spin_lock_init(&msgr->global_seq_lock); if (myaddr) { memcpy(&msgr->inst.addr.in_addr, &myaddr->in_addr, sizeof(msgr->inst.addr.in_addr)); ceph_addr_set_port(&msgr->inst.addr, 0); } /* * Since nautilus, clients are identified using type ANY. * For msgr1, ceph_encode_banner_addr() munges it to NONE. */ msgr->inst.addr.type = CEPH_ENTITY_ADDR_TYPE_ANY; /* generate a random non-zero nonce */ do { get_random_bytes(&msgr->inst.addr.nonce, sizeof(msgr->inst.addr.nonce)); } while (!msgr->inst.addr.nonce); ceph_encode_my_addr(msgr); atomic_set(&msgr->stopping, 0); write_pnet(&msgr->net, get_net(current->nsproxy->net_ns)); dout("%s %p\n", __func__, msgr); } void ceph_messenger_fini(struct ceph_messenger *msgr) { put_net(read_pnet(&msgr->net)); } static void msg_con_set(struct ceph_msg *msg, struct ceph_connection *con) { if (msg->con) msg->con->ops->put(msg->con); msg->con = con ? con->ops->get(con) : NULL; BUG_ON(msg->con != con); } static void clear_standby(struct ceph_connection *con) { /* come back from STANDBY? */ if (con->state == CEPH_CON_S_STANDBY) { dout("clear_standby %p and ++connect_seq\n", con); con->state = CEPH_CON_S_PREOPEN; con->v1.connect_seq++; WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_WRITE_PENDING)); WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_KEEPALIVE_PENDING)); } } /* * Queue up an outgoing message on the given connection. * * Consumes a ref on @msg. */ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg) { /* set src+dst */ msg->hdr.src = con->msgr->inst.name; BUG_ON(msg->front.iov_len != le32_to_cpu(msg->hdr.front_len)); msg->needs_out_seq = true; mutex_lock(&con->mutex); if (con->state == CEPH_CON_S_CLOSED) { dout("con_send %p closed, dropping %p\n", con, msg); ceph_msg_put(msg); mutex_unlock(&con->mutex); return; } msg_con_set(msg, con); BUG_ON(!list_empty(&msg->list_head)); list_add_tail(&msg->list_head, &con->out_queue); dout("----- %p to %s%lld %d=%s len %d+%d+%d -----\n", msg, ENTITY_NAME(con->peer_name), le16_to_cpu(msg->hdr.type), ceph_msg_type_name(le16_to_cpu(msg->hdr.type)), le32_to_cpu(msg->hdr.front_len), le32_to_cpu(msg->hdr.middle_len), le32_to_cpu(msg->hdr.data_len)); clear_standby(con); mutex_unlock(&con->mutex); /* if there wasn't anything waiting to send before, queue * new work */ if (!ceph_con_flag_test_and_set(con, CEPH_CON_F_WRITE_PENDING)) queue_con(con); } EXPORT_SYMBOL(ceph_con_send); /* * Revoke a message that was previously queued for send */ void ceph_msg_revoke(struct ceph_msg *msg) { struct ceph_connection *con = msg->con; if (!con) { dout("%s msg %p null con\n", __func__, msg); return; /* Message not in our possession */ } mutex_lock(&con->mutex); if (list_empty(&msg->list_head)) { WARN_ON(con->out_msg == msg); dout("%s con %p msg %p not linked\n", __func__, con, msg); mutex_unlock(&con->mutex); return; } dout("%s con %p msg %p was linked\n", __func__, con, msg); msg->hdr.seq = 0; ceph_msg_remove(msg); if (con->out_msg == msg) { WARN_ON(con->state != CEPH_CON_S_OPEN); dout("%s con %p msg %p was sending\n", __func__, con, msg); if (ceph_msgr2(from_msgr(con->msgr))) ceph_con_v2_revoke(con); else ceph_con_v1_revoke(con); ceph_msg_put(con->out_msg); con->out_msg = NULL; } else { dout("%s con %p msg %p not current, out_msg %p\n", __func__, con, msg, con->out_msg); } mutex_unlock(&con->mutex); } /* * Revoke a message that we may be reading data into */ void ceph_msg_revoke_incoming(struct ceph_msg *msg) { struct ceph_connection *con = msg->con; if (!con) { dout("%s msg %p null con\n", __func__, msg); return; /* Message not in our possession */ } mutex_lock(&con->mutex); if (con->in_msg == msg) { WARN_ON(con->state != CEPH_CON_S_OPEN); dout("%s con %p msg %p was recving\n", __func__, con, msg); if (ceph_msgr2(from_msgr(con->msgr))) ceph_con_v2_revoke_incoming(con); else ceph_con_v1_revoke_incoming(con); ceph_msg_put(con->in_msg); con->in_msg = NULL; } else { dout("%s con %p msg %p not current, in_msg %p\n", __func__, con, msg, con->in_msg); } mutex_unlock(&con->mutex); } /* * Queue a keepalive byte to ensure the tcp connection is alive. */ void ceph_con_keepalive(struct ceph_connection *con) { dout("con_keepalive %p\n", con); mutex_lock(&con->mutex); clear_standby(con); ceph_con_flag_set(con, CEPH_CON_F_KEEPALIVE_PENDING); mutex_unlock(&con->mutex); if (!ceph_con_flag_test_and_set(con, CEPH_CON_F_WRITE_PENDING)) queue_con(con); } EXPORT_SYMBOL(ceph_con_keepalive); bool ceph_con_keepalive_expired(struct ceph_connection *con, unsigned long interval) { if (interval > 0 && (con->peer_features & CEPH_FEATURE_MSGR_KEEPALIVE2)) { struct timespec64 now; struct timespec64 ts; ktime_get_real_ts64(&now); jiffies_to_timespec64(interval, &ts); ts = timespec64_add(con->last_keepalive_ack, ts); return timespec64_compare(&now, &ts) >= 0; } return false; } static struct ceph_msg_data *ceph_msg_data_add(struct ceph_msg *msg) { BUG_ON(msg->num_data_items >= msg->max_data_items); return &msg->data[msg->num_data_items++]; } static void ceph_msg_data_destroy(struct ceph_msg_data *data) { if (data->type == CEPH_MSG_DATA_PAGES && data->own_pages) { int num_pages = calc_pages_for(data->alignment, data->length); ceph_release_page_vector(data->pages, num_pages); } else if (data->type == CEPH_MSG_DATA_PAGELIST) { ceph_pagelist_release(data->pagelist); } } void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, size_t length, size_t alignment, bool own_pages) { struct ceph_msg_data *data; BUG_ON(!pages); BUG_ON(!length); data = ceph_msg_data_add(msg); data->type = CEPH_MSG_DATA_PAGES; data->pages = pages; data->length = length; data->alignment = alignment & ~PAGE_MASK; data->own_pages = own_pages; msg->data_length += length; } EXPORT_SYMBOL(ceph_msg_data_add_pages); void ceph_msg_data_add_pagelist(struct ceph_msg *msg, struct ceph_pagelist *pagelist) { struct ceph_msg_data *data; BUG_ON(!pagelist); BUG_ON(!pagelist->length); data = ceph_msg_data_add(msg); data->type = CEPH_MSG_DATA_PAGELIST; refcount_inc(&pagelist->refcnt); data->pagelist = pagelist; msg->data_length += pagelist->length; } EXPORT_SYMBOL(ceph_msg_data_add_pagelist); #ifdef CONFIG_BLOCK void ceph_msg_data_add_bio(struct ceph_msg *msg, struct ceph_bio_iter *bio_pos, u32 length) { struct ceph_msg_data *data; data = ceph_msg_data_add(msg); data->type = CEPH_MSG_DATA_BIO; data->bio_pos = *bio_pos; data->bio_length = length; msg->data_length += length; } EXPORT_SYMBOL(ceph_msg_data_add_bio); #endif /* CONFIG_BLOCK */ void ceph_msg_data_add_bvecs(struct ceph_msg *msg, struct ceph_bvec_iter *bvec_pos) { struct ceph_msg_data *data; data = ceph_msg_data_add(msg); data->type = CEPH_MSG_DATA_BVECS; data->bvec_pos = *bvec_pos; msg->data_length += bvec_pos->iter.bi_size; } EXPORT_SYMBOL(ceph_msg_data_add_bvecs); void ceph_msg_data_add_iter(struct ceph_msg *msg, struct iov_iter *iter) { struct ceph_msg_data *data; data = ceph_msg_data_add(msg); data->type = CEPH_MSG_DATA_ITER; data->iter = *iter; msg->data_length += iov_iter_count(&data->iter); } /* * construct a new message with given type, size * the new msg has a ref count of 1. */ struct ceph_msg *ceph_msg_new2(int type, int front_len, int max_data_items, gfp_t flags, bool can_fail) { struct ceph_msg *m; m = kmem_cache_zalloc(ceph_msg_cache, flags); if (m == NULL) goto out; m->hdr.type = cpu_to_le16(type); m->hdr.priority = cpu_to_le16(CEPH_MSG_PRIO_DEFAULT); m->hdr.front_len = cpu_to_le32(front_len); INIT_LIST_HEAD(&m->list_head); kref_init(&m->kref); /* front */ if (front_len) { m->front.iov_base = kvmalloc(front_len, flags); if (m->front.iov_base == NULL) { dout("ceph_msg_new can't allocate %d bytes\n", front_len); goto out2; } } else { m->front.iov_base = NULL; } m->front_alloc_len = m->front.iov_len = front_len; if (max_data_items) { m->data = kmalloc_array(max_data_items, sizeof(*m->data), flags); if (!m->data) goto out2; m->max_data_items = max_data_items; } dout("ceph_msg_new %p front %d\n", m, front_len); return m; out2: ceph_msg_put(m); out: if (!can_fail) { pr_err("msg_new can't create type %d front %d\n", type, front_len); WARN_ON(1); } else { dout("msg_new can't create type %d front %d\n", type, front_len); } return NULL; } EXPORT_SYMBOL(ceph_msg_new2); struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail) { return ceph_msg_new2(type, front_len, 0, flags, can_fail); } EXPORT_SYMBOL(ceph_msg_new); /* * Allocate "middle" portion of a message, if it is needed and wasn't * allocated by alloc_msg. This allows us to read a small fixed-size * per-type header in the front and then gracefully fail (i.e., * propagate the error to the caller based on info in the front) when * the middle is too large. */ static int ceph_alloc_middle(struct ceph_connection *con, struct ceph_msg *msg) { int type = le16_to_cpu(msg->hdr.type); int middle_len = le32_to_cpu(msg->hdr.middle_len); dout("alloc_middle %p type %d %s middle_len %d\n", msg, type, ceph_msg_type_name(type), middle_len); BUG_ON(!middle_len); BUG_ON(msg->middle); msg->middle = ceph_buffer_new(middle_len, GFP_NOFS); if (!msg->middle) return -ENOMEM; return 0; } /* * Allocate a message for receiving an incoming message on a * connection, and save the result in con->in_msg. Uses the * connection's private alloc_msg op if available. * * Returns 0 on success, or a negative error code. * * On success, if we set *skip = 1: * - the next message should be skipped and ignored. * - con->in_msg == NULL * or if we set *skip = 0: * - con->in_msg is non-null. * On error (ENOMEM, EAGAIN, ...), * - con->in_msg == NULL */ int ceph_con_in_msg_alloc(struct ceph_connection *con, struct ceph_msg_header *hdr, int *skip) { int middle_len = le32_to_cpu(hdr->middle_len); struct ceph_msg *msg; int ret = 0; BUG_ON(con->in_msg != NULL); BUG_ON(!con->ops->alloc_msg); mutex_unlock(&con->mutex); msg = con->ops->alloc_msg(con, hdr, skip); mutex_lock(&con->mutex); if (con->state != CEPH_CON_S_OPEN) { if (msg) ceph_msg_put(msg); return -EAGAIN; } if (msg) { BUG_ON(*skip); msg_con_set(msg, con); con->in_msg = msg; } else { /* * Null message pointer means either we should skip * this message or we couldn't allocate memory. The * former is not an error. */ if (*skip) return 0; con->error_msg = "error allocating memory for incoming message"; return -ENOMEM; } memcpy(&con->in_msg->hdr, hdr, sizeof(*hdr)); if (middle_len && !con->in_msg->middle) { ret = ceph_alloc_middle(con, con->in_msg); if (ret < 0) { ceph_msg_put(con->in_msg); con->in_msg = NULL; } } return ret; } void ceph_con_get_out_msg(struct ceph_connection *con) { struct ceph_msg *msg; BUG_ON(list_empty(&con->out_queue)); msg = list_first_entry(&con->out_queue, struct ceph_msg, list_head); WARN_ON(msg->con != con); /* * Put the message on "sent" list using a ref from ceph_con_send(). * It is put when the message is acked or revoked. */ list_move_tail(&msg->list_head, &con->out_sent); /* * Only assign outgoing seq # if we haven't sent this message * yet. If it is requeued, resend with it's original seq. */ if (msg->needs_out_seq) { msg->hdr.seq = cpu_to_le64(++con->out_seq); msg->needs_out_seq = false; if (con->ops->reencode_message) con->ops->reencode_message(msg); } /* * Get a ref for out_msg. It is put when we are done sending the * message or in case of a fault. */ WARN_ON(con->out_msg); con->out_msg = ceph_msg_get(msg); } /* * Free a generically kmalloc'd message. */ static void ceph_msg_free(struct ceph_msg *m) { dout("%s %p\n", __func__, m); kvfree(m->front.iov_base); kfree(m->data); kmem_cache_free(ceph_msg_cache, m); } static void ceph_msg_release(struct kref *kref) { struct ceph_msg *m = container_of(kref, struct ceph_msg, kref); int i; dout("%s %p\n", __func__, m); WARN_ON(!list_empty(&m->list_head)); msg_con_set(m, NULL); /* drop middle, data, if any */ if (m->middle) { ceph_buffer_put(m->middle); m->middle = NULL; } for (i = 0; i < m->num_data_items; i++) ceph_msg_data_destroy(&m->data[i]); if (m->pool) ceph_msgpool_put(m->pool, m); else ceph_msg_free(m); } struct ceph_msg *ceph_msg_get(struct ceph_msg *msg) { dout("%s %p (was %d)\n", __func__, msg, kref_read(&msg->kref)); kref_get(&msg->kref); return msg; } EXPORT_SYMBOL(ceph_msg_get); void ceph_msg_put(struct ceph_msg *msg) { dout("%s %p (was %d)\n", __func__, msg, kref_read(&msg->kref)); kref_put(&msg->kref, ceph_msg_release); } EXPORT_SYMBOL(ceph_msg_put); void ceph_msg_dump(struct ceph_msg *msg) { pr_debug("msg_dump %p (front_alloc_len %d length %zd)\n", msg, msg->front_alloc_len, msg->data_length); print_hex_dump(KERN_DEBUG, "header: ", DUMP_PREFIX_OFFSET, 16, 1, &msg->hdr, sizeof(msg->hdr), true); print_hex_dump(KERN_DEBUG, " front: ", DUMP_PREFIX_OFFSET, 16, 1, msg->front.iov_base, msg->front.iov_len, true); if (msg->middle) print_hex_dump(KERN_DEBUG, "middle: ", DUMP_PREFIX_OFFSET, 16, 1, msg->middle->vec.iov_base, msg->middle->vec.iov_len, true); print_hex_dump(KERN_DEBUG, "footer: ", DUMP_PREFIX_OFFSET, 16, 1, &msg->footer, sizeof(msg->footer), true); } EXPORT_SYMBOL(ceph_msg_dump); |
| 620 17 18 17 18 18 17 18 607 627 627 627 629 644 647 644 643 642 16 643 33 650 650 583 250 249 649 33 644 16 628 648 641 644 16 16 16 179 178 596 613 16 596 612 612 76 76 76 76 76 197 197 5 5 604 605 529 606 606 604 15 16 591 291 590 76 77 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Interface between ext4 and JBD */ #include "ext4_jbd2.h" #include <trace/events/ext4.h> int ext4_inode_journal_mode(struct inode *inode) { if (EXT4_JOURNAL(inode) == NULL) return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */ /* We do not support data journalling with delayed allocation */ if (!S_ISREG(inode->i_mode) || ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) || test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA || (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) && !test_opt(inode->i_sb, DELALLOC))) { /* We do not support data journalling for encrypted data */ if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode)) return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */ return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */ } if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */ BUG(); } /* Just increment the non-pointer handle value */ static handle_t *ext4_get_nojournal(void) { handle_t *handle = current->journal_info; unsigned long ref_cnt = (unsigned long)handle; BUG_ON(ref_cnt >= EXT4_NOJOURNAL_MAX_REF_COUNT); ref_cnt++; handle = (handle_t *)ref_cnt; current->journal_info = handle; return handle; } /* Decrement the non-pointer handle value */ static void ext4_put_nojournal(handle_t *handle) { unsigned long ref_cnt = (unsigned long)handle; BUG_ON(ref_cnt == 0); ref_cnt--; handle = (handle_t *)ref_cnt; current->journal_info = handle; } /* * Wrappers for jbd2_journal_start/end. */ static int ext4_journal_check_start(struct super_block *sb) { journal_t *journal; might_sleep(); if (unlikely(ext4_forced_shutdown(sb))) return -EIO; if (WARN_ON_ONCE(sb_rdonly(sb))) return -EROFS; WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE); journal = EXT4_SB(sb)->s_journal; /* * Special case here: if the journal has aborted behind our * backs (eg. EIO in the commit thread), then we still need to * take the FS itself readonly cleanly. */ if (journal && is_journal_aborted(journal)) { ext4_abort(sb, -journal->j_errno, "Detected aborted journal"); return -EROFS; } return 0; } handle_t *__ext4_journal_start_sb(struct inode *inode, struct super_block *sb, unsigned int line, int type, int blocks, int rsv_blocks, int revoke_creds) { journal_t *journal; int err; if (inode) trace_ext4_journal_start_inode(inode, blocks, rsv_blocks, revoke_creds, type, _RET_IP_); else trace_ext4_journal_start_sb(sb, blocks, rsv_blocks, revoke_creds, type, _RET_IP_); err = ext4_journal_check_start(sb); if (err < 0) return ERR_PTR(err); journal = EXT4_SB(sb)->s_journal; if (!journal || (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)) return ext4_get_nojournal(); return jbd2__journal_start(journal, blocks, rsv_blocks, revoke_creds, GFP_NOFS, type, line); } int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle) { struct super_block *sb; int err; int rc; if (!ext4_handle_valid(handle)) { ext4_put_nojournal(handle); return 0; } err = handle->h_err; if (!handle->h_transaction) { rc = jbd2_journal_stop(handle); return err ? err : rc; } sb = handle->h_transaction->t_journal->j_private; rc = jbd2_journal_stop(handle); if (!err) err = rc; if (err) __ext4_std_error(sb, where, line, err); return err; } handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line, int type) { struct super_block *sb; int err; if (!ext4_handle_valid(handle)) return ext4_get_nojournal(); sb = handle->h_journal->j_private; trace_ext4_journal_start_reserved(sb, jbd2_handle_buffer_credits(handle), _RET_IP_); err = ext4_journal_check_start(sb); if (err < 0) { jbd2_journal_free_reserved(handle); return ERR_PTR(err); } err = jbd2_journal_start_reserved(handle, type, line); if (err < 0) return ERR_PTR(err); return handle; } int __ext4_journal_ensure_credits(handle_t *handle, int check_cred, int extend_cred, int revoke_cred) { if (!ext4_handle_valid(handle)) return 0; if (is_handle_aborted(handle)) return -EROFS; if (jbd2_handle_buffer_credits(handle) >= check_cred && handle->h_revoke_credits >= revoke_cred) return 0; extend_cred = max(0, extend_cred - jbd2_handle_buffer_credits(handle)); revoke_cred = max(0, revoke_cred - handle->h_revoke_credits); return ext4_journal_extend(handle, extend_cred, revoke_cred); } static void ext4_journal_abort_handle(const char *caller, unsigned int line, const char *err_fn, struct buffer_head *bh, handle_t *handle, int err) { char nbuf[16]; const char *errstr = ext4_decode_error(NULL, err, nbuf); BUG_ON(!ext4_handle_valid(handle)); if (bh) BUFFER_TRACE(bh, "abort"); if (!handle->h_err) handle->h_err = err; if (is_handle_aborted(handle)) return; printk(KERN_ERR "EXT4-fs: %s:%d: aborting transaction: %s in %s\n", caller, line, errstr, err_fn); jbd2_journal_abort_handle(handle); } static void ext4_check_bdev_write_error(struct super_block *sb) { struct address_space *mapping = sb->s_bdev->bd_mapping; struct ext4_sb_info *sbi = EXT4_SB(sb); int err; /* * If the block device has write error flag, it may have failed to * async write out metadata buffers in the background. In this case, * we could read old data from disk and write it out again, which * may lead to on-disk filesystem inconsistency. */ if (errseq_check(&mapping->wb_err, READ_ONCE(sbi->s_bdev_wb_err))) { spin_lock(&sbi->s_bdev_wb_lock); err = errseq_check_and_advance(&mapping->wb_err, &sbi->s_bdev_wb_err); spin_unlock(&sbi->s_bdev_wb_lock); if (err) ext4_error_err(sb, -err, "Error while async write back metadata"); } } int __ext4_journal_get_write_access(const char *where, unsigned int line, handle_t *handle, struct super_block *sb, struct buffer_head *bh, enum ext4_journal_trigger_type trigger_type) { int err; might_sleep(); if (ext4_handle_valid(handle)) { err = jbd2_journal_get_write_access(handle, bh); if (err) { ext4_journal_abort_handle(where, line, __func__, bh, handle, err); return err; } } else ext4_check_bdev_write_error(sb); if (trigger_type == EXT4_JTR_NONE || !ext4_has_metadata_csum(sb)) return 0; BUG_ON(trigger_type >= EXT4_JOURNAL_TRIGGER_COUNT); jbd2_journal_set_triggers(bh, &EXT4_SB(sb)->s_journal_triggers[trigger_type].tr_triggers); return 0; } /* * The ext4 forget function must perform a revoke if we are freeing data * which has been journaled. Metadata (eg. indirect blocks) must be * revoked in all cases. * * "bh" may be NULL: a metadata block may have been freed from memory * but there may still be a record of it in the journal, and that record * still needs to be revoked. */ int __ext4_forget(const char *where, unsigned int line, handle_t *handle, int is_metadata, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t blocknr) { int err; might_sleep(); trace_ext4_forget(inode, is_metadata, blocknr); BUFFER_TRACE(bh, "enter"); ext4_debug("forgetting bh %p: is_metadata=%d, mode %o, data mode %x\n", bh, is_metadata, inode->i_mode, test_opt(inode->i_sb, DATA_FLAGS)); /* In the no journal case, we can just do a bforget and return */ if (!ext4_handle_valid(handle)) { bforget(bh); return 0; } /* Never use the revoke function if we are doing full data * journaling: there is no need to, and a V1 superblock won't * support it. Otherwise, only skip the revoke on un-journaled * data blocks. */ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA || (!is_metadata && !ext4_should_journal_data(inode))) { if (bh) { BUFFER_TRACE(bh, "call jbd2_journal_forget"); err = jbd2_journal_forget(handle, bh); if (err) ext4_journal_abort_handle(where, line, __func__, bh, handle, err); return err; } return 0; } /* * data!=journal && (is_metadata || should_journal_data(inode)) */ BUFFER_TRACE(bh, "call jbd2_journal_revoke"); err = jbd2_journal_revoke(handle, blocknr, bh); if (err) { ext4_journal_abort_handle(where, line, __func__, bh, handle, err); __ext4_error(inode->i_sb, where, line, true, -err, 0, "error %d when attempting revoke", err); } BUFFER_TRACE(bh, "exit"); return err; } int __ext4_journal_get_create_access(const char *where, unsigned int line, handle_t *handle, struct super_block *sb, struct buffer_head *bh, enum ext4_journal_trigger_type trigger_type) { int err; if (!ext4_handle_valid(handle)) return 0; err = jbd2_journal_get_create_access(handle, bh); if (err) { ext4_journal_abort_handle(where, line, __func__, bh, handle, err); return err; } if (trigger_type == EXT4_JTR_NONE || !ext4_has_metadata_csum(sb)) return 0; BUG_ON(trigger_type >= EXT4_JOURNAL_TRIGGER_COUNT); jbd2_journal_set_triggers(bh, &EXT4_SB(sb)->s_journal_triggers[trigger_type].tr_triggers); return 0; } int __ext4_handle_dirty_metadata(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct buffer_head *bh) { int err = 0; might_sleep(); set_buffer_meta(bh); set_buffer_prio(bh); set_buffer_uptodate(bh); if (ext4_handle_valid(handle)) { err = jbd2_journal_dirty_metadata(handle, bh); /* Errors can only happen due to aborted journal or a nasty bug */ if (!is_handle_aborted(handle) && WARN_ON_ONCE(err)) { ext4_journal_abort_handle(where, line, __func__, bh, handle, err); if (inode == NULL) { pr_err("EXT4: jbd2_journal_dirty_metadata " "failed: handle type %u started at " "line %u, credits %u/%u, errcode %d", handle->h_type, handle->h_line_no, handle->h_requested_credits, jbd2_handle_buffer_credits(handle), err); return err; } ext4_error_inode(inode, where, line, bh->b_blocknr, "journal_dirty_metadata failed: " "handle type %u started at line %u, " "credits %u/%u, errcode %d", handle->h_type, handle->h_line_no, handle->h_requested_credits, jbd2_handle_buffer_credits(handle), err); } } else { if (inode) mark_buffer_dirty_inode(bh, inode); else mark_buffer_dirty(bh); if (inode && inode_needs_sync(inode)) { sync_dirty_buffer(bh); if (buffer_req(bh) && !buffer_uptodate(bh)) { ext4_error_inode_err(inode, where, line, bh->b_blocknr, EIO, "IO error syncing itable block"); err = -EIO; } } } return err; } |
| 351 12 104 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_ICMPV6_H #define _LINUX_ICMPV6_H #include <linux/skbuff.h> #include <linux/ipv6.h> #include <uapi/linux/icmpv6.h> static inline struct icmp6hdr *icmp6_hdr(const struct sk_buff *skb) { return (struct icmp6hdr *)skb_transport_header(skb); } #include <linux/netdevice.h> #if IS_ENABLED(CONFIG_IPV6) typedef void ip6_icmp_send_t(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr, const struct inet6_skb_parm *parm); void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct in6_addr *force_saddr, const struct inet6_skb_parm *parm); #if IS_BUILTIN(CONFIG_IPV6) static inline void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct inet6_skb_parm *parm) { icmp6_send(skb, type, code, info, NULL, parm); } static inline int inet6_register_icmp_sender(ip6_icmp_send_t *fn) { BUILD_BUG_ON(fn != icmp6_send); return 0; } static inline int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn) { BUILD_BUG_ON(fn != icmp6_send); return 0; } #else extern void __icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, const struct inet6_skb_parm *parm); extern int inet6_register_icmp_sender(ip6_icmp_send_t *fn); extern int inet6_unregister_icmp_sender(ip6_icmp_send_t *fn); #endif static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { __icmpv6_send(skb, type, code, info, IP6CB(skb)); } int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, unsigned int data_len); #if IS_ENABLED(CONFIG_NF_NAT) void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info); #else static inline void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) { struct inet6_skb_parm parm = { 0 }; __icmpv6_send(skb_in, type, code, info, &parm); } #endif #else static inline void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { } static inline void icmpv6_ndo_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) { } #endif extern int icmpv6_init(void); extern int icmpv6_err_convert(u8 type, u8 code, int *err); extern void icmpv6_cleanup(void); extern void icmpv6_param_prob_reason(struct sk_buff *skb, u8 code, int pos, enum skb_drop_reason reason); struct flowi6; struct in6_addr; void icmpv6_flow_init(const struct sock *sk, struct flowi6 *fl6, u8 type, const struct in6_addr *saddr, const struct in6_addr *daddr, int oif); static inline void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos) { icmpv6_param_prob_reason(skb, code, pos, SKB_DROP_REASON_NOT_SPECIFIED); } static inline bool icmpv6_is_err(int type) { switch (type) { case ICMPV6_DEST_UNREACH: case ICMPV6_PKT_TOOBIG: case ICMPV6_TIME_EXCEED: case ICMPV6_PARAMPROB: return true; } return false; } #endif |
| 10 10 10 10 10 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 | /* * linux/fs/nls/mac-romanian.c * * Charset macromanian translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ /* * COPYRIGHT AND PERMISSION NOTICE * * Copyright 1991-2012 Unicode, Inc. All rights reserved. Distributed under * the Terms of Use in http://www.unicode.org/copyright.html. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of the Unicode data files and any associated documentation (the "Data * Files") or Unicode software and any associated documentation (the * "Software") to deal in the Data Files or Software without restriction, * including without limitation the rights to use, copy, modify, merge, * publish, distribute, and/or sell copies of the Data Files or Software, and * to permit persons to whom the Data Files or Software are furnished to do * so, provided that (a) the above copyright notice(s) and this permission * notice appear with all copies of the Data Files or Software, (b) both the * above copyright notice(s) and this permission notice appear in associated * documentation, and (c) there is clear notice in each modified Data File or * in the Software as well as in the documentation associated with the Data * File(s) or Software that the data or software has been modified. * * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY * KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF * THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS * INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR * PERFORMANCE OF THE DATA FILES OR SOFTWARE. * * Except as contained in this notice, the name of a copyright holder shall * not be used in advertising or otherwise to promote the sale, use or other * dealings in these Data Files or Software without prior written * authorization of the copyright holder. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00 */ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10 */ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20 */ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30 */ 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037, 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40 */ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50 */ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60 */ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70 */ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80 */ 0x00c4, 0x00c5, 0x00c7, 0x00c9, 0x00d1, 0x00d6, 0x00dc, 0x00e1, 0x00e0, 0x00e2, 0x00e4, 0x00e3, 0x00e5, 0x00e7, 0x00e9, 0x00e8, /* 0x90 */ 0x00ea, 0x00eb, 0x00ed, 0x00ec, 0x00ee, 0x00ef, 0x00f1, 0x00f3, 0x00f2, 0x00f4, 0x00f6, 0x00f5, 0x00fa, 0x00f9, 0x00fb, 0x00fc, /* 0xa0 */ 0x2020, 0x00b0, 0x00a2, 0x00a3, 0x00a7, 0x2022, 0x00b6, 0x00df, 0x00ae, 0x00a9, 0x2122, 0x00b4, 0x00a8, 0x2260, 0x0102, 0x0218, /* 0xb0 */ 0x221e, 0x00b1, 0x2264, 0x2265, 0x00a5, 0x00b5, 0x2202, 0x2211, 0x220f, 0x03c0, 0x222b, 0x00aa, 0x00ba, 0x03a9, 0x0103, 0x0219, /* 0xc0 */ 0x00bf, 0x00a1, 0x00ac, 0x221a, 0x0192, 0x2248, 0x2206, 0x00ab, 0x00bb, 0x2026, 0x00a0, 0x00c0, 0x00c3, 0x00d5, 0x0152, 0x0153, /* 0xd0 */ 0x2013, 0x2014, 0x201c, 0x201d, 0x2018, 0x2019, 0x00f7, 0x25ca, 0x00ff, 0x0178, 0x2044, 0x20ac, 0x2039, 0x203a, 0x021a, 0x021b, /* 0xe0 */ 0x2021, 0x00b7, 0x201a, 0x201e, 0x2030, 0x00c2, 0x00ca, 0x00c1, 0x00cb, 0x00c8, 0x00cd, 0x00ce, 0x00cf, 0x00cc, 0x00d3, 0x00d4, /* 0xf0 */ 0xf8ff, 0x00d2, 0x00da, 0x00db, 0x00d9, 0x0131, 0x02c6, 0x02dc, 0x00af, 0x02d8, 0x02d9, 0x02da, 0x00b8, 0x02dd, 0x02db, 0x02c7, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0xca, 0xc1, 0xa2, 0xa3, 0x00, 0xb4, 0x00, 0xa4, /* 0xa0-0xa7 */ 0xac, 0xa9, 0xbb, 0xc7, 0xc2, 0x00, 0xa8, 0xf8, /* 0xa8-0xaf */ 0xa1, 0xb1, 0x00, 0x00, 0xab, 0xb5, 0xa6, 0xe1, /* 0xb0-0xb7 */ 0xfc, 0x00, 0xbc, 0xc8, 0x00, 0x00, 0x00, 0xc0, /* 0xb8-0xbf */ 0xcb, 0xe7, 0xe5, 0xcc, 0x80, 0x81, 0x00, 0x82, /* 0xc0-0xc7 */ 0xe9, 0x83, 0xe6, 0xe8, 0xed, 0xea, 0xeb, 0xec, /* 0xc8-0xcf */ 0x00, 0x84, 0xf1, 0xee, 0xef, 0xcd, 0x85, 0x00, /* 0xd0-0xd7 */ 0x00, 0xf4, 0xf2, 0xf3, 0x86, 0x00, 0x00, 0xa7, /* 0xd8-0xdf */ 0x88, 0x87, 0x89, 0x8b, 0x8a, 0x8c, 0x00, 0x8d, /* 0xe0-0xe7 */ 0x8f, 0x8e, 0x90, 0x91, 0x93, 0x92, 0x94, 0x95, /* 0xe8-0xef */ 0x00, 0x96, 0x98, 0x97, 0x99, 0x9b, 0x9a, 0xd6, /* 0xf0-0xf7 */ 0x00, 0x9d, 0x9c, 0x9e, 0x9f, 0x00, 0x00, 0xd8, /* 0xf8-0xff */ }; static const unsigned char page01[256] = { 0x00, 0x00, 0xae, 0xbe, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0xf5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0xce, 0xcf, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0xd9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0xc4, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page02[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xaf, 0xbf, 0xde, 0xdf, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf6, 0xff, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0xf9, 0xfa, 0xfb, 0xfe, 0xf7, 0xfd, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page03[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0xbd, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0xb9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page20[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0xd0, 0xd1, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0xd4, 0xd5, 0xe2, 0x00, 0xd2, 0xd3, 0xe3, 0x00, /* 0x18-0x1f */ 0xa0, 0xe0, 0xa5, 0x00, 0x00, 0x00, 0xc9, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0xe4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0xdc, 0xdd, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0xdb, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page21[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0xaa, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page22[256] = { 0x00, 0x00, 0xb6, 0x00, 0x00, 0x00, 0xc6, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xb8, /* 0x08-0x0f */ 0x00, 0xb7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, 0xb0, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0xba, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0xc5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0xad, 0x00, 0x00, 0x00, 0xb2, 0xb3, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char page25[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0xd7, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char pagef8[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf0, /* 0xf8-0xff */ }; static const unsigned char *const page_uni2charset[256] = { page00, page01, page02, page03, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, page20, page21, page22, NULL, NULL, page25, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, pagef8, NULL, NULL, NULL, NULL, NULL, NULL, NULL, }; static const unsigned char charset2lower[256] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "macromanian", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_macromanian(void) { return register_nls(&table); } static void __exit exit_nls_macromanian(void) { unregister_nls(&table); } module_init(init_nls_macromanian) module_exit(exit_nls_macromanian) MODULE_DESCRIPTION("NLS Codepage macromanian"); MODULE_LICENSE("Dual BSD/GPL"); |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 | // SPDX-License-Identifier: GPL-2.0-only /* * Driver for the ov7660 sensor * * Copyright (C) 2009 Erik Andrén * Copyright (C) 2007 Ilyes Gouta. Based on the m5603x Linux Driver Project. * Copyright (C) 2005 m5603x Linux Driver Project <m5602@x3ng.com.br> * * Portions of code to USB interface and ALi driver software, * Copyright (c) 2006 Willem Duinker * v4l2 interface modeled after the V4L2 driver * for SN9C10x PC Camera Controllers */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "m5602_ov7660.h" static int ov7660_s_ctrl(struct v4l2_ctrl *ctrl); static void ov7660_dump_registers(struct sd *sd); static const unsigned char preinit_ov7660[][4] = { {BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02}, {BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0}, {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0}, {BRIDGE, M5602_XB_ADC_CTRL, 0xc0}, {BRIDGE, M5602_XB_SENSOR_TYPE, 0x0d}, {BRIDGE, M5602_XB_SENSOR_CTRL, 0x00}, {BRIDGE, M5602_XB_GPIO_DIR, 0x03}, {BRIDGE, M5602_XB_GPIO_DIR, 0x03}, {BRIDGE, M5602_XB_ADC_CTRL, 0xc0}, {BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c}, {SENSOR, OV7660_OFON, 0x0c}, {SENSOR, OV7660_COM2, 0x11}, {SENSOR, OV7660_COM7, 0x05}, {BRIDGE, M5602_XB_GPIO_DIR, 0x01}, {BRIDGE, M5602_XB_GPIO_DAT, 0x04}, {BRIDGE, M5602_XB_GPIO_EN_H, 0x06}, {BRIDGE, M5602_XB_GPIO_DIR_H, 0x06}, {BRIDGE, M5602_XB_GPIO_DAT_H, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x08}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0}, {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0}, {BRIDGE, M5602_XB_ADC_CTRL, 0xc0}, {BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c}, {BRIDGE, M5602_XB_GPIO_DIR, 0x05}, {BRIDGE, M5602_XB_GPIO_DAT, 0x00}, {BRIDGE, M5602_XB_GPIO_EN_H, 0x06}, {BRIDGE, M5602_XB_GPIO_EN_L, 0x00} }; static const unsigned char init_ov7660[][4] = { {BRIDGE, M5602_XB_MCU_CLK_DIV, 0x02}, {BRIDGE, M5602_XB_MCU_CLK_CTRL, 0xb0}, {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0}, {BRIDGE, M5602_XB_ADC_CTRL, 0xc0}, {BRIDGE, M5602_XB_SENSOR_TYPE, 0x0d}, {BRIDGE, M5602_XB_SENSOR_CTRL, 0x00}, {BRIDGE, M5602_XB_GPIO_DIR, 0x01}, {BRIDGE, M5602_XB_GPIO_DIR, 0x01}, {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0}, {BRIDGE, M5602_XB_ADC_CTRL, 0xc0}, {BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c}, {BRIDGE, M5602_XB_GPIO_DIR, 0x05}, {BRIDGE, M5602_XB_GPIO_DAT, 0x00}, {BRIDGE, M5602_XB_GPIO_EN_H, 0x06}, {BRIDGE, M5602_XB_GPIO_EN_L, 0x00}, {SENSOR, OV7660_COM7, 0x80}, {SENSOR, OV7660_CLKRC, 0x80}, {SENSOR, OV7660_COM9, 0x4c}, {SENSOR, OV7660_OFON, 0x43}, {SENSOR, OV7660_COM12, 0x28}, {SENSOR, OV7660_COM8, 0x00}, {SENSOR, OV7660_COM10, 0x40}, {SENSOR, OV7660_HSTART, 0x0c}, {SENSOR, OV7660_HSTOP, 0x61}, {SENSOR, OV7660_HREF, 0xa4}, {SENSOR, OV7660_PSHFT, 0x0b}, {SENSOR, OV7660_VSTART, 0x01}, {SENSOR, OV7660_VSTOP, 0x7a}, {SENSOR, OV7660_VSTOP, 0x00}, {SENSOR, OV7660_COM7, 0x05}, {SENSOR, OV7660_COM6, 0x42}, {SENSOR, OV7660_BBIAS, 0x94}, {SENSOR, OV7660_GbBIAS, 0x94}, {SENSOR, OV7660_RSVD29, 0x94}, {SENSOR, OV7660_RBIAS, 0x94}, {SENSOR, OV7660_COM1, 0x00}, {SENSOR, OV7660_AECH, 0x00}, {SENSOR, OV7660_AECHH, 0x00}, {SENSOR, OV7660_ADC, 0x05}, {SENSOR, OV7660_COM13, 0x00}, {SENSOR, OV7660_RSVDA1, 0x23}, {SENSOR, OV7660_TSLB, 0x0d}, {SENSOR, OV7660_HV, 0x80}, {SENSOR, OV7660_LCC1, 0x00}, {SENSOR, OV7660_LCC2, 0x00}, {SENSOR, OV7660_LCC3, 0x10}, {SENSOR, OV7660_LCC4, 0x40}, {SENSOR, OV7660_LCC5, 0x01}, {SENSOR, OV7660_AECH, 0x20}, {SENSOR, OV7660_COM1, 0x00}, {SENSOR, OV7660_OFON, 0x0c}, {SENSOR, OV7660_COM2, 0x11}, {SENSOR, OV7660_COM7, 0x05}, {BRIDGE, M5602_XB_GPIO_DIR, 0x01}, {BRIDGE, M5602_XB_GPIO_DAT, 0x04}, {BRIDGE, M5602_XB_GPIO_EN_H, 0x06}, {BRIDGE, M5602_XB_GPIO_DIR_H, 0x06}, {BRIDGE, M5602_XB_GPIO_DAT_H, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x08}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0}, {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0}, {BRIDGE, M5602_XB_ADC_CTRL, 0xc0}, {BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c}, {BRIDGE, M5602_XB_GPIO_DIR, 0x05}, {BRIDGE, M5602_XB_GPIO_DAT, 0x00}, {BRIDGE, M5602_XB_GPIO_EN_H, 0x06}, {BRIDGE, M5602_XB_GPIO_EN_L, 0x00}, {SENSOR, OV7660_AECH, 0x5f}, {SENSOR, OV7660_COM1, 0x03}, {SENSOR, OV7660_OFON, 0x0c}, {SENSOR, OV7660_COM2, 0x11}, {SENSOR, OV7660_COM7, 0x05}, {BRIDGE, M5602_XB_GPIO_DIR, 0x01}, {BRIDGE, M5602_XB_GPIO_DAT, 0x04}, {BRIDGE, M5602_XB_GPIO_EN_H, 0x06}, {BRIDGE, M5602_XB_GPIO_DIR_H, 0x06}, {BRIDGE, M5602_XB_GPIO_DAT_H, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x08}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0}, {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0}, {BRIDGE, M5602_XB_ADC_CTRL, 0xc0}, {BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c}, {BRIDGE, M5602_XB_GPIO_DIR, 0x05}, {BRIDGE, M5602_XB_GPIO_DAT, 0x00}, {BRIDGE, M5602_XB_GPIO_EN_H, 0x06}, {BRIDGE, M5602_XB_GPIO_EN_L, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x06}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0}, {BRIDGE, M5602_XB_ADC_CTRL, 0xc0}, {BRIDGE, M5602_XB_SENSOR_TYPE, 0x0c}, {BRIDGE, M5602_XB_LINE_OF_FRAME_H, 0x81}, {BRIDGE, M5602_XB_PIX_OF_LINE_H, 0x82}, {BRIDGE, M5602_XB_SIG_INI, 0x01}, {BRIDGE, M5602_XB_VSYNC_PARA, 0x00}, {BRIDGE, M5602_XB_VSYNC_PARA, 0x08}, {BRIDGE, M5602_XB_VSYNC_PARA, 0x00}, {BRIDGE, M5602_XB_VSYNC_PARA, 0x00}, {BRIDGE, M5602_XB_VSYNC_PARA, 0x01}, {BRIDGE, M5602_XB_VSYNC_PARA, 0xec}, {BRIDGE, M5602_XB_VSYNC_PARA, 0x00}, {BRIDGE, M5602_XB_VSYNC_PARA, 0x00}, {BRIDGE, M5602_XB_SIG_INI, 0x00}, {BRIDGE, M5602_XB_SIG_INI, 0x02}, {BRIDGE, M5602_XB_HSYNC_PARA, 0x00}, {BRIDGE, M5602_XB_HSYNC_PARA, 0x27}, {BRIDGE, M5602_XB_HSYNC_PARA, 0x02}, {BRIDGE, M5602_XB_HSYNC_PARA, 0xa7}, {BRIDGE, M5602_XB_SIG_INI, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_DIV, 0x00}, {BRIDGE, M5602_XB_SEN_CLK_CTRL, 0xb0}, }; static struct v4l2_pix_format ov7660_modes[] = { { 640, 480, V4L2_PIX_FMT_SBGGR8, V4L2_FIELD_NONE, .sizeimage = 640 * 480, .bytesperline = 640, .colorspace = V4L2_COLORSPACE_SRGB, .priv = 0 } }; static const struct v4l2_ctrl_ops ov7660_ctrl_ops = { .s_ctrl = ov7660_s_ctrl, }; int ov7660_probe(struct sd *sd) { int err = 0, i; u8 prod_id = 0, ver_id = 0; if (force_sensor) { if (force_sensor == OV7660_SENSOR) { pr_info("Forcing an %s sensor\n", ov7660.name); goto sensor_found; } /* If we want to force another sensor, don't try to probe this one */ return -ENODEV; } /* Do the preinit */ for (i = 0; i < ARRAY_SIZE(preinit_ov7660) && !err; i++) { u8 data[2]; if (preinit_ov7660[i][0] == BRIDGE) { err = m5602_write_bridge(sd, preinit_ov7660[i][1], preinit_ov7660[i][2]); } else { data[0] = preinit_ov7660[i][2]; err = m5602_write_sensor(sd, preinit_ov7660[i][1], data, 1); } } if (err < 0) return err; if (m5602_read_sensor(sd, OV7660_PID, &prod_id, 1)) return -ENODEV; if (m5602_read_sensor(sd, OV7660_VER, &ver_id, 1)) return -ENODEV; pr_info("Sensor reported 0x%x%x\n", prod_id, ver_id); if ((prod_id == 0x76) && (ver_id == 0x60)) { pr_info("Detected a ov7660 sensor\n"); goto sensor_found; } return -ENODEV; sensor_found: sd->gspca_dev.cam.cam_mode = ov7660_modes; sd->gspca_dev.cam.nmodes = ARRAY_SIZE(ov7660_modes); return 0; } int ov7660_init(struct sd *sd) { int i, err; /* Init the sensor */ for (i = 0; i < ARRAY_SIZE(init_ov7660); i++) { u8 data[2]; if (init_ov7660[i][0] == BRIDGE) { err = m5602_write_bridge(sd, init_ov7660[i][1], init_ov7660[i][2]); } else { data[0] = init_ov7660[i][2]; err = m5602_write_sensor(sd, init_ov7660[i][1], data, 1); } if (err < 0) return err; } if (dump_sensor) ov7660_dump_registers(sd); return 0; } int ov7660_init_controls(struct sd *sd) { struct v4l2_ctrl_handler *hdl = &sd->gspca_dev.ctrl_handler; sd->gspca_dev.vdev.ctrl_handler = hdl; v4l2_ctrl_handler_init(hdl, 6); v4l2_ctrl_new_std(hdl, &ov7660_ctrl_ops, V4L2_CID_AUTO_WHITE_BALANCE, 0, 1, 1, 1); v4l2_ctrl_new_std_menu(hdl, &ov7660_ctrl_ops, V4L2_CID_EXPOSURE_AUTO, 1, 0, V4L2_EXPOSURE_AUTO); sd->autogain = v4l2_ctrl_new_std(hdl, &ov7660_ctrl_ops, V4L2_CID_AUTOGAIN, 0, 1, 1, 1); sd->gain = v4l2_ctrl_new_std(hdl, &ov7660_ctrl_ops, V4L2_CID_GAIN, 0, 255, 1, OV7660_DEFAULT_GAIN); sd->hflip = v4l2_ctrl_new_std(hdl, &ov7660_ctrl_ops, V4L2_CID_HFLIP, 0, 1, 1, 0); sd->vflip = v4l2_ctrl_new_std(hdl, &ov7660_ctrl_ops, V4L2_CID_VFLIP, 0, 1, 1, 0); if (hdl->error) { pr_err("Could not initialize controls\n"); return hdl->error; } v4l2_ctrl_auto_cluster(2, &sd->autogain, 0, false); v4l2_ctrl_cluster(2, &sd->hflip); return 0; } int ov7660_start(struct sd *sd) { return 0; } int ov7660_stop(struct sd *sd) { return 0; } void ov7660_disconnect(struct sd *sd) { ov7660_stop(sd); sd->sensor = NULL; } static int ov7660_set_gain(struct gspca_dev *gspca_dev, __s32 val) { int err; u8 i2c_data = val; struct sd *sd = (struct sd *) gspca_dev; gspca_dbg(gspca_dev, D_CONF, "Setting gain to %d\n", val); err = m5602_write_sensor(sd, OV7660_GAIN, &i2c_data, 1); return err; } static int ov7660_set_auto_white_balance(struct gspca_dev *gspca_dev, __s32 val) { int err; u8 i2c_data; struct sd *sd = (struct sd *) gspca_dev; gspca_dbg(gspca_dev, D_CONF, "Set auto white balance to %d\n", val); err = m5602_read_sensor(sd, OV7660_COM8, &i2c_data, 1); if (err < 0) return err; i2c_data = ((i2c_data & 0xfd) | ((val & 0x01) << 1)); err = m5602_write_sensor(sd, OV7660_COM8, &i2c_data, 1); return err; } static int ov7660_set_auto_gain(struct gspca_dev *gspca_dev, __s32 val) { int err; u8 i2c_data; struct sd *sd = (struct sd *) gspca_dev; gspca_dbg(gspca_dev, D_CONF, "Set auto gain control to %d\n", val); err = m5602_read_sensor(sd, OV7660_COM8, &i2c_data, 1); if (err < 0) return err; i2c_data = ((i2c_data & 0xfb) | ((val & 0x01) << 2)); return m5602_write_sensor(sd, OV7660_COM8, &i2c_data, 1); } static int ov7660_set_auto_exposure(struct gspca_dev *gspca_dev, __s32 val) { int err; u8 i2c_data; struct sd *sd = (struct sd *) gspca_dev; gspca_dbg(gspca_dev, D_CONF, "Set auto exposure control to %d\n", val); err = m5602_read_sensor(sd, OV7660_COM8, &i2c_data, 1); if (err < 0) return err; val = (val == V4L2_EXPOSURE_AUTO); i2c_data = ((i2c_data & 0xfe) | ((val & 0x01) << 0)); return m5602_write_sensor(sd, OV7660_COM8, &i2c_data, 1); } static int ov7660_set_hvflip(struct gspca_dev *gspca_dev) { int err; u8 i2c_data; struct sd *sd = (struct sd *) gspca_dev; gspca_dbg(gspca_dev, D_CONF, "Set hvflip to %d, %d\n", sd->hflip->val, sd->vflip->val); i2c_data = (sd->hflip->val << 5) | (sd->vflip->val << 4); err = m5602_write_sensor(sd, OV7660_MVFP, &i2c_data, 1); return err; } static int ov7660_s_ctrl(struct v4l2_ctrl *ctrl) { struct gspca_dev *gspca_dev = container_of(ctrl->handler, struct gspca_dev, ctrl_handler); struct sd *sd = (struct sd *) gspca_dev; int err; if (!gspca_dev->streaming) return 0; switch (ctrl->id) { case V4L2_CID_AUTO_WHITE_BALANCE: err = ov7660_set_auto_white_balance(gspca_dev, ctrl->val); break; case V4L2_CID_EXPOSURE_AUTO: err = ov7660_set_auto_exposure(gspca_dev, ctrl->val); break; case V4L2_CID_AUTOGAIN: err = ov7660_set_auto_gain(gspca_dev, ctrl->val); if (err || ctrl->val) return err; err = ov7660_set_gain(gspca_dev, sd->gain->val); break; case V4L2_CID_HFLIP: err = ov7660_set_hvflip(gspca_dev); break; default: return -EINVAL; } return err; } static void ov7660_dump_registers(struct sd *sd) { int address; pr_info("Dumping the ov7660 register state\n"); for (address = 0; address < 0xa9; address++) { u8 value; m5602_read_sensor(sd, address, &value, 1); pr_info("register 0x%x contains 0x%x\n", address, value); } pr_info("ov7660 register state dump complete\n"); pr_info("Probing for which registers that are read/write\n"); for (address = 0; address < 0xff; address++) { u8 old_value, ctrl_value; u8 test_value[2] = {0xff, 0xff}; m5602_read_sensor(sd, address, &old_value, 1); m5602_write_sensor(sd, address, test_value, 1); m5602_read_sensor(sd, address, &ctrl_value, 1); if (ctrl_value == test_value[0]) pr_info("register 0x%x is writeable\n", address); else pr_info("register 0x%x is read only\n", address); /* Restore original value */ m5602_write_sensor(sd, address, &old_value, 1); } } |
| 5 4 5 5 3 5 5 3 3 1 3 2 5 6 3 6 2 5 2 3 6 5 2 2 4 4 4 4 2 2 2 2 2 2 2 2 11 9 11 11 11 13 11 13 3 11 13 11 2 2 2 3 2 3 3 2 2 2 2 2 1 1 1 1 1 1 1 2 2 2 2 8 7 6 5 1 4 4 1 4 2 2 2 4 4 8 18 17 17 16 15 14 14 2 14 18 1 8 12 11 10 12 9 9 9 9 8 8 7 7 7 1 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 | // SPDX-License-Identifier: GPL-2.0-only /* * (C) 2012-2013 by Pablo Neira Ayuso <pablo@netfilter.org> * * This software has been sponsored by Sophos Astaro <http://www.sophos.com> */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nf_tables.h> #include <linux/netfilter/nf_tables_compat.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter_bridge/ebtables.h> #include <linux/netfilter_arp/arp_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_log.h> /* Used for matches where *info is larger than X byte */ #define NFT_MATCH_LARGE_THRESH 192 struct nft_xt_match_priv { void *info; }; static int nft_compat_chain_validate_dependency(const struct nft_ctx *ctx, const char *tablename) { enum nft_chain_types type = NFT_CHAIN_T_DEFAULT; const struct nft_chain *chain = ctx->chain; const struct nft_base_chain *basechain; if (!tablename || !nft_is_base_chain(chain)) return 0; basechain = nft_base_chain(chain); if (strcmp(tablename, "nat") == 0) { if (ctx->family != NFPROTO_BRIDGE) type = NFT_CHAIN_T_NAT; if (basechain->type->type != type) return -EINVAL; } return 0; } union nft_entry { struct ipt_entry e4; struct ip6t_entry e6; struct ebt_entry ebt; struct arpt_entry arp; }; static inline void nft_compat_set_par(struct xt_action_param *par, const struct nft_pktinfo *pkt, const void *xt, const void *xt_info) { par->state = pkt->state; par->thoff = nft_thoff(pkt); par->fragoff = pkt->fragoff; par->target = xt; par->targinfo = xt_info; par->hotdrop = false; } static void nft_target_eval_xt(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { void *info = nft_expr_priv(expr); struct xt_target *target = expr->ops->data; struct sk_buff *skb = pkt->skb; struct xt_action_param xt; int ret; nft_compat_set_par(&xt, pkt, target, info); ret = target->target(skb, &xt); if (xt.hotdrop) ret = NF_DROP; switch (ret) { case XT_CONTINUE: regs->verdict.code = NFT_CONTINUE; break; default: regs->verdict.code = ret; break; } } static void nft_target_eval_bridge(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { void *info = nft_expr_priv(expr); struct xt_target *target = expr->ops->data; struct sk_buff *skb = pkt->skb; struct xt_action_param xt; int ret; nft_compat_set_par(&xt, pkt, target, info); ret = target->target(skb, &xt); if (xt.hotdrop) ret = NF_DROP; switch (ret) { case EBT_ACCEPT: regs->verdict.code = NF_ACCEPT; break; case EBT_DROP: regs->verdict.code = NF_DROP; break; case EBT_CONTINUE: regs->verdict.code = NFT_CONTINUE; break; case EBT_RETURN: regs->verdict.code = NFT_RETURN; break; default: regs->verdict.code = ret; break; } } static const struct nla_policy nft_target_policy[NFTA_TARGET_MAX + 1] = { [NFTA_TARGET_NAME] = { .type = NLA_NUL_STRING }, [NFTA_TARGET_REV] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_TARGET_INFO] = { .type = NLA_BINARY }, }; static void nft_target_set_tgchk_param(struct xt_tgchk_param *par, const struct nft_ctx *ctx, struct xt_target *target, void *info, union nft_entry *entry, u16 proto, bool inv) { par->net = ctx->net; par->table = ctx->table->name; switch (ctx->family) { case AF_INET: entry->e4.ip.proto = proto; entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0; break; case AF_INET6: if (proto) entry->e6.ipv6.flags |= IP6T_F_PROTO; entry->e6.ipv6.proto = proto; entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0; break; case NFPROTO_BRIDGE: entry->ebt.ethproto = (__force __be16)proto; entry->ebt.invflags = inv ? EBT_IPROTO : 0; break; case NFPROTO_ARP: break; } par->entryinfo = entry; par->target = target; par->targinfo = info; if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); const struct nf_hook_ops *ops = &basechain->ops; par->hook_mask = 1 << ops->hooknum; } else { par->hook_mask = 0; } par->family = ctx->family; par->nft_compat = true; } static void target_compat_from_user(struct xt_target *t, void *in, void *out) { int pad; memcpy(out, in, t->targetsize); pad = XT_ALIGN(t->targetsize) - t->targetsize; if (pad > 0) memset(out + t->targetsize, 0, pad); } static const struct nla_policy nft_rule_compat_policy[NFTA_RULE_COMPAT_MAX + 1] = { [NFTA_RULE_COMPAT_PROTO] = { .type = NLA_U32 }, [NFTA_RULE_COMPAT_FLAGS] = { .type = NLA_U32 }, }; static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) { struct nlattr *tb[NFTA_RULE_COMPAT_MAX+1]; u32 l4proto; u32 flags; int err; err = nla_parse_nested_deprecated(tb, NFTA_RULE_COMPAT_MAX, attr, nft_rule_compat_policy, NULL); if (err < 0) return err; if (!tb[NFTA_RULE_COMPAT_PROTO] || !tb[NFTA_RULE_COMPAT_FLAGS]) return -EINVAL; flags = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_FLAGS])); if (flags & NFT_RULE_COMPAT_F_UNUSED || flags & ~NFT_RULE_COMPAT_F_MASK) return -EINVAL; if (flags & NFT_RULE_COMPAT_F_INV) *inv = true; l4proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO])); if (l4proto > U16_MAX) return -EINVAL; *proto = l4proto; return 0; } static void nft_compat_wait_for_destructors(void) { /* xtables matches or targets can have side effects, e.g. * creation/destruction of /proc files. * The xt ->destroy functions are run asynchronously from * work queue. If we have pending invocations we thus * need to wait for those to finish. */ nf_tables_trans_destroy_flush_work(); } static int nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { void *info = nft_expr_priv(expr); struct xt_target *target = expr->ops->data; struct xt_tgchk_param par; size_t size = XT_ALIGN(nla_len(tb[NFTA_TARGET_INFO])); u16 proto = 0; bool inv = false; union nft_entry e = {}; int ret; target_compat_from_user(target, nla_data(tb[NFTA_TARGET_INFO]), info); if (ctx->nla[NFTA_RULE_COMPAT]) { ret = nft_parse_compat(ctx->nla[NFTA_RULE_COMPAT], &proto, &inv); if (ret < 0) return ret; } nft_target_set_tgchk_param(&par, ctx, target, info, &e, proto, inv); nft_compat_wait_for_destructors(); ret = xt_check_target(&par, size, proto, inv); if (ret < 0) { if (ret == -ENOENT) { const char *modname = NULL; if (strcmp(target->name, "LOG") == 0) modname = "nf_log_syslog"; else if (strcmp(target->name, "NFLOG") == 0) modname = "nfnetlink_log"; if (modname && nft_request_module(ctx->net, "%s", modname) == -EAGAIN) return -EAGAIN; } return ret; } /* The standard target cannot be used */ if (!target->target) return -EINVAL; return 0; } static void __nft_mt_tg_destroy(struct module *me, const struct nft_expr *expr) { module_put(me); kfree(expr->ops); } static void nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct xt_target *target = expr->ops->data; void *info = nft_expr_priv(expr); struct module *me = target->me; struct xt_tgdtor_param par; par.net = ctx->net; par.target = target; par.targinfo = info; par.family = ctx->family; if (par.target->destroy != NULL) par.target->destroy(&par); __nft_mt_tg_destroy(me, expr); } static int nft_extension_dump_info(struct sk_buff *skb, int attr, const void *info, unsigned int size, unsigned int user_size) { unsigned int info_size, aligned_size = XT_ALIGN(size); struct nlattr *nla; nla = nla_reserve(skb, attr, aligned_size); if (!nla) return -1; info_size = user_size ? : size; memcpy(nla_data(nla), info, info_size); memset(nla_data(nla) + info_size, 0, aligned_size - info_size); return 0; } static int nft_target_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct xt_target *target = expr->ops->data; void *info = nft_expr_priv(expr); if (nla_put_string(skb, NFTA_TARGET_NAME, target->name) || nla_put_be32(skb, NFTA_TARGET_REV, htonl(target->revision)) || nft_extension_dump_info(skb, NFTA_TARGET_INFO, info, target->targetsize, target->usersize)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int nft_target_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct xt_target *target = expr->ops->data; unsigned int hook_mask = 0; int ret; if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && ctx->family != NFPROTO_INET && ctx->family != NFPROTO_BRIDGE && ctx->family != NFPROTO_ARP) return -EOPNOTSUPP; ret = nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_POST_ROUTING)); if (ret) return ret; if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); const struct nf_hook_ops *ops = &basechain->ops; hook_mask = 1 << ops->hooknum; if (target->hooks && !(hook_mask & target->hooks)) return -EINVAL; ret = nft_compat_chain_validate_dependency(ctx, target->table); if (ret < 0) return ret; } return 0; } static void __nft_match_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt, void *info) { struct xt_match *match = expr->ops->data; struct sk_buff *skb = pkt->skb; struct xt_action_param xt; bool ret; nft_compat_set_par(&xt, pkt, match, info); ret = match->match(skb, &xt); if (xt.hotdrop) { regs->verdict.code = NF_DROP; return; } switch (ret ? 1 : 0) { case 1: regs->verdict.code = NFT_CONTINUE; break; case 0: regs->verdict.code = NFT_BREAK; break; } } static void nft_match_large_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_xt_match_priv *priv = nft_expr_priv(expr); __nft_match_eval(expr, regs, pkt, priv->info); } static void nft_match_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { __nft_match_eval(expr, regs, pkt, nft_expr_priv(expr)); } static const struct nla_policy nft_match_policy[NFTA_MATCH_MAX + 1] = { [NFTA_MATCH_NAME] = { .type = NLA_NUL_STRING }, [NFTA_MATCH_REV] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_MATCH_INFO] = { .type = NLA_BINARY }, }; /* struct xt_mtchk_param and xt_tgchk_param look very similar */ static void nft_match_set_mtchk_param(struct xt_mtchk_param *par, const struct nft_ctx *ctx, struct xt_match *match, void *info, union nft_entry *entry, u16 proto, bool inv) { par->net = ctx->net; par->table = ctx->table->name; switch (ctx->family) { case AF_INET: entry->e4.ip.proto = proto; entry->e4.ip.invflags = inv ? IPT_INV_PROTO : 0; break; case AF_INET6: if (proto) entry->e6.ipv6.flags |= IP6T_F_PROTO; entry->e6.ipv6.proto = proto; entry->e6.ipv6.invflags = inv ? IP6T_INV_PROTO : 0; break; case NFPROTO_BRIDGE: entry->ebt.ethproto = (__force __be16)proto; entry->ebt.invflags = inv ? EBT_IPROTO : 0; break; case NFPROTO_ARP: break; } par->entryinfo = entry; par->match = match; par->matchinfo = info; if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); const struct nf_hook_ops *ops = &basechain->ops; par->hook_mask = 1 << ops->hooknum; } else { par->hook_mask = 0; } par->family = ctx->family; par->nft_compat = true; } static void match_compat_from_user(struct xt_match *m, void *in, void *out) { int pad; memcpy(out, in, m->matchsize); pad = XT_ALIGN(m->matchsize) - m->matchsize; if (pad > 0) memset(out + m->matchsize, 0, pad); } static int __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[], void *info) { struct xt_match *match = expr->ops->data; struct xt_mtchk_param par; size_t size = XT_ALIGN(nla_len(tb[NFTA_MATCH_INFO])); u16 proto = 0; bool inv = false; union nft_entry e = {}; int ret; match_compat_from_user(match, nla_data(tb[NFTA_MATCH_INFO]), info); if (ctx->nla[NFTA_RULE_COMPAT]) { ret = nft_parse_compat(ctx->nla[NFTA_RULE_COMPAT], &proto, &inv); if (ret < 0) return ret; } nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv); nft_compat_wait_for_destructors(); return xt_check_match(&par, size, proto, inv); } static int nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { return __nft_match_init(ctx, expr, tb, nft_expr_priv(expr)); } static int nft_match_large_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_xt_match_priv *priv = nft_expr_priv(expr); struct xt_match *m = expr->ops->data; int ret; priv->info = kmalloc(XT_ALIGN(m->matchsize), GFP_KERNEL_ACCOUNT); if (!priv->info) return -ENOMEM; ret = __nft_match_init(ctx, expr, tb, priv->info); if (ret) kfree(priv->info); return ret; } static void __nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr, void *info) { struct xt_match *match = expr->ops->data; struct module *me = match->me; struct xt_mtdtor_param par; par.net = ctx->net; par.match = match; par.matchinfo = info; par.family = ctx->family; if (par.match->destroy != NULL) par.match->destroy(&par); __nft_mt_tg_destroy(me, expr); } static void nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { __nft_match_destroy(ctx, expr, nft_expr_priv(expr)); } static void nft_match_large_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct nft_xt_match_priv *priv = nft_expr_priv(expr); __nft_match_destroy(ctx, expr, priv->info); kfree(priv->info); } static int __nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr, void *info) { struct xt_match *match = expr->ops->data; if (nla_put_string(skb, NFTA_MATCH_NAME, match->name) || nla_put_be32(skb, NFTA_MATCH_REV, htonl(match->revision)) || nft_extension_dump_info(skb, NFTA_MATCH_INFO, info, match->matchsize, match->usersize)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static int nft_match_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { return __nft_match_dump(skb, expr, nft_expr_priv(expr)); } static int nft_match_large_dump(struct sk_buff *skb, const struct nft_expr *e, bool reset) { struct nft_xt_match_priv *priv = nft_expr_priv(e); return __nft_match_dump(skb, e, priv->info); } static int nft_match_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct xt_match *match = expr->ops->data; unsigned int hook_mask = 0; int ret; if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && ctx->family != NFPROTO_INET && ctx->family != NFPROTO_BRIDGE && ctx->family != NFPROTO_ARP) return -EOPNOTSUPP; ret = nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD) | (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_POST_ROUTING)); if (ret) return ret; if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); const struct nf_hook_ops *ops = &basechain->ops; hook_mask = 1 << ops->hooknum; if (match->hooks && !(hook_mask & match->hooks)) return -EINVAL; ret = nft_compat_chain_validate_dependency(ctx, match->table); if (ret < 0) return ret; } return 0; } static int nfnl_compat_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, u16 family, const char *name, int rev, int target) { struct nlmsghdr *nlh; unsigned int flags = portid ? NLM_F_MULTI : 0; event = nfnl_msg_type(NFNL_SUBSYS_NFT_COMPAT, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, family, NFNETLINK_V0, 0); if (!nlh) goto nlmsg_failure; if (nla_put_string(skb, NFTA_COMPAT_NAME, name) || nla_put_be32(skb, NFTA_COMPAT_REV, htonl(rev)) || nla_put_be32(skb, NFTA_COMPAT_TYPE, htonl(target))) goto nla_put_failure; nlmsg_end(skb, nlh); return skb->len; nlmsg_failure: nla_put_failure: nlmsg_cancel(skb, nlh); return -1; } static int nfnl_compat_get_rcu(struct sk_buff *skb, const struct nfnl_info *info, const struct nlattr * const tb[]) { u8 family = info->nfmsg->nfgen_family; const char *name, *fmt; struct sk_buff *skb2; int ret = 0, target; u32 rev; if (tb[NFTA_COMPAT_NAME] == NULL || tb[NFTA_COMPAT_REV] == NULL || tb[NFTA_COMPAT_TYPE] == NULL) return -EINVAL; name = nla_data(tb[NFTA_COMPAT_NAME]); rev = ntohl(nla_get_be32(tb[NFTA_COMPAT_REV])); target = ntohl(nla_get_be32(tb[NFTA_COMPAT_TYPE])); switch(family) { case AF_INET: fmt = "ipt_%s"; break; case AF_INET6: fmt = "ip6t_%s"; break; case NFPROTO_BRIDGE: fmt = "ebt_%s"; break; case NFPROTO_ARP: fmt = "arpt_%s"; break; default: pr_err("nft_compat: unsupported protocol %d\n", family); return -EINVAL; } if (!try_module_get(THIS_MODULE)) return -EINVAL; rcu_read_unlock(); try_then_request_module(xt_find_revision(family, name, rev, target, &ret), fmt, name); if (ret < 0) goto out_put; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) { ret = -ENOMEM; goto out_put; } /* include the best revision for this extension in the message */ if (nfnl_compat_fill_info(skb2, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFNL_MSG_TYPE(info->nlh->nlmsg_type), NFNL_MSG_COMPAT_GET, family, name, ret, target) <= 0) { kfree_skb(skb2); goto out_put; } ret = nfnetlink_unicast(skb2, info->net, NETLINK_CB(skb).portid); out_put: rcu_read_lock(); module_put(THIS_MODULE); return ret; } static const struct nla_policy nfnl_compat_policy_get[NFTA_COMPAT_MAX+1] = { [NFTA_COMPAT_NAME] = { .type = NLA_NUL_STRING, .len = NFT_COMPAT_NAME_MAX-1 }, [NFTA_COMPAT_REV] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_COMPAT_TYPE] = { .type = NLA_U32 }, }; static const struct nfnl_callback nfnl_nft_compat_cb[NFNL_MSG_COMPAT_MAX] = { [NFNL_MSG_COMPAT_GET] = { .call = nfnl_compat_get_rcu, .type = NFNL_CB_RCU, .attr_count = NFTA_COMPAT_MAX, .policy = nfnl_compat_policy_get }, }; static const struct nfnetlink_subsystem nfnl_compat_subsys = { .name = "nft-compat", .subsys_id = NFNL_SUBSYS_NFT_COMPAT, .cb_count = NFNL_MSG_COMPAT_MAX, .cb = nfnl_nft_compat_cb, }; static struct nft_expr_type nft_match_type; static bool nft_match_reduce(struct nft_regs_track *track, const struct nft_expr *expr) { const struct xt_match *match = expr->ops->data; return strcmp(match->name, "comment") == 0; } static const struct nft_expr_ops * nft_match_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_expr_ops *ops; struct xt_match *match; unsigned int matchsize; char *mt_name; u32 rev, family; int err; if (tb[NFTA_MATCH_NAME] == NULL || tb[NFTA_MATCH_REV] == NULL || tb[NFTA_MATCH_INFO] == NULL) return ERR_PTR(-EINVAL); mt_name = nla_data(tb[NFTA_MATCH_NAME]); rev = ntohl(nla_get_be32(tb[NFTA_MATCH_REV])); family = ctx->family; match = xt_request_find_match(family, mt_name, rev); if (IS_ERR(match)) return ERR_PTR(-ENOENT); if (match->matchsize > nla_len(tb[NFTA_MATCH_INFO])) { err = -EINVAL; goto err; } ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL_ACCOUNT); if (!ops) { err = -ENOMEM; goto err; } ops->type = &nft_match_type; ops->eval = nft_match_eval; ops->init = nft_match_init; ops->destroy = nft_match_destroy; ops->dump = nft_match_dump; ops->validate = nft_match_validate; ops->data = match; ops->reduce = nft_match_reduce; matchsize = NFT_EXPR_SIZE(XT_ALIGN(match->matchsize)); if (matchsize > NFT_MATCH_LARGE_THRESH) { matchsize = NFT_EXPR_SIZE(sizeof(struct nft_xt_match_priv)); ops->eval = nft_match_large_eval; ops->init = nft_match_large_init; ops->destroy = nft_match_large_destroy; ops->dump = nft_match_large_dump; } ops->size = matchsize; return ops; err: module_put(match->me); return ERR_PTR(err); } static void nft_match_release_ops(const struct nft_expr_ops *ops) { struct xt_match *match = ops->data; module_put(match->me); kfree(ops); } static struct nft_expr_type nft_match_type __read_mostly = { .name = "match", .select_ops = nft_match_select_ops, .release_ops = nft_match_release_ops, .policy = nft_match_policy, .maxattr = NFTA_MATCH_MAX, .owner = THIS_MODULE, }; static struct nft_expr_type nft_target_type; static const struct nft_expr_ops * nft_target_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_expr_ops *ops; struct xt_target *target; char *tg_name; u32 rev, family; int err; if (tb[NFTA_TARGET_NAME] == NULL || tb[NFTA_TARGET_REV] == NULL || tb[NFTA_TARGET_INFO] == NULL) return ERR_PTR(-EINVAL); tg_name = nla_data(tb[NFTA_TARGET_NAME]); rev = ntohl(nla_get_be32(tb[NFTA_TARGET_REV])); family = ctx->family; if (strcmp(tg_name, XT_ERROR_TARGET) == 0 || strcmp(tg_name, XT_STANDARD_TARGET) == 0 || strcmp(tg_name, "standard") == 0) return ERR_PTR(-EINVAL); target = xt_request_find_target(family, tg_name, rev); if (IS_ERR(target)) return ERR_PTR(-ENOENT); if (!target->target) { err = -EINVAL; goto err; } if (target->targetsize > nla_len(tb[NFTA_TARGET_INFO])) { err = -EINVAL; goto err; } ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL_ACCOUNT); if (!ops) { err = -ENOMEM; goto err; } ops->type = &nft_target_type; ops->size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); ops->init = nft_target_init; ops->destroy = nft_target_destroy; ops->dump = nft_target_dump; ops->validate = nft_target_validate; ops->data = target; ops->reduce = NFT_REDUCE_READONLY; if (family == NFPROTO_BRIDGE) ops->eval = nft_target_eval_bridge; else ops->eval = nft_target_eval_xt; return ops; err: module_put(target->me); return ERR_PTR(err); } static void nft_target_release_ops(const struct nft_expr_ops *ops) { struct xt_target *target = ops->data; module_put(target->me); kfree(ops); } static struct nft_expr_type nft_target_type __read_mostly = { .name = "target", .select_ops = nft_target_select_ops, .release_ops = nft_target_release_ops, .policy = nft_target_policy, .maxattr = NFTA_TARGET_MAX, .owner = THIS_MODULE, }; static int __init nft_compat_module_init(void) { int ret; ret = nft_register_expr(&nft_match_type); if (ret < 0) return ret; ret = nft_register_expr(&nft_target_type); if (ret < 0) goto err_match; ret = nfnetlink_subsys_register(&nfnl_compat_subsys); if (ret < 0) { pr_err("nft_compat: cannot register with nfnetlink.\n"); goto err_target; } return ret; err_target: nft_unregister_expr(&nft_target_type); err_match: nft_unregister_expr(&nft_match_type); return ret; } static void __exit nft_compat_module_exit(void) { nfnetlink_subsys_unregister(&nfnl_compat_subsys); nft_unregister_expr(&nft_target_type); nft_unregister_expr(&nft_match_type); } MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT); module_init(nft_compat_module_init); module_exit(nft_compat_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_EXPR("match"); MODULE_ALIAS_NFT_EXPR("target"); MODULE_DESCRIPTION("x_tables over nftables support"); |
| 7 5 4 5 5 54 2 2 2 2 52 5 5 5 5 4 5 5 5 6 6 6 6 5 5 5 5 5 5 5 5 5 5 5 5 5 4 5 5 5 4 5 5 5 2 2 5 5 5 5 5 4 5 5 5 4 5 5 5 5 5 5 5 5 5 5 5 5 5 5 4 5 5 5 5 5 5 5 5 4 5 5 5 5 4 5 5 5 5 5 5 4 4 5 5 5 4 5 5 5 5 5 5 5 4 5 5 5 5 5 5 5 5 4 5 5 5 5 6 6 6 6 6 6 6 6 1 6 4 5 5 5 4 5 5 4 5 5 5 3 5 5 5 5 4 5 5 5 5 5 5 5 5 5 4 5 5 5 5 5 5 5 5 5 3 46 22 22 22 22 22 22 22 22 22 22 22 22 20 22 22 22 22 22 19 3 53 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2010-2013 Felix Fietkau <nbd@openwrt.org> * Copyright (C) 2019-2022 Intel Corporation */ #include <linux/netdevice.h> #include <linux/types.h> #include <linux/skbuff.h> #include <linux/debugfs.h> #include <linux/random.h> #include <linux/moduleparam.h> #include <linux/ieee80211.h> #include <linux/minmax.h> #include <net/mac80211.h> #include "rate.h" #include "sta_info.h" #include "rc80211_minstrel_ht.h" #define AVG_AMPDU_SIZE 16 #define AVG_PKT_SIZE 1200 /* Number of bits for an average sized packet */ #define MCS_NBITS ((AVG_PKT_SIZE * AVG_AMPDU_SIZE) << 3) /* Number of symbols for a packet with (bps) bits per symbol */ #define MCS_NSYMS(bps) DIV_ROUND_UP(MCS_NBITS, (bps)) /* Transmission time (nanoseconds) for a packet containing (syms) symbols */ #define MCS_SYMBOL_TIME(sgi, syms) \ (sgi ? \ ((syms) * 18000 + 4000) / 5 : /* syms * 3.6 us */ \ ((syms) * 1000) << 2 /* syms * 4 us */ \ ) /* Transmit duration for the raw data part of an average sized packet */ #define MCS_DURATION(streams, sgi, bps) \ (MCS_SYMBOL_TIME(sgi, MCS_NSYMS((streams) * (bps))) / AVG_AMPDU_SIZE) #define BW_20 0 #define BW_40 1 #define BW_80 2 /* * Define group sort order: HT40 -> SGI -> #streams */ #define GROUP_IDX(_streams, _sgi, _ht40) \ MINSTREL_HT_GROUP_0 + \ MINSTREL_MAX_STREAMS * 2 * _ht40 + \ MINSTREL_MAX_STREAMS * _sgi + \ _streams - 1 #define _MAX(a, b) (((a)>(b))?(a):(b)) #define GROUP_SHIFT(duration) \ _MAX(0, 16 - __builtin_clz(duration)) /* MCS rate information for an MCS group */ #define __MCS_GROUP(_streams, _sgi, _ht40, _s) \ [GROUP_IDX(_streams, _sgi, _ht40)] = { \ .streams = _streams, \ .shift = _s, \ .bw = _ht40, \ .flags = \ IEEE80211_TX_RC_MCS | \ (_sgi ? IEEE80211_TX_RC_SHORT_GI : 0) | \ (_ht40 ? IEEE80211_TX_RC_40_MHZ_WIDTH : 0), \ .duration = { \ MCS_DURATION(_streams, _sgi, _ht40 ? 54 : 26) >> _s, \ MCS_DURATION(_streams, _sgi, _ht40 ? 108 : 52) >> _s, \ MCS_DURATION(_streams, _sgi, _ht40 ? 162 : 78) >> _s, \ MCS_DURATION(_streams, _sgi, _ht40 ? 216 : 104) >> _s, \ MCS_DURATION(_streams, _sgi, _ht40 ? 324 : 156) >> _s, \ MCS_DURATION(_streams, _sgi, _ht40 ? 432 : 208) >> _s, \ MCS_DURATION(_streams, _sgi, _ht40 ? 486 : 234) >> _s, \ MCS_DURATION(_streams, _sgi, _ht40 ? 540 : 260) >> _s \ } \ } #define MCS_GROUP_SHIFT(_streams, _sgi, _ht40) \ GROUP_SHIFT(MCS_DURATION(_streams, _sgi, _ht40 ? 54 : 26)) #define MCS_GROUP(_streams, _sgi, _ht40) \ __MCS_GROUP(_streams, _sgi, _ht40, \ MCS_GROUP_SHIFT(_streams, _sgi, _ht40)) #define VHT_GROUP_IDX(_streams, _sgi, _bw) \ (MINSTREL_VHT_GROUP_0 + \ MINSTREL_MAX_STREAMS * 2 * (_bw) + \ MINSTREL_MAX_STREAMS * (_sgi) + \ (_streams) - 1) #define BW2VBPS(_bw, r3, r2, r1) \ (_bw == BW_80 ? r3 : _bw == BW_40 ? r2 : r1) #define __VHT_GROUP(_streams, _sgi, _bw, _s) \ [VHT_GROUP_IDX(_streams, _sgi, _bw)] = { \ .streams = _streams, \ .shift = _s, \ .bw = _bw, \ .flags = \ IEEE80211_TX_RC_VHT_MCS | \ (_sgi ? IEEE80211_TX_RC_SHORT_GI : 0) | \ (_bw == BW_80 ? IEEE80211_TX_RC_80_MHZ_WIDTH : \ _bw == BW_40 ? IEEE80211_TX_RC_40_MHZ_WIDTH : 0), \ .duration = { \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 117, 54, 26)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 234, 108, 52)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 351, 162, 78)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 468, 216, 104)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 702, 324, 156)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 936, 432, 208)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 1053, 486, 234)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 1170, 540, 260)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 1404, 648, 312)) >> _s, \ MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 1560, 720, 346)) >> _s \ } \ } #define VHT_GROUP_SHIFT(_streams, _sgi, _bw) \ GROUP_SHIFT(MCS_DURATION(_streams, _sgi, \ BW2VBPS(_bw, 117, 54, 26))) #define VHT_GROUP(_streams, _sgi, _bw) \ __VHT_GROUP(_streams, _sgi, _bw, \ VHT_GROUP_SHIFT(_streams, _sgi, _bw)) #define CCK_DURATION(_bitrate, _short) \ (1000 * (10 /* SIFS */ + \ (_short ? 72 + 24 : 144 + 48) + \ (8 * (AVG_PKT_SIZE + 4) * 10) / (_bitrate))) #define CCK_DURATION_LIST(_short, _s) \ CCK_DURATION(10, _short) >> _s, \ CCK_DURATION(20, _short) >> _s, \ CCK_DURATION(55, _short) >> _s, \ CCK_DURATION(110, _short) >> _s #define __CCK_GROUP(_s) \ [MINSTREL_CCK_GROUP] = { \ .streams = 1, \ .flags = 0, \ .shift = _s, \ .duration = { \ CCK_DURATION_LIST(false, _s), \ CCK_DURATION_LIST(true, _s) \ } \ } #define CCK_GROUP_SHIFT \ GROUP_SHIFT(CCK_DURATION(10, false)) #define CCK_GROUP __CCK_GROUP(CCK_GROUP_SHIFT) #define OFDM_DURATION(_bitrate) \ (1000 * (16 /* SIFS + signal ext */ + \ 16 /* T_PREAMBLE */ + \ 4 /* T_SIGNAL */ + \ 4 * (((16 + 80 * (AVG_PKT_SIZE + 4) + 6) / \ ((_bitrate) * 4))))) #define OFDM_DURATION_LIST(_s) \ OFDM_DURATION(60) >> _s, \ OFDM_DURATION(90) >> _s, \ OFDM_DURATION(120) >> _s, \ OFDM_DURATION(180) >> _s, \ OFDM_DURATION(240) >> _s, \ OFDM_DURATION(360) >> _s, \ OFDM_DURATION(480) >> _s, \ OFDM_DURATION(540) >> _s #define __OFDM_GROUP(_s) \ [MINSTREL_OFDM_GROUP] = { \ .streams = 1, \ .flags = 0, \ .shift = _s, \ .duration = { \ OFDM_DURATION_LIST(_s), \ } \ } #define OFDM_GROUP_SHIFT \ GROUP_SHIFT(OFDM_DURATION(60)) #define OFDM_GROUP __OFDM_GROUP(OFDM_GROUP_SHIFT) static bool minstrel_vht_only = true; module_param(minstrel_vht_only, bool, 0644); MODULE_PARM_DESC(minstrel_vht_only, "Use only VHT rates when VHT is supported by sta."); /* * To enable sufficiently targeted rate sampling, MCS rates are divided into * groups, based on the number of streams and flags (HT40, SGI) that they * use. * * Sortorder has to be fixed for GROUP_IDX macro to be applicable: * BW -> SGI -> #streams */ const struct mcs_group minstrel_mcs_groups[] = { MCS_GROUP(1, 0, BW_20), MCS_GROUP(2, 0, BW_20), MCS_GROUP(3, 0, BW_20), MCS_GROUP(4, 0, BW_20), MCS_GROUP(1, 1, BW_20), MCS_GROUP(2, 1, BW_20), MCS_GROUP(3, 1, BW_20), MCS_GROUP(4, 1, BW_20), MCS_GROUP(1, 0, BW_40), MCS_GROUP(2, 0, BW_40), MCS_GROUP(3, 0, BW_40), MCS_GROUP(4, 0, BW_40), MCS_GROUP(1, 1, BW_40), MCS_GROUP(2, 1, BW_40), MCS_GROUP(3, 1, BW_40), MCS_GROUP(4, 1, BW_40), CCK_GROUP, OFDM_GROUP, VHT_GROUP(1, 0, BW_20), VHT_GROUP(2, 0, BW_20), VHT_GROUP(3, 0, BW_20), VHT_GROUP(4, 0, BW_20), VHT_GROUP(1, 1, BW_20), VHT_GROUP(2, 1, BW_20), VHT_GROUP(3, 1, BW_20), VHT_GROUP(4, 1, BW_20), VHT_GROUP(1, 0, BW_40), VHT_GROUP(2, 0, BW_40), VHT_GROUP(3, 0, BW_40), VHT_GROUP(4, 0, BW_40), VHT_GROUP(1, 1, BW_40), VHT_GROUP(2, 1, BW_40), VHT_GROUP(3, 1, BW_40), VHT_GROUP(4, 1, BW_40), VHT_GROUP(1, 0, BW_80), VHT_GROUP(2, 0, BW_80), VHT_GROUP(3, 0, BW_80), VHT_GROUP(4, 0, BW_80), VHT_GROUP(1, 1, BW_80), VHT_GROUP(2, 1, BW_80), VHT_GROUP(3, 1, BW_80), VHT_GROUP(4, 1, BW_80), }; const s16 minstrel_cck_bitrates[4] = { 10, 20, 55, 110 }; const s16 minstrel_ofdm_bitrates[8] = { 60, 90, 120, 180, 240, 360, 480, 540 }; static u8 sample_table[SAMPLE_COLUMNS][MCS_GROUP_RATES] __read_mostly; static const u8 minstrel_sample_seq[] = { MINSTREL_SAMPLE_TYPE_INC, MINSTREL_SAMPLE_TYPE_JUMP, MINSTREL_SAMPLE_TYPE_INC, MINSTREL_SAMPLE_TYPE_JUMP, MINSTREL_SAMPLE_TYPE_INC, MINSTREL_SAMPLE_TYPE_SLOW, }; static void minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi); /* * Some VHT MCSes are invalid (when Ndbps / Nes is not an integer) * e.g for MCS9@20MHzx1Nss: Ndbps=8x52*(5/6) Nes=1 * * Returns the valid mcs map for struct minstrel_mcs_group_data.supported */ static u16 minstrel_get_valid_vht_rates(int bw, int nss, __le16 mcs_map) { u16 mask = 0; if (bw == BW_20) { if (nss != 3 && nss != 6) mask = BIT(9); } else if (bw == BW_80) { if (nss == 3 || nss == 7) mask = BIT(6); else if (nss == 6) mask = BIT(9); } else { WARN_ON(bw != BW_40); } switch ((le16_to_cpu(mcs_map) >> (2 * (nss - 1))) & 3) { case IEEE80211_VHT_MCS_SUPPORT_0_7: mask |= 0x300; break; case IEEE80211_VHT_MCS_SUPPORT_0_8: mask |= 0x200; break; case IEEE80211_VHT_MCS_SUPPORT_0_9: break; default: mask = 0x3ff; } return 0x3ff & ~mask; } static bool minstrel_ht_is_legacy_group(int group) { return group == MINSTREL_CCK_GROUP || group == MINSTREL_OFDM_GROUP; } /* * Look up an MCS group index based on mac80211 rate information */ static int minstrel_ht_get_group_idx(struct ieee80211_tx_rate *rate) { return GROUP_IDX((rate->idx / 8) + 1, !!(rate->flags & IEEE80211_TX_RC_SHORT_GI), !!(rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)); } /* * Look up an MCS group index based on new cfg80211 rate_info. */ static int minstrel_ht_ri_get_group_idx(struct rate_info *rate) { return GROUP_IDX((rate->mcs / 8) + 1, !!(rate->flags & RATE_INFO_FLAGS_SHORT_GI), !!(rate->bw & RATE_INFO_BW_40)); } static int minstrel_vht_get_group_idx(struct ieee80211_tx_rate *rate) { return VHT_GROUP_IDX(ieee80211_rate_get_vht_nss(rate), !!(rate->flags & IEEE80211_TX_RC_SHORT_GI), !!(rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH) + 2*!!(rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)); } /* * Look up an MCS group index based on new cfg80211 rate_info. */ static int minstrel_vht_ri_get_group_idx(struct rate_info *rate) { return VHT_GROUP_IDX(rate->nss, !!(rate->flags & RATE_INFO_FLAGS_SHORT_GI), !!(rate->bw & RATE_INFO_BW_40) + 2*!!(rate->bw & RATE_INFO_BW_80)); } static struct minstrel_rate_stats * minstrel_ht_get_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, struct ieee80211_tx_rate *rate) { int group, idx; if (rate->flags & IEEE80211_TX_RC_MCS) { group = minstrel_ht_get_group_idx(rate); idx = rate->idx % 8; goto out; } if (rate->flags & IEEE80211_TX_RC_VHT_MCS) { group = minstrel_vht_get_group_idx(rate); idx = ieee80211_rate_get_vht_mcs(rate); goto out; } group = MINSTREL_CCK_GROUP; for (idx = 0; idx < ARRAY_SIZE(mp->cck_rates); idx++) { if (!(mi->supported[group] & BIT(idx))) continue; if (rate->idx != mp->cck_rates[idx]) continue; /* short preamble */ if ((mi->supported[group] & BIT(idx + 4)) && (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE)) idx += 4; goto out; } group = MINSTREL_OFDM_GROUP; for (idx = 0; idx < ARRAY_SIZE(mp->ofdm_rates[0]); idx++) if (rate->idx == mp->ofdm_rates[mi->band][idx]) goto out; idx = 0; out: return &mi->groups[group].rates[idx]; } /* * Get the minstrel rate statistics for specified STA and rate info. */ static struct minstrel_rate_stats * minstrel_ht_ri_get_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, struct ieee80211_rate_status *rate_status) { int group, idx; struct rate_info *rate = &rate_status->rate_idx; if (rate->flags & RATE_INFO_FLAGS_MCS) { group = minstrel_ht_ri_get_group_idx(rate); idx = rate->mcs % 8; goto out; } if (rate->flags & RATE_INFO_FLAGS_VHT_MCS) { group = minstrel_vht_ri_get_group_idx(rate); idx = rate->mcs; goto out; } group = MINSTREL_CCK_GROUP; for (idx = 0; idx < ARRAY_SIZE(mp->cck_rates); idx++) { if (rate->legacy != minstrel_cck_bitrates[ mp->cck_rates[idx] ]) continue; /* short preamble */ if ((mi->supported[group] & BIT(idx + 4)) && mi->use_short_preamble) idx += 4; goto out; } group = MINSTREL_OFDM_GROUP; for (idx = 0; idx < ARRAY_SIZE(mp->ofdm_rates[0]); idx++) if (rate->legacy == minstrel_ofdm_bitrates[ mp->ofdm_rates[mi->band][idx] ]) goto out; idx = 0; out: return &mi->groups[group].rates[idx]; } static inline struct minstrel_rate_stats * minstrel_get_ratestats(struct minstrel_ht_sta *mi, int index) { return &mi->groups[MI_RATE_GROUP(index)].rates[MI_RATE_IDX(index)]; } static inline int minstrel_get_duration(int index) { const struct mcs_group *group = &minstrel_mcs_groups[MI_RATE_GROUP(index)]; unsigned int duration = group->duration[MI_RATE_IDX(index)]; return duration << group->shift; } static unsigned int minstrel_ht_avg_ampdu_len(struct minstrel_ht_sta *mi) { int duration; if (mi->avg_ampdu_len) return MINSTREL_TRUNC(mi->avg_ampdu_len); if (minstrel_ht_is_legacy_group(MI_RATE_GROUP(mi->max_tp_rate[0]))) return 1; duration = minstrel_get_duration(mi->max_tp_rate[0]); if (duration > 400 * 1000) return 2; if (duration > 250 * 1000) return 4; if (duration > 150 * 1000) return 8; return 16; } /* * Return current throughput based on the average A-MPDU length, taking into * account the expected number of retransmissions and their expected length */ int minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate, int prob_avg) { unsigned int nsecs = 0, overhead = mi->overhead; unsigned int ampdu_len = 1; /* do not account throughput if success prob is below 10% */ if (prob_avg < MINSTREL_FRAC(10, 100)) return 0; if (minstrel_ht_is_legacy_group(group)) overhead = mi->overhead_legacy; else ampdu_len = minstrel_ht_avg_ampdu_len(mi); nsecs = 1000 * overhead / ampdu_len; nsecs += minstrel_mcs_groups[group].duration[rate] << minstrel_mcs_groups[group].shift; /* * For the throughput calculation, limit the probability value to 90% to * account for collision related packet error rate fluctuation * (prob is scaled - see MINSTREL_FRAC above) */ if (prob_avg > MINSTREL_FRAC(90, 100)) prob_avg = MINSTREL_FRAC(90, 100); return MINSTREL_TRUNC(100 * ((prob_avg * 1000000) / nsecs)); } /* * Find & sort topmost throughput rates * * If multiple rates provide equal throughput the sorting is based on their * current success probability. Higher success probability is preferred among * MCS groups, CCK rates do not provide aggregation and are therefore at last. */ static void minstrel_ht_sort_best_tp_rates(struct minstrel_ht_sta *mi, u16 index, u16 *tp_list) { int cur_group, cur_idx, cur_tp_avg, cur_prob; int tmp_group, tmp_idx, tmp_tp_avg, tmp_prob; int j = MAX_THR_RATES; cur_group = MI_RATE_GROUP(index); cur_idx = MI_RATE_IDX(index); cur_prob = mi->groups[cur_group].rates[cur_idx].prob_avg; cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx, cur_prob); do { tmp_group = MI_RATE_GROUP(tp_list[j - 1]); tmp_idx = MI_RATE_IDX(tp_list[j - 1]); tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_avg; tmp_tp_avg = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob); if (cur_tp_avg < tmp_tp_avg || (cur_tp_avg == tmp_tp_avg && cur_prob <= tmp_prob)) break; j--; } while (j > 0); if (j < MAX_THR_RATES - 1) { memmove(&tp_list[j + 1], &tp_list[j], (sizeof(*tp_list) * (MAX_THR_RATES - (j + 1)))); } if (j < MAX_THR_RATES) tp_list[j] = index; } /* * Find and set the topmost probability rate per sta and per group */ static void minstrel_ht_set_best_prob_rate(struct minstrel_ht_sta *mi, u16 *dest, u16 index) { struct minstrel_mcs_group_data *mg; struct minstrel_rate_stats *mrs; int tmp_group, tmp_idx, tmp_tp_avg, tmp_prob; int max_tp_group, max_tp_idx, max_tp_prob; int cur_tp_avg, cur_group, cur_idx; int max_gpr_group, max_gpr_idx; int max_gpr_tp_avg, max_gpr_prob; cur_group = MI_RATE_GROUP(index); cur_idx = MI_RATE_IDX(index); mg = &mi->groups[cur_group]; mrs = &mg->rates[cur_idx]; tmp_group = MI_RATE_GROUP(*dest); tmp_idx = MI_RATE_IDX(*dest); tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_avg; tmp_tp_avg = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob); /* if max_tp_rate[0] is from MCS_GROUP max_prob_rate get selected from * MCS_GROUP as well as CCK_GROUP rates do not allow aggregation */ max_tp_group = MI_RATE_GROUP(mi->max_tp_rate[0]); max_tp_idx = MI_RATE_IDX(mi->max_tp_rate[0]); max_tp_prob = mi->groups[max_tp_group].rates[max_tp_idx].prob_avg; if (minstrel_ht_is_legacy_group(MI_RATE_GROUP(index)) && !minstrel_ht_is_legacy_group(max_tp_group)) return; /* skip rates faster than max tp rate with lower prob */ if (minstrel_get_duration(mi->max_tp_rate[0]) > minstrel_get_duration(index) && mrs->prob_avg < max_tp_prob) return; max_gpr_group = MI_RATE_GROUP(mg->max_group_prob_rate); max_gpr_idx = MI_RATE_IDX(mg->max_group_prob_rate); max_gpr_prob = mi->groups[max_gpr_group].rates[max_gpr_idx].prob_avg; if (mrs->prob_avg > MINSTREL_FRAC(75, 100)) { cur_tp_avg = minstrel_ht_get_tp_avg(mi, cur_group, cur_idx, mrs->prob_avg); if (cur_tp_avg > tmp_tp_avg) *dest = index; max_gpr_tp_avg = minstrel_ht_get_tp_avg(mi, max_gpr_group, max_gpr_idx, max_gpr_prob); if (cur_tp_avg > max_gpr_tp_avg) mg->max_group_prob_rate = index; } else { if (mrs->prob_avg > tmp_prob) *dest = index; if (mrs->prob_avg > max_gpr_prob) mg->max_group_prob_rate = index; } } /* * Assign new rate set per sta and use CCK rates only if the fastest * rate (max_tp_rate[0]) is from CCK group. This prohibits such sorted * rate sets where MCS and CCK rates are mixed, because CCK rates can * not use aggregation. */ static void minstrel_ht_assign_best_tp_rates(struct minstrel_ht_sta *mi, u16 tmp_mcs_tp_rate[MAX_THR_RATES], u16 tmp_legacy_tp_rate[MAX_THR_RATES]) { unsigned int tmp_group, tmp_idx, tmp_cck_tp, tmp_mcs_tp, tmp_prob; int i; tmp_group = MI_RATE_GROUP(tmp_legacy_tp_rate[0]); tmp_idx = MI_RATE_IDX(tmp_legacy_tp_rate[0]); tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_avg; tmp_cck_tp = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob); tmp_group = MI_RATE_GROUP(tmp_mcs_tp_rate[0]); tmp_idx = MI_RATE_IDX(tmp_mcs_tp_rate[0]); tmp_prob = mi->groups[tmp_group].rates[tmp_idx].prob_avg; tmp_mcs_tp = minstrel_ht_get_tp_avg(mi, tmp_group, tmp_idx, tmp_prob); if (tmp_cck_tp > tmp_mcs_tp) { for(i = 0; i < MAX_THR_RATES; i++) { minstrel_ht_sort_best_tp_rates(mi, tmp_legacy_tp_rate[i], tmp_mcs_tp_rate); } } } /* * Try to increase robustness of max_prob rate by decrease number of * streams if possible. */ static inline void minstrel_ht_prob_rate_reduce_streams(struct minstrel_ht_sta *mi) { struct minstrel_mcs_group_data *mg; int tmp_max_streams, group, tmp_idx, tmp_prob; int tmp_tp = 0; if (!mi->sta->deflink.ht_cap.ht_supported) return; group = MI_RATE_GROUP(mi->max_tp_rate[0]); tmp_max_streams = minstrel_mcs_groups[group].streams; for (group = 0; group < ARRAY_SIZE(minstrel_mcs_groups); group++) { mg = &mi->groups[group]; if (!mi->supported[group] || group == MINSTREL_CCK_GROUP) continue; tmp_idx = MI_RATE_IDX(mg->max_group_prob_rate); tmp_prob = mi->groups[group].rates[tmp_idx].prob_avg; if (tmp_tp < minstrel_ht_get_tp_avg(mi, group, tmp_idx, tmp_prob) && (minstrel_mcs_groups[group].streams < tmp_max_streams)) { mi->max_prob_rate = mg->max_group_prob_rate; tmp_tp = minstrel_ht_get_tp_avg(mi, group, tmp_idx, tmp_prob); } } } static u16 __minstrel_ht_get_sample_rate(struct minstrel_ht_sta *mi, enum minstrel_sample_type type) { u16 *rates = mi->sample[type].sample_rates; u16 cur; int i; for (i = 0; i < MINSTREL_SAMPLE_RATES; i++) { if (!rates[i]) continue; cur = rates[i]; rates[i] = 0; return cur; } return 0; } static inline int minstrel_ewma(int old, int new, int weight) { int diff, incr; diff = new - old; incr = (EWMA_DIV - weight) * diff / EWMA_DIV; return old + incr; } static inline int minstrel_filter_avg_add(u16 *prev_1, u16 *prev_2, s32 in) { s32 out_1 = *prev_1; s32 out_2 = *prev_2; s32 val; if (!in) in += 1; if (!out_1) { val = out_1 = in; goto out; } val = MINSTREL_AVG_COEFF1 * in; val += MINSTREL_AVG_COEFF2 * out_1; val += MINSTREL_AVG_COEFF3 * out_2; val >>= MINSTREL_SCALE; if (val > 1 << MINSTREL_SCALE) val = 1 << MINSTREL_SCALE; if (val < 0) val = 1; out: *prev_2 = out_1; *prev_1 = val; return val; } /* * Recalculate statistics and counters of a given rate */ static void minstrel_ht_calc_rate_stats(struct minstrel_priv *mp, struct minstrel_rate_stats *mrs) { unsigned int cur_prob; if (unlikely(mrs->attempts > 0)) { cur_prob = MINSTREL_FRAC(mrs->success, mrs->attempts); minstrel_filter_avg_add(&mrs->prob_avg, &mrs->prob_avg_1, cur_prob); mrs->att_hist += mrs->attempts; mrs->succ_hist += mrs->success; } mrs->last_success = mrs->success; mrs->last_attempts = mrs->attempts; mrs->success = 0; mrs->attempts = 0; } static bool minstrel_ht_find_sample_rate(struct minstrel_ht_sta *mi, int type, int idx) { int i; for (i = 0; i < MINSTREL_SAMPLE_RATES; i++) { u16 cur = mi->sample[type].sample_rates[i]; if (cur == idx) return true; if (!cur) break; } return false; } static int minstrel_ht_move_sample_rates(struct minstrel_ht_sta *mi, int type, u32 fast_rate_dur, u32 slow_rate_dur) { u16 *rates = mi->sample[type].sample_rates; int i, j; for (i = 0, j = 0; i < MINSTREL_SAMPLE_RATES; i++) { u32 duration; bool valid = false; u16 cur; cur = rates[i]; if (!cur) continue; duration = minstrel_get_duration(cur); switch (type) { case MINSTREL_SAMPLE_TYPE_SLOW: valid = duration > fast_rate_dur && duration < slow_rate_dur; break; case MINSTREL_SAMPLE_TYPE_INC: case MINSTREL_SAMPLE_TYPE_JUMP: valid = duration < fast_rate_dur; break; default: valid = false; break; } if (!valid) { rates[i] = 0; continue; } if (i == j) continue; rates[j++] = cur; rates[i] = 0; } return j; } static int minstrel_ht_group_min_rate_offset(struct minstrel_ht_sta *mi, int group, u32 max_duration) { u16 supported = mi->supported[group]; int i; for (i = 0; i < MCS_GROUP_RATES && supported; i++, supported >>= 1) { if (!(supported & BIT(0))) continue; if (minstrel_get_duration(MI_RATE(group, i)) >= max_duration) continue; return i; } return -1; } /* * Incremental update rates: * Flip through groups and pick the first group rate that is faster than the * highest currently selected rate */ static u16 minstrel_ht_next_inc_rate(struct minstrel_ht_sta *mi, u32 fast_rate_dur) { u8 type = MINSTREL_SAMPLE_TYPE_INC; int i, index = 0; u8 group; group = mi->sample[type].sample_group; for (i = 0; i < ARRAY_SIZE(minstrel_mcs_groups); i++) { group = (group + 1) % ARRAY_SIZE(minstrel_mcs_groups); index = minstrel_ht_group_min_rate_offset(mi, group, fast_rate_dur); if (index < 0) continue; index = MI_RATE(group, index & 0xf); if (!minstrel_ht_find_sample_rate(mi, type, index)) goto out; } index = 0; out: mi->sample[type].sample_group = group; return index; } static int minstrel_ht_next_group_sample_rate(struct minstrel_ht_sta *mi, int group, u16 supported, int offset) { struct minstrel_mcs_group_data *mg = &mi->groups[group]; u16 idx; int i; for (i = 0; i < MCS_GROUP_RATES; i++) { idx = sample_table[mg->column][mg->index]; if (++mg->index >= MCS_GROUP_RATES) { mg->index = 0; if (++mg->column >= ARRAY_SIZE(sample_table)) mg->column = 0; } if (idx < offset) continue; if (!(supported & BIT(idx))) continue; return MI_RATE(group, idx); } return -1; } /* * Jump rates: * Sample random rates, use those that are faster than the highest * currently selected rate. Rates between the fastest and the slowest * get sorted into the slow sample bucket, but only if it has room */ static u16 minstrel_ht_next_jump_rate(struct minstrel_ht_sta *mi, u32 fast_rate_dur, u32 slow_rate_dur, int *slow_rate_ofs) { struct minstrel_rate_stats *mrs; u32 max_duration = slow_rate_dur; int i, index, offset; u16 *slow_rates; u16 supported; u32 duration; u8 group; if (*slow_rate_ofs >= MINSTREL_SAMPLE_RATES) max_duration = fast_rate_dur; slow_rates = mi->sample[MINSTREL_SAMPLE_TYPE_SLOW].sample_rates; group = mi->sample[MINSTREL_SAMPLE_TYPE_JUMP].sample_group; for (i = 0; i < ARRAY_SIZE(minstrel_mcs_groups); i++) { u8 type; group = (group + 1) % ARRAY_SIZE(minstrel_mcs_groups); supported = mi->supported[group]; if (!supported) continue; offset = minstrel_ht_group_min_rate_offset(mi, group, max_duration); if (offset < 0) continue; index = minstrel_ht_next_group_sample_rate(mi, group, supported, offset); if (index < 0) continue; duration = minstrel_get_duration(index); if (duration < fast_rate_dur) type = MINSTREL_SAMPLE_TYPE_JUMP; else type = MINSTREL_SAMPLE_TYPE_SLOW; if (minstrel_ht_find_sample_rate(mi, type, index)) continue; if (type == MINSTREL_SAMPLE_TYPE_JUMP) goto found; if (*slow_rate_ofs >= MINSTREL_SAMPLE_RATES) continue; if (duration >= slow_rate_dur) continue; /* skip slow rates with high success probability */ mrs = minstrel_get_ratestats(mi, index); if (mrs->prob_avg > MINSTREL_FRAC(95, 100)) continue; slow_rates[(*slow_rate_ofs)++] = index; if (*slow_rate_ofs >= MINSTREL_SAMPLE_RATES) max_duration = fast_rate_dur; } index = 0; found: mi->sample[MINSTREL_SAMPLE_TYPE_JUMP].sample_group = group; return index; } static void minstrel_ht_refill_sample_rates(struct minstrel_ht_sta *mi) { u32 prob_dur = minstrel_get_duration(mi->max_prob_rate); u32 tp_dur = minstrel_get_duration(mi->max_tp_rate[0]); u32 tp2_dur = minstrel_get_duration(mi->max_tp_rate[1]); u32 fast_rate_dur = min(min(tp_dur, tp2_dur), prob_dur); u32 slow_rate_dur = max(max(tp_dur, tp2_dur), prob_dur); u16 *rates; int i, j; rates = mi->sample[MINSTREL_SAMPLE_TYPE_INC].sample_rates; i = minstrel_ht_move_sample_rates(mi, MINSTREL_SAMPLE_TYPE_INC, fast_rate_dur, slow_rate_dur); while (i < MINSTREL_SAMPLE_RATES) { rates[i] = minstrel_ht_next_inc_rate(mi, tp_dur); if (!rates[i]) break; i++; } rates = mi->sample[MINSTREL_SAMPLE_TYPE_JUMP].sample_rates; i = minstrel_ht_move_sample_rates(mi, MINSTREL_SAMPLE_TYPE_JUMP, fast_rate_dur, slow_rate_dur); j = minstrel_ht_move_sample_rates(mi, MINSTREL_SAMPLE_TYPE_SLOW, fast_rate_dur, slow_rate_dur); while (i < MINSTREL_SAMPLE_RATES) { rates[i] = minstrel_ht_next_jump_rate(mi, fast_rate_dur, slow_rate_dur, &j); if (!rates[i]) break; i++; } for (i = 0; i < ARRAY_SIZE(mi->sample); i++) memcpy(mi->sample[i].cur_sample_rates, mi->sample[i].sample_rates, sizeof(mi->sample[i].cur_sample_rates)); } /* * Update rate statistics and select new primary rates * * Rules for rate selection: * - max_prob_rate must use only one stream, as a tradeoff between delivery * probability and throughput during strong fluctuations * - as long as the max prob rate has a probability of more than 75%, pick * higher throughput rates, even if the probability is a bit lower */ static void minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) { struct minstrel_mcs_group_data *mg; struct minstrel_rate_stats *mrs; int group, i, j, cur_prob; u16 tmp_mcs_tp_rate[MAX_THR_RATES], tmp_group_tp_rate[MAX_THR_RATES]; u16 tmp_legacy_tp_rate[MAX_THR_RATES], tmp_max_prob_rate; u16 index; bool ht_supported = mi->sta->deflink.ht_cap.ht_supported; if (mi->ampdu_packets > 0) { if (!ieee80211_hw_check(mp->hw, TX_STATUS_NO_AMPDU_LEN)) mi->avg_ampdu_len = minstrel_ewma(mi->avg_ampdu_len, MINSTREL_FRAC(mi->ampdu_len, mi->ampdu_packets), EWMA_LEVEL); else mi->avg_ampdu_len = 0; mi->ampdu_len = 0; mi->ampdu_packets = 0; } if (mi->supported[MINSTREL_CCK_GROUP]) group = MINSTREL_CCK_GROUP; else if (mi->supported[MINSTREL_OFDM_GROUP]) group = MINSTREL_OFDM_GROUP; else group = 0; index = MI_RATE(group, 0); for (j = 0; j < ARRAY_SIZE(tmp_legacy_tp_rate); j++) tmp_legacy_tp_rate[j] = index; if (mi->supported[MINSTREL_VHT_GROUP_0]) group = MINSTREL_VHT_GROUP_0; else if (ht_supported) group = MINSTREL_HT_GROUP_0; else if (mi->supported[MINSTREL_CCK_GROUP]) group = MINSTREL_CCK_GROUP; else group = MINSTREL_OFDM_GROUP; index = MI_RATE(group, 0); tmp_max_prob_rate = index; for (j = 0; j < ARRAY_SIZE(tmp_mcs_tp_rate); j++) tmp_mcs_tp_rate[j] = index; /* Find best rate sets within all MCS groups*/ for (group = 0; group < ARRAY_SIZE(minstrel_mcs_groups); group++) { u16 *tp_rate = tmp_mcs_tp_rate; u16 last_prob = 0; mg = &mi->groups[group]; if (!mi->supported[group]) continue; /* (re)Initialize group rate indexes */ for(j = 0; j < MAX_THR_RATES; j++) tmp_group_tp_rate[j] = MI_RATE(group, 0); if (group == MINSTREL_CCK_GROUP && ht_supported) tp_rate = tmp_legacy_tp_rate; for (i = MCS_GROUP_RATES - 1; i >= 0; i--) { if (!(mi->supported[group] & BIT(i))) continue; index = MI_RATE(group, i); mrs = &mg->rates[i]; mrs->retry_updated = false; minstrel_ht_calc_rate_stats(mp, mrs); if (mrs->att_hist) last_prob = max(last_prob, mrs->prob_avg); else mrs->prob_avg = max(last_prob, mrs->prob_avg); cur_prob = mrs->prob_avg; if (minstrel_ht_get_tp_avg(mi, group, i, cur_prob) == 0) continue; /* Find max throughput rate set */ minstrel_ht_sort_best_tp_rates(mi, index, tp_rate); /* Find max throughput rate set within a group */ minstrel_ht_sort_best_tp_rates(mi, index, tmp_group_tp_rate); } memcpy(mg->max_group_tp_rate, tmp_group_tp_rate, sizeof(mg->max_group_tp_rate)); } /* Assign new rate set per sta */ minstrel_ht_assign_best_tp_rates(mi, tmp_mcs_tp_rate, tmp_legacy_tp_rate); memcpy(mi->max_tp_rate, tmp_mcs_tp_rate, sizeof(mi->max_tp_rate)); for (group = 0; group < ARRAY_SIZE(minstrel_mcs_groups); group++) { if (!mi->supported[group]) continue; mg = &mi->groups[group]; mg->max_group_prob_rate = MI_RATE(group, 0); for (i = 0; i < MCS_GROUP_RATES; i++) { if (!(mi->supported[group] & BIT(i))) continue; index = MI_RATE(group, i); /* Find max probability rate per group and global */ minstrel_ht_set_best_prob_rate(mi, &tmp_max_prob_rate, index); } } mi->max_prob_rate = tmp_max_prob_rate; /* Try to increase robustness of max_prob_rate*/ minstrel_ht_prob_rate_reduce_streams(mi); minstrel_ht_refill_sample_rates(mi); #ifdef CONFIG_MAC80211_DEBUGFS /* use fixed index if set */ if (mp->fixed_rate_idx != -1) { for (i = 0; i < 4; i++) mi->max_tp_rate[i] = mp->fixed_rate_idx; mi->max_prob_rate = mp->fixed_rate_idx; } #endif /* Reset update timer */ mi->last_stats_update = jiffies; mi->sample_time = jiffies; } static bool minstrel_ht_txstat_valid(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, struct ieee80211_tx_rate *rate) { int i; if (rate->idx < 0) return false; if (!rate->count) return false; if (rate->flags & IEEE80211_TX_RC_MCS || rate->flags & IEEE80211_TX_RC_VHT_MCS) return true; for (i = 0; i < ARRAY_SIZE(mp->cck_rates); i++) if (rate->idx == mp->cck_rates[i]) return true; for (i = 0; i < ARRAY_SIZE(mp->ofdm_rates[0]); i++) if (rate->idx == mp->ofdm_rates[mi->band][i]) return true; return false; } /* * Check whether rate_status contains valid information. */ static bool minstrel_ht_ri_txstat_valid(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, struct ieee80211_rate_status *rate_status) { int i; if (!rate_status) return false; if (!rate_status->try_count) return false; if (rate_status->rate_idx.flags & RATE_INFO_FLAGS_MCS || rate_status->rate_idx.flags & RATE_INFO_FLAGS_VHT_MCS) return true; for (i = 0; i < ARRAY_SIZE(mp->cck_rates); i++) { if (rate_status->rate_idx.legacy == minstrel_cck_bitrates[ mp->cck_rates[i] ]) return true; } for (i = 0; i < ARRAY_SIZE(mp->ofdm_rates); i++) { if (rate_status->rate_idx.legacy == minstrel_ofdm_bitrates[ mp->ofdm_rates[mi->band][i] ]) return true; } return false; } static void minstrel_downgrade_rate(struct minstrel_ht_sta *mi, u16 *idx, bool primary) { int group, orig_group; orig_group = group = MI_RATE_GROUP(*idx); while (group > 0) { group--; if (!mi->supported[group]) continue; if (minstrel_mcs_groups[group].streams > minstrel_mcs_groups[orig_group].streams) continue; if (primary) *idx = mi->groups[group].max_group_tp_rate[0]; else *idx = mi->groups[group].max_group_tp_rate[1]; break; } } static void minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, void *priv_sta, struct ieee80211_tx_status *st) { struct ieee80211_tx_info *info = st->info; struct minstrel_ht_sta *mi = priv_sta; struct ieee80211_tx_rate *ar = info->status.rates; struct minstrel_rate_stats *rate, *rate2; struct minstrel_priv *mp = priv; u32 update_interval = mp->update_interval; bool last, update = false; int i; /* Ignore packet that was sent with noAck flag */ if (info->flags & IEEE80211_TX_CTL_NO_ACK) return; /* This packet was aggregated but doesn't carry status info */ if ((info->flags & IEEE80211_TX_CTL_AMPDU) && !(info->flags & IEEE80211_TX_STAT_AMPDU)) return; if (!(info->flags & IEEE80211_TX_STAT_AMPDU)) { info->status.ampdu_ack_len = (info->flags & IEEE80211_TX_STAT_ACK ? 1 : 0); info->status.ampdu_len = 1; } /* wraparound */ if (mi->total_packets >= ~0 - info->status.ampdu_len) { mi->total_packets = 0; mi->sample_packets = 0; } mi->total_packets += info->status.ampdu_len; if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) mi->sample_packets += info->status.ampdu_len; mi->ampdu_packets++; mi->ampdu_len += info->status.ampdu_len; if (st->rates && st->n_rates) { last = !minstrel_ht_ri_txstat_valid(mp, mi, &(st->rates[0])); for (i = 0; !last; i++) { last = (i == st->n_rates - 1) || !minstrel_ht_ri_txstat_valid(mp, mi, &(st->rates[i + 1])); rate = minstrel_ht_ri_get_stats(mp, mi, &(st->rates[i])); if (last) rate->success += info->status.ampdu_ack_len; rate->attempts += st->rates[i].try_count * info->status.ampdu_len; } } else { last = !minstrel_ht_txstat_valid(mp, mi, &ar[0]); for (i = 0; !last; i++) { last = (i == IEEE80211_TX_MAX_RATES - 1) || !minstrel_ht_txstat_valid(mp, mi, &ar[i + 1]); rate = minstrel_ht_get_stats(mp, mi, &ar[i]); if (last) rate->success += info->status.ampdu_ack_len; rate->attempts += ar[i].count * info->status.ampdu_len; } } if (mp->hw->max_rates > 1) { /* * check for sudden death of spatial multiplexing, * downgrade to a lower number of streams if necessary. */ rate = minstrel_get_ratestats(mi, mi->max_tp_rate[0]); if (rate->attempts > 30 && rate->success < rate->attempts / 4) { minstrel_downgrade_rate(mi, &mi->max_tp_rate[0], true); update = true; } rate2 = minstrel_get_ratestats(mi, mi->max_tp_rate[1]); if (rate2->attempts > 30 && rate2->success < rate2->attempts / 4) { minstrel_downgrade_rate(mi, &mi->max_tp_rate[1], false); update = true; } } if (time_after(jiffies, mi->last_stats_update + update_interval)) { update = true; minstrel_ht_update_stats(mp, mi); } if (update) minstrel_ht_update_rates(mp, mi); } static void minstrel_calc_retransmit(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, int index) { struct minstrel_rate_stats *mrs; unsigned int tx_time, tx_time_rtscts, tx_time_data; unsigned int cw = mp->cw_min; unsigned int ctime = 0; unsigned int t_slot = 9; /* FIXME */ unsigned int ampdu_len = minstrel_ht_avg_ampdu_len(mi); unsigned int overhead = 0, overhead_rtscts = 0; mrs = minstrel_get_ratestats(mi, index); if (mrs->prob_avg < MINSTREL_FRAC(1, 10)) { mrs->retry_count = 1; mrs->retry_count_rtscts = 1; return; } mrs->retry_count = 2; mrs->retry_count_rtscts = 2; mrs->retry_updated = true; tx_time_data = minstrel_get_duration(index) * ampdu_len / 1000; /* Contention time for first 2 tries */ ctime = (t_slot * cw) >> 1; cw = min((cw << 1) | 1, mp->cw_max); ctime += (t_slot * cw) >> 1; cw = min((cw << 1) | 1, mp->cw_max); if (minstrel_ht_is_legacy_group(MI_RATE_GROUP(index))) { overhead = mi->overhead_legacy; overhead_rtscts = mi->overhead_legacy_rtscts; } else { overhead = mi->overhead; overhead_rtscts = mi->overhead_rtscts; } /* Total TX time for data and Contention after first 2 tries */ tx_time = ctime + 2 * (overhead + tx_time_data); tx_time_rtscts = ctime + 2 * (overhead_rtscts + tx_time_data); /* See how many more tries we can fit inside segment size */ do { /* Contention time for this try */ ctime = (t_slot * cw) >> 1; cw = min((cw << 1) | 1, mp->cw_max); /* Total TX time after this try */ tx_time += ctime + overhead + tx_time_data; tx_time_rtscts += ctime + overhead_rtscts + tx_time_data; if (tx_time_rtscts < mp->segment_size) mrs->retry_count_rtscts++; } while ((tx_time < mp->segment_size) && (++mrs->retry_count < mp->max_retry)); } static void minstrel_ht_set_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, struct ieee80211_sta_rates *ratetbl, int offset, int index) { int group_idx = MI_RATE_GROUP(index); const struct mcs_group *group = &minstrel_mcs_groups[group_idx]; struct minstrel_rate_stats *mrs; u8 idx; u16 flags = group->flags; mrs = minstrel_get_ratestats(mi, index); if (!mrs->retry_updated) minstrel_calc_retransmit(mp, mi, index); if (mrs->prob_avg < MINSTREL_FRAC(20, 100) || !mrs->retry_count) { ratetbl->rate[offset].count = 2; ratetbl->rate[offset].count_rts = 2; ratetbl->rate[offset].count_cts = 2; } else { ratetbl->rate[offset].count = mrs->retry_count; ratetbl->rate[offset].count_cts = mrs->retry_count; ratetbl->rate[offset].count_rts = mrs->retry_count_rtscts; } index = MI_RATE_IDX(index); if (group_idx == MINSTREL_CCK_GROUP) idx = mp->cck_rates[index % ARRAY_SIZE(mp->cck_rates)]; else if (group_idx == MINSTREL_OFDM_GROUP) idx = mp->ofdm_rates[mi->band][index % ARRAY_SIZE(mp->ofdm_rates[0])]; else if (flags & IEEE80211_TX_RC_VHT_MCS) idx = ((group->streams - 1) << 4) | (index & 0xF); else idx = index + (group->streams - 1) * 8; /* enable RTS/CTS if needed: * - if station is in dynamic SMPS (and streams > 1) * - for fallback rates, to increase chances of getting through */ if (offset > 0 || (mi->sta->deflink.smps_mode == IEEE80211_SMPS_DYNAMIC && group->streams > 1)) { ratetbl->rate[offset].count = ratetbl->rate[offset].count_rts; flags |= IEEE80211_TX_RC_USE_RTS_CTS; } ratetbl->rate[offset].idx = idx; ratetbl->rate[offset].flags = flags; } static inline int minstrel_ht_get_prob_avg(struct minstrel_ht_sta *mi, int rate) { int group = MI_RATE_GROUP(rate); rate = MI_RATE_IDX(rate); return mi->groups[group].rates[rate].prob_avg; } static int minstrel_ht_get_max_amsdu_len(struct minstrel_ht_sta *mi) { int group = MI_RATE_GROUP(mi->max_prob_rate); const struct mcs_group *g = &minstrel_mcs_groups[group]; int rate = MI_RATE_IDX(mi->max_prob_rate); unsigned int duration; /* Disable A-MSDU if max_prob_rate is bad */ if (mi->groups[group].rates[rate].prob_avg < MINSTREL_FRAC(50, 100)) return 1; duration = g->duration[rate]; duration <<= g->shift; /* If the rate is slower than single-stream MCS1, make A-MSDU limit small */ if (duration > MCS_DURATION(1, 0, 52)) return 500; /* * If the rate is slower than single-stream MCS4, limit A-MSDU to usual * data packet size */ if (duration > MCS_DURATION(1, 0, 104)) return 1600; /* * If the rate is slower than single-stream MCS7, or if the max throughput * rate success probability is less than 75%, limit A-MSDU to twice the usual * data packet size */ if (duration > MCS_DURATION(1, 0, 260) || (minstrel_ht_get_prob_avg(mi, mi->max_tp_rate[0]) < MINSTREL_FRAC(75, 100))) return 3200; /* * HT A-MPDU limits maximum MPDU size under BA agreement to 4095 bytes. * Since aggregation sessions are started/stopped without txq flush, use * the limit here to avoid the complexity of having to de-aggregate * packets in the queue. */ if (!mi->sta->deflink.vht_cap.vht_supported) return IEEE80211_MAX_MPDU_LEN_HT_BA; /* unlimited */ return 0; } static void minstrel_ht_update_rates(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) { struct ieee80211_sta_rates *rates; int i = 0; int max_rates = min_t(int, mp->hw->max_rates, IEEE80211_TX_RATE_TABLE_SIZE); rates = kzalloc(sizeof(*rates), GFP_ATOMIC); if (!rates) return; /* Start with max_tp_rate[0] */ minstrel_ht_set_rate(mp, mi, rates, i++, mi->max_tp_rate[0]); /* Fill up remaining, keep one entry for max_probe_rate */ for (; i < (max_rates - 1); i++) minstrel_ht_set_rate(mp, mi, rates, i, mi->max_tp_rate[i]); if (i < max_rates) minstrel_ht_set_rate(mp, mi, rates, i++, mi->max_prob_rate); if (i < IEEE80211_TX_RATE_TABLE_SIZE) rates->rate[i].idx = -1; mi->sta->deflink.agg.max_rc_amsdu_len = minstrel_ht_get_max_amsdu_len(mi); ieee80211_sta_recalc_aggregates(mi->sta); rate_control_set_rates(mp->hw, mi->sta, rates); } static u16 minstrel_ht_get_sample_rate(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) { u8 seq; if (mp->hw->max_rates > 1) { seq = mi->sample_seq; mi->sample_seq = (seq + 1) % ARRAY_SIZE(minstrel_sample_seq); seq = minstrel_sample_seq[seq]; } else { seq = MINSTREL_SAMPLE_TYPE_INC; } return __minstrel_ht_get_sample_rate(mi, seq); } static void minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, struct ieee80211_tx_rate_control *txrc) { const struct mcs_group *sample_group; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(txrc->skb); struct ieee80211_tx_rate *rate = &info->status.rates[0]; struct minstrel_ht_sta *mi = priv_sta; struct minstrel_priv *mp = priv; u16 sample_idx; info->flags |= mi->tx_flags; #ifdef CONFIG_MAC80211_DEBUGFS if (mp->fixed_rate_idx != -1) return; #endif /* Don't use EAPOL frames for sampling on non-mrr hw */ if (mp->hw->max_rates == 1 && (info->control.flags & IEEE80211_TX_CTRL_PORT_CTRL_PROTO)) return; if (time_is_after_jiffies(mi->sample_time)) return; mi->sample_time = jiffies + MINSTREL_SAMPLE_INTERVAL; sample_idx = minstrel_ht_get_sample_rate(mp, mi); if (!sample_idx) return; sample_group = &minstrel_mcs_groups[MI_RATE_GROUP(sample_idx)]; sample_idx = MI_RATE_IDX(sample_idx); if (sample_group == &minstrel_mcs_groups[MINSTREL_CCK_GROUP] && (sample_idx >= 4) != txrc->short_preamble) return; info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE; rate->count = 1; if (sample_group == &minstrel_mcs_groups[MINSTREL_CCK_GROUP]) { int idx = sample_idx % ARRAY_SIZE(mp->cck_rates); rate->idx = mp->cck_rates[idx]; } else if (sample_group == &minstrel_mcs_groups[MINSTREL_OFDM_GROUP]) { int idx = sample_idx % ARRAY_SIZE(mp->ofdm_rates[0]); rate->idx = mp->ofdm_rates[mi->band][idx]; } else if (sample_group->flags & IEEE80211_TX_RC_VHT_MCS) { ieee80211_rate_set_vht(rate, MI_RATE_IDX(sample_idx), sample_group->streams); } else { rate->idx = sample_idx + (sample_group->streams - 1) * 8; } rate->flags = sample_group->flags; } static void minstrel_ht_update_cck(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, struct ieee80211_supported_band *sband, struct ieee80211_sta *sta) { int i; if (sband->band != NL80211_BAND_2GHZ) return; if (sta->deflink.ht_cap.ht_supported && !ieee80211_hw_check(mp->hw, SUPPORTS_HT_CCK_RATES)) return; for (i = 0; i < 4; i++) { if (mp->cck_rates[i] == 0xff || !rate_supported(sta, sband->band, mp->cck_rates[i])) continue; mi->supported[MINSTREL_CCK_GROUP] |= BIT(i); if (sband->bitrates[i].flags & IEEE80211_RATE_SHORT_PREAMBLE) mi->supported[MINSTREL_CCK_GROUP] |= BIT(i + 4); } } static void minstrel_ht_update_ofdm(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, struct ieee80211_supported_band *sband, struct ieee80211_sta *sta) { const u8 *rates; int i; if (sta->deflink.ht_cap.ht_supported) return; rates = mp->ofdm_rates[sband->band]; for (i = 0; i < ARRAY_SIZE(mp->ofdm_rates[0]); i++) { if (rates[i] == 0xff || !rate_supported(sta, sband->band, rates[i])) continue; mi->supported[MINSTREL_OFDM_GROUP] |= BIT(i); } } static void minstrel_ht_update_caps(void *priv, struct ieee80211_supported_band *sband, struct cfg80211_chan_def *chandef, struct ieee80211_sta *sta, void *priv_sta) { struct minstrel_priv *mp = priv; struct minstrel_ht_sta *mi = priv_sta; struct ieee80211_mcs_info *mcs = &sta->deflink.ht_cap.mcs; u16 ht_cap = sta->deflink.ht_cap.cap; struct ieee80211_sta_vht_cap *vht_cap = &sta->deflink.vht_cap; const struct ieee80211_rate *ctl_rate; struct sta_info *sta_info; bool ldpc, erp; int use_vht; int ack_dur; int stbc; int i; BUILD_BUG_ON(ARRAY_SIZE(minstrel_mcs_groups) != MINSTREL_GROUPS_NB); if (vht_cap->vht_supported) use_vht = vht_cap->vht_mcs.tx_mcs_map != cpu_to_le16(~0); else use_vht = 0; memset(mi, 0, sizeof(*mi)); mi->sta = sta; mi->band = sband->band; mi->last_stats_update = jiffies; ack_dur = ieee80211_frame_duration(sband->band, 10, 60, 1, 1); mi->overhead = ieee80211_frame_duration(sband->band, 0, 60, 1, 1); mi->overhead += ack_dur; mi->overhead_rtscts = mi->overhead + 2 * ack_dur; ctl_rate = &sband->bitrates[rate_lowest_index(sband, sta)]; erp = ctl_rate->flags & IEEE80211_RATE_ERP_G; ack_dur = ieee80211_frame_duration(sband->band, 10, ctl_rate->bitrate, erp, 1); mi->overhead_legacy = ack_dur; mi->overhead_legacy_rtscts = mi->overhead_legacy + 2 * ack_dur; mi->avg_ampdu_len = MINSTREL_FRAC(1, 1); if (!use_vht) { stbc = (ht_cap & IEEE80211_HT_CAP_RX_STBC) >> IEEE80211_HT_CAP_RX_STBC_SHIFT; ldpc = ht_cap & IEEE80211_HT_CAP_LDPC_CODING; } else { stbc = (vht_cap->cap & IEEE80211_VHT_CAP_RXSTBC_MASK) >> IEEE80211_VHT_CAP_RXSTBC_SHIFT; ldpc = vht_cap->cap & IEEE80211_VHT_CAP_RXLDPC; } mi->tx_flags |= stbc << IEEE80211_TX_CTL_STBC_SHIFT; if (ldpc) mi->tx_flags |= IEEE80211_TX_CTL_LDPC; for (i = 0; i < ARRAY_SIZE(mi->groups); i++) { u32 gflags = minstrel_mcs_groups[i].flags; int bw, nss; mi->supported[i] = 0; if (minstrel_ht_is_legacy_group(i)) continue; if (gflags & IEEE80211_TX_RC_SHORT_GI) { if (gflags & IEEE80211_TX_RC_40_MHZ_WIDTH) { if (!(ht_cap & IEEE80211_HT_CAP_SGI_40)) continue; } else { if (!(ht_cap & IEEE80211_HT_CAP_SGI_20)) continue; } } if (gflags & IEEE80211_TX_RC_40_MHZ_WIDTH && sta->deflink.bandwidth < IEEE80211_STA_RX_BW_40) continue; nss = minstrel_mcs_groups[i].streams; /* Mark MCS > 7 as unsupported if STA is in static SMPS mode */ if (sta->deflink.smps_mode == IEEE80211_SMPS_STATIC && nss > 1) continue; /* HT rate */ if (gflags & IEEE80211_TX_RC_MCS) { if (use_vht && minstrel_vht_only) continue; mi->supported[i] = mcs->rx_mask[nss - 1]; continue; } /* VHT rate */ if (!vht_cap->vht_supported || WARN_ON(!(gflags & IEEE80211_TX_RC_VHT_MCS)) || WARN_ON(gflags & IEEE80211_TX_RC_160_MHZ_WIDTH)) continue; if (gflags & IEEE80211_TX_RC_80_MHZ_WIDTH) { if (sta->deflink.bandwidth < IEEE80211_STA_RX_BW_80 || ((gflags & IEEE80211_TX_RC_SHORT_GI) && !(vht_cap->cap & IEEE80211_VHT_CAP_SHORT_GI_80))) { continue; } } if (gflags & IEEE80211_TX_RC_40_MHZ_WIDTH) bw = BW_40; else if (gflags & IEEE80211_TX_RC_80_MHZ_WIDTH) bw = BW_80; else bw = BW_20; mi->supported[i] = minstrel_get_valid_vht_rates(bw, nss, vht_cap->vht_mcs.tx_mcs_map); } sta_info = container_of(sta, struct sta_info, sta); mi->use_short_preamble = test_sta_flag(sta_info, WLAN_STA_SHORT_PREAMBLE) && sta_info->sdata->vif.bss_conf.use_short_preamble; minstrel_ht_update_cck(mp, mi, sband, sta); minstrel_ht_update_ofdm(mp, mi, sband, sta); /* create an initial rate table with the lowest supported rates */ minstrel_ht_update_stats(mp, mi); minstrel_ht_update_rates(mp, mi); } static void minstrel_ht_rate_init(void *priv, struct ieee80211_supported_band *sband, struct cfg80211_chan_def *chandef, struct ieee80211_sta *sta, void *priv_sta) { minstrel_ht_update_caps(priv, sband, chandef, sta, priv_sta); } static void minstrel_ht_rate_update(void *priv, struct ieee80211_supported_band *sband, struct cfg80211_chan_def *chandef, struct ieee80211_sta *sta, void *priv_sta, u32 changed) { minstrel_ht_update_caps(priv, sband, chandef, sta, priv_sta); } static void * minstrel_ht_alloc_sta(void *priv, struct ieee80211_sta *sta, gfp_t gfp) { struct ieee80211_supported_band *sband; struct minstrel_ht_sta *mi; struct minstrel_priv *mp = priv; struct ieee80211_hw *hw = mp->hw; int max_rates = 0; int i; for (i = 0; i < NUM_NL80211_BANDS; i++) { sband = hw->wiphy->bands[i]; if (sband && sband->n_bitrates > max_rates) max_rates = sband->n_bitrates; } return kzalloc(sizeof(*mi), gfp); } static void minstrel_ht_free_sta(void *priv, struct ieee80211_sta *sta, void *priv_sta) { kfree(priv_sta); } static void minstrel_ht_fill_rate_array(u8 *dest, struct ieee80211_supported_band *sband, const s16 *bitrates, int n_rates, u32 rate_flags) { int i, j; for (i = 0; i < sband->n_bitrates; i++) { struct ieee80211_rate *rate = &sband->bitrates[i]; if ((rate_flags & sband->bitrates[i].flags) != rate_flags) continue; for (j = 0; j < n_rates; j++) { if (rate->bitrate != bitrates[j]) continue; dest[j] = i; break; } } } static void minstrel_ht_init_cck_rates(struct minstrel_priv *mp) { static const s16 bitrates[4] = { 10, 20, 55, 110 }; struct ieee80211_supported_band *sband; u32 rate_flags = ieee80211_chandef_rate_flags(&mp->hw->conf.chandef); memset(mp->cck_rates, 0xff, sizeof(mp->cck_rates)); sband = mp->hw->wiphy->bands[NL80211_BAND_2GHZ]; if (!sband) return; BUILD_BUG_ON(ARRAY_SIZE(mp->cck_rates) != ARRAY_SIZE(bitrates)); minstrel_ht_fill_rate_array(mp->cck_rates, sband, minstrel_cck_bitrates, ARRAY_SIZE(minstrel_cck_bitrates), rate_flags); } static void minstrel_ht_init_ofdm_rates(struct minstrel_priv *mp, enum nl80211_band band) { static const s16 bitrates[8] = { 60, 90, 120, 180, 240, 360, 480, 540 }; struct ieee80211_supported_band *sband; u32 rate_flags = ieee80211_chandef_rate_flags(&mp->hw->conf.chandef); memset(mp->ofdm_rates[band], 0xff, sizeof(mp->ofdm_rates[band])); sband = mp->hw->wiphy->bands[band]; if (!sband) return; BUILD_BUG_ON(ARRAY_SIZE(mp->ofdm_rates[band]) != ARRAY_SIZE(bitrates)); minstrel_ht_fill_rate_array(mp->ofdm_rates[band], sband, minstrel_ofdm_bitrates, ARRAY_SIZE(minstrel_ofdm_bitrates), rate_flags); } static void * minstrel_ht_alloc(struct ieee80211_hw *hw) { struct minstrel_priv *mp; int i; mp = kzalloc(sizeof(struct minstrel_priv), GFP_ATOMIC); if (!mp) return NULL; /* contention window settings * Just an approximation. Using the per-queue values would complicate * the calculations and is probably unnecessary */ mp->cw_min = 15; mp->cw_max = 1023; /* maximum time that the hw is allowed to stay in one MRR segment */ mp->segment_size = 6000; if (hw->max_rate_tries > 0) mp->max_retry = hw->max_rate_tries; else /* safe default, does not necessarily have to match hw properties */ mp->max_retry = 7; mp->hw = hw; mp->update_interval = HZ / 20; minstrel_ht_init_cck_rates(mp); for (i = 0; i < ARRAY_SIZE(mp->hw->wiphy->bands); i++) minstrel_ht_init_ofdm_rates(mp, i); return mp; } #ifdef CONFIG_MAC80211_DEBUGFS static void minstrel_ht_add_debugfs(struct ieee80211_hw *hw, void *priv, struct dentry *debugfsdir) { struct minstrel_priv *mp = priv; mp->fixed_rate_idx = (u32) -1; debugfs_create_u32("fixed_rate_idx", S_IRUGO | S_IWUGO, debugfsdir, &mp->fixed_rate_idx); } #endif static void minstrel_ht_free(void *priv) { kfree(priv); } static u32 minstrel_ht_get_expected_throughput(void *priv_sta) { struct minstrel_ht_sta *mi = priv_sta; int i, j, prob, tp_avg; i = MI_RATE_GROUP(mi->max_tp_rate[0]); j = MI_RATE_IDX(mi->max_tp_rate[0]); prob = mi->groups[i].rates[j].prob_avg; /* convert tp_avg from pkt per second in kbps */ tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * 10; tp_avg = tp_avg * AVG_PKT_SIZE * 8 / 1024; return tp_avg; } static const struct rate_control_ops mac80211_minstrel_ht = { .name = "minstrel_ht", .capa = RATE_CTRL_CAPA_AMPDU_TRIGGER, .tx_status_ext = minstrel_ht_tx_status, .get_rate = minstrel_ht_get_rate, .rate_init = minstrel_ht_rate_init, .rate_update = minstrel_ht_rate_update, .alloc_sta = minstrel_ht_alloc_sta, .free_sta = minstrel_ht_free_sta, .alloc = minstrel_ht_alloc, .free = minstrel_ht_free, #ifdef CONFIG_MAC80211_DEBUGFS .add_debugfs = minstrel_ht_add_debugfs, .add_sta_debugfs = minstrel_ht_add_sta_debugfs, #endif .get_expected_throughput = minstrel_ht_get_expected_throughput, }; static void __init init_sample_table(void) { int col, i, new_idx; u8 rnd[MCS_GROUP_RATES]; memset(sample_table, 0xff, sizeof(sample_table)); for (col = 0; col < SAMPLE_COLUMNS; col++) { get_random_bytes(rnd, sizeof(rnd)); for (i = 0; i < MCS_GROUP_RATES; i++) { new_idx = (i + rnd[i]) % MCS_GROUP_RATES; while (sample_table[col][new_idx] != 0xff) new_idx = (new_idx + 1) % MCS_GROUP_RATES; sample_table[col][new_idx] = i; } } } int __init rc80211_minstrel_init(void) { init_sample_table(); return ieee80211_rate_control_register(&mac80211_minstrel_ht); } void rc80211_minstrel_exit(void) { ieee80211_rate_control_unregister(&mac80211_minstrel_ht); } |
| 23 8 8 8 8 7 27 5 28 28 28 28 28 28 28 137 137 137 137 2 2 2 2 1 137 137 136 107 28 24 28 28 27 23 28 23 27 28 27 109 108 8 109 136 135 1 134 5 135 28 28 28 8 28 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Main USB camera driver * * Copyright (C) 2008-2011 Jean-François Moine <http://moinejf.free.fr> * * Camera button input handling by Márton Németh * Copyright (C) 2009-2010 Márton Németh <nm127@freemail.hu> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define GSPCA_VERSION "2.14.0" #include <linux/init.h> #include <linux/fs.h> #include <linux/vmalloc.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/pagemap.h> #include <linux/io.h> #include <asm/page.h> #include <linux/uaccess.h> #include <linux/ktime.h> #include <media/v4l2-ioctl.h> #include <media/v4l2-ctrls.h> #include <media/v4l2-fh.h> #include <media/v4l2-event.h> #include "gspca.h" #if IS_ENABLED(CONFIG_INPUT) #include <linux/input.h> #include <linux/usb/input.h> #endif /* global values */ #define DEF_NURBS 3 /* default number of URBs */ #if DEF_NURBS > MAX_NURBS #error "DEF_NURBS too big" #endif MODULE_AUTHOR("Jean-François Moine <http://moinejf.free.fr>"); MODULE_DESCRIPTION("GSPCA USB Camera Driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(GSPCA_VERSION); int gspca_debug; EXPORT_SYMBOL(gspca_debug); static void PDEBUG_MODE(struct gspca_dev *gspca_dev, int debug, char *txt, __u32 pixfmt, int w, int h) { if ((pixfmt >> 24) >= '0' && (pixfmt >> 24) <= 'z') { gspca_dbg(gspca_dev, debug, "%s %c%c%c%c %dx%d\n", txt, pixfmt & 0xff, (pixfmt >> 8) & 0xff, (pixfmt >> 16) & 0xff, pixfmt >> 24, w, h); } else { gspca_dbg(gspca_dev, debug, "%s 0x%08x %dx%d\n", txt, pixfmt, w, h); } } /* specific memory types - !! should be different from V4L2_MEMORY_xxx */ #define GSPCA_MEMORY_NO 0 /* V4L2_MEMORY_xxx starts from 1 */ #define GSPCA_MEMORY_READ 7 /* * Input and interrupt endpoint handling functions */ #if IS_ENABLED(CONFIG_INPUT) static void int_irq(struct urb *urb) { struct gspca_dev *gspca_dev = (struct gspca_dev *) urb->context; int ret; ret = urb->status; switch (ret) { case 0: if (gspca_dev->sd_desc->int_pkt_scan(gspca_dev, urb->transfer_buffer, urb->actual_length) < 0) { gspca_err(gspca_dev, "Unknown packet received\n"); } break; case -ENOENT: case -ECONNRESET: case -ENODEV: case -ESHUTDOWN: /* Stop is requested either by software or hardware is gone, * keep the ret value non-zero and don't resubmit later. */ break; default: gspca_err(gspca_dev, "URB error %i, resubmitting\n", urb->status); urb->status = 0; ret = 0; } if (ret == 0) { ret = usb_submit_urb(urb, GFP_ATOMIC); if (ret < 0) pr_err("Resubmit URB failed with error %i\n", ret); } } static int gspca_input_connect(struct gspca_dev *dev) { struct input_dev *input_dev; int err = 0; dev->input_dev = NULL; if (dev->sd_desc->int_pkt_scan || dev->sd_desc->other_input) { input_dev = input_allocate_device(); if (!input_dev) return -ENOMEM; usb_make_path(dev->dev, dev->phys, sizeof(dev->phys)); strlcat(dev->phys, "/input0", sizeof(dev->phys)); input_dev->name = dev->sd_desc->name; input_dev->phys = dev->phys; usb_to_input_id(dev->dev, &input_dev->id); input_dev->evbit[0] = BIT_MASK(EV_KEY); input_dev->keybit[BIT_WORD(KEY_CAMERA)] = BIT_MASK(KEY_CAMERA); input_dev->dev.parent = &dev->dev->dev; err = input_register_device(input_dev); if (err) { pr_err("Input device registration failed with error %i\n", err); input_dev->dev.parent = NULL; input_free_device(input_dev); } else { dev->input_dev = input_dev; } } return err; } static int alloc_and_submit_int_urb(struct gspca_dev *gspca_dev, struct usb_endpoint_descriptor *ep) { unsigned int buffer_len; int interval; struct urb *urb; struct usb_device *dev; void *buffer = NULL; int ret = -EINVAL; buffer_len = le16_to_cpu(ep->wMaxPacketSize); interval = ep->bInterval; gspca_dbg(gspca_dev, D_CONF, "found int in endpoint: 0x%x, buffer_len=%u, interval=%u\n", ep->bEndpointAddress, buffer_len, interval); dev = gspca_dev->dev; urb = usb_alloc_urb(0, GFP_KERNEL); if (!urb) { ret = -ENOMEM; goto error; } buffer = usb_alloc_coherent(dev, buffer_len, GFP_KERNEL, &urb->transfer_dma); if (!buffer) { ret = -ENOMEM; goto error_buffer; } usb_fill_int_urb(urb, dev, usb_rcvintpipe(dev, ep->bEndpointAddress), buffer, buffer_len, int_irq, (void *)gspca_dev, interval); urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; ret = usb_submit_urb(urb, GFP_KERNEL); if (ret < 0) { gspca_err(gspca_dev, "submit int URB failed with error %i\n", ret); goto error_submit; } gspca_dev->int_urb = urb; return ret; error_submit: usb_free_coherent(dev, urb->transfer_buffer_length, urb->transfer_buffer, urb->transfer_dma); error_buffer: usb_free_urb(urb); error: return ret; } static void gspca_input_create_urb(struct gspca_dev *gspca_dev) { struct usb_interface *intf; struct usb_host_interface *intf_desc; struct usb_endpoint_descriptor *ep; int i; if (gspca_dev->sd_desc->int_pkt_scan) { intf = usb_ifnum_to_if(gspca_dev->dev, gspca_dev->iface); intf_desc = intf->cur_altsetting; for (i = 0; i < intf_desc->desc.bNumEndpoints; i++) { ep = &intf_desc->endpoint[i].desc; if (usb_endpoint_dir_in(ep) && usb_endpoint_xfer_int(ep)) { alloc_and_submit_int_urb(gspca_dev, ep); break; } } } } static void gspca_input_destroy_urb(struct gspca_dev *gspca_dev) { struct urb *urb; urb = gspca_dev->int_urb; if (urb) { gspca_dev->int_urb = NULL; usb_kill_urb(urb); usb_free_coherent(gspca_dev->dev, urb->transfer_buffer_length, urb->transfer_buffer, urb->transfer_dma); usb_free_urb(urb); } } #else static inline void gspca_input_destroy_urb(struct gspca_dev *gspca_dev) { } static inline void gspca_input_create_urb(struct gspca_dev *gspca_dev) { } static inline int gspca_input_connect(struct gspca_dev *dev) { return 0; } #endif /* * fill a video frame from an URB and resubmit */ static void fill_frame(struct gspca_dev *gspca_dev, struct urb *urb) { u8 *data; /* address of data in the iso message */ int i, len, st; cam_pkt_op pkt_scan; if (urb->status != 0) { if (urb->status == -ESHUTDOWN) return; /* disconnection */ #ifdef CONFIG_PM if (gspca_dev->frozen) return; #endif gspca_err(gspca_dev, "urb status: %d\n", urb->status); urb->status = 0; goto resubmit; } pkt_scan = gspca_dev->sd_desc->pkt_scan; for (i = 0; i < urb->number_of_packets; i++) { len = urb->iso_frame_desc[i].actual_length; /* check the packet status and length */ st = urb->iso_frame_desc[i].status; if (st) { gspca_dbg(gspca_dev, D_PACK, "ISOC data error: [%d] len=%d, status=%d\n", i, len, st); gspca_dev->last_packet_type = DISCARD_PACKET; continue; } if (len == 0) { if (gspca_dev->empty_packet == 0) gspca_dev->empty_packet = 1; continue; } /* let the packet be analyzed by the subdriver */ gspca_dbg(gspca_dev, D_PACK, "packet [%d] o:%d l:%d\n", i, urb->iso_frame_desc[i].offset, len); data = (u8 *) urb->transfer_buffer + urb->iso_frame_desc[i].offset; pkt_scan(gspca_dev, data, len); } resubmit: if (!gspca_dev->streaming) return; /* resubmit the URB */ st = usb_submit_urb(urb, GFP_ATOMIC); if (st < 0) pr_err("usb_submit_urb() ret %d\n", st); } /* * ISOC message interrupt from the USB device * * Analyse each packet and call the subdriver for copy to the frame buffer. */ static void isoc_irq(struct urb *urb) { struct gspca_dev *gspca_dev = (struct gspca_dev *) urb->context; gspca_dbg(gspca_dev, D_PACK, "isoc irq\n"); if (!gspca_dev->streaming) return; fill_frame(gspca_dev, urb); } /* * bulk message interrupt from the USB device */ static void bulk_irq(struct urb *urb) { struct gspca_dev *gspca_dev = (struct gspca_dev *) urb->context; int st; gspca_dbg(gspca_dev, D_PACK, "bulk irq\n"); if (!gspca_dev->streaming) return; switch (urb->status) { case 0: break; case -ESHUTDOWN: return; /* disconnection */ default: #ifdef CONFIG_PM if (gspca_dev->frozen) return; #endif gspca_err(gspca_dev, "urb status: %d\n", urb->status); urb->status = 0; goto resubmit; } gspca_dbg(gspca_dev, D_PACK, "packet l:%d\n", urb->actual_length); gspca_dev->sd_desc->pkt_scan(gspca_dev, urb->transfer_buffer, urb->actual_length); resubmit: if (!gspca_dev->streaming) return; /* resubmit the URB */ if (gspca_dev->cam.bulk_nurbs != 0) { st = usb_submit_urb(urb, GFP_ATOMIC); if (st < 0) pr_err("usb_submit_urb() ret %d\n", st); } } /* * add data to the current frame * * This function is called by the subdrivers at interrupt level. * * To build a frame, these ones must add * - one FIRST_PACKET * - 0 or many INTER_PACKETs * - one LAST_PACKET * DISCARD_PACKET invalidates the whole frame. */ void gspca_frame_add(struct gspca_dev *gspca_dev, enum gspca_packet_type packet_type, const u8 *data, int len) { struct gspca_buffer *buf; unsigned long flags; gspca_dbg(gspca_dev, D_PACK, "add t:%d l:%d\n", packet_type, len); spin_lock_irqsave(&gspca_dev->qlock, flags); buf = list_first_entry_or_null(&gspca_dev->buf_list, typeof(*buf), list); spin_unlock_irqrestore(&gspca_dev->qlock, flags); if (packet_type == FIRST_PACKET) { /* if there is no queued buffer, discard the whole frame */ if (!buf) { gspca_dev->last_packet_type = DISCARD_PACKET; gspca_dev->sequence++; return; } gspca_dev->image = vb2_plane_vaddr(&buf->vb.vb2_buf, 0); gspca_dev->image_len = 0; } else { switch (gspca_dev->last_packet_type) { case DISCARD_PACKET: if (packet_type == LAST_PACKET) { gspca_dev->last_packet_type = packet_type; gspca_dev->image = NULL; gspca_dev->image_len = 0; } return; case LAST_PACKET: return; } } /* append the packet to the frame buffer */ if (len > 0) { if (gspca_dev->image_len + len > PAGE_ALIGN(gspca_dev->pixfmt.sizeimage)) { gspca_err(gspca_dev, "frame overflow %d > %d\n", gspca_dev->image_len + len, PAGE_ALIGN(gspca_dev->pixfmt.sizeimage)); packet_type = DISCARD_PACKET; } else { /* !! image is NULL only when last pkt is LAST or DISCARD if (gspca_dev->image == NULL) { pr_err("gspca_frame_add() image == NULL\n"); return; } */ memcpy(gspca_dev->image + gspca_dev->image_len, data, len); gspca_dev->image_len += len; } } gspca_dev->last_packet_type = packet_type; /* if last packet, invalidate packet concatenation until * next first packet, wake up the application and advance * in the queue */ if (packet_type == LAST_PACKET) { if (gspca_dev->image_len > gspca_dev->pixfmt.sizeimage) gspca_dev->image_len = gspca_dev->pixfmt.sizeimage; spin_lock_irqsave(&gspca_dev->qlock, flags); list_del(&buf->list); spin_unlock_irqrestore(&gspca_dev->qlock, flags); buf->vb.vb2_buf.timestamp = ktime_get_ns(); vb2_set_plane_payload(&buf->vb.vb2_buf, 0, gspca_dev->image_len); buf->vb.sequence = gspca_dev->sequence++; buf->vb.field = V4L2_FIELD_NONE; gspca_dbg(gspca_dev, D_FRAM, "frame complete len:%d\n", gspca_dev->image_len); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_DONE); gspca_dev->image = NULL; gspca_dev->image_len = 0; } } EXPORT_SYMBOL(gspca_frame_add); static void destroy_urbs(struct gspca_dev *gspca_dev) { struct urb *urb; unsigned int i; gspca_dbg(gspca_dev, D_STREAM, "kill transfer\n"); /* Killing all URBs guarantee that no URB completion * handler is running. Therefore, there shouldn't * be anyone trying to access gspca_dev->urb[i] */ for (i = 0; i < MAX_NURBS; i++) usb_kill_urb(gspca_dev->urb[i]); gspca_dbg(gspca_dev, D_STREAM, "releasing urbs\n"); for (i = 0; i < MAX_NURBS; i++) { urb = gspca_dev->urb[i]; if (!urb) continue; gspca_dev->urb[i] = NULL; usb_free_coherent(gspca_dev->dev, urb->transfer_buffer_length, urb->transfer_buffer, urb->transfer_dma); usb_free_urb(urb); } } static int gspca_set_alt0(struct gspca_dev *gspca_dev) { int ret; if (gspca_dev->alt == 0) return 0; ret = usb_set_interface(gspca_dev->dev, gspca_dev->iface, 0); if (ret < 0) pr_err("set alt 0 err %d\n", ret); return ret; } /* * look for an input transfer endpoint in an alternate setting. * * If xfer_ep is invalid, return the first valid ep found, otherwise * look for exactly the ep with address equal to xfer_ep. */ static struct usb_host_endpoint *alt_xfer(struct usb_host_interface *alt, int xfer, int xfer_ep) { struct usb_host_endpoint *ep; int i, attr; for (i = 0; i < alt->desc.bNumEndpoints; i++) { ep = &alt->endpoint[i]; attr = ep->desc.bmAttributes & USB_ENDPOINT_XFERTYPE_MASK; if (attr == xfer && ep->desc.wMaxPacketSize != 0 && usb_endpoint_dir_in(&ep->desc) && (xfer_ep < 0 || ep->desc.bEndpointAddress == xfer_ep)) return ep; } return NULL; } /* compute the minimum bandwidth for the current transfer */ static u32 which_bandwidth(struct gspca_dev *gspca_dev) { u32 bandwidth; /* get the (max) image size */ bandwidth = gspca_dev->pixfmt.sizeimage; /* if the image is compressed, estimate its mean size */ if (!gspca_dev->cam.needs_full_bandwidth && bandwidth < gspca_dev->pixfmt.width * gspca_dev->pixfmt.height) bandwidth = bandwidth * 3 / 8; /* 0.375 */ /* estimate the frame rate */ if (gspca_dev->sd_desc->get_streamparm) { struct v4l2_streamparm parm; gspca_dev->sd_desc->get_streamparm(gspca_dev, &parm); bandwidth *= parm.parm.capture.timeperframe.denominator; bandwidth /= parm.parm.capture.timeperframe.numerator; } else { /* don't hope more than 15 fps with USB 1.1 and * image resolution >= 640x480 */ if (gspca_dev->pixfmt.width >= 640 && gspca_dev->dev->speed == USB_SPEED_FULL) bandwidth *= 15; /* 15 fps */ else bandwidth *= 30; /* 30 fps */ } gspca_dbg(gspca_dev, D_STREAM, "min bandwidth: %d\n", bandwidth); return bandwidth; } /* endpoint table */ #define MAX_ALT 16 struct ep_tb_s { u32 alt; u32 bandwidth; }; /* * build the table of the endpoints * and compute the minimum bandwidth for the image transfer */ static int build_isoc_ep_tb(struct gspca_dev *gspca_dev, struct usb_interface *intf, struct ep_tb_s *ep_tb) { struct usb_host_endpoint *ep; int i, j, nbalt, psize, found; u32 bandwidth, last_bw; nbalt = intf->num_altsetting; if (nbalt > MAX_ALT) nbalt = MAX_ALT; /* fixme: should warn */ /* build the endpoint table */ i = 0; last_bw = 0; for (;;) { ep_tb->bandwidth = 2000 * 2000 * 120; found = 0; for (j = 0; j < nbalt; j++) { ep = alt_xfer(&intf->altsetting[j], USB_ENDPOINT_XFER_ISOC, gspca_dev->xfer_ep); if (ep == NULL) continue; if (ep->desc.bInterval == 0) { pr_err("alt %d iso endp with 0 interval\n", j); continue; } psize = le16_to_cpu(ep->desc.wMaxPacketSize); psize = (psize & 0x07ff) * (1 + ((psize >> 11) & 3)); bandwidth = psize * 1000; if (gspca_dev->dev->speed == USB_SPEED_HIGH || gspca_dev->dev->speed >= USB_SPEED_SUPER) bandwidth *= 8; bandwidth /= 1 << (ep->desc.bInterval - 1); if (bandwidth <= last_bw) continue; if (bandwidth < ep_tb->bandwidth) { ep_tb->bandwidth = bandwidth; ep_tb->alt = j; found = 1; } } if (!found) break; gspca_dbg(gspca_dev, D_STREAM, "alt %d bandwidth %d\n", ep_tb->alt, ep_tb->bandwidth); last_bw = ep_tb->bandwidth; i++; ep_tb++; } /* * If the camera: * has a usb audio class interface (a built in usb mic); and * is a usb 1 full speed device; and * uses the max full speed iso bandwidth; and * and has more than 1 alt setting * then skip the highest alt setting to spare bandwidth for the mic */ if (gspca_dev->audio && gspca_dev->dev->speed == USB_SPEED_FULL && last_bw >= 1000000 && i > 1) { gspca_dbg(gspca_dev, D_STREAM, "dev has usb audio, skipping highest alt\n"); i--; ep_tb--; } /* get the requested bandwidth and start at the highest atlsetting */ bandwidth = which_bandwidth(gspca_dev); ep_tb--; while (i > 1) { ep_tb--; if (ep_tb->bandwidth < bandwidth) break; i--; } return i; } /* * create the URBs for image transfer */ static int create_urbs(struct gspca_dev *gspca_dev, struct usb_host_endpoint *ep) { struct urb *urb; int n, nurbs, i, psize, npkt, bsize; /* calculate the packet size and the number of packets */ psize = le16_to_cpu(ep->desc.wMaxPacketSize); if (!gspca_dev->cam.bulk) { /* isoc */ /* See paragraph 5.9 / table 5-11 of the usb 2.0 spec. */ if (gspca_dev->pkt_size == 0) psize = (psize & 0x07ff) * (1 + ((psize >> 11) & 3)); else psize = gspca_dev->pkt_size; npkt = gspca_dev->cam.npkt; if (npkt == 0) npkt = 32; /* default value */ bsize = psize * npkt; gspca_dbg(gspca_dev, D_STREAM, "isoc %d pkts size %d = bsize:%d\n", npkt, psize, bsize); nurbs = DEF_NURBS; } else { /* bulk */ npkt = 0; bsize = gspca_dev->cam.bulk_size; if (bsize == 0) bsize = psize; gspca_dbg(gspca_dev, D_STREAM, "bulk bsize:%d\n", bsize); if (gspca_dev->cam.bulk_nurbs != 0) nurbs = gspca_dev->cam.bulk_nurbs; else nurbs = 1; } for (n = 0; n < nurbs; n++) { urb = usb_alloc_urb(npkt, GFP_KERNEL); if (!urb) return -ENOMEM; gspca_dev->urb[n] = urb; urb->transfer_buffer = usb_alloc_coherent(gspca_dev->dev, bsize, GFP_KERNEL, &urb->transfer_dma); if (urb->transfer_buffer == NULL) { pr_err("usb_alloc_coherent failed\n"); return -ENOMEM; } urb->dev = gspca_dev->dev; urb->context = gspca_dev; urb->transfer_buffer_length = bsize; if (npkt != 0) { /* ISOC */ urb->pipe = usb_rcvisocpipe(gspca_dev->dev, ep->desc.bEndpointAddress); urb->transfer_flags = URB_ISO_ASAP | URB_NO_TRANSFER_DMA_MAP; urb->interval = 1 << (ep->desc.bInterval - 1); urb->complete = isoc_irq; urb->number_of_packets = npkt; for (i = 0; i < npkt; i++) { urb->iso_frame_desc[i].length = psize; urb->iso_frame_desc[i].offset = psize * i; } } else { /* bulk */ urb->pipe = usb_rcvbulkpipe(gspca_dev->dev, ep->desc.bEndpointAddress); urb->transfer_flags = URB_NO_TRANSFER_DMA_MAP; urb->complete = bulk_irq; } } return 0; } /* Note: both the queue and the usb locks should be held when calling this */ static void gspca_stream_off(struct gspca_dev *gspca_dev) { gspca_dev->streaming = false; gspca_dev->usb_err = 0; if (gspca_dev->sd_desc->stopN) gspca_dev->sd_desc->stopN(gspca_dev); destroy_urbs(gspca_dev); gspca_input_destroy_urb(gspca_dev); gspca_set_alt0(gspca_dev); if (gspca_dev->present) gspca_input_create_urb(gspca_dev); if (gspca_dev->sd_desc->stop0) gspca_dev->sd_desc->stop0(gspca_dev); gspca_dbg(gspca_dev, D_STREAM, "stream off OK\n"); } /* * start the USB transfer */ static int gspca_init_transfer(struct gspca_dev *gspca_dev) { struct usb_interface *intf; struct usb_host_endpoint *ep; struct urb *urb; struct ep_tb_s ep_tb[MAX_ALT]; int n, ret, xfer, alt, alt_idx; /* reset the streaming variables */ gspca_dev->image = NULL; gspca_dev->image_len = 0; gspca_dev->last_packet_type = DISCARD_PACKET; gspca_dev->usb_err = 0; /* do the specific subdriver stuff before endpoint selection */ intf = usb_ifnum_to_if(gspca_dev->dev, gspca_dev->iface); gspca_dev->alt = gspca_dev->cam.bulk ? intf->num_altsetting : 0; if (gspca_dev->sd_desc->isoc_init) { ret = gspca_dev->sd_desc->isoc_init(gspca_dev); if (ret < 0) return ret; } xfer = gspca_dev->cam.bulk ? USB_ENDPOINT_XFER_BULK : USB_ENDPOINT_XFER_ISOC; /* if bulk or the subdriver forced an altsetting, get the endpoint */ if (gspca_dev->alt != 0) { gspca_dev->alt--; /* (previous version compatibility) */ ep = alt_xfer(&intf->altsetting[gspca_dev->alt], xfer, gspca_dev->xfer_ep); if (ep == NULL) { pr_err("bad altsetting %d\n", gspca_dev->alt); return -EIO; } ep_tb[0].alt = gspca_dev->alt; alt_idx = 1; } else { /* else, compute the minimum bandwidth * and build the endpoint table */ alt_idx = build_isoc_ep_tb(gspca_dev, intf, ep_tb); if (alt_idx <= 0) { pr_err("no transfer endpoint found\n"); return -EIO; } } /* set the highest alternate setting and * loop until urb submit succeeds */ gspca_input_destroy_urb(gspca_dev); gspca_dev->alt = ep_tb[--alt_idx].alt; alt = -1; for (;;) { if (alt != gspca_dev->alt) { alt = gspca_dev->alt; if (intf->num_altsetting > 1) { ret = usb_set_interface(gspca_dev->dev, gspca_dev->iface, alt); if (ret < 0) { if (ret == -ENOSPC) goto retry; /*fixme: ugly*/ pr_err("set alt %d err %d\n", alt, ret); goto out; } } } if (!gspca_dev->cam.no_urb_create) { gspca_dbg(gspca_dev, D_STREAM, "init transfer alt %d\n", alt); ret = create_urbs(gspca_dev, alt_xfer(&intf->altsetting[alt], xfer, gspca_dev->xfer_ep)); if (ret < 0) { destroy_urbs(gspca_dev); goto out; } } /* clear the bulk endpoint */ if (gspca_dev->cam.bulk) usb_clear_halt(gspca_dev->dev, gspca_dev->urb[0]->pipe); /* start the cam */ ret = gspca_dev->sd_desc->start(gspca_dev); if (ret < 0) { destroy_urbs(gspca_dev); goto out; } v4l2_ctrl_handler_setup(gspca_dev->vdev.ctrl_handler); gspca_dev->streaming = true; /* some bulk transfers are started by the subdriver */ if (gspca_dev->cam.bulk && gspca_dev->cam.bulk_nurbs == 0) break; /* submit the URBs */ for (n = 0; n < MAX_NURBS; n++) { urb = gspca_dev->urb[n]; if (urb == NULL) break; ret = usb_submit_urb(urb, GFP_KERNEL); if (ret < 0) break; } if (ret >= 0) break; /* transfer is started */ /* something when wrong * stop the webcam and free the transfer resources */ gspca_stream_off(gspca_dev); if (ret != -ENOSPC) { pr_err("usb_submit_urb alt %d err %d\n", gspca_dev->alt, ret); goto out; } /* the bandwidth is not wide enough * negotiate or try a lower alternate setting */ retry: gspca_err(gspca_dev, "alt %d - bandwidth not wide enough, trying again\n", alt); msleep(20); /* wait for kill complete */ if (gspca_dev->sd_desc->isoc_nego) { ret = gspca_dev->sd_desc->isoc_nego(gspca_dev); if (ret < 0) goto out; } else { if (alt_idx <= 0) { pr_err("no transfer endpoint found\n"); ret = -EIO; goto out; } gspca_dev->alt = ep_tb[--alt_idx].alt; } } out: gspca_input_create_urb(gspca_dev); return ret; } static void gspca_set_default_mode(struct gspca_dev *gspca_dev) { int i; i = gspca_dev->cam.nmodes - 1; /* take the highest mode */ gspca_dev->curr_mode = i; gspca_dev->pixfmt = gspca_dev->cam.cam_mode[i]; /* does nothing if ctrl_handler == NULL */ v4l2_ctrl_handler_setup(gspca_dev->vdev.ctrl_handler); } static int wxh_to_mode(struct gspca_dev *gspca_dev, int width, int height, u32 pixelformat) { int i; for (i = 0; i < gspca_dev->cam.nmodes; i++) { if (width == gspca_dev->cam.cam_mode[i].width && height == gspca_dev->cam.cam_mode[i].height && pixelformat == gspca_dev->cam.cam_mode[i].pixelformat) return i; } return -EINVAL; } static int wxh_to_nearest_mode(struct gspca_dev *gspca_dev, int width, int height, u32 pixelformat) { int i; for (i = gspca_dev->cam.nmodes; --i >= 0; ) { if (width >= gspca_dev->cam.cam_mode[i].width && height >= gspca_dev->cam.cam_mode[i].height && pixelformat == gspca_dev->cam.cam_mode[i].pixelformat) return i; } for (i = gspca_dev->cam.nmodes; --i > 0; ) { if (width >= gspca_dev->cam.cam_mode[i].width && height >= gspca_dev->cam.cam_mode[i].height) break; } return i; } /* * search a mode with the right pixel format */ static int gspca_get_mode(struct gspca_dev *gspca_dev, int mode, int pixfmt) { int modeU, modeD; modeU = modeD = mode; while ((modeU < gspca_dev->cam.nmodes) || modeD >= 0) { if (--modeD >= 0) { if (gspca_dev->cam.cam_mode[modeD].pixelformat == pixfmt) return modeD; } if (++modeU < gspca_dev->cam.nmodes) { if (gspca_dev->cam.cam_mode[modeU].pixelformat == pixfmt) return modeU; } } return -EINVAL; } #ifdef CONFIG_VIDEO_ADV_DEBUG static int vidioc_g_chip_info(struct file *file, void *priv, struct v4l2_dbg_chip_info *chip) { struct gspca_dev *gspca_dev = video_drvdata(file); gspca_dev->usb_err = 0; if (gspca_dev->sd_desc->get_chip_info) return gspca_dev->sd_desc->get_chip_info(gspca_dev, chip); return chip->match.addr ? -EINVAL : 0; } static int vidioc_g_register(struct file *file, void *priv, struct v4l2_dbg_register *reg) { struct gspca_dev *gspca_dev = video_drvdata(file); gspca_dev->usb_err = 0; return gspca_dev->sd_desc->get_register(gspca_dev, reg); } static int vidioc_s_register(struct file *file, void *priv, const struct v4l2_dbg_register *reg) { struct gspca_dev *gspca_dev = video_drvdata(file); gspca_dev->usb_err = 0; return gspca_dev->sd_desc->set_register(gspca_dev, reg); } #endif static int vidioc_enum_fmt_vid_cap(struct file *file, void *priv, struct v4l2_fmtdesc *fmtdesc) { struct gspca_dev *gspca_dev = video_drvdata(file); int i, j, index; __u32 fmt_tb[8]; /* give an index to each format */ index = 0; for (i = gspca_dev->cam.nmodes; --i >= 0; ) { fmt_tb[index] = gspca_dev->cam.cam_mode[i].pixelformat; j = 0; for (;;) { if (fmt_tb[j] == fmt_tb[index]) break; j++; } if (j == index) { if (fmtdesc->index == index) break; /* new format */ index++; if (index >= ARRAY_SIZE(fmt_tb)) return -EINVAL; } } if (i < 0) return -EINVAL; /* no more format */ fmtdesc->pixelformat = fmt_tb[index]; return 0; } static int vidioc_g_fmt_vid_cap(struct file *file, void *_priv, struct v4l2_format *fmt) { struct gspca_dev *gspca_dev = video_drvdata(file); u32 priv = fmt->fmt.pix.priv; fmt->fmt.pix = gspca_dev->pixfmt; /* some drivers use priv internally, so keep the original value */ fmt->fmt.pix.priv = priv; return 0; } static int try_fmt_vid_cap(struct gspca_dev *gspca_dev, struct v4l2_format *fmt) { int w, h, mode, mode2; w = fmt->fmt.pix.width; h = fmt->fmt.pix.height; PDEBUG_MODE(gspca_dev, D_CONF, "try fmt cap", fmt->fmt.pix.pixelformat, w, h); /* search the nearest mode for width and height */ mode = wxh_to_nearest_mode(gspca_dev, w, h, fmt->fmt.pix.pixelformat); /* OK if right palette */ if (gspca_dev->cam.cam_mode[mode].pixelformat != fmt->fmt.pix.pixelformat) { /* else, search the closest mode with the same pixel format */ mode2 = gspca_get_mode(gspca_dev, mode, fmt->fmt.pix.pixelformat); if (mode2 >= 0) mode = mode2; } fmt->fmt.pix = gspca_dev->cam.cam_mode[mode]; if (gspca_dev->sd_desc->try_fmt) { /* pass original resolution to subdriver try_fmt */ fmt->fmt.pix.width = w; fmt->fmt.pix.height = h; gspca_dev->sd_desc->try_fmt(gspca_dev, fmt); } return mode; /* used when s_fmt */ } static int vidioc_try_fmt_vid_cap(struct file *file, void *_priv, struct v4l2_format *fmt) { struct gspca_dev *gspca_dev = video_drvdata(file); u32 priv = fmt->fmt.pix.priv; if (try_fmt_vid_cap(gspca_dev, fmt) < 0) return -EINVAL; /* some drivers use priv internally, so keep the original value */ fmt->fmt.pix.priv = priv; return 0; } static int vidioc_s_fmt_vid_cap(struct file *file, void *_priv, struct v4l2_format *fmt) { struct gspca_dev *gspca_dev = video_drvdata(file); u32 priv = fmt->fmt.pix.priv; int mode; if (vb2_is_busy(&gspca_dev->queue)) return -EBUSY; mode = try_fmt_vid_cap(gspca_dev, fmt); if (mode < 0) return -EINVAL; gspca_dev->curr_mode = mode; if (gspca_dev->sd_desc->try_fmt) /* subdriver try_fmt can modify format parameters */ gspca_dev->pixfmt = fmt->fmt.pix; else gspca_dev->pixfmt = gspca_dev->cam.cam_mode[mode]; /* some drivers use priv internally, so keep the original value */ fmt->fmt.pix.priv = priv; return 0; } static int vidioc_enum_framesizes(struct file *file, void *priv, struct v4l2_frmsizeenum *fsize) { struct gspca_dev *gspca_dev = video_drvdata(file); int i; __u32 index = 0; if (gspca_dev->sd_desc->enum_framesizes) return gspca_dev->sd_desc->enum_framesizes(gspca_dev, fsize); for (i = 0; i < gspca_dev->cam.nmodes; i++) { if (fsize->pixel_format != gspca_dev->cam.cam_mode[i].pixelformat) continue; if (fsize->index == index) { fsize->type = V4L2_FRMSIZE_TYPE_DISCRETE; fsize->discrete.width = gspca_dev->cam.cam_mode[i].width; fsize->discrete.height = gspca_dev->cam.cam_mode[i].height; return 0; } index++; } return -EINVAL; } static int vidioc_enum_frameintervals(struct file *filp, void *priv, struct v4l2_frmivalenum *fival) { struct gspca_dev *gspca_dev = video_drvdata(filp); int mode; __u32 i; mode = wxh_to_mode(gspca_dev, fival->width, fival->height, fival->pixel_format); if (mode < 0) return -EINVAL; if (gspca_dev->cam.mode_framerates == NULL || gspca_dev->cam.mode_framerates[mode].nrates == 0) return -EINVAL; if (fival->pixel_format != gspca_dev->cam.cam_mode[mode].pixelformat) return -EINVAL; for (i = 0; i < gspca_dev->cam.mode_framerates[mode].nrates; i++) { if (fival->index == i) { fival->type = V4L2_FRMIVAL_TYPE_DISCRETE; fival->discrete.numerator = 1; fival->discrete.denominator = gspca_dev->cam.mode_framerates[mode].rates[i]; return 0; } } return -EINVAL; } static void gspca_release(struct v4l2_device *v4l2_device) { struct gspca_dev *gspca_dev = container_of(v4l2_device, struct gspca_dev, v4l2_dev); v4l2_ctrl_handler_free(gspca_dev->vdev.ctrl_handler); v4l2_device_unregister(&gspca_dev->v4l2_dev); kfree(gspca_dev->usb_buf); kfree(gspca_dev); } static int vidioc_querycap(struct file *file, void *priv, struct v4l2_capability *cap) { struct gspca_dev *gspca_dev = video_drvdata(file); strscpy((char *)cap->driver, gspca_dev->sd_desc->name, sizeof(cap->driver)); if (gspca_dev->dev->product != NULL) { strscpy((char *)cap->card, gspca_dev->dev->product, sizeof(cap->card)); } else { snprintf((char *) cap->card, sizeof cap->card, "USB Camera (%04x:%04x)", le16_to_cpu(gspca_dev->dev->descriptor.idVendor), le16_to_cpu(gspca_dev->dev->descriptor.idProduct)); } usb_make_path(gspca_dev->dev, (char *) cap->bus_info, sizeof(cap->bus_info)); return 0; } static int vidioc_enum_input(struct file *file, void *priv, struct v4l2_input *input) { struct gspca_dev *gspca_dev = video_drvdata(file); if (input->index != 0) return -EINVAL; input->type = V4L2_INPUT_TYPE_CAMERA; input->status = gspca_dev->cam.input_flags; strscpy(input->name, gspca_dev->sd_desc->name, sizeof input->name); return 0; } static int vidioc_g_input(struct file *file, void *priv, unsigned int *i) { *i = 0; return 0; } static int vidioc_s_input(struct file *file, void *priv, unsigned int i) { if (i > 0) return -EINVAL; return 0; } static int vidioc_g_jpegcomp(struct file *file, void *priv, struct v4l2_jpegcompression *jpegcomp) { struct gspca_dev *gspca_dev = video_drvdata(file); gspca_dev->usb_err = 0; return gspca_dev->sd_desc->get_jcomp(gspca_dev, jpegcomp); } static int vidioc_s_jpegcomp(struct file *file, void *priv, const struct v4l2_jpegcompression *jpegcomp) { struct gspca_dev *gspca_dev = video_drvdata(file); gspca_dev->usb_err = 0; return gspca_dev->sd_desc->set_jcomp(gspca_dev, jpegcomp); } static int vidioc_g_parm(struct file *filp, void *priv, struct v4l2_streamparm *parm) { struct gspca_dev *gspca_dev = video_drvdata(filp); parm->parm.capture.readbuffers = gspca_dev->queue.min_queued_buffers; if (!gspca_dev->sd_desc->get_streamparm) return 0; parm->parm.capture.capability = V4L2_CAP_TIMEPERFRAME; gspca_dev->usb_err = 0; gspca_dev->sd_desc->get_streamparm(gspca_dev, parm); return gspca_dev->usb_err; } static int vidioc_s_parm(struct file *filp, void *priv, struct v4l2_streamparm *parm) { struct gspca_dev *gspca_dev = video_drvdata(filp); parm->parm.capture.readbuffers = gspca_dev->queue.min_queued_buffers; if (!gspca_dev->sd_desc->set_streamparm) { parm->parm.capture.capability = 0; return 0; } parm->parm.capture.capability = V4L2_CAP_TIMEPERFRAME; gspca_dev->usb_err = 0; gspca_dev->sd_desc->set_streamparm(gspca_dev, parm); return gspca_dev->usb_err; } static int gspca_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers, unsigned int *nplanes, unsigned int sizes[], struct device *alloc_devs[]) { struct gspca_dev *gspca_dev = vb2_get_drv_priv(vq); unsigned int size = PAGE_ALIGN(gspca_dev->pixfmt.sizeimage); if (*nplanes) return sizes[0] < size ? -EINVAL : 0; *nplanes = 1; sizes[0] = size; return 0; } static int gspca_buffer_prepare(struct vb2_buffer *vb) { struct gspca_dev *gspca_dev = vb2_get_drv_priv(vb->vb2_queue); unsigned long size = PAGE_ALIGN(gspca_dev->pixfmt.sizeimage); if (vb2_plane_size(vb, 0) < size) { gspca_err(gspca_dev, "buffer too small (%lu < %lu)\n", vb2_plane_size(vb, 0), size); return -EINVAL; } return 0; } static void gspca_buffer_finish(struct vb2_buffer *vb) { struct gspca_dev *gspca_dev = vb2_get_drv_priv(vb->vb2_queue); if (!gspca_dev->sd_desc->dq_callback) return; gspca_dev->usb_err = 0; if (gspca_dev->present) gspca_dev->sd_desc->dq_callback(gspca_dev); } static void gspca_buffer_queue(struct vb2_buffer *vb) { struct gspca_dev *gspca_dev = vb2_get_drv_priv(vb->vb2_queue); struct gspca_buffer *buf = to_gspca_buffer(vb); unsigned long flags; spin_lock_irqsave(&gspca_dev->qlock, flags); list_add_tail(&buf->list, &gspca_dev->buf_list); spin_unlock_irqrestore(&gspca_dev->qlock, flags); } static void gspca_return_all_buffers(struct gspca_dev *gspca_dev, enum vb2_buffer_state state) { struct gspca_buffer *buf, *node; unsigned long flags; spin_lock_irqsave(&gspca_dev->qlock, flags); list_for_each_entry_safe(buf, node, &gspca_dev->buf_list, list) { vb2_buffer_done(&buf->vb.vb2_buf, state); list_del(&buf->list); } spin_unlock_irqrestore(&gspca_dev->qlock, flags); } static int gspca_start_streaming(struct vb2_queue *vq, unsigned int count) { struct gspca_dev *gspca_dev = vb2_get_drv_priv(vq); int ret; gspca_dev->sequence = 0; ret = gspca_init_transfer(gspca_dev); if (ret) gspca_return_all_buffers(gspca_dev, VB2_BUF_STATE_QUEUED); return ret; } static void gspca_stop_streaming(struct vb2_queue *vq) { struct gspca_dev *gspca_dev = vb2_get_drv_priv(vq); gspca_stream_off(gspca_dev); /* Release all active buffers */ gspca_return_all_buffers(gspca_dev, VB2_BUF_STATE_ERROR); } static const struct vb2_ops gspca_qops = { .queue_setup = gspca_queue_setup, .buf_prepare = gspca_buffer_prepare, .buf_finish = gspca_buffer_finish, .buf_queue = gspca_buffer_queue, .start_streaming = gspca_start_streaming, .stop_streaming = gspca_stop_streaming, }; static const struct v4l2_file_operations dev_fops = { .owner = THIS_MODULE, .open = v4l2_fh_open, .release = vb2_fop_release, .unlocked_ioctl = video_ioctl2, .read = vb2_fop_read, .mmap = vb2_fop_mmap, .poll = vb2_fop_poll, }; static const struct v4l2_ioctl_ops dev_ioctl_ops = { .vidioc_querycap = vidioc_querycap, .vidioc_enum_fmt_vid_cap = vidioc_enum_fmt_vid_cap, .vidioc_try_fmt_vid_cap = vidioc_try_fmt_vid_cap, .vidioc_g_fmt_vid_cap = vidioc_g_fmt_vid_cap, .vidioc_s_fmt_vid_cap = vidioc_s_fmt_vid_cap, .vidioc_enum_input = vidioc_enum_input, .vidioc_g_input = vidioc_g_input, .vidioc_s_input = vidioc_s_input, .vidioc_g_jpegcomp = vidioc_g_jpegcomp, .vidioc_s_jpegcomp = vidioc_s_jpegcomp, .vidioc_g_parm = vidioc_g_parm, .vidioc_s_parm = vidioc_s_parm, .vidioc_enum_framesizes = vidioc_enum_framesizes, .vidioc_enum_frameintervals = vidioc_enum_frameintervals, .vidioc_reqbufs = vb2_ioctl_reqbufs, .vidioc_create_bufs = vb2_ioctl_create_bufs, .vidioc_querybuf = vb2_ioctl_querybuf, .vidioc_qbuf = vb2_ioctl_qbuf, .vidioc_dqbuf = vb2_ioctl_dqbuf, .vidioc_expbuf = vb2_ioctl_expbuf, .vidioc_streamon = vb2_ioctl_streamon, .vidioc_streamoff = vb2_ioctl_streamoff, #ifdef CONFIG_VIDEO_ADV_DEBUG .vidioc_g_chip_info = vidioc_g_chip_info, .vidioc_g_register = vidioc_g_register, .vidioc_s_register = vidioc_s_register, #endif .vidioc_subscribe_event = v4l2_ctrl_subscribe_event, .vidioc_unsubscribe_event = v4l2_event_unsubscribe, }; static const struct video_device gspca_template = { .name = "gspca main driver", .fops = &dev_fops, .ioctl_ops = &dev_ioctl_ops, .release = video_device_release_empty, /* We use v4l2_dev.release */ }; /* * probe and create a new gspca device * * This function must be called by the sub-driver when it is * called for probing a new device. */ int gspca_dev_probe2(struct usb_interface *intf, const struct usb_device_id *id, const struct sd_desc *sd_desc, int dev_size, struct module *module) { struct gspca_dev *gspca_dev; struct usb_device *dev = interface_to_usbdev(intf); struct vb2_queue *q; int ret; pr_info("%s-" GSPCA_VERSION " probing %04x:%04x\n", sd_desc->name, id->idVendor, id->idProduct); /* create the device */ if (dev_size < sizeof *gspca_dev) dev_size = sizeof *gspca_dev; gspca_dev = kzalloc(dev_size, GFP_KERNEL); if (!gspca_dev) { pr_err("couldn't kzalloc gspca struct\n"); return -ENOMEM; } gspca_dev->usb_buf = kzalloc(USB_BUF_SZ, GFP_KERNEL); if (!gspca_dev->usb_buf) { pr_err("out of memory\n"); ret = -ENOMEM; goto out; } gspca_dev->dev = dev; gspca_dev->iface = intf->cur_altsetting->desc.bInterfaceNumber; gspca_dev->xfer_ep = -1; /* check if any audio device */ if (dev->actconfig->desc.bNumInterfaces != 1) { int i; struct usb_interface *intf2; for (i = 0; i < dev->actconfig->desc.bNumInterfaces; i++) { intf2 = dev->actconfig->interface[i]; if (intf2 != NULL && intf2->altsetting != NULL && intf2->altsetting->desc.bInterfaceClass == USB_CLASS_AUDIO) { gspca_dev->audio = 1; break; } } } gspca_dev->v4l2_dev.release = gspca_release; ret = v4l2_device_register(&intf->dev, &gspca_dev->v4l2_dev); if (ret) goto out; gspca_dev->present = true; gspca_dev->sd_desc = sd_desc; gspca_dev->empty_packet = -1; /* don't check the empty packets */ gspca_dev->vdev = gspca_template; gspca_dev->vdev.v4l2_dev = &gspca_dev->v4l2_dev; gspca_dev->vdev.device_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_STREAMING | V4L2_CAP_READWRITE; video_set_drvdata(&gspca_dev->vdev, gspca_dev); gspca_dev->module = module; mutex_init(&gspca_dev->usb_lock); gspca_dev->vdev.lock = &gspca_dev->usb_lock; init_waitqueue_head(&gspca_dev->wq); /* Initialize the vb2 queue */ q = &gspca_dev->queue; q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE; q->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF | VB2_READ; q->drv_priv = gspca_dev; q->buf_struct_size = sizeof(struct gspca_buffer); q->ops = &gspca_qops; q->mem_ops = &vb2_vmalloc_memops; q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; q->min_queued_buffers = 2; q->lock = &gspca_dev->usb_lock; ret = vb2_queue_init(q); if (ret) goto out; gspca_dev->vdev.queue = q; INIT_LIST_HEAD(&gspca_dev->buf_list); spin_lock_init(&gspca_dev->qlock); /* configure the subdriver and initialize the USB device */ ret = sd_desc->config(gspca_dev, id); if (ret < 0) goto out; ret = sd_desc->init(gspca_dev); if (ret < 0) goto out; if (sd_desc->init_controls) ret = sd_desc->init_controls(gspca_dev); if (ret < 0) goto out; gspca_set_default_mode(gspca_dev); ret = gspca_input_connect(gspca_dev); if (ret) goto out; #ifdef CONFIG_VIDEO_ADV_DEBUG if (!gspca_dev->sd_desc->get_register) v4l2_disable_ioctl(&gspca_dev->vdev, VIDIOC_DBG_G_REGISTER); if (!gspca_dev->sd_desc->set_register) v4l2_disable_ioctl(&gspca_dev->vdev, VIDIOC_DBG_S_REGISTER); #endif if (!gspca_dev->sd_desc->get_jcomp) v4l2_disable_ioctl(&gspca_dev->vdev, VIDIOC_G_JPEGCOMP); if (!gspca_dev->sd_desc->set_jcomp) v4l2_disable_ioctl(&gspca_dev->vdev, VIDIOC_S_JPEGCOMP); /* init video stuff */ ret = video_register_device(&gspca_dev->vdev, VFL_TYPE_VIDEO, -1); if (ret < 0) { pr_err("video_register_device err %d\n", ret); goto out; } usb_set_intfdata(intf, gspca_dev); gspca_dbg(gspca_dev, D_PROBE, "%s created\n", video_device_node_name(&gspca_dev->vdev)); gspca_input_create_urb(gspca_dev); return 0; out: #if IS_ENABLED(CONFIG_INPUT) if (gspca_dev->input_dev) input_unregister_device(gspca_dev->input_dev); #endif v4l2_ctrl_handler_free(gspca_dev->vdev.ctrl_handler); v4l2_device_unregister(&gspca_dev->v4l2_dev); if (sd_desc->probe_error) sd_desc->probe_error(gspca_dev); kfree(gspca_dev->usb_buf); kfree(gspca_dev); return ret; } EXPORT_SYMBOL(gspca_dev_probe2); /* same function as the previous one, but check the interface */ int gspca_dev_probe(struct usb_interface *intf, const struct usb_device_id *id, const struct sd_desc *sd_desc, int dev_size, struct module *module) { struct usb_device *dev = interface_to_usbdev(intf); /* we don't handle multi-config cameras */ if (dev->descriptor.bNumConfigurations != 1) { pr_err("%04x:%04x too many config\n", id->idVendor, id->idProduct); return -ENODEV; } /* the USB video interface must be the first one */ if (dev->actconfig->desc.bNumInterfaces != 1 && intf->cur_altsetting->desc.bInterfaceNumber != 0) return -ENODEV; return gspca_dev_probe2(intf, id, sd_desc, dev_size, module); } EXPORT_SYMBOL(gspca_dev_probe); /* * USB disconnection * * This function must be called by the sub-driver * when the device disconnects, after the specific resources are freed. */ void gspca_disconnect(struct usb_interface *intf) { struct gspca_dev *gspca_dev = usb_get_intfdata(intf); #if IS_ENABLED(CONFIG_INPUT) struct input_dev *input_dev; #endif gspca_dbg(gspca_dev, D_PROBE, "%s disconnect\n", video_device_node_name(&gspca_dev->vdev)); mutex_lock(&gspca_dev->usb_lock); gspca_dev->present = false; destroy_urbs(gspca_dev); gspca_input_destroy_urb(gspca_dev); vb2_queue_error(&gspca_dev->queue); #if IS_ENABLED(CONFIG_INPUT) input_dev = gspca_dev->input_dev; if (input_dev) { gspca_dev->input_dev = NULL; input_unregister_device(input_dev); } #endif v4l2_device_disconnect(&gspca_dev->v4l2_dev); video_unregister_device(&gspca_dev->vdev); mutex_unlock(&gspca_dev->usb_lock); /* (this will call gspca_release() immediately or on last close) */ v4l2_device_put(&gspca_dev->v4l2_dev); } EXPORT_SYMBOL(gspca_disconnect); #ifdef CONFIG_PM int gspca_suspend(struct usb_interface *intf, pm_message_t message) { struct gspca_dev *gspca_dev = usb_get_intfdata(intf); gspca_input_destroy_urb(gspca_dev); if (!vb2_start_streaming_called(&gspca_dev->queue)) return 0; mutex_lock(&gspca_dev->usb_lock); gspca_dev->frozen = 1; /* avoid urb error messages */ gspca_dev->usb_err = 0; if (gspca_dev->sd_desc->stopN) gspca_dev->sd_desc->stopN(gspca_dev); destroy_urbs(gspca_dev); gspca_set_alt0(gspca_dev); if (gspca_dev->sd_desc->stop0) gspca_dev->sd_desc->stop0(gspca_dev); mutex_unlock(&gspca_dev->usb_lock); return 0; } EXPORT_SYMBOL(gspca_suspend); int gspca_resume(struct usb_interface *intf) { struct gspca_dev *gspca_dev = usb_get_intfdata(intf); int streaming, ret = 0; mutex_lock(&gspca_dev->usb_lock); gspca_dev->frozen = 0; gspca_dev->usb_err = 0; gspca_dev->sd_desc->init(gspca_dev); /* * Most subdrivers send all ctrl values on sd_start and thus * only write to the device registers on s_ctrl when streaming -> * Clear streaming to avoid setting all ctrls twice. */ streaming = vb2_start_streaming_called(&gspca_dev->queue); if (streaming) ret = gspca_init_transfer(gspca_dev); else gspca_input_create_urb(gspca_dev); mutex_unlock(&gspca_dev->usb_lock); return ret; } EXPORT_SYMBOL(gspca_resume); #endif /* -- module insert / remove -- */ static int __init gspca_init(void) { pr_info("v" GSPCA_VERSION " registered\n"); return 0; } static void __exit gspca_exit(void) { } module_init(gspca_init); module_exit(gspca_exit); module_param_named(debug, gspca_debug, int, 0644); MODULE_PARM_DESC(debug, "1:probe 2:config 3:stream 4:frame 5:packet 6:usbi 7:usbo"); |
| 3 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * iptables module for DCCP protocol header matching * * (C) 2005 by Harald Welte <laforge@netfilter.org> */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <net/ip.h> #include <linux/dccp.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_dccp.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv6/ip6_tables.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_DESCRIPTION("Xtables: DCCP protocol packet match"); MODULE_ALIAS("ipt_dccp"); MODULE_ALIAS("ip6t_dccp"); #define DCCHECK(cond, option, flag, invflag) (!((flag) & (option)) \ || (!!((invflag) & (option)) ^ (cond))) static unsigned char *dccp_optbuf; static DEFINE_SPINLOCK(dccp_buflock); static inline bool dccp_find_option(u_int8_t option, const struct sk_buff *skb, unsigned int protoff, const struct dccp_hdr *dh, bool *hotdrop) { /* tcp.doff is only 4 bits, ie. max 15 * 4 bytes */ const unsigned char *op; unsigned int optoff = __dccp_hdr_len(dh); unsigned int optlen = dh->dccph_doff*4 - __dccp_hdr_len(dh); unsigned int i; if (dh->dccph_doff * 4 < __dccp_hdr_len(dh)) goto invalid; if (!optlen) return false; spin_lock_bh(&dccp_buflock); op = skb_header_pointer(skb, protoff + optoff, optlen, dccp_optbuf); if (op == NULL) { /* If we don't have the whole header, drop packet. */ goto partial; } for (i = 0; i < optlen; ) { if (op[i] == option) { spin_unlock_bh(&dccp_buflock); return true; } if (op[i] < 2) i++; else i += op[i+1]?:1; } spin_unlock_bh(&dccp_buflock); return false; partial: spin_unlock_bh(&dccp_buflock); invalid: *hotdrop = true; return false; } static inline bool match_types(const struct dccp_hdr *dh, u_int16_t typemask) { return typemask & (1 << dh->dccph_type); } static inline bool match_option(u_int8_t option, const struct sk_buff *skb, unsigned int protoff, const struct dccp_hdr *dh, bool *hotdrop) { return dccp_find_option(option, skb, protoff, dh, hotdrop); } static bool dccp_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_dccp_info *info = par->matchinfo; const struct dccp_hdr *dh; struct dccp_hdr _dh; if (par->fragoff != 0) return false; dh = skb_header_pointer(skb, par->thoff, sizeof(_dh), &_dh); if (dh == NULL) { par->hotdrop = true; return false; } return DCCHECK(ntohs(dh->dccph_sport) >= info->spts[0] && ntohs(dh->dccph_sport) <= info->spts[1], XT_DCCP_SRC_PORTS, info->flags, info->invflags) && DCCHECK(ntohs(dh->dccph_dport) >= info->dpts[0] && ntohs(dh->dccph_dport) <= info->dpts[1], XT_DCCP_DEST_PORTS, info->flags, info->invflags) && DCCHECK(match_types(dh, info->typemask), XT_DCCP_TYPE, info->flags, info->invflags) && DCCHECK(match_option(info->option, skb, par->thoff, dh, &par->hotdrop), XT_DCCP_OPTION, info->flags, info->invflags); } static int dccp_mt_check(const struct xt_mtchk_param *par) { const struct xt_dccp_info *info = par->matchinfo; if (info->flags & ~XT_DCCP_VALID_FLAGS) return -EINVAL; if (info->invflags & ~XT_DCCP_VALID_FLAGS) return -EINVAL; if (info->invflags & ~info->flags) return -EINVAL; return 0; } static struct xt_match dccp_mt_reg[] __read_mostly = { { .name = "dccp", .family = NFPROTO_IPV4, .checkentry = dccp_mt_check, .match = dccp_mt, .matchsize = sizeof(struct xt_dccp_info), .proto = IPPROTO_DCCP, .me = THIS_MODULE, }, { .name = "dccp", .family = NFPROTO_IPV6, .checkentry = dccp_mt_check, .match = dccp_mt, .matchsize = sizeof(struct xt_dccp_info), .proto = IPPROTO_DCCP, .me = THIS_MODULE, }, }; static int __init dccp_mt_init(void) { int ret; /* doff is 8 bits, so the maximum option size is (4*256). Don't put * this in BSS since DaveM is worried about locked TLB's for kernel * BSS. */ dccp_optbuf = kmalloc(256 * 4, GFP_KERNEL); if (!dccp_optbuf) return -ENOMEM; ret = xt_register_matches(dccp_mt_reg, ARRAY_SIZE(dccp_mt_reg)); if (ret) goto out_kfree; return ret; out_kfree: kfree(dccp_optbuf); return ret; } static void __exit dccp_mt_exit(void) { xt_unregister_matches(dccp_mt_reg, ARRAY_SIZE(dccp_mt_reg)); kfree(dccp_optbuf); } module_init(dccp_mt_init); module_exit(dccp_mt_exit); |
| 232 97 232 85 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM 9p #if !defined(_TRACE_9P_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_9P_H #include <linux/tracepoint.h> #define P9_MSG_T \ EM( P9_TLERROR, "P9_TLERROR" ) \ EM( P9_RLERROR, "P9_RLERROR" ) \ EM( P9_TSTATFS, "P9_TSTATFS" ) \ EM( P9_RSTATFS, "P9_RSTATFS" ) \ EM( P9_TLOPEN, "P9_TLOPEN" ) \ EM( P9_RLOPEN, "P9_RLOPEN" ) \ EM( P9_TLCREATE, "P9_TLCREATE" ) \ EM( P9_RLCREATE, "P9_RLCREATE" ) \ EM( P9_TSYMLINK, "P9_TSYMLINK" ) \ EM( P9_RSYMLINK, "P9_RSYMLINK" ) \ EM( P9_TMKNOD, "P9_TMKNOD" ) \ EM( P9_RMKNOD, "P9_RMKNOD" ) \ EM( P9_TRENAME, "P9_TRENAME" ) \ EM( P9_RRENAME, "P9_RRENAME" ) \ EM( P9_TREADLINK, "P9_TREADLINK" ) \ EM( P9_RREADLINK, "P9_RREADLINK" ) \ EM( P9_TGETATTR, "P9_TGETATTR" ) \ EM( P9_RGETATTR, "P9_RGETATTR" ) \ EM( P9_TSETATTR, "P9_TSETATTR" ) \ EM( P9_RSETATTR, "P9_RSETATTR" ) \ EM( P9_TXATTRWALK, "P9_TXATTRWALK" ) \ EM( P9_RXATTRWALK, "P9_RXATTRWALK" ) \ EM( P9_TXATTRCREATE, "P9_TXATTRCREATE" ) \ EM( P9_RXATTRCREATE, "P9_RXATTRCREATE" ) \ EM( P9_TREADDIR, "P9_TREADDIR" ) \ EM( P9_RREADDIR, "P9_RREADDIR" ) \ EM( P9_TFSYNC, "P9_TFSYNC" ) \ EM( P9_RFSYNC, "P9_RFSYNC" ) \ EM( P9_TLOCK, "P9_TLOCK" ) \ EM( P9_RLOCK, "P9_RLOCK" ) \ EM( P9_TGETLOCK, "P9_TGETLOCK" ) \ EM( P9_RGETLOCK, "P9_RGETLOCK" ) \ EM( P9_TLINK, "P9_TLINK" ) \ EM( P9_RLINK, "P9_RLINK" ) \ EM( P9_TMKDIR, "P9_TMKDIR" ) \ EM( P9_RMKDIR, "P9_RMKDIR" ) \ EM( P9_TRENAMEAT, "P9_TRENAMEAT" ) \ EM( P9_RRENAMEAT, "P9_RRENAMEAT" ) \ EM( P9_TUNLINKAT, "P9_TUNLINKAT" ) \ EM( P9_RUNLINKAT, "P9_RUNLINKAT" ) \ EM( P9_TVERSION, "P9_TVERSION" ) \ EM( P9_RVERSION, "P9_RVERSION" ) \ EM( P9_TAUTH, "P9_TAUTH" ) \ EM( P9_RAUTH, "P9_RAUTH" ) \ EM( P9_TATTACH, "P9_TATTACH" ) \ EM( P9_RATTACH, "P9_RATTACH" ) \ EM( P9_TERROR, "P9_TERROR" ) \ EM( P9_RERROR, "P9_RERROR" ) \ EM( P9_TFLUSH, "P9_TFLUSH" ) \ EM( P9_RFLUSH, "P9_RFLUSH" ) \ EM( P9_TWALK, "P9_TWALK" ) \ EM( P9_RWALK, "P9_RWALK" ) \ EM( P9_TOPEN, "P9_TOPEN" ) \ EM( P9_ROPEN, "P9_ROPEN" ) \ EM( P9_TCREATE, "P9_TCREATE" ) \ EM( P9_RCREATE, "P9_RCREATE" ) \ EM( P9_TREAD, "P9_TREAD" ) \ EM( P9_RREAD, "P9_RREAD" ) \ EM( P9_TWRITE, "P9_TWRITE" ) \ EM( P9_RWRITE, "P9_RWRITE" ) \ EM( P9_TCLUNK, "P9_TCLUNK" ) \ EM( P9_RCLUNK, "P9_RCLUNK" ) \ EM( P9_TREMOVE, "P9_TREMOVE" ) \ EM( P9_RREMOVE, "P9_RREMOVE" ) \ EM( P9_TSTAT, "P9_TSTAT" ) \ EM( P9_RSTAT, "P9_RSTAT" ) \ EM( P9_TWSTAT, "P9_TWSTAT" ) \ EMe(P9_RWSTAT, "P9_RWSTAT" ) #define P9_FID_REFTYPE \ EM( P9_FID_REF_CREATE, "create " ) \ EM( P9_FID_REF_GET, "get " ) \ EM( P9_FID_REF_PUT, "put " ) \ EMe(P9_FID_REF_DESTROY, "destroy" ) /* Define EM() to export the enums to userspace via TRACE_DEFINE_ENUM() */ #undef EM #undef EMe #define EM(a, b) TRACE_DEFINE_ENUM(a); #define EMe(a, b) TRACE_DEFINE_ENUM(a); P9_MSG_T P9_FID_REFTYPE /* And also use EM/EMe to define helper enums -- once */ #ifndef __9P_DECLARE_TRACE_ENUMS_ONLY_ONCE #define __9P_DECLARE_TRACE_ENUMS_ONLY_ONCE #undef EM #undef EMe #define EM(a, b) a, #define EMe(a, b) a enum p9_fid_reftype { P9_FID_REFTYPE } __mode(byte); #endif /* * Now redefine the EM() and EMe() macros to map the enums to the strings * that will be printed in the output. */ #undef EM #undef EMe #define EM(a, b) { a, b }, #define EMe(a, b) { a, b } #define show_9p_op(type) \ __print_symbolic(type, P9_MSG_T) #define show_9p_fid_reftype(type) \ __print_symbolic(type, P9_FID_REFTYPE) TRACE_EVENT(9p_client_req, TP_PROTO(struct p9_client *clnt, int8_t type, int tag), TP_ARGS(clnt, type, tag), TP_STRUCT__entry( __field( void *, clnt ) __field( __u8, type ) __field( __u32, tag ) ), TP_fast_assign( __entry->clnt = clnt; __entry->type = type; __entry->tag = tag; ), TP_printk("client %lu request %s tag %d", (long)__entry->clnt, show_9p_op(__entry->type), __entry->tag) ); TRACE_EVENT(9p_client_res, TP_PROTO(struct p9_client *clnt, int8_t type, int tag, int err), TP_ARGS(clnt, type, tag, err), TP_STRUCT__entry( __field( void *, clnt ) __field( __u8, type ) __field( __u32, tag ) __field( __u32, err ) ), TP_fast_assign( __entry->clnt = clnt; __entry->type = type; __entry->tag = tag; __entry->err = err; ), TP_printk("client %lu response %s tag %d err %d", (long)__entry->clnt, show_9p_op(__entry->type), __entry->tag, __entry->err) ); /* dump 32 bytes of protocol data */ #define P9_PROTO_DUMP_SZ 32 TRACE_EVENT(9p_protocol_dump, TP_PROTO(struct p9_client *clnt, struct p9_fcall *pdu), TP_ARGS(clnt, pdu), TP_STRUCT__entry( __field( void *, clnt ) __field( __u8, type ) __field( __u16, tag ) __dynamic_array(unsigned char, line, min_t(size_t, pdu->capacity, P9_PROTO_DUMP_SZ)) ), TP_fast_assign( __entry->clnt = clnt; __entry->type = pdu->id; __entry->tag = pdu->tag; memcpy(__get_dynamic_array(line), pdu->sdata, __get_dynamic_array_len(line)); ), TP_printk("clnt %lu %s(tag = %d)\n%*ph\n", (unsigned long)__entry->clnt, show_9p_op(__entry->type), __entry->tag, __get_dynamic_array_len(line), __get_dynamic_array(line)) ); TRACE_EVENT(9p_fid_ref, TP_PROTO(struct p9_fid *fid, __u8 type), TP_ARGS(fid, type), TP_STRUCT__entry( __field( int, fid ) __field( int, refcount ) __field( __u8, type ) ), TP_fast_assign( __entry->fid = fid->fid; __entry->refcount = refcount_read(&fid->count); __entry->type = type; ), TP_printk("%s fid %d, refcount %d", show_9p_fid_reftype(__entry->type), __entry->fid, __entry->refcount) ); #endif /* _TRACE_9P_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 6 2 6 6 6 6 4 6 6 2 2 2 4 4 4 4 4 4 6 6 6 6 6 6 6 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 6 6 6 1 6 6 6 6 6 5 6 6 6 6 6 6 1 6 6 5 1 6 1 6 6 6 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 6 6 6 6 6 6 5 6 6 6 6 6 6 6 2 6 5 1 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 | // SPDX-License-Identifier: GPL-2.0 /* * SME code for cfg80211 * both driver SME event handling and the SME implementation * (for nl80211's connect() and wext) * * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2009, 2020, 2022-2024 Intel Corporation. All rights reserved. * Copyright 2017 Intel Deutschland GmbH */ #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/wireless.h> #include <linux/export.h> #include <net/iw_handler.h> #include <net/cfg80211.h> #include <net/rtnetlink.h> #include "nl80211.h" #include "reg.h" #include "rdev-ops.h" /* * Software SME in cfg80211, using auth/assoc/deauth calls to the * driver. This is for implementing nl80211's connect/disconnect * and wireless extensions (if configured.) */ struct cfg80211_conn { struct cfg80211_connect_params params; /* these are sub-states of the _CONNECTING sme_state */ enum { CFG80211_CONN_SCANNING, CFG80211_CONN_SCAN_AGAIN, CFG80211_CONN_AUTHENTICATE_NEXT, CFG80211_CONN_AUTHENTICATING, CFG80211_CONN_AUTH_FAILED_TIMEOUT, CFG80211_CONN_ASSOCIATE_NEXT, CFG80211_CONN_ASSOCIATING, CFG80211_CONN_ASSOC_FAILED, CFG80211_CONN_ASSOC_FAILED_TIMEOUT, CFG80211_CONN_DEAUTH, CFG80211_CONN_ABANDON, CFG80211_CONN_CONNECTED, } state; u8 bssid[ETH_ALEN], prev_bssid[ETH_ALEN]; const u8 *ie; size_t ie_len; bool auto_auth, prev_bssid_valid; }; static void cfg80211_sme_free(struct wireless_dev *wdev) { if (!wdev->conn) return; kfree(wdev->conn->ie); kfree(wdev->conn); wdev->conn = NULL; } static int cfg80211_conn_scan(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_scan_request *request; int n_channels, err; lockdep_assert_wiphy(wdev->wiphy); if (rdev->scan_req || rdev->scan_msg) return -EBUSY; if (wdev->conn->params.channel) n_channels = 1; else n_channels = ieee80211_get_num_supported_channels(wdev->wiphy); request = kzalloc(sizeof(*request) + sizeof(request->ssids[0]) + sizeof(request->channels[0]) * n_channels, GFP_KERNEL); if (!request) return -ENOMEM; request->n_channels = n_channels; if (wdev->conn->params.channel) { enum nl80211_band band = wdev->conn->params.channel->band; struct ieee80211_supported_band *sband = wdev->wiphy->bands[band]; if (!sband) { kfree(request); return -EINVAL; } request->channels[0] = wdev->conn->params.channel; request->rates[band] = (1 << sband->n_bitrates) - 1; } else { int i = 0, j; enum nl80211_band band; struct ieee80211_supported_band *bands; struct ieee80211_channel *channel; for (band = 0; band < NUM_NL80211_BANDS; band++) { bands = wdev->wiphy->bands[band]; if (!bands) continue; for (j = 0; j < bands->n_channels; j++) { channel = &bands->channels[j]; if (channel->flags & IEEE80211_CHAN_DISABLED) continue; request->channels[i++] = channel; } request->rates[band] = (1 << bands->n_bitrates) - 1; } n_channels = i; } request->n_channels = n_channels; request->ssids = (void *)request + struct_size(request, channels, n_channels); request->n_ssids = 1; memcpy(request->ssids[0].ssid, wdev->conn->params.ssid, wdev->conn->params.ssid_len); request->ssids[0].ssid_len = wdev->conn->params.ssid_len; eth_broadcast_addr(request->bssid); request->wdev = wdev; request->wiphy = &rdev->wiphy; request->scan_start = jiffies; rdev->scan_req = request; err = cfg80211_scan(rdev); if (!err) { wdev->conn->state = CFG80211_CONN_SCANNING; nl80211_send_scan_start(rdev, wdev); dev_hold(wdev->netdev); } else { rdev->scan_req = NULL; kfree(request); } return err; } static int cfg80211_conn_do_work(struct wireless_dev *wdev, enum nl80211_timeout_reason *treason) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_connect_params *params; struct cfg80211_auth_request auth_req = {}; struct cfg80211_assoc_request req = {}; int err; lockdep_assert_wiphy(wdev->wiphy); if (!wdev->conn) return 0; params = &wdev->conn->params; switch (wdev->conn->state) { case CFG80211_CONN_SCANNING: /* didn't find it during scan ... */ return -ENOENT; case CFG80211_CONN_SCAN_AGAIN: return cfg80211_conn_scan(wdev); case CFG80211_CONN_AUTHENTICATE_NEXT: if (WARN_ON(!rdev->ops->auth)) return -EOPNOTSUPP; wdev->conn->state = CFG80211_CONN_AUTHENTICATING; auth_req.key = params->key; auth_req.key_len = params->key_len; auth_req.key_idx = params->key_idx; auth_req.auth_type = params->auth_type; auth_req.bss = cfg80211_get_bss(&rdev->wiphy, params->channel, params->bssid, params->ssid, params->ssid_len, IEEE80211_BSS_TYPE_ESS, IEEE80211_PRIVACY_ANY); auth_req.link_id = -1; err = cfg80211_mlme_auth(rdev, wdev->netdev, &auth_req); cfg80211_put_bss(&rdev->wiphy, auth_req.bss); return err; case CFG80211_CONN_AUTH_FAILED_TIMEOUT: *treason = NL80211_TIMEOUT_AUTH; return -ENOTCONN; case CFG80211_CONN_ASSOCIATE_NEXT: if (WARN_ON(!rdev->ops->assoc)) return -EOPNOTSUPP; wdev->conn->state = CFG80211_CONN_ASSOCIATING; if (wdev->conn->prev_bssid_valid) req.prev_bssid = wdev->conn->prev_bssid; req.ie = params->ie; req.ie_len = params->ie_len; req.use_mfp = params->mfp != NL80211_MFP_NO; req.crypto = params->crypto; req.flags = params->flags; req.ht_capa = params->ht_capa; req.ht_capa_mask = params->ht_capa_mask; req.vht_capa = params->vht_capa; req.vht_capa_mask = params->vht_capa_mask; req.link_id = -1; req.bss = cfg80211_get_bss(&rdev->wiphy, params->channel, params->bssid, params->ssid, params->ssid_len, IEEE80211_BSS_TYPE_ESS, IEEE80211_PRIVACY_ANY); if (!req.bss) { err = -ENOENT; } else { err = cfg80211_mlme_assoc(rdev, wdev->netdev, &req, NULL); cfg80211_put_bss(&rdev->wiphy, req.bss); } if (err) cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); return err; case CFG80211_CONN_ASSOC_FAILED_TIMEOUT: *treason = NL80211_TIMEOUT_ASSOC; fallthrough; case CFG80211_CONN_ASSOC_FAILED: cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); return -ENOTCONN; case CFG80211_CONN_DEAUTH: cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); fallthrough; case CFG80211_CONN_ABANDON: /* free directly, disconnected event already sent */ cfg80211_sme_free(wdev); return 0; default: return 0; } } void cfg80211_conn_work(struct work_struct *work) { struct cfg80211_registered_device *rdev = container_of(work, struct cfg80211_registered_device, conn_work); struct wireless_dev *wdev; u8 bssid_buf[ETH_ALEN], *bssid = NULL; enum nl80211_timeout_reason treason; guard(wiphy)(&rdev->wiphy); list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (!wdev->netdev) continue; if (!netif_running(wdev->netdev)) continue; if (!wdev->conn || wdev->conn->state == CFG80211_CONN_CONNECTED) continue; if (wdev->conn->params.bssid) { memcpy(bssid_buf, wdev->conn->params.bssid, ETH_ALEN); bssid = bssid_buf; } treason = NL80211_TIMEOUT_UNSPECIFIED; if (cfg80211_conn_do_work(wdev, &treason)) { struct cfg80211_connect_resp_params cr; memset(&cr, 0, sizeof(cr)); cr.status = -1; cr.links[0].bssid = bssid; cr.timeout_reason = treason; __cfg80211_connect_result(wdev->netdev, &cr, false); } } } static void cfg80211_step_auth_next(struct cfg80211_conn *conn, struct cfg80211_bss *bss) { memcpy(conn->bssid, bss->bssid, ETH_ALEN); conn->params.bssid = conn->bssid; conn->params.channel = bss->channel; conn->state = CFG80211_CONN_AUTHENTICATE_NEXT; } /* Returned bss is reference counted and must be cleaned up appropriately. */ static struct cfg80211_bss *cfg80211_get_conn_bss(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bss *bss; lockdep_assert_wiphy(wdev->wiphy); bss = cfg80211_get_bss(wdev->wiphy, wdev->conn->params.channel, wdev->conn->params.bssid, wdev->conn->params.ssid, wdev->conn->params.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY(wdev->conn->params.privacy)); if (!bss) return NULL; cfg80211_step_auth_next(wdev->conn, bss); schedule_work(&rdev->conn_work); return bss; } void cfg80211_sme_scan_done(struct net_device *dev) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bss *bss; lockdep_assert_wiphy(wdev->wiphy); if (!wdev->conn) return; if (wdev->conn->state != CFG80211_CONN_SCANNING && wdev->conn->state != CFG80211_CONN_SCAN_AGAIN) return; bss = cfg80211_get_conn_bss(wdev); if (bss) cfg80211_put_bss(&rdev->wiphy, bss); else schedule_work(&rdev->conn_work); } void cfg80211_sme_rx_auth(struct wireless_dev *wdev, const u8 *buf, size_t len) { struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf; u16 status_code = le16_to_cpu(mgmt->u.auth.status_code); lockdep_assert_wiphy(wdev->wiphy); if (!wdev->conn || wdev->conn->state == CFG80211_CONN_CONNECTED) return; if (status_code == WLAN_STATUS_NOT_SUPPORTED_AUTH_ALG && wdev->conn->auto_auth && wdev->conn->params.auth_type != NL80211_AUTHTYPE_NETWORK_EAP) { /* select automatically between only open, shared, leap */ switch (wdev->conn->params.auth_type) { case NL80211_AUTHTYPE_OPEN_SYSTEM: if (wdev->connect_keys) wdev->conn->params.auth_type = NL80211_AUTHTYPE_SHARED_KEY; else wdev->conn->params.auth_type = NL80211_AUTHTYPE_NETWORK_EAP; break; case NL80211_AUTHTYPE_SHARED_KEY: wdev->conn->params.auth_type = NL80211_AUTHTYPE_NETWORK_EAP; break; default: /* huh? */ wdev->conn->params.auth_type = NL80211_AUTHTYPE_OPEN_SYSTEM; break; } wdev->conn->state = CFG80211_CONN_AUTHENTICATE_NEXT; schedule_work(&rdev->conn_work); } else if (status_code != WLAN_STATUS_SUCCESS) { struct cfg80211_connect_resp_params cr; memset(&cr, 0, sizeof(cr)); cr.status = status_code; cr.links[0].bssid = mgmt->bssid; cr.timeout_reason = NL80211_TIMEOUT_UNSPECIFIED; __cfg80211_connect_result(wdev->netdev, &cr, false); } else if (wdev->conn->state == CFG80211_CONN_AUTHENTICATING) { wdev->conn->state = CFG80211_CONN_ASSOCIATE_NEXT; schedule_work(&rdev->conn_work); } } bool cfg80211_sme_rx_assoc_resp(struct wireless_dev *wdev, u16 status) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return false; if (status == WLAN_STATUS_SUCCESS) { wdev->conn->state = CFG80211_CONN_CONNECTED; return false; } if (wdev->conn->prev_bssid_valid) { /* * Some stupid APs don't accept reassoc, so we * need to fall back to trying regular assoc; * return true so no event is sent to userspace. */ wdev->conn->prev_bssid_valid = false; wdev->conn->state = CFG80211_CONN_ASSOCIATE_NEXT; schedule_work(&rdev->conn_work); return true; } wdev->conn->state = CFG80211_CONN_ASSOC_FAILED; schedule_work(&rdev->conn_work); return false; } void cfg80211_sme_deauth(struct wireless_dev *wdev) { cfg80211_sme_free(wdev); } void cfg80211_sme_auth_timeout(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return; wdev->conn->state = CFG80211_CONN_AUTH_FAILED_TIMEOUT; schedule_work(&rdev->conn_work); } void cfg80211_sme_disassoc(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return; wdev->conn->state = CFG80211_CONN_DEAUTH; schedule_work(&rdev->conn_work); } void cfg80211_sme_assoc_timeout(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return; wdev->conn->state = CFG80211_CONN_ASSOC_FAILED_TIMEOUT; schedule_work(&rdev->conn_work); } void cfg80211_sme_abandon_assoc(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); if (!wdev->conn) return; wdev->conn->state = CFG80211_CONN_ABANDON; schedule_work(&rdev->conn_work); } static void cfg80211_wdev_release_bsses(struct wireless_dev *wdev) { unsigned int link; for_each_valid_link(wdev, link) { if (!wdev->links[link].client.current_bss) continue; cfg80211_unhold_bss(wdev->links[link].client.current_bss); cfg80211_put_bss(wdev->wiphy, &wdev->links[link].client.current_bss->pub); wdev->links[link].client.current_bss = NULL; } } void cfg80211_wdev_release_link_bsses(struct wireless_dev *wdev, u16 link_mask) { unsigned int link; for_each_valid_link(wdev, link) { if (!wdev->links[link].client.current_bss || !(link_mask & BIT(link))) continue; cfg80211_unhold_bss(wdev->links[link].client.current_bss); cfg80211_put_bss(wdev->wiphy, &wdev->links[link].client.current_bss->pub); wdev->links[link].client.current_bss = NULL; } } static int cfg80211_sme_get_conn_ies(struct wireless_dev *wdev, const u8 *ies, size_t ies_len, const u8 **out_ies, size_t *out_ies_len) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u8 *buf; size_t offs; if (!rdev->wiphy.extended_capabilities_len || (ies && cfg80211_find_ie(WLAN_EID_EXT_CAPABILITY, ies, ies_len))) { *out_ies = kmemdup(ies, ies_len, GFP_KERNEL); if (!*out_ies) return -ENOMEM; *out_ies_len = ies_len; return 0; } buf = kmalloc(ies_len + rdev->wiphy.extended_capabilities_len + 2, GFP_KERNEL); if (!buf) return -ENOMEM; if (ies_len) { static const u8 before_extcapa[] = { /* not listing IEs expected to be created by driver */ WLAN_EID_RSN, WLAN_EID_QOS_CAPA, WLAN_EID_RRM_ENABLED_CAPABILITIES, WLAN_EID_MOBILITY_DOMAIN, WLAN_EID_SUPPORTED_REGULATORY_CLASSES, WLAN_EID_BSS_COEX_2040, }; offs = ieee80211_ie_split(ies, ies_len, before_extcapa, ARRAY_SIZE(before_extcapa), 0); memcpy(buf, ies, offs); /* leave a whole for extended capabilities IE */ memcpy(buf + offs + rdev->wiphy.extended_capabilities_len + 2, ies + offs, ies_len - offs); } else { offs = 0; } /* place extended capabilities IE (with only driver capabilities) */ buf[offs] = WLAN_EID_EXT_CAPABILITY; buf[offs + 1] = rdev->wiphy.extended_capabilities_len; memcpy(buf + offs + 2, rdev->wiphy.extended_capabilities, rdev->wiphy.extended_capabilities_len); *out_ies = buf; *out_ies_len = ies_len + rdev->wiphy.extended_capabilities_len + 2; return 0; } static int cfg80211_sme_connect(struct wireless_dev *wdev, struct cfg80211_connect_params *connect, const u8 *prev_bssid) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_bss *bss; int err; if (!rdev->ops->auth || !rdev->ops->assoc) return -EOPNOTSUPP; cfg80211_wdev_release_bsses(wdev); if (wdev->connected) { cfg80211_sme_free(wdev); wdev->connected = false; } if (wdev->conn) return -EINPROGRESS; wdev->conn = kzalloc(sizeof(*wdev->conn), GFP_KERNEL); if (!wdev->conn) return -ENOMEM; /* * Copy all parameters, and treat explicitly IEs, BSSID, SSID. */ memcpy(&wdev->conn->params, connect, sizeof(*connect)); if (connect->bssid) { wdev->conn->params.bssid = wdev->conn->bssid; memcpy(wdev->conn->bssid, connect->bssid, ETH_ALEN); } if (cfg80211_sme_get_conn_ies(wdev, connect->ie, connect->ie_len, &wdev->conn->ie, &wdev->conn->params.ie_len)) { kfree(wdev->conn); wdev->conn = NULL; return -ENOMEM; } wdev->conn->params.ie = wdev->conn->ie; if (connect->auth_type == NL80211_AUTHTYPE_AUTOMATIC) { wdev->conn->auto_auth = true; /* start with open system ... should mostly work */ wdev->conn->params.auth_type = NL80211_AUTHTYPE_OPEN_SYSTEM; } else { wdev->conn->auto_auth = false; } wdev->conn->params.ssid = wdev->u.client.ssid; wdev->conn->params.ssid_len = wdev->u.client.ssid_len; /* see if we have the bss already */ bss = cfg80211_get_bss(wdev->wiphy, wdev->conn->params.channel, wdev->conn->params.bssid, wdev->conn->params.ssid, wdev->conn->params.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY(wdev->conn->params.privacy)); if (prev_bssid) { memcpy(wdev->conn->prev_bssid, prev_bssid, ETH_ALEN); wdev->conn->prev_bssid_valid = true; } /* we're good if we have a matching bss struct */ if (bss) { enum nl80211_timeout_reason treason; cfg80211_step_auth_next(wdev->conn, bss); err = cfg80211_conn_do_work(wdev, &treason); cfg80211_put_bss(wdev->wiphy, bss); } else { /* otherwise we'll need to scan for the AP first */ err = cfg80211_conn_scan(wdev); /* * If we can't scan right now, then we need to scan again * after the current scan finished, since the parameters * changed (unless we find a good AP anyway). */ if (err == -EBUSY) { err = 0; wdev->conn->state = CFG80211_CONN_SCAN_AGAIN; } } if (err) cfg80211_sme_free(wdev); return err; } static int cfg80211_sme_disconnect(struct wireless_dev *wdev, u16 reason) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int err; if (!wdev->conn) return 0; if (!rdev->ops->deauth) return -EOPNOTSUPP; if (wdev->conn->state == CFG80211_CONN_SCANNING || wdev->conn->state == CFG80211_CONN_SCAN_AGAIN) { err = 0; goto out; } /* wdev->conn->params.bssid must be set if > SCANNING */ err = cfg80211_mlme_deauth(rdev, wdev->netdev, wdev->conn->params.bssid, NULL, 0, reason, false); out: cfg80211_sme_free(wdev); return err; } /* * code shared for in-device and software SME */ static bool cfg80211_is_all_idle(void) { struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; bool is_all_idle = true; /* * All devices must be idle as otherwise if you are actively * scanning some new beacon hints could be learned and would * count as new regulatory hints. * Also if there is any other active beaconing interface we * need not issue a disconnect hint and reset any info such * as chan dfs state, etc. */ for_each_rdev(rdev) { guard(wiphy)(&rdev->wiphy); list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (wdev->conn || wdev->connected || cfg80211_beaconing_iface_active(wdev)) is_all_idle = false; } } return is_all_idle; } static void disconnect_work(struct work_struct *work) { rtnl_lock(); if (cfg80211_is_all_idle()) regulatory_hint_disconnect(); rtnl_unlock(); } DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); static void cfg80211_connect_result_release_bsses(struct wireless_dev *wdev, struct cfg80211_connect_resp_params *cr) { unsigned int link; for_each_valid_link(cr, link) { if (!cr->links[link].bss) continue; cfg80211_unhold_bss(bss_from_pub(cr->links[link].bss)); cfg80211_put_bss(wdev->wiphy, cr->links[link].bss); } } /* * API calls for drivers implementing connect/disconnect and * SME event handling */ /* This method must consume bss one way or another */ void __cfg80211_connect_result(struct net_device *dev, struct cfg80211_connect_resp_params *cr, bool wextev) { struct wireless_dev *wdev = dev->ieee80211_ptr; const struct element *country_elem = NULL; const struct element *ssid; const u8 *country_data; u8 country_datalen; #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif unsigned int link; const u8 *connected_addr; bool bss_not_found = false; lockdep_assert_wiphy(wdev->wiphy); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) goto out; if (cr->valid_links) { if (WARN_ON(!cr->ap_mld_addr)) goto out; for_each_valid_link(cr, link) { if (WARN_ON(!cr->links[link].addr)) goto out; } if (WARN_ON(wdev->connect_keys)) goto out; } wdev->unprot_beacon_reported = 0; nl80211_send_connect_result(wiphy_to_rdev(wdev->wiphy), dev, cr, GFP_KERNEL); connected_addr = cr->valid_links ? cr->ap_mld_addr : cr->links[0].bssid; #ifdef CONFIG_CFG80211_WEXT if (wextev && !cr->valid_links) { if (cr->req_ie && cr->status == WLAN_STATUS_SUCCESS) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = cr->req_ie_len; wireless_send_event(dev, IWEVASSOCREQIE, &wrqu, cr->req_ie); } if (cr->resp_ie && cr->status == WLAN_STATUS_SUCCESS) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = cr->resp_ie_len; wireless_send_event(dev, IWEVASSOCRESPIE, &wrqu, cr->resp_ie); } memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; if (connected_addr && cr->status == WLAN_STATUS_SUCCESS) { memcpy(wrqu.ap_addr.sa_data, connected_addr, ETH_ALEN); memcpy(wdev->wext.prev_bssid, connected_addr, ETH_ALEN); wdev->wext.prev_bssid_valid = true; } wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); } #endif if (cr->status == WLAN_STATUS_SUCCESS) { if (!wiphy_to_rdev(wdev->wiphy)->ops->connect) { for_each_valid_link(cr, link) { if (WARN_ON_ONCE(!cr->links[link].bss)) break; } } for_each_valid_link(cr, link) { /* don't do extra lookups for failures */ if (cr->links[link].status != WLAN_STATUS_SUCCESS) continue; if (cr->links[link].bss) continue; cr->links[link].bss = cfg80211_get_bss(wdev->wiphy, NULL, cr->links[link].bssid, wdev->u.client.ssid, wdev->u.client.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (!cr->links[link].bss) { bss_not_found = true; break; } cfg80211_hold_bss(bss_from_pub(cr->links[link].bss)); } } cfg80211_wdev_release_bsses(wdev); if (cr->status != WLAN_STATUS_SUCCESS) { kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; wdev->u.client.ssid_len = 0; wdev->conn_owner_nlportid = 0; cfg80211_connect_result_release_bsses(wdev, cr); cfg80211_sme_free(wdev); return; } if (WARN_ON(bss_not_found)) { cfg80211_connect_result_release_bsses(wdev, cr); return; } memset(wdev->links, 0, sizeof(wdev->links)); for_each_valid_link(cr, link) { if (cr->links[link].status == WLAN_STATUS_SUCCESS) continue; cr->valid_links &= ~BIT(link); /* don't require bss pointer for failed links */ if (!cr->links[link].bss) continue; cfg80211_unhold_bss(bss_from_pub(cr->links[link].bss)); cfg80211_put_bss(wdev->wiphy, cr->links[link].bss); } wdev->valid_links = cr->valid_links; for_each_valid_link(cr, link) wdev->links[link].client.current_bss = bss_from_pub(cr->links[link].bss); wdev->connected = true; ether_addr_copy(wdev->u.client.connected_addr, connected_addr); if (cr->valid_links) { for_each_valid_link(cr, link) memcpy(wdev->links[link].addr, cr->links[link].addr, ETH_ALEN); } cfg80211_upload_connect_keys(wdev); rcu_read_lock(); for_each_valid_link(cr, link) { country_elem = ieee80211_bss_get_elem(cr->links[link].bss, WLAN_EID_COUNTRY); if (country_elem) break; } if (!country_elem) { rcu_read_unlock(); return; } country_datalen = country_elem->datalen; country_data = kmemdup(country_elem->data, country_datalen, GFP_ATOMIC); rcu_read_unlock(); if (!country_data) return; regulatory_hint_country_ie(wdev->wiphy, cr->links[link].bss->channel->band, country_data, country_datalen); kfree(country_data); if (!wdev->u.client.ssid_len) { rcu_read_lock(); for_each_valid_link(cr, link) { ssid = ieee80211_bss_get_elem(cr->links[link].bss, WLAN_EID_SSID); if (!ssid || !ssid->datalen) continue; memcpy(wdev->u.client.ssid, ssid->data, ssid->datalen); wdev->u.client.ssid_len = ssid->datalen; break; } rcu_read_unlock(); } return; out: for_each_valid_link(cr, link) cfg80211_put_bss(wdev->wiphy, cr->links[link].bss); } static void cfg80211_update_link_bss(struct wireless_dev *wdev, struct cfg80211_bss **bss) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_internal_bss *ibss; if (!*bss) return; ibss = bss_from_pub(*bss); if (list_empty(&ibss->list)) { struct cfg80211_bss *found = NULL, *tmp = *bss; found = cfg80211_get_bss(wdev->wiphy, NULL, (*bss)->bssid, wdev->u.client.ssid, wdev->u.client.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (found) { /* The same BSS is already updated so use it * instead, as it has latest info. */ *bss = found; } else { /* Update with BSS provided by driver, it will * be freshly added and ref cnted, we can free * the old one. * * signal_valid can be false, as we are not * expecting the BSS to be found. * * keep the old timestamp to avoid confusion */ cfg80211_bss_update(rdev, ibss, false, ibss->ts); } cfg80211_put_bss(wdev->wiphy, tmp); } } /* Consumes bss object(s) one way or another */ void cfg80211_connect_done(struct net_device *dev, struct cfg80211_connect_resp_params *params, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; u8 *next; size_t link_info_size = 0; unsigned int link; for_each_valid_link(params, link) { cfg80211_update_link_bss(wdev, ¶ms->links[link].bss); link_info_size += params->links[link].bssid ? ETH_ALEN : 0; link_info_size += params->links[link].addr ? ETH_ALEN : 0; } ev = kzalloc(sizeof(*ev) + (params->ap_mld_addr ? ETH_ALEN : 0) + params->req_ie_len + params->resp_ie_len + params->fils.kek_len + params->fils.pmk_len + (params->fils.pmkid ? WLAN_PMKID_LEN : 0) + link_info_size, gfp); if (!ev) { for_each_valid_link(params, link) cfg80211_put_bss(wdev->wiphy, params->links[link].bss); return; } ev->type = EVENT_CONNECT_RESULT; next = ((u8 *)ev) + sizeof(*ev); if (params->ap_mld_addr) { ev->cr.ap_mld_addr = next; memcpy((void *)ev->cr.ap_mld_addr, params->ap_mld_addr, ETH_ALEN); next += ETH_ALEN; } if (params->req_ie_len) { ev->cr.req_ie = next; ev->cr.req_ie_len = params->req_ie_len; memcpy((void *)ev->cr.req_ie, params->req_ie, params->req_ie_len); next += params->req_ie_len; } if (params->resp_ie_len) { ev->cr.resp_ie = next; ev->cr.resp_ie_len = params->resp_ie_len; memcpy((void *)ev->cr.resp_ie, params->resp_ie, params->resp_ie_len); next += params->resp_ie_len; } if (params->fils.kek_len) { ev->cr.fils.kek = next; ev->cr.fils.kek_len = params->fils.kek_len; memcpy((void *)ev->cr.fils.kek, params->fils.kek, params->fils.kek_len); next += params->fils.kek_len; } if (params->fils.pmk_len) { ev->cr.fils.pmk = next; ev->cr.fils.pmk_len = params->fils.pmk_len; memcpy((void *)ev->cr.fils.pmk, params->fils.pmk, params->fils.pmk_len); next += params->fils.pmk_len; } if (params->fils.pmkid) { ev->cr.fils.pmkid = next; memcpy((void *)ev->cr.fils.pmkid, params->fils.pmkid, WLAN_PMKID_LEN); next += WLAN_PMKID_LEN; } ev->cr.fils.update_erp_next_seq_num = params->fils.update_erp_next_seq_num; if (params->fils.update_erp_next_seq_num) ev->cr.fils.erp_next_seq_num = params->fils.erp_next_seq_num; ev->cr.valid_links = params->valid_links; for_each_valid_link(params, link) { if (params->links[link].bss) cfg80211_hold_bss( bss_from_pub(params->links[link].bss)); ev->cr.links[link].bss = params->links[link].bss; ev->cr.links[link].status = params->links[link].status; if (params->links[link].addr) { ev->cr.links[link].addr = next; memcpy((void *)ev->cr.links[link].addr, params->links[link].addr, ETH_ALEN); next += ETH_ALEN; } if (params->links[link].bssid) { ev->cr.links[link].bssid = next; memcpy((void *)ev->cr.links[link].bssid, params->links[link].bssid, ETH_ALEN); next += ETH_ALEN; } } ev->cr.status = params->status; ev->cr.timeout_reason = params->timeout_reason; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); } EXPORT_SYMBOL(cfg80211_connect_done); /* Consumes bss object one way or another */ void __cfg80211_roamed(struct wireless_dev *wdev, struct cfg80211_roam_info *info) { #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif unsigned int link; const u8 *connected_addr; lockdep_assert_wiphy(wdev->wiphy); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) goto out; if (WARN_ON(!wdev->connected)) goto out; if (info->valid_links) { if (WARN_ON(!info->ap_mld_addr)) goto out; for_each_valid_link(info, link) { if (WARN_ON(!info->links[link].addr)) goto out; } } cfg80211_wdev_release_bsses(wdev); for_each_valid_link(info, link) { if (WARN_ON(!info->links[link].bss)) goto out; } memset(wdev->links, 0, sizeof(wdev->links)); wdev->valid_links = info->valid_links; for_each_valid_link(info, link) { cfg80211_hold_bss(bss_from_pub(info->links[link].bss)); wdev->links[link].client.current_bss = bss_from_pub(info->links[link].bss); } connected_addr = info->valid_links ? info->ap_mld_addr : info->links[0].bss->bssid; ether_addr_copy(wdev->u.client.connected_addr, connected_addr); if (info->valid_links) { for_each_valid_link(info, link) memcpy(wdev->links[link].addr, info->links[link].addr, ETH_ALEN); } wdev->unprot_beacon_reported = 0; nl80211_send_roamed(wiphy_to_rdev(wdev->wiphy), wdev->netdev, info, GFP_KERNEL); #ifdef CONFIG_CFG80211_WEXT if (!info->valid_links) { if (info->req_ie) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = info->req_ie_len; wireless_send_event(wdev->netdev, IWEVASSOCREQIE, &wrqu, info->req_ie); } if (info->resp_ie) { memset(&wrqu, 0, sizeof(wrqu)); wrqu.data.length = info->resp_ie_len; wireless_send_event(wdev->netdev, IWEVASSOCRESPIE, &wrqu, info->resp_ie); } memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; memcpy(wrqu.ap_addr.sa_data, connected_addr, ETH_ALEN); memcpy(wdev->wext.prev_bssid, connected_addr, ETH_ALEN); wdev->wext.prev_bssid_valid = true; wireless_send_event(wdev->netdev, SIOCGIWAP, &wrqu, NULL); } #endif return; out: for_each_valid_link(info, link) cfg80211_put_bss(wdev->wiphy, info->links[link].bss); } /* Consumes info->links.bss object(s) one way or another */ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; u8 *next; unsigned int link; size_t link_info_size = 0; bool bss_not_found = false; for_each_valid_link(info, link) { link_info_size += info->links[link].addr ? ETH_ALEN : 0; link_info_size += info->links[link].bssid ? ETH_ALEN : 0; if (info->links[link].bss) continue; info->links[link].bss = cfg80211_get_bss(wdev->wiphy, info->links[link].channel, info->links[link].bssid, wdev->u.client.ssid, wdev->u.client.ssid_len, wdev->conn_bss_type, IEEE80211_PRIVACY_ANY); if (!info->links[link].bss) { bss_not_found = true; break; } } if (WARN_ON(bss_not_found)) goto out; ev = kzalloc(sizeof(*ev) + info->req_ie_len + info->resp_ie_len + info->fils.kek_len + info->fils.pmk_len + (info->fils.pmkid ? WLAN_PMKID_LEN : 0) + (info->ap_mld_addr ? ETH_ALEN : 0) + link_info_size, gfp); if (!ev) goto out; ev->type = EVENT_ROAMED; next = ((u8 *)ev) + sizeof(*ev); if (info->req_ie_len) { ev->rm.req_ie = next; ev->rm.req_ie_len = info->req_ie_len; memcpy((void *)ev->rm.req_ie, info->req_ie, info->req_ie_len); next += info->req_ie_len; } if (info->resp_ie_len) { ev->rm.resp_ie = next; ev->rm.resp_ie_len = info->resp_ie_len; memcpy((void *)ev->rm.resp_ie, info->resp_ie, info->resp_ie_len); next += info->resp_ie_len; } if (info->fils.kek_len) { ev->rm.fils.kek = next; ev->rm.fils.kek_len = info->fils.kek_len; memcpy((void *)ev->rm.fils.kek, info->fils.kek, info->fils.kek_len); next += info->fils.kek_len; } if (info->fils.pmk_len) { ev->rm.fils.pmk = next; ev->rm.fils.pmk_len = info->fils.pmk_len; memcpy((void *)ev->rm.fils.pmk, info->fils.pmk, info->fils.pmk_len); next += info->fils.pmk_len; } if (info->fils.pmkid) { ev->rm.fils.pmkid = next; memcpy((void *)ev->rm.fils.pmkid, info->fils.pmkid, WLAN_PMKID_LEN); next += WLAN_PMKID_LEN; } ev->rm.fils.update_erp_next_seq_num = info->fils.update_erp_next_seq_num; if (info->fils.update_erp_next_seq_num) ev->rm.fils.erp_next_seq_num = info->fils.erp_next_seq_num; if (info->ap_mld_addr) { ev->rm.ap_mld_addr = next; memcpy((void *)ev->rm.ap_mld_addr, info->ap_mld_addr, ETH_ALEN); next += ETH_ALEN; } ev->rm.valid_links = info->valid_links; for_each_valid_link(info, link) { ev->rm.links[link].bss = info->links[link].bss; if (info->links[link].addr) { ev->rm.links[link].addr = next; memcpy((void *)ev->rm.links[link].addr, info->links[link].addr, ETH_ALEN); next += ETH_ALEN; } if (info->links[link].bssid) { ev->rm.links[link].bssid = next; memcpy((void *)ev->rm.links[link].bssid, info->links[link].bssid, ETH_ALEN); next += ETH_ALEN; } } spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); return; out: for_each_valid_link(info, link) cfg80211_put_bss(wdev->wiphy, info->links[link].bss); } EXPORT_SYMBOL(cfg80211_roamed); void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *peer_addr, const u8 *td_bitmap, u8 td_bitmap_len) { lockdep_assert_wiphy(wdev->wiphy); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_P2P_CLIENT && wdev->iftype != NL80211_IFTYPE_AP && wdev->iftype != NL80211_IFTYPE_P2P_GO)) return; if (wdev->iftype == NL80211_IFTYPE_STATION || wdev->iftype == NL80211_IFTYPE_P2P_CLIENT) { if (WARN_ON(!wdev->connected) || WARN_ON(!ether_addr_equal(wdev->u.client.connected_addr, peer_addr))) return; } nl80211_send_port_authorized(wiphy_to_rdev(wdev->wiphy), wdev->netdev, peer_addr, td_bitmap, td_bitmap_len); } void cfg80211_port_authorized(struct net_device *dev, const u8 *peer_addr, const u8 *td_bitmap, u8 td_bitmap_len, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; if (WARN_ON(!peer_addr)) return; ev = kzalloc(sizeof(*ev) + td_bitmap_len, gfp); if (!ev) return; ev->type = EVENT_PORT_AUTHORIZED; memcpy(ev->pa.peer_addr, peer_addr, ETH_ALEN); ev->pa.td_bitmap = ((u8 *)ev) + sizeof(*ev); ev->pa.td_bitmap_len = td_bitmap_len; memcpy((void *)ev->pa.td_bitmap, td_bitmap, td_bitmap_len); /* * Use the wdev event list so that if there are pending * connected/roamed events, they will be reported first. */ spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); } EXPORT_SYMBOL(cfg80211_port_authorized); void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, size_t ie_len, u16 reason, bool from_ap) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int i; #ifdef CONFIG_CFG80211_WEXT union iwreq_data wrqu; #endif lockdep_assert_wiphy(wdev->wiphy); if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) return; cfg80211_wdev_release_bsses(wdev); wdev->valid_links = 0; wdev->connected = false; wdev->u.client.ssid_len = 0; wdev->conn_owner_nlportid = 0; kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; nl80211_send_disconnected(rdev, dev, reason, ie, ie_len, from_ap); /* stop critical protocol if supported */ if (rdev->ops->crit_proto_stop && rdev->crit_proto_nlportid) { rdev->crit_proto_nlportid = 0; rdev_crit_proto_stop(rdev, wdev); } /* * Delete all the keys ... pairwise keys can't really * exist any more anyway, but default keys might. */ if (rdev->ops->del_key) { int max_key_idx = 5; if (wiphy_ext_feature_isset( wdev->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION) || wiphy_ext_feature_isset( wdev->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT)) max_key_idx = 7; for (i = 0; i <= max_key_idx; i++) rdev_del_key(rdev, dev, -1, i, false, NULL); } rdev_set_qos_map(rdev, dev, NULL); #ifdef CONFIG_CFG80211_WEXT memset(&wrqu, 0, sizeof(wrqu)); wrqu.ap_addr.sa_family = ARPHRD_ETHER; wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); wdev->wext.connect.ssid_len = 0; #endif schedule_work(&cfg80211_disconnect_work); cfg80211_schedule_channels_check(wdev); } void cfg80211_disconnected(struct net_device *dev, u16 reason, const u8 *ie, size_t ie_len, bool locally_generated, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_event *ev; unsigned long flags; ev = kzalloc(sizeof(*ev) + ie_len, gfp); if (!ev) return; ev->type = EVENT_DISCONNECTED; ev->dc.ie = ((u8 *)ev) + sizeof(*ev); ev->dc.ie_len = ie_len; memcpy((void *)ev->dc.ie, ie, ie_len); ev->dc.reason = reason; ev->dc.locally_generated = locally_generated; spin_lock_irqsave(&wdev->event_lock, flags); list_add_tail(&ev->list, &wdev->event_list); spin_unlock_irqrestore(&wdev->event_lock, flags); queue_work(cfg80211_wq, &rdev->event_work); } EXPORT_SYMBOL(cfg80211_disconnected); /* * API calls for nl80211/wext compatibility code */ int cfg80211_connect(struct cfg80211_registered_device *rdev, struct net_device *dev, struct cfg80211_connect_params *connect, struct cfg80211_cached_keys *connkeys, const u8 *prev_bssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err; lockdep_assert_wiphy(wdev->wiphy); /* * If we have an ssid_len, we're trying to connect or are * already connected, so reject a new SSID unless it's the * same (which is the case for re-association.) */ if (wdev->u.client.ssid_len && (wdev->u.client.ssid_len != connect->ssid_len || memcmp(wdev->u.client.ssid, connect->ssid, wdev->u.client.ssid_len))) return -EALREADY; /* * If connected, reject (re-)association unless prev_bssid * matches the current BSSID. */ if (wdev->connected) { if (!prev_bssid) return -EALREADY; if (!ether_addr_equal(prev_bssid, wdev->u.client.connected_addr)) return -ENOTCONN; } /* * Reject if we're in the process of connecting with WEP, * this case isn't very interesting and trying to handle * it would make the code much more complex. */ if (wdev->connect_keys) return -EINPROGRESS; cfg80211_oper_and_ht_capa(&connect->ht_capa_mask, rdev->wiphy.ht_capa_mod_mask); cfg80211_oper_and_vht_capa(&connect->vht_capa_mask, rdev->wiphy.vht_capa_mod_mask); if (connkeys && connkeys->def >= 0) { int idx; u32 cipher; idx = connkeys->def; cipher = connkeys->params[idx].cipher; /* If given a WEP key we may need it for shared key auth */ if (cipher == WLAN_CIPHER_SUITE_WEP40 || cipher == WLAN_CIPHER_SUITE_WEP104) { connect->key_idx = idx; connect->key = connkeys->params[idx].key; connect->key_len = connkeys->params[idx].key_len; /* * If ciphers are not set (e.g. when going through * iwconfig), we have to set them appropriately here. */ if (connect->crypto.cipher_group == 0) connect->crypto.cipher_group = cipher; if (connect->crypto.n_ciphers_pairwise == 0) { connect->crypto.n_ciphers_pairwise = 1; connect->crypto.ciphers_pairwise[0] = cipher; } } } else { if (WARN_ON(connkeys)) return -EINVAL; /* connect can point to wdev->wext.connect which * can hold key data from a previous connection */ connect->key = NULL; connect->key_len = 0; connect->key_idx = 0; } wdev->connect_keys = connkeys; memcpy(wdev->u.client.ssid, connect->ssid, connect->ssid_len); wdev->u.client.ssid_len = connect->ssid_len; wdev->conn_bss_type = connect->pbss ? IEEE80211_BSS_TYPE_PBSS : IEEE80211_BSS_TYPE_ESS; if (!rdev->ops->connect) err = cfg80211_sme_connect(wdev, connect, prev_bssid); else err = rdev_connect(rdev, dev, connect); if (err) { wdev->connect_keys = NULL; /* * This could be reassoc getting refused, don't clear * ssid_len in that case. */ if (!wdev->connected) wdev->u.client.ssid_len = 0; return err; } return 0; } int cfg80211_disconnect(struct cfg80211_registered_device *rdev, struct net_device *dev, u16 reason, bool wextev) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err = 0; lockdep_assert_wiphy(wdev->wiphy); kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; wdev->conn_owner_nlportid = 0; if (wdev->conn) err = cfg80211_sme_disconnect(wdev, reason); else if (!rdev->ops->disconnect) cfg80211_mlme_down(rdev, dev); else if (wdev->u.client.ssid_len) err = rdev_disconnect(rdev, dev, reason); /* * Clear ssid_len unless we actually were fully connected, * in which case cfg80211_disconnected() will take care of * this later. */ if (!wdev->connected) wdev->u.client.ssid_len = 0; return err; } /* * Used to clean up after the connection / connection attempt owner socket * disconnects */ void cfg80211_autodisconnect_wk(struct work_struct *work) { struct wireless_dev *wdev = container_of(work, struct wireless_dev, disconnect_wk); struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); guard(wiphy)(wdev->wiphy); if (wdev->conn_owner_nlportid) { switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: cfg80211_leave_ibss(rdev, wdev->netdev, false); break; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: cfg80211_stop_ap(rdev, wdev->netdev, -1, false); break; case NL80211_IFTYPE_MESH_POINT: cfg80211_leave_mesh(rdev, wdev->netdev); break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: /* * Use disconnect_bssid if still connecting and * ops->disconnect not implemented. Otherwise we can * use cfg80211_disconnect. */ if (rdev->ops->disconnect || wdev->connected) cfg80211_disconnect(rdev, wdev->netdev, WLAN_REASON_DEAUTH_LEAVING, true); else cfg80211_mlme_deauth(rdev, wdev->netdev, wdev->disconnect_bssid, NULL, 0, WLAN_REASON_DEAUTH_LEAVING, false); break; default: break; } } } |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Glue Code for x86_64/AVX2 assembler optimized version of Serpent * * Copyright © 2012-2013 Jussi Kivilinna <jussi.kivilinna@mbnet.fi> */ #include <linux/module.h> #include <linux/types.h> #include <linux/crypto.h> #include <linux/err.h> #include <crypto/algapi.h> #include <crypto/internal/simd.h> #include <crypto/serpent.h> #include "serpent-avx.h" #include "ecb_cbc_helpers.h" #define SERPENT_AVX2_PARALLEL_BLOCKS 16 /* 16-way AVX2 parallel cipher functions */ asmlinkage void serpent_ecb_enc_16way(const void *ctx, u8 *dst, const u8 *src); asmlinkage void serpent_ecb_dec_16way(const void *ctx, u8 *dst, const u8 *src); asmlinkage void serpent_cbc_dec_16way(const void *ctx, u8 *dst, const u8 *src); static int serpent_setkey_skcipher(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { return __serpent_setkey(crypto_skcipher_ctx(tfm), key, keylen); } static int ecb_encrypt(struct skcipher_request *req) { ECB_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS); ECB_BLOCK(SERPENT_AVX2_PARALLEL_BLOCKS, serpent_ecb_enc_16way); ECB_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_ecb_enc_8way_avx); ECB_BLOCK(1, __serpent_encrypt); ECB_WALK_END(); } static int ecb_decrypt(struct skcipher_request *req) { ECB_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS); ECB_BLOCK(SERPENT_AVX2_PARALLEL_BLOCKS, serpent_ecb_dec_16way); ECB_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_ecb_dec_8way_avx); ECB_BLOCK(1, __serpent_decrypt); ECB_WALK_END(); } static int cbc_encrypt(struct skcipher_request *req) { CBC_WALK_START(req, SERPENT_BLOCK_SIZE, -1); CBC_ENC_BLOCK(__serpent_encrypt); CBC_WALK_END(); } static int cbc_decrypt(struct skcipher_request *req) { CBC_WALK_START(req, SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS); CBC_DEC_BLOCK(SERPENT_AVX2_PARALLEL_BLOCKS, serpent_cbc_dec_16way); CBC_DEC_BLOCK(SERPENT_PARALLEL_BLOCKS, serpent_cbc_dec_8way_avx); CBC_DEC_BLOCK(1, __serpent_decrypt); CBC_WALK_END(); } static struct skcipher_alg serpent_algs[] = { { .base.cra_name = "__ecb(serpent)", .base.cra_driver_name = "__ecb-serpent-avx2", .base.cra_priority = 600, .base.cra_flags = CRYPTO_ALG_INTERNAL, .base.cra_blocksize = SERPENT_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct serpent_ctx), .base.cra_module = THIS_MODULE, .min_keysize = SERPENT_MIN_KEY_SIZE, .max_keysize = SERPENT_MAX_KEY_SIZE, .setkey = serpent_setkey_skcipher, .encrypt = ecb_encrypt, .decrypt = ecb_decrypt, }, { .base.cra_name = "__cbc(serpent)", .base.cra_driver_name = "__cbc-serpent-avx2", .base.cra_priority = 600, .base.cra_flags = CRYPTO_ALG_INTERNAL, .base.cra_blocksize = SERPENT_BLOCK_SIZE, .base.cra_ctxsize = sizeof(struct serpent_ctx), .base.cra_module = THIS_MODULE, .min_keysize = SERPENT_MIN_KEY_SIZE, .max_keysize = SERPENT_MAX_KEY_SIZE, .ivsize = SERPENT_BLOCK_SIZE, .setkey = serpent_setkey_skcipher, .encrypt = cbc_encrypt, .decrypt = cbc_decrypt, }, }; static struct simd_skcipher_alg *serpent_simd_algs[ARRAY_SIZE(serpent_algs)]; static int __init serpent_avx2_init(void) { const char *feature_name; if (!boot_cpu_has(X86_FEATURE_AVX2) || !boot_cpu_has(X86_FEATURE_OSXSAVE)) { pr_info("AVX2 instructions are not detected.\n"); return -ENODEV; } if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, &feature_name)) { pr_info("CPU feature '%s' is not supported.\n", feature_name); return -ENODEV; } return simd_register_skciphers_compat(serpent_algs, ARRAY_SIZE(serpent_algs), serpent_simd_algs); } static void __exit serpent_avx2_fini(void) { simd_unregister_skciphers(serpent_algs, ARRAY_SIZE(serpent_algs), serpent_simd_algs); } module_init(serpent_avx2_init); module_exit(serpent_avx2_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX2 optimized"); MODULE_ALIAS_CRYPTO("serpent"); MODULE_ALIAS_CRYPTO("serpent-asm"); |
| 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 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 2 2 2 2 2 2 2 2 4 4 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * refcounttree.c * * Copyright (C) 2009 Oracle. All rights reserved. */ #include <linux/sort.h> #include <cluster/masklog.h> #include "ocfs2.h" #include "inode.h" #include "alloc.h" #include "suballoc.h" #include "journal.h" #include "uptodate.h" #include "super.h" #include "buffer_head_io.h" #include "blockcheck.h" #include "refcounttree.h" #include "sysfile.h" #include "dlmglue.h" #include "extent_map.h" #include "aops.h" #include "xattr.h" #include "namei.h" #include "ocfs2_trace.h" #include "file.h" #include "symlink.h" #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/slab.h> #include <linux/writeback.h> #include <linux/pagevec.h> #include <linux/swap.h> #include <linux/security.h> #include <linux/fsnotify.h> #include <linux/quotaops.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/posix_acl.h> struct ocfs2_cow_context { struct inode *inode; u32 cow_start; u32 cow_len; struct ocfs2_extent_tree data_et; struct ocfs2_refcount_tree *ref_tree; struct buffer_head *ref_root_bh; struct ocfs2_alloc_context *meta_ac; struct ocfs2_alloc_context *data_ac; struct ocfs2_cached_dealloc_ctxt dealloc; void *cow_object; struct ocfs2_post_refcount *post_refcount; int extra_credits; int (*get_clusters)(struct ocfs2_cow_context *context, u32 v_cluster, u32 *p_cluster, u32 *num_clusters, unsigned int *extent_flags); int (*cow_duplicate_clusters)(handle_t *handle, struct inode *inode, u32 cpos, u32 old_cluster, u32 new_cluster, u32 new_len); }; static inline struct ocfs2_refcount_tree * cache_info_to_refcount(struct ocfs2_caching_info *ci) { return container_of(ci, struct ocfs2_refcount_tree, rf_ci); } static int ocfs2_validate_refcount_block(struct super_block *sb, struct buffer_head *bh) { int rc; struct ocfs2_refcount_block *rb = (struct ocfs2_refcount_block *)bh->b_data; trace_ocfs2_validate_refcount_block((unsigned long long)bh->b_blocknr); BUG_ON(!buffer_uptodate(bh)); /* * If the ecc fails, we return the error but otherwise * leave the filesystem running. We know any error is * local to this block. */ rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &rb->rf_check); if (rc) { mlog(ML_ERROR, "Checksum failed for refcount block %llu\n", (unsigned long long)bh->b_blocknr); return rc; } if (!OCFS2_IS_VALID_REFCOUNT_BLOCK(rb)) { rc = ocfs2_error(sb, "Refcount block #%llu has bad signature %.*s\n", (unsigned long long)bh->b_blocknr, 7, rb->rf_signature); goto out; } if (le64_to_cpu(rb->rf_blkno) != bh->b_blocknr) { rc = ocfs2_error(sb, "Refcount block #%llu has an invalid rf_blkno of %llu\n", (unsigned long long)bh->b_blocknr, (unsigned long long)le64_to_cpu(rb->rf_blkno)); goto out; } if (le32_to_cpu(rb->rf_fs_generation) != OCFS2_SB(sb)->fs_generation) { rc = ocfs2_error(sb, "Refcount block #%llu has an invalid rf_fs_generation of #%u\n", (unsigned long long)bh->b_blocknr, le32_to_cpu(rb->rf_fs_generation)); goto out; } out: return rc; } static int ocfs2_read_refcount_block(struct ocfs2_caching_info *ci, u64 rb_blkno, struct buffer_head **bh) { int rc; struct buffer_head *tmp = *bh; rc = ocfs2_read_block(ci, rb_blkno, &tmp, ocfs2_validate_refcount_block); /* If ocfs2_read_block() got us a new bh, pass it up. */ if (!rc && !*bh) *bh = tmp; return rc; } static u64 ocfs2_refcount_cache_owner(struct ocfs2_caching_info *ci) { struct ocfs2_refcount_tree *rf = cache_info_to_refcount(ci); return rf->rf_blkno; } static struct super_block * ocfs2_refcount_cache_get_super(struct ocfs2_caching_info *ci) { struct ocfs2_refcount_tree *rf = cache_info_to_refcount(ci); return rf->rf_sb; } static void ocfs2_refcount_cache_lock(struct ocfs2_caching_info *ci) __acquires(&rf->rf_lock) { struct ocfs2_refcount_tree *rf = cache_info_to_refcount(ci); spin_lock(&rf->rf_lock); } static void ocfs2_refcount_cache_unlock(struct ocfs2_caching_info *ci) __releases(&rf->rf_lock) { struct ocfs2_refcount_tree *rf = cache_info_to_refcount(ci); spin_unlock(&rf->rf_lock); } static void ocfs2_refcount_cache_io_lock(struct ocfs2_caching_info *ci) { struct ocfs2_refcount_tree *rf = cache_info_to_refcount(ci); mutex_lock(&rf->rf_io_mutex); } static void ocfs2_refcount_cache_io_unlock(struct ocfs2_caching_info *ci) { struct ocfs2_refcount_tree *rf = cache_info_to_refcount(ci); mutex_unlock(&rf->rf_io_mutex); } static const struct ocfs2_caching_operations ocfs2_refcount_caching_ops = { .co_owner = ocfs2_refcount_cache_owner, .co_get_super = ocfs2_refcount_cache_get_super, .co_cache_lock = ocfs2_refcount_cache_lock, .co_cache_unlock = ocfs2_refcount_cache_unlock, .co_io_lock = ocfs2_refcount_cache_io_lock, .co_io_unlock = ocfs2_refcount_cache_io_unlock, }; static struct ocfs2_refcount_tree * ocfs2_find_refcount_tree(struct ocfs2_super *osb, u64 blkno) { struct rb_node *n = osb->osb_rf_lock_tree.rb_node; struct ocfs2_refcount_tree *tree = NULL; while (n) { tree = rb_entry(n, struct ocfs2_refcount_tree, rf_node); if (blkno < tree->rf_blkno) n = n->rb_left; else if (blkno > tree->rf_blkno) n = n->rb_right; else return tree; } return NULL; } /* osb_lock is already locked. */ static void ocfs2_insert_refcount_tree(struct ocfs2_super *osb, struct ocfs2_refcount_tree *new) { u64 rf_blkno = new->rf_blkno; struct rb_node *parent = NULL; struct rb_node **p = &osb->osb_rf_lock_tree.rb_node; struct ocfs2_refcount_tree *tmp; while (*p) { parent = *p; tmp = rb_entry(parent, struct ocfs2_refcount_tree, rf_node); if (rf_blkno < tmp->rf_blkno) p = &(*p)->rb_left; else if (rf_blkno > tmp->rf_blkno) p = &(*p)->rb_right; else { /* This should never happen! */ mlog(ML_ERROR, "Duplicate refcount block %llu found!\n", (unsigned long long)rf_blkno); BUG(); } } rb_link_node(&new->rf_node, parent, p); rb_insert_color(&new->rf_node, &osb->osb_rf_lock_tree); } static void ocfs2_free_refcount_tree(struct ocfs2_refcount_tree *tree) { ocfs2_metadata_cache_exit(&tree->rf_ci); ocfs2_simple_drop_lockres(OCFS2_SB(tree->rf_sb), &tree->rf_lockres); ocfs2_lock_res_free(&tree->rf_lockres); kfree(tree); } static inline void ocfs2_erase_refcount_tree_from_list_no_lock(struct ocfs2_super *osb, struct ocfs2_refcount_tree *tree) { rb_erase(&tree->rf_node, &osb->osb_rf_lock_tree); if (osb->osb_ref_tree_lru && osb->osb_ref_tree_lru == tree) osb->osb_ref_tree_lru = NULL; } static void ocfs2_erase_refcount_tree_from_list(struct ocfs2_super *osb, struct ocfs2_refcount_tree *tree) { spin_lock(&osb->osb_lock); ocfs2_erase_refcount_tree_from_list_no_lock(osb, tree); spin_unlock(&osb->osb_lock); } static void ocfs2_kref_remove_refcount_tree(struct kref *kref) { struct ocfs2_refcount_tree *tree = container_of(kref, struct ocfs2_refcount_tree, rf_getcnt); ocfs2_free_refcount_tree(tree); } static inline void ocfs2_refcount_tree_get(struct ocfs2_refcount_tree *tree) { kref_get(&tree->rf_getcnt); } static inline void ocfs2_refcount_tree_put(struct ocfs2_refcount_tree *tree) { kref_put(&tree->rf_getcnt, ocfs2_kref_remove_refcount_tree); } static inline void ocfs2_init_refcount_tree_ci(struct ocfs2_refcount_tree *new, struct super_block *sb) { ocfs2_metadata_cache_init(&new->rf_ci, &ocfs2_refcount_caching_ops); mutex_init(&new->rf_io_mutex); new->rf_sb = sb; spin_lock_init(&new->rf_lock); } static inline void ocfs2_init_refcount_tree_lock(struct ocfs2_super *osb, struct ocfs2_refcount_tree *new, u64 rf_blkno, u32 generation) { init_rwsem(&new->rf_sem); ocfs2_refcount_lock_res_init(&new->rf_lockres, osb, rf_blkno, generation); } static struct ocfs2_refcount_tree* ocfs2_allocate_refcount_tree(struct ocfs2_super *osb, u64 rf_blkno) { struct ocfs2_refcount_tree *new; new = kzalloc(sizeof(struct ocfs2_refcount_tree), GFP_NOFS); if (!new) return NULL; new->rf_blkno = rf_blkno; kref_init(&new->rf_getcnt); ocfs2_init_refcount_tree_ci(new, osb->sb); return new; } static int ocfs2_get_refcount_tree(struct ocfs2_super *osb, u64 rf_blkno, struct ocfs2_refcount_tree **ret_tree) { int ret = 0; struct ocfs2_refcount_tree *tree, *new = NULL; struct buffer_head *ref_root_bh = NULL; struct ocfs2_refcount_block *ref_rb; spin_lock(&osb->osb_lock); if (osb->osb_ref_tree_lru && osb->osb_ref_tree_lru->rf_blkno == rf_blkno) tree = osb->osb_ref_tree_lru; else tree = ocfs2_find_refcount_tree(osb, rf_blkno); if (tree) goto out; spin_unlock(&osb->osb_lock); new = ocfs2_allocate_refcount_tree(osb, rf_blkno); if (!new) { ret = -ENOMEM; mlog_errno(ret); return ret; } /* * We need the generation to create the refcount tree lock and since * it isn't changed during the tree modification, we are safe here to * read without protection. * We also have to purge the cache after we create the lock since the * refcount block may have the stale data. It can only be trusted when * we hold the refcount lock. */ ret = ocfs2_read_refcount_block(&new->rf_ci, rf_blkno, &ref_root_bh); if (ret) { mlog_errno(ret); ocfs2_metadata_cache_exit(&new->rf_ci); kfree(new); return ret; } ref_rb = (struct ocfs2_refcount_block *)ref_root_bh->b_data; new->rf_generation = le32_to_cpu(ref_rb->rf_generation); ocfs2_init_refcount_tree_lock(osb, new, rf_blkno, new->rf_generation); ocfs2_metadata_cache_purge(&new->rf_ci); spin_lock(&osb->osb_lock); tree = ocfs2_find_refcount_tree(osb, rf_blkno); if (tree) goto out; ocfs2_insert_refcount_tree(osb, new); tree = new; new = NULL; out: *ret_tree = tree; osb->osb_ref_tree_lru = tree; spin_unlock(&osb->osb_lock); if (new) ocfs2_free_refcount_tree(new); brelse(ref_root_bh); return ret; } static int ocfs2_get_refcount_block(struct inode *inode, u64 *ref_blkno) { int ret; struct buffer_head *di_bh = NULL; struct ocfs2_dinode *di; ret = ocfs2_read_inode_block(inode, &di_bh); if (ret) { mlog_errno(ret); goto out; } BUG_ON(!ocfs2_is_refcount_inode(inode)); di = (struct ocfs2_dinode *)di_bh->b_data; *ref_blkno = le64_to_cpu(di->i_refcount_loc); brelse(di_bh); out: return ret; } static int __ocfs2_lock_refcount_tree(struct ocfs2_super *osb, struct ocfs2_refcount_tree *tree, int rw) { int ret; ret = ocfs2_refcount_lock(tree, rw); if (ret) { mlog_errno(ret); goto out; } if (rw) down_write(&tree->rf_sem); else down_read(&tree->rf_sem); out: return ret; } /* * Lock the refcount tree pointed by ref_blkno and return the tree. * In most case, we lock the tree and read the refcount block. * So read it here if the caller really needs it. * * If the tree has been re-created by other node, it will free the * old one and re-create it. */ int ocfs2_lock_refcount_tree(struct ocfs2_super *osb, u64 ref_blkno, int rw, struct ocfs2_refcount_tree **ret_tree, struct buffer_head **ref_bh) { int ret, delete_tree = 0; struct ocfs2_refcount_tree *tree = NULL; struct buffer_head *ref_root_bh = NULL; struct ocfs2_refcount_block *rb; again: ret = ocfs2_get_refcount_tree(osb, ref_blkno, &tree); if (ret) { mlog_errno(ret); return ret; } ocfs2_refcount_tree_get(tree); ret = __ocfs2_lock_refcount_tree(osb, tree, rw); if (ret) { mlog_errno(ret); ocfs2_refcount_tree_put(tree); goto out; } ret = ocfs2_read_refcount_block(&tree->rf_ci, tree->rf_blkno, &ref_root_bh); if (ret) { mlog_errno(ret); ocfs2_unlock_refcount_tree(osb, tree, rw); goto out; } rb = (struct ocfs2_refcount_block *)ref_root_bh->b_data; /* * If the refcount block has been freed and re-created, we may need * to recreate the refcount tree also. * * Here we just remove the tree from the rb-tree, and the last * kref holder will unlock and delete this refcount_tree. * Then we goto "again" and ocfs2_get_refcount_tree will create * the new refcount tree for us. */ if (tree->rf_generation != le32_to_cpu(rb->rf_generation)) { if (!tree->rf_removed) { ocfs2_erase_refcount_tree_from_list(osb, tree); tree->rf_removed = 1; delete_tree = 1; } ocfs2_unlock_refcount_tree(osb, tree, rw); /* * We get an extra reference when we create the refcount * tree, so another put will destroy it. */ if (delete_tree) ocfs2_refcount_tree_put(tree); brelse(ref_root_bh); ref_root_bh = NULL; goto again; } *ret_tree = tree; if (ref_bh) { *ref_bh = ref_root_bh; ref_root_bh = NULL; } out: brelse(ref_root_bh); return ret; } void ocfs2_unlock_refcount_tree(struct ocfs2_super *osb, struct ocfs2_refcount_tree *tree, int rw) { if (rw) up_write(&tree->rf_sem); else up_read(&tree->rf_sem); ocfs2_refcount_unlock(tree, rw); ocfs2_refcount_tree_put(tree); } void ocfs2_purge_refcount_trees(struct ocfs2_super *osb) { struct rb_node *node; struct ocfs2_refcount_tree *tree; struct rb_root *root = &osb->osb_rf_lock_tree; while ((node = rb_last(root)) != NULL) { tree = rb_entry(node, struct ocfs2_refcount_tree, rf_node); trace_ocfs2_purge_refcount_trees( (unsigned long long) tree->rf_blkno); rb_erase(&tree->rf_node, root); ocfs2_free_refcount_tree(tree); } } /* * Create a refcount tree for an inode. * We take for granted that the inode is already locked. */ static int ocfs2_create_refcount_tree(struct inode *inode, struct buffer_head *di_bh) { int ret; handle_t *handle = NULL; struct ocfs2_alloc_context *meta_ac = NULL; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct buffer_head *new_bh = NULL; struct ocfs2_refcount_block *rb; struct ocfs2_refcount_tree *new_tree = NULL, *tree = NULL; u16 suballoc_bit_start; u32 num_got; u64 suballoc_loc, first_blkno; BUG_ON(ocfs2_is_refcount_inode(inode)); trace_ocfs2_create_refcount_tree( (unsigned long long)oi->ip_blkno); ret = ocfs2_reserve_new_metadata_blocks(osb, 1, &meta_ac); if (ret) { mlog_errno(ret); goto out; } handle = ocfs2_start_trans(osb, OCFS2_REFCOUNT_TREE_CREATE_CREDITS); if (IS_ERR(handle)) { ret = PTR_ERR(handle); 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); goto out_commit; } ret = ocfs2_claim_metadata(handle, meta_ac, 1, &suballoc_loc, &suballoc_bit_start, &num_got, &first_blkno); if (ret) { mlog_errno(ret); goto out_commit; } new_tree = ocfs2_allocate_refcount_tree(osb, first_blkno); if (!new_tree) { ret = -ENOMEM; mlog_errno(ret); goto out_commit; } new_bh = sb_getblk(inode->i_sb, first_blkno); if (!new_bh) { ret = -ENOMEM; mlog_errno(ret); goto out_commit; } ocfs2_set_new_buffer_uptodate(&new_tree->rf_ci, new_bh); ret = ocfs2_journal_access_rb(handle, &new_tree->rf_ci, new_bh, OCFS2_JOURNAL_ACCESS_CREATE); if (ret) { mlog_errno(ret); goto out_commit; } /* Initialize ocfs2_refcount_block. */ rb = (struct ocfs2_refcount_block *)new_bh->b_data; memset(rb, 0, inode->i_sb->s_blocksize); strcpy((void *)rb, OCFS2_REFCOUNT_BLOCK_SIGNATURE); rb->rf_suballoc_slot = cpu_to_le16(meta_ac->ac_alloc_slot); rb->rf_suballoc_loc = cpu_to_le64(suballoc_loc); rb->rf_suballoc_bit = cpu_to_le16(suballoc_bit_start); rb->rf_fs_generation = cpu_to_le32(osb->fs_generation); rb->rf_blkno = cpu_to_le64(first_blkno); rb->rf_count = cpu_to_le32(1); rb->rf_records.rl_count = cpu_to_le16(ocfs2_refcount_recs_per_rb(osb->sb)); spin_lock(&osb->osb_lock); rb->rf_generation = cpu_to_le32(osb->s_next_generation++); spin_unlock(&osb->osb_lock); ocfs2_journal_dirty(handle, new_bh); spin_lock(&oi->ip_lock); oi->ip_dyn_features |= OCFS2_HAS_REFCOUNT_FL; di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features); di->i_refcount_loc = cpu_to_le64(first_blkno); spin_unlock(&oi->ip_lock); trace_ocfs2_create_refcount_tree_blkno((unsigned long long)first_blkno); ocfs2_journal_dirty(handle, di_bh); /* * We have to init the tree lock here since it will use * the generation number to create it. */ new_tree->rf_generation = le32_to_cpu(rb->rf_generation); ocfs2_init_refcount_tree_lock(osb, new_tree, first_blkno, new_tree->rf_generation); spin_lock(&osb->osb_lock); tree = ocfs2_find_refcount_tree(osb, first_blkno); /* * We've just created a new refcount tree in this block. If * we found a refcount tree on the ocfs2_super, it must be * one we just deleted. We free the old tree before * inserting the new tree. */ BUG_ON(tree && tree->rf_generation == new_tree->rf_generation); if (tree) ocfs2_erase_refcount_tree_from_list_no_lock(osb, tree); ocfs2_insert_refcount_tree(osb, new_tree); spin_unlock(&osb->osb_lock); new_tree = NULL; if (tree) ocfs2_refcount_tree_put(tree); out_commit: ocfs2_commit_trans(osb, handle); out: if (new_tree) { ocfs2_metadata_cache_exit(&new_tree->rf_ci); kfree(new_tree); } brelse(new_bh); if (meta_ac) ocfs2_free_alloc_context(meta_ac); return ret; } static int ocfs2_set_refcount_tree(struct inode *inode, struct buffer_head *di_bh, u64 refcount_loc) { int ret; handle_t *handle = NULL; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct buffer_head *ref_root_bh = NULL; struct ocfs2_refcount_block *rb; struct ocfs2_refcount_tree *ref_tree; BUG_ON(ocfs2_is_refcount_inode(inode)); ret = ocfs2_lock_refcount_tree(osb, refcount_loc, 1, &ref_tree, &ref_root_bh); if (ret) { mlog_errno(ret); return ret; } handle = ocfs2_start_trans(osb, OCFS2_REFCOUNT_TREE_SET_CREDITS); if (IS_ERR(handle)) { ret = PTR_ERR(handle); 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); goto out_commit; } ret = ocfs2_journal_access_rb(handle, &ref_tree->rf_ci, ref_root_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_commit; } rb = (struct ocfs2_refcount_block *)ref_root_bh->b_data; le32_add_cpu(&rb->rf_count, 1); ocfs2_journal_dirty(handle, ref_root_bh); spin_lock(&oi->ip_lock); oi->ip_dyn_features |= OCFS2_HAS_REFCOUNT_FL; di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features); di->i_refcount_loc = cpu_to_le64(refcount_loc); spin_unlock(&oi->ip_lock); ocfs2_journal_dirty(handle, di_bh); out_commit: ocfs2_commit_trans(osb, handle); out: ocfs2_unlock_refcount_tree(osb, ref_tree, 1); brelse(ref_root_bh); return ret; } int ocfs2_remove_refcount_tree(struct inode *inode, struct buffer_head *di_bh) { int ret, delete_tree = 0; handle_t *handle = NULL; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_refcount_block *rb; struct inode *alloc_inode = NULL; struct buffer_head *alloc_bh = NULL; struct buffer_head *blk_bh = NULL; struct ocfs2_refcount_tree *ref_tree; int credits = OCFS2_REFCOUNT_TREE_REMOVE_CREDITS; u64 blk = 0, bg_blkno = 0, ref_blkno = le64_to_cpu(di->i_refcount_loc); u16 bit = 0; if (!ocfs2_is_refcount_inode(inode)) return 0; BUG_ON(!ref_blkno); ret = ocfs2_lock_refcount_tree(osb, ref_blkno, 1, &ref_tree, &blk_bh); if (ret) { mlog_errno(ret); return ret; } rb = (struct ocfs2_refcount_block *)blk_bh->b_data; /* * If we are the last user, we need to free the block. * So lock the allocator ahead. */ if (le32_to_cpu(rb->rf_count) == 1) { blk = le64_to_cpu(rb->rf_blkno); bit = le16_to_cpu(rb->rf_suballoc_bit); if (rb->rf_suballoc_loc) bg_blkno = le64_to_cpu(rb->rf_suballoc_loc); else bg_blkno = ocfs2_which_suballoc_group(blk, bit); alloc_inode = ocfs2_get_system_file_inode(osb, EXTENT_ALLOC_SYSTEM_INODE, le16_to_cpu(rb->rf_suballoc_slot)); if (!alloc_inode) { ret = -ENOMEM; mlog_errno(ret); goto out; } inode_lock(alloc_inode); ret = ocfs2_inode_lock(alloc_inode, &alloc_bh, 1); if (ret) { mlog_errno(ret); goto out_mutex; } credits += OCFS2_SUBALLOC_FREE; } handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto out_unlock; } ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_commit; } ret = ocfs2_journal_access_rb(handle, &ref_tree->rf_ci, blk_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_commit; } spin_lock(&oi->ip_lock); oi->ip_dyn_features &= ~OCFS2_HAS_REFCOUNT_FL; di->i_dyn_features = cpu_to_le16(oi->ip_dyn_features); di->i_refcount_loc = 0; spin_unlock(&oi->ip_lock); ocfs2_journal_dirty(handle, di_bh); le32_add_cpu(&rb->rf_count , -1); ocfs2_journal_dirty(handle, blk_bh); if (!rb->rf_count) { delete_tree = 1; ocfs2_erase_refcount_tree_from_list(osb, ref_tree); ret = ocfs2_free_suballoc_bits(handle, alloc_inode, alloc_bh, bit, bg_blkno, 1); if (ret) mlog_errno(ret); } out_commit: ocfs2_commit_trans(osb, handle); out_unlock: if (alloc_inode) { ocfs2_inode_unlock(alloc_inode, 1); brelse(alloc_bh); } out_mutex: if (alloc_inode) { inode_unlock(alloc_inode); iput(alloc_inode); } out: ocfs2_unlock_refcount_tree(osb, ref_tree, 1); if (delete_tree) ocfs2_refcount_tree_put(ref_tree); brelse(blk_bh); return ret; } static void ocfs2_find_refcount_rec_in_rl(struct ocfs2_caching_info *ci, struct buffer_head *ref_leaf_bh, u64 cpos, unsigned int len, struct ocfs2_refcount_rec *ret_rec, int *index) { int i = 0; struct ocfs2_refcount_block *rb = (struct ocfs2_refcount_block *)ref_leaf_bh->b_data; struct ocfs2_refcount_rec *rec = NULL; for (; i < le16_to_cpu(rb->rf_records.rl_used); i++) { rec = &rb->rf_records.rl_recs[i]; if (le64_to_cpu(rec->r_cpos) + le32_to_cpu(rec->r_clusters) <= cpos) continue; else if (le64_to_cpu(rec->r_cpos) > cpos) break; /* ok, cpos fail in this rec. Just return. */ if (ret_rec) *ret_rec = *rec; goto out; } if (ret_rec) { /* We meet with a hole here, so fake the rec. */ ret_rec->r_cpos = cpu_to_le64(cpos); ret_rec->r_refcount = 0; if (i < le16_to_cpu(rb->rf_records.rl_used) && le64_to_cpu(rec->r_cpos) < cpos + len) ret_rec->r_clusters = cpu_to_le32(le64_to_cpu(rec->r_cpos) - cpos); else ret_rec->r_clusters = cpu_to_le32(len); } out: *index = i; } /* * Try to remove refcount tree. The mechanism is: * 1) Check whether i_clusters == 0, if no, exit. * 2) check whether we have i_xattr_loc in dinode. if yes, exit. * 3) Check whether we have inline xattr stored outside, if yes, exit. * 4) Remove the tree. */ int ocfs2_try_remove_refcount_tree(struct inode *inode, struct buffer_head *di_bh) { int ret; struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; down_write(&oi->ip_xattr_sem); down_write(&oi->ip_alloc_sem); if (oi->ip_clusters) goto out; if ((oi->ip_dyn_features & OCFS2_HAS_XATTR_FL) && di->i_xattr_loc) goto out; if (oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL && ocfs2_has_inline_xattr_value_outside(inode, di)) goto out; ret = ocfs2_remove_refcount_tree(inode, di_bh); if (ret) mlog_errno(ret); out: up_write(&oi->ip_alloc_sem); up_write(&oi->ip_xattr_sem); return 0; } /* * Find the end range for a leaf refcount block indicated by * el->l_recs[index].e_blkno. */ static int ocfs2_get_refcount_cpos_end(struct ocfs2_caching_info *ci, struct buffer_head *ref_root_bh, struct ocfs2_extent_block *eb, struct ocfs2_extent_list *el, int index, u32 *cpos_end) { int ret, i, subtree_root; u32 cpos; u64 blkno; struct super_block *sb = ocfs2_metadata_cache_get_super(ci); struct ocfs2_path *left_path = NULL, *right_path = NULL; struct ocfs2_extent_tree et; struct ocfs2_extent_list *tmp_el; if (index < le16_to_cpu(el->l_next_free_rec) - 1) { /* * We have a extent rec after index, so just use the e_cpos * of the next extent rec. */ *cpos_end = le32_to_cpu(el->l_recs[index+1].e_cpos); return 0; } if (!eb || !eb->h_next_leaf_blk) { /* * We are the last extent rec, so any high cpos should * be stored in this leaf refcount block. */ *cpos_end = UINT_MAX; return 0; } /* * If the extent block isn't the last one, we have to find * the subtree root between this extent block and the next * leaf extent block and get the corresponding e_cpos from * the subroot. Otherwise we may corrupt the b-tree. */ ocfs2_init_refcount_extent_tree(&et, ci, ref_root_bh); left_path = ocfs2_new_path_from_et(&et); if (!left_path) { ret = -ENOMEM; mlog_errno(ret); goto out; } cpos = le32_to_cpu(eb->h_list.l_recs[index].e_cpos); ret = ocfs2_find_path(ci, left_path, cpos); if (ret) { mlog_errno(ret); goto out; } right_path = ocfs2_new_path_from_path(left_path); if (!right_path) { ret = -ENOMEM; mlog_errno(ret); goto out; } ret = ocfs2_find_cpos_for_right_leaf(sb, left_path, &cpos); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_find_path(ci, right_path, cpos); if (ret) { mlog_errno(ret); goto out; } subtree_root = ocfs2_find_subtree_root(&et, left_path, right_path); tmp_el = left_path->p_node[subtree_root].el; blkno = left_path->p_node[subtree_root+1].bh->b_blocknr; for (i = 0; i < le16_to_cpu(tmp_el->l_next_free_rec); i++) { if (le64_to_cpu(tmp_el->l_recs[i].e_blkno) == blkno) { *cpos_end = le32_to_cpu(tmp_el->l_recs[i+1].e_cpos); break; } } BUG_ON(i == le16_to_cpu(tmp_el->l_next_free_rec)); out: ocfs2_free_path(left_path); ocfs2_free_path(right_path); return ret; } /* * Given a cpos and len, try to find the refcount record which contains cpos. * 1. If cpos can be found in one refcount record, return the record. * 2. If cpos can't be found, return a fake record which start from cpos * and end at a small value between cpos+len and start of the next record. * This fake record has r_refcount = 0. */ static int ocfs2_get_refcount_rec(struct ocfs2_caching_info *ci, struct buffer_head *ref_root_bh, u64 cpos, unsigned int len, struct ocfs2_refcount_rec *ret_rec, int *index, struct buffer_head **ret_bh) { int ret = 0, i, found; u32 low_cpos, cpos_end; struct ocfs2_extent_list *el; struct ocfs2_extent_rec *rec = NULL; struct ocfs2_extent_block *eb = NULL; struct buffer_head *eb_bh = NULL, *ref_leaf_bh = NULL; struct super_block *sb = ocfs2_metadata_cache_get_super(ci); struct ocfs2_refcount_block *rb = (struct ocfs2_refcount_block *)ref_root_bh->b_data; if (!(le32_to_cpu(rb->rf_flags) & OCFS2_REFCOUNT_TREE_FL)) { ocfs2_find_refcount_rec_in_rl(ci, ref_root_bh, cpos, len, ret_rec, index); *ret_bh = ref_root_bh; get_bh(ref_root_bh); return 0; } el = &rb->rf_list; low_cpos = cpos & OCFS2_32BIT_POS_MASK; if (el->l_tree_depth) { ret = ocfs2_find_leaf(ci, el, low_cpos, &eb_bh); if (ret) { mlog_errno(ret); goto out; } eb = (struct ocfs2_extent_block *) eb_bh->b_data; el = &eb->h_list; if (el->l_tree_depth) { ret = ocfs2_error(sb, "refcount tree %llu has non zero tree depth in leaf btree tree block %llu\n", (unsigned long long)ocfs2_metadata_cache_owner(ci), (unsigned long long)eb_bh->b_blocknr); goto out; } } found = 0; 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) <= low_cpos) { found = 1; break; } } if (found) { ret = ocfs2_get_refcount_cpos_end(ci, ref_root_bh, eb, el, i, &cpos_end); if (ret) { mlog_errno(ret); goto out; } if (cpos_end < low_cpos + len) len = cpos_end - low_cpos; } ret = ocfs2_read_refcount_block(ci, le64_to_cpu(rec->e_blkno), &ref_leaf_bh); if (ret) { mlog_errno(ret); goto out; } ocfs2_find_refcount_rec_in_rl(ci, ref_leaf_bh, cpos, len, ret_rec, index); *ret_bh = ref_leaf_bh; out: brelse(eb_bh); return ret; } enum ocfs2_ref_rec_contig { REF_CONTIG_NONE = 0, REF_CONTIG_LEFT, REF_CONTIG_RIGHT, REF_CONTIG_LEFTRIGHT, }; static enum ocfs2_ref_rec_contig ocfs2_refcount_rec_adjacent(struct ocfs2_refcount_block *rb, int index) { if ((rb->rf_records.rl_recs[index].r_refcount == rb->rf_records.rl_recs[index + 1].r_refcount) && (le64_to_cpu(rb->rf_records.rl_recs[index].r_cpos) + le32_to_cpu(rb->rf_records.rl_recs[index].r_clusters) == le64_to_cpu(rb->rf_records.rl_recs[index + 1].r_cpos))) return REF_CONTIG_RIGHT; return REF_CONTIG_NONE; } static enum ocfs2_ref_rec_contig ocfs2_refcount_rec_contig(struct ocfs2_refcount_block *rb, int index) { enum ocfs2_ref_rec_contig ret = REF_CONTIG_NONE; if (index < le16_to_cpu(rb->rf_records.rl_used) - 1) ret = ocfs2_refcount_rec_adjacent(rb, index); if (index > 0) { enum ocfs2_ref_rec_contig tmp; tmp = ocfs2_refcount_rec_adjacent(rb, index - 1); if (tmp == REF_CONTIG_RIGHT) { if (ret == REF_CONTIG_RIGHT) ret = REF_CONTIG_LEFTRIGHT; else ret = REF_CONTIG_LEFT; } } return ret; } static void ocfs2_rotate_refcount_rec_left(struct ocfs2_refcount_block *rb, int index) { BUG_ON(rb->rf_records.rl_recs[index].r_refcount != rb->rf_records.rl_recs[index+1].r_refcount); le32_add_cpu(&rb->rf_records.rl_recs[index].r_clusters, le32_to_cpu(rb->rf_records.rl_recs[index+1].r_clusters)); if (index < le16_to_cpu(rb->rf_records.rl_used) - 2) memmove(&rb->rf_records.rl_recs[index + 1], &rb->rf_records.rl_recs[index + 2], sizeof(struct ocfs2_refcount_rec) * (le16_to_cpu(rb->rf_records.rl_used) - index - 2)); memset(&rb->rf_records.rl_recs[le16_to_cpu(rb->rf_records.rl_used) - 1], 0, sizeof(struct ocfs2_refcount_rec)); le16_add_cpu(&rb->rf_records.rl_used, -1); } /* * Merge the refcount rec if we are contiguous with the adjacent recs. */ static void ocfs2_refcount_rec_merge(struct ocfs2_refcount_block *rb, int index) { enum ocfs2_ref_rec_contig contig = ocfs2_refcount_rec_contig(rb, index); if (contig == REF_CONTIG_NONE) return; if (contig == REF_CONTIG_LEFT || contig == REF_CONTIG_LEFTRIGHT) { BUG_ON(index == 0); index--; } ocfs2_rotate_refcount_rec_left(rb, index); if (contig == REF_CONTIG_LEFTRIGHT) ocfs2_rotate_refcount_rec_left(rb, index); } /* * Change the refcount indexed by "index" in ref_bh. * If refcount reaches 0, remove it. */ static int ocfs2_change_refcount_rec(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *ref_leaf_bh, int index, int merge, int change) { int ret; struct ocfs2_refcount_block *rb = (struct ocfs2_refcount_block *)ref_leaf_bh->b_data; struct ocfs2_refcount_list *rl = &rb->rf_records; struct ocfs2_refcount_rec *rec = &rl->rl_recs[index]; ret = ocfs2_journal_access_rb(handle, ci, ref_leaf_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; } trace_ocfs2_change_refcount_rec( (unsigned long long)ocfs2_metadata_cache_owner(ci), index, le32_to_cpu(rec->r_refcount), change); le32_add_cpu(&rec->r_refcount, change); if (!rec->r_refcount) { if (index != le16_to_cpu(rl->rl_used) - 1) { memmove(rec, rec + 1, (le16_to_cpu(rl->rl_used) - index - 1) * sizeof(struct ocfs2_refcount_rec)); memset(&rl->rl_recs[le16_to_cpu(rl->rl_used) - 1], 0, sizeof(struct ocfs2_refcount_rec)); } le16_add_cpu(&rl->rl_used, -1); } else if (merge) ocfs2_refcount_rec_merge(rb, index); ocfs2_journal_dirty(handle, ref_leaf_bh); out: return ret; } static int ocfs2_expand_inline_ref_root(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *ref_root_bh, struct buffer_head **ref_leaf_bh, struct ocfs2_alloc_context *meta_ac) { int ret; u16 suballoc_bit_start; u32 num_got; u64 suballoc_loc, blkno; struct super_block *sb = ocfs2_metadata_cache_get_super(ci); struct buffer_head *new_bh = NULL; struct ocfs2_refcount_block *new_rb; struct ocfs2_refcount_block *root_rb = (struct ocfs2_refcount_block *)ref_root_bh->b_data; ret = ocfs2_journal_access_rb(handle, ci, ref_root_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_claim_metadata(handle, meta_ac, 1, &suballoc_loc, &suballoc_bit_start, &num_got, &blkno); if (ret) { mlog_errno(ret); goto out; } new_bh = sb_getblk(sb, blkno); if (new_bh == NULL) { ret = -ENOMEM; mlog_errno(ret); goto out; } ocfs2_set_new_buffer_uptodate(ci, new_bh); ret = ocfs2_journal_access_rb(handle, ci, new_bh, OCFS2_JOURNAL_ACCESS_CREATE); if (ret) { mlog_errno(ret); goto out; } /* * Initialize ocfs2_refcount_block. * It should contain the same information as the old root. * so just memcpy it and change the corresponding field. */ memcpy(new_bh->b_data, ref_root_bh->b_data, sb->s_blocksize); new_rb = (struct ocfs2_refcount_block *)new_bh->b_data; new_rb->rf_suballoc_slot = cpu_to_le16(meta_ac->ac_alloc_slot); new_rb->rf_suballoc_loc = cpu_to_le64(suballoc_loc); new_rb->rf_suballoc_bit = cpu_to_le16(suballoc_bit_start); new_rb->rf_blkno = cpu_to_le64(blkno); new_rb->rf_cpos = cpu_to_le32(0); new_rb->rf_parent = cpu_to_le64(ref_root_bh->b_blocknr); new_rb->rf_flags = cpu_to_le32(OCFS2_REFCOUNT_LEAF_FL); ocfs2_journal_dirty(handle, new_bh); /* Now change the root. */ memset(&root_rb->rf_list, 0, sb->s_blocksize - offsetof(struct ocfs2_refcount_block, rf_list)); root_rb->rf_list.l_count = cpu_to_le16(ocfs2_extent_recs_per_rb(sb)); root_rb->rf_clusters = cpu_to_le32(1); root_rb->rf_list.l_next_free_rec = cpu_to_le16(1); root_rb->rf_list.l_recs[0].e_blkno = cpu_to_le64(blkno); root_rb->rf_list.l_recs[0].e_leaf_clusters = cpu_to_le16(1); root_rb->rf_flags = cpu_to_le32(OCFS2_REFCOUNT_TREE_FL); ocfs2_journal_dirty(handle, ref_root_bh); trace_ocfs2_expand_inline_ref_root((unsigned long long)blkno, le16_to_cpu(new_rb->rf_records.rl_used)); *ref_leaf_bh = new_bh; new_bh = NULL; out: brelse(new_bh); return ret; } static int ocfs2_refcount_rec_no_intersect(struct ocfs2_refcount_rec *prev, struct ocfs2_refcount_rec *next) { if (ocfs2_get_ref_rec_low_cpos(prev) + le32_to_cpu(prev->r_clusters) <= ocfs2_get_ref_rec_low_cpos(next)) return 1; return 0; } static int cmp_refcount_rec_by_low_cpos(const void *a, const void *b) { const struct ocfs2_refcount_rec *l = a, *r = b; u32 l_cpos = ocfs2_get_ref_rec_low_cpos(l); u32 r_cpos = ocfs2_get_ref_rec_low_cpos(r); if (l_cpos > r_cpos) return 1; if (l_cpos < r_cpos) return -1; return 0; } static int cmp_refcount_rec_by_cpos(const void *a, const void *b) { const struct ocfs2_refcount_rec *l = a, *r = b; u64 l_cpos = le64_to_cpu(l->r_cpos); u64 r_cpos = le64_to_cpu(r->r_cpos); if (l_cpos > r_cpos) return 1; if (l_cpos < r_cpos) return -1; return 0; } /* * The refcount cpos are ordered by their 64bit cpos, * But we will use the low 32 bit to be the e_cpos in the b-tree. * So we need to make sure that this pos isn't intersected with others. * * Note: The refcount block is already sorted by their low 32 bit cpos, * So just try the middle pos first, and we will exit when we find * the good position. */ static int ocfs2_find_refcount_split_pos(struct ocfs2_refcount_list *rl, u32 *split_pos, int *split_index) { int num_used = le16_to_cpu(rl->rl_used); int delta, middle = num_used / 2; for (delta = 0; delta < middle; delta++) { /* Let's check delta earlier than middle */ if (ocfs2_refcount_rec_no_intersect( &rl->rl_recs[middle - delta - 1], &rl->rl_recs[middle - delta])) { *split_index = middle - delta; break; } /* For even counts, don't walk off the end */ if ((middle + delta + 1) == num_used) continue; /* Now try delta past middle */ if (ocfs2_refcount_rec_no_intersect( &rl->rl_recs[middle + delta], &rl->rl_recs[middle + delta + 1])) { *split_index = middle + delta + 1; break; } } if (delta >= middle) return -ENOSPC; *split_pos = ocfs2_get_ref_rec_low_cpos(&rl->rl_recs[*split_index]); return 0; } static int ocfs2_divide_leaf_refcount_block(struct buffer_head *ref_leaf_bh, struct buffer_head *new_bh, u32 *split_cpos) { int split_index = 0, num_moved, ret; u32 cpos = 0; struct ocfs2_refcount_block *rb = (struct ocfs2_refcount_block *)ref_leaf_bh->b_data; struct ocfs2_refcount_list *rl = &rb->rf_records; struct ocfs2_refcount_block *new_rb = (struct ocfs2_refcount_block *)new_bh->b_data; struct ocfs2_refcount_list *new_rl = &new_rb->rf_records; trace_ocfs2_divide_leaf_refcount_block( (unsigned long long)ref_leaf_bh->b_blocknr, le16_to_cpu(rl->rl_count), le16_to_cpu(rl->rl_used)); /* * XXX: Improvement later. * If we know all the high 32 bit cpos is the same, no need to sort. * * In order to make the whole process safe, we do: * 1. sort the entries by their low 32 bit cpos first so that we can * find the split cpos easily. * 2. call ocfs2_insert_extent to insert the new refcount block. * 3. move the refcount rec to the new block. * 4. sort the entries by their 64 bit cpos. * 5. dirty the new_rb and rb. */ sort(&rl->rl_recs, le16_to_cpu(rl->rl_used), sizeof(struct ocfs2_refcount_rec), cmp_refcount_rec_by_low_cpos, NULL); ret = ocfs2_find_refcount_split_pos(rl, &cpos, &split_index); if (ret) { mlog_errno(ret); return ret; } new_rb->rf_cpos = cpu_to_le32(cpos); /* move refcount records starting from split_index to the new block. */ num_moved = le16_to_cpu(rl->rl_used) - split_index; memcpy(new_rl->rl_recs, &rl->rl_recs[split_index], num_moved * sizeof(struct ocfs2_refcount_rec)); /*ok, remove the entries we just moved over to the other block. */ memset(&rl->rl_recs[split_index], 0, num_moved * sizeof(struct ocfs2_refcount_rec)); /* change old and new rl_used accordingly. */ le16_add_cpu(&rl->rl_used, -num_moved); new_rl->rl_used = cpu_to_le16(num_moved); sort(&rl->rl_recs, le16_to_cpu(rl->rl_used), sizeof(struct ocfs2_refcount_rec), cmp_refcount_rec_by_cpos, NULL); sort(&new_rl->rl_recs, le16_to_cpu(new_rl->rl_used), sizeof(struct ocfs2_refcount_rec), cmp_refcount_rec_by_cpos, NULL); *split_cpos = cpos; return 0; } static int ocfs2_new_leaf_refcount_block(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *ref_root_bh, struct buffer_head *ref_leaf_bh, struct ocfs2_alloc_context *meta_ac) { int ret; u16 suballoc_bit_start; u32 num_got, new_cpos; u64 suballoc_loc, blkno; struct super_block *sb = ocfs2_metadata_cache_get_super(ci); struct ocfs2_refcount_block *root_rb = (struct ocfs2_refcount_block *)ref_root_bh->b_data; struct buffer_head *new_bh = NULL; struct ocfs2_refcount_block *new_rb; struct ocfs2_extent_tree ref_et; BUG_ON(!(le32_to_cpu(root_rb->rf_flags) & OCFS2_REFCOUNT_TREE_FL)); ret = ocfs2_journal_access_rb(handle, ci, ref_root_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_journal_access_rb(handle, ci, ref_leaf_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_claim_metadata(handle, meta_ac, 1, &suballoc_loc, &suballoc_bit_start, &num_got, &blkno); if (ret) { mlog_errno(ret); goto out; } new_bh = sb_getblk(sb, blkno); if (new_bh == NULL) { ret = -ENOMEM; mlog_errno(ret); goto out; } ocfs2_set_new_buffer_uptodate(ci, new_bh); ret = ocfs2_journal_access_rb(handle, ci, new_bh, OCFS2_JOURNAL_ACCESS_CREATE); if (ret) { mlog_errno(ret); goto out; } /* Initialize ocfs2_refcount_block. */ new_rb = (struct ocfs2_refcount_block *)new_bh->b_data; memset(new_rb, 0, sb->s_blocksize); strcpy((void *)new_rb, OCFS2_REFCOUNT_BLOCK_SIGNATURE); new_rb->rf_suballoc_slot = cpu_to_le16(meta_ac->ac_alloc_slot); new_rb->rf_suballoc_loc = cpu_to_le64(suballoc_loc); new_rb->rf_suballoc_bit = cpu_to_le16(suballoc_bit_start); new_rb->rf_fs_generation = cpu_to_le32(OCFS2_SB(sb)->fs_generation); new_rb->rf_blkno = cpu_to_le64(blkno); new_rb->rf_parent = cpu_to_le64(ref_root_bh->b_blocknr); new_rb->rf_flags = cpu_to_le32(OCFS2_REFCOUNT_LEAF_FL); new_rb->rf_records.rl_count = cpu_to_le16(ocfs2_refcount_recs_per_rb(sb)); new_rb->rf_generation = root_rb->rf_generation; ret = ocfs2_divide_leaf_refcount_block(ref_leaf_bh, new_bh, &new_cpos); if (ret) { mlog_errno(ret); goto out; } ocfs2_journal_dirty(handle, ref_leaf_bh); ocfs2_journal_dirty(handle, new_bh); ocfs2_init_refcount_extent_tree(&ref_et, ci, ref_root_bh); trace_ocfs2_new_leaf_refcount_block( (unsigned long long)new_bh->b_blocknr, new_cpos); /* Insert the new leaf block with the specific offset cpos. */ ret = ocfs2_insert_extent(handle, &ref_et, new_cpos, new_bh->b_blocknr, 1, 0, meta_ac); if (ret) mlog_errno(ret); out: brelse(new_bh); return ret; } static int ocfs2_expand_refcount_tree(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *ref_root_bh, struct buffer_head *ref_leaf_bh, struct ocfs2_alloc_context *meta_ac) { int ret; struct buffer_head *expand_bh = NULL; if (ref_root_bh == ref_leaf_bh) { /* * the old root bh hasn't been expanded to a b-tree, * so expand it first. */ ret = ocfs2_expand_inline_ref_root(handle, ci, ref_root_bh, &expand_bh, meta_ac); if (ret) { mlog_errno(ret); goto out; } } else { expand_bh = ref_leaf_bh; get_bh(expand_bh); } /* Now add a new refcount block into the tree.*/ ret = ocfs2_new_leaf_refcount_block(handle, ci, ref_root_bh, expand_bh, meta_ac); if (ret) mlog_errno(ret); out: brelse(expand_bh); return ret; } /* * Adjust the extent rec in b-tree representing ref_leaf_bh. * * Only called when we have inserted a new refcount rec at index 0 * which means ocfs2_extent_rec.e_cpos may need some change. */ static int ocfs2_adjust_refcount_rec(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *ref_root_bh, struct buffer_head *ref_leaf_bh, struct ocfs2_refcount_rec *rec) { int ret = 0, i; u32 new_cpos, old_cpos; struct ocfs2_path *path = NULL; struct ocfs2_extent_tree et; struct ocfs2_refcount_block *rb = (struct ocfs2_refcount_block *)ref_root_bh->b_data; struct ocfs2_extent_list *el; if (!(le32_to_cpu(rb->rf_flags) & OCFS2_REFCOUNT_TREE_FL)) goto out; rb = (struct ocfs2_refcount_block *)ref_leaf_bh->b_data; old_cpos = le32_to_cpu(rb->rf_cpos); new_cpos = le64_to_cpu(rec->r_cpos) & OCFS2_32BIT_POS_MASK; if (old_cpos <= new_cpos) goto out; ocfs2_init_refcount_extent_tree(&et, ci, ref_root_bh); path = ocfs2_new_path_from_et(&et); if (!path) { ret = -ENOMEM; mlog_errno(ret); goto out; } ret = ocfs2_find_path(ci, path, old_cpos); if (ret) { mlog_errno(ret); goto out; } /* * 2 more credits, one for the leaf refcount block, one for * the extent block contains the extent rec. */ ret = ocfs2_extend_trans(handle, 2); if (ret < 0) { mlog_errno(ret); goto out; } ret = ocfs2_journal_access_rb(handle, ci, ref_leaf_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret < 0) { mlog_errno(ret); goto out; } ret = ocfs2_journal_access_eb(handle, ci, path_leaf_bh(path), OCFS2_JOURNAL_ACCESS_WRITE); if (ret < 0) { mlog_errno(ret); goto out; } /* change the leaf extent block first. */ el = path_leaf_el(path); for (i = 0; i < le16_to_cpu(el->l_next_free_rec); i++) if (le32_to_cpu(el->l_recs[i].e_cpos) == old_cpos) break; BUG_ON(i == le16_to_cpu(el->l_next_free_rec)); el->l_recs[i].e_cpos = cpu_to_le32(new_cpos); /* change the r_cpos in the leaf block. */ rb->rf_cpos = cpu_to_le32(new_cpos); ocfs2_journal_dirty(handle, path_leaf_bh(path)); ocfs2_journal_dirty(handle, ref_leaf_bh); out: ocfs2_free_path(path); return ret; } static int ocfs2_insert_refcount_rec(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *ref_root_bh, struct buffer_head *ref_leaf_bh, struct ocfs2_refcount_rec *rec, int index, int merge, struct ocfs2_alloc_context *meta_ac) { int ret; struct ocfs2_refcount_block *rb = (struct ocfs2_refcount_block *)ref_leaf_bh->b_data; struct ocfs2_refcount_list *rf_list = &rb->rf_records; struct buffer_head *new_bh = NULL; BUG_ON(le32_to_cpu(rb->rf_flags) & OCFS2_REFCOUNT_TREE_FL); if (rf_list->rl_used == rf_list->rl_count) { u64 cpos = le64_to_cpu(rec->r_cpos); u32 len = le32_to_cpu(rec->r_clusters); ret = ocfs2_expand_refcount_tree(handle, ci, ref_root_bh, ref_leaf_bh, meta_ac); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_get_refcount_rec(ci, ref_root_bh, cpos, len, NULL, &index, &new_bh); if (ret) { mlog_errno(ret); goto out; } ref_leaf_bh = new_bh; rb = (struct ocfs2_refcount_block *)ref_leaf_bh->b_data; rf_list = &rb->rf_records; } ret = ocfs2_journal_access_rb(handle, ci, ref_leaf_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; } if (index < le16_to_cpu(rf_list->rl_used)) memmove(&rf_list->rl_recs[index + 1], &rf_list->rl_recs[index], (le16_to_cpu(rf_list->rl_used) - index) * sizeof(struct ocfs2_refcount_rec)); trace_ocfs2_insert_refcount_rec( (unsigned long long)ref_leaf_bh->b_blocknr, index, (unsigned long long)le64_to_cpu(rec->r_cpos), le32_to_cpu(rec->r_clusters), le32_to_cpu(rec->r_refcount)); rf_list->rl_recs[index] = *rec; le16_add_cpu(&rf_list->rl_used, 1); if (merge) ocfs2_refcount_rec_merge(rb, index); ocfs2_journal_dirty(handle, ref_leaf_bh); if (index == 0) { ret = ocfs2_adjust_refcount_rec(handle, ci, ref_root_bh, ref_leaf_bh, rec); if (ret) mlog_errno(ret); } out: brelse(new_bh); return ret; } /* * Split the refcount_rec indexed by "index" in ref_leaf_bh. * This is much simple than our b-tree code. * split_rec is the new refcount rec we want to insert. * If split_rec->r_refcount > 0, we are changing the refcount(in case we * increase refcount or decrease a refcount to non-zero). * If split_rec->r_refcount == 0, we are punching a hole in current refcount * rec( in case we decrease a refcount to zero). */ static int ocfs2_split_refcount_rec(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *ref_root_bh, struct buffer_head *ref_leaf_bh, struct ocfs2_refcount_rec *split_rec, int index, int merge, struct ocfs2_alloc_context *meta_ac, struct ocfs2_cached_dealloc_ctxt *dealloc) { int ret, recs_need; u32 len; struct ocfs2_refcount_block *rb = (struct ocfs2_refcount_block *)ref_leaf_bh->b_data; struct ocfs2_refcount_list *rf_list = &rb->rf_records; struct ocfs2_refcount_rec *orig_rec = &rf_list->rl_recs[index]; struct ocfs2_refcount_rec *tail_rec = NULL; struct buffer_head *new_bh = NULL; BUG_ON(le32_to_cpu(rb->rf_flags) & OCFS2_REFCOUNT_TREE_FL); trace_ocfs2_split_refcount_rec(le64_to_cpu(orig_rec->r_cpos), le32_to_cpu(orig_rec->r_clusters), le32_to_cpu(orig_rec->r_refcount), le64_to_cpu(split_rec->r_cpos), le32_to_cpu(split_rec->r_clusters), le32_to_cpu(split_rec->r_refcount)); /* * If we just need to split the header or tail clusters, * no more recs are needed, just split is OK. * Otherwise we at least need one new recs. */ if (!split_rec->r_refcount && (split_rec->r_cpos == orig_rec->r_cpos || le64_to_cpu(split_rec->r_cpos) + le32_to_cpu(split_rec->r_clusters) == le64_to_cpu(orig_rec->r_cpos) + le32_to_cpu(orig_rec->r_clusters))) recs_need = 0; else recs_need = 1; /* * We need one more rec if we split in the middle and the new rec have * some refcount in it. */ if (split_rec->r_refcount && (split_rec->r_cpos != orig_rec->r_cpos && le64_to_cpu(split_rec->r_cpos) + le32_to_cpu(split_rec->r_clusters) != le64_to_cpu(orig_rec->r_cpos) + le32_to_cpu(orig_rec->r_clusters))) recs_need++; /* If the leaf block don't have enough record, expand it. */ if (le16_to_cpu(rf_list->rl_used) + recs_need > le16_to_cpu(rf_list->rl_count)) { struct ocfs2_refcount_rec tmp_rec; u64 cpos = le64_to_cpu(orig_rec->r_cpos); len = le32_to_cpu(orig_rec->r_clusters); ret = ocfs2_expand_refcount_tree(handle, ci, ref_root_bh, ref_leaf_bh, meta_ac); if (ret) { mlog_errno(ret); goto out; } /* * We have to re-get it since now cpos may be moved to * another leaf block. */ ret = ocfs2_get_refcount_rec(ci, ref_root_bh, cpos, len, &tmp_rec, &index, &new_bh); if (ret) { mlog_errno(ret); goto out; } ref_leaf_bh = new_bh; rb = (struct ocfs2_refcount_block *)ref_leaf_bh->b_data; rf_list = &rb->rf_records; orig_rec = &rf_list->rl_recs[index]; } ret = ocfs2_journal_access_rb(handle, ci, ref_leaf_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; } /* * We have calculated out how many new records we need and store * in recs_need, so spare enough space first by moving the records * after "index" to the end. */ if (index != le16_to_cpu(rf_list->rl_used) - 1) memmove(&rf_list->rl_recs[index + 1 + recs_need], &rf_list->rl_recs[index + 1], (le16_to_cpu(rf_list->rl_used) - index - 1) * sizeof(struct ocfs2_refcount_rec)); len = (le64_to_cpu(orig_rec->r_cpos) + le32_to_cpu(orig_rec->r_clusters)) - (le64_to_cpu(split_rec->r_cpos) + le32_to_cpu(split_rec->r_clusters)); /* * If we have "len", the we will split in the tail and move it * to the end of the space we have just spared. */ if (len) { tail_rec = &rf_list->rl_recs[index + recs_need]; memcpy(tail_rec, orig_rec, sizeof(struct ocfs2_refcount_rec)); le64_add_cpu(&tail_rec->r_cpos, le32_to_cpu(tail_rec->r_clusters) - len); tail_rec->r_clusters = cpu_to_le32(len); } /* * If the split pos isn't the same as the original one, we need to * split in the head. * * Note: We have the chance that split_rec.r_refcount = 0, * recs_need = 0 and len > 0, which means we just cut the head from * the orig_rec and in that case we have done some modification in * orig_rec above, so the check for r_cpos is faked. */ if (split_rec->r_cpos != orig_rec->r_cpos && tail_rec != orig_rec) { len = le64_to_cpu(split_rec->r_cpos) - le64_to_cpu(orig_rec->r_cpos); orig_rec->r_clusters = cpu_to_le32(len); index++; } le16_add_cpu(&rf_list->rl_used, recs_need); if (split_rec->r_refcount) { rf_list->rl_recs[index] = *split_rec; trace_ocfs2_split_refcount_rec_insert( (unsigned long long)ref_leaf_bh->b_blocknr, index, (unsigned long long)le64_to_cpu(split_rec->r_cpos), le32_to_cpu(split_rec->r_clusters), le32_to_cpu(split_rec->r_refcount)); if (merge) ocfs2_refcount_rec_merge(rb, index); } ocfs2_journal_dirty(handle, ref_leaf_bh); out: brelse(new_bh); return ret; } static int __ocfs2_increase_refcount(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *ref_root_bh, u64 cpos, u32 len, int merge, struct ocfs2_alloc_context *meta_ac, struct ocfs2_cached_dealloc_ctxt *dealloc) { int ret = 0, index; struct buffer_head *ref_leaf_bh = NULL; struct ocfs2_refcount_rec rec; unsigned int set_len = 0; trace_ocfs2_increase_refcount_begin( (unsigned long long)ocfs2_metadata_cache_owner(ci), (unsigned long long)cpos, len); while (len) { ret = ocfs2_get_refcount_rec(ci, ref_root_bh, cpos, len, &rec, &index, &ref_leaf_bh); if (ret) { mlog_errno(ret); goto out; } set_len = le32_to_cpu(rec.r_clusters); /* * Here we may meet with 3 situations: * * 1. If we find an already existing record, and the length * is the same, cool, we just need to increase the r_refcount * and it is OK. * 2. If we find a hole, just insert it with r_refcount = 1. * 3. If we are in the middle of one extent record, split * it. */ if (rec.r_refcount && le64_to_cpu(rec.r_cpos) == cpos && set_len <= len) { trace_ocfs2_increase_refcount_change( (unsigned long long)cpos, set_len, le32_to_cpu(rec.r_refcount)); ret = ocfs2_change_refcount_rec(handle, ci, ref_leaf_bh, index, merge, 1); if (ret) { mlog_errno(ret); goto out; } } else if (!rec.r_refcount) { rec.r_refcount = cpu_to_le32(1); trace_ocfs2_increase_refcount_insert( (unsigned long long)le64_to_cpu(rec.r_cpos), set_len); ret = ocfs2_insert_refcount_rec(handle, ci, ref_root_bh, ref_leaf_bh, &rec, index, merge, meta_ac); if (ret) { mlog_errno(ret); goto out; } } else { set_len = min((u64)(cpos + len), le64_to_cpu(rec.r_cpos) + set_len) - cpos; rec.r_cpos = cpu_to_le64(cpos); rec.r_clusters = cpu_to_le32(set_len); le32_add_cpu(&rec.r_refcount, 1); trace_ocfs2_increase_refcount_split( (unsigned long long)le64_to_cpu(rec.r_cpos), set_len, le32_to_cpu(rec.r_refcount)); ret = ocfs2_split_refcount_rec(handle, ci, ref_root_bh, ref_leaf_bh, &rec, index, merge, meta_ac, dealloc); if (ret) { mlog_errno(ret); goto out; } } cpos += set_len; len -= set_len; brelse(ref_leaf_bh); ref_leaf_bh = NULL; } out: brelse(ref_leaf_bh); return ret; } static int ocfs2_remove_refcount_extent(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *ref_root_bh, struct buffer_head *ref_leaf_bh, struct ocfs2_alloc_context *meta_ac, struct ocfs2_cached_dealloc_ctxt *dealloc) { int ret; struct super_block *sb = ocfs2_metadata_cache_get_super(ci); struct ocfs2_refcount_block *rb = (struct ocfs2_refcount_block *)ref_leaf_bh->b_data; struct ocfs2_extent_tree et; BUG_ON(rb->rf_records.rl_used); trace_ocfs2_remove_refcount_extent( (unsigned long long)ocfs2_metadata_cache_owner(ci), (unsigned long long)ref_leaf_bh->b_blocknr, le32_to_cpu(rb->rf_cpos)); ocfs2_init_refcount_extent_tree(&et, ci, ref_root_bh); ret = ocfs2_remove_extent(handle, &et, le32_to_cpu(rb->rf_cpos), 1, meta_ac, dealloc); if (ret) { mlog_errno(ret); goto out; } ocfs2_remove_from_cache(ci, ref_leaf_bh); /* * add the freed block to the dealloc so that it will be freed * when we run dealloc. */ ret = ocfs2_cache_block_dealloc(dealloc, EXTENT_ALLOC_SYSTEM_INODE, le16_to_cpu(rb->rf_suballoc_slot), le64_to_cpu(rb->rf_suballoc_loc), le64_to_cpu(rb->rf_blkno), le16_to_cpu(rb->rf_suballoc_bit)); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_journal_access_rb(handle, ci, ref_root_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out; } rb = (struct ocfs2_refcount_block *)ref_root_bh->b_data; le32_add_cpu(&rb->rf_clusters, -1); /* * check whether we need to restore the root refcount block if * there is no leaf extent block at atll. */ if (!rb->rf_list.l_next_free_rec) { BUG_ON(rb->rf_clusters); trace_ocfs2_restore_refcount_block( (unsigned long long)ref_root_bh->b_blocknr); rb->rf_flags = 0; rb->rf_parent = 0; rb->rf_cpos = 0; memset(&rb->rf_records, 0, sb->s_blocksize - offsetof(struct ocfs2_refcount_block, rf_records)); rb->rf_records.rl_count = cpu_to_le16(ocfs2_refcount_recs_per_rb(sb)); } ocfs2_journal_dirty(handle, ref_root_bh); out: return ret; } int ocfs2_increase_refcount(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *ref_root_bh, u64 cpos, u32 len, struct ocfs2_alloc_context *meta_ac, struct ocfs2_cached_dealloc_ctxt *dealloc) { return __ocfs2_increase_refcount(handle, ci, ref_root_bh, cpos, len, 1, meta_ac, dealloc); } static int ocfs2_decrease_refcount_rec(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *ref_root_bh, struct buffer_head *ref_leaf_bh, int index, u64 cpos, unsigned int len, struct ocfs2_alloc_context *meta_ac, struct ocfs2_cached_dealloc_ctxt *dealloc) { int ret; struct ocfs2_refcount_block *rb = (struct ocfs2_refcount_block *)ref_leaf_bh->b_data; struct ocfs2_refcount_rec *rec = &rb->rf_records.rl_recs[index]; BUG_ON(cpos < le64_to_cpu(rec->r_cpos)); BUG_ON(cpos + len > le64_to_cpu(rec->r_cpos) + le32_to_cpu(rec->r_clusters)); trace_ocfs2_decrease_refcount_rec( (unsigned long long)ocfs2_metadata_cache_owner(ci), (unsigned long long)cpos, len); if (cpos == le64_to_cpu(rec->r_cpos) && len == le32_to_cpu(rec->r_clusters)) ret = ocfs2_change_refcount_rec(handle, ci, ref_leaf_bh, index, 1, -1); else { struct ocfs2_refcount_rec split = *rec; split.r_cpos = cpu_to_le64(cpos); split.r_clusters = cpu_to_le32(len); le32_add_cpu(&split.r_refcount, -1); ret = ocfs2_split_refcount_rec(handle, ci, ref_root_bh, ref_leaf_bh, &split, index, 1, meta_ac, dealloc); } if (ret) { mlog_errno(ret); goto out; } /* Remove the leaf refcount block if it contains no refcount record. */ if (!rb->rf_records.rl_used && ref_leaf_bh != ref_root_bh) { ret = ocfs2_remove_refcount_extent(handle, ci, ref_root_bh, ref_leaf_bh, meta_ac, dealloc); if (ret) mlog_errno(ret); } out: return ret; } static int __ocfs2_decrease_refcount(handle_t *handle, struct ocfs2_caching_info *ci, struct buffer_head *ref_root_bh, u64 cpos, u32 len, struct ocfs2_alloc_context *meta_ac, struct ocfs2_cached_dealloc_ctxt *dealloc, int delete) { int ret = 0, index = 0; struct ocfs2_refcount_rec rec; unsigned int r_count = 0, r_len; struct super_block *sb = ocfs2_metadata_cache_get_super(ci); struct buffer_head *ref_leaf_bh = NULL; trace_ocfs2_decrease_refcount( (unsigned long long)ocfs2_metadata_cache_owner(ci), (unsigned long long)cpos, len, delete); while (len) { ret = ocfs2_get_refcount_rec(ci, ref_root_bh, cpos, len, &rec, &index, &ref_leaf_bh); if (ret) { mlog_errno(ret); goto out; } r_count = le32_to_cpu(rec.r_refcount); BUG_ON(r_count == 0); if (!delete) BUG_ON(r_count > 1); r_len = min((u64)(cpos + len), le64_to_cpu(rec.r_cpos) + le32_to_cpu(rec.r_clusters)) - cpos; ret = ocfs2_decrease_refcount_rec(handle, ci, ref_root_bh, ref_leaf_bh, index, cpos, r_len, meta_ac, dealloc); if (ret) { mlog_errno(ret); goto out; } if (le32_to_cpu(rec.r_refcount) == 1 && delete) { ret = ocfs2_cache_cluster_dealloc(dealloc, ocfs2_clusters_to_blocks(sb, cpos), r_len); if (ret) { mlog_errno(ret); goto out; } } cpos += r_len; len -= r_len; brelse(ref_leaf_bh); ref_leaf_bh = NULL; } out: brelse(ref_leaf_bh); return ret; } /* Caller must hold refcount tree lock. */ int ocfs2_decrease_refcount(struct inode *inode, handle_t *handle, u32 cpos, u32 len, struct ocfs2_alloc_context *meta_ac, struct ocfs2_cached_dealloc_ctxt *dealloc, int delete) { int ret; u64 ref_blkno; struct buffer_head *ref_root_bh = NULL; struct ocfs2_refcount_tree *tree; BUG_ON(!ocfs2_is_refcount_inode(inode)); ret = ocfs2_get_refcount_block(inode, &ref_blkno); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_get_refcount_tree(OCFS2_SB(inode->i_sb), ref_blkno, &tree); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_read_refcount_block(&tree->rf_ci, tree->rf_blkno, &ref_root_bh); if (ret) { mlog_errno(ret); goto out; } ret = __ocfs2_decrease_refcount(handle, &tree->rf_ci, ref_root_bh, cpos, len, meta_ac, dealloc, delete); if (ret) mlog_errno(ret); out: brelse(ref_root_bh); return ret; } /* * Mark the already-existing extent at cpos as refcounted for len clusters. * This adds the refcount extent flag. * * If the existing extent is larger than the request, initiate a * split. An attempt will be made at merging with adjacent extents. * * The caller is responsible for passing down meta_ac if we'll need it. */ static int ocfs2_mark_extent_refcounted(struct inode *inode, struct ocfs2_extent_tree *et, handle_t *handle, u32 cpos, u32 len, u32 phys, struct ocfs2_alloc_context *meta_ac, struct ocfs2_cached_dealloc_ctxt *dealloc) { int ret; trace_ocfs2_mark_extent_refcounted(OCFS2_I(inode)->ip_blkno, cpos, len, phys); if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) { ret = ocfs2_error(inode->i_sb, "Inode %lu want to use refcount tree, but the feature bit is not set in the super block\n", inode->i_ino); goto out; } ret = ocfs2_change_extent_flag(handle, et, cpos, len, phys, meta_ac, dealloc, OCFS2_EXT_REFCOUNTED, 0); if (ret) mlog_errno(ret); out: return ret; } /* * Given some contiguous physical clusters, calculate what we need * for modifying their refcount. */ static int ocfs2_calc_refcount_meta_credits(struct super_block *sb, struct ocfs2_caching_info *ci, struct buffer_head *ref_root_bh, u64 start_cpos, u32 clusters, int *meta_add, int *credits) { int ret = 0, index, ref_blocks = 0, recs_add = 0; u64 cpos = start_cpos; struct ocfs2_refcount_block *rb; struct ocfs2_refcount_rec rec; struct buffer_head *ref_leaf_bh = NULL, *prev_bh = NULL; u32 len; while (clusters) { ret = ocfs2_get_refcount_rec(ci, ref_root_bh, cpos, clusters, &rec, &index, &ref_leaf_bh); if (ret) { mlog_errno(ret); goto out; } if (ref_leaf_bh != prev_bh) { /* * Now we encounter a new leaf block, so calculate * whether we need to extend the old leaf. */ if (prev_bh) { rb = (struct ocfs2_refcount_block *) prev_bh->b_data; if (le16_to_cpu(rb->rf_records.rl_used) + recs_add > le16_to_cpu(rb->rf_records.rl_count)) ref_blocks++; } recs_add = 0; *credits += 1; brelse(prev_bh); prev_bh = ref_leaf_bh; get_bh(prev_bh); } trace_ocfs2_calc_refcount_meta_credits_iterate( recs_add, (unsigned long long)cpos, clusters, (unsigned long long)le64_to_cpu(rec.r_cpos), le32_to_cpu(rec.r_clusters), le32_to_cpu(rec.r_refcount), index); len = min((u64)cpos + clusters, le64_to_cpu(rec.r_cpos) + le32_to_cpu(rec.r_clusters)) - cpos; /* * We record all the records which will be inserted to the * same refcount block, so that we can tell exactly whether * we need a new refcount block or not. * * If we will insert a new one, this is easy and only happens * during adding refcounted flag to the extent, so we don't * have a chance of splitting. We just need one record. * * If the refcount rec already exists, that would be a little * complicated. we may have to: * 1) split at the beginning if the start pos isn't aligned. * we need 1 more record in this case. * 2) split int the end if the end pos isn't aligned. * we need 1 more record in this case. * 3) split in the middle because of file system fragmentation. * we need 2 more records in this case(we can't detect this * beforehand, so always think of the worst case). */ if (rec.r_refcount) { recs_add += 2; /* Check whether we need a split at the beginning. */ if (cpos == start_cpos && cpos != le64_to_cpu(rec.r_cpos)) recs_add++; /* Check whether we need a split in the end. */ if (cpos + clusters < le64_to_cpu(rec.r_cpos) + le32_to_cpu(rec.r_clusters)) recs_add++; } else recs_add++; brelse(ref_leaf_bh); ref_leaf_bh = NULL; clusters -= len; cpos += len; } if (prev_bh) { rb = (struct ocfs2_refcount_block *)prev_bh->b_data; if (le16_to_cpu(rb->rf_records.rl_used) + recs_add > le16_to_cpu(rb->rf_records.rl_count)) ref_blocks++; *credits += 1; } if (!ref_blocks) goto out; *meta_add += ref_blocks; *credits += ref_blocks; /* * So we may need ref_blocks to insert into the tree. * That also means we need to change the b-tree and add that number * of records since we never merge them. * We need one more block for expansion since the new created leaf * block is also full and needs split. */ rb = (struct ocfs2_refcount_block *)ref_root_bh->b_data; if (le32_to_cpu(rb->rf_flags) & OCFS2_REFCOUNT_TREE_FL) { struct ocfs2_extent_tree et; ocfs2_init_refcount_extent_tree(&et, ci, ref_root_bh); *meta_add += ocfs2_extend_meta_needed(et.et_root_el); *credits += ocfs2_calc_extend_credits(sb, et.et_root_el); } else { *credits += OCFS2_EXPAND_REFCOUNT_TREE_CREDITS; *meta_add += 1; } out: trace_ocfs2_calc_refcount_meta_credits( (unsigned long long)start_cpos, clusters, *meta_add, *credits); brelse(ref_leaf_bh); brelse(prev_bh); return ret; } /* * For refcount tree, we will decrease some contiguous clusters * refcount count, so just go through it to see how many blocks * we gonna touch and whether we need to create new blocks. * * Normally the refcount blocks store these refcount should be * contiguous also, so that we can get the number easily. * We will at most add split 2 refcount records and 2 more * refcount blocks, so just check it in a rough way. * * Caller must hold refcount tree lock. */ int ocfs2_prepare_refcount_change_for_del(struct inode *inode, u64 refcount_loc, u64 phys_blkno, u32 clusters, int *credits, int *ref_blocks) { int ret; struct buffer_head *ref_root_bh = NULL; struct ocfs2_refcount_tree *tree; u64 start_cpos = ocfs2_blocks_to_clusters(inode->i_sb, phys_blkno); if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) { ret = ocfs2_error(inode->i_sb, "Inode %lu want to use refcount tree, but the feature bit is not set in the super block\n", inode->i_ino); goto out; } BUG_ON(!ocfs2_is_refcount_inode(inode)); ret = ocfs2_get_refcount_tree(OCFS2_SB(inode->i_sb), refcount_loc, &tree); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_read_refcount_block(&tree->rf_ci, refcount_loc, &ref_root_bh); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_calc_refcount_meta_credits(inode->i_sb, &tree->rf_ci, ref_root_bh, start_cpos, clusters, ref_blocks, credits); if (ret) { mlog_errno(ret); goto out; } trace_ocfs2_prepare_refcount_change_for_del(*ref_blocks, *credits); out: brelse(ref_root_bh); return ret; } #define MAX_CONTIG_BYTES 1048576 static inline unsigned int ocfs2_cow_contig_clusters(struct super_block *sb) { return ocfs2_clusters_for_bytes(sb, MAX_CONTIG_BYTES); } static inline unsigned int ocfs2_cow_contig_mask(struct super_block *sb) { return ~(ocfs2_cow_contig_clusters(sb) - 1); } /* * Given an extent that starts at 'start' and an I/O that starts at 'cpos', * find an offset (start + (n * contig_clusters)) that is closest to cpos * while still being less than or equal to it. * * The goal is to break the extent at a multiple of contig_clusters. */ static inline unsigned int ocfs2_cow_align_start(struct super_block *sb, unsigned int start, unsigned int cpos) { BUG_ON(start > cpos); return start + ((cpos - start) & ocfs2_cow_contig_mask(sb)); } /* * Given a cluster count of len, pad it out so that it is a multiple * of contig_clusters. */ static inline unsigned int ocfs2_cow_align_length(struct super_block *sb, unsigned int len) { unsigned int padded = (len + (ocfs2_cow_contig_clusters(sb) - 1)) & ocfs2_cow_contig_mask(sb); /* Did we wrap? */ if (padded < len) padded = UINT_MAX; return padded; } /* * Calculate out the start and number of virtual clusters we need to CoW. * * cpos is virtual start cluster position we want to do CoW in a * file and write_len is the cluster length. * max_cpos is the place where we want to stop CoW intentionally. * * Normal we will start CoW from the beginning of extent record containing cpos. * We try to break up extents on boundaries of MAX_CONTIG_BYTES so that we * get good I/O from the resulting extent tree. */ static int ocfs2_refcount_cal_cow_clusters(struct inode *inode, struct ocfs2_extent_list *el, u32 cpos, u32 write_len, u32 max_cpos, u32 *cow_start, u32 *cow_len) { int ret = 0; int tree_height = le16_to_cpu(el->l_tree_depth), i; struct buffer_head *eb_bh = NULL; struct ocfs2_extent_block *eb = NULL; struct ocfs2_extent_rec *rec; unsigned int want_clusters, rec_end = 0; int contig_clusters = ocfs2_cow_contig_clusters(inode->i_sb); int leaf_clusters; BUG_ON(cpos + write_len > max_cpos); if (tree_height > 0) { ret = ocfs2_find_leaf(INODE_CACHE(inode), el, cpos, &eb_bh); if (ret) { mlog_errno(ret); goto out; } eb = (struct ocfs2_extent_block *) eb_bh->b_data; el = &eb->h_list; if (el->l_tree_depth) { ret = ocfs2_error(inode->i_sb, "Inode %lu has non zero tree depth in leaf block %llu\n", inode->i_ino, (unsigned long long)eb_bh->b_blocknr); goto out; } } *cow_len = 0; for (i = 0; i < le16_to_cpu(el->l_next_free_rec); i++) { rec = &el->l_recs[i]; if (ocfs2_is_empty_extent(rec)) { mlog_bug_on_msg(i != 0, "Inode %lu has empty record in " "index %d\n", inode->i_ino, i); continue; } if (le32_to_cpu(rec->e_cpos) + le16_to_cpu(rec->e_leaf_clusters) <= cpos) continue; if (*cow_len == 0) { /* * We should find a refcounted record in the * first pass. */ BUG_ON(!(rec->e_flags & OCFS2_EXT_REFCOUNTED)); *cow_start = le32_to_cpu(rec->e_cpos); } /* * If we encounter a hole, a non-refcounted record or * pass the max_cpos, stop the search. */ if ((!(rec->e_flags & OCFS2_EXT_REFCOUNTED)) || (*cow_len && rec_end != le32_to_cpu(rec->e_cpos)) || (max_cpos <= le32_to_cpu(rec->e_cpos))) break; leaf_clusters = le16_to_cpu(rec->e_leaf_clusters); rec_end = le32_to_cpu(rec->e_cpos) + leaf_clusters; if (rec_end > max_cpos) { rec_end = max_cpos; leaf_clusters = rec_end - le32_to_cpu(rec->e_cpos); } /* * How many clusters do we actually need from * this extent? First we see how many we actually * need to complete the write. If that's smaller * than contig_clusters, we try for contig_clusters. */ if (!*cow_len) want_clusters = write_len; else want_clusters = (cpos + write_len) - (*cow_start + *cow_len); if (want_clusters < contig_clusters) want_clusters = contig_clusters; /* * If the write does not cover the whole extent, we * need to calculate how we're going to split the extent. * We try to do it on contig_clusters boundaries. * * Any extent smaller than contig_clusters will be * CoWed in its entirety. */ if (leaf_clusters <= contig_clusters) *cow_len += leaf_clusters; else if (*cow_len || (*cow_start == cpos)) { /* * This extent needs to be CoW'd from its * beginning, so all we have to do is compute * how many clusters to grab. We align * want_clusters to the edge of contig_clusters * to get better I/O. */ want_clusters = ocfs2_cow_align_length(inode->i_sb, want_clusters); if (leaf_clusters < want_clusters) *cow_len += leaf_clusters; else *cow_len += want_clusters; } else if ((*cow_start + contig_clusters) >= (cpos + write_len)) { /* * Breaking off contig_clusters at the front * of the extent will cover our write. That's * easy. */ *cow_len = contig_clusters; } else if ((rec_end - cpos) <= contig_clusters) { /* * Breaking off contig_clusters at the tail of * this extent will cover cpos. */ *cow_start = rec_end - contig_clusters; *cow_len = contig_clusters; } else if ((rec_end - cpos) <= want_clusters) { /* * While we can't fit the entire write in this * extent, we know that the write goes from cpos * to the end of the extent. Break that off. * We try to break it at some multiple of * contig_clusters from the front of the extent. * Failing that (ie, cpos is within * contig_clusters of the front), we'll CoW the * entire extent. */ *cow_start = ocfs2_cow_align_start(inode->i_sb, *cow_start, cpos); *cow_len = rec_end - *cow_start; } else { /* * Ok, the entire write lives in the middle of * this extent. Let's try to slice the extent up * nicely. Optimally, our CoW region starts at * m*contig_clusters from the beginning of the * extent and goes for n*contig_clusters, * covering the entire write. */ *cow_start = ocfs2_cow_align_start(inode->i_sb, *cow_start, cpos); want_clusters = (cpos + write_len) - *cow_start; want_clusters = ocfs2_cow_align_length(inode->i_sb, want_clusters); if (*cow_start + want_clusters <= rec_end) *cow_len = want_clusters; else *cow_len = rec_end - *cow_start; } /* Have we covered our entire write yet? */ if ((*cow_start + *cow_len) >= (cpos + write_len)) break; /* * If we reach the end of the extent block and don't get enough * clusters, continue with the next extent block if possible. */ if (i + 1 == le16_to_cpu(el->l_next_free_rec) && eb && eb->h_next_leaf_blk) { brelse(eb_bh); eb_bh = NULL; ret = ocfs2_read_extent_block(INODE_CACHE(inode), le64_to_cpu(eb->h_next_leaf_blk), &eb_bh); if (ret) { mlog_errno(ret); goto out; } eb = (struct ocfs2_extent_block *) eb_bh->b_data; el = &eb->h_list; i = -1; } } out: brelse(eb_bh); return ret; } /* * Prepare meta_ac, data_ac and calculate credits when we want to add some * num_clusters in data_tree "et" and change the refcount for the old * clusters(starting form p_cluster) in the refcount tree. * * Note: * 1. since we may split the old tree, so we at most will need num_clusters + 2 * more new leaf records. * 2. In some case, we may not need to reserve new clusters(e.g, reflink), so * just give data_ac = NULL. */ static int ocfs2_lock_refcount_allocators(struct super_block *sb, u32 p_cluster, u32 num_clusters, struct ocfs2_extent_tree *et, struct ocfs2_caching_info *ref_ci, struct buffer_head *ref_root_bh, struct ocfs2_alloc_context **meta_ac, struct ocfs2_alloc_context **data_ac, int *credits) { int ret = 0, meta_add = 0; int num_free_extents = ocfs2_num_free_extents(et); if (num_free_extents < 0) { ret = num_free_extents; mlog_errno(ret); goto out; } if (num_free_extents < num_clusters + 2) meta_add = ocfs2_extend_meta_needed(et->et_root_el); *credits += ocfs2_calc_extend_credits(sb, et->et_root_el); ret = ocfs2_calc_refcount_meta_credits(sb, ref_ci, ref_root_bh, p_cluster, num_clusters, &meta_add, credits); if (ret) { mlog_errno(ret); goto out; } trace_ocfs2_lock_refcount_allocators(meta_add, *credits); ret = ocfs2_reserve_new_metadata_blocks(OCFS2_SB(sb), meta_add, meta_ac); if (ret) { mlog_errno(ret); goto out; } if (data_ac) { ret = ocfs2_reserve_clusters(OCFS2_SB(sb), num_clusters, data_ac); if (ret) mlog_errno(ret); } out: if (ret) { if (*meta_ac) { ocfs2_free_alloc_context(*meta_ac); *meta_ac = NULL; } } return ret; } static int ocfs2_clear_cow_buffer(handle_t *handle, struct buffer_head *bh) { BUG_ON(buffer_dirty(bh)); clear_buffer_mapped(bh); return 0; } int ocfs2_duplicate_clusters_by_page(handle_t *handle, struct inode *inode, u32 cpos, u32 old_cluster, u32 new_cluster, u32 new_len) { int ret = 0, partial; struct super_block *sb = inode->i_sb; u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster); pgoff_t page_index; unsigned int from, to; loff_t offset, end, map_end; struct address_space *mapping = inode->i_mapping; trace_ocfs2_duplicate_clusters_by_page(cpos, old_cluster, new_cluster, new_len); offset = ((loff_t)cpos) << OCFS2_SB(sb)->s_clustersize_bits; end = offset + (new_len << OCFS2_SB(sb)->s_clustersize_bits); /* * We only duplicate pages until we reach the page contains i_size - 1. * So trim 'end' to i_size. */ if (end > i_size_read(inode)) end = i_size_read(inode); while (offset < end) { struct folio *folio; page_index = offset >> PAGE_SHIFT; map_end = ((loff_t)page_index + 1) << PAGE_SHIFT; if (map_end > end) map_end = end; /* from, to is the offset within the page. */ from = offset & (PAGE_SIZE - 1); to = PAGE_SIZE; if (map_end & (PAGE_SIZE - 1)) to = map_end & (PAGE_SIZE - 1); retry: folio = __filemap_get_folio(mapping, page_index, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, GFP_NOFS); if (IS_ERR(folio)) { ret = PTR_ERR(folio); mlog_errno(ret); break; } /* * In case PAGE_SIZE <= CLUSTER_SIZE, we do not expect a dirty * page, so write it back. */ if (PAGE_SIZE <= OCFS2_SB(sb)->s_clustersize) { if (folio_test_dirty(folio)) { folio_unlock(folio); folio_put(folio); ret = filemap_write_and_wait_range(mapping, offset, map_end - 1); goto retry; } } if (!folio_test_uptodate(folio)) { ret = block_read_full_folio(folio, ocfs2_get_block); if (ret) { mlog_errno(ret); goto unlock; } folio_lock(folio); } if (folio_buffers(folio)) { ret = walk_page_buffers(handle, folio_buffers(folio), from, to, &partial, ocfs2_clear_cow_buffer); if (ret) { mlog_errno(ret); goto unlock; } } ocfs2_map_and_dirty_folio(inode, handle, from, to, folio, 0, &new_block); folio_mark_accessed(folio); unlock: folio_unlock(folio); folio_put(folio); offset = map_end; if (ret) break; } return ret; } int ocfs2_duplicate_clusters_by_jbd(handle_t *handle, struct inode *inode, u32 cpos, u32 old_cluster, u32 new_cluster, u32 new_len) { int ret = 0; struct super_block *sb = inode->i_sb; struct ocfs2_caching_info *ci = INODE_CACHE(inode); int i, blocks = ocfs2_clusters_to_blocks(sb, new_len); u64 old_block = ocfs2_clusters_to_blocks(sb, old_cluster); u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster); struct ocfs2_super *osb = OCFS2_SB(sb); struct buffer_head *old_bh = NULL; struct buffer_head *new_bh = NULL; trace_ocfs2_duplicate_clusters_by_page(cpos, old_cluster, new_cluster, new_len); for (i = 0; i < blocks; i++, old_block++, new_block++) { new_bh = sb_getblk(osb->sb, new_block); if (new_bh == NULL) { ret = -ENOMEM; mlog_errno(ret); break; } ocfs2_set_new_buffer_uptodate(ci, new_bh); ret = ocfs2_read_block(ci, old_block, &old_bh, NULL); if (ret) { mlog_errno(ret); break; } ret = ocfs2_journal_access(handle, ci, new_bh, OCFS2_JOURNAL_ACCESS_CREATE); if (ret) { mlog_errno(ret); break; } memcpy(new_bh->b_data, old_bh->b_data, sb->s_blocksize); ocfs2_journal_dirty(handle, new_bh); brelse(new_bh); brelse(old_bh); new_bh = NULL; old_bh = NULL; } brelse(new_bh); brelse(old_bh); return ret; } static int ocfs2_clear_ext_refcount(handle_t *handle, struct ocfs2_extent_tree *et, u32 cpos, u32 p_cluster, u32 len, unsigned int ext_flags, struct ocfs2_alloc_context *meta_ac, struct ocfs2_cached_dealloc_ctxt *dealloc) { int ret, index; struct ocfs2_extent_rec replace_rec; struct ocfs2_path *path = NULL; struct ocfs2_extent_list *el; struct super_block *sb = ocfs2_metadata_cache_get_super(et->et_ci); u64 ino = ocfs2_metadata_cache_owner(et->et_ci); trace_ocfs2_clear_ext_refcount((unsigned long long)ino, cpos, len, p_cluster, ext_flags); memset(&replace_rec, 0, sizeof(replace_rec)); replace_rec.e_cpos = cpu_to_le32(cpos); replace_rec.e_leaf_clusters = cpu_to_le16(len); replace_rec.e_blkno = cpu_to_le64(ocfs2_clusters_to_blocks(sb, p_cluster)); replace_rec.e_flags = ext_flags; replace_rec.e_flags &= ~OCFS2_EXT_REFCOUNTED; path = ocfs2_new_path_from_et(et); if (!path) { ret = -ENOMEM; mlog_errno(ret); goto out; } ret = ocfs2_find_path(et->et_ci, path, cpos); if (ret) { mlog_errno(ret); goto out; } el = path_leaf_el(path); index = ocfs2_search_extent_list(el, cpos); if (index == -1) { ret = ocfs2_error(sb, "Inode %llu has an extent at cpos %u which can no longer be found\n", (unsigned long long)ino, cpos); goto out; } ret = ocfs2_split_extent(handle, et, path, index, &replace_rec, meta_ac, dealloc); if (ret) mlog_errno(ret); out: ocfs2_free_path(path); return ret; } static int ocfs2_replace_clusters(handle_t *handle, struct ocfs2_cow_context *context, u32 cpos, u32 old, u32 new, u32 len, unsigned int ext_flags) { int ret; struct ocfs2_caching_info *ci = context->data_et.et_ci; u64 ino = ocfs2_metadata_cache_owner(ci); trace_ocfs2_replace_clusters((unsigned long long)ino, cpos, old, new, len, ext_flags); /*If the old clusters is unwritten, no need to duplicate. */ if (!(ext_flags & OCFS2_EXT_UNWRITTEN)) { ret = context->cow_duplicate_clusters(handle, context->inode, cpos, old, new, len); if (ret) { mlog_errno(ret); goto out; } } ret = ocfs2_clear_ext_refcount(handle, &context->data_et, cpos, new, len, ext_flags, context->meta_ac, &context->dealloc); if (ret) mlog_errno(ret); out: return ret; } int ocfs2_cow_sync_writeback(struct super_block *sb, struct inode *inode, u32 cpos, u32 num_clusters) { int ret; loff_t start, end; if (ocfs2_should_order_data(inode)) return 0; start = ((loff_t)cpos) << OCFS2_SB(sb)->s_clustersize_bits; end = start + (num_clusters << OCFS2_SB(sb)->s_clustersize_bits) - 1; ret = filemap_write_and_wait_range(inode->i_mapping, start, end); if (ret < 0) mlog_errno(ret); return ret; } static int ocfs2_di_get_clusters(struct ocfs2_cow_context *context, u32 v_cluster, u32 *p_cluster, u32 *num_clusters, unsigned int *extent_flags) { return ocfs2_get_clusters(context->inode, v_cluster, p_cluster, num_clusters, extent_flags); } static int ocfs2_make_clusters_writable(struct super_block *sb, struct ocfs2_cow_context *context, u32 cpos, u32 p_cluster, u32 num_clusters, unsigned int e_flags) { int ret, delete, index, credits = 0; u32 new_bit, new_len, orig_num_clusters; unsigned int set_len; struct ocfs2_super *osb = OCFS2_SB(sb); handle_t *handle; struct buffer_head *ref_leaf_bh = NULL; struct ocfs2_caching_info *ref_ci = &context->ref_tree->rf_ci; struct ocfs2_refcount_rec rec; trace_ocfs2_make_clusters_writable(cpos, p_cluster, num_clusters, e_flags); ret = ocfs2_lock_refcount_allocators(sb, p_cluster, num_clusters, &context->data_et, ref_ci, context->ref_root_bh, &context->meta_ac, &context->data_ac, &credits); if (ret) { mlog_errno(ret); return ret; } if (context->post_refcount) credits += context->post_refcount->credits; credits += context->extra_credits; handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto out; } orig_num_clusters = num_clusters; while (num_clusters) { ret = ocfs2_get_refcount_rec(ref_ci, context->ref_root_bh, p_cluster, num_clusters, &rec, &index, &ref_leaf_bh); if (ret) { mlog_errno(ret); goto out_commit; } BUG_ON(!rec.r_refcount); set_len = min((u64)p_cluster + num_clusters, le64_to_cpu(rec.r_cpos) + le32_to_cpu(rec.r_clusters)) - p_cluster; /* * There are many different situation here. * 1. If refcount == 1, remove the flag and don't COW. * 2. If refcount > 1, allocate clusters. * Here we may not allocate r_len once at a time, so continue * until we reach num_clusters. */ if (le32_to_cpu(rec.r_refcount) == 1) { delete = 0; ret = ocfs2_clear_ext_refcount(handle, &context->data_et, cpos, p_cluster, set_len, e_flags, context->meta_ac, &context->dealloc); if (ret) { mlog_errno(ret); goto out_commit; } } else { delete = 1; ret = __ocfs2_claim_clusters(handle, context->data_ac, 1, set_len, &new_bit, &new_len); if (ret) { mlog_errno(ret); goto out_commit; } ret = ocfs2_replace_clusters(handle, context, cpos, p_cluster, new_bit, new_len, e_flags); if (ret) { mlog_errno(ret); goto out_commit; } set_len = new_len; } ret = __ocfs2_decrease_refcount(handle, ref_ci, context->ref_root_bh, p_cluster, set_len, context->meta_ac, &context->dealloc, delete); if (ret) { mlog_errno(ret); goto out_commit; } cpos += set_len; p_cluster += set_len; num_clusters -= set_len; brelse(ref_leaf_bh); ref_leaf_bh = NULL; } /* handle any post_cow action. */ if (context->post_refcount && context->post_refcount->func) { ret = context->post_refcount->func(context->inode, handle, context->post_refcount->para); if (ret) { mlog_errno(ret); goto out_commit; } } /* * Here we should write the new page out first if we are * in write-back mode. */ if (context->get_clusters == ocfs2_di_get_clusters) { ret = ocfs2_cow_sync_writeback(sb, context->inode, cpos, orig_num_clusters); if (ret) mlog_errno(ret); } out_commit: ocfs2_commit_trans(osb, handle); out: if (context->data_ac) { ocfs2_free_alloc_context(context->data_ac); context->data_ac = NULL; } if (context->meta_ac) { ocfs2_free_alloc_context(context->meta_ac); context->meta_ac = NULL; } brelse(ref_leaf_bh); return ret; } static int ocfs2_replace_cow(struct ocfs2_cow_context *context) { int ret = 0; struct inode *inode = context->inode; u32 cow_start = context->cow_start, cow_len = context->cow_len; u32 p_cluster, num_clusters; unsigned int ext_flags; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); if (!ocfs2_refcount_tree(osb)) { return ocfs2_error(inode->i_sb, "Inode %lu want to use refcount tree, but the feature bit is not set in the super block\n", inode->i_ino); } ocfs2_init_dealloc_ctxt(&context->dealloc); while (cow_len) { ret = context->get_clusters(context, cow_start, &p_cluster, &num_clusters, &ext_flags); if (ret) { mlog_errno(ret); break; } BUG_ON(!(ext_flags & OCFS2_EXT_REFCOUNTED)); if (cow_len < num_clusters) num_clusters = cow_len; ret = ocfs2_make_clusters_writable(inode->i_sb, context, cow_start, p_cluster, num_clusters, ext_flags); if (ret) { mlog_errno(ret); break; } cow_len -= num_clusters; cow_start += num_clusters; } if (ocfs2_dealloc_has_cluster(&context->dealloc)) { ocfs2_schedule_truncate_log_flush(osb, 1); ocfs2_run_deallocs(osb, &context->dealloc); } return ret; } /* * Starting at cpos, try to CoW write_len clusters. Don't CoW * past max_cpos. This will stop when it runs into a hole or an * unrefcounted extent. */ static int ocfs2_refcount_cow_hunk(struct inode *inode, struct buffer_head *di_bh, u32 cpos, u32 write_len, u32 max_cpos) { int ret; u32 cow_start = 0, cow_len = 0; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct buffer_head *ref_root_bh = NULL; struct ocfs2_refcount_tree *ref_tree; struct ocfs2_cow_context *context = NULL; BUG_ON(!ocfs2_is_refcount_inode(inode)); ret = ocfs2_refcount_cal_cow_clusters(inode, &di->id2.i_list, cpos, write_len, max_cpos, &cow_start, &cow_len); if (ret) { mlog_errno(ret); goto out; } trace_ocfs2_refcount_cow_hunk(OCFS2_I(inode)->ip_blkno, cpos, write_len, max_cpos, cow_start, cow_len); BUG_ON(cow_len == 0); context = kzalloc(sizeof(struct ocfs2_cow_context), GFP_NOFS); if (!context) { ret = -ENOMEM; mlog_errno(ret); goto out; } ret = ocfs2_lock_refcount_tree(osb, le64_to_cpu(di->i_refcount_loc), 1, &ref_tree, &ref_root_bh); if (ret) { mlog_errno(ret); goto out; } context->inode = inode; context->cow_start = cow_start; context->cow_len = cow_len; context->ref_tree = ref_tree; context->ref_root_bh = ref_root_bh; context->cow_duplicate_clusters = ocfs2_duplicate_clusters_by_page; context->get_clusters = ocfs2_di_get_clusters; ocfs2_init_dinode_extent_tree(&context->data_et, INODE_CACHE(inode), di_bh); ret = ocfs2_replace_cow(context); if (ret) mlog_errno(ret); /* * truncate the extent map here since no matter whether we meet with * any error during the action, we shouldn't trust cached extent map * any more. */ ocfs2_extent_map_trunc(inode, cow_start); ocfs2_unlock_refcount_tree(osb, ref_tree, 1); brelse(ref_root_bh); out: kfree(context); return ret; } /* * CoW any and all clusters between cpos and cpos+write_len. * Don't CoW past max_cpos. If this returns successfully, all * clusters between cpos and cpos+write_len are safe to modify. */ int ocfs2_refcount_cow(struct inode *inode, struct buffer_head *di_bh, u32 cpos, u32 write_len, u32 max_cpos) { int ret = 0; u32 p_cluster, num_clusters; unsigned int ext_flags; while (write_len) { ret = ocfs2_get_clusters(inode, cpos, &p_cluster, &num_clusters, &ext_flags); if (ret) { mlog_errno(ret); break; } if (write_len < num_clusters) num_clusters = write_len; if (ext_flags & OCFS2_EXT_REFCOUNTED) { ret = ocfs2_refcount_cow_hunk(inode, di_bh, cpos, num_clusters, max_cpos); if (ret) { mlog_errno(ret); break; } } write_len -= num_clusters; cpos += num_clusters; } return ret; } static int ocfs2_xattr_value_get_clusters(struct ocfs2_cow_context *context, u32 v_cluster, u32 *p_cluster, u32 *num_clusters, unsigned int *extent_flags) { struct inode *inode = context->inode; struct ocfs2_xattr_value_root *xv = context->cow_object; return ocfs2_xattr_get_clusters(inode, v_cluster, p_cluster, num_clusters, &xv->xr_list, extent_flags); } /* * Given a xattr value root, calculate the most meta/credits we need for * refcount tree change if we truncate it to 0. */ int ocfs2_refcounted_xattr_delete_need(struct inode *inode, struct ocfs2_caching_info *ref_ci, struct buffer_head *ref_root_bh, struct ocfs2_xattr_value_root *xv, int *meta_add, int *credits) { int ret = 0, index, ref_blocks = 0; u32 p_cluster, num_clusters; u32 cpos = 0, clusters = le32_to_cpu(xv->xr_clusters); struct ocfs2_refcount_block *rb; struct ocfs2_refcount_rec rec; struct buffer_head *ref_leaf_bh = NULL; while (cpos < clusters) { ret = ocfs2_xattr_get_clusters(inode, cpos, &p_cluster, &num_clusters, &xv->xr_list, NULL); if (ret) { mlog_errno(ret); goto out; } cpos += num_clusters; while (num_clusters) { ret = ocfs2_get_refcount_rec(ref_ci, ref_root_bh, p_cluster, num_clusters, &rec, &index, &ref_leaf_bh); if (ret) { mlog_errno(ret); goto out; } BUG_ON(!rec.r_refcount); rb = (struct ocfs2_refcount_block *)ref_leaf_bh->b_data; /* * We really don't know whether the other clusters is in * this refcount block or not, so just take the worst * case that all the clusters are in this block and each * one will split a refcount rec, so totally we need * clusters * 2 new refcount rec. */ if (le16_to_cpu(rb->rf_records.rl_used) + clusters * 2 > le16_to_cpu(rb->rf_records.rl_count)) ref_blocks++; *credits += 1; brelse(ref_leaf_bh); ref_leaf_bh = NULL; if (num_clusters <= le32_to_cpu(rec.r_clusters)) break; else num_clusters -= le32_to_cpu(rec.r_clusters); p_cluster += num_clusters; } } *meta_add += ref_blocks; if (!ref_blocks) goto out; rb = (struct ocfs2_refcount_block *)ref_root_bh->b_data; if (le32_to_cpu(rb->rf_flags) & OCFS2_REFCOUNT_TREE_FL) *credits += OCFS2_EXPAND_REFCOUNT_TREE_CREDITS; else { struct ocfs2_extent_tree et; ocfs2_init_refcount_extent_tree(&et, ref_ci, ref_root_bh); *credits += ocfs2_calc_extend_credits(inode->i_sb, et.et_root_el); } out: brelse(ref_leaf_bh); return ret; } /* * Do CoW for xattr. */ int ocfs2_refcount_cow_xattr(struct inode *inode, struct ocfs2_dinode *di, struct ocfs2_xattr_value_buf *vb, struct ocfs2_refcount_tree *ref_tree, struct buffer_head *ref_root_bh, u32 cpos, u32 write_len, struct ocfs2_post_refcount *post) { int ret; struct ocfs2_xattr_value_root *xv = vb->vb_xv; struct ocfs2_cow_context *context = NULL; u32 cow_start, cow_len; BUG_ON(!ocfs2_is_refcount_inode(inode)); ret = ocfs2_refcount_cal_cow_clusters(inode, &xv->xr_list, cpos, write_len, UINT_MAX, &cow_start, &cow_len); if (ret) { mlog_errno(ret); goto out; } BUG_ON(cow_len == 0); context = kzalloc(sizeof(struct ocfs2_cow_context), GFP_NOFS); if (!context) { ret = -ENOMEM; mlog_errno(ret); goto out; } context->inode = inode; context->cow_start = cow_start; context->cow_len = cow_len; context->ref_tree = ref_tree; context->ref_root_bh = ref_root_bh; context->cow_object = xv; context->cow_duplicate_clusters = ocfs2_duplicate_clusters_by_jbd; /* We need the extra credits for duplicate_clusters by jbd. */ context->extra_credits = ocfs2_clusters_to_blocks(inode->i_sb, 1) * cow_len; context->get_clusters = ocfs2_xattr_value_get_clusters; context->post_refcount = post; ocfs2_init_xattr_value_extent_tree(&context->data_et, INODE_CACHE(inode), vb); ret = ocfs2_replace_cow(context); if (ret) mlog_errno(ret); out: kfree(context); return ret; } /* * Insert a new extent into refcount tree and mark a extent rec * as refcounted in the dinode tree. */ int ocfs2_add_refcount_flag(struct inode *inode, struct ocfs2_extent_tree *data_et, struct ocfs2_caching_info *ref_ci, struct buffer_head *ref_root_bh, u32 cpos, u32 p_cluster, u32 num_clusters, struct ocfs2_cached_dealloc_ctxt *dealloc, struct ocfs2_post_refcount *post) { int ret; handle_t *handle; int credits = 1, ref_blocks = 0; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_alloc_context *meta_ac = NULL; /* We need to be able to handle at least an extent tree split. */ ref_blocks = ocfs2_extend_meta_needed(data_et->et_root_el); ret = ocfs2_calc_refcount_meta_credits(inode->i_sb, ref_ci, ref_root_bh, p_cluster, num_clusters, &ref_blocks, &credits); if (ret) { mlog_errno(ret); goto out; } trace_ocfs2_add_refcount_flag(ref_blocks, credits); if (ref_blocks) { ret = ocfs2_reserve_new_metadata_blocks(osb, ref_blocks, &meta_ac); if (ret) { mlog_errno(ret); goto out; } } if (post) credits += post->credits; handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto out; } ret = ocfs2_mark_extent_refcounted(inode, data_et, handle, cpos, num_clusters, p_cluster, meta_ac, dealloc); if (ret) { mlog_errno(ret); goto out_commit; } ret = __ocfs2_increase_refcount(handle, ref_ci, ref_root_bh, p_cluster, num_clusters, 0, meta_ac, dealloc); if (ret) { mlog_errno(ret); goto out_commit; } if (post && post->func) { ret = post->func(inode, handle, post->para); if (ret) mlog_errno(ret); } out_commit: ocfs2_commit_trans(osb, handle); out: if (meta_ac) ocfs2_free_alloc_context(meta_ac); return ret; } static int ocfs2_change_ctime(struct inode *inode, struct buffer_head *di_bh) { int ret; handle_t *handle; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; handle = ocfs2_start_trans(OCFS2_SB(inode->i_sb), 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), di_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_commit; } inode_set_ctime_current(inode); di->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode)); di->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode)); ocfs2_journal_dirty(handle, di_bh); out_commit: ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle); out: return ret; } static int ocfs2_attach_refcount_tree(struct inode *inode, struct buffer_head *di_bh) { int ret, data_changed = 0; struct buffer_head *ref_root_bh = NULL; struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_refcount_tree *ref_tree; unsigned int ext_flags; loff_t size; u32 cpos, num_clusters, clusters, p_cluster; struct ocfs2_cached_dealloc_ctxt dealloc; struct ocfs2_extent_tree di_et; ocfs2_init_dealloc_ctxt(&dealloc); if (!ocfs2_is_refcount_inode(inode)) { ret = ocfs2_create_refcount_tree(inode, di_bh); if (ret) { mlog_errno(ret); goto out; } } BUG_ON(!di->i_refcount_loc); ret = ocfs2_lock_refcount_tree(osb, le64_to_cpu(di->i_refcount_loc), 1, &ref_tree, &ref_root_bh); if (ret) { mlog_errno(ret); goto out; } if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL) goto attach_xattr; ocfs2_init_dinode_extent_tree(&di_et, INODE_CACHE(inode), di_bh); size = i_size_read(inode); clusters = ocfs2_clusters_for_bytes(inode->i_sb, size); cpos = 0; while (cpos < clusters) { ret = ocfs2_get_clusters(inode, cpos, &p_cluster, &num_clusters, &ext_flags); if (ret) { mlog_errno(ret); goto unlock; } if (p_cluster && !(ext_flags & OCFS2_EXT_REFCOUNTED)) { ret = ocfs2_add_refcount_flag(inode, &di_et, &ref_tree->rf_ci, ref_root_bh, cpos, p_cluster, num_clusters, &dealloc, NULL); if (ret) { mlog_errno(ret); goto unlock; } data_changed = 1; } cpos += num_clusters; } attach_xattr: if (oi->ip_dyn_features & OCFS2_HAS_XATTR_FL) { ret = ocfs2_xattr_attach_refcount_tree(inode, di_bh, &ref_tree->rf_ci, ref_root_bh, &dealloc); if (ret) { mlog_errno(ret); goto unlock; } } if (data_changed) { ret = ocfs2_change_ctime(inode, di_bh); if (ret) mlog_errno(ret); } unlock: ocfs2_unlock_refcount_tree(osb, ref_tree, 1); brelse(ref_root_bh); if (!ret && ocfs2_dealloc_has_cluster(&dealloc)) { ocfs2_schedule_truncate_log_flush(osb, 1); ocfs2_run_deallocs(osb, &dealloc); } out: /* * Empty the extent map so that we may get the right extent * record from the disk. */ ocfs2_extent_map_trunc(inode, 0); return ret; } static int ocfs2_add_refcounted_extent(struct inode *inode, struct ocfs2_extent_tree *et, struct ocfs2_caching_info *ref_ci, struct buffer_head *ref_root_bh, u32 cpos, u32 p_cluster, u32 num_clusters, unsigned int ext_flags, struct ocfs2_cached_dealloc_ctxt *dealloc) { int ret; handle_t *handle; int credits = 0; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); struct ocfs2_alloc_context *meta_ac = NULL; ret = ocfs2_lock_refcount_allocators(inode->i_sb, p_cluster, num_clusters, et, ref_ci, ref_root_bh, &meta_ac, NULL, &credits); if (ret) { mlog_errno(ret); goto out; } handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); goto out; } ret = ocfs2_insert_extent(handle, et, cpos, ocfs2_clusters_to_blocks(inode->i_sb, p_cluster), num_clusters, ext_flags, meta_ac); if (ret) { mlog_errno(ret); goto out_commit; } ret = ocfs2_increase_refcount(handle, ref_ci, ref_root_bh, p_cluster, num_clusters, meta_ac, dealloc); if (ret) { mlog_errno(ret); goto out_commit; } ret = dquot_alloc_space_nodirty(inode, ocfs2_clusters_to_bytes(osb->sb, num_clusters)); if (ret) mlog_errno(ret); out_commit: ocfs2_commit_trans(osb, handle); out: if (meta_ac) ocfs2_free_alloc_context(meta_ac); return ret; } static int ocfs2_duplicate_inline_data(struct inode *s_inode, struct buffer_head *s_bh, struct inode *t_inode, struct buffer_head *t_bh) { int ret; handle_t *handle; struct ocfs2_super *osb = OCFS2_SB(s_inode->i_sb); struct ocfs2_dinode *s_di = (struct ocfs2_dinode *)s_bh->b_data; struct ocfs2_dinode *t_di = (struct ocfs2_dinode *)t_bh->b_data; BUG_ON(!(OCFS2_I(s_inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)); 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(t_inode), t_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_commit; } t_di->id2.i_data.id_count = s_di->id2.i_data.id_count; memcpy(t_di->id2.i_data.id_data, s_di->id2.i_data.id_data, le16_to_cpu(s_di->id2.i_data.id_count)); spin_lock(&OCFS2_I(t_inode)->ip_lock); OCFS2_I(t_inode)->ip_dyn_features |= OCFS2_INLINE_DATA_FL; t_di->i_dyn_features = cpu_to_le16(OCFS2_I(t_inode)->ip_dyn_features); spin_unlock(&OCFS2_I(t_inode)->ip_lock); ocfs2_journal_dirty(handle, t_bh); out_commit: ocfs2_commit_trans(osb, handle); out: return ret; } static int ocfs2_duplicate_extent_list(struct inode *s_inode, struct inode *t_inode, struct buffer_head *t_bh, struct ocfs2_caching_info *ref_ci, struct buffer_head *ref_root_bh, struct ocfs2_cached_dealloc_ctxt *dealloc) { int ret = 0; u32 p_cluster, num_clusters, clusters, cpos; loff_t size; unsigned int ext_flags; struct ocfs2_extent_tree et; ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(t_inode), t_bh); size = i_size_read(s_inode); clusters = ocfs2_clusters_for_bytes(s_inode->i_sb, size); cpos = 0; while (cpos < clusters) { ret = ocfs2_get_clusters(s_inode, cpos, &p_cluster, &num_clusters, &ext_flags); if (ret) { mlog_errno(ret); goto out; } if (p_cluster) { ret = ocfs2_add_refcounted_extent(t_inode, &et, ref_ci, ref_root_bh, cpos, p_cluster, num_clusters, ext_flags, dealloc); if (ret) { mlog_errno(ret); goto out; } } cpos += num_clusters; } out: return ret; } /* * change the new file's attributes to the src. * * reflink creates a snapshot of a file, that means the attributes * must be identical except for three exceptions - nlink, ino, and ctime. */ static int ocfs2_complete_reflink(struct inode *s_inode, struct buffer_head *s_bh, struct inode *t_inode, struct buffer_head *t_bh, bool preserve) { int ret; handle_t *handle; struct ocfs2_dinode *s_di = (struct ocfs2_dinode *)s_bh->b_data; struct ocfs2_dinode *di = (struct ocfs2_dinode *)t_bh->b_data; loff_t size = i_size_read(s_inode); handle = ocfs2_start_trans(OCFS2_SB(t_inode->i_sb), OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { ret = PTR_ERR(handle); mlog_errno(ret); return ret; } ret = ocfs2_journal_access_di(handle, INODE_CACHE(t_inode), t_bh, OCFS2_JOURNAL_ACCESS_WRITE); if (ret) { mlog_errno(ret); goto out_commit; } spin_lock(&OCFS2_I(t_inode)->ip_lock); OCFS2_I(t_inode)->ip_clusters = OCFS2_I(s_inode)->ip_clusters; OCFS2_I(t_inode)->ip_attr = OCFS2_I(s_inode)->ip_attr; OCFS2_I(t_inode)->ip_dyn_features = OCFS2_I(s_inode)->ip_dyn_features; spin_unlock(&OCFS2_I(t_inode)->ip_lock); i_size_write(t_inode, size); t_inode->i_blocks = s_inode->i_blocks; di->i_xattr_inline_size = s_di->i_xattr_inline_size; di->i_clusters = s_di->i_clusters; di->i_size = s_di->i_size; di->i_dyn_features = s_di->i_dyn_features; di->i_attr = s_di->i_attr; if (preserve) { t_inode->i_uid = s_inode->i_uid; t_inode->i_gid = s_inode->i_gid; t_inode->i_mode = s_inode->i_mode; di->i_uid = s_di->i_uid; di->i_gid = s_di->i_gid; di->i_mode = s_di->i_mode; /* * update time. * we want mtime to appear identical to the source and * update ctime. */ inode_set_ctime_current(t_inode); di->i_ctime = cpu_to_le64(inode_get_ctime_sec(t_inode)); di->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(t_inode)); inode_set_mtime_to_ts(t_inode, inode_get_mtime(s_inode)); di->i_mtime = s_di->i_mtime; di->i_mtime_nsec = s_di->i_mtime_nsec; } ocfs2_journal_dirty(handle, t_bh); out_commit: ocfs2_commit_trans(OCFS2_SB(t_inode->i_sb), handle); return ret; } static int ocfs2_create_reflink_node(struct inode *s_inode, struct buffer_head *s_bh, struct inode *t_inode, struct buffer_head *t_bh, bool preserve) { int ret; struct buffer_head *ref_root_bh = NULL; struct ocfs2_cached_dealloc_ctxt dealloc; struct ocfs2_super *osb = OCFS2_SB(s_inode->i_sb); struct ocfs2_dinode *di = (struct ocfs2_dinode *)s_bh->b_data; struct ocfs2_refcount_tree *ref_tree; ocfs2_init_dealloc_ctxt(&dealloc); ret = ocfs2_set_refcount_tree(t_inode, t_bh, le64_to_cpu(di->i_refcount_loc)); if (ret) { mlog_errno(ret); goto out; } if (OCFS2_I(s_inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) { ret = ocfs2_duplicate_inline_data(s_inode, s_bh, t_inode, t_bh); if (ret) mlog_errno(ret); goto out; } ret = ocfs2_lock_refcount_tree(osb, le64_to_cpu(di->i_refcount_loc), 1, &ref_tree, &ref_root_bh); if (ret) { mlog_errno(ret); goto out; } ret = ocfs2_duplicate_extent_list(s_inode, t_inode, t_bh, &ref_tree->rf_ci, ref_root_bh, &dealloc); if (ret) { mlog_errno(ret); goto out_unlock_refcount; } out_unlock_refcount: ocfs2 |